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 <[e-mail]>
Acked-by: Pravin B Shelar <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

include/uapi/linux/openvswitch.h

···
  * @OVS_PACKET_ATTR_LEN: Packet size before truncation.
  * %OVS_PACKET_ATTR_USERSPACE action specify the Maximum received fragment
  * size.
+ * @OVS_PACKET_ATTR_HASH: Packet hash info (e.g. hash, sw_hash and l4_hash in skb).
  *
  * These attributes follow the &struct ovs_header within the Generic Netlink
  * payload for %OVS_PACKET_* commands.
···
 	OVS_PACKET_ATTR_PROBE,      /* Packet operation is a feature probe,
 				       error logging should be suppressed. */
 	OVS_PACKET_ATTR_MRU,	    /* Maximum received IP fragment size. */
-	OVS_PACKET_ATTR_LEN,		/* Packet size before truncation. */
+	OVS_PACKET_ATTR_LEN,	    /* Packet size before truncation. */
+	OVS_PACKET_ATTR_HASH,	    /* Packet hash. */
 	__OVS_PACKET_ATTR_MAX
 };
 

net/openvswitch/datapath.c

···
 	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)
···
 	size_t len;
 	unsigned int hlen;
 	int err, dp_ifindex;
+	u64 hash;
 
 	dp_ifindex = get_dpifindex(dp);
 	if (!dp_ifindex)
···
 		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))) {
···
 	struct datapath *dp;
 	struct vport *input_vport;
 	u16 mru = 0;
+	u64 hash;
 	int len;
 	int err;
 	bool log = !a[OVS_PACKET_ATTR_PROBE];
···
 		packet->ignore_df = 1;
 	}
 	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();

net/openvswitch/datapath.h

···
 	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);