Merge tag 'kvmarm-6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 6.12

* New features:

  - Add a Stage-2 page table dumper, reusing the main ptdump
    infrastructure, and allowing easier debugging of the our
    page-table infrastructure

  - Add FP8 support to the KVM/arm64 floating point handling.

  - Add NV support for the AT family of instructions, which mostly
    results in adding a page table walker that deals with most of the
    complexity of the architecture.

* Improvements, fixes and cleanups:

  - Add selftest checks for a bunch of timer emulation corner cases

  - Fix the multiple of cases where KVM/arm64 doesn't correctly handle
    the guest trying to use a GICv3 that isn't advertised

  - Remove REG_HIDDEN_USER from the sysreg infrastructure, making
    things little more simple

  - Prevent MTE tags being restored by userspace if we are actively
    logging writes, as that's a recipe for disaster

  - Correct the refcount on a page that is not considered for MTE tag
    copying (such as a device)

  - Relax the synchronisation when walking a page table to split block
    mappings, moving it at the end the walk, as there is no need to
    perform it on every store.

  - Fix boundary check when transfering memory using FFA

  - Fix pKVM TLB invalidation, only affecting currently out of tree
    code but worth addressing for peace of mind

19 files changed, 160 insertions, 37 deletions

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 8c4768c44a01..d3b66d77df7a 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -270,6 +270,18 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst,
 		dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits);
 }
 
+static inline void bitmap_copy_and_extend(unsigned long *to,
+					  const unsigned long *from,
+					  unsigned int count, unsigned int size)
+{
+	unsigned int copy = BITS_TO_LONGS(count);
+
+	memcpy(to, from, copy * sizeof(long));
+	if (count % BITS_PER_LONG)
+		to[copy - 1] &= BITMAP_LAST_WORD_MASK(count);
+	memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long));
+}
+
 /*
  * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64
  * machines the order of hi and lo parts of numbers match the bitmap structure.
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index e85ec73a07d5..b7664d593486 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1296,12 +1296,7 @@ bdev_max_secure_erase_sectors(struct block_device *bdev)
 
 static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return q->limits.max_write_zeroes_sectors;
-
-	return 0;
+	return bdev_get_queue(bdev)->limits.max_write_zeroes_sectors;
 }
 
 static inline bool bdev_nonrot(struct block_device *bdev)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 6503c85b10a3..7b776dae36e5 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -856,8 +856,8 @@ static inline u32 type_flag(u32 type)
 /* only use after check_attach_btf_id() */
 static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog)
 {
-	return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->dst_prog) ?
-		prog->aux->dst_prog->type : prog->type;
+	return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ?
+		prog->aux->saved_dst_prog_type : prog->type;
 }
 
 static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h
index dca2969015d8..6fbfbde68a37 100644
--- a/include/linux/dsa/ocelot.h
+++ b/include/linux/dsa/ocelot.h
@@ -5,6 +5,8 @@
 #ifndef _NET_DSA_TAG_OCELOT_H
 #define _NET_DSA_TAG_OCELOT_H
 
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
 #include <linux/kthread.h>
 #include <linux/packing.h>
 #include <linux/skbuff.h>
@@ -273,4 +275,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb)
 	return rew_op;
 }
 
+/**
+ * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame
+ * @skb: Pointer to socket buffer
+ * @br: Pointer to bridge device that the port is under, if any
+ * @vlan_tci:
+ * @tag_type:
+ *
+ * If the port is under a VLAN-aware bridge, remove the VLAN header from the
+ * payload and move it into the DSA tag, which will make the switch classify
+ * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero,
+ * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not
+ * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()).
+ * Anyway, VID 0 is fine because it is stripped on egress for these port modes,
+ * and source address learning is not performed for packets injected from the
+ * CPU anyway, so it doesn't matter that the VID is "wrong".
+ */
+static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb,
+					     struct net_device *br,
+					     u64 *vlan_tci, u64 *tag_type)
+{
+	struct vlan_ethhdr *hdr;
+	u16 proto, tci;
+
+	if (!br || !br_vlan_enabled(br)) {
+		*vlan_tci = 0;
+		*tag_type = IFH_TAG_TYPE_C;
+		return;
+	}
+
+	hdr = (struct vlan_ethhdr *)skb_mac_header(skb);
+	br_vlan_get_proto(br, &proto);
+
+	if (ntohs(hdr->h_vlan_proto) == proto) {
+		vlan_remove_tag(skb, &tci);
+		*vlan_tci = tci;
+	} else {
+		rcu_read_lock();
+		br_vlan_get_pvid_rcu(br, &tci);
+		rcu_read_unlock();
+		*vlan_tci = tci;
+	}
+
+	*tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C;
+}
+
 #endif
diff --git a/include/linux/file.h b/include/linux/file.h
index 237931f20739..59b146a14dca 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -110,7 +110,7 @@ DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T),
  *
  * f = dentry_open(&path, O_RDONLY, current_cred());
  * if (IS_ERR(f))
- *         return PTR_ERR(fd);
+ *         return PTR_ERR(f);
  *
  * fd_install(fd, f);
  * return take_fd(fd);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index fd34b5755c0b..fb0426f349fc 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2392,6 +2392,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
  *
  * I_PINNING_FSCACHE_WB	Inode is pinning an fscache object for writeback.
  *
+ * I_LRU_ISOLATING	Inode is pinned being isolated from LRU without holding
+ *			i_count.
+ *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
 #define I_DIRTY_SYNC		(1 << 0)
@@ -2415,6 +2418,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
 #define I_DONTCACHE		(1 << 16)
 #define I_SYNC_QUEUED		(1 << 17)
 #define I_PINNING_NETFS_WB	(1 << 18)
+#define __I_LRU_ISOLATING	19
+#define I_LRU_ISOLATING		(1 << __I_LRU_ISOLATING)
 
 #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index c9bf68c239a0..45bf05ad5c53 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -944,10 +944,37 @@ static inline bool htlb_allow_alloc_fallback(int reason)
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
-	if (huge_page_size(h) == PMD_SIZE)
+	const unsigned long size = huge_page_size(h);
+
+	VM_WARN_ON(size == PAGE_SIZE);
+
+	/*
+	 * hugetlb must use the exact same PT locks as core-mm page table
+	 * walkers would. When modifying a PTE table, hugetlb must take the
+	 * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD
+	 * PT lock etc.
+	 *
+	 * The expectation is that any hugetlb folio smaller than a PMD is
+	 * always mapped into a single PTE table and that any hugetlb folio
+	 * smaller than a PUD (but at least as big as a PMD) is always mapped
+	 * into a single PMD table.
+	 *
+	 * If that does not hold for an architecture, then that architecture
+	 * must disable split PT locks such that all *_lockptr() functions
+	 * will give us the same result: the per-MM PT lock.
+	 *
+	 * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where
+	 * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr()
+	 * and core-mm would use pmd_lockptr(). However, in such configurations
+	 * split PMD locks are disabled -- they don't make sense on a single
+	 * PGDIR page table -- and the end result is the same.
+	 */
+	if (size >= PUD_SIZE)
+		return pud_lockptr(mm, (pud_t *) pte);
+	else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE))
 		return pmd_lockptr(mm, (pmd_t *) pte);
-	VM_BUG_ON(huge_page_size(h) == PAGE_SIZE);
-	return &mm->page_table_lock;
+	/* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */
+	return ptep_lockptr(mm, pte);
 }
 
 #ifndef hugepages_supported
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 7eedd0c662da..377def497298 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -1066,7 +1066,7 @@ static inline int of_i2c_get_board_info(struct device *dev,
 struct acpi_resource;
 struct acpi_resource_i2c_serialbus;
 
-#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_I2C)
+#if IS_REACHABLE(CONFIG_ACPI) && IS_REACHABLE(CONFIG_I2C)
 bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares,
 			       struct acpi_resource_i2c_serialbus **i2c);
 int i2c_acpi_client_count(struct acpi_device *adev);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 4d47f2c33311..04cbdae0052e 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -795,8 +795,6 @@ extern int iommu_attach_device(struct iommu_domain *domain,
 			       struct device *dev);
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
-extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-				   struct device *dev, ioasid_t pasid);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 79a6b1a63027..b23c6d48392f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -715,6 +715,13 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
 }
 #endif
 
+#ifndef kvm_arch_has_readonly_mem
+static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm)
+{
+	return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM);
+}
+#endif
+
 struct kvm_memslots {
 	u64 generation;
 	atomic_long_t last_used_slot;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c4b238a20b76..6549d0979b28 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2920,6 +2920,13 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
 	return ptlock_ptr(page_ptdesc(pmd_page(*pmd)));
 }
 
+static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte)
+{
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE));
+	BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE);
+	return ptlock_ptr(virt_to_ptdesc(pte));
+}
+
 static inline bool ptlock_init(struct ptdesc *ptdesc)
 {
 	/*
@@ -2944,6 +2951,10 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
 	return &mm->page_table_lock;
 }
+static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte)
+{
+	return &mm->page_table_lock;
+}
 static inline void ptlock_cache_init(void) {}
 static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; }
 static inline void ptlock_free(struct ptdesc *ptdesc) {}
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 41458892bc8a..1dc6248feb83 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -220,8 +220,6 @@ enum node_stat_item {
 	PGDEMOTE_KSWAPD,
 	PGDEMOTE_DIRECT,
 	PGDEMOTE_KHUGEPAGED,
-	NR_MEMMAP, /* page metadata allocated through buddy allocator */
-	NR_MEMMAP_BOOT, /* page metadata allocated through boot allocator */
 	NR_VM_NODE_STAT_ITEMS
 };
 
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 5d0288938cc2..983816608f15 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -73,8 +73,6 @@ struct netfs_inode {
 #define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
 #define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
 #define NETFS_ICTX_WRITETHROUGH	2		/* Write-through caching */
-#define NETFS_ICTX_USE_PGPRIV2	31		/* [DEPRECATED] Use PG_private_2 to mark
-						 * write to cache on read */
 };
 
 /*
@@ -269,7 +267,6 @@ struct netfs_io_request {
 #define NETFS_RREQ_DONT_UNLOCK_FOLIOS	3	/* Don't unlock the folios on completion */
 #define NETFS_RREQ_FAILED		4	/* The request failed */
 #define NETFS_RREQ_IN_PROGRESS		5	/* Unlocked when the request completes */
-#define NETFS_RREQ_WRITE_TO_CACHE	7	/* Need to write to the cache */
 #define NETFS_RREQ_UPLOAD_TO_SERVER	8	/* Need to write to the server */
 #define NETFS_RREQ_NONBLOCK		9	/* Don't block if possible (O_NONBLOCK) */
 #define NETFS_RREQ_BLOCKED		10	/* We blocked */
diff --git a/include/linux/panic.h b/include/linux/panic.h
index 3130e0b5116b..54d90b6c5f47 100644
--- a/include/linux/panic.h
+++ b/include/linux/panic.h
@@ -16,6 +16,7 @@ extern void oops_enter(void);
 extern void oops_exit(void);
 extern bool oops_may_print(void);
 
+extern bool panic_triggering_all_cpu_backtrace;
 extern int panic_timeout;
 extern unsigned long panic_print;
 extern int panic_on_oops;
diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h
index 18cd0c0c73d9..207f0c83c8e9 100644
--- a/include/linux/pgalloc_tag.h
+++ b/include/linux/pgalloc_tag.h
@@ -43,6 +43,18 @@ static inline void put_page_tag_ref(union codetag_ref *ref)
 	page_ext_put(page_ext_from_codetag_ref(ref));
 }
 
+static inline void clear_page_tag_ref(struct page *page)
+{
+	if (mem_alloc_profiling_enabled()) {
+		union codetag_ref *ref = get_page_tag_ref(page);
+
+		if (ref) {
+			set_codetag_empty(ref);
+			put_page_tag_ref(ref);
+		}
+	}
+}
+
 static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
 				   unsigned int nr)
 {
@@ -126,6 +138,7 @@ static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr)
 
 static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; }
 static inline void put_page_tag_ref(union codetag_ref *ref) {}
+static inline void clear_page_tag_ref(struct page *page) {}
 static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
 				   unsigned int nr) {}
 static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {}
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index 59b3b752394d..35f039ecb272 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -266,12 +266,12 @@ bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
 	if (oldp)
 		*oldp = old;
 
-	if (old == i) {
+	if (old > 0 && old == i) {
 		smp_acquire__after_ctrl_dep();
 		return true;
 	}
 
-	if (unlikely(old < 0 || old - i < 0))
+	if (unlikely(old <= 0 || old - i < 0))
 		refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
 
 	return false;
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index e4f3f3d30a03..d47d5f14ff99 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -902,12 +902,29 @@ extern int devm_spi_register_controller(struct device *dev,
 					struct spi_controller *ctlr);
 extern void spi_unregister_controller(struct spi_controller *ctlr);
 
-#if IS_ENABLED(CONFIG_ACPI)
+#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SPI_MASTER)
 extern struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev);
 extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr,
 						struct acpi_device *adev,
 						int index);
 int acpi_spi_count_resources(struct acpi_device *adev);
+#else
+static inline struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev)
+{
+	return NULL;
+}
+
+static inline struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr,
+						       struct acpi_device *adev,
+						       int index)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+static inline int acpi_spi_count_resources(struct acpi_device *adev)
+{
+	return 0;
+}
 #endif
 
 /*
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 25fbf960b474..b86ddca46b9e 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -55,6 +55,7 @@ enum thermal_notify_event {
 	THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */
 	THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */
 	THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */
+	THERMAL_TZ_RESUME, /* Thermal zone is resuming after system sleep */
 };
 
 /**
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 23cd17942036..9eb77c9007e6 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -34,10 +34,13 @@ struct reclaim_stat {
 	unsigned nr_lazyfree_fail;
 };
 
-enum writeback_stat_item {
+/* Stat data for system wide items */
+enum vm_stat_item {
 	NR_DIRTY_THRESHOLD,
 	NR_DIRTY_BG_THRESHOLD,
-	NR_VM_WRITEBACK_STAT_ITEMS,
+	NR_MEMMAP_PAGES,	/* page metadata allocated through buddy allocator */
+	NR_MEMMAP_BOOT_PAGES,	/* page metadata allocated through boot allocator */
+	NR_VM_STAT_ITEMS,
 };
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
@@ -514,21 +517,13 @@ static inline const char *lru_list_name(enum lru_list lru)
 	return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
 }
 
-static inline const char *writeback_stat_name(enum writeback_stat_item item)
-{
-	return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
-			   NR_VM_NUMA_EVENT_ITEMS +
-			   NR_VM_NODE_STAT_ITEMS +
-			   item];
-}
-
 #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG)
 static inline const char *vm_event_name(enum vm_event_item item)
 {
 	return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
 			   NR_VM_NUMA_EVENT_ITEMS +
 			   NR_VM_NODE_STAT_ITEMS +
-			   NR_VM_WRITEBACK_STAT_ITEMS +
+			   NR_VM_STAT_ITEMS +
 			   item];
 }
 #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */
@@ -625,7 +620,6 @@ static inline void lruvec_stat_sub_folio(struct folio *folio,
 	lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio));
 }
 
-void __meminit mod_node_early_perpage_metadata(int nid, long delta);
-void __meminit store_early_perpage_metadata(void);
-
+void memmap_boot_pages_add(long delta);
+void memmap_pages_add(long delta);
 #endif /* _LINUX_VMSTAT_H */