net: openvswitch: add hash info to upcall
When using the kernel datapath, the upcall don't
include skb hash info relatived. That will introduce
some problem, because the hash of skb is important
in kernel stack. For example, VXLAN module uses
it to select UDP src port. The tx queue selection
may also use the hash in stack.
Hash is computed in different ways. Hash is random
for a TCP socket, and hash may be computed in hardware,
or software stack. Recalculation hash is not easy.
Hash of TCP socket is computed:
tcp_v4_connect
-> sk_set_txhash (is random)
__tcp_transmit_skb
-> skb_set_hash_from_sk
There will be one upcall, without information of skb
hash, to ovs-vswitchd, for the first packet of a TCP
session. The rest packets will be processed in Open vSwitch
modules, hash kept. If this tcp session is forward to
VXLAN module, then the UDP src port of first tcp packet
is different from rest packets.
TCP packets may come from the host or dockers, to Open vSwitch.
To fix it, we store the hash info to upcall, and restore hash
when packets sent back.
+---------------+ +-------------------------+
| Docker/VMs | | ovs-vswitchd |
+----+----------+ +-+--------------------+--+
| ^ |
| | |
| | upcall v restore packet hash (not recalculate)
| +-+--------------------+--+
| tap netdev | | vxlan module
+---------------> +--> Open vSwitch ko +-->
or internal type | |
+-------------------------+
Reported-at: https://mail.openvswitch.org/pipermail/ovs-dev/2019-October/364062.html
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 2088619..8ce1f77 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -350,7 +350,8 @@ static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
+ nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
+ nla_total_size(ovs_key_attr_size()) /* OVS_PACKET_ATTR_KEY */
- + nla_total_size(sizeof(unsigned int)); /* OVS_PACKET_ATTR_LEN */
+ + nla_total_size(sizeof(unsigned int)) /* OVS_PACKET_ATTR_LEN */
+ + nla_total_size(sizeof(u64)); /* OVS_PACKET_ATTR_HASH */
/* OVS_PACKET_ATTR_USERDATA */
if (upcall_info->userdata)
@@ -393,6 +394,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
size_t len;
unsigned int hlen;
int err, dp_ifindex;
+ u64 hash;
dp_ifindex = get_dpifindex(dp);
if (!dp_ifindex)
@@ -504,6 +506,19 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
pad_packet(dp, user_skb);
}
+ /* Add OVS_PACKET_ATTR_HASH */
+ hash = skb_get_hash_raw(skb);
+ if (skb->sw_hash)
+ hash |= OVS_PACKET_HASH_SW_BIT;
+
+ if (skb->l4_hash)
+ hash |= OVS_PACKET_HASH_L4_BIT;
+
+ if (nla_put(user_skb, OVS_PACKET_ATTR_HASH, sizeof (u64), &hash)) {
+ err = -ENOBUFS;
+ goto out;
+ }
+
/* Only reserve room for attribute header, packet data is added
* in skb_zerocopy() */
if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
@@ -543,6 +558,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
struct datapath *dp;
struct vport *input_vport;
u16 mru = 0;
+ u64 hash;
int len;
int err;
bool log = !a[OVS_PACKET_ATTR_PROBE];
@@ -568,6 +584,14 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
}
OVS_CB(packet)->mru = mru;
+ if (a[OVS_PACKET_ATTR_HASH]) {
+ hash = nla_get_u64(a[OVS_PACKET_ATTR_HASH]);
+
+ __skb_set_hash(packet, hash & 0xFFFFFFFFULL,
+ !!(hash & OVS_PACKET_HASH_SW_BIT),
+ !!(hash & OVS_PACKET_HASH_L4_BIT));
+ }
+
/* Build an sw_flow for sending this packet. */
flow = ovs_flow_alloc();
err = PTR_ERR(flow);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 81e85dd..e239a46 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -139,6 +139,18 @@ struct ovs_net {
bool xt_label;
};
+/**
+ * enum ovs_pkt_hash_types - hash info to include with a packet
+ * to send to userspace.
+ * @OVS_PACKET_HASH_SW_BIT: indicates hash was computed in software stack.
+ * @OVS_PACKET_HASH_L4_BIT: indicates hash is a canonical 4-tuple hash
+ * over transport ports.
+ */
+enum ovs_pkt_hash_types {
+ OVS_PACKET_HASH_SW_BIT = (1ULL << 32),
+ OVS_PACKET_HASH_L4_BIT = (1ULL << 33),
+};
+
extern unsigned int ovs_net_id;
void ovs_lock(void);
void ovs_unlock(void);