Merge tag 'vfs-7.0-rc1.misc.2' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull more misc vfs updates from Christian Brauner:
 "Features:

   - Optimize close_range() from O(range size) to O(active FDs) by using
     find_next_bit() on the open_fds bitmap instead of linearly scanning
     the entire requested range. This is a significant improvement for
     large-range close operations on sparse file descriptor tables.

   - Add FS_XFLAG_VERITY file attribute for fs-verity files, retrievable
     via FS_IOC_FSGETXATTR and file_getattr(). The flag is read-only.
     Add tracepoints for fs-verity enable and verify operations,
     replacing the previously removed debug printk's.

   - Prevent nfsd from exporting special kernel filesystems like pidfs
     and nsfs. These filesystems have custom ->open() and ->permission()
     export methods that are designed for open_by_handle_at(2) only and
     are incompatible with nfsd. Update the exportfs documentation
     accordingly.

  Fixes:

   - Fix KMSAN uninit-value in ovl_fill_real() where strcmp() was used
     on a non-null-terminated decrypted directory entry name from
     fscrypt. This triggered on encrypted lower layers when the
     decrypted name buffer contained uninitialized tail data.

     The fix also adds VFS-level name_is_dot(), name_is_dotdot(), and
     name_is_dot_dotdot() helpers, replacing various open-coded "." and
     ".." checks across the tree.

   - Fix read-only fsflags not being reset together with xflags in
     vfs_fileattr_set(). Currently harmless since no read-only xflags
     overlap with flags, but this would cause inconsistencies for any
     future shared read-only flag

   - Return -EREMOTE instead of -ESRCH from PIDFD_GET_INFO when the
     target process is in a different pid namespace. This lets userspace
     distinguish "process exited" from "process in another namespace",
     matching glibc's pidfd_getpid() behavior

  Cleanups:

   - Use C-string literals in the Rust seq_file bindings, replacing the
     kernel::c_str!() macro (available since Rust 1.77)

   - Fix typo in d_walk_ret enum comment, add porting notes for the
     readlink_copy() calling convention change"

* tag 'vfs-7.0-rc1.misc.2' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  fs: add porting notes about readlink_copy()
  pidfs: return -EREMOTE when PIDFD_GET_INFO is called on another ns
  nfsd: do not allow exporting of special kernel filesystems
  exportfs: clarify the documentation of open()/permission() expotrfs ops
  fsverity: add tracepoints
  fs: add FS_XFLAG_VERITY for fs-verity files
  rust: seq_file: replace `kernel::c_str!` with C-Strings
  fs: dcache: fix typo in enum d_walk_ret comment
  ovl: use name_is_dot* helpers in readdir code
  fs: add helpers name_is_dot{,dot,_dotdot}
  ovl: Fix uninit-value in ovl_fill_real
  fs: reset read-only fsflags together with xflags
  fs/file: optimize close_range() complexity from O(N) to O(Sparse)

17 files changed, 64 insertions, 48 deletions

diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index a9a4432d12ba..629eb0d72e86 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -76,7 +76,7 @@ struct fscrypt_nokey_name {
 
 static inline bool fscrypt_is_dot_dotdot(const struct qstr *str)
 {
-	return is_dot_dotdot(str->name, str->len);
+	return name_is_dot_dotdot(str->name, str->len);
 }
 
 /**
diff --git a/fs/dcache.c b/fs/dcache.c
index 2758fe7322d4..7ba1801d8132 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1298,8 +1298,8 @@ void shrink_dcache_sb(struct super_block *sb)
 EXPORT_SYMBOL(shrink_dcache_sb);
 
 /**
- * enum d_walk_ret - action to talke during tree walk
- * @D_WALK_CONTINUE:	contrinue walk
+ * enum d_walk_ret - action to take during tree walk
+ * @D_WALK_CONTINUE:	continue walk
  * @D_WALK_QUIT:	quit walk
  * @D_WALK_NORETRY:	quit when retry is needed
  * @D_WALK_SKIP:	skip this dentry and its children
@@ -1722,7 +1722,7 @@ void d_invalidate(struct dentry *dentry)
 EXPORT_SYMBOL(d_invalidate);
 
 /**
- * __d_alloc	-	allocate a dcache entry
+ * __d_alloc - allocate a dcache entry
  * @sb: filesystem it will belong to
  * @name: qstr of the name
  *
@@ -1806,7 +1806,7 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 }
 
 /**
- * d_alloc	-	allocate a dcache entry
+ * d_alloc - allocate a dcache entry
  * @parent: parent of entry to allocate
  * @name: qstr of the name
  *
@@ -2546,7 +2546,7 @@ static void __d_rehash(struct dentry *entry)
 }
 
 /**
- * d_rehash	- add an entry back to the hash
+ * d_rehash - add an entry back to the hash
  * @entry: dentry to add to the hash
  *
  * Adds a dentry to the hash according to its name.
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 260f8a4938b0..3c89f06c7453 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1904,7 +1904,7 @@ int ecryptfs_decode_and_decrypt_filename(char **plaintext_name,
 
 	if ((mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) &&
 	    !(mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)) {
-		if (is_dot_dotdot(name, name_size)) {
+		if (name_is_dot_dotdot(name, name_size)) {
 			rc = ecryptfs_copy_filename(plaintext_name,
 						    plaintext_name_size,
 						    name, name_size);
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index d3e55de4a2a2..6c9be60a3e48 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -253,7 +253,8 @@ static bool filldir_one(struct dir_context *ctx, const char *name, int len,
 		container_of(ctx, struct getdents_callback, ctx);
 
 	buf->sequence++;
-	if (buf->ino == ino && len <= NAME_MAX && !is_dot_dotdot(name, len)) {
+	if (buf->ino == ino && len <= NAME_MAX &&
+	    !name_is_dot_dotdot(name, len)) {
 		memcpy(buf->name, name, len);
 		buf->name[len] = '\0';
 		buf->found = 1;
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index be70dfb3b152..f70092e231f0 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -68,7 +68,7 @@ int f2fs_init_casefolded_name(const struct inode *dir,
 	int len;
 
 	if (IS_CASEFOLDED(dir) &&
-	    !is_dot_dotdot(fname->usr_fname->name, fname->usr_fname->len)) {
+	    !name_is_dot_dotdot(fname->usr_fname->name, fname->usr_fname->len)) {
 		buf = f2fs_kmem_cache_alloc(f2fs_cf_name_slab,
 					    GFP_NOFS, false, F2FS_SB(sb));
 		if (!buf)
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index 049ce50cec9b..14082fe5e6b2 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -100,7 +100,7 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname)
 
 	WARN_ON_ONCE(!name);
 
-	if (is_dot_dotdot(name, len)) {
+	if (name_is_dot_dotdot(name, len)) {
 		fname->hash = 0;
 		return;
 	}
diff --git a/fs/file.c b/fs/file.c
index 0a4f3bdb2dec..51ddcff0081a 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -777,23 +777,29 @@ static inline void __range_close(struct files_struct *files, unsigned int fd,
 				 unsigned int max_fd)
 {
 	struct file *file;
+	struct fdtable *fdt;
 	unsigned n;
 
 	spin_lock(&files->file_lock);
-	n = last_fd(files_fdtable(files));
+	fdt = files_fdtable(files);
+	n = last_fd(fdt);
 	max_fd = min(max_fd, n);
 
-	for (; fd <= max_fd; fd++) {
+	for (fd = find_next_bit(fdt->open_fds, max_fd + 1, fd);
+	     fd <= max_fd;
+	     fd = find_next_bit(fdt->open_fds, max_fd + 1, fd + 1)) {
 		file = file_close_fd_locked(files, fd);
 		if (file) {
 			spin_unlock(&files->file_lock);
 			filp_close(file, files);
 			cond_resched();
 			spin_lock(&files->file_lock);
+			fdt = files_fdtable(files);
 		} else if (need_resched()) {
 			spin_unlock(&files->file_lock);
 			cond_resched();
 			spin_lock(&files->file_lock);
+			fdt = files_fdtable(files);
 		}
 	}
 	spin_unlock(&files->file_lock);
diff --git a/fs/file_attr.c b/fs/file_attr.c
index 42721427245a..6d2a298a786d 100644
--- a/fs/file_attr.c
+++ b/fs/file_attr.c
@@ -37,6 +37,8 @@ void fileattr_fill_xflags(struct file_kattr *fa, u32 xflags)
 		fa->flags |= FS_DAX_FL;
 	if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT)
 		fa->flags |= FS_PROJINHERIT_FL;
+	if (fa->fsx_xflags & FS_XFLAG_VERITY)
+		fa->flags |= FS_VERITY_FL;
 }
 EXPORT_SYMBOL(fileattr_fill_xflags);
 
@@ -67,6 +69,8 @@ void fileattr_fill_flags(struct file_kattr *fa, u32 flags)
 		fa->fsx_xflags |= FS_XFLAG_DAX;
 	if (fa->flags & FS_PROJINHERIT_FL)
 		fa->fsx_xflags |= FS_XFLAG_PROJINHERIT;
+	if (fa->flags & FS_VERITY_FL)
+		fa->fsx_xflags |= FS_XFLAG_VERITY;
 }
 EXPORT_SYMBOL(fileattr_fill_flags);
 
@@ -142,8 +146,7 @@ static int file_attr_to_fileattr(const struct file_attr *fattr,
 	if (fattr->fa_xflags & ~mask)
 		return -EINVAL;
 
-	fileattr_fill_xflags(fa, fattr->fa_xflags);
-	fa->fsx_xflags &= ~FS_XFLAG_RDONLY_MASK;
+	fileattr_fill_xflags(fa, fattr->fa_xflags & ~FS_XFLAG_RDONLY_MASK);
 	fa->fsx_extsize = fattr->fa_extsize;
 	fa->fsx_projid = fattr->fa_projid;
 	fa->fsx_cowextsize = fattr->fa_cowextsize;
@@ -163,8 +166,7 @@ static int copy_fsxattr_from_user(struct file_kattr *fa,
 	if (xfa.fsx_xflags & ~mask)
 		return -EOPNOTSUPP;
 
-	fileattr_fill_xflags(fa, xfa.fsx_xflags);
-	fa->fsx_xflags &= ~FS_XFLAG_RDONLY_MASK;
+	fileattr_fill_xflags(fa, xfa.fsx_xflags & ~FS_XFLAG_RDONLY_MASK);
 	fa->fsx_extsize = xfa.fsx_extsize;
 	fa->fsx_nextents = xfa.fsx_nextents;
 	fa->fsx_projid = xfa.fsx_projid;
diff --git a/fs/namei.c b/fs/namei.c
index 8e7792de0000..5fe6cac48df8 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3088,7 +3088,7 @@ int lookup_noperm_common(struct qstr *qname, struct dentry *base)
 	if (!len)
 		return -EACCES;
 
-	if (is_dot_dotdot(name, len))
+	if (name_is_dot_dotdot(name, len))
 		return -EACCES;
 
 	while (len--) {
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 2a1499f2ad19..09fe268fe2c7 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -427,7 +427,8 @@ static int check_export(const struct path *path, int *flags, unsigned char *uuid
 	 *       either a device number (so FS_REQUIRES_DEV needed)
 	 *       or an FSID number (so NFSEXP_FSID or ->uuid is needed).
 	 * 2:  We must be able to find an inode from a filehandle.
-	 *       This means that s_export_op must be set.
+	 *       This means that s_export_op must be set and comply with
+	 *       the requirements for remote filesystem export.
 	 * 3: We must not currently be on an idmapped mount.
 	 */
 	if (!(inode->i_sb->s_type->fs_flags & FS_REQUIRES_DEV) &&
@@ -437,8 +438,9 @@ static int check_export(const struct path *path, int *flags, unsigned char *uuid
 		return -EINVAL;
 	}
 
-	if (!exportfs_can_decode_fh(inode->i_sb->s_export_op)) {
-		dprintk("exp_export: export of invalid fs type.\n");
+	if (!exportfs_may_export(inode->i_sb->s_export_op)) {
+		dprintk("exp_export: export of invalid fs type (%s).\n",
+			inode->i_sb->s_type->name);
 		return -EINVAL;
 	}
 
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 7fd415d7471e..bb09142b4e15 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -77,7 +77,8 @@ static int ovl_casefold(struct ovl_readdir_data *rdd, const char *str, int len,
 	char *cf_name;
 	int cf_len;
 
-	if (!IS_ENABLED(CONFIG_UNICODE) || !rdd->map || is_dot_dotdot(str, len))
+	if (!IS_ENABLED(CONFIG_UNICODE) || !rdd->map ||
+	    name_is_dot_dotdot(str, len))
 		return 0;
 
 	cf_name = kmalloc(NAME_MAX, GFP_KERNEL);
@@ -154,7 +155,7 @@ static bool ovl_calc_d_ino(struct ovl_readdir_data *rdd,
 		return true;
 
 	/* Always recalc d_ino for parent */
-	if (strcmp(p->name, "..") == 0)
+	if (name_is_dotdot(p->name, p->len))
 		return true;
 
 	/* If this is lower, then native d_ino will do */
@@ -165,7 +166,7 @@ static bool ovl_calc_d_ino(struct ovl_readdir_data *rdd,
 	 * Recalc d_ino for '.' and for all entries if dir is impure (contains
 	 * copied up entries)
 	 */
-	if ((p->name[0] == '.' && p->len == 1) ||
+	if (name_is_dot(p->name, p->len) ||
 	    ovl_test_flag(OVL_IMPURE, d_inode(rdd->dentry)))
 		return true;
 
@@ -561,12 +562,12 @@ static int ovl_cache_update(const struct path *path, struct ovl_cache_entry *p,
 	if (!ovl_same_dev(ofs) && !p->check_xwhiteout)
 		goto out;
 
-	if (p->name[0] == '.') {
+	if (name_is_dot_dotdot(p->name, p->len)) {
 		if (p->len == 1) {
 			this = dget(dir);
 			goto get;
 		}
-		if (p->len == 2 && p->name[1] == '.') {
+		if (p->len == 2) {
 			/* we shall not be moved */
 			this = dget(dir->d_parent);
 			goto get;
@@ -666,8 +667,7 @@ static int ovl_dir_read_impure(const struct path *path,  struct list_head *list,
 		return err;
 
 	list_for_each_entry_safe(p, n, list, l_node) {
-		if (strcmp(p->name, ".") != 0 &&
-		    strcmp(p->name, "..") != 0) {
+		if (!name_is_dot_dotdot(p->name, p->len)) {
 			err = ovl_cache_update(path, p, true);
 			if (err)
 				return err;
@@ -756,7 +756,7 @@ static bool ovl_fill_real(struct dir_context *ctx, const char *name,
 	struct dir_context *orig_ctx = rdt->orig_ctx;
 	bool res;
 
-	if (rdt->parent_ino && strcmp(name, "..") == 0) {
+	if (rdt->parent_ino && name_is_dotdot(name, namelen)) {
 		ino = rdt->parent_ino;
 	} else if (rdt->cache) {
 		struct ovl_cache_entry *p;
@@ -1098,12 +1098,8 @@ int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
 			goto del_entry;
 		}
 
-		if (p->name[0] == '.') {
-			if (p->len == 1)
-				goto del_entry;
-			if (p->len == 2 && p->name[1] == '.')
-				goto del_entry;
-		}
+		if (name_is_dot_dotdot(p->name, p->len))
+			goto del_entry;
 		err = -ENOTEMPTY;
 		break;
 
@@ -1147,7 +1143,7 @@ static bool ovl_check_d_type(struct dir_context *ctx, const char *name,
 		container_of(ctx, struct ovl_readdir_data, ctx);
 
 	/* Even if d_type is not supported, DT_DIR is returned for . and .. */
-	if (!strncmp(name, ".", namelen) || !strncmp(name, "..", namelen))
+	if (name_is_dot_dotdot(name, namelen))
 		return true;
 
 	if (d_type != DT_UNKNOWN)
@@ -1210,11 +1206,8 @@ static int ovl_workdir_cleanup_recurse(struct ovl_fs *ofs, const struct path *pa
 	list_for_each_entry(p, &list, l_node) {
 		struct dentry *dentry;
 
-		if (p->name[0] == '.') {
-			if (p->len == 1)
-				continue;
-			if (p->len == 2 && p->name[1] == '.')
-				continue;
+		if (name_is_dot_dotdot(p->name, p->len)) {
+			continue;
 		} else if (incompat) {
 			pr_err("overlay with incompat feature '%s' cannot be mounted\n",
 				p->name);
@@ -1279,12 +1272,8 @@ int ovl_indexdir_cleanup(struct ovl_fs *ofs)
 		goto out;
 
 	list_for_each_entry(p, &list, l_node) {
-		if (p->name[0] == '.') {
-			if (p->len == 1)
-				continue;
-			if (p->len == 2 && p->name[1] == '.')
-				continue;
-		}
+		if (name_is_dot_dotdot(p->name, p->len))
+			continue;
 		index = ovl_lookup_upper_unlocked(ofs, p->name, indexdir, p->len);
 		if (IS_ERR(index)) {
 			err = PTR_ERR(index);
diff --git a/fs/pidfs.c b/fs/pidfs.c
index 3ffa5e4707de..318253344b5c 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -360,7 +360,7 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg)
 	 * namespace hierarchy.
 	 */
 	if (!pid_in_current_pidns(pid))
-		return -ESRCH;
+		return -EREMOTE;
 
 	attr = READ_ONCE(pid->attr);
 	if (mask & PIDFD_INFO_EXIT) {
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index fbdc854dba0f..d08973b288e5 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -1044,7 +1044,7 @@ static bool __dir_empty(struct dir_context *ctx, const char *name, int namlen,
 	struct ksmbd_readdir_data *buf;
 
 	buf = container_of(ctx, struct ksmbd_readdir_data, ctx);
-	if (!is_dot_dotdot(name, namlen))
+	if (!name_is_dot_dotdot(name, namlen))
 		buf->dirent_count++;
 
 	return !buf->dirent_count;
diff --git a/fs/verity/enable.c b/fs/verity/enable.c
index c9448074cce1..42dfed1ce0ce 100644
--- a/fs/verity/enable.c
+++ b/fs/verity/enable.c
@@ -223,6 +223,8 @@ static int enable_verity(struct file *filp,
 	if (err)
 		goto out;
 
+	trace_fsverity_enable(inode, &params);
+
 	/*
 	 * Start enabling verity on this file, serialized by the inode lock.
 	 * Fail if verity is already enabled or is already being enabled.
@@ -265,6 +267,8 @@ static int enable_verity(struct file *filp,
 		goto rollback;
 	}
 
+	trace_fsverity_tree_done(inode, vi, &params);
+
 	/*
 	 * Add the fsverity_info into the hash table before finishing the
 	 * initialization so that we don't have to undo the enabling when memory
diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h
index 2887cb849cec..6e6854c19078 100644
--- a/fs/verity/fsverity_private.h
+++ b/fs/verity/fsverity_private.h
@@ -163,4 +163,6 @@ static inline void fsverity_init_signature(void)
 
 void __init fsverity_init_workqueue(void);
 
+#include <trace/events/fsverity.h>
+
 #endif /* _FSVERITY_PRIVATE_H */
diff --git a/fs/verity/init.c b/fs/verity/init.c
index 6e8d33b50240..d65206608583 100644
--- a/fs/verity/init.c
+++ b/fs/verity/init.c
@@ -5,6 +5,7 @@
  * Copyright 2019 Google LLC
  */
 
+#define CREATE_TRACE_POINTS
 #include "fsverity_private.h"
 
 #include <linux/ratelimit.h>
diff --git a/fs/verity/verify.c b/fs/verity/verify.c
index 31797f9b24d0..404ab68aaf9b 100644
--- a/fs/verity/verify.c
+++ b/fs/verity/verify.c
@@ -177,6 +177,9 @@ static bool verify_data_block(struct fsverity_info *vi,
 		/* Byte offset of the wanted hash relative to @addr */
 		unsigned int hoffset;
 	} hblocks[FS_VERITY_MAX_LEVELS];
+
+	trace_fsverity_verify_data_block(inode, params, data_pos);
+
 	/*
 	 * The index of the previous level's block within that level; also the
 	 * index of that block's hash within the current level.
@@ -255,6 +258,9 @@ static bool verify_data_block(struct fsverity_info *vi,
 			want_hash = _want_hash;
 			kunmap_local(haddr);
 			put_page(hpage);
+			trace_fsverity_merkle_hit(inode, data_pos, hblock_idx,
+					level,
+					hoffset >> params->log_digestsize);
 			goto descend;
 		}
 		hblocks[level].page = hpage;
@@ -273,6 +279,9 @@ descend:
 		unsigned long hblock_idx = hblocks[level - 1].index;
 		unsigned int hoffset = hblocks[level - 1].hoffset;
 
+		trace_fsverity_verify_merkle_block(inode, hblock_idx,
+				level, hoffset >> params->log_digestsize);
+
 		fsverity_hash_block(params, haddr, real_hash);
 		if (memcmp(want_hash, real_hash, hsize) != 0)
 			goto corrupted;