diff options
author | Jesper Dangaard Brouer <brouer@redhat.com> | 2017-08-29 16:37:56 +0200 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2017-08-29 10:51:29 -0700 |
commit | f5836ca5e9867fa6ab88cadb9873af56d9ceb589 (patch) | |
tree | 81b8317a3d986fb176b2df280d946bd250e4ad1a /net/core | |
parent | b06337dfdb16bc3f668326b6a618c472c671182a (diff) |
xdp: separate xdp_redirect tracepoint in error case
There is a need to separate the xdp_redirect tracepoint into two
tracepoints, for separating the error case from the normal forward
case.
Due to the extreme speeds XDP is operating at, loading a tracepoint
have a measurable impact. Single core XDP REDIRECT (ethtool tuned
rx-usecs 25) can do 13.7 Mpps forwarding, but loading a simple
bpf_prog at the tracepoint (with a return 0) reduce perf to 10.2 Mpps
(CPU E5-1650 v4 @ 3.60GHz, driver: ixgbe)
The overhead of loading a bpf-based tracepoint can be calculated to
cost 25 nanosec ((1/13782002-1/10267937)*10^9 = -24.83 ns).
Using perf record on the tracepoint event, with a non-matching --filter
expression, the overhead is much larger. Performance drops to 8.3 Mpps,
cost 48 nanosec ((1/13782002-1/8312497)*10^9 = -47.74))
Having a separate tracepoint for err cases, which should be less
frequent, allow running a continuous monitor for errors while not
affecting the redirect forward performance (this have also been
verified by measurements).
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/filter.c | 37 |
1 files changed, 24 insertions, 13 deletions
diff --git a/net/core/filter.c b/net/core/filter.c index 31eab77cc842..096e78de0b97 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2515,16 +2515,20 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, fwd = __dev_map_lookup_elem(map, index); if (!fwd) { err = -EINVAL; - goto out; + goto err; } if (ri->map_to_flush && ri->map_to_flush != map) xdp_do_flush_map(); err = __bpf_tx_xdp(fwd, map, xdp, index); - if (likely(!err)) - ri->map_to_flush = map; -out: - trace_xdp_redirect_map(dev, xdp_prog, fwd, err, map, index); + if (unlikely(err)) + goto err; + + ri->map_to_flush = map; + trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index); + return 0; +err: + trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err); return err; } @@ -2543,12 +2547,17 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, ri->ifindex = 0; if (unlikely(!fwd)) { err = -EINVAL; - goto out; + goto err; } err = __bpf_tx_xdp(fwd, NULL, xdp, 0); -out: - _trace_xdp_redirect(dev, xdp_prog, index, err); + if (unlikely(err)) + goto err; + + _trace_xdp_redirect(dev, xdp_prog, index); + return 0; +err: + _trace_xdp_redirect_err(dev, xdp_prog, index, err); return err; } EXPORT_SYMBOL_GPL(xdp_do_redirect); @@ -2566,23 +2575,25 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, ri->ifindex = 0; if (unlikely(!fwd)) { err = -EINVAL; - goto out; + goto err; } if (unlikely(!(fwd->flags & IFF_UP))) { err = -ENETDOWN; - goto out; + goto err; } len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; if (skb->len > len) { err = -EMSGSIZE; - goto out; + goto err; } skb->dev = fwd; -out: - _trace_xdp_redirect(dev, xdp_prog, index, err); + _trace_xdp_redirect(dev, xdp_prog, index); + return 0; +err: + _trace_xdp_redirect_err(dev, xdp_prog, index, err); return err; } EXPORT_SYMBOL_GPL(xdp_do_generic_redirect); |