Merge tag 'vfs-6.12.file' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs file updates from Christian Brauner:
 "This is the work to cleanup and shrink struct file significantly.

  Right now, (focusing on x86) struct file is 232 bytes. After this
  series struct file will be 184 bytes aka 3 cacheline and a spare 8
  bytes for future extensions at the end of the struct.

  With struct file being as ubiquitous as it is this should make a
  difference for file heavy workloads and allow further optimizations in
  the future.

   - struct fown_struct was embedded into struct file letting it take up
     32 bytes in total when really it shouldn't even be embedded in
     struct file in the first place. Instead, actual users of struct
     fown_struct now allocate the struct on demand. This frees up 24
     bytes.

   - Move struct file_ra_state into the union containg the cleanup hooks
     and move f_iocb_flags out of the union. This closes a 4 byte hole
     we created earlier and brings struct file to 192 bytes. Which means
     struct file is 3 cachelines and we managed to shrink it by 40
     bytes.

   - Reorder struct file so that nothing crosses a cacheline.

     I suspect that in the future we will end up reordering some members
     to mitigate false sharing issues or just because someone does
     actually provide really good perf data.

   - Shrinking struct file to 192 bytes is only part of the work.

     Files use a slab that is SLAB_TYPESAFE_BY_RCU and when a kmem cache
     is created with SLAB_TYPESAFE_BY_RCU the free pointer must be
     located outside of the object because the cache doesn't know what
     part of the memory can safely be overwritten as it may be needed to
     prevent object recycling.

     That has the consequence that SLAB_TYPESAFE_BY_RCU may end up
     adding a new cacheline.

     So this also contains work to add a new kmem_cache_create_rcu()
     function that allows the caller to specify an offset where the
     freelist pointer is supposed to be placed. Thus avoiding the
     implicit addition of a fourth cacheline.

   - And finally this removes the f_version member in struct file.

     The f_version member isn't particularly well-defined. It is mainly
     used as a cookie to detect concurrent seeks when iterating
     directories. But it is also abused by some subsystems for
     completely unrelated things.

     It is mostly a directory and filesystem specific thing that doesn't
     really need to live in struct file and with its wonky semantics it
     really lacks a specific function.

     For pipes, f_version is (ab)used to defer poll notifications until
     a write has happened. And struct pipe_inode_info is used by
     multiple struct files in their ->private_data so there's no chance
     of pushing that down into file->private_data without introducing
     another pointer indirection.

     But pipes don't rely on f_pos_lock so this adds a union into struct
     file encompassing f_pos_lock and a pipe specific f_pipe member that
     pipes can use. This union of course can be extended to other file
     types and is similar to what we do in struct inode already"

* tag 'vfs-6.12.file' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (26 commits)
  fs: remove f_version
  pipe: use f_pipe
  fs: add f_pipe
  ubifs: store cookie in private data
  ufs: store cookie in private data
  udf: store cookie in private data
  proc: store cookie in private data
  ocfs2: store cookie in private data
  input: remove f_version abuse
  ext4: store cookie in private data
  ext2: store cookie in private data
  affs: store cookie in private data
  fs: add generic_llseek_cookie()
  fs: use must_set_pos()
  fs: add must_set_pos()
  fs: add vfs_setpos_cookie()
  s390: remove unused f_version
  ceph: remove unused f_version
  adi: remove unused f_version
  mm: Removed @freeptr_offset to prevent doc warning
  ...

1 files changed, 66 insertions, 40 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index e8d078e98379..0df3e5f0dd2b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -963,6 +963,7 @@ static inline unsigned imajor(const struct inode *inode)
 }
 
 struct fown_struct {
+	struct file *file;	/* backpointer for security modules */
 	rwlock_t lock;          /* protects pid, uid, euid fields */
 	struct pid *pid;	/* pid or -pgrp where SIGIO should be sent */
 	enum pid_type pid_type;	/* Kind of process group SIGIO should be sent to */
@@ -1002,52 +1003,69 @@ 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 - Represents a file
+ * @f_count: reference count
+ * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context.
+ * @f_mode: FMODE_* flags often used in hotpaths
+ * @f_op: file operations
+ * @f_mapping: Contents of a cacheable, mappable object.
+ * @private_data: filesystem or driver specific data
+ * @f_inode: cached inode
+ * @f_flags: file flags
+ * @f_iocb_flags: iocb flags
+ * @f_cred: stashed credentials of creator/opener
+ * @f_path: path of the file
+ * @f_pos_lock: lock protecting file position
+ * @f_pipe: specific to pipes
+ * @f_pos: file position
+ * @f_security: LSM security context of this file
+ * @f_owner: file owner
+ * @f_wb_err: writeback error
+ * @f_sb_err: per sb writeback errors
+ * @f_ep: link of all epoll hooks for this file
+ * @f_task_work: task work entry point
+ * @f_llist: work queue entrypoint
+ * @f_ra: file's readahead state
+ * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.)
  */
 struct file {
+	atomic_long_t			f_count;
+	spinlock_t			f_lock;
+	fmode_t				f_mode;
+	const struct file_operations	*f_op;
+	struct address_space		*f_mapping;
+	void				*private_data;
+	struct inode			*f_inode;
+	unsigned int			f_flags;
+	unsigned int			f_iocb_flags;
+	const struct cred		*f_cred;
+	/* --- cacheline 1 boundary (64 bytes) --- */
+	struct path			f_path;
 	union {
-		/* fput() uses task work when closing and freeing file (default). */
-		struct callback_head 	f_task_work;
-		/* fput() must use workqueue (most kernel threads). */
-		struct llist_node	f_llist;
-		unsigned int 		f_iocb_flags;
+		/* regular files (with FMODE_ATOMIC_POS) and directories */
+		struct mutex		f_pos_lock;
+		/* pipes */
+		u64			f_pipe;
 	};
-
-	/*
-	 * Protects f_ep, f_flags.
-	 * Must not be taken from IRQ context.
-	 */
-	spinlock_t		f_lock;
-	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;
+	loff_t				f_pos;
 #ifdef CONFIG_SECURITY
-	void			*f_security;
+	void				*f_security;
 #endif
-	/* needed for tty driver, and maybe others */
-	void			*private_data;
-
+	/* --- cacheline 2 boundary (128 bytes) --- */
+	struct fown_struct		*f_owner;
+	errseq_t			f_wb_err;
+	errseq_t			f_sb_err;
 #ifdef CONFIG_EPOLL
-	/* Used by fs/eventpoll.c to link all the hooks to this file */
-	struct hlist_head	*f_ep;
-#endif /* #ifdef CONFIG_EPOLL */
-	struct address_space	*f_mapping;
-	errseq_t		f_wb_err;
-	errseq_t		f_sb_err; /* for syncfs */
+	struct hlist_head		*f_ep;
+#endif
+	union {
+		struct callback_head	f_task_work;
+		struct llist_node	f_llist;
+		struct file_ra_state	f_ra;
+		freeptr_t		f_freeptr;
+	};
+	/* --- cacheline 3 boundary (192 bytes) --- */
 } __randomize_layout
   __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
 
@@ -1092,6 +1110,12 @@ struct file_lease;
 #define OFFT_OFFSET_MAX	type_max(off_t)
 #endif
 
+int file_f_owner_allocate(struct file *file);
+static inline struct fown_struct *file_f_owner(const struct file *file)
+{
+	return READ_ONCE(file->f_owner);
+}
+
 extern void send_sigio(struct fown_struct *fown, int fd, int band);
 
 static inline struct inode *file_inode(const struct file *f)
@@ -1140,7 +1164,7 @@ extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force
 extern int f_setown(struct file *filp, int who, int force);
 extern void f_delown(struct file *filp);
 extern pid_t f_getown(struct file *filp);
-extern int send_sigurg(struct fown_struct *fown);
+extern int send_sigurg(struct file *file);
 
 /*
  * sb->s_flags.  Note that these mirror the equivalent MS_* flags where
@@ -3207,6 +3231,8 @@ extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize);
 extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence);
 extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
 		int whence, loff_t maxsize, loff_t eof);
+loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence,
+			     u64 *cookie);
 extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
 		int whence, loff_t size);
 extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t);