| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20220310140911.50924-2-chao.p.peng@linux.intel.com>
Date: Thu, 10 Mar 2022 22:08:59 +0800
From: Chao Peng <chao.p.peng@...ux.intel.com>
To: kvm@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-mm@...ck.org, linux-fsdevel@...r.kernel.org,
linux-api@...r.kernel.org, qemu-devel@...gnu.org
Cc: Paolo Bonzini <pbonzini@...hat.com>,
Jonathan Corbet <corbet@....net>,
Sean Christopherson <seanjc@...gle.com>,
Vitaly Kuznetsov <vkuznets@...hat.com>,
Wanpeng Li <wanpengli@...cent.com>,
Jim Mattson <jmattson@...gle.com>,
Joerg Roedel <joro@...tes.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
x86@...nel.org, "H . Peter Anvin" <hpa@...or.com>,
Hugh Dickins <hughd@...gle.com>,
Jeff Layton <jlayton@...nel.org>,
"J . Bruce Fields" <bfields@...ldses.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Mike Rapoport <rppt@...nel.org>,
Steven Price <steven.price@....com>,
"Maciej S . Szmigiero" <mail@...iej.szmigiero.name>,
Vlastimil Babka <vbabka@...e.cz>,
Vishal Annapurve <vannapurve@...gle.com>,
Yu Zhang <yu.c.zhang@...ux.intel.com>,
Chao Peng <chao.p.peng@...ux.intel.com>,
"Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>,
luto@...nel.org, jun.nakajima@...el.com, dave.hansen@...el.com,
ak@...ux.intel.com, david@...hat.com
Subject: [PATCH v5 01/13] mm/memfd: Introduce MFD_INACCESSIBLE flag
From: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Introduce a new memfd_create() flag indicating the content of the
created memfd is inaccessible from userspace through ordinary MMU
access (e.g., read/write/mmap). However, the file content can be
accessed via a different mechanism (e.g. KVM MMU) indirectly.
It provides semantics required for KVM guest private memory support
that a file descriptor with this flag set is going to be used as the
source of guest memory in confidential computing environments such
as Intel TDX/AMD SEV but may not be accessible from host userspace.
Since page migration/swapping is not yet supported for such usages
so these pages are currently marked as UNMOVABLE and UNEVICTABLE
which makes them behave like long-term pinned pages.
The flag can not coexist with MFD_ALLOW_SEALING, future sealing is
also impossible for a memfd created with this flag.
At this time only shmem implements this flag.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@...ux.intel.com>
---
include/linux/shmem_fs.h | 7 +++++
include/uapi/linux/memfd.h | 1 +
mm/memfd.c | 26 +++++++++++++++--
mm/shmem.c | 57 ++++++++++++++++++++++++++++++++++++++
4 files changed, 88 insertions(+), 3 deletions(-)
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index e65b80ed09e7..2dde843f28ef 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -12,6 +12,9 @@
/* inode in-kernel data */
+/* shmem extended flags */
+#define SHM_F_INACCESSIBLE 0x0001 /* prevent ordinary MMU access (e.g. read/write/mmap) to file content */
+
struct shmem_inode_info {
spinlock_t lock;
unsigned int seals; /* shmem seals */
@@ -24,6 +27,7 @@ struct shmem_inode_info {
struct shared_policy policy; /* NUMA memory alloc policy */
struct simple_xattrs xattrs; /* list of xattrs */
atomic_t stop_eviction; /* hold when working on inode */
+ unsigned int xflags; /* shmem extended flags */
struct inode vfs_inode;
};
@@ -61,6 +65,9 @@ extern struct file *shmem_file_setup(const char *name,
loff_t size, unsigned long flags);
extern struct file *shmem_kernel_file_setup(const char *name, loff_t size,
unsigned long flags);
+extern struct file *shmem_file_setup_xflags(const char *name, loff_t size,
+ unsigned long flags,
+ unsigned int xflags);
extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt,
const char *name, loff_t size, unsigned long flags);
extern int shmem_zero_setup(struct vm_area_struct *);
diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h
index 7a8a26751c23..48750474b904 100644
--- a/include/uapi/linux/memfd.h
+++ b/include/uapi/linux/memfd.h
@@ -8,6 +8,7 @@
#define MFD_CLOEXEC 0x0001U
#define MFD_ALLOW_SEALING 0x0002U
#define MFD_HUGETLB 0x0004U
+#define MFD_INACCESSIBLE 0x0008U
/*
* Huge page size encoding when MFD_HUGETLB is specified, and a huge page
diff --git a/mm/memfd.c b/mm/memfd.c
index 9f80f162791a..74d45a26cf5d 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -245,16 +245,20 @@ long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
#define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)
#define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
-#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB)
+#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | \
+ MFD_INACCESSIBLE)
SYSCALL_DEFINE2(memfd_create,
const char __user *, uname,
unsigned int, flags)
{
+ struct address_space *mapping;
unsigned int *file_seals;
+ unsigned int xflags;
struct file *file;
int fd, error;
char *name;
+ gfp_t gfp;
long len;
if (!(flags & MFD_HUGETLB)) {
@@ -267,6 +271,10 @@ SYSCALL_DEFINE2(memfd_create,
return -EINVAL;
}
+ /* Disallow sealing when MFD_INACCESSIBLE is set. */
+ if (flags & MFD_INACCESSIBLE && flags & MFD_ALLOW_SEALING)
+ return -EINVAL;
+
/* length includes terminating zero */
len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
if (len <= 0)
@@ -301,8 +309,11 @@ SYSCALL_DEFINE2(memfd_create,
HUGETLB_ANONHUGE_INODE,
(flags >> MFD_HUGE_SHIFT) &
MFD_HUGE_MASK);
- } else
- file = shmem_file_setup(name, 0, VM_NORESERVE);
+ } else {
+ xflags = flags & MFD_INACCESSIBLE ? SHM_F_INACCESSIBLE : 0;
+ file = shmem_file_setup_xflags(name, 0, VM_NORESERVE, xflags);
+ }
+
if (IS_ERR(file)) {
error = PTR_ERR(file);
goto err_fd;
@@ -313,6 +324,15 @@ SYSCALL_DEFINE2(memfd_create,
if (flags & MFD_ALLOW_SEALING) {
file_seals = memfd_file_seals_ptr(file);
*file_seals &= ~F_SEAL_SEAL;
+ } else if (flags & MFD_INACCESSIBLE) {
+ mapping = file_inode(file)->i_mapping;
+ gfp = mapping_gfp_mask(mapping);
+ gfp &= ~__GFP_MOVABLE;
+ mapping_set_gfp_mask(mapping, gfp);
+ mapping_set_unevictable(mapping);
+
+ file_seals = memfd_file_seals_ptr(file);
+ *file_seals = F_SEAL_SEAL;
}
fd_install(fd, file);
diff --git a/mm/shmem.c b/mm/shmem.c
index a09b29ec2b45..9b31a7056009 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1084,6 +1084,13 @@ static int shmem_setattr(struct user_namespace *mnt_userns,
(newsize > oldsize && (info->seals & F_SEAL_GROW)))
return -EPERM;
+ if (info->xflags & SHM_F_INACCESSIBLE) {
+ if(oldsize)
+ return -EPERM;
+ if (!PAGE_ALIGNED(newsize))
+ return -EINVAL;
+ }
+
if (newsize != oldsize) {
error = shmem_reacct_size(SHMEM_I(inode)->flags,
oldsize, newsize);
@@ -1331,6 +1338,8 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
goto redirty;
if (!total_swap_pages)
goto redirty;
+ if (info->xflags & SHM_F_INACCESSIBLE)
+ goto redirty;
/*
* Our capabilities prevent regular writeback or sync from ever calling
@@ -2228,6 +2237,9 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
if (ret)
return ret;
+ if (info->xflags & SHM_F_INACCESSIBLE)
+ return -EPERM;
+
/* arm64 - allow memory tagging on RAM-based files */
vma->vm_flags |= VM_MTE_ALLOWED;
@@ -2433,6 +2445,8 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size)
return -EPERM;
}
+ if (unlikely(info->xflags & SHM_F_INACCESSIBLE))
+ return -EPERM;
ret = shmem_getpage(inode, index, pagep, SGP_WRITE);
@@ -2517,6 +2531,21 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
end_index = i_size >> PAGE_SHIFT;
if (index > end_index)
break;
+
+ /*
+ * inode_lock protects setting up seals as well as write to
+ * i_size. Setting SHM_F_INACCESSIBLE only allowed with
+ * i_size == 0.
+ *
+ * Check SHM_F_INACCESSIBLE after i_size. It effectively
+ * serialize read vs. setting SHM_F_INACCESSIBLE without
+ * taking inode_lock in read path.
+ */
+ if (SHMEM_I(inode)->xflags & SHM_F_INACCESSIBLE) {
+ error = -EPERM;
+ break;
+ }
+
if (index == end_index) {
nr = i_size & ~PAGE_MASK;
if (nr <= offset)
@@ -2648,6 +2677,12 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
goto out;
}
+ if ((info->xflags & SHM_F_INACCESSIBLE) &&
+ (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len))) {
+ error = -EINVAL;
+ goto out;
+ }
+
shmem_falloc.waitq = &shmem_falloc_waitq;
shmem_falloc.start = (u64)unmap_start >> PAGE_SHIFT;
shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
@@ -4082,6 +4117,28 @@ struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned lon
return __shmem_file_setup(shm_mnt, name, size, flags, S_PRIVATE);
}
+/**
+ * shmem_file_setup_xflags - get an unlinked file living in tmpfs with
+ * additional xflags.
+ * @name: name for dentry (to be seen in /proc/<pid>/maps
+ * @size: size to be set for the file
+ * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
+ * @xflags: SHM_F_INACCESSIBLE prevents ordinary MMU access to the file content
+ */
+
+struct file *shmem_file_setup_xflags(const char *name, loff_t size,
+ unsigned long flags, unsigned int xflags)
+{
+ struct shmem_inode_info *info;
+ struct file *res = __shmem_file_setup(shm_mnt, name, size, flags, 0);
+
+ if(!IS_ERR(res)) {
+ info = SHMEM_I(file_inode(res));
+ info->xflags = xflags & SHM_F_INACCESSIBLE;
+ }
+ return res;
+}
+
/**
* shmem_file_setup - get an unlinked file living in tmpfs
* @name: name for dentry (to be seen in /proc/<pid>/maps
--
2.17.1
Powered by blists - more mailing lists