diff mbox series

[RFC,v2,1/2] mm: restrictedmem: Allow userspace to specify mount for memfd_restricted

Message ID 6e800e069c7fc400841b75ea49d1227bd101c1cf.1679428901.git.ackerleytng@google.com (mailing list archive)
State New
Headers show
Series Providing mount in memfd_restricted() syscall | expand

Commit Message

Ackerley Tng March 21, 2023, 8:15 p.m. UTC
By default, the backing shmem file for a restrictedmem fd is created
on shmem's kernel space mount.

With this patch, an optional tmpfs mount can be specified via an fd,
which will be used as the mountpoint for backing the shmem file
associated with a restrictedmem fd.

This change is modeled after how sys_open() can create an unnamed
temporary file in a given directory with O_TMPFILE.

This will help restrictedmem fds inherit the properties of the
provided tmpfs mounts, for example, hugepage allocation hints, NUMA
binding hints, etc.

Signed-off-by: Ackerley Tng <ackerleytng@google.com>
---
 include/linux/syscalls.h           |  2 +-
 include/uapi/linux/restrictedmem.h |  8 ++++
 mm/restrictedmem.c                 | 63 +++++++++++++++++++++++++++---
 3 files changed, 66 insertions(+), 7 deletions(-)
 create mode 100644 include/uapi/linux/restrictedmem.h

Comments

Christian Brauner March 22, 2023, 11:19 a.m. UTC | #1
On Tue, Mar 21, 2023 at 08:15:32PM +0000, Ackerley Tng wrote:
> By default, the backing shmem file for a restrictedmem fd is created
> on shmem's kernel space mount.
> 
> With this patch, an optional tmpfs mount can be specified via an fd,
> which will be used as the mountpoint for backing the shmem file
> associated with a restrictedmem fd.
> 
> This change is modeled after how sys_open() can create an unnamed
> temporary file in a given directory with O_TMPFILE.
> 
> This will help restrictedmem fds inherit the properties of the
> provided tmpfs mounts, for example, hugepage allocation hints, NUMA
> binding hints, etc.
> 
> Signed-off-by: Ackerley Tng <ackerleytng@google.com>
> ---
>  include/linux/syscalls.h           |  2 +-
>  include/uapi/linux/restrictedmem.h |  8 ++++
>  mm/restrictedmem.c                 | 63 +++++++++++++++++++++++++++---
>  3 files changed, 66 insertions(+), 7 deletions(-)
>  create mode 100644 include/uapi/linux/restrictedmem.h
> 
> diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
> index f9e9e0c820c5..a23c4c385cd3 100644
> --- a/include/linux/syscalls.h
> +++ b/include/linux/syscalls.h
> @@ -1056,7 +1056,7 @@ asmlinkage long sys_memfd_secret(unsigned int flags);
>  asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len,
>  					    unsigned long home_node,
>  					    unsigned long flags);
> -asmlinkage long sys_memfd_restricted(unsigned int flags);
> +asmlinkage long sys_memfd_restricted(unsigned int flags, int mount_fd);
>  
>  /*
>   * Architecture-specific system calls
> diff --git a/include/uapi/linux/restrictedmem.h b/include/uapi/linux/restrictedmem.h
> new file mode 100644
> index 000000000000..9f108dd1ac4c
> --- /dev/null
> +++ b/include/uapi/linux/restrictedmem.h
> @@ -0,0 +1,8 @@
> +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
> +#ifndef _UAPI_LINUX_RESTRICTEDMEM_H
> +#define _UAPI_LINUX_RESTRICTEDMEM_H
> +
> +/* flags for memfd_restricted */
> +#define RMFD_TMPFILE		0x0001U
> +
> +#endif /* _UAPI_LINUX_RESTRICTEDMEM_H */
> diff --git a/mm/restrictedmem.c b/mm/restrictedmem.c
> index c5d869d8c2d8..4d83b949d84e 100644
> --- a/mm/restrictedmem.c
> +++ b/mm/restrictedmem.c
> @@ -1,11 +1,12 @@
>  // SPDX-License-Identifier: GPL-2.0
> -#include "linux/sbitmap.h"
> +#include <linux/namei.h>
>  #include <linux/pagemap.h>
>  #include <linux/pseudo_fs.h>
>  #include <linux/shmem_fs.h>
>  #include <linux/syscalls.h>
>  #include <uapi/linux/falloc.h>
>  #include <uapi/linux/magic.h>
> +#include <uapi/linux/restrictedmem.h>
>  #include <linux/restrictedmem.h>
>  
>  struct restrictedmem {
> @@ -189,19 +190,20 @@ static struct file *restrictedmem_file_create(struct file *memfd)
>  	return file;
>  }
>  
> -SYSCALL_DEFINE1(memfd_restricted, unsigned int, flags)
> +static int restrictedmem_create(struct vfsmount *mount)
>  {
>  	struct file *file, *restricted_file;
>  	int fd, err;
>  
> -	if (flags)
> -		return -EINVAL;
> -
>  	fd = get_unused_fd_flags(0);
>  	if (fd < 0)
>  		return fd;
>  
> -	file = shmem_file_setup("memfd:restrictedmem", 0, VM_NORESERVE);
> +	if (mount)
> +		file = shmem_file_setup_with_mnt(mount, "memfd:restrictedmem", 0, VM_NORESERVE);
> +	else
> +		file = shmem_file_setup("memfd:restrictedmem", 0, VM_NORESERVE);
> +
>  	if (IS_ERR(file)) {
>  		err = PTR_ERR(file);
>  		goto err_fd;
> @@ -223,6 +225,55 @@ SYSCALL_DEFINE1(memfd_restricted, unsigned int, flags)
>  	return err;
>  }
>  
> +static bool is_shmem_mount(struct vfsmount *mnt)
> +{
> +	return mnt && mnt->mnt_sb && mnt->mnt_sb->s_magic == TMPFS_MAGIC;
> +}
> +
> +static int restrictedmem_create_from_file(int mount_fd)
> +{
> +	int ret;
> +	struct fd f;
> +	struct vfsmount *mnt;
> +
> +	f = fdget_raw(mount_fd);
> +	if (!f.file)
> +		return -EBADF;
> +
> +	mnt = f.file->f_path.mnt;
> +	if (!is_shmem_mount(mnt)) {
> +		ret = -EINVAL;
> +		goto out;
> +	}
> +

This looks like you can just pass in some tmpfs fd and you just use it
to identify the mnt and then you create a restricted memfd area in that
instance. So if I did:

mount -t tmpfs tmpfs /mnt
mknod /mnt/bla c 0 0
fd = open("/mnt/bla")
memfd_restricted(fd)

then it would create a memfd restricted entry in the tmpfs instance
using the arbitrary dummy device node to infer the tmpfs instance.

Looking at the older thread briefly and the cover letter. Afaict, the
new mount api shouldn't figure into the design of this. fsopen() returns
fds referencing a VFS-internal fs_context object. They can't be used to
create or lookup files or identify mounts. The mount doesn't exist at
that time. Not even a superblock might exist at the time before
fsconfig(FSCONFIG_CMD_CREATE).

When fsmount() is called after superblock setup then it's similar to any
other fd from open() or open_tree() or whatever (glossing over some
details that are irrelevant here). Difference is that open_tree() and
fsmount() would refer to the root of a mount.

At first I wondered why this doesn't just use standard *at() semantics
but I guess the restricted memfd is unlinked and doesn't show up in the
tmpfs instance.

So if you go down that route then I would suggest to enforce that the
provided fd refer to the root of a tmpfs mount. IOW, it can't just be an
arbitrary file descriptor in a tmpfs instance. That seems cleaner to me:

sb = f_path->mnt->mnt_sb;
sb->s_magic == TMPFS_MAGIC && f_path->mnt->mnt_root == sb->s_root

and has much tigher semantics than just allowing any kind of fd.

Another wrinkly I find odd but that's for you to judge is that this
bypasses the permission model of the tmpfs instance. IOW, as long as you
have a handle to the root of a tmpfs mount you can just create
restricted memfds in there. So if I provided a completely sandboxed
service - running in a user namespace or whatever - with an fd to the
host's tmpfs instance they can just create restricted memfds in there no
questions asked.

Maybe that's fine but it's certainly something to spell out and think
about the implications.
diff mbox series

Patch

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index f9e9e0c820c5..a23c4c385cd3 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1056,7 +1056,7 @@  asmlinkage long sys_memfd_secret(unsigned int flags);
 asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len,
 					    unsigned long home_node,
 					    unsigned long flags);
-asmlinkage long sys_memfd_restricted(unsigned int flags);
+asmlinkage long sys_memfd_restricted(unsigned int flags, int mount_fd);
 
 /*
  * Architecture-specific system calls
diff --git a/include/uapi/linux/restrictedmem.h b/include/uapi/linux/restrictedmem.h
new file mode 100644
index 000000000000..9f108dd1ac4c
--- /dev/null
+++ b/include/uapi/linux/restrictedmem.h
@@ -0,0 +1,8 @@ 
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_RESTRICTEDMEM_H
+#define _UAPI_LINUX_RESTRICTEDMEM_H
+
+/* flags for memfd_restricted */
+#define RMFD_TMPFILE		0x0001U
+
+#endif /* _UAPI_LINUX_RESTRICTEDMEM_H */
diff --git a/mm/restrictedmem.c b/mm/restrictedmem.c
index c5d869d8c2d8..4d83b949d84e 100644
--- a/mm/restrictedmem.c
+++ b/mm/restrictedmem.c
@@ -1,11 +1,12 @@ 
 // SPDX-License-Identifier: GPL-2.0
-#include "linux/sbitmap.h"
+#include <linux/namei.h>
 #include <linux/pagemap.h>
 #include <linux/pseudo_fs.h>
 #include <linux/shmem_fs.h>
 #include <linux/syscalls.h>
 #include <uapi/linux/falloc.h>
 #include <uapi/linux/magic.h>
+#include <uapi/linux/restrictedmem.h>
 #include <linux/restrictedmem.h>
 
 struct restrictedmem {
@@ -189,19 +190,20 @@  static struct file *restrictedmem_file_create(struct file *memfd)
 	return file;
 }
 
-SYSCALL_DEFINE1(memfd_restricted, unsigned int, flags)
+static int restrictedmem_create(struct vfsmount *mount)
 {
 	struct file *file, *restricted_file;
 	int fd, err;
 
-	if (flags)
-		return -EINVAL;
-
 	fd = get_unused_fd_flags(0);
 	if (fd < 0)
 		return fd;
 
-	file = shmem_file_setup("memfd:restrictedmem", 0, VM_NORESERVE);
+	if (mount)
+		file = shmem_file_setup_with_mnt(mount, "memfd:restrictedmem", 0, VM_NORESERVE);
+	else
+		file = shmem_file_setup("memfd:restrictedmem", 0, VM_NORESERVE);
+
 	if (IS_ERR(file)) {
 		err = PTR_ERR(file);
 		goto err_fd;
@@ -223,6 +225,55 @@  SYSCALL_DEFINE1(memfd_restricted, unsigned int, flags)
 	return err;
 }
 
+static bool is_shmem_mount(struct vfsmount *mnt)
+{
+	return mnt && mnt->mnt_sb && mnt->mnt_sb->s_magic == TMPFS_MAGIC;
+}
+
+static int restrictedmem_create_from_file(int mount_fd)
+{
+	int ret;
+	struct fd f;
+	struct vfsmount *mnt;
+
+	f = fdget_raw(mount_fd);
+	if (!f.file)
+		return -EBADF;
+
+	mnt = f.file->f_path.mnt;
+	if (!is_shmem_mount(mnt)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = mnt_want_write(mnt);
+	if (unlikely(ret))
+		goto out;
+
+	ret = restrictedmem_create(mnt);
+
+	mnt_drop_write(mnt);
+out:
+	fdput(f);
+
+	return ret;
+}
+
+SYSCALL_DEFINE2(memfd_restricted, unsigned int, flags, int, mount_fd)
+{
+	if (flags & ~RMFD_TMPFILE)
+		return -EINVAL;
+
+	if (flags == RMFD_TMPFILE) {
+		if (mount_fd < 0)
+			return -EINVAL;
+
+		return restrictedmem_create_from_file(mount_fd);
+	} else {
+		return restrictedmem_create(NULL);
+	}
+}
+
 int restrictedmem_bind(struct file *file, pgoff_t start, pgoff_t end,
 		       struct restrictedmem_notifier *notifier, bool exclusive)
 {