summaryrefslogtreecommitdiffstats
path: root/kernel/bpf/devmap.c
diff options
context:
space:
mode:
authorJesper Dangaard Brouer <brouer@redhat.com>2018-05-24 16:46:12 +0200
committerAlexei Starovoitov <ast@kernel.org>2018-05-25 03:36:15 +0200
commit735fc4054b3a25034445c6713d259da0f96f8131 (patch)
tree355f7a0672e6239fa4227d562f7d5b65fac9c011 /kernel/bpf/devmap.c
parentxdp: introduce xdp_return_frame_rx_napi (diff)
downloadlinux-735fc4054b3a25034445c6713d259da0f96f8131.tar.xz
linux-735fc4054b3a25034445c6713d259da0f96f8131.zip
xdp: change ndo_xdp_xmit API to support bulking
This patch change the API for ndo_xdp_xmit to support bulking xdp_frames. When kernel is compiled with CONFIG_RETPOLINE, XDP sees a huge slowdown. Most of the slowdown is caused by DMA API indirect function calls, but also the net_device->ndo_xdp_xmit() call. Benchmarked patch with CONFIG_RETPOLINE, using xdp_redirect_map with single flow/core test (CPU E5-1650 v4 @ 3.60GHz), showed performance improved: for driver ixgbe: 6,042,682 pps -> 6,853,768 pps = +811,086 pps for driver i40e : 6,187,169 pps -> 6,724,519 pps = +537,350 pps With frames avail as a bulk inside the driver ndo_xdp_xmit call, further optimizations are possible, like bulk DMA-mapping for TX. Testing without CONFIG_RETPOLINE show the same performance for physical NIC drivers. The virtual NIC driver tun sees a huge performance boost, as it can avoid doing per frame producer locking, but instead amortize the locking cost over the bulk. V2: Fix compile errors reported by kbuild test robot <lkp@intel.com> V4: Isolated ndo, driver changes and callers. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'kernel/bpf/devmap.c')
-rw-r--r--kernel/bpf/devmap.c29
1 files changed, 18 insertions, 11 deletions
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index a9cd5c93dd2b..77908311ec98 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -232,24 +232,31 @@ static int bq_xmit_all(struct bpf_dtab_netdev *obj,
prefetch(xdpf);
}
- for (i = 0; i < bq->count; i++) {
- struct xdp_frame *xdpf = bq->q[i];
- int err;
-
- err = dev->netdev_ops->ndo_xdp_xmit(dev, xdpf);
- if (err) {
- drops++;
- xdp_return_frame_rx_napi(xdpf);
- } else {
- sent++;
- }
+ sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q);
+ if (sent < 0) {
+ sent = 0;
+ goto error;
}
+ drops = bq->count - sent;
+out:
bq->count = 0;
trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit,
sent, drops, bq->dev_rx, dev);
bq->dev_rx = NULL;
return 0;
+error:
+ /* If ndo_xdp_xmit fails with an errno, no frames have been
+ * xmit'ed and it's our responsibility to them free all.
+ */
+ for (i = 0; i < bq->count; i++) {
+ struct xdp_frame *xdpf = bq->q[i];
+
+ /* RX path under NAPI protection, can return frames faster */
+ xdp_return_frame_rx_napi(xdpf);
+ drops++;
+ }
+ goto out;
}
/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled