Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Fri,  5 Aug 2022 22:21:26 +0000
In-Reply-To: <20220805222126.142525-1-jeffxu@google.com>
Message-Id: <20220805222126.142525-6-jeffxu@google.com>
Mime-Version: 1.0
References: <20220805222126.142525-1-jeffxu@google.com>
Subject: [PATCH v2 5/5] sysctl: add support for mfd_noexec
From:   <jeffxu@google.com>
To:     skhan@linuxfoundation.org
Cc:     akpm@linux-foundation.org, dmitry.torokhov@gmail.com,
        dverkamp@chromium.org, hughd@google.com, jeffxu@google.com,
        jorgelo@chromium.org, keescook@chromium.org,
        linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org,
        linux-mm@kvack.org, mnissler@chromium.org, jannh@google.com,
        Jeff Xu <jeffxu@chromium.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

From: Jeff Xu <jeffxu@chromium.org>

Add vm.mfd_noexec.  When the value is 1 (enabled),
memfd_create syscall will created non-executable memfd.

The default value is 0 (disabled), admin can change the
setting from 0 => 1, however 1 => 0 is not allowed,
unless reboot.

Signed-off-by: Jeff Xu <jeffxu@chromium.org>
---
 include/linux/mm.h |  4 ++++
 kernel/sysctl.c    |  9 +++++++++
 mm/memfd.c         | 27 +++++++++++++++++++++++++++
 3 files changed, 40 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7898e29bcfb5..1c66cf4aca11 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -203,6 +203,10 @@ extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
 extern unsigned long sysctl_overcommit_kbytes;
 
+extern int sysctl_mfd_noexec_scope;
+extern int mfd_noexec_dointvec_minmax(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos);
+
 int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *,
 		loff_t *);
 int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b233714a1c78..54510da007ff 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2362,6 +2362,15 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= mmap_min_addr_handler,
 	},
+	{
+		.procname       = "mfd_noexec",
+		.data           = &sysctl_mfd_noexec_scope,
+		.maxlen         = sizeof(sysctl_mfd_noexec_scope),
+		.mode           = 0644,
+		.proc_handler   = mfd_noexec_dointvec_minmax,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
 #endif
 #ifdef CONFIG_NUMA
 	{
diff --git a/mm/memfd.c b/mm/memfd.c
index b841514eb0fd..c6ccb8481ed2 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -20,6 +20,11 @@
 #include <linux/memfd.h>
 #include <uapi/linux/memfd.h>
 
+#define MFD_NOEXEC_SCOPE_DISABLED	0
+#define MFD_NOEXEC_SCOPE_ENABLED	1
+
+int sysctl_mfd_noexec_scope __read_mostly = MFD_NOEXEC_SCOPE_DISABLED;
+
 /*
  * We need a tag: a new tag would expand every xa_node by 8 bytes,
  * so reuse a tag which we firmly believe is never set or cleared on tmpfs
@@ -275,6 +280,10 @@ SYSCALL_DEFINE2(memfd_create,
 	char *name;
 	long len;
 
+	if (sysctl_mfd_noexec_scope == MFD_NOEXEC_SCOPE_ENABLED) {
+		flags |= MFD_NOEXEC;
+	}
+
 	if (!(flags & MFD_HUGETLB)) {
 		if (flags & ~(unsigned int)MFD_ALL_FLAGS)
 			return -EINVAL;
@@ -351,3 +360,21 @@ SYSCALL_DEFINE2(memfd_create,
 	kfree(name);
 	return error;
 }
+
+#ifdef CONFIG_SYSCTL
+int mfd_noexec_dointvec_minmax(struct ctl_table *table, int write,
+		void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table table_copy;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* Lock the max value if it ever gets set. */
+	table_copy = *table;
+	if (*(int *)table_copy.data == *(int *)table_copy.extra2)
+		table_copy.extra1 = table_copy.extra2;
+
+	return proc_dointvec_minmax(&table_copy, write, buffer, lenp, ppos);
+}
+#endif
-- 
2.37.1.559.g78731f0fdb-goog