linux-kernel - [RFC PATCH 1/2] mm: restrictedmem: Add flag as THP allocation hint for memfd

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: <4ea08e03d57152d505b747a6a570752dd698e315.1676680548.git.ackerleytng@google.com>
Date:   Sat, 18 Feb 2023 00:43:01 +0000
From:   Ackerley Tng <ackerleytng@...gle.com>
To:     kvm@...r.kernel.org, linux-api@...r.kernel.org,
        linux-arch@...r.kernel.org, linux-doc@...r.kernel.org,
        linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org, qemu-devel@...gnu.org
Cc:     aarcange@...hat.com, ak@...ux.intel.com, akpm@...ux-foundation.org,
        arnd@...db.de, bfields@...ldses.org, bp@...en8.de,
        chao.p.peng@...ux.intel.com, corbet@....net, dave.hansen@...el.com,
        david@...hat.com, ddutile@...hat.com, dhildenb@...hat.com,
        hpa@...or.com, hughd@...gle.com, jlayton@...nel.org,
        jmattson@...gle.com, joro@...tes.org, jun.nakajima@...el.com,
        kirill.shutemov@...ux.intel.com, linmiaohe@...wei.com,
        luto@...nel.org, mail@...iej.szmigiero.name, mhocko@...e.com,
        michael.roth@....com, mingo@...hat.com, naoya.horiguchi@....com,
        pbonzini@...hat.com, qperret@...gle.com, rppt@...nel.org,
        seanjc@...gle.com, shuah@...nel.org, steven.price@....com,
        tabba@...gle.com, tglx@...utronix.de, vannapurve@...gle.com,
        vbabka@...e.cz, vkuznets@...hat.com, wanpengli@...cent.com,
        wei.w.wang@...el.com, x86@...nel.org, yu.c.zhang@...ux.intel.com,
        Ackerley Tng <ackerleytng@...gle.com>
Subject: [RFC PATCH 1/2] mm: restrictedmem: Add flag as THP allocation hint
 for memfd_restricted() syscall

Allow userspace to hint the kernel to use Transparent HugePages to
back restricted memory on a per-file basis.

Signed-off-by: Ackerley Tng <ackerleytng@...gle.com>
---
 include/uapi/linux/restrictedmem.h |  1 +
 mm/restrictedmem.c                 | 27 +++++++++++++++++----------
 2 files changed, 18 insertions(+), 10 deletions(-)

diff --git a/include/uapi/linux/restrictedmem.h b/include/uapi/linux/restrictedmem.h
index 9f108dd1ac4c..f671ccbb43bc 100644
--- a/include/uapi/linux/restrictedmem.h
+++ b/include/uapi/linux/restrictedmem.h
@@ -4,5 +4,6 @@
 
 /* flags for memfd_restricted */
 #define RMFD_TMPFILE		0x0001U
+#define RMFD_HUGEPAGE		0x0002U
 
 #endif /* _UAPI_LINUX_RESTRICTEDMEM_H */
diff --git a/mm/restrictedmem.c b/mm/restrictedmem.c
index 97f3e2159e8b..87c829960b31 100644
--- a/mm/restrictedmem.c
+++ b/mm/restrictedmem.c
@@ -190,19 +190,25 @@ static struct file *restrictedmem_file_create(struct file *memfd)
 	return file;
 }
 
-static int restrictedmem_create(struct vfsmount *mount)
+static int restrictedmem_create(unsigned int flags, struct vfsmount *mount)
 {
 	struct file *file, *restricted_file;
 	int fd, err;
+	unsigned long shmem_setup_flags = VM_NORESERVE;
 
 	fd = get_unused_fd_flags(0);
 	if (fd < 0)
 		return fd;
 
-	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 (flags & RMFD_HUGEPAGE)
+		shmem_setup_flags |= VM_HUGEPAGE;
+
+	if (mount) {
+		file = shmem_file_setup_with_mnt(mount, "memfd:restrictedmem",
+						 0, shmem_setup_flags);
+	} else {
+		file = shmem_file_setup("memfd:restrictedmem", 0, shmem_setup_flags);
+	}
 
 	if (IS_ERR(file)) {
 		err = PTR_ERR(file);
@@ -230,7 +236,8 @@ static bool is_shmem_mount(struct vfsmount *mnt)
 	return mnt->mnt_sb->s_magic == TMPFS_MAGIC;
 }
 
-static int restrictedmem_create_from_path(const char __user *mount_path)
+static int restrictedmem_create_from_path(unsigned int flags,
+					  const char __user *mount_path)
 {
 	int ret;
 	struct path path;
@@ -250,7 +257,7 @@ static int restrictedmem_create_from_path(const char __user *mount_path)
 	if (unlikely(ret))
 		goto out;
 
-	ret = restrictedmem_create(path.mnt);
+	ret = restrictedmem_create(flags, path.mnt);
 
 	mnt_drop_write(path.mnt);
 out:
@@ -261,16 +268,16 @@ static int restrictedmem_create_from_path(const char __user *mount_path)
 
 SYSCALL_DEFINE2(memfd_restricted, unsigned int, flags, const char __user *, mount_path)
 {
-	if (flags & ~RMFD_TMPFILE)
+	if (flags & ~(RMFD_TMPFILE | RMFD_HUGEPAGE))
 		return -EINVAL;
 
 	if (flags == RMFD_TMPFILE) {
 		if (!mount_path)
 			return -EINVAL;
 
-		return restrictedmem_create_from_path(mount_path);
+		return restrictedmem_create_from_path(flags, mount_path);
 	} else {
-		return restrictedmem_create(NULL);
+		return restrictedmem_create(flags, NULL);
 	}
 }
 
-- 
2.39.2.637.g21b0678d19-goog