[PATCH net v5 5/7] net: add a sysctl to opt out of virtio net hdr checksum validation

["Michael S. Tsirkin" <mst@redhat.com>]

The ingress validation as implemented by the previous
patch is stricter than what it replaced: GSO
packets whose checksum metadata matches no transport header are
dropped, and non-GSO ones get their checksum completed in place.
Such packets used to pass with the metadata unvalidated,
and with no overhead.

I judge that this should not affect any deployments, but there is still
some risk that it does.  In case a deployment depends on them anyway,
provide a per-netns switch to get the old behavior back:

echo 0 > /proc/sys/net/core/virtio_net_hdr_validate

The default is validating.

Reviewed-by: Björn Töpel <bjorn@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---

Notes (changelog):
    v4->v5:
        document the netns lifetime requirement (sashiko)

 Documentation/admin-guide/sysctl/net.rst | 19 +++++++++
 include/linux/virtio_net.h               | 27 +++++++++++++
 include/net/netns/core.h                 |  1 +
 net/core/dev.c                           |  7 ++++
 net/core/net_namespace.c                 |  1 +
 net/core/sysctl_net_core.c               | 50 ++++++++++++++++++++++++
 6 files changed, 105 insertions(+)

diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index e586e17fc7a5..3c0223575438 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -246,6 +246,25 @@ processes are dropped unless socket option SOF_TIMESTAMPING_OPT_TSONLY is set.
 Default: 1 (on)
 
 
+virtio_net_hdr_validate
+-----------------------
+
+When processing packets with a virtio net header (through tun, tap, a
+packet socket or a virtio network device) that request checksum offload
+(VIRTIO_NET_HDR_F_NEEDS_CSUM), validate the packet: complete the checksum
+in software, or drop the packet where the header does not match it.
+
+When disabled, the header is trusted not to corrupt the packet, and the
+checksum is offloaded to hardware (or not verified if it never reaches
+hardware). This is only safe if no protocol is processing the packets.
+
+The setting is per network namespace, but only writable by the host
+root: root inside a network namespace created by an unprivileged user
+cannot disable the validation.
+
+Default: 1 (on)
+
+
 wmem_default
 ------------
 
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 52852a33a2db..cea70ccf0ed4 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -5,6 +5,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/jump_label.h>
 #include <linux/netdevice.h>
 #include <linux/udp.h>
 #include <net/gso.h>
@@ -78,6 +79,20 @@ static inline struct iphdr *virtio_net_ip4_parse(struct sk_buff *skb,
 	*thoff = nhoff + iph->ihl * sizeof(u32);
 	return iph;
 }
+/* Defined in net/core/dev.c, enabled while any network namespace
+ * has net.core.virtio_net_hdr_validate set to 0.
+ */
+DECLARE_STATIC_KEY_FALSE(virtio_net_hdr_validate_disabled_key);
+
+/* Failsafe: a namespace can disable the check with
+ * net.core.virtio_net_hdr_validate.
+ * The caller must keep the netns of skb->dev alive.
+ */
+static inline bool virtio_net_hdr_validate_disabled(struct sk_buff *skb)
+{
+	return static_branch_unlikely(&virtio_net_hdr_validate_disabled_key) &&
+	       !READ_ONCE(dev_net(skb->dev)->core.sysctl_virtio_net_hdr_validate);
+}
 
 /* Where does the L3 header start, and what protocol is it?
  * Handles Ethernet and VLAN headers; other devices use the
@@ -189,6 +204,12 @@ virtio_net_csum_partial_ok_at_offset(struct sk_buff *skb, u8 hdr_gso_type,
 	unsigned int thoff;
 	int ip_proto;
 
+	/* Failsafe: a namespace opted out of the validation,
+	 * trust the checksum metadata as before.
+	 */
+	if (virtio_net_hdr_validate_disabled(skb))
+		return true;
+
 	if (!virtio_net_l4_start(skb, nhoff, proto, &thoff, &ip_proto))
 		return false;
 
@@ -231,6 +252,9 @@ virtio_net_csum_partial_ok(struct sk_buff *skb, u8 hdr_gso_type)
 	int nhoff;
 	__be16 proto;
 
+	if (virtio_net_hdr_validate_disabled(skb))
+		return true;
+
 	if (!virtio_net_l3_start(skb, &nhoff, &proto))
 		return false;
 
@@ -522,6 +546,9 @@ virtio_net_tnl_offsets_ok(struct sk_buff *skb, bool outer_isv6,
 	unsigned int thoff;
 	int ip_proto;
 
+	if (virtio_net_hdr_validate_disabled(skb))
+		return true;
+
 	if (!virtio_net_l3_start(skb, &nhoff, &proto))
 		return false;
 	if (outer_isv6 != (proto == htons(ETH_P_IPV6)))
diff --git a/include/net/netns/core.h b/include/net/netns/core.h
index 9ef3d70e5e9c..02ce232fe9a9 100644
--- a/include/net/netns/core.h
+++ b/include/net/netns/core.h
@@ -18,6 +18,7 @@ struct netns_core {
 	u8	sysctl_txrehash;
 	u8	sysctl_tstamp_allow_data;
 	u8	sysctl_bypass_prot_mem;
+	u8	sysctl_virtio_net_hdr_validate;
 
 #ifdef CONFIG_PROC_FS
 	struct prot_inuse __percpu *prot_inuse;
diff --git a/net/core/dev.c b/net/core/dev.c
index e76762e29360..43b8823c83f6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -128,6 +128,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <net/ip.h>
+#include <linux/virtio_net.h>
 #include <net/mpls.h>
 #include <linux/ipv6.h>
 #include <linux/in.h>
@@ -2389,6 +2390,12 @@ EXPORT_SYMBOL(tcf_sw_enabled_key);
 
 DEFINE_STATIC_KEY_FALSE(netstamp_needed_key);
 EXPORT_SYMBOL(netstamp_needed_key);
+
+/* Enabled while any network namespace has net.core.virtio_net_hdr_validate
+ * set to 0.
+ */
+DEFINE_STATIC_KEY_FALSE(virtio_net_hdr_validate_disabled_key);
+EXPORT_SYMBOL(virtio_net_hdr_validate_disabled_key);
 #ifdef CONFIG_JUMP_LABEL
 static atomic_t netstamp_needed_deferred;
 static atomic_t netstamp_wanted;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index da5f881fbd3b..8a21baaa7e6d 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -396,6 +396,7 @@ static __net_init void preinit_net_sysctl(struct net *net)
 	net->core.sysctl_optmem_max = 128 * 1024;
 	net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED;
 	net->core.sysctl_tstamp_allow_data = 1;
+	net->core.sysctl_virtio_net_hdr_validate = 1;
 	net->core.sysctl_txq_reselection = msecs_to_jiffies(1000);
 }
 
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index eb35da3556f4..3e4037b82a97 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -18,6 +18,8 @@
 #include <linux/slab.h>
 #include <linux/sched/isolation.h>
 #include <linux/hex.h>
+#include <linux/virtio_net.h>
+#include <linux/jump_label.h>
 
 #include <net/ip.h>
 #include <net/sock.h>
@@ -678,6 +680,43 @@ static struct ctl_table net_core_table[] = {
 	},
 };
 
+/* Protects changes to virtio_net_hdr_validate_disabled_key and each
+ * net->core.sysctl_virtio_net_hdr_validate.  The packet path reads
+ * the value without a lock.
+ */
+static DEFINE_MUTEX(virtio_net_hdr_validate_mutex);
+
+static int virtio_net_hdr_validate_sysctl(const struct ctl_table *table,
+					  int write, void *buffer,
+					  size_t *lenp, loff_t *ppos)
+{
+	u8 *value = table->data;
+	u8 old, new;
+	int ret;
+
+	/* Root in a user namespace must not be able to weaken the
+	 * validation for the network namespace it controls.
+	 */
+	if (write && !capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	mutex_lock(&virtio_net_hdr_validate_mutex);
+
+	old = READ_ONCE(*value);
+	ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos);
+	new = READ_ONCE(*value);
+	if (write && !ret && old != new) {
+		if (new)
+			static_branch_dec(&virtio_net_hdr_validate_disabled_key);
+		else
+			static_branch_inc(&virtio_net_hdr_validate_disabled_key);
+	}
+
+	mutex_unlock(&virtio_net_hdr_validate_mutex);
+
+	return ret;
+}
+
 static const struct ctl_table netns_core_table[] = {
 #if IS_ENABLED(CONFIG_RPS)
 	{
@@ -737,6 +776,15 @@ static const struct ctl_table netns_core_table[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_ONE
 	},
+	{
+		.procname	= "virtio_net_hdr_validate",
+		.data		= &init_net.core.sysctl_virtio_net_hdr_validate,
+		.maxlen		= sizeof(u8),
+		.mode		= 0644,
+		.proc_handler	= virtio_net_hdr_validate_sysctl,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE
+	},
 	/* sysctl_core_net_init() will set the values after this
 	 * to readonly in network namespaces
 	 */
@@ -841,6 +889,8 @@ static __net_exit void sysctl_core_net_exit(struct net *net)
 	tbl = net->core.sysctl_hdr->ctl_table_arg;
 	unregister_net_sysctl_table(net->core.sysctl_hdr);
 	BUG_ON(tbl == netns_core_table);
+	if (!net->core.sysctl_virtio_net_hdr_validate)
+		static_branch_dec(&virtio_net_hdr_validate_disabled_key);
 #if IS_ENABLED(CONFIG_RPS)
 	kfree(net->core.rps_default_mask);
 #endif
-- 
MST