[PATCH RFC v7 1/5] net: account for ingress-resolved virtio net hdr state

[PATCH RFC v7 1/5] net: account for ingress-resolved virtio net hdr state

[Michael S. Tsirkin]

The following patch will add ingress resolution of uncommon virtio net
hdr checksum metadata (software checksum completion at ingress) which
adds performance overhead to the packet processing.

We should make it visible, so a hypothetical workload relying on
uncommon metadata can be distinguished from none at all. This way issues
in the parsing will be reported and not quietly pay the host-CPU
checksum overhead instead of offload.

Flip every call to virtio_net_hdr_to_skb to test for negative errno
only.  The um vector raw transport even ignored the return value
altogether: rejected packets went on into the stack with their
metadata unvalidated, so check it there as well.

Have tun count these events per device as rx_csum_sw, exposed via
ethtool -S.

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

Notes (changelog):
    v4->v5:
        count on tun only: dropped the tap, macvtap, ipvtap and
        virtio_net counters (Willem de Bruijn)

 arch/um/drivers/vector_transports.c |  4 ++-
 drivers/net/tap.c                   |  4 +--
 drivers/net/tun.c                   | 41 +++++++++++++++++++++++++++--
 drivers/net/virtio_net.c            |  2 +-
 net/packet/af_packet.c              |  4 +--
 5 files changed, 47 insertions(+), 8 deletions(-)

diff --git a/arch/um/drivers/vector_transports.c b/arch/um/drivers/vector_transports.c
index e1fb2a76fdff..8b7548458663 100644
--- a/arch/um/drivers/vector_transports.c
+++ b/arch/um/drivers/vector_transports.c
@@ -210,7 +210,9 @@ static int raw_verify_header(
 		return 1;
 
 	skb_set_network_header(skb, ETH_HLEN);
-	virtio_net_hdr_to_skb(skb, vheader, virtio_legacy_is_little_endian());
+	if (virtio_net_hdr_to_skb(skb, vheader,
+			virtio_legacy_is_little_endian()) < 0)
+		return -1;
 	return 0;
 }
 
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 2f19fb07bb2d..101994870bac 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -650,7 +650,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 
 	if (vnet_hdr_len) {
 		err = tun_vnet_hdr_to_skb(q->flags, skb, &vnet_hdr);
-		if (err) {
+		if (err < 0) {
 			rcu_read_unlock();
 			drop_reason = SKB_DROP_REASON_DEV_HDR;
 			goto err_kfree;
@@ -1090,7 +1090,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 
 	if (vnet_hdr_len) {
 		err = tun_vnet_hdr_to_skb(q->flags, skb, gso);
-		if (err) {
+		if (err < 0) {
 			rcu_read_unlock();
 			goto err_kfree;
 		}
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 770b8fe085c3..82ea59594eba 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -210,6 +210,7 @@ struct tun_struct {
 	u32 flow_count;
 	u32 rx_batched;
 	atomic_long_t rx_frame_errors;
+	atomic64_t rx_csum_sw;
 	struct bpf_prog __rcu *xdp_prog;
 	struct tun_prog __rcu *steering_prog;
 	struct tun_prog __rcu *filter_prog;
@@ -1944,10 +1945,14 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		break;
 	}
 
-	if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr)) {
+	err = tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, &hdr);
+	if (err < 0) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		err = -EINVAL;
 		goto free_skb;
+	} else if (err > 0) {
+		atomic64_inc(&tun->rx_csum_sw);
+		err = 0;
 	}
 
 	if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP)
@@ -2615,11 +2620,15 @@ static int tun_xdp_one(struct tun_struct *tun,
 	tnl_hdr = (struct virtio_net_hdr_v1_hash_tunnel *)gso;
 	skb->dev = tun->dev;
 	skb_set_network_header(skb, ETH_HLEN);
-	if (tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, tnl_hdr)) {
+	ret = tun_vnet_hdr_tnl_to_skb(tun->flags, features, skb, tnl_hdr);
+	if (ret < 0) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		kfree_skb(skb);
 		ret = -EINVAL;
 		goto out;
+	} else if (ret > 0) {
+		atomic64_inc(&tun->rx_csum_sw);
+		ret = 0;
 	}
 
 	skb->protocol = eth_type_trans(skb, tun->dev);
@@ -3749,7 +3758,35 @@ static void tun_get_channels(struct net_device *dev,
 	channels->max_combined = tun->flags & IFF_MULTI_QUEUE ? MAX_TAP_QUEUES : 1;
 }
 
+#define TUN_STATS_LEN	1
+static const char tun_ethtool_strings[TUN_STATS_LEN][ETH_GSTRING_LEN] = {
+	"rx_csum_sw",
+};
+
+static int tun_get_sset_count(struct net_device *dev, int sset)
+{
+	return sset == ETH_SS_STATS ? TUN_STATS_LEN : -EOPNOTSUPP;
+}
+
+static void tun_get_strings(struct net_device *dev, u32 stringset, u8 *data)
+{
+	if (stringset == ETH_SS_STATS)
+		memcpy(data, tun_ethtool_strings,
+		       sizeof(tun_ethtool_strings));
+}
+
+static void tun_get_ethtool_stats(struct net_device *dev,
+				  struct ethtool_stats *stats, u64 *data)
+{
+	struct tun_struct *tun = netdev_priv(dev);
+
+	data[0] = atomic64_read(&tun->rx_csum_sw);
+}
+
 static const struct ethtool_ops tun_ethtool_ops = {
+	.get_sset_count		= tun_get_sset_count,
+	.get_strings		= tun_get_strings,
+	.get_ethtool_stats	= tun_get_ethtool_stats,
 	.supported_coalesce_params = ETHTOOL_COALESCE_RX_MAX_FRAMES,
 	.get_drvinfo	= tun_get_drvinfo,
 	.get_msglevel	= tun_get_msglevel,
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index dd2c41ef6fbe..dd3f39516f90 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2535,7 +2535,7 @@ static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue *
 	skb_set_network_header(skb, ETH_HLEN);
 	if (virtio_net_hdr_tnl_to_skb(skb, &hdr->tnl_hdr, vi->rx_tnl,
 				      vi->rx_tnl_csum,
-				      virtio_is_little_endian(vi->vdev))) {
+				      virtio_is_little_endian(vi->vdev)) < 0) {
 		net_warn_ratelimited("%s: bad gso: type: %x, size: %u, flags %x tunnel %d tnl csum %d\n",
 				     dev->name, hdr->hdr.gso_type,
 				     hdr->hdr.gso_size, hdr->hdr.flags,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 823e0911c910..c0cd36be53d6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2921,7 +2921,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		}
 
 		if (has_vnet_hdr) {
-			if (virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le())) {
+			if (virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()) < 0) {
 				tp_len = -EINVAL;
 				goto tpacket_error;
 			}
@@ -3144,7 +3144,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	if (vnet_hdr_sz) {
 		err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
-		if (err)
+		if (err < 0)
 			goto out_free;
 		len += vnet_hdr_sz;
 	}
-- 
MST

[PATCH RFC v7 2/5] um: vector: trim skbs before verifying the header

[Michael S. Tsirkin]

The vector receive path over-allocates the skb and only trims it
to the received length after the transport header is verified.

A follow up patch will complete the packet checksum in software within
virtio_net_hdr_to_skb so we need the packet trimmed (otherwise the
checksum would be computed incorrectly over the unreceived tail of the
buffer).

Trim first, so the import sees the packet as it was received.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 arch/um/drivers/vector_kern.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c
index e902e78c5ff6..828bd61995b8 100644
--- a/arch/um/drivers/vector_kern.c
+++ b/arch/um/drivers/vector_kern.c
@@ -873,6 +873,7 @@ static int vector_legacy_rx(struct vector_private *vp)
 
 	if (skb != NULL) {
 		if (pkt_len > vp->header_size) {
+			pskb_trim(skb, pkt_len - vp->rx_header_size);
 			if (vp->header_size > 0) {
 				header_check = vp->verify_header(
 					vp->header_rxbuffer, skb, vp);
@@ -887,7 +888,6 @@ static int vector_legacy_rx(struct vector_private *vp)
 					skb->ip_summed = CHECKSUM_UNNECESSARY;
 				}
 			}
-			pskb_trim(skb, pkt_len - vp->rx_header_size);
 			skb->protocol = eth_type_trans(skb, skb->dev);
 			vp->dev->stats.rx_bytes += skb->len;
 			vp->dev->stats.rx_packets++;
@@ -989,6 +989,8 @@ static int vector_mmsg_rx(struct vector_private *vp, int budget)
 	for (i = 0; i < packet_count; i++) {
 		skb = (*skbuff_vector);
 		if (mmsg_vector->msg_len > vp->header_size) {
+			pskb_trim(skb,
+				mmsg_vector->msg_len - vp->rx_header_size);
 			if (vp->header_size > 0) {
 				header_check = vp->verify_header(
 					mmsg_vector->msg_hdr.msg_iov->iov_base,
@@ -1013,8 +1015,6 @@ static int vector_mmsg_rx(struct vector_private *vp, int budget)
 					skb->ip_summed = CHECKSUM_UNNECESSARY;
 				}
 			}
-			pskb_trim(skb,
-				mmsg_vector->msg_len - vp->rx_header_size);
 			skb->protocol = eth_type_trans(skb, skb->dev);
 			/*
 			 * We do not need to lock on updating stats here
-- 
MST

[PATCH RFC v7 3/5] virtio_net: parse tunnel csum_start little-endian

[Michael S. Tsirkin]

All tunnel related virtio features are > 32, so none of this
functionality can be enabled on legacy mixed-endian device.

Accordingly, all tunnel header fields, csum_start included, are
little-endian.

The nested virtio net header import parses csum_start that way, but the
inner transport offset is parsed with the endianness specified by the
interface.

If tun is misconfigured to legacy big-endian mode while the tunnel
features are enabled, the two parses of this field disagree, and the
value stored in skb->inner_transport_header - which is only
bounds-checked from below - can point past the end of the packet, where
GSO segmentation later dereferences it.

To fix, parse the field little-endian in both places.

Fixes: a2fb4bc4e2a6 ("net: implement virtio helpers to handle UDP GSO tunneling.")
Cc: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_net.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index d6466f96cdd0..013c6c7e2dea 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -324,7 +324,7 @@ virtio_net_hdr_tnl_to_skb(struct sk_buff *skb,
 	inner_l3min = virtio_l3min(inner_isv6);
 	outer_l3min = ETH_HLEN + virtio_l3min(outer_isv6);
 
-	inner_th = __virtio16_to_cpu(little_endian, hdr->csum_start);
+	inner_th = __virtio16_to_cpu(true, hdr->csum_start);
 	inner_nh = le16_to_cpu(vhdr->inner_nh_offset);
 	outer_th = le16_to_cpu(vhdr->outer_th_offset);
 	if (outer_th < outer_l3min ||
-- 
MST

[PATCH RFC v7 4/5] net: resolve uncommon partial checksums at ingress

[Michael S. Tsirkin]

As reported first by Paulos Yibelo <habte.yibelo@gmail.com> (after which
others, credited below, found more ways the bug can affect users) a
virtio net header can place CHECKSUM_PARTIAL at any in-packet offset.
If that state is retained, later checksum completion can modify the
packet after protocol processing has made decisions from it.

Let's fix that: let's validate csum_start and csum_offset and only keep
CHECKSUM_PARTIAL when csum_start and csum_offset match a parsed TCP or
UDP header, while handling VLAN headers, IPv4 options and IPv6 extension
headers.  Complete other non-GSO checksums immediately, before any
protocol processing runs.

We can't easily "complete the checksum" for GSO we don't recognize - GSO
assumes knowledge of the protocol. We could segment ignoring the
checksum then do whatever csum_start and csum_offset say, but that
seems like an overkill for something that shouldn't happen.

There's some risk here:
- non-gso packets which can't be parsed get checksum calculated in
  software, adding performance overhead
- gso packets which can't be parsed get dropped

Note that for zero copy, userspace can change the data after the
checksum has been calculated.  This is fundamental to zero copy by
design, and the only outcome is a bad checksum and a packet drop.

To mitigate the risks, the following patch will add a sysctl knob to
bypass the resolution. This is reasonable if the setup is such that
there is no protocol processing at all.

UDP tunnel headers get the same handling on the inner header.

Packets without VIRTIO_NET_HDR_F_NEEDS_CSUM are unaffected.

Note a fundamental limitation of this approach: an nf/BPF program
that tweaks the payload of a packet in flight may rely on the
checksum being fixed up later, assuming the packet carries
CHECKSUM_PARTIAL.

For metadata that fails validation the checksum
is now completed at input, so such edits leave a stale checksum
and the packet is dropped at the receiver.  Protocols whose
transport header we cannot parse (anything but TCP and UDP) are
affected even when the metadata is self-consistent.

The sysctl added in the next patch is the escape hatch for these setups,
but it is a very blunt tool.

Reported-by: Paulos Yibelo <habte.yibelo@gmail.com>
Reported-by: Chris Arges <carges@cloudflare.com>
Tested-by: Chris Arges <carges@cloudflare.com>
Fixes: f43798c27684 ("tun: Allow GSO using virtio_net_hdr")
Suggested-by: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---

Notes (changelog):
    v4->v5:
        caller changes moved to "account for ingress-resolved
        virtio net hdr state" (Willem de Bruijn)
        a packet too small to be GSO: ignore the tunnel GSO request,
        complete wild metadata in place (sashiko)
        document the zero copy interaction (sashiko)
        honor a preset skb->protocol on ethernet: the stack uses it,
        except on loopback which re-parses the frame (sashiko)
    v5->v6:
        read both skb->protocol and the frame ethertype: do not
        validate when they disagree, instead of preferring the
        preset protocol; same check after the IP version inference
        where there is no L2 header (Willem de Bruijn)
        pull the IPv4 options in the helper as introduced, with the
        transport header offset computed before the pull
        (Willem de Bruijn)
        fold the trivial protocol calculation cleanup, formerly a
        separate patch, in (Willem de Bruijn)

 include/linux/virtio_net.h | 315 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 311 insertions(+), 4 deletions(-)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 013c6c7e2dea..54048759cc6e 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -5,7 +5,11 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/netdevice.h>
 #include <linux/udp.h>
+#include <net/gso.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
 #include <net/tcp.h>
 #include <uapi/linux/tcp.h>
 #include <uapi/linux/virtio_net.h>
@@ -48,6 +52,216 @@ static inline int virtio_net_hdr_set_proto(struct sk_buff *skb,
 	return 0;
 }
 
+/* TODO: nothing virtio specific here, move to ip.h */
+
+/*
+ * Pull and minimally validate the IPv4 header at @nhoff.
+ * Returns the header and stores the transport header offset in
+ * @thoff, or NULL if truncated or malformed.  The whole header,
+ * options included, is guaranteed linear on return.
+ */
+static inline struct iphdr *virtio_net_ip4_parse(struct sk_buff *skb,
+						  unsigned int nhoff,
+						  unsigned int *thoff)
+{
+	unsigned int ihl;
+	struct iphdr *iph;
+
+	if (!pskb_may_pull(skb, nhoff + sizeof(struct iphdr)))
+		return NULL;
+
+	iph = (struct iphdr *)(skb->data + nhoff);
+	if (iph->version != 4 ||
+	    iph->ihl < sizeof(struct iphdr) / sizeof(u32))
+		return NULL;
+
+	ihl = iph->ihl * sizeof(u32);
+	*thoff = nhoff + ihl;
+	/* Pull the options as well: the transport header offset
+	 * returned above must be within the linear data.  iph goes
+	 * stale across the pull.
+	 */
+	if (!pskb_may_pull(skb, nhoff + ihl))
+		return NULL;
+
+	return (struct iphdr *)(skb->data + nhoff);
+}
+
+/* Where does the L3 header start, and what protocol is it?
+ * Handles Ethernet and VLAN headers; other devices use the
+ * network header offset the caller set up.
+ */
+static inline bool
+virtio_net_l3_start(struct sk_buff *skb, int *nhoff, __be16 *proto)
+{
+	/* skb->dev should always be set here already,
+	 * but let's not crash when it is not.
+	 */
+	if (WARN_ON_ONCE(!skb->dev))
+		return false;
+
+	if (skb->dev->type == ARPHRD_ETHER ||
+	    skb->dev->type == ARPHRD_LOOPBACK) {
+		__be16 h_proto;
+
+		if (!pskb_may_pull(skb, ETH_HLEN))
+			return false;
+		h_proto = eth_hdr(skb)->h_proto;
+		/* skb->protocol is a sender claim, and parts of the
+		 * stack parse the packet per it: when it disagrees with
+		 * the frame we do not know which view the packet will
+		 * be parsed as, so do not validate.
+		 */
+		if (skb->protocol && skb->protocol != h_proto)
+			return false;
+		*nhoff = ETH_HLEN;
+		*proto = h_proto;
+		if (eth_type_vlan(*proto)) {
+			*proto = __vlan_get_protocol(skb, *proto, nhoff);
+			if (!*proto)
+				return false;
+		}
+	} else {
+		const struct iphdr *iph;
+
+		*nhoff = skb_network_offset(skb);
+		/* An unset network header shows up as an offset
+		 * outside of the packet.
+		 */
+		if (*nhoff < 0 || (unsigned int)*nhoff >= skb->len)
+			return false;
+		/* No L2 header to cross-check with: take the protocol
+		 * from the IP version at the network header.
+		 */
+		if (!pskb_may_pull(skb, *nhoff + 1))
+			return false;
+		iph = (const struct iphdr *)(skb->data + *nhoff);
+		if (iph->version == 4)
+			*proto = htons(ETH_P_IP);
+		else if (iph->version == 6)
+			*proto = htons(ETH_P_IPV6);
+		else
+			return false;
+		if (skb->protocol && skb->protocol != *proto)
+			return false;
+	}
+	return true;
+}
+
+/* Walk the L3 header at @nhoff: where does its transport header
+ * start, and which protocol is it?  Returns false if the header
+ * is truncated, malformed or fragmented.
+ */
+static inline bool
+virtio_net_l4_start(struct sk_buff *skb, unsigned int nhoff, __be16 proto,
+		    unsigned int *thoff, int *ip_proto)
+{
+	if (proto == htons(ETH_P_IP)) {
+		const struct iphdr *iph = virtio_net_ip4_parse(skb, nhoff, thoff);
+
+		if (!iph || ip_is_fragment(iph))
+			return false;
+		*ip_proto = iph->protocol;
+		return true;
+	}
+
+	if (proto == htons(ETH_P_IPV6)) {
+		const struct ipv6hdr *iph;
+		int flags = 0;
+
+		if (!pskb_may_pull(skb, nhoff + sizeof(*iph)))
+			return false;
+		iph = (const void *)(skb->data + nhoff);
+		if (iph->version != 6)
+			return false;
+		*thoff = nhoff + sizeof(*iph);
+		*ip_proto = iph->nexthdr;
+		if (*ip_proto != IPPROTO_TCP && *ip_proto != IPPROTO_UDP) {
+			*thoff = nhoff;
+			/* Find the transport header behind any
+			 * extension headers, AH included.
+			 */
+			*ip_proto = ipv6_find_hdr(skb, thoff, -1, NULL,
+						  &flags);
+			if (*ip_proto < 0 || flags & IP6_FH_F_FRAG)
+				return false;
+		}
+		return true;
+	}
+
+	return false;
+}
+
+/* Does checksum metadata match a known TCP or UDP header? */
+static inline bool
+virtio_net_csum_partial_ok_at_offset(struct sk_buff *skb, u8 hdr_gso_type,
+				     unsigned int nhoff, __be16 proto)
+{
+	unsigned int thoff;
+	int ip_proto;
+
+	if (!virtio_net_l4_start(skb, nhoff, proto, &thoff, &ip_proto))
+		return false;
+
+	if (skb_checksum_start_offset(skb) != thoff)
+		return false;
+
+	switch (ip_proto) {
+	case IPPROTO_TCP:
+		if (skb->csum_offset != offsetof(struct tcphdr, check) ||
+		    !pskb_may_pull(skb, thoff + sizeof(struct tcphdr)))
+			return false;
+		break;
+	case IPPROTO_UDP:
+		if (skb->csum_offset != offsetof(struct udphdr, check) ||
+		    !pskb_may_pull(skb, thoff + sizeof(struct udphdr)))
+			return false;
+		break;
+	default:
+		return false;
+	}
+
+	switch (hdr_gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+	case VIRTIO_NET_HDR_GSO_NONE:
+		return true;
+	case VIRTIO_NET_HDR_GSO_TCPV4:
+		return proto == htons(ETH_P_IP) && ip_proto == IPPROTO_TCP;
+	case VIRTIO_NET_HDR_GSO_TCPV6:
+		return proto == htons(ETH_P_IPV6) && ip_proto == IPPROTO_TCP;
+	case VIRTIO_NET_HDR_GSO_UDP:
+	case VIRTIO_NET_HDR_GSO_UDP_L4:
+		return ip_proto == IPPROTO_UDP;
+	default:
+		return false;
+	}
+}
+
+static inline bool
+virtio_net_csum_partial_ok(struct sk_buff *skb, u8 hdr_gso_type)
+{
+	int nhoff;
+	__be16 proto;
+
+	if (!virtio_net_l3_start(skb, &nhoff, &proto))
+		return false;
+
+	return virtio_net_csum_partial_ok_at_offset(skb, hdr_gso_type, nhoff,
+						   proto);
+}
+
+/*
+ * Handle a packet whose checksum metadata does not match the packet:
+ * GSO packets are dropped, as segmentation needs one checksum per
+ * segment; others are completed in software.
+ */
+static inline int __virtio_net_resolve_csum_partial_mismatch(struct sk_buff *skb)
+{
+	if (skb_is_gso(skb))
+		return -EINVAL;
+
+	return skb_checksum_help(skb) ?: 1;
+}
+
 static inline int __virtio_net_hdr_to_skb(struct sk_buff *skb,
 					  const struct virtio_net_hdr *hdr,
 					  bool little_endian, u8 hdr_gso_type)
@@ -194,11 +408,35 @@ static inline int __virtio_net_hdr_to_skb(struct sk_buff *skb,
 	return 0;
 }
 
+/*
+ * Return value:
+ * 0 - success
+ * >0 - checksum was completed in software (slow path)
+ * <0 - failure
+ */
 static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					const struct virtio_net_hdr *hdr,
 					bool little_endian)
 {
-	return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type);
+	typeof(skb->transport_header) old_transport = skb->transport_header;
+	int ret = __virtio_net_hdr_to_skb(skb, hdr, little_endian,
+					  hdr->gso_type);
+
+	if (ret < 0)
+		return ret;
+
+	if (likely(skb->ip_summed != CHECKSUM_PARTIAL ||
+		   virtio_net_csum_partial_ok(skb, hdr->gso_type)))
+		return 0;
+
+	/*
+	 * Here we do not trust the checksum metadata.
+	 * __virtio_net_hdr_to_skb set the transport header to csum_start
+	 * from virtio hdr, restore it to a known good value.
+	 */
+	skb->transport_header = old_transport;
+
+	return __virtio_net_resolve_csum_partial_mismatch(skb);
 }
 
 /* This function must be called after virtio_net_hdr_from_skb(). */
@@ -282,6 +520,35 @@ static inline unsigned int virtio_l3min(bool is_ipv6)
 	return is_ipv6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr);
 }
 
+/* Do the tunnel offsets match the outer headers in the frame?
+ * The L3 header the tunnel claims must be the one the frame
+ * carries, with UDP following it at @outer_th.
+ */
+static inline bool
+virtio_net_tnl_offsets_ok(struct sk_buff *skb, bool outer_isv6,
+			  unsigned int outer_th)
+{
+	int nhoff;
+	__be16 proto;
+	unsigned int thoff;
+	int ip_proto;
+
+	if (!virtio_net_l3_start(skb, &nhoff, &proto))
+		return false;
+	if (outer_isv6 != (proto == htons(ETH_P_IPV6)))
+		return false;
+	if (!virtio_net_l4_start(skb, nhoff, proto, &thoff, &ip_proto))
+		return false;
+
+	return ip_proto == IPPROTO_UDP && outer_th == thoff;
+}
+
+/*
+ * Return value:
+ * 0 - success
+ * >0 - checksum was completed in software (slow path)
+ * <0 - failure
+ */
 static inline int
 virtio_net_hdr_tnl_to_skb(struct sk_buff *skb,
 			  const struct virtio_net_hdr_v1_hash_tunnel *vhdr,
@@ -290,9 +557,11 @@ virtio_net_hdr_tnl_to_skb(struct sk_buff *skb,
 			  bool little_endian)
 {
 	const struct virtio_net_hdr *hdr = (const struct virtio_net_hdr *)vhdr;
+	typeof(skb->transport_header) old_transport = skb->transport_header;
 	unsigned int inner_nh, outer_th, inner_th;
 	unsigned int inner_l3min, outer_l3min;
 	u8 gso_inner_type, gso_tunnel_type;
+	__be16 inner_proto;
 	bool outer_isv6, inner_isv6;
 	int ret;
 
@@ -335,9 +604,12 @@ virtio_net_hdr_tnl_to_skb(struct sk_buff *skb,
 	/* Let the basic parsing deal with plain GSO features. */
 	ret = __virtio_net_hdr_to_skb(skb, hdr, true,
 				      hdr->gso_type & ~gso_tunnel_type);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
+	if (!virtio_net_tnl_offsets_ok(skb, outer_isv6, outer_th))
+		return -EINVAL;
+
 	/* In case of USO, the inner protocol is still unknown and
 	 * `inner_isv6` is just a guess, additional parsing is needed.
 	 * The previous validation ensures that accessing an ipv4 inner
@@ -352,9 +624,29 @@ virtio_net_hdr_tnl_to_skb(struct sk_buff *skb,
 			return -EINVAL;
 	}
 
-	skb_set_inner_protocol(skb, inner_isv6 ? htons(ETH_P_IPV6) :
-						 htons(ETH_P_IP));
+	inner_proto = inner_isv6 ? htons(ETH_P_IPV6) : htons(ETH_P_IP);
+
+	/*
+	 * We know VIRTIO_NET_HDR_F_NEEDS_CSUM was set so __virtio_net_hdr_to_skb
+	 * set CHECKSUM_PARTIAL.
+	 */
+	if (unlikely(!virtio_net_csum_partial_ok_at_offset(skb, gso_inner_type,
+							  inner_nh,
+							  inner_proto))) {
+		/* __virtio_net_hdr_to_skb set the transport header to
+		 * csum_start, restore it to a known good value.
+		 */
+		skb->transport_header = old_transport;
+
+		return __virtio_net_resolve_csum_partial_mismatch(skb);
+	}
+
+	skb_set_inner_protocol(skb, inner_proto);
 	if (hdr->flags & VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM) {
+		/* Checked here, after the validation: a packet completed
+		 * in software never uses the feature, so an unnegotiated
+		 * request only matters for metadata good enough to act on.
+		 */
 		if (!tnl_csum_negotiated)
 			return -EINVAL;
 
@@ -368,6 +660,21 @@ virtio_net_hdr_tnl_to_skb(struct sk_buff *skb,
 	skb->inner_mac_header = inner_nh + skb_headroom(skb);
 	skb->transport_header = outer_th + skb_headroom(skb);
 	skb->encapsulation = 1;
+
+	if (!skb_is_gso(skb)) {
+		/* Too small to segment: complete the checksum in place
+		 * instead of dropping - senders do tag small packets
+		 * with GSO headers, e.g. packetdrill sets gso_type and
+		 * gso_size with --mss, whatever the packet size.
+		 * The outer UDP checksum is not calculated, but a zero
+		 * one is fine: UDP over IPv4 allows a disabled
+		 * checksum, and so do tunnels over IPv6 where the
+		 * receiver opts in (RFC 6935, RFC 6936).
+		 */
+		skb_shinfo(skb)->gso_type &= ~(SKB_GSO_UDP_TUNNEL_CSUM |
+					       SKB_GSO_UDP_TUNNEL);
+	}
+
 	return 0;
 }
 
-- 
MST

[PATCH RFC v7 5/5] net: add a sysctl to opt out of virtio net hdr checksum validation

[Michael S. Tsirkin]

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               | 25 ++++++++++++
 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, 103 insertions(+)

diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index fe43e8595958..3d89772cb7fe 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 54048759cc6e..b2bd5ab3fdb6 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>
@@ -87,6 +88,18 @@ static inline struct iphdr *virtio_net_ip4_parse(struct sk_buff *skb,
 	return (struct iphdr *)(skb->data + nhoff);
 }
 
+/* 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);
+
+/*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
  * network header offset the caller set up.
@@ -200,6 +213,12 @@ 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;
 
@@ -242,6 +261,9 @@ 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;
 
@@ -533,6 +555,9 @@ 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 87a79d6004c8..960c97980544 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 <net/route.h>
 #include <linux/ipv6.h>
@@ -2427,6 +2428,12 @@ 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 473c162736d6..04cd2d758ccc 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>
@@ -693,6 +695,43 @@ 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)
 	{
@@ -752,6 +791,15 @@ 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
 	 */
@@ -856,6 +904,8 @@ 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