Merge branch 'x86/cpu' into x86/asm, to pick up dependent commits

Signed-off-by: Ingo Molnar <mingo@kernel.org>

21 files changed, 143 insertions, 57 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 248416ecd01c..d37751789bf5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -196,10 +196,11 @@ struct gendisk {
 	unsigned int		zone_capacity;
 	unsigned int		last_zone_capacity;
 	unsigned long __rcu	*conv_zones_bitmap;
-	unsigned int            zone_wplugs_hash_bits;
-	spinlock_t              zone_wplugs_lock;
+	unsigned int		zone_wplugs_hash_bits;
+	atomic_t		nr_zone_wplugs;
+	spinlock_t		zone_wplugs_lock;
 	struct mempool_s	*zone_wplugs_pool;
-	struct hlist_head       *zone_wplugs_hash;
+	struct hlist_head	*zone_wplugs_hash;
 	struct workqueue_struct *zone_wplugs_wq;
 #endif /* CONFIG_BLK_DEV_ZONED */
 
@@ -367,6 +368,7 @@ struct queue_limits {
 	unsigned int		max_sectors;
 	unsigned int		max_user_sectors;
 	unsigned int		max_segment_size;
+	unsigned int		min_segment_size;
 	unsigned int		physical_block_size;
 	unsigned int		logical_block_size;
 	unsigned int		alignment_offset;
diff --git a/include/linux/call_once.h b/include/linux/call_once.h
index 6261aa0b3fb0..13cd6469e7e5 100644
--- a/include/linux/call_once.h
+++ b/include/linux/call_once.h
@@ -26,20 +26,41 @@ do {									\
 	__once_init((once), #once, &__key);				\
 } while (0)
 
-static inline void call_once(struct once *once, void (*cb)(struct once *))
+/*
+ * call_once - Ensure a function has been called exactly once
+ *
+ * @once: Tracking struct
+ * @cb: Function to be called
+ *
+ * If @once has never completed successfully before, call @cb and, if
+ * it returns a zero or positive value, mark @once as completed.  Return
+ * the value returned by @cb
+ *
+ * If @once has completed succesfully before, return 0.
+ *
+ * The call to @cb is implicitly surrounded by a mutex, though for
+ * efficiency the * function avoids taking it after the first call.
+ */
+static inline int call_once(struct once *once, int (*cb)(struct once *))
 {
-        /* Pairs with atomic_set_release() below.  */
-        if (atomic_read_acquire(&once->state) == ONCE_COMPLETED)
-                return;
-
-        guard(mutex)(&once->lock);
-        WARN_ON(atomic_read(&once->state) == ONCE_RUNNING);
-        if (atomic_read(&once->state) != ONCE_NOT_STARTED)
-                return;
-
-        atomic_set(&once->state, ONCE_RUNNING);
-        cb(once);
-        atomic_set_release(&once->state, ONCE_COMPLETED);
+	int r, state;
+
+	/* Pairs with atomic_set_release() below.  */
+	if (atomic_read_acquire(&once->state) == ONCE_COMPLETED)
+		return 0;
+
+	guard(mutex)(&once->lock);
+	state = atomic_read(&once->state);
+	if (unlikely(state != ONCE_NOT_STARTED))
+		return WARN_ON_ONCE(state != ONCE_COMPLETED) ? -EINVAL : 0;
+
+	atomic_set(&once->state, ONCE_RUNNING);
+	r = cb(once);
+	if (r < 0)
+		atomic_set(&once->state, ONCE_NOT_STARTED);
+	else
+		atomic_set_release(&once->state, ONCE_COMPLETED);
+	return r;
 }
 
 #endif /* _LINUX_CALL_ONCE_H */
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 200fd3c5bc70..155385754824 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -110,7 +110,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 /* Unreachable code */
 #ifdef CONFIG_OBJTOOL
 /* Annotate a C jump table to allow objtool to follow the code flow */
-#define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #")
+#define __annotate_jump_table __section(".data.rel.ro.c_jump_table")
 #else /* !CONFIG_OBJTOOL */
 #define __annotate_jump_table
 #endif /* CONFIG_OBJTOOL */
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index 64130ae19690..65655a5d1be2 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -65,6 +65,37 @@ enum execmem_range_flags {
  * Architectures that use EXECMEM_ROX_CACHE must implement this.
  */
 void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable);
+
+/**
+ * execmem_make_temp_rw - temporarily remap region with read-write
+ *			  permissions
+ * @ptr:	address of the region to remap
+ * @size:	size of the region to remap
+ *
+ * Remaps a part of the cached large page in the ROX cache in the range
+ * [@ptr, @ptr + @size) as writable and not executable. The caller must
+ * have exclusive ownership of this range and ensure nothing will try to
+ * execute code in this range.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int execmem_make_temp_rw(void *ptr, size_t size);
+
+/**
+ * execmem_restore_rox - restore read-only-execute permissions
+ * @ptr:	address of the region to remap
+ * @size:	size of the region to remap
+ *
+ * Restores read-only-execute permissions on a range [@ptr, @ptr + @size)
+ * after it was temporarily remapped as writable. Relies on architecture
+ * implementation of set_memory_rox() to restore mapping using large pages.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int execmem_restore_rox(void *ptr, size_t size);
+#else
+static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; }
+static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
 #endif
 
 /**
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2c3b2f8a621f..2788df98080f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2975,8 +2975,8 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
 	} else if (iocb->ki_flags & IOCB_DONTCACHE) {
 		struct address_space *mapping = iocb->ki_filp->f_mapping;
 
-		filemap_fdatawrite_range_kick(mapping, iocb->ki_pos,
-					      iocb->ki_pos + count);
+		filemap_fdatawrite_range_kick(mapping, iocb->ki_pos - count,
+					      iocb->ki_pos - 1);
 	}
 
 	return count;
@@ -3452,6 +3452,8 @@ extern const struct file_operations generic_ro_fops;
 
 extern int readlink_copy(char __user *, int, const char *, int);
 extern int page_readlink(struct dentry *, char __user *, int);
+extern const char *page_get_link_raw(struct dentry *, struct inode *,
+				     struct delayed_call *);
 extern const char *page_get_link(struct dentry *, struct inode *,
 				 struct delayed_call *);
 extern void page_put_link(void *);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ec8c0ccc8f95..bf5f7256bd28 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -1004,7 +1004,9 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
 static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
 						unsigned long addr, pte_t *ptep)
 {
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 #endif
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6b27db7f9496..0234f14f2aa6 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -875,10 +875,11 @@ struct mm_struct {
 		 */
 		unsigned int nr_cpus_allowed;
 		/**
-		 * @max_nr_cid: Maximum number of concurrency IDs allocated.
+		 * @max_nr_cid: Maximum number of allowed concurrency
+		 *              IDs allocated.
 		 *
-		 * Track the highest number of concurrency IDs allocated for the
-		 * mm.
+		 * Track the highest number of allowed concurrency IDs
+		 * allocated for the mm.
 		 */
 		atomic_t max_nr_cid;
 		/**
diff --git a/include/linux/module.h b/include/linux/module.h
index 30e5b19bafa9..9937e71a3b5b 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -370,7 +370,6 @@ enum mod_mem_type {
 
 struct module_memory {
 	void *base;
-	void *rw_copy;
 	bool is_rox;
 	unsigned int size;
 
@@ -772,16 +771,6 @@ static inline bool is_livepatch_module(struct module *mod)
 
 void set_module_sig_enforced(void);
 
-void *__module_writable_address(struct module *mod, void *loc);
-
-static inline void *module_writable_address(struct module *mod, void *loc)
-{
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod ||
-	    mod->state != MODULE_STATE_UNFORMED)
-		return loc;
-	return __module_writable_address(mod, loc);
-}
-
 #else /* !CONFIG_MODULES... */
 
 static inline struct module *__module_address(unsigned long addr)
@@ -889,11 +878,6 @@ static inline bool module_is_coming(struct module *mod)
 {
 	return false;
 }
-
-static inline void *module_writable_address(struct module *mod, void *loc)
-{
-	return loc;
-}
 #endif /* CONFIG_MODULES */
 
 #ifdef CONFIG_SYSFS
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index 1f5507ba5a12..e395461d59e5 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -108,10 +108,6 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *mod);
 
-int module_post_finalize(const Elf_Ehdr *hdr,
-			 const Elf_Shdr *sechdrs,
-			 struct module *mod);
-
 #ifdef CONFIG_MODULES
 void flush_module_init_free_work(void);
 #else
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c0a86afb85da..ab550a89b9bf 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3275,6 +3275,8 @@ static inline struct net_device *first_net_device_rcu(struct net *net)
 }
 
 int netdev_boot_setup_check(struct net_device *dev);
+struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type,
+				   const char *hwaddr);
 struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
 				       const char *hwaddr);
 struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
@@ -4115,7 +4117,6 @@ void netif_receive_skb_list(struct list_head *head);
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
 void napi_gro_flush(struct napi_struct *napi, bool flush_old);
 struct sk_buff *napi_get_frags(struct napi_struct *napi);
-void napi_get_frags_check(struct napi_struct *napi);
 gro_result_t napi_gro_frags(struct napi_struct *napi);
 
 static inline void napi_free_frags(struct napi_struct *napi)
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 071d05d81d38..c86a11cfc4a3 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -278,7 +278,7 @@ struct netfs_io_request {
 #define NETFS_RREQ_PAUSE		11	/* Pause subrequest generation */
 #define NETFS_RREQ_USE_IO_ITER		12	/* Use ->io_iter rather than ->i_pages */
 #define NETFS_RREQ_ALL_QUEUED		13	/* All subreqs are now queued */
-#define NETFS_RREQ_NEED_RETRY		14	/* Need to try retrying */
+#define NETFS_RREQ_RETRYING		14	/* Set if we're in the retry path */
 #define NETFS_RREQ_USE_PGPRIV2		31	/* [DEPRECATED] Use PG_private_2 to mark
 						 * write to cache on read */
 	const struct netfs_request_ops *netfs_ops;
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 71fbebfa43c7..9ac83ca88326 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -47,6 +47,7 @@ struct nfs4_acl {
 struct nfs4_label {
 	uint32_t	lfs;
 	uint32_t	pi;
+	u32		lsmid;
 	u32		len;
 	char	*label;
 };
diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h
index e07e8978d691..e435250fcb4d 100644
--- a/include/linux/nvme-tcp.h
+++ b/include/linux/nvme-tcp.h
@@ -13,6 +13,8 @@
 #define NVME_TCP_ADMIN_CCSZ	SZ_8K
 #define NVME_TCP_DIGEST_LENGTH	4
 #define NVME_TCP_MIN_MAXH2CDATA 4096
+#define NVME_TCP_MIN_C2HTERM_PLEN	24
+#define NVME_TCP_MAX_C2HTERM_PLEN	152
 
 enum nvme_tcp_pfv {
 	NVME_TCP_PFV_1_0 = 0x0,
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index fe3b60818fdc..2dc05b1c3283 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -199,28 +199,54 @@ enum {
 #define NVME_NVM_IOSQES		6
 #define NVME_NVM_IOCQES		4
 
+/*
+ * Controller Configuration (CC) register (Offset 14h)
+ */
 enum {
+	/* Enable (EN): bit 0 */
 	NVME_CC_ENABLE		= 1 << 0,
 	NVME_CC_EN_SHIFT	= 0,
+
+	/* Bits 03:01 are reserved (NVMe Base Specification rev 2.1) */
+
+	/* I/O Command Set Selected (CSS): bits 06:04 */
 	NVME_CC_CSS_SHIFT	= 4,
-	NVME_CC_MPS_SHIFT	= 7,
-	NVME_CC_AMS_SHIFT	= 11,
-	NVME_CC_SHN_SHIFT	= 14,
-	NVME_CC_IOSQES_SHIFT	= 16,
-	NVME_CC_IOCQES_SHIFT	= 20,
+	NVME_CC_CSS_MASK	= 7 << NVME_CC_CSS_SHIFT,
 	NVME_CC_CSS_NVM		= 0 << NVME_CC_CSS_SHIFT,
 	NVME_CC_CSS_CSI		= 6 << NVME_CC_CSS_SHIFT,
-	NVME_CC_CSS_MASK	= 7 << NVME_CC_CSS_SHIFT,
+
+	/* Memory Page Size (MPS): bits 10:07 */
+	NVME_CC_MPS_SHIFT	= 7,
+	NVME_CC_MPS_MASK	= 0xf << NVME_CC_MPS_SHIFT,
+
+	/* Arbitration Mechanism Selected (AMS): bits 13:11 */
+	NVME_CC_AMS_SHIFT	= 11,
+	NVME_CC_AMS_MASK	= 7 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_RR		= 0 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_WRRU	= 1 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_VS		= 7 << NVME_CC_AMS_SHIFT,
+
+	/* Shutdown Notification (SHN): bits 15:14 */
+	NVME_CC_SHN_SHIFT	= 14,
+	NVME_CC_SHN_MASK	= 3 << NVME_CC_SHN_SHIFT,
 	NVME_CC_SHN_NONE	= 0 << NVME_CC_SHN_SHIFT,
 	NVME_CC_SHN_NORMAL	= 1 << NVME_CC_SHN_SHIFT,
 	NVME_CC_SHN_ABRUPT	= 2 << NVME_CC_SHN_SHIFT,
-	NVME_CC_SHN_MASK	= 3 << NVME_CC_SHN_SHIFT,
+
+	/* I/O Submission Queue Entry Size (IOSQES): bits 19:16 */
+	NVME_CC_IOSQES_SHIFT	= 16,
+	NVME_CC_IOSQES_MASK	= 0xf << NVME_CC_IOSQES_SHIFT,
 	NVME_CC_IOSQES		= NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT,
+
+	/* I/O Completion Queue Entry Size (IOCQES): bits 23:20 */
+	NVME_CC_IOCQES_SHIFT	= 20,
+	NVME_CC_IOCQES_MASK	= 0xf << NVME_CC_IOCQES_SHIFT,
 	NVME_CC_IOCQES		= NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT,
+
+	/* Controller Ready Independent of Media Enable (CRIME): bit 24 */
 	NVME_CC_CRIME		= 1 << 24,
+
+	/* Bits 25:31 are reserved (NVMe Base Specification rev 2.1) */
 };
 
 enum {
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index de5deb1a0118..1a2594a38199 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -3134,6 +3134,7 @@
 #define PCI_DEVICE_ID_INTEL_HDA_LNL_P	0xa828
 #define PCI_DEVICE_ID_INTEL_S21152BB	0xb152
 #define PCI_DEVICE_ID_INTEL_HDA_BMG	0xe2f7
+#define PCI_DEVICE_ID_INTEL_HDA_PTL_H	0xe328
 #define PCI_DEVICE_ID_INTEL_HDA_PTL	0xe428
 #define PCI_DEVICE_ID_INTEL_HDA_CML_R	0xf0c8
 #define PCI_DEVICE_ID_INTEL_HDA_RKL_S	0xf1c8
diff --git a/include/linux/rcuref.h b/include/linux/rcuref.h
index 2c8bfd0f1b6b..6322d8c1c6b4 100644
--- a/include/linux/rcuref.h
+++ b/include/linux/rcuref.h
@@ -71,27 +71,30 @@ static inline __must_check bool rcuref_get(rcuref_t *ref)
 	return rcuref_get_slowpath(ref);
 }
 
-extern __must_check bool rcuref_put_slowpath(rcuref_t *ref);
+extern __must_check bool rcuref_put_slowpath(rcuref_t *ref, unsigned int cnt);
 
 /*
  * Internal helper. Do not invoke directly.
  */
 static __always_inline __must_check bool __rcuref_put(rcuref_t *ref)
 {
+	int cnt;
+
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(),
 			 "suspicious rcuref_put_rcusafe() usage");
 	/*
 	 * Unconditionally decrease the reference count. The saturation and
 	 * dead zones provide enough tolerance for this.
 	 */
-	if (likely(!atomic_add_negative_release(-1, &ref->refcnt)))
+	cnt = atomic_sub_return_release(1, &ref->refcnt);
+	if (likely(cnt >= 0))
 		return false;
 
 	/*
 	 * Handle the last reference drop and cases inside the saturation
 	 * and dead zones.
 	 */
-	return rcuref_put_slowpath(ref);
+	return rcuref_put_slowpath(ref, cnt);
 }
 
 /**
diff --git a/include/linux/sizes.h b/include/linux/sizes.h
index c3a00b967d18..49039494076f 100644
--- a/include/linux/sizes.h
+++ b/include/linux/sizes.h
@@ -23,17 +23,25 @@
 #define SZ_4K				0x00001000
 #define SZ_8K				0x00002000
 #define SZ_16K				0x00004000
+#define SZ_24K				0x00006000
 #define SZ_32K				0x00008000
 #define SZ_64K				0x00010000
 #define SZ_128K				0x00020000
+#define SZ_192K				0x00030000
 #define SZ_256K				0x00040000
+#define SZ_384K				0x00060000
 #define SZ_512K				0x00080000
 
 #define SZ_1M				0x00100000
 #define SZ_2M				0x00200000
+#define SZ_3M				0x00300000
 #define SZ_4M				0x00400000
+#define SZ_6M				0x00600000
 #define SZ_8M				0x00800000
+#define SZ_12M				0x00c00000
 #define SZ_16M				0x01000000
+#define SZ_18M				0x01200000
+#define SZ_24M				0x01800000
 #define SZ_32M				0x02000000
 #define SZ_64M				0x04000000
 #define SZ_128M				0x08000000
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 2cbe0c22a32f..0b9095a281b8 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -91,6 +91,8 @@ struct sk_psock {
 	struct sk_psock_progs		progs;
 #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
 	struct strparser		strp;
+	u32				copied_seq;
+	u32				ingress_bytes;
 #endif
 	struct sk_buff_head		ingress_skb;
 	struct list_head		ingress_msg;
diff --git a/include/linux/socket.h b/include/linux/socket.h
index d18cc47e89bd..c3322eb3d686 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -392,6 +392,8 @@ struct ucred {
 
 extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr);
 extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
+extern int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len,
+			    void *data);
 
 struct timespec64;
 struct __kernel_timespec;
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index fec1e8a1570c..eac57914dcf3 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -158,7 +158,6 @@ enum {
 	RPC_TASK_NEED_XMIT,
 	RPC_TASK_NEED_RECV,
 	RPC_TASK_MSG_PIN_WAIT,
-	RPC_TASK_SIGNALLED,
 };
 
 #define rpc_test_and_set_running(t) \
@@ -171,7 +170,7 @@ enum {
 
 #define RPC_IS_ACTIVATED(t)	test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate)
 
-#define RPC_SIGNALLED(t)	test_bit(RPC_TASK_SIGNALLED, &(t)->tk_runstate)
+#define RPC_SIGNALLED(t)	(READ_ONCE(task->tk_rpc_status) == -ERESTARTSYS)
 
 /*
  * Task priorities.
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index f70d0958095c..5a37cb2b6f93 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -151,6 +151,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_X86
 		DIRECT_MAP_LEVEL2_SPLIT,
 		DIRECT_MAP_LEVEL3_SPLIT,
+		DIRECT_MAP_LEVEL2_COLLAPSE,
+		DIRECT_MAP_LEVEL3_COLLAPSE,
 #endif
 #ifdef CONFIG_PER_VMA_LOCK_STATS
 		VMA_LOCK_SUCCESS,