From: Ackerley Tng <ackerleytng@google.com>
To: kvm@vger.kernel.org, linux-api@vger.kernel.org,
linux-arch@vger.kernel.org, linux-doc@vger.kernel.org,
linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, qemu-devel@nongnu.org
Cc: aarcange@redhat.com, ak@linux.intel.com,
akpm@linux-foundation.org, arnd@arndb.de, bfields@fieldses.org,
bp@alien8.de, chao.p.peng@linux.intel.com, corbet@lwn.net,
dave.hansen@intel.com, david@redhat.com, ddutile@redhat.com,
dhildenb@redhat.com, hpa@zytor.com, hughd@google.com,
jlayton@kernel.org, jmattson@google.com, joro@8bytes.org,
jun.nakajima@intel.com, kirill.shutemov@linux.intel.com,
linmiaohe@huawei.com, luto@kernel.org,
mail@maciej.szmigiero.name, mhocko@suse.com,
michael.roth@amd.com, mingo@redhat.com, naoya.horiguchi@nec.com,
pbonzini@redhat.com, qperret@google.com, rppt@kernel.org,
seanjc@google.com, shuah@kernel.org, steven.price@arm.com,
tabba@google.com, tglx@linutronix.de, vannapurve@google.com,
vbabka@suse.cz, vkuznets@redhat.com, wanpengli@tencent.com,
wei.w.wang@intel.com, x86@kernel.org,
yu.c.zhang@linux.intel.com,
Ackerley Tng <ackerleytng@google.com>
Subject: [RFC PATCH v2 1/2] mm: restrictedmem: Allow userspace to specify mount for memfd_restricted
Date: Tue, 21 Mar 2023 20:15:32 +0000 [thread overview]
Message-ID: <6e800e069c7fc400841b75ea49d1227bd101c1cf.1679428901.git.ackerleytng@google.com> (raw)
In-Reply-To: <cover.1679428901.git.ackerleytng@google.com>
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;
+ }
+
+ 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)
{
--
2.40.0.rc2.332.ga46443480c-goog
next prev parent reply other threads:[~2023-03-21 20:15 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-21 20:15 [RFC PATCH v2 0/2] Providing mount in memfd_restricted() syscall Ackerley Tng
2023-03-21 20:15 ` Ackerley Tng [this message]
2023-03-22 11:19 ` [RFC PATCH v2 1/2] mm: restrictedmem: Allow userspace to specify mount for memfd_restricted Christian Brauner
2023-03-31 23:56 ` Ackerley Tng
2023-03-21 20:15 ` [RFC PATCH v2 2/2] selftests: restrictedmem: Check hugepage-ness of shmem file backing restrictedmem fd Ackerley Tng
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=6e800e069c7fc400841b75ea49d1227bd101c1cf.1679428901.git.ackerleytng@google.com \
--to=ackerleytng@google.com \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=arnd@arndb.de \
--cc=bfields@fieldses.org \
--cc=bp@alien8.de \
--cc=chao.p.peng@linux.intel.com \
--cc=corbet@lwn.net \
--cc=dave.hansen@intel.com \
--cc=david@redhat.com \
--cc=ddutile@redhat.com \
--cc=dhildenb@redhat.com \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=jlayton@kernel.org \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=jun.nakajima@intel.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=linmiaohe@huawei.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mail@maciej.szmigiero.name \
--cc=mhocko@suse.com \
--cc=michael.roth@amd.com \
--cc=mingo@redhat.com \
--cc=naoya.horiguchi@nec.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=qperret@google.com \
--cc=rppt@kernel.org \
--cc=seanjc@google.com \
--cc=shuah@kernel.org \
--cc=steven.price@arm.com \
--cc=tabba@google.com \
--cc=tglx@linutronix.de \
--cc=vannapurve@google.com \
--cc=vbabka@suse.cz \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=wei.w.wang@intel.com \
--cc=x86@kernel.org \
--cc=yu.c.zhang@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox