Merge tag 'kvm-riscv-6.18-1' of https://github.com/kvm-riscv/linux into HEAD

KVM/riscv changes for 6.18

- Added SBI FWFT extension for Guest/VM with misaligned
  delegation and pointer masking PMLEN features
- Added ONE_REG interface for SBI FWFT extension
- Added Zicbop and bfloat16 extensions for Guest/VM
- Enabled more common KVM selftests for RISC-V such as
  access_tracking_perf_test, dirty_log_perf_test,
  memslot_modification_stress_test, memslot_perf_test,
  mmu_stress_test, and rseq_test
- Added SBI v3.0 PMU enhancements in KVM and perf driver

10 files changed, 82 insertions, 33 deletions

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 1b10a5d84b68..39fe3e6cd282 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -460,7 +460,8 @@ bool kexec_load_permitted(int kexec_image_type);
 
 /* List of defined/legal kexec file flags */
 #define KEXEC_FILE_FLAGS	(KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \
-				 KEXEC_FILE_NO_INITRAMFS | KEXEC_FILE_DEBUG)
+				 KEXEC_FILE_NO_INITRAMFS | KEXEC_FILE_DEBUG | \
+				 KEXEC_FILE_NO_CMA)
 
 /* flag to track if kexec reboot is in progress */
 extern bool kexec_in_progress;
diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h
index 701974639ff2..f82a28040594 100644
--- a/include/linux/perf/riscv_pmu.h
+++ b/include/linux/perf/riscv_pmu.h
@@ -89,6 +89,7 @@ static inline void riscv_pmu_legacy_skip_init(void) {};
 struct riscv_pmu *riscv_pmu_alloc(void);
 #ifdef CONFIG_RISCV_PMU_SBI
 int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr);
+int riscv_pmu_get_event_info(u32 type, u64 config, u64 *econfig);
 #endif
 
 #endif /* CONFIG_RISCV_PMU */
diff --git a/include/linux/pgalloc.h b/include/linux/pgalloc.h
new file mode 100644
index 000000000000..9174fa59bbc5
--- /dev/null
+++ b/include/linux/pgalloc.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PGALLOC_H
+#define _LINUX_PGALLOC_H
+
+#include <linux/pgtable.h>
+#include <asm/pgalloc.h>
+
+/*
+ * {pgd,p4d}_populate_kernel() are defined as macros to allow
+ * compile-time optimization based on the configured page table levels.
+ * Without this, linking may fail because callers (e.g., KASAN) may rely
+ * on calls to these functions being optimized away when passing symbols
+ * that exist only for certain page table levels.
+ */
+#define pgd_populate_kernel(addr, pgd, p4d)				\
+	do {								\
+		pgd_populate(&init_mm, pgd, p4d);			\
+		if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_PGD_MODIFIED)	\
+			arch_sync_kernel_mappings(addr, addr);		\
+	} while (0)
+
+#define p4d_populate_kernel(addr, p4d, pud)				\
+	do {								\
+		p4d_populate(&init_mm, p4d, pud);			\
+		if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_P4D_MODIFIED)	\
+			arch_sync_kernel_mappings(addr, addr);		\
+	} while (0)
+
+#endif /* _LINUX_PGALLOC_H */
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 4c035637eeb7..2b80fd456c8b 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1467,6 +1467,22 @@ static inline void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned
 }
 #endif
 
+/*
+ * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values
+ * and let generic vmalloc, ioremap and page table update code know when
+ * arch_sync_kernel_mappings() needs to be called.
+ */
+#ifndef ARCH_PAGE_TABLE_SYNC_MASK
+#define ARCH_PAGE_TABLE_SYNC_MASK 0
+#endif
+
+/*
+ * There is no default implementation for arch_sync_kernel_mappings(). It is
+ * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK
+ * is 0.
+ */
+void arch_sync_kernel_mappings(unsigned long start, unsigned long end);
+
 #endif /* CONFIG_MMU */
 
 /*
@@ -1938,10 +1954,11 @@ static inline bool arch_has_pfn_modify_check(void)
 /*
  * Page Table Modification bits for pgtbl_mod_mask.
  *
- * These are used by the p?d_alloc_track*() set of functions an in the generic
- * vmalloc/ioremap code to track at which page-table levels entries have been
- * modified. Based on that the code can better decide when vmalloc and ioremap
- * mapping changes need to be synchronized to other page-tables in the system.
+ * These are used by the p?d_alloc_track*() and p*d_populate_kernel()
+ * functions in the generic vmalloc, ioremap and page table update code
+ * to track at which page-table levels entries have been modified.
+ * Based on that the code can better decide when page table changes need
+ * to be synchronized to other page-tables in the system.
  */
 #define		__PGTBL_PGD_MODIFIED	0
 #define		__PGTBL_P4D_MODIFIED	1
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 4c2b8b6e7187..bb45787d8684 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -169,6 +169,11 @@ static inline bool phy_interface_empty(const unsigned long *intf)
 	return bitmap_empty(intf, PHY_INTERFACE_MODE_MAX);
 }
 
+static inline unsigned int phy_interface_weight(const unsigned long *intf)
+{
+	return bitmap_weight(intf, PHY_INTERFACE_MODE_MAX);
+}
+
 static inline void phy_interface_and(unsigned long *dst, const unsigned long *a,
 				     const unsigned long *b)
 {
diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index c27aac67cb3f..b8ae89ea28ab 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -76,6 +76,7 @@ struct tk_read_base {
  * @cs_was_changed_seq:		The sequence number of clocksource change events
  * @clock_valid:		Indicator for valid clock
  * @monotonic_to_boot:		CLOCK_MONOTONIC to CLOCK_BOOTTIME offset
+ * @monotonic_to_aux:		CLOCK_MONOTONIC to CLOCK_AUX offset
  * @cycle_interval:		Number of clock cycles in one NTP interval
  * @xtime_interval:		Number of clock shifted nano seconds in one NTP
  *				interval.
@@ -117,6 +118,9 @@ struct tk_read_base {
  * @offs_aux is used by the auxiliary timekeepers which do not utilize any
  * of the regular timekeeper offset fields.
  *
+ * @monotonic_to_aux is a timespec64 representation of @offs_aux to
+ * accelerate the VDSO update for CLOCK_AUX.
+ *
  * The cacheline ordering of the structure is optimized for in kernel usage of
  * the ktime_get() and ktime_get_ts64() family of time accessors. Struct
  * timekeeper is prepended in the core timekeeping code with a sequence count,
@@ -159,7 +163,10 @@ struct timekeeper {
 	u8			cs_was_changed_seq;
 	u8			clock_valid;
 
-	struct timespec64	monotonic_to_boot;
+	union {
+		struct timespec64	monotonic_to_boot;
+		struct timespec64	monotonic_to_aux;
+	};
 
 	u64			cycle_interval;
 	u64			xtime_interval;
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index fdc9aeb74a44..2759dac6be44 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -220,22 +220,6 @@ int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot,
 		     struct page **pages, unsigned int page_shift);
 
 /*
- * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values
- * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings()
- * needs to be called.
- */
-#ifndef ARCH_PAGE_TABLE_SYNC_MASK
-#define ARCH_PAGE_TABLE_SYNC_MASK 0
-#endif
-
-/*
- * There is no default implementation for arch_sync_kernel_mappings(). It is
- * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK
- * is 0.
- */
-void arch_sync_kernel_mappings(unsigned long start, unsigned long end);
-
-/*
  *	Lowlevel-APIs (not for driver use!)
  */
 
diff --git a/include/net/sock.h b/include/net/sock.h
index c8a4b283df6f..fb13322a11fc 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -285,6 +285,7 @@ struct sk_filter;
   *	@sk_ack_backlog: current listen backlog
   *	@sk_max_ack_backlog: listen backlog set in listen()
   *	@sk_uid: user id of owner
+  *	@sk_ino: inode number (zero if orphaned)
   *	@sk_prefer_busy_poll: prefer busypolling over softirq processing
   *	@sk_busy_poll_budget: napi processing budget when busypolling
   *	@sk_priority: %SO_PRIORITY setting
@@ -518,6 +519,7 @@ struct sock {
 	u32			sk_ack_backlog;
 	u32			sk_max_ack_backlog;
 	kuid_t			sk_uid;
+	unsigned long		sk_ino;
 	spinlock_t		sk_peer_lock;
 	int			sk_bind_phc;
 	struct pid		*sk_peer_pid;
@@ -2056,6 +2058,10 @@ static inline int sk_rx_queue_get(const struct sock *sk)
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
 	sk->sk_socket = sock;
+	if (sock) {
+		WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid);
+		WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino);
+	}
 }
 
 static inline wait_queue_head_t *sk_sleep(struct sock *sk)
@@ -2077,6 +2083,7 @@ static inline void sock_orphan(struct sock *sk)
 	sk_set_socket(sk, NULL);
 	sk->sk_wq  = NULL;
 	/* Note: sk_uid is unchanged. */
+	WRITE_ONCE(sk->sk_ino, 0);
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
@@ -2087,20 +2094,22 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 	rcu_assign_pointer(sk->sk_wq, &parent->wq);
 	parent->sk = sk;
 	sk_set_socket(sk, parent);
-	WRITE_ONCE(sk->sk_uid, SOCK_INODE(parent)->i_uid);
 	security_sock_graft(sk, parent);
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
+static inline unsigned long sock_i_ino(const struct sock *sk)
+{
+	/* Paired with WRITE_ONCE() in sock_graft() and sock_orphan() */
+	return READ_ONCE(sk->sk_ino);
+}
+
 static inline kuid_t sk_uid(const struct sock *sk)
 {
 	/* Paired with WRITE_ONCE() in sockfs_setattr() */
 	return READ_ONCE(sk->sk_uid);
 }
 
-unsigned long __sock_i_ino(struct sock *sk);
-unsigned long sock_i_ino(struct sock *sk);
-
 static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk)
 {
 	return sk ? sk_uid(sk) : make_kuid(net->user_ns, 0);
diff --git a/include/pcmcia/ss.h b/include/pcmcia/ss.h
index 7cf7dbbfa131..89aed99bfeae 100644
--- a/include/pcmcia/ss.h
+++ b/include/pcmcia/ss.h
@@ -227,12 +227,8 @@ struct pcmcia_socket {
 
 
 /* socket drivers must define the resource operations type they use. There
- * are three options:
+ * are two options:
  * - pccard_static_ops		iomem and ioport areas are assigned statically
- * - pccard_iodyn_ops		iomem areas is assigned statically, ioport
- *				areas dynamically
- *				If this option is selected, use
- *				"select PCCARD_IODYN" in Kconfig.
  * - pccard_nonstatic_ops	iomem and ioport areas are assigned dynamically.
  *				If this option is selected, use
  *				"select PCCARD_NONSTATIC" in Kconfig.
@@ -240,13 +236,11 @@ struct pcmcia_socket {
  */
 extern struct pccard_resource_ops pccard_static_ops;
 #if defined(CONFIG_PCMCIA) || defined(CONFIG_PCMCIA_MODULE)
-extern struct pccard_resource_ops pccard_iodyn_ops;
 extern struct pccard_resource_ops pccard_nonstatic_ops;
 #else
 /* If PCMCIA is not used, but only CARDBUS, these functions are not used
  * at all. Therefore, do not use the large (240K!) rsrc_nonstatic module
  */
-#define pccard_iodyn_ops pccard_static_ops
 #define pccard_nonstatic_ops pccard_static_ops
 #endif
 
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 2beb30be2c5f..8e0eb832bc01 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1784,10 +1784,12 @@ enum nft_synproxy_attributes {
  * enum nft_device_attributes - nf_tables device netlink attributes
  *
  * @NFTA_DEVICE_NAME: name of this device (NLA_STRING)
+ * @NFTA_DEVICE_PREFIX: device name prefix, a simple wildcard (NLA_STRING)
  */
 enum nft_devices_attributes {
 	NFTA_DEVICE_UNSPEC,
 	NFTA_DEVICE_NAME,
+	NFTA_DEVICE_PREFIX,
 	__NFTA_DEVICE_MAX
 };
 #define NFTA_DEVICE_MAX		(__NFTA_DEVICE_MAX - 1)