summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--fs/attr.c2
-rw-r--r--fs/binfmt_elf.c2
-rw-r--r--fs/binfmt_elf_fdpic.c5
-rw-r--r--fs/binfmt_misc.c7
-rw-r--r--fs/dcache.c30
-rw-r--r--fs/exec.c14
-rw-r--r--fs/exportfs/expfs.c9
-rw-r--r--fs/f2fs/acl.c3
-rw-r--r--fs/f2fs/file.c6
-rw-r--r--fs/fhandle.c178
-rw-r--r--fs/fsopen.c7
-rw-r--r--fs/fuse/acl.c4
-rw-r--r--fs/hfs/inode.c3
-rw-r--r--fs/hfsplus/bfind.c15
-rw-r--r--fs/hfsplus/extents.c9
-rw-r--r--fs/hfsplus/hfsplus_fs.h21
-rw-r--r--fs/hfsplus/ioctl.c4
-rw-r--r--fs/inode.c1
-rw-r--r--fs/internal.h14
-rw-r--r--fs/mount.h1
-rw-r--r--fs/namei.c98
-rw-r--r--fs/namespace.c74
-rw-r--r--fs/nfsd/nfsfh.c2
-rw-r--r--fs/open.c17
-rw-r--r--fs/proc/generic.c6
-rw-r--r--fs/quota/dquot.c8
-rw-r--r--fs/readdir.c4
-rw-r--r--fs/stat.c172
-rw-r--r--include/linux/dcache.h2
-rw-r--r--include/linux/exportfs.h2
-rw-r--r--include/linux/fs.h85
-rw-r--r--include/linux/namei.h8
-rw-r--r--io_uring/statx.c3
-rw-r--r--io_uring/xattr.c4
-rw-r--r--ipc/mqueue.c3
-rw-r--r--kernel/fork.c26
-rw-r--r--mm/khugepaged.c10
-rw-r--r--mm/shmem.c9
38 files changed, 539 insertions, 329 deletions
diff --git a/fs/attr.c b/fs/attr.c
index 960a310581eb..825007d5cda4 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -17,8 +17,6 @@
#include <linux/filelock.h>
#include <linux/security.h>
-#include "internal.h"
-
/**
* setattr_should_drop_sgid - determine whether the setgid bit needs to be
* removed
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index a43897b03ce9..6fdec541f8bf 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1216,7 +1216,6 @@ out_free_interp:
}
reloc_func_desc = interp_load_addr;
- allow_write_access(interpreter);
fput(interpreter);
kfree(interp_elf_ex);
@@ -1308,7 +1307,6 @@ out_free_dentry:
kfree(interp_elf_ex);
kfree(interp_elf_phdata);
out_free_file:
- allow_write_access(interpreter);
if (interpreter)
fput(interpreter);
out_free_ph:
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index b799701454a9..28a3439f163a 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -394,7 +394,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
goto error;
}
- allow_write_access(interpreter);
fput(interpreter);
interpreter = NULL;
}
@@ -466,10 +465,8 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
retval = 0;
error:
- if (interpreter) {
- allow_write_access(interpreter);
+ if (interpreter)
fput(interpreter);
- }
kfree(interpreter_name);
kfree(exec_params.phdrs);
kfree(exec_params.loadmap);
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 68fa225f89e5..21ce5ec1ea76 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -247,13 +247,10 @@ static int load_misc_binary(struct linux_binprm *bprm)
if (retval < 0)
goto ret;
- if (fmt->flags & MISC_FMT_OPEN_FILE) {
+ if (fmt->flags & MISC_FMT_OPEN_FILE)
interp_file = file_clone_open(fmt->interp_file);
- if (!IS_ERR(interp_file))
- deny_write_access(interp_file);
- } else {
+ else
interp_file = open_exec(fmt->interpreter);
- }
retval = PTR_ERR(interp_file);
if (IS_ERR(interp_file))
goto ret;
diff --git a/fs/dcache.c b/fs/dcache.c
index 5f9ffe5c9917..8bdc278a0205 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1555,7 +1555,7 @@ void shrink_dcache_for_umount(struct super_block *sb)
{
struct dentry *dentry;
- WARN(down_read_trylock(&sb->s_umount), "s_umount should've been locked");
+ rwsem_assert_held_write(&sb->s_umount);
dentry = sb->s_root;
sb->s_root = NULL;
@@ -3106,6 +3106,34 @@ void d_tmpfile(struct file *file, struct inode *inode)
}
EXPORT_SYMBOL(d_tmpfile);
+/*
+ * Obtain inode number of the parent dentry.
+ */
+ino_t d_parent_ino(struct dentry *dentry)
+{
+ struct dentry *parent;
+ struct inode *iparent;
+ unsigned seq;
+ ino_t ret;
+
+ scoped_guard(rcu) {
+ seq = raw_seqcount_begin(&dentry->d_seq);
+ parent = READ_ONCE(dentry->d_parent);
+ iparent = d_inode_rcu(parent);
+ if (likely(iparent)) {
+ ret = iparent->i_ino;
+ if (!read_seqcount_retry(&dentry->d_seq, seq))
+ return ret;
+ }
+ }
+
+ spin_lock(&dentry->d_lock);
+ ret = dentry->d_parent->d_inode->i_ino;
+ spin_unlock(&dentry->d_lock);
+ return ret;
+}
+EXPORT_SYMBOL(d_parent_ino);
+
static __initdata unsigned long dhash_entries;
static int __init set_dhash_entries(char *str)
{
diff --git a/fs/exec.c b/fs/exec.c
index 40073142288f..4dee205452e2 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -952,10 +952,6 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
path_noexec(&file->f_path)))
goto exit;
- err = deny_write_access(file);
- if (err)
- goto exit;
-
out:
return file;
@@ -971,8 +967,7 @@ exit:
*
* Returns ERR_PTR on failure or allocated struct file on success.
*
- * As this is a wrapper for the internal do_open_execat(), callers
- * must call allow_write_access() before fput() on release. Also see
+ * As this is a wrapper for the internal do_open_execat(). Also see
* do_close_execat().
*/
struct file *open_exec(const char *name)
@@ -1524,10 +1519,8 @@ static int prepare_bprm_creds(struct linux_binprm *bprm)
/* Matches do_open_execat() */
static void do_close_execat(struct file *file)
{
- if (!file)
- return;
- allow_write_access(file);
- fput(file);
+ if (file)
+ fput(file);
}
static void free_bprm(struct linux_binprm *bprm)
@@ -1846,7 +1839,6 @@ static int exec_binprm(struct linux_binprm *bprm)
bprm->file = bprm->interpreter;
bprm->interpreter = NULL;
- allow_write_access(exec);
if (unlikely(bprm->have_execfd)) {
if (bprm->executable) {
fput(exec);
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 07ea3d62b298..4f2dd4ab4486 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -427,7 +427,7 @@ EXPORT_SYMBOL_GPL(exportfs_encode_fh);
struct dentry *
exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len,
- int fileid_type,
+ int fileid_type, unsigned int flags,
int (*acceptable)(void *, struct dentry *),
void *context)
{
@@ -445,6 +445,11 @@ exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len,
if (IS_ERR_OR_NULL(result))
return result;
+ if ((flags & EXPORT_FH_DIR_ONLY) && !d_is_dir(result)) {
+ err = -ENOTDIR;
+ goto err_result;
+ }
+
/*
* If no acceptance criteria was specified by caller, a disconnected
* dentry is also accepatable. Callers may use this mode to query if
@@ -581,7 +586,7 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
{
struct dentry *ret;
- ret = exportfs_decode_fh_raw(mnt, fid, fh_len, fileid_type,
+ ret = exportfs_decode_fh_raw(mnt, fid, fh_len, fileid_type, 0,
acceptable, context);
if (IS_ERR_OR_NULL(ret)) {
if (ret == ERR_PTR(-ENOMEM))
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index ec2aeccb69a3..8bffdeccdbc3 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -219,8 +219,7 @@ static int f2fs_acl_update_mode(struct mnt_idmap *idmap,
return error;
if (error == 0)
*acl = NULL;
- if (!vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode)) &&
- !capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID))
+ if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode)))
mode &= ~S_ISGID;
*mode_p = mode;
return 0;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 5c0b281a70f3..c1ad9b278c47 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -185,7 +185,7 @@ static int get_parent_ino(struct inode *inode, nid_t *pino)
if (!dentry)
return 0;
- *pino = parent_ino(dentry);
+ *pino = d_parent_ino(dentry);
dput(dentry);
return 1;
}
@@ -923,10 +923,8 @@ static void __setattr_copy(struct mnt_idmap *idmap,
inode_set_ctime_to_ts(inode, attr->ia_ctime);
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
- vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode);
- if (!vfsgid_in_group_p(vfsgid) &&
- !capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID))
+ if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode)))
mode &= ~S_ISGID;
set_acl_inode(inode, mode);
}
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 8a7f86c2139a..6e8cea16790e 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -115,88 +115,188 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
return err;
}
-static struct vfsmount *get_vfsmount_from_fd(int fd)
+static int get_path_from_fd(int fd, struct path *root)
{
- struct vfsmount *mnt;
-
if (fd == AT_FDCWD) {
struct fs_struct *fs = current->fs;
spin_lock(&fs->lock);
- mnt = mntget(fs->pwd.mnt);
+ *root = fs->pwd;
+ path_get(root);
spin_unlock(&fs->lock);
} else {
struct fd f = fdget(fd);
if (!f.file)
- return ERR_PTR(-EBADF);
- mnt = mntget(f.file->f_path.mnt);
+ return -EBADF;
+ *root = f.file->f_path;
+ path_get(root);
fdput(f);
}
- return mnt;
+
+ return 0;
}
+enum handle_to_path_flags {
+ HANDLE_CHECK_PERMS = (1 << 0),
+ HANDLE_CHECK_SUBTREE = (1 << 1),
+};
+
+struct handle_to_path_ctx {
+ struct path root;
+ enum handle_to_path_flags flags;
+ unsigned int fh_flags;
+};
+
static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
{
- return 1;
+ struct handle_to_path_ctx *ctx = context;
+ struct user_namespace *user_ns = current_user_ns();
+ struct dentry *d, *root = ctx->root.dentry;
+ struct mnt_idmap *idmap = mnt_idmap(ctx->root.mnt);
+ int retval = 0;
+
+ if (!root)
+ return 1;
+
+ /* Old permission model with global CAP_DAC_READ_SEARCH. */
+ if (!ctx->flags)
+ return 1;
+
+ /*
+ * It's racy as we're not taking rename_lock but we're able to ignore
+ * permissions and we just need an approximation whether we were able
+ * to follow a path to the file.
+ *
+ * It's also potentially expensive on some filesystems especially if
+ * there is a deep path.
+ */
+ d = dget(dentry);
+ while (d != root && !IS_ROOT(d)) {
+ struct dentry *parent = dget_parent(d);
+
+ /*
+ * We know that we have the ability to override DAC permissions
+ * as we've verified this earlier via CAP_DAC_READ_SEARCH. But
+ * we also need to make sure that there aren't any unmapped
+ * inodes in the path that would prevent us from reaching the
+ * file.
+ */
+ if (!privileged_wrt_inode_uidgid(user_ns, idmap,
+ d_inode(parent))) {
+ dput(d);
+ dput(parent);
+ return retval;
+ }
+
+ dput(d);
+ d = parent;
+ }
+
+ if (!(ctx->flags & HANDLE_CHECK_SUBTREE) || d == root)
+ retval = 1;
+ WARN_ON_ONCE(d != root && d != root->d_sb->s_root);
+ dput(d);
+ return retval;
}
-static int do_handle_to_path(int mountdirfd, struct file_handle *handle,
- struct path *path)
+static int do_handle_to_path(struct file_handle *handle, struct path *path,
+ struct handle_to_path_ctx *ctx)
{
- int retval = 0;
int handle_dwords;
+ struct vfsmount *mnt = ctx->root.mnt;
- path->mnt = get_vfsmount_from_fd(mountdirfd);
- if (IS_ERR(path->mnt)) {
- retval = PTR_ERR(path->mnt);
- goto out_err;
- }
/* change the handle size to multiple of sizeof(u32) */
handle_dwords = handle->handle_bytes >> 2;
- path->dentry = exportfs_decode_fh(path->mnt,
+ path->dentry = exportfs_decode_fh_raw(mnt,
(struct fid *)handle->f_handle,
handle_dwords, handle->handle_type,
- vfs_dentry_acceptable, NULL);
- if (IS_ERR(path->dentry)) {
- retval = PTR_ERR(path->dentry);
- goto out_mnt;
+ ctx->fh_flags,
+ vfs_dentry_acceptable, ctx);
+ if (IS_ERR_OR_NULL(path->dentry)) {
+ if (path->dentry == ERR_PTR(-ENOMEM))
+ return -ENOMEM;
+ return -ESTALE;
}
+ path->mnt = mntget(mnt);
return 0;
-out_mnt:
- mntput(path->mnt);
-out_err:
- return retval;
+}
+
+/*
+ * Allow relaxed permissions of file handles if the caller has the
+ * ability to mount the filesystem or create a bind-mount of the
+ * provided @mountdirfd.
+ *
+ * In both cases the caller may be able to get an unobstructed way to
+ * the encoded file handle. If the caller is only able to create a
+ * bind-mount we need to verify that there are no locked mounts on top
+ * of it that could prevent us from getting to the encoded file.
+ *
+ * In principle, locked mounts can prevent the caller from mounting the
+ * filesystem but that only applies to procfs and sysfs neither of which
+ * support decoding file handles.
+ */
+static inline bool may_decode_fh(struct handle_to_path_ctx *ctx,
+ unsigned int o_flags)
+{
+ struct path *root = &ctx->root;
+
+ /*
+ * Restrict to O_DIRECTORY to provide a deterministic API that avoids a
+ * confusing api in the face of disconnected non-dir dentries.
+ *
+ * There's only one dentry for each directory inode (VFS rule)...
+ */
+ if (!(o_flags & O_DIRECTORY))
+ return false;
+
+ if (ns_capable(root->mnt->mnt_sb->s_user_ns, CAP_SYS_ADMIN))
+ ctx->flags = HANDLE_CHECK_PERMS;
+ else if (is_mounted(root->mnt) &&
+ ns_capable(real_mount(root->mnt)->mnt_ns->user_ns,
+ CAP_SYS_ADMIN) &&
+ !has_locked_children(real_mount(root->mnt), root->dentry))
+ ctx->flags = HANDLE_CHECK_PERMS | HANDLE_CHECK_SUBTREE;
+ else
+ return false;
+
+ /* Are we able to override DAC permissions? */
+ if (!ns_capable(current_user_ns(), CAP_DAC_READ_SEARCH))
+ return false;
+
+ ctx->fh_flags = EXPORT_FH_DIR_ONLY;
+ return true;
}
static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
- struct path *path)
+ struct path *path, unsigned int o_flags)
{
int retval = 0;
struct file_handle f_handle;
struct file_handle *handle = NULL;
+ struct handle_to_path_ctx ctx = {};
- /*
- * With handle we don't look at the execute bit on the
- * directory. Ideally we would like CAP_DAC_SEARCH.
- * But we don't have that
- */
- if (!capable(CAP_DAC_READ_SEARCH)) {
- retval = -EPERM;
+ retval = get_path_from_fd(mountdirfd, &ctx.root);
+ if (retval)
goto out_err;
+
+ if (!capable(CAP_DAC_READ_SEARCH) && !may_decode_fh(&ctx, o_flags)) {
+ retval = -EPERM;
+ goto out_path;
}
+
if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) {
retval = -EFAULT;
- goto out_err;
+ goto out_path;
}
if ((f_handle.handle_bytes > MAX_HANDLE_SZ) ||
(f_handle.handle_bytes == 0)) {
retval = -EINVAL;
- goto out_err;
+ goto out_path;
}
handle = kmalloc(struct_size(handle, f_handle, f_handle.handle_bytes),
GFP_KERNEL);
if (!handle) {
retval = -ENOMEM;
- goto out_err;
+ goto out_path;
}
/* copy the full handle */
*handle = f_handle;
@@ -207,10 +307,12 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
goto out_handle;
}
- retval = do_handle_to_path(mountdirfd, handle, path);
+ retval = do_handle_to_path(handle, path, &ctx);
out_handle:
kfree(handle);
+out_path:
+ path_put(&ctx.root);
out_err:
return retval;
}
@@ -223,7 +325,7 @@ static long do_handle_open(int mountdirfd, struct file_handle __user *ufh,
struct file *file;
int fd;
- retval = handle_to_path(mountdirfd, ufh, &path);
+ retval = handle_to_path(mountdirfd, ufh, &path, open_flag);
if (retval)
return retval;
diff --git a/fs/fsopen.c b/fs/fsopen.c
index 6593ae518115..ed2dd000622e 100644
--- a/fs/fsopen.c
+++ b/fs/fsopen.c
@@ -220,10 +220,6 @@ static int vfs_cmd_create(struct fs_context *fc, bool exclusive)
if (!mount_capable(fc))
return -EPERM;
- /* require the new mount api */
- if (exclusive && fc->ops == &legacy_fs_context_ops)
- return -EOPNOTSUPP;
-
fc->phase = FS_CONTEXT_CREATING;
fc->exclusive = exclusive;
@@ -411,6 +407,7 @@ SYSCALL_DEFINE5(fsconfig,
case FSCONFIG_SET_PATH:
case FSCONFIG_SET_PATH_EMPTY:
case FSCONFIG_SET_FD:
+ case FSCONFIG_CMD_CREATE_EXCL:
ret = -EOPNOTSUPP;
goto out_f;
}
@@ -451,7 +448,7 @@ SYSCALL_DEFINE5(fsconfig,
fallthrough;
case FSCONFIG_SET_PATH:
param.type = fs_value_is_filename;
- param.name = getname_flags(_value, lookup_flags, NULL);
+ param.name = getname_flags(_value, lookup_flags);
if (IS_ERR(param.name)) {
ret = PTR_ERR(param.name);
goto out_key;
diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c
index 3d192b80a561..04cfd8fee992 100644
--- a/fs/fuse/acl.c
+++ b/fs/fuse/acl.c
@@ -146,8 +146,8 @@ int fuse_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
* be stripped.
*/
if (fc->posix_acl &&
- !vfsgid_in_group_p(i_gid_into_vfsgid(&nop_mnt_idmap, inode)) &&
- !capable_wrt_inode_uidgid(&nop_mnt_idmap, inode, CAP_FSETID))
+ !in_group_or_capable(&nop_mnt_idmap, inode,
+ i_gid_into_vfsgid(&nop_mnt_idmap, inode)))
extra_flags |= FUSE_SETXATTR_ACL_KILL_SGID;
ret = fuse_setxattr(inode, name, value, size, 0, extra_flags);
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 8c34798a0715..744e10b46904 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -200,6 +200,7 @@ struct inode *hfs_new_inode(struct inode *dir, const struct qstr *name, umode_t
HFS_I(inode)->flags = 0;
HFS_I(inode)->rsrc_inode = NULL;
HFS_I(inode)->fs_blocks = 0;
+ HFS_I(inode)->tz_secondswest = sys_tz.tz_minuteswest * 60;
if (S_ISDIR(mode)) {
inode->i_size = 2;
HFS_SB(sb)->folder_count++;
@@ -275,6 +276,8 @@ void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext,
for (count = 0, i = 0; i < 3; i++)
count += be16_to_cpu(ext[i].count);
HFS_I(inode)->first_blocks = count;
+ HFS_I(inode)->cached_start = 0;
+ HFS_I(inode)->cached_blocks = 0;
inode->i_size = HFS_I(inode)->phys_size = log_size;
HFS_I(inode)->fs_blocks = (log_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c
index ca2ba8c9f82e..901e83d65d20 100644
--- a/fs/hfsplus/bfind.c
+++ b/fs/hfsplus/bfind.c
@@ -25,19 +25,8 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd)
fd->key = ptr + tree->max_key_len + 2;
hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n",
tree->cnid, __builtin_return_address(0));
- switch (tree->cnid) {
- case HFSPLUS_CAT_CNID:
- mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX);
- break;
- case HFSPLUS_EXT_CNID:
- mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX);
- break;
- case HFSPLUS_ATTR_CNID:
- mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX);
- break;
- default:
- BUG();
- }
+ mutex_lock_nested(&tree->tree_lock,
+ hfsplus_btree_lock_class(tree));
return 0;
}
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index 3c572e44f2ad..9c51867dddc5 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -430,7 +430,8 @@ int hfsplus_free_fork(struct super_block *sb, u32 cnid,
hfsplus_free_extents(sb, ext_entry, total_blocks - start,
total_blocks);
total_blocks = start;
- mutex_lock(&fd.tree->tree_lock);
+ mutex_lock_nested(&fd.tree->tree_lock,
+ hfsplus_btree_lock_class(fd.tree));
} while (total_blocks > blocks);
hfs_find_exit(&fd);
@@ -592,7 +593,8 @@ void hfsplus_file_truncate(struct inode *inode)
alloc_cnt, alloc_cnt - blk_cnt);
hfsplus_dump_extent(hip->first_extents);
hip->first_blocks = blk_cnt;
- mutex_lock(&fd.tree->tree_lock);
+ mutex_lock_nested(&fd.tree->tree_lock,
+ hfsplus_btree_lock_class(fd.tree));
break;
}
res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt);
@@ -606,7 +608,8 @@ void hfsplus_file_truncate(struct inode *inode)
hfsplus_free_extents(sb, hip->cached_extents,
alloc_cnt - start, alloc_cnt - blk_cnt);
hfsplus_dump_extent(hip->cached_extents);
- mutex_lock(&fd.tree->tree_lock);
+ mutex_lock_nested(&fd.tree->tree_lock,
+ hfsplus_btree_lock_class(fd.tree));
if (blk_cnt > start) {
hip->extent_state |= HFSPLUS_EXT_DIRTY;
break;
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 012a3d003fbe..9e78f181c24f 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -553,6 +553,27 @@ static inline __be32 __hfsp_ut2mt(time64_t ut)
return cpu_to_be32(lower_32_bits(ut) + HFSPLUS_UTC_OFFSET);
}
+static inline enum hfsplus_btree_mutex_classes
+hfsplus_btree_lock_class(struct hfs_btree *tree)
+{
+ enum hfsplus_btree_mutex_classes class;
+
+ switch (tree->cnid) {
+ case HFSPLUS_CAT_CNID:
+ class = CATALOG_BTREE_MUTEX;
+ break;
+ case HFSPLUS_EXT_CNID:
+ class = EXTENTS_BTREE_MUTEX;
+ break;
+ case HFSPLUS_ATTR_CNID:
+ class = ATTR_BTREE_MUTEX;
+ break;
+ default:
+ BUG();
+ }
+ return class;
+}
+
/* compatibility */
#define hfsp_mt2ut(t) (struct timespec64){ .tv_sec = __hfsp_mt2ut(t) }
#define hfsp_ut2mt(t) __hfsp_ut2mt((t).tv_sec)
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index 5661a2e24d03..40d04dba13ac 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -40,7 +40,7 @@ static int hfsplus_ioctl_bless(struct file *file, int __user *user_flags)
/* Directory containing the bootable system */
vh->finder_info[0] = bvh->finder_info[0] =
- cpu_to_be32(parent_ino(dentry));
+ cpu_to_be32(d_parent_ino(dentry));
/*
* Bootloader. Just using the inode here breaks in the case of
@@ -51,7 +51,7 @@ static int hfsplus_ioctl_bless(struct file *file, int __user *user_flags)
/* Per spec, the OS X system folder - same as finder_info[0] here */
vh->finder_info[5] = bvh->finder_info[5] =
- cpu_to_be32(parent_ino(dentry));
+ cpu_to_be32(d_parent_ino(dentry));
mutex_unlock(&sbi->vh_mutex);
return 0;
diff --git a/fs/inode.c b/fs/inode.c
index 3a41f83a4ba5..e0815acc5abb 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -2538,6 +2538,7 @@ bool in_group_or_capable(struct mnt_idmap *idmap,
return true;
return false;
}
+EXPORT_SYMBOL(in_group_or_capable);
/**
* mode_strip_sgid - handle the sgid bit for non-directories
diff --git a/fs/internal.h b/fs/internal.h
index ab2225136f60..f26454c60a98 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -247,6 +247,8 @@ extern const struct dentry_operations ns_dentry_operations;
int getname_statx_lookup_flags(int flags);
int do_statx(int dfd, struct filename *filename, unsigned int flags,
unsigned int mask, struct statx __user *buffer);
+int do_statx_fd(int fd, unsigned int flags, unsigned int mask,
+ struct statx __user *buffer);
/*
* fs/splice.c:
@@ -321,3 +323,15 @@ struct stashed_operations {
int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data,
struct path *path);
void stashed_dentry_prune(struct dentry *dentry);
+/**
+ * path_mounted - check whether path is mounted
+ * @path: path to check
+ *
+ * Determine whether @path refers to the root of a mount.
+ *
+ * Return: true if @path is the root of a mount, false if not.
+ */
+static inline bool path_mounted(const struct path *path)
+{
+ return path->mnt->mnt_root == path->dentry;
+}
diff --git a/fs/mount.h b/fs/mount.h
index 4a42fc68f4cc..4adce73211ae 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -152,3 +152,4 @@ static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
}
extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor);
+bool has_locked_children(struct mount *mnt, struct dentry *dentry);
diff --git a/fs/namei.c b/fs/namei.c
index 87f96a9078f4..3a4c40e12f78 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -126,7 +126,7 @@
#define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname))
struct filename *
-getname_flags(const char __user *filename, int flags, int *empty)
+getname_flags(const char __user *filename, int flags)
{
struct filename *result;
char *kname;
@@ -148,9 +148,20 @@ getname_flags(const char __user *filename, int flags, int *empty)
result->name = kname;
len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX);
- if (unlikely(len < 0)) {
- __putname(result);
- return ERR_PTR(len);
+ /*
+ * Handle both empty path and copy failure in one go.
+ */
+ if (unlikely(len <= 0)) {
+ if (unlikely(len < 0)) {
+ __putname(result);
+ return ERR_PTR(len);
+ }
+
+ /* The empty path is special. */
+ if (!(flags & LOOKUP_EMPTY)) {
+ __putname(result);
+ return ERR_PTR(-ENOENT);
+ }
}
/*
@@ -180,6 +191,12 @@ getname_flags(const char __user *filename, int flags, int *empty)
kfree(result);
return ERR_PTR(len);
}
+ /* The empty path is special. */
+ if (unlikely(!len) && !(flags & LOOKUP_EMPTY)) {
+ __putname(kname);
+ kfree(result);
+ return ERR_PTR(-ENOENT);
+ }
if (unlikely(len == PATH_MAX)) {
__putname(kname);
kfree(result);
@@ -188,16 +205,6 @@ getname_flags(const char __user *filename, int flags, int *empty)
}
atomic_set(&result->refcnt, 1);
- /* The empty path is special. */
- if (unlikely(!len)) {
- if (empty)
- *empty = 1;
- if (!(flags & LOOKUP_EMPTY)) {
- putname(result);
- return ERR_PTR(-ENOENT);
- }
- }
-
result->uptr = filename;
result->aname = NULL;
audit_getname(result);
@@ -209,13 +216,13 @@ getname_uflags(const char __user *filename, int uflags)
{
int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
- return getname_flags(filename, flags, NULL);
+ return getname_flags(filename, flags);
}
struct filename *
getname(const char __user * filename)
{
- return getname_flags(filename, 0, NULL);
+ return getname_flags(filename, 0);
}
struct filename *
@@ -1233,29 +1240,48 @@ int may_linkat(struct mnt_idmap *idmap, const struct path *link)
*
* Returns 0 if the open is allowed, -ve on error.
*/
-static int may_create_in_sticky(struct mnt_idmap *idmap,
- struct nameidata *nd, struct inode *const inode)
+static int may_create_in_sticky(struct mnt_idmap *idmap, struct nameidata *nd,
+ struct inode *const inode)
{
umode_t dir_mode = nd->dir_mode;
- vfsuid_t dir_vfsuid = nd->dir_vfsuid;
+ vfsuid_t dir_vfsuid = nd->dir_vfsuid, i_vfsuid;
+
+ if (likely(!(dir_mode & S_ISVTX)))
+ return 0;
+
+ if (S_ISREG(inode->i_mode) && !sysctl_protected_regular)
+ return 0;
- if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) ||
- (!sysctl_protected_regular && S_ISREG(inode->i_mode)) ||
- likely(!(dir_mode & S_ISVTX)) ||
- vfsuid_eq(i_uid_into_vfsuid(idmap, inode), dir_vfsuid) ||
- vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), current_fsuid()))
+ if (S_ISFIFO(inode->i_mode) && !sysctl_protected_fifos)
return 0;
- if (likely(dir_mode & 0002) ||
- (dir_mode & 0020 &&
- ((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) ||
- (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) {
- const char *operation = S_ISFIFO(inode->i_mode) ?
- "sticky_create_fifo" :
- "sticky_create_regular";
- audit_log_path_denied(AUDIT_ANOM_CREAT, operation);
+ i_vfsuid = i_uid_into_vfsuid(idmap, inode);
+
+ if (vfsuid_eq(i_vfsuid, dir_vfsuid))
+ return 0;
+
+ if (vfsuid_eq_kuid(i_vfsuid, current_fsuid()))
+ return 0;
+
+ if (likely(dir_mode & 0002)) {
+ audit_log_path_denied(AUDIT_ANOM_CREAT, "sticky_create");
return -EACCES;
}
+
+ if (dir_mode & 0020) {
+ if (sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) {
+ audit_log_path_denied(AUDIT_ANOM_CREAT,
+ "sticky_create_fifo");
+ return -EACCES;
+ }
+
+ if (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode)) {
+ audit_log_path_denied(AUDIT_ANOM_CREAT,
+ "sticky_create_regular");
+ return -EACCES;
+ }
+ }
+
return 0;
}
@@ -2969,16 +2995,16 @@ int path_pts(struct path *path)
}
#endif
-int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
- struct path *path, int *empty)
+int user_path_at(int dfd, const char __user *name, unsigned flags,
+ struct path *path)
{
- struct filename *filename = getname_flags(name, flags, empty);
+ struct filename *filename = getname_flags(name, flags);
int ret = filename_lookup(dfd, filename, flags, path, NULL);
putname(filename);
return ret;
}
-EXPORT_SYMBOL(user_path_at_empty);
+EXPORT_SYMBOL(user_path_at);
int __check_sticky(struct mnt_idmap *idmap, struct inode *dir,
struct inode *inode)
diff --git a/fs/namespace.c b/fs/namespace.c
index 5a51315c6678..3aadd5361a18 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1846,19 +1846,6 @@ bool may_mount(void)
return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN);
}
-/**
- * path_mounted - check whether path is mounted
- * @path: path to check
- *
- * Determine whether @path refers to the root of a mount.
- *
- * Return: true if @path is the root of a mount, false if not.
- */
-static inline bool path_mounted(const struct path *path)
-{
- return path->mnt->mnt_root == path->dentry;
-}
-
static void warn_mandlock(void)
{
pr_warn_once("=======================================================\n"
@@ -1966,69 +1953,72 @@ static bool mnt_ns_loop(struct dentry *dentry)
return current->nsproxy->mnt_ns->seq >= mnt_ns->seq;
}
-struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
+struct mount *copy_tree(struct mount *src_root, struct dentry *dentry,
int flag)
{
- struct mount *res, *p, *q, *r, *parent;
+ struct mount *res, *src_parent, *src_root_child, *src_mnt,
+ *dst_parent, *dst_mnt;
- if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(mnt))
+ if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(src_root))
return ERR_PTR(-EINVAL);
if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry))
return ERR_PTR(-EINVAL);
- res = q = clone_mnt(mnt, dentry, flag);
- if (IS_ERR(q))
- return q;
+ res = dst_mnt = clone_mnt(src_root, dentry, flag);
+ if (IS_ERR(dst_mnt))
+ return dst_mnt;
- q->mnt_mountpoint = mnt->mnt_mountpoint;
+ src_parent = src_root;
+ dst_mnt->mnt_mountpoint = src_root->mnt_mountpoint;
- p = mnt;
- list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) {
- struct mount *s;
- if (!is_subdir(r->mnt_mountpoint, dentry))
+ list_for_each_entry(src_root_child, &src_root->mnt_mounts, mnt_child) {
+ if (!is_subdir(src_root_child->mnt_mountpoint, dentry))
continue;
- for (s = r; s; s = next_mnt(s, r)) {
+ for (src_mnt = src_root_child; src_mnt;
+ src_mnt = next_mnt(src_mnt, src_root_child)) {
if (!(flag & CL_COPY_UNBINDABLE) &&
- IS_MNT_UNBINDABLE(s)) {
- if (s->mnt.mnt_flags & MNT_LOCKED) {
+ IS_MNT_UNBINDABLE(src_mnt)) {
+ if (src_mnt->mnt.mnt_flags & MNT_LOCKED) {
/* Both unbindable and locked. */
- q = ERR_PTR(-EPERM);
+ dst_mnt = ERR_PTR(-EPERM);
goto out;
} else {
- s = skip_mnt_tree(s);
+ src_mnt = skip_mnt_tree(src_mnt);
continue;
}
}
if (!(flag & CL_COPY_MNT_NS_FILE) &&
- is_mnt_ns_file(s->mnt.mnt_root)) {
- s = skip_mnt_tree(s);
+ is_mnt_ns_file(src_mnt->mnt.mnt_root)) {
+ src_mnt = skip_mnt_tree(src_mnt);
continue;
}
- while (p != s->mnt_parent) {
- p = p->mnt_parent;
- q = q->mnt_parent;
+ while (src_parent != src_mnt->mnt_parent) {
+ src_parent = src_parent->mnt_parent;
+ dst_mnt = dst_mnt->mnt_parent;
}
- p = s;
- parent = q;
- q = clone_mnt(p, p->mnt.mnt_root, flag);
- if (IS_ERR(q))
+
+ src_parent = src_mnt;
+ dst_parent = dst_mnt;
+ dst_mnt = clone_mnt(src_mnt, src_mnt->mnt.mnt_root, flag);
+ if (IS_ERR(dst_mnt))
goto out;
lock_mount_hash();
- list_add_tail(&q->mnt_list, &res->mnt_list);
- attach_mnt(q, parent, p->mnt_mp, false);
+ list_add_tail(&dst_mnt->mnt_list, &res->mnt_list);
+ attach_mnt(dst_mnt, dst_parent, src_parent->mnt_mp, false);
unlock_mount_hash();
}
}
return res;
+
out:
if (res) {
lock_mount_hash();
umount_tree(res, UMOUNT_SYNC);
unlock_mount_hash();
}
- return q;
+ return dst_mnt;
}
/* Caller should check returned pointer for errors */
@@ -2078,7 +2068,7 @@ void drop_collected_mounts(struct vfsmount *mnt)
namespace_unlock();
}
-static bool has_locked_children(struct mount *mnt, struct dentry *dentry)
+bool has_locked_children(struct mount *mnt, struct dentry *dentry)
{
struct mount *child;
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 0b75305fb5f5..dd4e11a703aa 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -247,7 +247,7 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
dentry = dget(exp->ex_path.dentry);
else {
dentry = exportfs_decode_fh_raw(exp->ex_path.mnt, fid,
- data_left, fileid_type,
+ data_left, fileid_type, 0,
nfsd_acceptable, exp);
if (IS_ERR_OR_NULL(dentry)) {
trace_nfsd_set_fh_dentry_badhandle(rqstp, fhp,
diff --git a/fs/open.c b/fs/open.c
index 278b3edcda44..22adbef7ecc2 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -247,6 +247,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
long ret;
+ loff_t sum;
if (offset < 0 || len <= 0)
return -EINVAL;
@@ -319,8 +320,11 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
return -ENODEV;
- /* Check for wrap through zero too */
- if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
+ /* Check for wraparound */
+ if (check_add_overflow(offset, len, &sum))
+ return -EFBIG;
+
+ if (sum > inode->i_sb->s_maxbytes)
return -EFBIG;
if (!file->f_op->fallocate)
@@ -982,12 +986,11 @@ static int do_dentry_open(struct file *f,
*/
if (f->f_mode & FMODE_WRITE) {
/*
- * Paired with smp_mb() in collapse_file() to ensure nr_thps
- * is up to date and the update to i_writecount by
- * get_write_access() is visible. Ensures subsequent insertion
- * of THPs into the page cache will fail.
+ * Depends on full fence from get_write_access() to synchronize
+ * against collapse_file() regarding i_writecount and nr_thps
+ * updates. Ensures subsequent insertion of THPs into the page
+ * cache will fail.
*/
- smp_mb();
if (filemap_nr_thps(inode->i_mapping)) {
struct address_space *mapping = inode->i_mapping;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 775ce0bcf08c..c02f1e63f82d 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -202,8 +202,8 @@ int proc_alloc_inum(unsigned int *inum)
{
int i;
- i = ida_simple_get(&proc_inum_ida, 0, UINT_MAX - PROC_DYNAMIC_FIRST + 1,
- GFP_KERNEL);
+ i = ida_alloc_max(&proc_inum_ida, UINT_MAX - PROC_DYNAMIC_FIRST,
+ GFP_KERNEL);
if (i < 0)
return i;
@@ -213,7 +213,7 @@ int proc_alloc_inum(unsigned int *inum)
void proc_free_inum(unsigned int inum)
{
- ida_simple_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
+ ida_free(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
}
static int proc_misc_d_revalidate(struct dentry *dentry, unsigned int flags)
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 627eb2f72ef3..a2b256dac36e 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2246,9 +2246,7 @@ int dquot_disable(struct super_block *sb, int type, unsigned int flags)
int cnt;
struct quota_info *dqopt = sb_dqopt(sb);
- /* s_umount should be held in exclusive mode */
- if (WARN_ON_ONCE(down_read_trylock(&sb->s_umount)))
- up_read(&sb->s_umount);
+ rwsem_assert_held_write(&sb->s_umount);
/* Cannot turn off usage accounting without turning off limits, or
* suspend quotas and simultaneously turn quotas off. */
@@ -2510,9 +2508,7 @@ int dquot_resume(struct super_block *sb, int type)
int ret = 0, cnt;
unsigned int flags;
- /* s_umount should be held in exclusive mode */
- if (WARN_ON_ONCE(down_read_trylock(&sb->s_umount)))
- up_read(&sb->s_umount);
+ rwsem_assert_held_write(&sb->s_umount);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
if (type != -1 && cnt != type)
diff --git a/fs/readdir.c b/fs/readdir.c
index 278bc0254732..d6c82421902a 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -22,8 +22,6 @@
#include <linux/compat.h>
#include <linux/uaccess.h>
-#include <asm/unaligned.h>
-
/*
* Some filesystems were never converted to '->iterate_shared()'
* and their directory iterators want the inode lock held for
@@ -72,7 +70,7 @@ int wrap_directory_iterator(struct file *file,
EXPORT_SYMBOL(wrap_directory_iterator);
/*
- * Note the "unsafe_put_user() semantics: we goto a
+ * Note the "unsafe_put_user()" semantics: we goto a
* label for errors.
*/
#define unsafe_copy_dirent_name(_dst, _src, _len, label) do { \
diff --git a/fs/stat.c b/fs/stat.c
index 70bd3e888cfa..6f65b3456cad 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -214,6 +214,43 @@ int getname_statx_lookup_flags(int flags)
return lookup_flags;
}
+static int vfs_statx_path(struct path *path, int flags, struct kstat *stat,
+ u32 request_mask)
+{
+ int error = vfs_getattr(path, stat, request_mask, flags);
+
+ if (request_mask & STATX_MNT_ID_UNIQUE) {
+ stat->mnt_id = real_mount(path->mnt)->mnt_id_unique;
+ stat->result_mask |= STATX_MNT_ID_UNIQUE;
+ } else {
+ stat->mnt_id = real_mount(path->mnt)->mnt_id;
+ stat->result_mask |= STATX_MNT_ID;
+ }
+
+ if (path_mounted(path))
+ stat->attributes |= STATX_ATTR_MOUNT_ROOT;
+ stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT;
+
+ /* Handle STATX_DIOALIGN for block devices. */
+ if (request_mask & STATX_DIOALIGN) {
+ struct inode *inode = d_backing_inode(path->dentry);
+
+ if (S_ISBLK(inode->i_mode))
+ bdev_statx_dioalign(inode, stat);
+ }
+
+ return error;
+}
+
+static int vfs_statx_fd(int fd, int flags, struct kstat *stat,
+ u32 request_mask)
+{
+ CLASS(fd_raw, f)(fd);
+ if (!f.file)
+ return -EBADF;
+ return vfs_statx_path(&f.file->f_path, flags, stat, request_mask);
+}
+
/**
* vfs_statx - Get basic and extra attributes by filename
* @dfd: A file descriptor representing the base dir for a relative filename
@@ -243,36 +280,13 @@ static int vfs_statx(int dfd, struct filename *filename, int flags,
retry:
error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
if (error)
- goto out;
-
- error = vfs_getattr(&path, stat, request_mask, flags);
-
- if (request_mask & STATX_MNT_ID_UNIQUE) {
- stat->mnt_id = real_mount(path.mnt)->mnt_id_unique;
- stat->result_mask |= STATX_MNT_ID_UNIQUE;
- } else {
- stat->mnt_id = real_mount(path.mnt)->mnt_id;
- stat->result_mask |= STATX_MNT_ID;
- }
-
- if (path.mnt->mnt_root == path.dentry)
- stat->attributes |= STATX_ATTR_MOUNT_ROOT;
- stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT;
-
- /* Handle STATX_DIOALIGN for block devices. */
- if (request_mask & STATX_DIOALIGN) {
- struct inode *inode = d_backing_inode(path.dentry);
-
- if (S_ISBLK(inode->i_mode))
- bdev_statx_dioalign(inode, stat);
- }
-
+ return error;
+ error = vfs_statx_path(&path, flags, stat, request_mask);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
-out:
return error;
}
@@ -289,18 +303,10 @@ int vfs_fstatat(int dfd, const char __user *filename,
* If AT_EMPTY_PATH is set, we expect the common case to be that
* empty path, and avoid doing all the extra pathname work.
*/
- if (dfd >= 0 && flags == AT_EMPTY_PATH) {
- char c;
-
- ret = get_user(c, filename);
- if (unlikely(ret))
- return ret;
-
- if (likely(!c))
- return vfs_fstat(dfd, stat);
- }
+ if (flags == AT_EMPTY_PATH && vfs_empty_path(dfd, filename))
+ return vfs_fstat(dfd, stat);
- name = getname_flags(filename, getname_statx_lookup_flags(statx_flags), NULL);
+ name = getname_flags(filename, getname_statx_lookup_flags(statx_flags));
ret = vfs_statx(dfd, name, statx_flags, stat, STATX_BASIC_STATS);
putname(name);
@@ -488,34 +494,39 @@ static int do_readlinkat(int dfd, const char __user *pathname,
char __user *buf, int bufsiz)
{
struct path path;
+ struct filename *name;
int error;
- int empty = 0;
unsigned int lookup_flags = LOOKUP_EMPTY;
if (bufsiz <= 0)
return -EINVAL;
retry:
- error = user_path_at_empty(dfd, pathname, lookup_flags, &path, &empty);
- if (!error) {
- struct inode *inode = d_backing_inode(path.dentry);
-
- error = empty ? -ENOENT : -EINVAL;
- /*
- * AFS mountpoints allow readlink(2) but are not symlinks
- */
- if (d_is_symlink(path.dentry) || inode->i_op->readlink) {
- error = security_inode_readlink(path.dentry);
- if (!error) {
- touch_atime(&path);
- error = vfs_readlink(path.dentry, buf, bufsiz);
- }
- }
- path_put(&path);
- if (retry_estale(error, lookup_flags)) {
- lookup_flags |= LOOKUP_REVAL;
- goto retry;
+ name = getname_flags(pathname, lookup_flags);
+ error = filename_lookup(dfd, name, lookup_flags, &path, NULL);
+ if (unlikely(error)) {
+ putname(name);
+ return error;
+ }
+
+ /*
+ * AFS mountpoints allow readlink(2) but are not symlinks
+ */
+ if (d_is_symlink(path.dentry) ||
+ d_backing_inode(path.dentry)->i_op->readlink) {
+ error = security_inode_readlink(path.dentry);
+ if (!error) {
+ touch_atime(&path);
+ error = vfs_readlink(path.dentry, buf, bufsiz);
}
+ } else {
+ error = (name->name[0] == '\0') ? -ENOENT : -EINVAL;
+ }
+ path_put(&path);
+ putname(name);
+ if (retry_estale(error, lookup_flags)) {
+ lookup_flags |= LOOKUP_REVAL;
+ goto retry;
}
return error;
}
@@ -674,7 +685,8 @@ int do_statx(int dfd, struct filename *filename, unsigned int flags,
if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
return -EINVAL;
- /* STATX_CHANGE_COOKIE is kernel-only for now. Ignore requests
+ /*
+ * STATX_CHANGE_COOKIE is kernel-only for now. Ignore requests
* from userland.
*/
mask &= ~STATX_CHANGE_COOKIE;
@@ -686,16 +698,41 @@ int do_statx(int dfd, struct filename *filename, unsigned int flags,
return cp_statx(&stat, buffer);
}
+int do_statx_fd(int fd, unsigned int flags, unsigned int mask,
+ struct statx __user *buffer)
+{
+ struct kstat stat;
+ int error;
+
+ if (mask & STATX__RESERVED)
+ return -EINVAL;
+ if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
+ return -EINVAL;
+
+ /*
+ * STATX_CHANGE_COOKIE is kernel-only for now. Ignore requests
+ * from userland.
+ */
+ mask &= ~STATX_CHANGE_COOKIE;
+
+ error = vfs_statx_fd(fd, flags, &stat, mask);
+ if (error)
+ return error;
+
+ return cp_statx(&stat, buffer);
+}
+
/**
* sys_statx - System call to get enhanced stats
* @dfd: Base directory to pathwalk from *or* fd to stat.
- * @filename: File to stat or "" with AT_EMPTY_PATH
+ * @filename: File to stat or either NULL or "" with AT_EMPTY_PATH
* @flags: AT_* flags to control pathwalk.
* @mask: Parts of statx struct actually required.
* @buffer: Result buffer.
*
* Note that fstat() can be emulated by setting dfd to the fd of interest,
- * supplying "" as the filename and setting AT_EMPTY_PATH in the flags.
+ * supplying "" (or preferably NULL) as the filename and setting AT_EMPTY_PATH
+ * in the flags.
*/
SYSCALL_DEFINE5(statx,
int, dfd, const char __user *, filename, unsigned, flags,
@@ -703,9 +740,24 @@ SYSCALL_DEFINE5(statx,
struct statx __user *, buffer)
{
int ret;
+ unsigned lflags;
struct filename *name;
- name = getname_flags(filename, getname_statx_lookup_flags(flags), NULL);
+ /*
+ * Short-circuit handling of NULL and "" paths.
+ *
+ * For a NULL path we require and accept only the AT_EMPTY_PATH flag
+ * (possibly |'d with AT_STATX flags).
+ *
+ * However, glibc on 32-bit architectures implements fstatat as statx
+ * with the "" pathname and AT_NO_AUTOMOUNT | AT_EMPTY_PATH flags.
+ * Supporting this results in the uglification below.
+ */
+ lflags = flags & ~(AT_NO_AUTOMOUNT | AT_STATX_SYNC_TYPE);
+ if (lflags == AT_EMPTY_PATH && vfs_empty_path(dfd, filename))
+ return do_statx_fd(dfd, flags & ~AT_NO_AUTOMOUNT, mask, buffer);
+
+ name = getname_flags(filename, getname_statx_lookup_flags(flags));
ret = do_statx(dfd, name, flags, mask, buffer);
putname(name);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index bf53e3894aae..ea58843942b9 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -278,6 +278,8 @@ static inline unsigned d_count(const struct dentry *dentry)
return dentry->d_lockref.count;
}
+ino_t d_parent_ino(struct dentry *dentry);
+
/*
* helper function for dentry_operations.d_dname() members
*/
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index bb37ad5cc954..893a1d21dc1c 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -158,6 +158,7 @@ struct fid {
#define EXPORT_FH_CONNECTABLE 0x1 /* Encode file handle with parent */
#define EXPORT_FH_FID 0x2 /* File handle may be non-decodeable */
+#define EXPORT_FH_DIR_ONLY 0x4 /* Only decode file handle for a directory */
/**
* struct export_operations - for nfsd to communicate with file systems
@@ -305,6 +306,7 @@ static inline int exportfs_encode_fid(struct inode *inode, struct fid *fid,
extern struct dentry *exportfs_decode_fh_raw(struct vfsmount *mnt,
struct fid *fid, int fh_len,
int fileid_type,
+ unsigned int flags,
int (*acceptable)(void *, struct dentry *),
void *context);
extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0283cf366c2a..2fa06a4d197a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -660,9 +660,13 @@ struct inode {
};
dev_t i_rdev;
loff_t i_size;
- struct timespec64 __i_atime;
- struct timespec64 __i_mtime;
- struct timespec64 __i_ctime; /* use inode_*_ctime accessors! */
+ time64_t i_atime_sec;
+ time64_t i_mtime_sec;
+ time64_t i_ctime_sec;
+ u32 i_atime_nsec;
+ u32 i_mtime_nsec;
+ u32 i_ctime_nsec;
+ u32 i_generation;
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned short i_bytes;
u8 i_blkbits;
@@ -719,10 +723,10 @@ struct inode {
unsigned i_dir_seq;
};
- __u32 i_generation;
#ifdef CONFIG_FSNOTIFY
__u32 i_fsnotify_mask; /* all events this inode cares about */
+ /* 32-bit hole reserved for expanding i_fsnotify_mask */
struct fsnotify_mark_connector __rcu *i_fsnotify_marks;
#endif
@@ -1538,23 +1542,27 @@ struct timespec64 inode_set_ctime_current(struct inode *inode);
static inline time64_t inode_get_atime_sec(const struct inode *inode)
{
- return inode->__i_atime.tv_sec;
+ return inode->i_atime_sec;
}
static inline long inode_get_atime_nsec(const struct inode *inode)
{
- return inode->__i_atime.tv_nsec;
+ return inode->i_atime_nsec;
}
static inline struct timespec64 inode_get_atime(const struct inode *inode)
{
- return inode->__i_atime;
+ struct timespec64 ts = { .tv_sec = inode_get_atime_sec(inode),
+ .tv_nsec = inode_get_atime_nsec(inode) };
+
+ return ts;
}
static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode,
struct timespec64 ts)
{
- inode->__i_atime = ts;
+ inode->i_atime_sec = ts.tv_sec;
+ inode->i_atime_nsec = ts.tv_nsec;
return ts;
}
@@ -1563,28 +1571,32 @@ static inline struct timespec64 inode_set_atime(struct inode *inode,
{
struct timespec64 ts = { .tv_sec = sec,
.tv_nsec = nsec };
+
return inode_set_atime_to_ts(inode, ts);
}
static inline time64_t inode_get_mtime_sec(const struct inode *inode)
{
- return inode->__i_mtime.tv_sec;
+ return inode->i_mtime_sec;
}
static inline long inode_get_mtime_nsec(const struct inode *inode)
{
- return inode->__i_mtime.tv_nsec;
+ return inode->i_mtime_nsec;
}
static inline struct timespec64 inode_get_mtime(const struct inode *inode)
{
- return inode->__i_mtime;
+ struct timespec64 ts = { .tv_sec = inode_get_mtime_sec(inode),
+ .tv_nsec = inode_get_mtime_nsec(inode) };
+ return ts;
}
static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode,
struct timespec64 ts)
{
- inode->__i_mtime = ts;
+ inode->i_mtime_sec = ts.tv_sec;
+ inode->i_mtime_nsec = ts.tv_nsec;
return ts;
}
@@ -1598,23 +1610,27 @@ static inline struct timespec64 inode_set_mtime(struct inode *inode,
static inline time64_t inode_get_ctime_sec(const struct inode *inode)
{
- return inode->__i_ctime.tv_sec;
+ return inode->i_ctime_sec;
}
static inline long inode_get_ctime_nsec(const struct inode *inode)
{
- return inode->__i_ctime.tv_nsec;
+ return inode->i_ctime_nsec;
}
static inline struct timespec64 inode_get_ctime(const struct inode *inode)
{
- return inode->__i_ctime;
+ struct timespec64 ts = { .tv_sec = inode_get_ctime_sec(inode),
+ .tv_nsec = inode_get_ctime_nsec(inode) };
+
+ return ts;
}
static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode,
struct timespec64 ts)
{
- inode->__i_ctime = ts;
+ inode->i_ctime_sec = ts.tv_sec;
+ inode->i_ctime_nsec = ts.tv_nsec;
return ts;
}
@@ -1926,6 +1942,8 @@ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode,
extern bool may_open_dev(const struct path *path);
umode_t mode_strip_sgid(struct mnt_idmap *idmap,
const struct inode *dir, umode_t mode);
+bool in_group_or_capable(struct mnt_idmap *idmap,
+ const struct inode *inode, vfsgid_t vfsgid);
/*
* This is the "filldir" function type, used by readdir() to let
@@ -2685,7 +2703,7 @@ static inline struct file *file_clone_open(struct file *file)
}
extern int filp_close(struct file *, fl_owner_t id);
-extern struct filename *getname_flags(const char __user *, int, int *);
+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 *);
extern struct filename *getname_kernel(const char *);
@@ -3436,20 +3454,6 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
return 0;
}
-static inline ino_t parent_ino(struct dentry *dentry)
-{
- ino_t res;
-
- /*
- * Don't strictly need d_lock here? If the parent ino could change
- * then surely we'd have a deeper race in the caller?
- */
- spin_lock(&dentry->d_lock);
- res = dentry->d_parent->d_inode->i_ino;
- spin_unlock(&dentry->d_lock);
- return res;
-}
-
/* Transaction based IO helpers */
/*
@@ -3574,7 +3578,7 @@ static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx)
static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx)
{
return ctx->actor(ctx, "..", 2, ctx->pos,
- parent_ino(file->f_path.dentry), DT_DIR);
+ d_parent_ino(file->f_path.dentry), DT_DIR);
}
static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx)
{
@@ -3613,4 +3617,21 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len,
extern int generic_fadvise(struct file *file, loff_t offset, loff_t len,
int advice);
+static inline bool vfs_empty_path(int dfd, const char __user *path)
+{
+ char c;
+
+ if (dfd < 0)
+ return false;
+
+ /* We now allow NULL to be used for empty path. */
+ if (!path)
+ return true;
+
+ if (unlikely(get_user(c, path)))
+ return false;
+
+ return !c;
+}
+
#endif /* _LINUX_FS_H */
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 967aa9ea9f96..8ec8fed3bce8 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -50,13 +50,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT};
extern int path_pts(struct path *path);
-extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty);
-
-static inline int user_path_at(int dfd, const char __user *name, unsigned flags,
- struct path *path)
-{
- return user_path_at_empty(dfd, name, flags, path, NULL);
-}
+extern int user_path_at(int, const char __user *, unsigned, struct path *);
struct dentry *lookup_one_qstr_excl(const struct qstr *name,
struct dentry *base,
diff --git a/io_uring/statx.c b/io_uring/statx.c
index abb874209caa..f7f9b202eec0 100644
--- a/io_uring/statx.c
+++ b/io_uring/statx.c
@@ -37,8 +37,7 @@ int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
sx->flags = READ_ONCE(sqe->statx_flags);
sx->filename = getname_flags(path,
- getname_statx_lookup_flags(sx->flags),
- NULL);
+ getname_statx_lookup_flags(sx->flags));
if (IS_ERR(sx->filename)) {
int ret = PTR_ERR(sx->filename);
diff --git a/io_uring/xattr.c b/io_uring/xattr.c
index 44905b82eea8..6cf41c3bc369 100644
--- a/io_uring/xattr.c
+++ b/io_uring/xattr.c
@@ -96,7 +96,7 @@ int io_getxattr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
path = u64_to_user_ptr(READ_ONCE(sqe->addr3));
- ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL);
+ ix->filename = getname_flags(path, LOOKUP_FOLLOW);
if (IS_ERR(ix->filename)) {
ret = PTR_ERR(ix->filename);
ix->filename = NULL;
@@ -189,7 +189,7 @@ int io_setxattr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
path = u64_to_user_ptr(READ_ONCE(sqe->addr3));
- ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL);
+ ix->filename = getname_flags(path, LOOKUP_FOLLOW);
if (IS_ERR(ix->filename)) {
ret = PTR_ERR(ix->filename);
ix->filename = NULL;
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 5eea4dc0509e..a7cbd69efbef 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -903,7 +903,8 @@ static int do_mq_open(const char __user *u_name, int oflag, umode_t mode,
audit_mq_open(oflag, mode, attr);
- if (IS_ERR(name = getname(u_name)))
+ name = getname(u_name);
+ if (IS_ERR(name))
return PTR_ERR(name);
fd = get_unused_fd_flags(O_CLOEXEC);
diff --git a/kernel/fork.c b/kernel/fork.c
index 99076dbe27d8..763a042eef9c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -616,12 +616,6 @@ static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
exe_file = get_mm_exe_file(oldmm);
RCU_INIT_POINTER(mm->exe_file, exe_file);
- /*
- * We depend on the oldmm having properly denied write access to the
- * exe_file already.
- */
- if (exe_file && deny_write_access(exe_file))
- pr_warn_once("deny_write_access() failed in %s\n", __func__);
}
#ifdef CONFIG_MMU
@@ -1412,20 +1406,11 @@ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
*/
old_exe_file = rcu_dereference_raw(mm->exe_file);
- if (new_exe_file) {
- /*
- * We expect the caller (i.e., sys_execve) to already denied
- * write access, so this is unlikely to fail.
- */
- if (unlikely(deny_write_access(new_exe_file)))
- return -EACCES;
+ if (new_exe_file)
get_file(new_exe_file);
- }
rcu_assign_pointer(mm->exe_file, new_exe_file);
- if (old_exe_file) {
- allow_write_access(old_exe_file);
+ if (old_exe_file)
fput(old_exe_file);
- }
return 0;
}
@@ -1464,9 +1449,6 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
return ret;
}
- ret = deny_write_access(new_exe_file);
- if (ret)
- return -EACCES;
get_file(new_exe_file);
/* set the new file */
@@ -1475,10 +1457,8 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
rcu_assign_pointer(mm->exe_file, new_exe_file);
mmap_write_unlock(mm);
- if (old_exe_file) {
- allow_write_access(old_exe_file);
+ if (old_exe_file)
fput(old_exe_file);
- }
return 0;
}
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 774a97e6e2da..aab471791bd9 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -2000,9 +2000,9 @@ out_unlock:
if (!is_shmem) {
filemap_nr_thps_inc(mapping);
/*
- * Paired with smp_mb() in do_dentry_open() to ensure
- * i_writecount is up to date and the update to nr_thps is
- * visible. Ensures the page cache will be truncated if the
+ * Paired with the fence in do_dentry_open() -> get_write_access()
+ * to ensure i_writecount is up to date and the update to nr_thps
+ * is visible. Ensures the page cache will be truncated if the
* file is opened writable.
*/
smp_mb();
@@ -2190,8 +2190,8 @@ rollback:
if (!is_shmem && result == SCAN_COPY_MC) {
filemap_nr_thps_dec(mapping);
/*
- * Paired with smp_mb() in do_dentry_open() to
- * ensure the update to nr_thps is visible.
+ * Paired with the fence in do_dentry_open() -> get_write_access()
+ * to ensure the update to nr_thps is visible.
*/
smp_mb();
}
diff --git a/mm/shmem.c b/mm/shmem.c
index c1befe046c7e..36de3da15426 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3177,10 +3177,13 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
struct folio *folio;
/*
- * Good, the fallocate(2) manpage permits EINTR: we may have
- * been interrupted because we are using up too much memory.
+ * Check for fatal signal so that we abort early in OOM
+ * situations. We don't want to abort in case of non-fatal
+ * signals as large fallocate can take noticeable time and
+ * e.g. periodic timers may result in fallocate constantly
+ * restarting.
*/
- if (signal_pending(current))
+ if (fatal_signal_pending(current))
error = -EINTR;
else if (shmem_falloc.nr_unswapped > shmem_falloc.nr_falloced)
error = -ENOMEM;