11 files changed, 130 insertions, 50 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/cred.h b/include/linux/cred.h
index 0c3c4b16b469..5658a3bfe803 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -172,18 +172,12 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred)
 
 static inline const struct cred *override_creds(const struct cred *override_cred)
 {
-	const struct cred *old = current->cred;
-
-	rcu_assign_pointer(current->cred, override_cred);
-	return old;
+	return rcu_replace_pointer(current->cred, override_cred, 1);
 }
 
 static inline const struct cred *revert_creds(const struct cred *revert_cred)
 {
-	const struct cred *override_cred = current->cred;
-
-	rcu_assign_pointer(current->cred, revert_cred);
-	return override_cred;
+	return rcu_replace_pointer(current->cred, revert_cred, 1);
 }
 
 /**
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/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/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 8ff23bf5a819..b698758000f8 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -31,6 +31,33 @@ struct pipe_buffer {
 	unsigned long private;
 };
 
+/*
+ * Really only alpha needs 32-bit fields, but
+ * might as well do it for 64-bit architectures
+ * since that's what we've historically done,
+ * and it makes 'head_tail' always be a simple
+ * 'unsigned long'.
+ */
+#ifdef CONFIG_64BIT
+typedef unsigned int pipe_index_t;
+#else
+typedef unsigned short pipe_index_t;
+#endif
+
+/*
+ * We have to declare this outside 'struct pipe_inode_info',
+ * but then we can't use 'union pipe_index' for an anonymous
+ * union, so we end up having to duplicate this declaration
+ * below. Annoying.
+ */
+union pipe_index {
+	unsigned long head_tail;
+	struct {
+		pipe_index_t head;
+		pipe_index_t tail;
+	};
+};
+
 /**
  *	struct pipe_inode_info - a linux kernel pipe
  *	@mutex: mutex protecting the whole thing
@@ -38,6 +65,7 @@ struct pipe_buffer {
  *	@wr_wait: writer wait point in case of full pipe
  *	@head: The point of buffer production
  *	@tail: The point of buffer consumption
+ *	@head_tail: unsigned long union of @head and @tail
  *	@note_loss: The next read() should insert a data-lost message
  *	@max_usage: The maximum number of slots that may be used in the ring
  *	@ring_size: total number of buffers (should be a power of 2)
@@ -58,8 +86,16 @@ struct pipe_buffer {
 struct pipe_inode_info {
 	struct mutex mutex;
 	wait_queue_head_t rd_wait, wr_wait;
-	unsigned int head;
-	unsigned int tail;
+
+	/* This has to match the 'union pipe_index' above */
+	union {
+		unsigned long head_tail;
+		struct {
+			pipe_index_t head;
+			pipe_index_t tail;
+		};
+	};
+
 	unsigned int max_usage;
 	unsigned int ring_size;
 	unsigned int nr_accounted;
@@ -141,23 +177,23 @@ static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe)
 }
 
 /**
- * pipe_empty - Return true if the pipe is empty
+ * pipe_occupancy - Return number of slots used in the pipe
  * @head: The pipe ring head pointer
  * @tail: The pipe ring tail pointer
  */
-static inline bool pipe_empty(unsigned int head, unsigned int tail)
+static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail)
 {
-	return head == tail;
+	return (pipe_index_t)(head - tail);
 }
 
 /**
- * pipe_occupancy - Return number of slots used in the pipe
+ * pipe_empty - Return true if the pipe is empty
  * @head: The pipe ring head pointer
  * @tail: The pipe ring tail pointer
  */
-static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail)
+static inline bool pipe_empty(unsigned int head, unsigned int tail)
 {
-	return head - tail;
+	return !pipe_occupancy(head, tail);
 }
 
 /**
@@ -173,6 +209,33 @@ static inline bool pipe_full(unsigned int head, unsigned int tail,
 }
 
 /**
+ * pipe_is_full - Return true if the pipe is full
+ * @pipe: the pipe
+ */
+static inline bool pipe_is_full(const struct pipe_inode_info *pipe)
+{
+	return pipe_full(pipe->head, pipe->tail, pipe->max_usage);
+}
+
+/**
+ * pipe_is_empty - Return true if the pipe is empty
+ * @pipe: the pipe
+ */
+static inline bool pipe_is_empty(const struct pipe_inode_info *pipe)
+{
+	return pipe_empty(pipe->head, pipe->tail);
+}
+
+/**
+ * pipe_buf_usage - Return how many pipe buffers are in use
+ * @pipe: the pipe
+ */
+static inline unsigned int pipe_buf_usage(const struct pipe_inode_info *pipe)
+{
+	return pipe_occupancy(pipe->head, pipe->tail);
+}
+
+/**
  * pipe_buf - Return the pipe buffer for the specified slot in the pipe ring
  * @pipe: The pipe to access
  * @slot: The slot of interest
@@ -245,15 +308,6 @@ static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe,
 	return buf->ops->try_steal(pipe, buf);
 }
 
-static inline void pipe_discard_from(struct pipe_inode_info *pipe,
-		unsigned int old_head)
-{
-	unsigned int mask = pipe->ring_size - 1;
-
-	while (pipe->head > old_head)
-		pipe_buf_release(pipe, &pipe->bufs[--pipe->head & mask]);
-}
-
 /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual
    memory allocation, whereas PIPE_BUF makes atomicity guarantees.  */
 #define PIPE_SIZE		PAGE_SIZE
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/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.