| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1472688605-2613704-5-git-send-email-tom@herbertland.com>
Date: Wed, 31 Aug 2016 17:10:05 -0700
From: Tom Herbert <tom@...bertland.com>
To: <davem@...emloft.net>, <netdev@...r.kernel.org>
CC: <kernel-team@...com>, <rick.jones2@....com>
Subject: [PATCH net-next 4/4] xps_flows: XPS for packets that don't have a socket
xps_flows maintains a per device flow table that is indexed by the
skbuff hash. The table is only consulted when there is no queue saved in
a transmit socket for an skbuff.
Each entry in the flow table contains a queue index and a queue
pointer. The queue pointer is set when a queue is chosen using a
flow table entry. This pointer is set to the head pointer in the
transmit queue (which is maintained by BQL).
The new function get_xps_flows_index that looks up flows in the
xps_flows table. The entry returned gives the last queue a matching flow
used. The returned queue is compared against the normal XPS queue. If
they are different, then we only switch if the tail pointer in the TX
queue has advanced past the pointer saved in the entry. In this
way OOO should be avoided when XPS wants to use a different queue.
Signed-off-by: Tom Herbert <tom@...bertland.com>
---
net/Kconfig | 6 +++++
net/core/dev.c | 85 +++++++++++++++++++++++++++++++++++++++++++++++-----------
2 files changed, 76 insertions(+), 15 deletions(-)
diff --git a/net/Kconfig b/net/Kconfig
index 7b6cd34..f77fad1 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -255,6 +255,12 @@ config XPS
depends on SMP
default y
+config XPS_FLOWS
+ bool
+ depends on XPS
+ depends on BQL
+ default y
+
config HWBM
bool
diff --git a/net/core/dev.c b/net/core/dev.c
index 34b5322..fc68d19 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3210,6 +3210,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
}
#endif /* CONFIG_NET_EGRESS */
+/* Must be called with RCU read_lock */
static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_XPS
@@ -3217,7 +3218,6 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
struct xps_map *map;
int queue_index = -1;
- rcu_read_lock();
dev_maps = rcu_dereference(dev->xps_maps);
if (dev_maps) {
map = rcu_dereference(
@@ -3232,7 +3232,6 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
queue_index = -1;
}
}
- rcu_read_unlock();
return queue_index;
#else
@@ -3240,26 +3239,82 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
#endif
}
-static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+/* Must be called with RCU read_lock */
+static int get_xps_flows_index(struct net_device *dev, struct sk_buff *skb)
{
- struct sock *sk = skb->sk;
- int queue_index = sk_tx_queue_get(sk);
+#ifdef CONFIG_XPS_FLOWS
+ struct xps_dev_flow_table *flow_table;
+ struct xps_dev_flow ent;
+ int queue_index;
+ struct netdev_queue *txq;
+ u32 hash;
- if (queue_index < 0 || skb->ooo_okay ||
- queue_index >= dev->real_num_tx_queues) {
- int new_index = get_xps_queue(dev, skb);
- if (new_index < 0)
- new_index = skb_tx_hash(dev, skb);
+ flow_table = rcu_dereference(dev->xps_flow_table);
+ if (!flow_table)
+ return -1;
- if (queue_index != new_index && sk &&
- sk_fullsock(sk) &&
- rcu_access_pointer(sk->sk_dst_cache))
- sk_tx_queue_set(sk, new_index);
+ queue_index = get_xps_queue(dev, skb);
+ if (queue_index < 0)
+ return -1;
- queue_index = new_index;
+ hash = skb_get_hash(skb);
+ if (!hash)
+ return -1;
+
+ ent.v64 = flow_table->flows[hash & flow_table->mask].v64;
+
+ if (queue_index != ent.queue_index &&
+ ent.queue_index >= 0 &&
+ ent.queue_index < dev->real_num_tx_queues) {
+ txq = netdev_get_tx_queue(dev, ent.queue_index);
+ if ((int)(txq->dql.num_completed_ops - ent.queue_ptr) < 0) {
+ /* The current queue's tail has not advanced beyond the
+ * last packet that was enqueued using the table entry.
+ * We can't change queues without risking OOO. Stick
+ * with the queue listed in the flow table.
+ */
+ queue_index = ent.queue_index;
+ }
}
+ /* Save the updated entry */
+ txq = netdev_get_tx_queue(dev, queue_index);
+ ent.queue_index = queue_index;
+ ent.queue_ptr = txq->dql.num_enqueue_ops;
+ flow_table->flows[hash & flow_table->mask].v64 = ent.v64;
+
return queue_index;
+#else
+ return get_xps_queue(dev, skb);
+#endif
+}
+
+static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+{
+ struct sock *sk = skb->sk;
+ int queue_index = sk_tx_queue_get(sk);
+ int new_index;
+
+ if (queue_index < 0) {
+ /* Socket did not provide a queue index, try xps_flows */
+ new_index = get_xps_flows_index(dev, skb);
+ } else if (skb->ooo_okay || queue_index >= dev->real_num_tx_queues) {
+ /* Queue index in socket, see if we can find a better one */
+ new_index = get_xps_queue(dev, skb);
+ } else {
+ /* Valid queue in socket and can't send OOO. Just return it */
+ return queue_index;
+ }
+
+ /* No queue index from flow steering, fallback to hash */
+ if (new_index < 0)
+ new_index = skb_tx_hash(dev, skb);
+
+ if (queue_index != new_index && sk && sk_fullsock(sk) &&
+ rcu_access_pointer(sk->sk_dst_cache))
+ sk_tx_queue_set(sk, new_index);
+
+ return new_index;
}
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
--
2.8.0.rc2
Powered by blists - more mailing lists