From 1d233886dd904edbf239eeffe435c3308ae97625 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Thu, 16 Jan 2020 16:14:45 +0100 Subject: xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk --- kernel/bpf/devmap.c | 32 ++++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 10 deletions(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 030d125c3839..d5311009953f 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -81,7 +81,7 @@ struct bpf_dtab { u32 n_buckets; }; -static DEFINE_PER_CPU(struct list_head, dev_map_flush_list); +static DEFINE_PER_CPU(struct list_head, dev_flush_list); static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); @@ -357,16 +357,16 @@ error: goto out; } -/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled +/* __dev_flush is called from xdp_do_flush() which _must_ be signaled * from the driver before returning from its napi->poll() routine. The poll() * routine is called either from busy_poll context or net_rx_action signaled * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the * net device can be torn down. On devmap tear down we ensure the flush list * is empty before completing to ensure all flush operations have completed. */ -void __dev_map_flush(void) +void __dev_flush(void) { - struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list); + struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); struct xdp_dev_bulk_queue *bq, *tmp; rcu_read_lock(); @@ -396,9 +396,8 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key) */ static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) - { - struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list); + struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) @@ -419,10 +418,9 @@ static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, return 0; } -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, - struct net_device *dev_rx) +static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, + struct net_device *dev_rx) { - struct net_device *dev = dst->dev; struct xdp_frame *xdpf; int err; @@ -440,6 +438,20 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, return bq_enqueue(dev, xdpf, dev_rx); } +int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + return __xdp_enqueue(dev, xdp, dev_rx); +} + +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + struct net_device *dev = dst->dev; + + return __xdp_enqueue(dev, xdp, dev_rx); +} + int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { @@ -762,7 +774,7 @@ static int __init dev_map_init(void) register_netdevice_notifier(&dev_map_notifier); for_each_possible_cpu(cpu) - INIT_LIST_HEAD(&per_cpu(dev_map_flush_list, cpu)); + INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu)); return 0; } -- cgit v1.2.3