Merge tag 'v6.5/vfs.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc vfs updates from Christian Brauner:
 "Miscellaneous features, cleanups, and fixes for vfs and individual fs

  Features:

   - Use mode 0600 for file created by cachefilesd so it can be run by
     unprivileged users. This aligns them with directories which are
     already created with mode 0700 by cachefilesd

   - Reorder a few members in struct file to prevent some false sharing
     scenarios

   - Indicate that an eventfd is used a semaphore in the eventfd's
     fdinfo procfs file

   - Add a missing uapi header for eventfd exposing relevant uapi
     defines

   - Let the VFS protect transitions of a superblock from read-only to
     read-write in addition to the protection it already provides for
     transitions from read-write to read-only. Protecting read-only to
     read-write transitions allows filesystems such as ext4 to perform
     internal writes, keeping writers away until the transition is
     completed

  Cleanups:

   - Arnd removed the architecture specific arch_report_meminfo()
     prototypes and added a generic one into procfs.h. Note, we got a
     report about a warning in amdpgpu codepaths that suggested this was
     bisectable to this change but we concluded it was a false positive

   - Remove unused parameters from split_fs_names()

   - Rename put_and_unmap_page() to unmap_and_put_page() to let the name
     reflect the order of the cleanup operation that has to unmap before
     the actual put

   - Unexport buffer_check_dirty_writeback() as it is not used outside
     of block device aops

   - Stop allocating aio rings from highmem

   - Protecting read-{only,write} transitions in the VFS used open-coded
     barriers in various places. Replace them with proper little helpers
     and document both the helpers and all barrier interactions involved
     when transitioning between read-{only,write} states

   - Use flexible array members in old readdir codepaths

  Fixes:

   - Use the correct type __poll_t for epoll and eventfd

   - Replace all deprecated strlcpy() invocations, whose return value
     isn't checked with an equivalent strscpy() call

   - Fix some kernel-doc warnings in fs/open.c

   - Reduce the stack usage in jffs2's xattr codepaths finally getting
     rid of this: fs/jffs2/xattr.c:887:1: error: the frame size of 1088
     bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
     royally annoying compilation warning

   - Use __FMODE_NONOTIFY instead of FMODE_NONOTIFY where an int and not
     fmode_t is required to avoid fmode_t to integer degradation
     warnings

   - Create coredumps with O_WRONLY instead of O_RDWR. There's a long
     explanation in that commit how O_RDWR is actually a bug which we
     found out with the help of Linus and git archeology

   - Fix "no previous prototype" warnings in the pipe codepaths

   - Add overflow calculations for remap_verify_area() as a signed
     addition overflow could be triggered in xfstests

   - Fix a null pointer dereference in sysv

   - Use an unsigned variable for length calculations in jfs avoiding
     compilation warnings with gcc 13

   - Fix a dangling pipe pointer in the watch queue codepath

   - The legacy mount option parser provided as a fallback by the VFS
     for filesystems not yet converted to the new mount api did prefix
     the generated mount option string with a leading ',' causing issues
     for some filesystems

   - Fix a repeated word in a comment in fs.h

   - autofs: Update the ctime when mtime is updated as mandated by
     POSIX"

* tag 'v6.5/vfs.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (27 commits)
  readdir: Replace one-element arrays with flexible-array members
  fs: Provide helpers for manipulating sb->s_readonly_remount
  fs: Protect reconfiguration of sb read-write from racing writes
  eventfd: add a uapi header for eventfd userspace APIs
  autofs: set ctime as well when mtime changes on a dir
  eventfd: show the EFD_SEMAPHORE flag in fdinfo
  fs/aio: Stop allocating aio rings from HIGHMEM
  fs: Fix comment typo
  fs: unexport buffer_check_dirty_writeback
  fs: avoid empty option when generating legacy mount string
  watch_queue: prevent dangling pipe pointer
  fs.h: Optimize file struct to prevent false sharing
  highmem: Rename put_and_unmap_page() to unmap_and_put_page()
  cachefiles: Allow the cache to be non-root
  init: remove unused names parameter in split_fs_names()
  jfs: Use unsigned variable for length calculations
  fs/sysv: Null check to prevent null-ptr-deref bug
  fs: use UB-safe check for signed addition overflow in remap_verify_area
  procfs: consolidate arch_report_meminfo declaration
  fs: pipe: reveal missing function protoypes
  ...

6 files changed, 19 insertions, 20 deletions

diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index 36a486505b08..b9d83652c097 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -9,12 +9,12 @@
 #ifndef _LINUX_EVENTFD_H
 #define _LINUX_EVENTFD_H
 
-#include <linux/fcntl.h>
 #include <linux/wait.h>
 #include <linux/err.h>
 #include <linux/percpu-defs.h>
 #include <linux/percpu.h>
 #include <linux/sched.h>
+#include <uapi/linux/eventfd.h>
 
 /*
  * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
@@ -23,10 +23,6 @@
  * from eventfd, in order to leave a free define-space for
  * shared O_* flags.
  */
-#define EFD_SEMAPHORE (1 << 0)
-#define EFD_CLOEXEC O_CLOEXEC
-#define EFD_NONBLOCK O_NONBLOCK
-
 #define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
 #define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE)
 
@@ -40,7 +36,7 @@ struct file *eventfd_fget(int fd);
 struct eventfd_ctx *eventfd_ctx_fdget(int fd);
 struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
 __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
-__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask);
+__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
 void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 133f0640fb24..66f105ef3427 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -956,29 +956,35 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 		index <  ra->start + ra->size);
 }
 
+/*
+ * f_{lock,count,pos_lock} members can be highly contended and share
+ * the same cacheline. f_{lock,mode} are very frequently used together
+ * and so share the same cacheline as well. The read-mostly
+ * f_{path,inode,op} are kept on a separate cacheline.
+ */
 struct file {
 	union {
 		struct llist_node	f_llist;
 		struct rcu_head 	f_rcuhead;
 		unsigned int 		f_iocb_flags;
 	};
-	struct path		f_path;
-	struct inode		*f_inode;	/* cached value */
-	const struct file_operations	*f_op;
 
 	/*
 	 * Protects f_ep, f_flags.
 	 * Must not be taken from IRQ context.
 	 */
 	spinlock_t		f_lock;
-	atomic_long_t		f_count;
-	unsigned int 		f_flags;
 	fmode_t			f_mode;
+	atomic_long_t		f_count;
 	struct mutex		f_pos_lock;
 	loff_t			f_pos;
+	unsigned int		f_flags;
 	struct fown_struct	f_owner;
 	const struct cred	*f_cred;
 	struct file_ra_state	f_ra;
+	struct path		f_path;
+	struct inode		*f_inode;	/* cached value */
+	const struct file_operations	*f_op;
 
 	u64			f_version;
 #ifdef CONFIG_SECURITY
@@ -1242,7 +1248,7 @@ struct super_block {
 	 */
 	atomic_long_t s_fsnotify_connectors;
 
-	/* Being remounted read-only */
+	/* Read-only state of the superblock is being changed */
 	int s_readonly_remount;
 
 	/* per-sb errseq_t for reporting writeback errors via syncfs */
@@ -2669,7 +2675,7 @@ extern void evict_inodes(struct super_block *sb);
 void dump_mapping(const struct address_space *);
 
 /*
- * Userspace may rely on the the inode number being non-zero. For example, glibc
+ * Userspace may rely on the inode number being non-zero. For example, glibc
  * simply ignores files with zero i_ino in unlink() and other places.
  *
  * As an additional complication, if userspace was compiled with
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 4de1dbcd3ef6..68da30625a6c 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -507,7 +507,7 @@ static inline void folio_zero_range(struct folio *folio,
 	zero_user_segments(&folio->page, start, start + length, 0, 0);
 }
 
-static inline void put_and_unmap_page(struct page *page, void *addr)
+static inline void unmap_and_put_page(struct page *page, void *addr)
 {
 	kunmap_local(addr);
 	put_page(page);
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index d2c3f16cf6b1..02e0086b10f6 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -261,18 +261,14 @@ void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
 
 extern const struct pipe_buf_operations nosteal_pipe_buf_ops;
 
-#ifdef CONFIG_WATCH_QUEUE
 unsigned long account_pipe_buffers(struct user_struct *user,
 				   unsigned long old, unsigned long new);
 bool too_many_pipe_buffers_soft(unsigned long user_bufs);
 bool too_many_pipe_buffers_hard(unsigned long user_bufs);
 bool pipe_is_unprivileged_user(void);
-#endif
 
 /* for F_SETPIPE_SZ and F_GETPIPE_SZ */
-#ifdef CONFIG_WATCH_QUEUE
 int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots);
-#endif
 long pipe_fcntl(struct file *, unsigned int, unsigned long arg);
 struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice);
 
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 0260f5ea98fe..253f2676d93a 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -158,6 +158,8 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns,
 			struct pid *pid, struct task_struct *task);
 #endif /* CONFIG_PROC_PID_ARCH_STATUS */
 
+void arch_report_meminfo(struct seq_file *m);
+
 #else /* CONFIG_PROC_FS */
 
 static inline void proc_root_init(void)
diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h
index fc6bba20273b..45cd42f55d49 100644
--- a/include/linux/watch_queue.h
+++ b/include/linux/watch_queue.h
@@ -38,7 +38,7 @@ struct watch_filter {
 struct watch_queue {
 	struct rcu_head		rcu;
 	struct watch_filter __rcu *filter;
-	struct pipe_inode_info	*pipe;		/* The pipe we're using as a buffer */
+	struct pipe_inode_info	*pipe;		/* Pipe we use as a buffer, NULL if queue closed */
 	struct hlist_head	watches;	/* Contributory watches */
 	struct page		**notes;	/* Preallocated notifications */
 	unsigned long		*notes_bitmap;	/* Allocation bitmap for notes */
@@ -46,7 +46,6 @@ struct watch_queue {
 	spinlock_t		lock;
 	unsigned int		nr_notes;	/* Number of notes */
 	unsigned int		nr_pages;	/* Number of pages in notes[] */
-	bool			defunct;	/* T when queues closed */
 };
 
 /*