diff mbox series

[X,2/2] net: openvswitch: add hash info to upcall

Message ID 20200508181051.25162-3-kelsey.skunberg@canonical.com
State New
Headers show
Series openvswitch: Same tcp session encapsulated with different udp src port for ovs vxlan tunnel | expand

Commit Message

Kelsey Skunberg May 8, 2020, 6:10 p.m. UTC 
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>

BugLink: https://bugs.launchpad.net/bugs/1860986

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>
(cherry picked from commit bd1903b7c4596ba6f7677d0dfefd05ba5876707d)
Signed-off-by: Kelsey Skunberg <kelsey.skunberg@canonical.com>
---
 include/uapi/linux/openvswitch.h |  2 ++
 net/openvswitch/datapath.c       | 26 +++++++++++++++++++++++++-
 net/openvswitch/datapath.h       | 12 ++++++++++++
 3 files changed, 39 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index a27222d5b413..784fb8d7e08d 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -167,6 +167,7 @@  enum ovs_packet_cmd {
  * @OVS_PACKET_ATTR_MRU: Present for an %OVS_PACKET_CMD_ACTION and
  * %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.
@@ -184,6 +185,7 @@  enum ovs_packet_attr {
 	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_HASH,       /* Packet hash. */
 	__OVS_PACKET_ATTR_MAX
 };
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index d21d914ad9cc..7ed8b3882961 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -383,7 +383,8 @@  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(ovs_key_attr_size()) /* OVS_PACKET_ATTR_KEY */
+		+ nla_total_size(sizeof(u64)); /* OVS_PACKET_ATTR_HASH */
 
 	/* OVS_PACKET_ATTR_USERDATA */
 	if (upcall_info->userdata)
@@ -429,6 +430,7 @@  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)
@@ -513,6 +515,19 @@  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))) {
@@ -553,6 +568,7 @@  static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	struct ethhdr *eth;
 	struct vport *input_vport;
 	u16 mru = 0;
+	u64 hash;
 	int len;
 	int err;
 	bool log = !a[OVS_PACKET_ATTR_PROBE];
@@ -589,6 +605,14 @@  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 67bdecd9fdc1..6bc11fd27f35 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -138,6 +138,18 @@  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 int ovs_net_id;
 void ovs_lock(void);
 void ovs_unlock(void);