[PATCH 1/2] fs: reorganize path_openat()

[PATCH 1/2] fs: reorganize path_openat()

[Stas Sergeev]

This patch moves the call to alloc_empty_file() below the call to
path_init(). That changes is needed for the next patch, which adds
a cred override for alloc_empty_file(). The needed cred info is only
available after the call to path_init().

No functional changes are intended by that patch.

Signed-off-by: Stas Sergeev <stsp2@yandex.ru>

CC: Eric Biederman <ebiederm@xmission.com>
CC: Alexander Viro <viro@zeniv.linux.org.uk>
CC: Christian Brauner <brauner@kernel.org>
CC: Jan Kara <jack@suse.cz>
CC: Andy Lutomirski <luto@kernel.org>
CC: linux-fsdevel@vger.kernel.org
CC: linux-kernel@vger.kernel.org
---
 fs/namei.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index c5b2a25be7d0..2fde2c320ae9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3782,22 +3782,30 @@ static struct file *path_openat(struct nameidata *nd,
 	struct file *file;
 	int error;
 
-	file = alloc_empty_file(op->open_flag, current_cred());
-	if (IS_ERR(file))
-		return file;
-
-	if (unlikely(file->f_flags & __O_TMPFILE)) {
+	if (unlikely(op->open_flag & __O_TMPFILE)) {
+		file = alloc_empty_file(op->open_flag, current_cred());
+		if (IS_ERR(file))
+			return file;
 		error = do_tmpfile(nd, flags, op, file);
-	} else if (unlikely(file->f_flags & O_PATH)) {
+	} else if (unlikely(op->open_flag & O_PATH)) {
+		file = alloc_empty_file(op->open_flag, current_cred());
+		if (IS_ERR(file))
+			return file;
 		error = do_o_path(nd, flags, file);
 	} else {
 		const char *s = path_init(nd, flags);
-		while (!(error = link_path_walk(s, nd)) &&
-		       (s = open_last_lookups(nd, file, op)) != NULL)
-			;
+		file = alloc_empty_file(op->open_flag, current_cred());
+		error = PTR_ERR_OR_ZERO(file);
+		if (!error) {
+			while (!(error = link_path_walk(s, nd)) &&
+			       (s = open_last_lookups(nd, file, op)) != NULL)
+				;
+		}
 		if (!error)
 			error = do_open(nd, file, op);
 		terminate_walk(nd);
+		if (IS_ERR(file))
+			return file;
 	}
 	if (likely(!error)) {
 		if (likely(file->f_mode & FMODE_OPENED))
-- 
2.44.0

[PATCH 2/2] openat2: add OA2_INHERIT_CRED flag

[Stas Sergeev]

This flag performs the open operation with the fsuid/fsgid that
were in effect when dir_fd was opened.
This allows the process to pre-open some directories and then
change eUID (and all other UIDs/GIDs) to a less-privileged user,
retaining the ability to open/create files within these directories.

Design goal:
The idea is to provide a very light-weight sandboxing, where the
process, without the use of any heavy-weight techniques like chroot
within namespaces, can restrict the access to the set of pre-opened
directories.
This patch is just a first step to such sandboxing. If things go
well, in the future the same extension can be added to more syscalls.
These should include at least unlinkat(), renameat2() and the
not-yet-upstreamed setxattrat().

Security considerations:
To avoid sandboxing escape, this patch makes sure the restricted
lookup modes are used. Namely, RESOLVE_BENEATH or RESOLVE_IN_ROOT.
To avoid leaking creds across exec, this patch requires O_CLOEXEC
flag on a directory.

Use cases:
Virtual machines that deal with untrusted code, can use that
instead of a more heavy-weighted approaches.
Currently the approach is being tested on a dosemu2 VM.

Signed-off-by: Stas Sergeev <stsp2@yandex.ru>

CC: Eric Biederman <ebiederm@xmission.com>
CC: Alexander Viro <viro@zeniv.linux.org.uk>
CC: Andy Lutomirski <luto@kernel.org>
CC: Christian Brauner <brauner@kernel.org>
CC: Jan Kara <jack@suse.cz>
CC: Jeff Layton <jlayton@kernel.org>
CC: Chuck Lever <chuck.lever@oracle.com>
CC: Alexander Aring <alex.aring@gmail.com>
CC: linux-fsdevel@vger.kernel.org
CC: linux-kernel@vger.kernel.org
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Christian Göttsche <cgzones@googlemail.com>
---
 fs/file_table.c              |  2 ++
 fs/internal.h                |  2 +-
 fs/namei.c                   | 54 ++++++++++++++++++++++++++++++++++--
 fs/open.c                    |  2 +-
 include/linux/fcntl.h        |  2 ++
 include/linux/fs.h           |  2 ++
 include/uapi/linux/openat2.h |  3 ++
 7 files changed, 63 insertions(+), 4 deletions(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index 4f03beed4737..9991bdd538e9 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -160,6 +160,8 @@ static int init_file(struct file *f, int flags, const struct cred *cred)
 	mutex_init(&f->f_pos_lock);
 	f->f_flags = flags;
 	f->f_mode = OPEN_FMODE(flags);
+	f->f_fsuid = cred->fsuid;
+	f->f_fsgid = cred->fsgid;
 	/* f->f_version: 0 */
 
 	/*
diff --git a/fs/internal.h b/fs/internal.h
index 7ca738904e34..692b53b19aad 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -169,7 +169,7 @@ static inline void sb_end_ro_state_change(struct super_block *sb)
  * open.c
  */
 struct open_flags {
-	int open_flag;
+	u64 open_flag;
 	umode_t mode;
 	int acc_mode;
 	int intent;
diff --git a/fs/namei.c b/fs/namei.c
index 2fde2c320ae9..d1db6ceee4bd 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -586,6 +586,8 @@ struct nameidata {
 	int		dfd;
 	vfsuid_t	dir_vfsuid;
 	umode_t		dir_mode;
+	kuid_t		dir_open_fsuid;
+	kgid_t		dir_open_fsgid;
 } __randomize_layout;
 
 #define ND_ROOT_PRESET 1
@@ -2414,6 +2416,8 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 			get_fs_pwd(current->fs, &nd->path);
 			nd->inode = nd->path.dentry->d_inode;
 		}
+		nd->dir_open_fsuid = current_cred()->fsuid;
+		nd->dir_open_fsgid = current_cred()->fsgid;
 	} else {
 		/* Caller must check execute permissions on the starting path component */
 		struct fd f = fdget_raw(nd->dfd);
@@ -2437,6 +2441,8 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 			path_get(&nd->path);
 			nd->inode = nd->path.dentry->d_inode;
 		}
+		nd->dir_open_fsuid = f.file->f_fsuid;
+		nd->dir_open_fsgid = f.file->f_fsgid;
 		fdput(f);
 	}
 
@@ -3653,6 +3659,28 @@ static int do_open(struct nameidata *nd,
 	return error;
 }
 
+static const struct cred *openat2_override_creds(struct nameidata *nd)
+{
+	const struct cred *old_cred;
+	struct cred *override_cred;
+
+	override_cred = prepare_creds();
+	if (!override_cred)
+		return NULL;
+
+	override_cred->fsuid = nd->dir_open_fsuid;
+	override_cred->fsgid = nd->dir_open_fsgid;
+
+	override_cred->non_rcu = 1;
+
+	old_cred = override_creds(override_cred);
+
+	/* override_cred() gets its own ref */
+	put_cred(override_cred);
+
+	return old_cred;
+}
+
 /**
  * vfs_tmpfile - create tmpfile
  * @idmap:	idmap of the mount the inode was found from
@@ -3794,8 +3822,28 @@ static struct file *path_openat(struct nameidata *nd,
 		error = do_o_path(nd, flags, file);
 	} else {
 		const char *s = path_init(nd, flags);
-		file = alloc_empty_file(op->open_flag, current_cred());
-		error = PTR_ERR_OR_ZERO(file);
+		const struct cred *old_cred = NULL;
+
+		error = 0;
+		if (op->open_flag & OA2_INHERIT_CRED) {
+			/* Make sure to work only with restricted
+			 * look-up modes.
+			 */
+			if (!(nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT)))
+				error = -EPERM;
+			/* Only work with O_CLOEXEC dirs. */
+			if (!get_close_on_exec(nd->dfd))
+				error = -EPERM;
+
+			if (!error)
+				old_cred = openat2_override_creds(nd);
+		}
+		if (!error) {
+			file = alloc_empty_file(op->open_flag, current_cred());
+			error = PTR_ERR_OR_ZERO(file);
+		} else {
+			file = ERR_PTR(error);
+		}
 		if (!error) {
 			while (!(error = link_path_walk(s, nd)) &&
 			       (s = open_last_lookups(nd, file, op)) != NULL)
@@ -3803,6 +3851,8 @@ static struct file *path_openat(struct nameidata *nd,
 		}
 		if (!error)
 			error = do_open(nd, file, op);
+		if (old_cred)
+			revert_creds(old_cred);
 		terminate_walk(nd);
 		if (IS_ERR(file))
 			return file;
diff --git a/fs/open.c b/fs/open.c
index ee8460c83c77..6be013182a35 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1225,7 +1225,7 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op)
 	 * values before calling build_open_flags(), but openat2(2) checks all
 	 * of its arguments.
 	 */
-	if (flags & ~VALID_OPEN_FLAGS)
+	if (flags & ~VALID_OPENAT2_FLAGS)
 		return -EINVAL;
 	if (how->resolve & ~VALID_RESOLVE_FLAGS)
 		return -EINVAL;
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index a332e79b3207..b71f8b162102 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -12,6 +12,8 @@
 	 FASYNC	| O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \
 	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE)
 
+#define VALID_OPENAT2_FLAGS (VALID_OPEN_FLAGS | OA2_INHERIT_CRED)
+
 /* List of all valid flags for the how->resolve argument: */
 #define VALID_RESOLVE_FLAGS \
 	(RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8dfd53b52744..ea954b6945d0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1028,6 +1028,8 @@ struct file {
 	struct address_space	*f_mapping;
 	errseq_t		f_wb_err;
 	errseq_t		f_sb_err; /* for syncfs */
+	kuid_t			f_fsuid;  /* fsUID of the opener */
+	kgid_t			f_fsgid;  /* fsGID of the opener */
 } __randomize_layout
   __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
 
diff --git a/include/uapi/linux/openat2.h b/include/uapi/linux/openat2.h
index a5feb7604948..cdd676a10b62 100644
--- a/include/uapi/linux/openat2.h
+++ b/include/uapi/linux/openat2.h
@@ -40,4 +40,7 @@ struct open_how {
 					return -EAGAIN if that's not
 					possible. */
 
+/* openat2-specific flags go to upper 4 bytes. */
+#define OA2_INHERIT_CRED		(1ULL << 32)
+
 #endif /* _UAPI_LINUX_OPENAT2_H */
-- 
2.44.0

Re: [PATCH 2/2] openat2: add OA2_INHERIT_CRED flag

[Stefan Metzmacher]

Am 22.04.24 um 10:45 schrieb Stas Sergeev:
> This flag performs the open operation with the fsuid/fsgid that
> were in effect when dir_fd was opened.
> This allows the process to pre-open some directories and then
> change eUID (and all other UIDs/GIDs) to a less-privileged user,
> retaining the ability to open/create files within these directories.
> 
> Design goal:
> The idea is to provide a very light-weight sandboxing, where the
> process, without the use of any heavy-weight techniques like chroot
> within namespaces, can restrict the access to the set of pre-opened
> directories.
> This patch is just a first step to such sandboxing. If things go
> well, in the future the same extension can be added to more syscalls.
> These should include at least unlinkat(), renameat2() and the
> not-yet-upstreamed setxattrat().
> 
> Security considerations:
> To avoid sandboxing escape, this patch makes sure the restricted
> lookup modes are used. Namely, RESOLVE_BENEATH or RESOLVE_IN_ROOT.
> To avoid leaking creds across exec, this patch requires O_CLOEXEC
> flag on a directory.
> 
> Use cases:
> Virtual machines that deal with untrusted code, can use that
> instead of a more heavy-weighted approaches.
> Currently the approach is being tested on a dosemu2 VM.
> 
> Signed-off-by: Stas Sergeev <stsp2@yandex.ru>
> 
> CC: Eric Biederman <ebiederm@xmission.com>
> CC: Alexander Viro <viro@zeniv.linux.org.uk>
> CC: Andy Lutomirski <luto@kernel.org>
> CC: Christian Brauner <brauner@kernel.org>
> CC: Jan Kara <jack@suse.cz>
> CC: Jeff Layton <jlayton@kernel.org>
> CC: Chuck Lever <chuck.lever@oracle.com>
> CC: Alexander Aring <alex.aring@gmail.com>
> CC: linux-fsdevel@vger.kernel.org
> CC: linux-kernel@vger.kernel.org
> CC: Paolo Bonzini <pbonzini@redhat.com>
> CC: Christian Göttsche <cgzones@googlemail.com>
> ---
>   fs/file_table.c              |  2 ++
>   fs/internal.h                |  2 +-
>   fs/namei.c                   | 54 ++++++++++++++++++++++++++++++++++--
>   fs/open.c                    |  2 +-
>   include/linux/fcntl.h        |  2 ++
>   include/linux/fs.h           |  2 ++
>   include/uapi/linux/openat2.h |  3 ++
>   7 files changed, 63 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/file_table.c b/fs/file_table.c
> index 4f03beed4737..9991bdd538e9 100644
> --- a/fs/file_table.c
> +++ b/fs/file_table.c
> @@ -160,6 +160,8 @@ static int init_file(struct file *f, int flags, const struct cred *cred)
>   	mutex_init(&f->f_pos_lock);
>   	f->f_flags = flags;
>   	f->f_mode = OPEN_FMODE(flags);
> +	f->f_fsuid = cred->fsuid;
> +	f->f_fsgid = cred->fsgid;
>   	/* f->f_version: 0 */
>   
>   	/*
> diff --git a/fs/internal.h b/fs/internal.h
> index 7ca738904e34..692b53b19aad 100644
> --- a/fs/internal.h
> +++ b/fs/internal.h
> @@ -169,7 +169,7 @@ static inline void sb_end_ro_state_change(struct super_block *sb)
>    * open.c
>    */
>   struct open_flags {
> -	int open_flag;
> +	u64 open_flag;
>   	umode_t mode;
>   	int acc_mode;
>   	int intent;
> diff --git a/fs/namei.c b/fs/namei.c
> index 2fde2c320ae9..d1db6ceee4bd 100644
> --- a/fs/namei.c
> +++ b/fs/namei.c
> @@ -586,6 +586,8 @@ struct nameidata {
>   	int		dfd;
>   	vfsuid_t	dir_vfsuid;
>   	umode_t		dir_mode;
> +	kuid_t		dir_open_fsuid;
> +	kgid_t		dir_open_fsgid;
>   } __randomize_layout;
>   
>   #define ND_ROOT_PRESET 1
> @@ -2414,6 +2416,8 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
>   			get_fs_pwd(current->fs, &nd->path);
>   			nd->inode = nd->path.dentry->d_inode;
>   		}
> +		nd->dir_open_fsuid = current_cred()->fsuid;
> +		nd->dir_open_fsgid = current_cred()->fsgid;

I'm wondering if it would be better to capture the whole cred structure.

Similar to io_register_personality(), which uses get_current_cred().

Only using uid and gid, won't reflect any group memberships or capabilities...

metze

Re: [PATCH 2/2] openat2: add OA2_INHERIT_CRED flag

[stsp]

22.04.2024 22:53, Stefan Metzmacher пишет:
> I'm wondering if it would be better to capture the whole cred structure.
>
> Similar to io_register_personality(), which uses get_current_cred().
>
> Only using uid and gid, won't reflect any group memberships or 
> capabilities...
Hmm, I thought about that, but was
under an impression that with get_current_cred()
you only increment a refcount.
But I guess the trick here is that due
to an RCU machinery, you can actually
get your local copy if someone else
changes it?

I'll try what you say, thanks.

Re: [PATCH 2/2] openat2: add OA2_INHERIT_CRED flag

[stsp]

22.04.2024 22:53, Stefan Metzmacher пишет:
> I'm wondering if it would be better to capture the whole cred structure.
>
> Similar to io_register_personality(), which uses get_current_cred().
>
> Only using uid and gid, won't reflect any group memberships or 
> capabilities... 
I ended up posting v3 where the
group memberships are added but
the rest, including capabilities, is
omitted to avoid security risks.

Does adding just a groupinfo to the
set of overridden members (which is
now: fsuid, fsgid and group_info) address
your concern?
I really think that raising caps is far
out of the scope for my approach, which
aims to be safe and simple. Someone
else can do that later, if need be.

RE: [PATCH 1/2] fs: reorganize path_openat()

[David Laight]

From: Stas Sergeev
> Sent: 22 April 2024 09:45

I seem to have 5 copies of this patch.....

> This patch moves the call to alloc_empty_file() below the call to
> path_init(). That changes is needed for the next patch, which adds
> a cred override for alloc_empty_file(). The needed cred info is only
> available after the call to path_init().
> 
> No functional changes are intended by that patch.
...
> ---
>  fs/namei.c | 26 +++++++++++++++++---------
>  1 file changed, 17 insertions(+), 9 deletions(-)
> 
> diff --git a/fs/namei.c b/fs/namei.c
> index c5b2a25be7d0..2fde2c320ae9 100644
> --- a/fs/namei.c
> +++ b/fs/namei.c
> @@ -3782,22 +3782,30 @@ static struct file *path_openat(struct nameidata *nd,
>  	struct file *file;
>  	int error;
> 
> -	file = alloc_empty_file(op->open_flag, current_cred());
> -	if (IS_ERR(file))
> -		return file;
> -
> -	if (unlikely(file->f_flags & __O_TMPFILE)) {
> +	if (unlikely(op->open_flag & __O_TMPFILE)) {
> +		file = alloc_empty_file(op->open_flag, current_cred());
> +		if (IS_ERR(file))
> +			return file;
>  		error = do_tmpfile(nd, flags, op, file);
> -	} else if (unlikely(file->f_flags & O_PATH)) {
> +	} else if (unlikely(op->open_flag & O_PATH)) {
> +		file = alloc_empty_file(op->open_flag, current_cred());
> +		if (IS_ERR(file))
> +			return file;
>  		error = do_o_path(nd, flags, file);

You probably ought to merge the two 'unlikely' tests.
Otherwise there'll be two conditionals in the 'hot path'.
(There probably always were.)
So something like:
	if (unlikely(op->open_flag & (__O_TMPFILE | O_PATH))) {
		file = alloc_empty_file(op->open_flag, current_cred());
		if (IS_ERR(file))
			return file;
		if (op->open_flag & __O_TMFILE)
			error = do_tmpfile(nd, flags, op, file);
		else
			error = do_o_path(nd, flags, file);
	} else {
Copying op->open_flag to a local may also generate better code.

	David
		
>  	} else {
>  		const char *s = path_init(nd, flags);
> -		while (!(error = link_path_walk(s, nd)) &&
> -		       (s = open_last_lookups(nd, file, op)) != NULL)
> -			;
> +		file = alloc_empty_file(op->open_flag, current_cred());
> +		error = PTR_ERR_OR_ZERO(file);
> +		if (!error) {
> +			while (!(error = link_path_walk(s, nd)) &&
> +			       (s = open_last_lookups(nd, file, op)) != NULL)
> +				;
> +		}
>  		if (!error)
>  			error = do_open(nd, file, op);
>  		terminate_walk(nd);
> +		if (IS_ERR(file))
> +			return file;
>  	}
>  	if (likely(!error)) {
>  		if (likely(file->f_mode & FMODE_OPENED))
> --
> 2.44.0
> 

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

Re: [PATCH 1/2] fs: reorganize path_openat()

[stsp]

24.04.2024 12:17, David Laight пишет:
> From: Stas Sergeev
>> Sent: 22 April 2024 09:45
> I seem to have 5 copies of this patch.....

Yep, its re-sent with every new iteartion,
but doesn't change by itself (the other
one changes).
Is there anything I can do to avoid
unneeded duplicates of an unchanged
patch?
Manually reduce Cc list until the patch
changes? That looks too much of a trouble
though.

> You probably ought to merge the two 'unlikely' tests.

Ok.


> Copying op->open_flag to a local may also generate better code.

Can't gcc deduce this on its own?
But ok, will do.

Re: [PATCH 1/2] fs: reorganize path_openat()

[stsp]

24.04.2024 12:17, David Laight пишет:
> You probably ought to merge the two 'unlikely' tests.
> Otherwise there'll be two conditionals in the 'hot path'.
> (There probably always were.)
> So something like:
> 	if (unlikely(op->open_flag & (__O_TMPFILE | O_PATH))) {
> 		file = alloc_empty_file(op->open_flag, current_cred());
> 		if (IS_ERR(file))
> 			return file;
> 		if (op->open_flag & __O_TMFILE)
> 			error = do_tmpfile(nd, flags, op, file);
> 		else
> 			error = do_o_path(nd, flags, file);
> 	} else {

Posted v4 with this code verbatim.

> Copying op->open_flag to a local may also generate better code.
Done this as well.

Thank you.

RE: [PATCH 1/2] fs: reorganize path_openat()

[David Laight]

From: stsp
> Sent: 24 April 2024 11:59
...
> Posted v4 with this code verbatim.

Nope - you've just posted a different version of the 'v1' patch.
Should be [PATCH v4 1/2]

	David

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

Re: [PATCH 1/2] fs: reorganize path_openat()

[stsp]

24.04.2024 18:07, David Laight пишет:
> From: stsp
>> Sent: 24 April 2024 11:59
> ...
>> Posted v4 with this code verbatim.
> Nope - you've just posted a different version of the 'v1' patch.
> Should be [PATCH v4 1/2]
I simply use `git format-patch`
and `git send-email`.
Are all those customizations needs
to be done by hands?

Re: [PATCH 1/2] fs: reorganize path_openat()

[kernel test robot]

Hello,

kernel test robot noticed "BUG:sleeping_function_called_from_invalid_context_at_include/linux/sched/mm.h" on:

commit: 831d3c6cc6f05873e33f4aaebafbb9c27618ea0b ("[PATCH 1/2] fs: reorganize path_openat()")
url: https://github.com/intel-lab-lkp/linux/commits/Stas-Sergeev/fs-reorganize-path_openat/20240424-185527
base: https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git 9d1ddab261f3e2af7c384dc02238784ce0cf9f98
patch link: https://lore.kernel.org/all/20240424105248.189032-2-stsp2@yandex.ru/
patch subject: [PATCH 1/2] fs: reorganize path_openat()

in testcase: boot

compiler: clang-17
test machine: qemu-system-x86_64 -enable-kvm -cpu SandyBridge -smp 2 -m 16G

(please refer to attached dmesg/kmsg for entire log/backtrace)


+-------------------------------------------------------------------------------+------------+------------+
|                                                                               | 9d1ddab261 | 831d3c6cc6 |
+-------------------------------------------------------------------------------+------------+------------+
| boot_successes                                                                | 6          | 0          |
| boot_failures                                                                 | 0          | 6          |
| BUG:sleeping_function_called_from_invalid_context_at_include/linux/sched/mm.h | 0          | 6          |
+-------------------------------------------------------------------------------+------------+------------+


If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202404251525.39b4af4e-lkp@intel.com


[    0.591465][   T33] BUG: sleeping function called from invalid context at include/linux/sched/mm.h:315
[    0.592508][   T33] in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 33, name: kworker/u8:2
[    0.593515][   T33] preempt_count: 0, expected: 0
[    0.594071][   T33] RCU nest depth: 1, expected: 0
[    0.594633][   T33] CPU: 0 PID: 33 Comm: kworker/u8:2 Not tainted 6.9.0-rc5-00037-g831d3c6cc6f0 #1
[    0.595637][   T33] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
[    0.596216][   T33] Workqueue: async async_run_entry_fn
[    0.596216][   T33] Call Trace:
[    0.596216][   T33]  <TASK>
[ 0.596216][ T33] dump_stack_lvl (lib/dump_stack.c:116) 
[ 0.596216][ T33] __might_resched (kernel/sched/core.c:10198) 
[ 0.596216][ T33] kmem_cache_alloc (include/linux/kernel.h:73 include/linux/sched/mm.h:315 mm/slub.c:3746 mm/slub.c:3827 mm/slub.c:3852) 
[ 0.596216][ T33] alloc_empty_file (fs/file_table.c:203) 
[ 0.596216][ T33] path_openat (fs/namei.c:3796) 
[ 0.596216][ T33] do_filp_open (fs/namei.c:3833) 
[ 0.596216][ T33] file_open_name (fs/open.c:1352) 
[ 0.596216][ T33] filp_open (fs/open.c:1371) 
[ 0.596216][ T33] do_name (init/initramfs.c:373) 
[ 0.596216][ T33] flush_buffer (init/initramfs.c:452 init/initramfs.c:464) 
[ 0.596216][ T33] ? __pfx_flush_buffer (init/initramfs.c:458) 
[ 0.596216][ T33] __gunzip (lib/decompress_inflate.c:161) 
[ 0.596216][ T33] ? __pfx_nofill (lib/decompress_inflate.c:37) 
[ 0.596216][ T33] unpack_to_rootfs (init/initramfs.c:520) 
[ 0.596216][ T33] ? __pfx_error (init/initramfs.c:59) 
[ 0.596216][ T33] do_populate_rootfs (init/initramfs.c:714) 
[ 0.596216][ T33] async_run_entry_fn (kernel/async.c:136) 
[ 0.596216][ T33] process_scheduled_works (kernel/workqueue.c:3259) 
[ 0.596216][ T33] worker_thread (include/linux/list.h:373 kernel/workqueue.c:955 kernel/workqueue.c:3417) 
[ 0.596216][ T33] ? __pfx_worker_thread (kernel/workqueue.c:3362) 
[ 0.596216][ T33] kthread (kernel/kthread.c:390) 
[ 0.596216][ T33] ? __pfx_kthread (kernel/kthread.c:341) 
[ 0.596216][ T33] ret_from_fork (arch/x86/kernel/process.c:153) 
[ 0.596216][ T33] ? __pfx_kthread (kernel/kthread.c:341) 
[ 0.596216][ T33] ret_from_fork_asm (arch/x86/entry/entry_64.S:257) 
[    0.596216][   T33]  </TASK>
[    1.603321][   T33] BUG: sleeping function called from invalid context at include/linux/sched/mm.h:315
[    1.604448][   T33] in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 33, name: kworker/u8:2
[    1.605466][   T33] preempt_count: 0, expected: 0
[    1.606028][   T33] RCU nest depth: 1, expected: 0
[    1.606599][   T33] CPU: 0 PID: 33 Comm: kworker/u8:2 Tainted: G        W          6.9.0-rc5-00037-g831d3c6cc6f0 #1
[    1.607761][   T33] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
[    1.608136][   T33] Workqueue: async async_run_entry_fn
[    1.608136][   T33] Call Trace:
[    1.608136][   T33]  <TASK>
[ 1.608136][ T33] dump_stack_lvl (lib/dump_stack.c:116) 
[ 1.608136][ T33] __might_resched (kernel/sched/core.c:10198) 
[ 1.608136][ T33] kmem_cache_alloc (include/linux/kernel.h:73 include/linux/sched/mm.h:315 mm/slub.c:3746 mm/slub.c:3827 mm/slub.c:3852) 
[ 1.608136][ T33] alloc_empty_file (fs/file_table.c:203) 
[ 1.608136][ T33] path_openat (fs/namei.c:3796) 
[ 1.608136][ T33] do_filp_open (fs/namei.c:3833) 
[ 1.608136][ T33] file_open_name (fs/open.c:1352) 
[ 1.608136][ T33] filp_open (fs/open.c:1371) 
[ 1.608136][ T33] do_name (init/initramfs.c:373) 
[ 1.608136][ T33] flush_buffer (init/initramfs.c:452 init/initramfs.c:464) 
[ 1.608136][ T33] ? __pfx_flush_buffer (init/initramfs.c:458) 
[ 1.608136][ T33] __gunzip (lib/decompress_inflate.c:161) 
[ 1.608136][ T33] ? __pfx_nofill (lib/decompress_inflate.c:37) 
[ 1.608136][ T33] unpack_to_rootfs (init/initramfs.c:520) 
[ 1.608136][ T33] ? __pfx_error (init/initramfs.c:59) 
[ 1.608136][ T33] do_populate_rootfs (init/initramfs.c:714) 
[ 1.608136][ T33] async_run_entry_fn (kernel/async.c:136) 
[ 1.608136][ T33] process_scheduled_works (kernel/workqueue.c:3259) 
[ 1.608136][ T33] worker_thread (include/linux/list.h:373 kernel/workqueue.c:955 kernel/workqueue.c:3417) 
[ 1.608136][ T33] ? __pfx_worker_thread (kernel/workqueue.c:3362) 
[ 1.608136][ T33] kthread (kernel/kthread.c:390) 
[ 1.608136][ T33] ? __pfx_kthread (kernel/kthread.c:341) 
[ 1.608136][ T33] ret_from_fork (arch/x86/kernel/process.c:153) 
[ 1.608136][ T33] ? __pfx_kthread (kernel/kthread.c:341) 
[ 1.608136][ T33] ret_from_fork_asm (arch/x86/entry/entry_64.S:257) 
[    1.608136][   T33]  </TASK>
[    2.602317][   T33] BUG: sleeping function called from invalid context at include/linux/sched/mm.h:315
[    2.603414][   T33] in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 33, name: kworker/u8:2
[    2.604433][   T33] preempt_count: 0, expected: 0
[    2.604985][   T33] RCU nest depth: 1, expected: 0
[    2.605547][   T33] CPU: 0 PID: 33 Comm: kworker/u8:2 Tainted: G        W          6.9.0-rc5-00037-g831d3c6cc6f0 #1
[    2.606689][   T33] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
[    2.607825][   T33] Workqueue: async async_run_entry_fn
[    2.608140][   T33] Call Trace:
[    2.608140][   T33]  <TASK>
[ 2.608140][ T33] dump_stack_lvl (lib/dump_stack.c:116) 
[ 2.608140][ T33] __might_resched (kernel/sched/core.c:10198) 
[ 2.608140][ T33] kmem_cache_alloc (include/linux/kernel.h:73 include/linux/sched/mm.h:315 mm/slub.c:3746 mm/slub.c:3827 mm/slub.c:3852) 
[ 2.608140][ T33] alloc_empty_file (fs/file_table.c:203) 
[ 2.608140][ T33] path_openat (fs/namei.c:3796) 
[ 2.608140][ T33] do_filp_open (fs/namei.c:3833) 
[ 2.608140][ T33] file_open_name (fs/open.c:1352) 
[ 2.608140][ T33] filp_open (fs/open.c:1371) 
[ 2.608140][ T33] do_name (init/initramfs.c:373) 
[ 2.608140][ T33] flush_buffer (init/initramfs.c:452 init/initramfs.c:464) 
[ 2.608140][ T33] ? __pfx_flush_buffer (init/initramfs.c:458) 
[ 2.608140][ T33] __gunzip (lib/decompress_inflate.c:161) 
[ 2.608140][ T33] ? __pfx_nofill (lib/decompress_inflate.c:37) 
[ 2.608140][ T33] unpack_to_rootfs (init/initramfs.c:520) 
[ 2.608140][ T33] ? __pfx_error (init/initramfs.c:59) 
[ 2.608140][ T33] do_populate_rootfs (init/initramfs.c:714) 
[ 2.608140][ T33] async_run_entry_fn (kernel/async.c:136) 
[ 2.608140][ T33] process_scheduled_works (kernel/workqueue.c:3259) 
[ 2.608140][ T33] worker_thread (include/linux/list.h:373 kernel/workqueue.c:955 kernel/workqueue.c:3417) 
[ 2.608140][ T33] ? __pfx_worker_thread (kernel/workqueue.c:3362) 
[ 2.608140][ T33] kthread (kernel/kthread.c:390) 
[ 2.608140][ T33] ? __pfx_kthread (kernel/kthread.c:341) 
[ 2.608140][ T33] ret_from_fork (arch/x86/kernel/process.c:153) 
[ 2.608140][ T33] ? __pfx_kthread (kernel/kthread.c:341) 
[ 2.608140][ T33] ret_from_fork_asm (arch/x86/entry/entry_64.S:257) 
[    2.608140][   T33]  </TASK>
[    3.648001][   T33] BUG: sleeping function called from invalid context at include/linux/sched/mm.h:315
[    3.649103][   T33] in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 33, name: kworker/u8:2
[    3.650109][   T33] preempt_count: 0, expected: 0
[    3.650660][   T33] RCU nest depth: 1, expected: 0
[    3.651223][   T33] CPU: 0 PID: 33 Comm: kworker/u8:2 Tainted: G        W          6.9.0-rc5-00037-g831d3c6cc6f0 #1
[    3.651979][   T33] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
[    3.651979][   T33] Workqueue: async async_run_entry_fn
[    3.651979][   T33] Call Trace:
[    3.651979][   T33]  <TASK>
[ 3.651979][ T33] dump_stack_lvl (lib/dump_stack.c:116) 
[ 3.651979][ T33] __might_resched (kernel/sched/core.c:10198) 
[ 3.651979][ T33] kmem_cache_alloc (include/linux/kernel.h:73 include/linux/sched/mm.h:315 mm/slub.c:3746 mm/slub.c:3827 mm/slub.c:3852) 
[ 3.651979][ T33] alloc_empty_file (fs/file_table.c:203) 
[ 3.651979][ T33] path_openat (fs/namei.c:3796) 
[ 3.651979][ T33] do_filp_open (fs/namei.c:3833) 
[ 3.651979][ T33] file_open_name (fs/open.c:1352) 
[ 3.651979][ T33] filp_open (fs/open.c:1371) 
[ 3.651979][ T33] do_name (init/initramfs.c:373) 
[ 3.651979][ T33] flush_buffer (init/initramfs.c:452 init/initramfs.c:464) 
[ 3.651979][ T33] ? __pfx_flush_buffer (init/initramfs.c:458) 
[ 3.651979][ T33] __gunzip (lib/decompress_inflate.c:161) 
[ 3.651979][ T33] ? __pfx_nofill (lib/decompress_inflate.c:37) 
[ 3.651979][ T33] unpack_to_rootfs (init/initramfs.c:520) 
[ 3.651979][ T33] ? __pfx_error (init/initramfs.c:59) 
[ 3.651979][ T33] do_populate_rootfs (init/initramfs.c:714) 
[ 3.651979][ T33] async_run_entry_fn (kernel/async.c:136) 
[ 3.651979][ T33] process_scheduled_works (kernel/workqueue.c:3259) 
[ 3.651979][ T33] worker_thread (include/linux/list.h:373 kernel/workqueue.c:955 kernel/workqueue.c:3417) 
[ 3.651979][ T33] ? __pfx_worker_thread (kernel/workqueue.c:3362) 
[ 3.651979][ T33] kthread (kernel/kthread.c:390) 
[ 3.651979][ T33] ? __pfx_kthread (kernel/kthread.c:341) 
[ 3.651979][ T33] ret_from_fork (arch/x86/kernel/process.c:153) 
[ 3.651979][ T33] ? __pfx_kthread (kernel/kthread.c:341) 
[ 3.651979][ T33] ret_from_fork_asm (arch/x86/entry/entry_64.S:257) 
[    3.651979][   T33]  </TASK>
[    3.705833][   T33] Freeing initrd memory: 185612K



The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20240425/202404251525.39b4af4e-lkp@intel.com



-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

[PATCH 1/2] fs: reorganize path_openat()

[Stas Sergeev]

This patch moves the call to alloc_empty_file() below the call to
path_init(). That changes is needed for the next patch, which adds
a cred override for alloc_empty_file(). The needed cred info is only
available after the call to path_init().

No functional changes are intended by that patch.

Signed-off-by: Stas Sergeev <stsp2@yandex.ru>

CC: Eric Biederman <ebiederm@xmission.com>
CC: Alexander Viro <viro@zeniv.linux.org.uk>
CC: Christian Brauner <brauner@kernel.org>
CC: Jan Kara <jack@suse.cz>
CC: Andy Lutomirski <luto@kernel.org>
CC: David Laight <David.Laight@ACULAB.COM>
CC: linux-fsdevel@vger.kernel.org
CC: linux-kernel@vger.kernel.org
---
 fs/namei.c | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index c5b2a25be7d0..413eef134234 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3781,23 +3781,30 @@ static struct file *path_openat(struct nameidata *nd,
 {
 	struct file *file;
 	int error;
+	u64 open_flags = op->open_flag;
 
-	file = alloc_empty_file(op->open_flag, current_cred());
-	if (IS_ERR(file))
-		return file;
-
-	if (unlikely(file->f_flags & __O_TMPFILE)) {
-		error = do_tmpfile(nd, flags, op, file);
-	} else if (unlikely(file->f_flags & O_PATH)) {
-		error = do_o_path(nd, flags, file);
+	if (unlikely(open_flags & (__O_TMPFILE | O_PATH))) {
+		file = alloc_empty_file(open_flags, current_cred());
+		if (IS_ERR(file))
+			return file;
+		if (open_flags & __O_TMPFILE)
+			error = do_tmpfile(nd, flags, op, file);
+		else
+			error = do_o_path(nd, flags, file);
 	} else {
 		const char *s = path_init(nd, flags);
-		while (!(error = link_path_walk(s, nd)) &&
-		       (s = open_last_lookups(nd, file, op)) != NULL)
-			;
+		file = alloc_empty_file(open_flags, current_cred());
+		error = PTR_ERR_OR_ZERO(file);
+		if (!error) {
+			while (!(error = link_path_walk(s, nd)) &&
+			       (s = open_last_lookups(nd, file, op)) != NULL)
+				;
+		}
 		if (!error)
 			error = do_open(nd, file, op);
 		terminate_walk(nd);
+		if (IS_ERR(file))
+			return file;
 	}
 	if (likely(!error)) {
 		if (likely(file->f_mode & FMODE_OPENED))
-- 
2.44.0

[PATCH 1/2] fs: reorganize path_openat()

[Stas Sergeev]

This patch moves the call to alloc_empty_file() below the call to
path_init(). That changes is needed for the next patch, which adds
a cred override for alloc_empty_file(). The needed cred info is only
available after the call to path_init().

No functional changes are intended by that patch.

Signed-off-by: Stas Sergeev <stsp2@yandex.ru>

CC: Eric Biederman <ebiederm@xmission.com>
CC: Alexander Viro <viro@zeniv.linux.org.uk>
CC: Christian Brauner <brauner@kernel.org>
CC: Jan Kara <jack@suse.cz>
CC: Andy Lutomirski <luto@kernel.org>
CC: linux-fsdevel@vger.kernel.org
CC: linux-kernel@vger.kernel.org
---
 fs/namei.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index c5b2a25be7d0..2fde2c320ae9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3782,22 +3782,30 @@ static struct file *path_openat(struct nameidata *nd,
 	struct file *file;
 	int error;
 
-	file = alloc_empty_file(op->open_flag, current_cred());
-	if (IS_ERR(file))
-		return file;
-
-	if (unlikely(file->f_flags & __O_TMPFILE)) {
+	if (unlikely(op->open_flag & __O_TMPFILE)) {
+		file = alloc_empty_file(op->open_flag, current_cred());
+		if (IS_ERR(file))
+			return file;
 		error = do_tmpfile(nd, flags, op, file);
-	} else if (unlikely(file->f_flags & O_PATH)) {
+	} else if (unlikely(op->open_flag & O_PATH)) {
+		file = alloc_empty_file(op->open_flag, current_cred());
+		if (IS_ERR(file))
+			return file;
 		error = do_o_path(nd, flags, file);
 	} else {
 		const char *s = path_init(nd, flags);
-		while (!(error = link_path_walk(s, nd)) &&
-		       (s = open_last_lookups(nd, file, op)) != NULL)
-			;
+		file = alloc_empty_file(op->open_flag, current_cred());
+		error = PTR_ERR_OR_ZERO(file);
+		if (!error) {
+			while (!(error = link_path_walk(s, nd)) &&
+			       (s = open_last_lookups(nd, file, op)) != NULL)
+				;
+		}
 		if (!error)
 			error = do_open(nd, file, op);
 		terminate_walk(nd);
+		if (IS_ERR(file))
+			return file;
 	}
 	if (likely(!error)) {
 		if (likely(file->f_mode & FMODE_OPENED))
-- 
2.44.0

[PATCH 1/2] fs: reorganize path_openat()

[Stas Sergeev]

This patch moves the call to alloc_empty_file() below the call to
path_init(). That changes is needed for the next patch, which adds
a cred override for alloc_empty_file(). The needed cred info is only
available after the call to path_init().

No functional changes are intended by that patch.

Signed-off-by: Stas Sergeev <stsp2@yandex.ru>

CC: Eric Biederman <ebiederm@xmission.com>
CC: Alexander Viro <viro@zeniv.linux.org.uk>
CC: Christian Brauner <brauner@kernel.org>
CC: Jan Kara <jack@suse.cz>
CC: Andy Lutomirski <luto@kernel.org>
CC: linux-fsdevel@vger.kernel.org
CC: linux-kernel@vger.kernel.org
---
 fs/namei.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index c5b2a25be7d0..2fde2c320ae9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3782,22 +3782,30 @@ static struct file *path_openat(struct nameidata *nd,
 	struct file *file;
 	int error;
 
-	file = alloc_empty_file(op->open_flag, current_cred());
-	if (IS_ERR(file))
-		return file;
-
-	if (unlikely(file->f_flags & __O_TMPFILE)) {
+	if (unlikely(op->open_flag & __O_TMPFILE)) {
+		file = alloc_empty_file(op->open_flag, current_cred());
+		if (IS_ERR(file))
+			return file;
 		error = do_tmpfile(nd, flags, op, file);
-	} else if (unlikely(file->f_flags & O_PATH)) {
+	} else if (unlikely(op->open_flag & O_PATH)) {
+		file = alloc_empty_file(op->open_flag, current_cred());
+		if (IS_ERR(file))
+			return file;
 		error = do_o_path(nd, flags, file);
 	} else {
 		const char *s = path_init(nd, flags);
-		while (!(error = link_path_walk(s, nd)) &&
-		       (s = open_last_lookups(nd, file, op)) != NULL)
-			;
+		file = alloc_empty_file(op->open_flag, current_cred());
+		error = PTR_ERR_OR_ZERO(file);
+		if (!error) {
+			while (!(error = link_path_walk(s, nd)) &&
+			       (s = open_last_lookups(nd, file, op)) != NULL)
+				;
+		}
 		if (!error)
 			error = do_open(nd, file, op);
 		terminate_walk(nd);
+		if (IS_ERR(file))
+			return file;
 	}
 	if (likely(!error)) {
 		if (likely(file->f_mode & FMODE_OPENED))
-- 
2.44.0

[PATCH 1/2] fs: reorganize path_openat()

[Stas Sergeev]

This patch moves the call to alloc_empty_file() below the call to
path_init(). That changes is needed for the next patch, which adds
a cred override for alloc_empty_file(). The needed cred info is only
available after the call to path_init().

No functional changes are intended by that patch.

Signed-off-by: Stas Sergeev <stsp2@yandex.ru>

CC: Eric Biederman <ebiederm@xmission.com>
CC: Alexander Viro <viro@zeniv.linux.org.uk>
CC: Christian Brauner <brauner@kernel.org>
CC: Jan Kara <jack@suse.cz>
CC: Andy Lutomirski <luto@kernel.org>
CC: linux-fsdevel@vger.kernel.org
CC: linux-kernel@vger.kernel.org
---
 fs/namei.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index c5b2a25be7d0..2fde2c320ae9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3782,22 +3782,30 @@ static struct file *path_openat(struct nameidata *nd,
 	struct file *file;
 	int error;
 
-	file = alloc_empty_file(op->open_flag, current_cred());
-	if (IS_ERR(file))
-		return file;
-
-	if (unlikely(file->f_flags & __O_TMPFILE)) {
+	if (unlikely(op->open_flag & __O_TMPFILE)) {
+		file = alloc_empty_file(op->open_flag, current_cred());
+		if (IS_ERR(file))
+			return file;
 		error = do_tmpfile(nd, flags, op, file);
-	} else if (unlikely(file->f_flags & O_PATH)) {
+	} else if (unlikely(op->open_flag & O_PATH)) {
+		file = alloc_empty_file(op->open_flag, current_cred());
+		if (IS_ERR(file))
+			return file;
 		error = do_o_path(nd, flags, file);
 	} else {
 		const char *s = path_init(nd, flags);
-		while (!(error = link_path_walk(s, nd)) &&
-		       (s = open_last_lookups(nd, file, op)) != NULL)
-			;
+		file = alloc_empty_file(op->open_flag, current_cred());
+		error = PTR_ERR_OR_ZERO(file);
+		if (!error) {
+			while (!(error = link_path_walk(s, nd)) &&
+			       (s = open_last_lookups(nd, file, op)) != NULL)
+				;
+		}
 		if (!error)
 			error = do_open(nd, file, op);
 		terminate_walk(nd);
+		if (IS_ERR(file))
+			return file;
 	}
 	if (likely(!error)) {
 		if (likely(file->f_mode & FMODE_OPENED))
-- 
2.44.0

[PATCH 1/2] fs: reorganize path_openat()

[Stas Sergeev]

This patch moves the call to alloc_empty_file() below the call to
path_init(). That changes is needed for the next patch, which adds
a cred override for alloc_empty_file(). The needed cred info is only
available after the call to path_init().

No functional changes are intended by that patch.

Signed-off-by: Stas Sergeev <stsp2@yandex.ru>

CC: Eric Biederman <ebiederm@xmission.com>
CC: Alexander Viro <viro@zeniv.linux.org.uk>
CC: Christian Brauner <brauner@kernel.org>
CC: Jan Kara <jack@suse.cz>
CC: Andy Lutomirski <luto@kernel.org>
CC: linux-fsdevel@vger.kernel.org
CC: linux-kernel@vger.kernel.org
---
 fs/namei.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index c5b2a25be7d0..2fde2c320ae9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3782,22 +3782,30 @@ static struct file *path_openat(struct nameidata *nd,
 	struct file *file;
 	int error;
 
-	file = alloc_empty_file(op->open_flag, current_cred());
-	if (IS_ERR(file))
-		return file;
-
-	if (unlikely(file->f_flags & __O_TMPFILE)) {
+	if (unlikely(op->open_flag & __O_TMPFILE)) {
+		file = alloc_empty_file(op->open_flag, current_cred());
+		if (IS_ERR(file))
+			return file;
 		error = do_tmpfile(nd, flags, op, file);
-	} else if (unlikely(file->f_flags & O_PATH)) {
+	} else if (unlikely(op->open_flag & O_PATH)) {
+		file = alloc_empty_file(op->open_flag, current_cred());
+		if (IS_ERR(file))
+			return file;
 		error = do_o_path(nd, flags, file);
 	} else {
 		const char *s = path_init(nd, flags);
-		while (!(error = link_path_walk(s, nd)) &&
-		       (s = open_last_lookups(nd, file, op)) != NULL)
-			;
+		file = alloc_empty_file(op->open_flag, current_cred());
+		error = PTR_ERR_OR_ZERO(file);
+		if (!error) {
+			while (!(error = link_path_walk(s, nd)) &&
+			       (s = open_last_lookups(nd, file, op)) != NULL)
+				;
+		}
 		if (!error)
 			error = do_open(nd, file, op);
 		terminate_walk(nd);
+		if (IS_ERR(file))
+			return file;
 	}
 	if (likely(!error)) {
 		if (likely(file->f_mode & FMODE_OPENED))
-- 
2.44.0