Merge tag 'vfs-6.15-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc vfs updates from Christian Brauner:
 "Features:

   - Add CONFIG_DEBUG_VFS infrastucture:
      - Catch invalid modes in open
      - Use the new debug macros in inode_set_cached_link()
      - Use debug-only asserts around fd allocation and install

   - Place f_ref to 3rd cache line in struct file to resolve false
     sharing

Cleanups:

   - Start using anon_inode_getfile_fmode() helper in various places

   - Don't take f_lock during SEEK_CUR if exclusion is guaranteed by
     f_pos_lock

   - Add unlikely() to kcmp()

   - Remove legacy ->remount_fs method from ecryptfs after port to the
     new mount api

   - Remove invalidate_inodes() in favour of evict_inodes()

   - Simplify ep_busy_loopER by removing unused argument

   - Avoid mmap sem relocks when coredumping with many missing pages

   - Inline getname()

   - Inline new_inode_pseudo() and de-staticize alloc_inode()

   - Dodge an atomic in putname if ref == 1

   - Consistently deref the files table with rcu_dereference_raw()

   - Dedup handling of struct filename init and refcounts bumps

   - Use wq_has_sleeper() in end_dir_add()

   - Drop the lock trip around I_NEW wake up in evict()

   - Load the ->i_sb pointer once in inode_sb_list_{add,del}

   - Predict not reaching the limit in alloc_empty_file()

   - Tidy up do_sys_openat2() with likely/unlikely

   - Call inode_sb_list_add() outside of inode hash lock

   - Sort out fd allocation vs dup2 race commentary

   - Turn page_offset() into a wrapper around folio_pos()

   - Remove locking in exportfs around ->get_parent() call

   - try_lookup_one_len() does not need any locks in autofs

   - Fix return type of several functions from long to int in open

   - Fix return type of several functions from long to int in ioctls

  Fixes:

   - Fix watch queue accounting mismatch"

* tag 'vfs-6.15-rc1.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (30 commits)
  fs: sort out fd allocation vs dup2 race commentary, take 2
  fs: call inode_sb_list_add() outside of inode hash lock
  fs: tidy up do_sys_openat2() with likely/unlikely
  fs: predict not reaching the limit in alloc_empty_file()
  fs: load the ->i_sb pointer once in inode_sb_list_{add,del}
  fs: drop the lock trip around I_NEW wake up in evict()
  fs: use wq_has_sleeper() in end_dir_add()
  VFS/autofs: try_lookup_one_len() does not need any locks
  fs: dedup handling of struct filename init and refcounts bumps
  fs: consistently deref the files table with rcu_dereference_raw()
  exportfs: remove locking around ->get_parent() call.
  fs: use debug-only asserts around fd allocation and install
  fs: dodge an atomic in putname if ref == 1
  vfs: Remove invalidate_inodes()
  ecryptfs: remove NULL remount_fs from super_operations
  watch_queue: fix pipe accounting mismatch
  fs: place f_ref to 3rd cache line in struct file to resolve false sharing
  epoll: simplify ep_busy_loop by removing always 0 argument
  fs: Turn page_offset() into a wrapper around folio_pos()
  kcmp: improve performance adding an unlikely hint to task comparisons
  ...

5 files changed, 85 insertions, 35 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index b570138ff114..91b1e191530c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_FS_H
 #define _LINUX_FS_H
 
+#include <linux/vfsdebug.h>
 #include <linux/linkage.h>
 #include <linux/wait_bit.h>
 #include <linux/kdev_t.h>
@@ -790,19 +791,8 @@ struct inode {
 
 static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen)
 {
-	int testlen;
-
-	/*
-	 * TODO: patch it into a debug-only check if relevant macros show up.
-	 * In the meantime, since we are suffering strlen even on production kernels
-	 * to find the right length, do a fixup if the wrong value got passed.
-	 */
-	testlen = strlen(link);
-	if (testlen != linklen) {
-		WARN_ONCE(1, "bad length passed for symlink [%s] (got %d, expected %d)",
-			  link, linklen, testlen);
-		linklen = testlen;
-	}
+	VFS_WARN_ON_INODE(strlen(link) != linklen, inode);
+	VFS_WARN_ON_INODE(inode->i_opflags & IOP_CACHED_LINK, inode);
 	inode->i_link = link;
 	inode->i_linklen = linklen;
 	inode->i_opflags |= IOP_CACHED_LINK;
@@ -1067,7 +1057,6 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 
 /**
  * struct file - Represents a file
- * @f_ref: 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
@@ -1077,12 +1066,12 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
  * @f_flags: file flags
  * @f_iocb_flags: iocb flags
  * @f_cred: stashed credentials of creator/opener
+ * @f_owner: file owner
  * @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
@@ -1090,9 +1079,9 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
  * @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.)
+ * @f_ref: reference count
  */
 struct file {
-	file_ref_t			f_ref;
 	spinlock_t			f_lock;
 	fmode_t				f_mode;
 	const struct file_operations	*f_op;
@@ -1102,6 +1091,7 @@ struct file {
 	unsigned int			f_flags;
 	unsigned int			f_iocb_flags;
 	const struct cred		*f_cred;
+	struct fown_struct		*f_owner;
 	/* --- cacheline 1 boundary (64 bytes) --- */
 	struct path			f_path;
 	union {
@@ -1115,7 +1105,6 @@ struct file {
 	void				*f_security;
 #endif
 	/* --- cacheline 2 boundary (128 bytes) --- */
-	struct fown_struct		*f_owner;
 	errseq_t			f_wb_err;
 	errseq_t			f_sb_err;
 #ifdef CONFIG_EPOLL
@@ -1127,6 +1116,7 @@ struct file {
 		struct file_ra_state	f_ra;
 		freeptr_t		f_freeptr;
 	};
+	file_ref_t			f_ref;
 	/* --- cacheline 3 boundary (192 bytes) --- */
 } __randomize_layout
   __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
@@ -2039,7 +2029,7 @@ int vfs_fchown(struct file *file, uid_t user, gid_t group);
 int vfs_fchmod(struct file *file, umode_t mode);
 int vfs_utimes(const struct path *path, struct timespec64 *times);
 
-extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+int vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 
 #ifdef CONFIG_COMPAT
 extern long compat_ptr_ioctl(struct file *file, unsigned int cmd,
@@ -2791,13 +2781,13 @@ static inline bool is_idmapped_mnt(const struct vfsmount *mnt)
 	return mnt_idmap(mnt) != &nop_mnt_idmap;
 }
 
-extern long vfs_truncate(const struct path *, loff_t);
+int vfs_truncate(const struct path *, loff_t);
 int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start,
 		unsigned int time_attrs, struct file *filp);
 extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
 			loff_t len);
-extern long do_sys_open(int dfd, const char __user *filename, int flags,
-			umode_t mode);
+int do_sys_open(int dfd, const char __user *filename, int flags,
+		umode_t mode);
 extern struct file *file_open_name(struct filename *, int, umode_t);
 extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(const struct path *,
@@ -2848,7 +2838,10 @@ extern int filp_close(struct file *, fl_owner_t id);
 
 extern struct filename *getname_flags(const char __user *, int);
 extern struct filename *getname_uflags(const char __user *, int);
-extern struct filename *getname(const char __user *);
+static inline struct filename *getname(const char __user *name)
+{
+	return getname_flags(name, 0);
+}
 extern struct filename *getname_kernel(const char *);
 extern struct filename *__getname_maybe_null(const char __user *);
 static inline struct filename *getname_maybe_null(const char __user *name, int flags)
@@ -2862,6 +2855,12 @@ static inline struct filename *getname_maybe_null(const char __user *name, int f
 }
 extern void putname(struct filename *name);
 
+static inline struct filename *refname(struct filename *name)
+{
+	atomic_inc(&name->refcnt);
+	return name;
+}
+
 extern int finish_open(struct file *file, struct dentry *dentry,
 			int (*open)(struct inode *, struct file *));
 extern int finish_no_open(struct file *file, struct dentry *dentry);
@@ -3294,7 +3293,11 @@ static inline void __iget(struct inode *inode)
 extern void iget_failed(struct inode *);
 extern void clear_inode(struct inode *);
 extern void __destroy_inode(struct inode *);
-extern struct inode *new_inode_pseudo(struct super_block *sb);
+struct inode *alloc_inode(struct super_block *sb);
+static inline struct inode *new_inode_pseudo(struct super_block *sb)
+{
+	return alloc_inode(sb);
+}
 extern struct inode *new_inode(struct super_block *sb);
 extern void free_inode_nonrcu(struct inode *inode);
 extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1f80baddacc5..2edb8d14d165 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2555,7 +2555,7 @@ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
 			struct task_struct *task, bool bypass_rlim);
 
 struct kvec;
-struct page *get_dump_page(unsigned long addr);
+struct page *get_dump_page(unsigned long addr, int *locked);
 
 bool folio_mark_dirty(struct folio *folio);
 bool folio_mark_dirty_lock(struct folio *folio);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 47bfc6b1b632..f348e7005306 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -1044,21 +1044,23 @@ static inline pgoff_t page_pgoff(const struct folio *folio,
 	return folio->index + folio_page_idx(folio, page);
 }
 
-/*
- * Return byte-offset into filesystem object for page.
+/**
+ * folio_pos - Returns the byte position of this folio in its file.
+ * @folio: The folio.
  */
-static inline loff_t page_offset(struct page *page)
+static inline loff_t folio_pos(const struct folio *folio)
 {
-	return ((loff_t)page->index) << PAGE_SHIFT;
+	return ((loff_t)folio->index) * PAGE_SIZE;
 }
 
-/**
- * folio_pos - Returns the byte position of this folio in its file.
- * @folio: The folio.
+/*
+ * Return byte-offset into filesystem object for page.
  */
-static inline loff_t folio_pos(struct folio *folio)
+static inline loff_t page_offset(struct page *page)
 {
-	return page_offset(&folio->page);
+	struct folio *folio = page_folio(page);
+
+	return folio_pos(folio) + folio_page_idx(folio, page) * PAGE_SIZE;
 }
 
 /*
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index c6333204d451..bae4490c1dda 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1266,14 +1266,14 @@ static inline long ksys_lchown(const char __user *filename, uid_t user,
 			     AT_SYMLINK_NOFOLLOW);
 }
 
-extern long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
+int do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 
 static inline long ksys_ftruncate(unsigned int fd, loff_t length)
 {
 	return do_sys_ftruncate(fd, length, 1);
 }
 
-extern long do_sys_truncate(const char __user *pathname, loff_t length);
+int do_sys_truncate(const char __user *pathname, loff_t length);
 
 static inline long ksys_truncate(const char __user *pathname, loff_t length)
 {
diff --git a/include/linux/vfsdebug.h b/include/linux/vfsdebug.h
new file mode 100644
index 000000000000..9cf22d3eb9dd
--- /dev/null
+++ b/include/linux/vfsdebug.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_VFS_DEBUG_H
+#define LINUX_VFS_DEBUG_H 1
+
+#include <linux/bug.h>
+
+struct inode;
+
+#ifdef CONFIG_DEBUG_VFS
+void dump_inode(struct inode *inode, const char *reason);
+
+#define VFS_BUG_ON(cond) BUG_ON(cond)
+#define VFS_WARN_ON(cond) (void)WARN_ON(cond)
+#define VFS_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond)
+#define VFS_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format)
+#define VFS_WARN(cond, format...) (void)WARN(cond, format)
+
+#define VFS_BUG_ON_INODE(cond, inode)		({			\
+	if (unlikely(!!(cond))) {					\
+		dump_inode(inode, "VFS_BUG_ON_INODE(" #cond")");\
+		BUG_ON(1);						\
+	}								\
+})
+
+#define VFS_WARN_ON_INODE(cond, inode)		({			\
+	int __ret_warn = !!(cond);					\
+									\
+	if (unlikely(__ret_warn)) {					\
+		dump_inode(inode, "VFS_WARN_ON_INODE(" #cond")");\
+		WARN_ON(1);						\
+	}								\
+	unlikely(__ret_warn);						\
+})
+#else
+#define VFS_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond)
+#define VFS_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond)
+#define VFS_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
+#define VFS_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
+#define VFS_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond)
+
+#define VFS_BUG_ON_INODE(cond, inode) VFS_BUG_ON(cond)
+#define VFS_WARN_ON_INODE(cond, inode)  BUILD_BUG_ON_INVALID(cond)
+#endif /* CONFIG_DEBUG_VFS */
+
+#endif