Merge tag 'vfs-7.3-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc vfs updates from Christian Brauner:
 "Bigger cleanups:

   - The lockref dead-count handling is tidied up.

     The open-coded check for a count below zero as the dead marker
     relies on information the caller should not have.

   - make put_mnt_ns() leave mounts connected. Destroying a mount
     namespace disconnected its mounts from their mount points. So a
     file descriptor still open on the parent of a mount point could be
     used to peek under it.

     Locked mounts were already kept connected to prevent exactly that.
     But a mount is only locked when its tree is copied across a user
     namespace boundary. So a mount namespace set up by a privileged
     component had no locked mounts and its mounts were disconnected.
     Passing UMOUNT_CONNECTED keeps every mount connected and prevents
     that bug.

   - vfs_prepare_mode() passes S_IFDIR for directories. I meant to fix
     that ago but didn't get to it. So now someone finally did it.

     This kills the exception where the mode could be 0 when a directory
     was created whereas every other creation operation passed it
     explicitly already.

   - move long delayed work for ufs, jffs2, hfsplus, hfs and affs from
     the per-cpu system_long_wq to the new unbound system_dfl_long_wq.

     None of that work relies on per-cpu state and the work item is
     enqueued with queue_delayed_work() whose timer is global anyway. So
     it may as well benefit from scheduler task placement.

  Smaller fixes and cleanups:

   - unlock_buffer() and journal_end_buffer_io_sync() use
     clear_and_wake_up_bit()

   - the pipe page pools are unified into a single per-pipe pool and the
     extra wake_up(rd_wait) is limited to EPOLLET consumers

   - eventpoll now computes its timer slack lazily in ep_poll()

   - shrink_dcache_for_umount() keeps making progress on busy roots

   - excess xarray nodes are freed in clear_inode()

   - romfs detects hard link cycles

   - the user path of nested backing files is fixed

   - pidfd holds exec_update_lock around the namespace ioctl

   - non-memcg-aware nr_cached_objects is skipped during memcg slab
     shrink

   - iomap_write_iter() always returns status

   - mangle_path() is renamed to seq_mangle_path()

   - inode timestamp accessors are annotated

   - new regression test for pipe->poll_usage.

   - a few documentation, kernel-doc and selftest fixes"

* tag 'vfs-7.3-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (67 commits)
  selftests/namespaces: Fix racy pipe handshake in timens and pidns_separate
  selftests/epoll: add a regression test for pipe->poll_usage
  pipe: only enable the extra wake_up(rd_wait) for EPOLLET consumers
  pidfd: hold exec_update_lock around namespace ioctl
  fs: fix user path of nested backing files
  fs: remove stale inode_insert5() kernel-doc parameter
  fs: fix switch/case indentation in sysfs() syscall
  fs: document semantics of kstat::{uid,gid} fields
  dcache: keep shrink_dcache_for_umount() making progress on busy roots
  seq_file: rename mangle_path to seq_mangle_path
  nstree: add/fix struct ns_id_req kernel-doc member fields
  dcache: use lockref routines for dead count checks
  lockref: tidy up dead count handling
  initramfs: fix typo in reserve_initrd_mem comment
  fs/pipe: unify the page pools into a single per-pipe pool
  fs: annotate inode timestamp accessors
  eventpoll: compute timer slack lazily in ep_poll()
  selftests/filesystems: add mntns cleanup test
  put_mnt_ns(): leave mounts connected
  affs: Move long delayed work on system_dfl_long_wq
  ...

5 files changed, 45 insertions, 19 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index c3c4a40c90a0..2f243b1554d8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1598,12 +1598,12 @@ struct timespec64 inode_set_ctime_deleg(struct inode *inode,
 
 static inline time64_t inode_get_atime_sec(const struct inode *inode)
 {
-	return inode->i_atime_sec;
+	return READ_ONCE(inode->i_atime_sec);
 }
 
 static inline long inode_get_atime_nsec(const struct inode *inode)
 {
-	return inode->i_atime_nsec;
+	return READ_ONCE(inode->i_atime_nsec);
 }
 
 static inline struct timespec64 inode_get_atime(const struct inode *inode)
@@ -1617,8 +1617,8 @@ static inline struct timespec64 inode_get_atime(const struct inode *inode)
 static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode,
 						      struct timespec64 ts)
 {
-	inode->i_atime_sec = ts.tv_sec;
-	inode->i_atime_nsec = ts.tv_nsec;
+	WRITE_ONCE(inode->i_atime_sec, ts.tv_sec);
+	WRITE_ONCE(inode->i_atime_nsec, ts.tv_nsec);
 	return ts;
 }
 
@@ -1633,12 +1633,12 @@ static inline struct timespec64 inode_set_atime(struct inode *inode,
 
 static inline time64_t inode_get_mtime_sec(const struct inode *inode)
 {
-	return inode->i_mtime_sec;
+	return READ_ONCE(inode->i_mtime_sec);
 }
 
 static inline long inode_get_mtime_nsec(const struct inode *inode)
 {
-	return inode->i_mtime_nsec;
+	return READ_ONCE(inode->i_mtime_nsec);
 }
 
 static inline struct timespec64 inode_get_mtime(const struct inode *inode)
@@ -1651,8 +1651,8 @@ static inline struct timespec64 inode_get_mtime(const struct inode *inode)
 static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode,
 						      struct timespec64 ts)
 {
-	inode->i_mtime_sec = ts.tv_sec;
-	inode->i_mtime_nsec = ts.tv_nsec;
+	WRITE_ONCE(inode->i_mtime_sec, ts.tv_sec);
+	WRITE_ONCE(inode->i_mtime_nsec, ts.tv_nsec);
 	return ts;
 }
 
@@ -1677,12 +1677,12 @@ static inline struct timespec64 inode_set_mtime(struct inode *inode,
 
 static inline time64_t inode_get_ctime_sec(const struct inode *inode)
 {
-	return inode->i_ctime_sec;
+	return READ_ONCE(inode->i_ctime_sec);
 }
 
 static inline long inode_get_ctime_nsec(const struct inode *inode)
 {
-	return inode->i_ctime_nsec & ~I_CTIME_QUERIED;
+	return READ_ONCE(inode->i_ctime_nsec) & ~I_CTIME_QUERIED;
 }
 
 static inline struct timespec64 inode_get_ctime(const struct inode *inode)
diff --git a/include/linux/lockref.h b/include/linux/lockref.h
index 6ded24cdb4a8..ddfb7d3b8cec 100644
--- a/include/linux/lockref.h
+++ b/include/linux/lockref.h
@@ -34,6 +34,8 @@ struct lockref {
 	};
 };
 
+#define __LOCKREF_DEAD_VAL	-128
+
 /**
  * lockref_init - Initialize a lockref
  * @lockref: pointer to lockref structure
@@ -55,9 +57,15 @@ void lockref_mark_dead(struct lockref *lockref);
 bool lockref_get_not_dead(struct lockref *lockref);
 
 /* Must be called under spinlock for reliable results */
-static inline bool __lockref_is_dead(const struct lockref *l)
+static inline bool lockref_is_dead(const struct lockref *l)
+{
+	return (READ_ONCE(l->count) == __LOCKREF_DEAD_VAL);
+}
+
+static inline bool lockref_is_dead_or_zero(const struct lockref *l)
 {
-	return ((int)l->count < 0);
+	int count = READ_ONCE(l->count);
+	return (count == __LOCKREF_DEAD_VAL || count == 0);
 }
 
 #endif /* __LINUX_LOCKREF_H */
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 7f6a92ac9704..6402930282e5 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -14,6 +14,9 @@
 #define PIPE_BUF_FLAG_LOSS	0x40	/* Message loss happened after this buffer */
 #endif
 
+#define PIPE_PREALLOC_MAX	8	/* max pages in prealloc pool */
+#define PIPE_PREALLOC_KEEP	2	/* keep at least this many after trim */
+
 /**
  *	struct pipe_buffer - a linux kernel pipe buffer
  *	@page: the page containing the data for the pipe buffer
@@ -59,6 +62,21 @@ union pipe_index {
 };
 
 /**
+ *	struct anon_pipe_prealloc - per-pipe page preallocation pool
+ *	@pages: array of cached pages (pool)
+ *	@count: number of pages currently in the pool
+ *
+ * Each pipe keeps a small bounded pool of preallocated pages to reduce
+ * allocation overhead during writes. The pool is bounded at PIPE_PREALLOC_MAX
+ * and trimmed down to PIPE_PREALLOC_KEEP after a write completes.
+ */
+struct anon_pipe_prealloc {
+	struct page *pages[PIPE_PREALLOC_MAX];
+
+	unsigned int __data_racy count;
+};
+
+/**
  *	struct pipe_inode_info - a linux kernel pipe
  *	@mutex: mutex protecting the whole thing
  *	@rd_wait: reader wait point in case of empty pipe
@@ -68,13 +86,13 @@ union pipe_index {
  *	@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)
  *	@nr_accounted: The amount this pipe accounts for in user->pipe_bufs
- *	@tmp_page: cached released page
+ *	@prealloc: per-pipe page preallocation pool
  *	@readers: number of current readers of this pipe
  *	@writers: number of current writers of this pipe
  *	@files: number of struct file referring this pipe (protected by ->i_lock)
  *	@r_counter: reader counter
  *	@w_counter: writer counter
- *	@poll_usage: is this pipe used for epoll, which has crazy wakeups?
+ *	@pseudo_edgetrigger: has an EPOLLET consumer, enable per-write wakeups
  *	@fasync_readers: reader side fasync
  *	@fasync_writers: writer side fasync
  *	@bufs: the circular array of pipe buffers
@@ -95,11 +113,11 @@ struct pipe_inode_info {
 	unsigned int files;
 	unsigned int r_counter;
 	unsigned int w_counter;
-	bool poll_usage;
+	bool pseudo_edgetrigger;
 #ifdef CONFIG_WATCH_QUEUE
 	bool note_loss;
 #endif
-	struct page *tmp_page[2];
+	struct anon_pipe_prealloc prealloc;
 	struct fasync_struct *fasync_readers;
 	struct fasync_struct *fasync_writers;
 	struct pipe_buffer *bufs;
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 2fb266ea69fa..dc0e8c62d9e0 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -104,7 +104,7 @@ static inline void seq_setwidth(struct seq_file *m, size_t size)
 }
 void seq_pad(struct seq_file *m, char c);
 
-char *mangle_path(char *s, const char *p, const char *esc);
+char *seq_mangle_path(char *s, const char *p, const char *esc);
 int seq_open(struct file *, const struct seq_operations *);
 ssize_t seq_read(struct file *, char __user *, size_t, loff_t *);
 ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter);
diff --git a/include/linux/stat.h b/include/linux/stat.h
index e3d00e7bb26d..9c5709132862 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -41,8 +41,8 @@ struct kstat {
 	u64		ino;
 	dev_t		dev;
 	dev_t		rdev;
-	kuid_t		uid;
-	kgid_t		gid;
+	kuid_t		uid;		/* This is logically a vfsuid_t. */
+	kgid_t		gid;		/* This is logically a vfsgid_t. */
 	loff_t		size;
 	struct timespec64 atime;
 	struct timespec64 mtime;