linux-kernel - [PATCH 16/16] memfd: memfd_create(name, MFD_MEM

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <be7c30cc-20fd-b5d6-83a2-366410753145@google.com>
Date:   Fri, 30 Jul 2021 01:13:00 -0700 (PDT)
From:   Hugh Dickins <hughd@...gle.com>
To:     Andrew Morton <akpm@...ux-foundation.org>
cc:     Hugh Dickins <hughd@...gle.com>,
        Shakeel Butt <shakeelb@...gle.com>,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        Yang Shi <shy828301@...il.com>,
        Miaohe Lin <linmiaohe@...wei.com>,
        Mike Kravetz <mike.kravetz@...cle.com>,
        Michal Hocko <mhocko@...e.com>,
        Rik van Riel <riel@...riel.com>,
        Christoph Hellwig <hch@...radead.org>,
        Matthew Wilcox <willy@...radead.org>,
        "Eric W. Biederman" <ebiederm@...ssion.com>,
        Alexey Gladkov <legion@...nel.org>,
        Chris Wilson <chris@...is-wilson.co.uk>,
        Matthew Auld <matthew.auld@...el.com>,
        linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-api@...r.kernel.org, linux-mm@...ck.org
Subject: [PATCH 16/16] memfd: memfd_create(name, MFD_MEM_LOCK) for memlocked
 shmem

Now that the size of a memlocked file can be changed, memfd_create() can
accept an MFD_MEM_LOCK flag to request memlocking, even though the initial
size is of course 0.

Signed-off-by: Hugh Dickins <hughd@...gle.com>
---
 include/uapi/linux/memfd.h |  1 +
 mm/memfd.c                 |  7 +++++--
 mm/shmem.c                 | 13 ++++++++++++-
 3 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h
index 8358a69e78cc..9113b5aa1763 100644
--- a/include/uapi/linux/memfd.h
+++ b/include/uapi/linux/memfd.h
@@ -9,6 +9,7 @@
 #define MFD_ALLOW_SEALING	0x0002U
 #define MFD_HUGETLB		0x0004U		/* Use hugetlbfs */
 #define MFD_HUGEPAGE		0x0008U		/* Use huge tmpfs */
+#define MFD_MEM_LOCK		0x0010U		/* Memlock tmpfs */
 
 /*
  * Huge page size encoding when MFD_HUGETLB is specified, and a huge page
diff --git a/mm/memfd.c b/mm/memfd.c
index 0d1a504d2fc9..e39f9eed55d2 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -248,7 +248,8 @@ long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 #define MFD_ALL_FLAGS  (MFD_CLOEXEC | \
 			MFD_ALLOW_SEALING | \
 			MFD_HUGETLB | \
-			MFD_HUGEPAGE)
+			MFD_HUGEPAGE | \
+			MFD_MEM_LOCK)
 
 SYSCALL_DEFINE2(memfd_create,
 		const char __user *, uname,
@@ -262,7 +263,7 @@ SYSCALL_DEFINE2(memfd_create,
 
 	if (flags & MFD_HUGETLB) {
 		/* Disallow huge tmpfs when choosing hugetlbfs */
-		if (flags & MFD_HUGEPAGE)
+		if (flags & (MFD_HUGEPAGE | MFD_MEM_LOCK))
 			return -EINVAL;
 		/* Allow huge page size encoding in flags. */
 		if (flags & ~(unsigned int)(MFD_ALL_FLAGS |
@@ -314,6 +315,8 @@ SYSCALL_DEFINE2(memfd_create,
 
 		if (flags & MFD_HUGEPAGE)
 			vm_flags |= VM_HUGEPAGE;
+		if (flags & MFD_MEM_LOCK)
+			vm_flags |= VM_LOCKED;
 		file = shmem_file_setup(name, 0, vm_flags);
 	}
 
diff --git a/mm/shmem.c b/mm/shmem.c
index fa4a264453bf..a0a83e59ae07 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2395,7 +2395,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 		spin_lock_init(&info->lock);
 		atomic_set(&info->stop_eviction, 0);
 		info->seals = F_SEAL_SEAL;
-		info->flags = flags & VM_NORESERVE;
+		info->flags = flags & (VM_NORESERVE | VM_LOCKED);
 		if ((flags & VM_HUGEPAGE) &&
 		    transparent_hugepage_allowed(sbinfo) &&
 		    !test_bit(MMF_DISABLE_THP, &current->mm->flags))
@@ -4254,6 +4254,17 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l
 	inode->i_size = size;
 	clear_nlink(inode);	/* It is unlinked */
 	res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size));
+	if (!IS_ERR(res) && (flags & VM_LOCKED)) {
+		struct ucounts *ucounts = current_ucounts();
+		/*
+		 * Only memfd_create() may pass VM_LOCKED, and it passes
+		 * size 0; but avoid that assumption in case it changes.
+		 */
+		if (user_shm_lock(size, ucounts, true))
+			SHMEM_I(inode)->mlock_ucounts = ucounts;
+		else
+			res = ERR_PTR(-EPERM);
+	}
 	if (!IS_ERR(res))
 		res = alloc_file_pseudo(inode, mnt, name, O_RDWR,
 				&shmem_file_operations);
-- 
2.26.2