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
  ...

Author: torvalds

Documentation/filesystems/porting.rst

@@ -1157,3 +1157,8 @@ in normal case it points into the pathname being looked up.
 NOTE: if you need something like full path from the root of filesystem,
 you are still on your own - this assists with simple cases, but it's not
 magic.
+
+---
+
+** mandatory **
+invalidate_inodes() is gone use evict_inodes() instead.

arch/arm64/kernel/elfcore.c

@@ -27,9 +27,10 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
 	int ret = 1;
 	unsigned long addr;
 	void *tags = NULL;
+	int locked = 0;
 
 	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
-		struct page *page = get_dump_page(addr);
+		struct page *page = get_dump_page(addr, &locked);
 
 		/*
 		 * get_dump_page() returns NULL when encountering an empty

arch/powerpc/platforms/pseries/papr-vpd.c

@@ -482,14 +482,13 @@ static long papr_vpd_create_handle(struct papr_location_code __user *ulc)
 		goto free_blob;
 	}
 
-	file = anon_inode_getfile("[papr-vpd]", &papr_vpd_handle_ops,
-				  (void *)blob, O_RDONLY);
+	file = anon_inode_getfile_fmode("[papr-vpd]", &papr_vpd_handle_ops,
+				  (void *)blob, O_RDONLY,
+				  FMODE_LSEEK | FMODE_PREAD);
 	if (IS_ERR(file)) {
 		err = PTR_ERR(file);
 		goto put_fd;
 	}
-
-	file->f_mode |= FMODE_LSEEK | FMODE_PREAD;
 	fd_install(fd, file);
 	return fd;
 put_fd:

drivers/vfio/group.c

@@ -266,24 +266,12 @@ static struct file *vfio_device_open_file(struct vfio_device *device)
 	if (ret)
 		goto err_free;
 
-	/*
-	 * We can't use anon_inode_getfd() because we need to modify
-	 * the f_mode flags directly to allow more than just ioctls
-	 */
-	filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
-				   df, O_RDWR);
+	filep = anon_inode_getfile_fmode("[vfio-device]", &vfio_device_fops,
+				   df, O_RDWR, FMODE_PREAD | FMODE_PWRITE);
 	if (IS_ERR(filep)) {
 		ret = PTR_ERR(filep);
 		goto err_close_device;
 	}
-
-	/*
-	 * TODO: add an anon_inode interface to do this.
-	 * Appears to be missing by lack of need rather than
-	 * explicitly prevented.  Now there's need.
-	 */
-	filep->f_mode |= (FMODE_PREAD | FMODE_PWRITE);
-
 	/*
 	 * Use the pseudo fs inode on the device to link all mmaps
 	 * to the same address space, allowing us to unmap all vmas

fs/autofs/dev-ioctl.c

@@ -442,7 +442,6 @@ static int autofs_dev_ioctl_timeout(struct file *fp,
 		sbi->exp_timeout = timeout * HZ;
 	} else {
 		struct dentry *base = fp->f_path.dentry;
-		struct inode *inode = base->d_inode;
 		int path_len = param->size - AUTOFS_DEV_IOCTL_SIZE - 1;
 		struct dentry *dentry;
 		struct autofs_info *ino;
@@ -460,9 +459,7 @@ static int autofs_dev_ioctl_timeout(struct file *fp,
 				"the parent autofs mount timeout which could "
 				"prevent shutdown\n");
 
-		inode_lock_shared(inode);
 		dentry = try_lookup_one_len(param->path, base, path_len);
-		inode_unlock_shared(inode);
 		if (IS_ERR_OR_NULL(dentry))
 			return dentry ? PTR_ERR(dentry) : -ENOENT;
 		ino = autofs_dentry_ino(dentry);

fs/cachefiles/ondemand.c

@@ -317,8 +317,9 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req,
 		goto err_free_id;
 	}
 
-	anon_file->file = anon_inode_getfile("[cachefiles]",
-				&cachefiles_ondemand_fd_fops, object, O_WRONLY);
+	anon_file->file = anon_inode_getfile_fmode("[cachefiles]",
+				&cachefiles_ondemand_fd_fops, object,
+				O_WRONLY, FMODE_PWRITE | FMODE_LSEEK);
 	if (IS_ERR(anon_file->file)) {
 		ret = PTR_ERR(anon_file->file);
 		goto err_put_fd;
@@ -333,8 +334,6 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req,
 		goto err_put_file;
 	}
 
-	anon_file->file->f_mode |= FMODE_PWRITE | FMODE_LSEEK;
-
 	load = (void *)req->msg.data;
 	load->fd = anon_file->fd;
 	object->ondemand->ondemand_id = object_id;

fs/coredump.c

@@ -926,36 +926,62 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start,
 {
 	unsigned long addr;
 	struct page *dump_page;
+	int locked, ret;
 
 	dump_page = dump_page_alloc();
 	if (!dump_page)
 		return 0;
 
+	ret = 0;
+	locked = 0;
 	for (addr = start; addr < start + len; addr += PAGE_SIZE) {
 		struct page *page;
 
+		if (!locked) {
+			if (mmap_read_lock_killable(current->mm))
+				goto out;
+			locked = 1;
+		}
+
 		/*
 		 * To avoid having to allocate page tables for virtual address
 		 * ranges that have never been used yet, and also to make it
 		 * easy to generate sparse core files, use a helper that returns
 		 * NULL when encountering an empty page table entry that would
 		 * otherwise have been filled with the zero page.
 		 */
-		page = get_dump_page(addr);
+		page = get_dump_page(addr, &locked);
 		if (page) {
+			if (locked) {
+				mmap_read_unlock(current->mm);
+				locked = 0;
+			}
 			int stop = !dump_emit_page(cprm, dump_page_copy(page, dump_page));
 			put_page(page);
-			if (stop) {
-				dump_page_free(dump_page);
-				return 0;
-			}
+			if (stop)
+				goto out;
 		} else {
 			dump_skip(cprm, PAGE_SIZE);
 		}
+
+		if (dump_interrupted())
+			goto out;
+
+		if (!need_resched())
+			continue;
+		if (locked) {
+			mmap_read_unlock(current->mm);
+			locked = 0;
+		}
 		cond_resched();
 	}
+	ret = 1;
+out:
+	if (locked)
+		mmap_read_unlock(current->mm);
+
 	dump_page_free(dump_page);
-	return 1;
+	return ret;
 }
 #endif
 

fs/dcache.c

@@ -2480,7 +2480,8 @@ static inline void end_dir_add(struct inode *dir, unsigned int n,
 {
 	smp_store_release(&dir->i_dir_seq, n + 2);
 	preempt_enable_nested();
-	wake_up_all(d_wait);
+	if (wq_has_sleeper(d_wait))
+		wake_up_all(d_wait);
 }
 
 static void d_wait_lookup(struct dentry *dentry)

fs/ecryptfs/super.c

@@ -172,7 +172,6 @@ const struct super_operations ecryptfs_sops = {
 	.destroy_inode = ecryptfs_destroy_inode,
 	.free_inode = ecryptfs_free_inode,
 	.statfs = ecryptfs_statfs,
-	.remount_fs = NULL,
 	.evict_inode = ecryptfs_evict_inode,
 	.show_options = ecryptfs_show_options
 };

fs/eventfd.c

@@ -406,14 +406,13 @@ static int do_eventfd(unsigned int count, int flags)
 	if (fd < 0)
 		goto err;
 
-	file = anon_inode_getfile("[eventfd]", &eventfd_fops, ctx, flags);
+	file = anon_inode_getfile_fmode("[eventfd]", &eventfd_fops,
+					ctx, flags, FMODE_NOWAIT);
 	if (IS_ERR(file)) {
 		put_unused_fd(fd);
 		fd = PTR_ERR(file);
 		goto err;
 	}
-
-	file->f_mode |= FMODE_NOWAIT;
 	fd_install(fd, file);
 	return fd;
 err: