bpf: fix SO_MAX_PACING_RATE to support TCP internal pacing
authorYuchung Cheng <ycheng@google.com>
Thu, 17 Jan 2019 16:51:01 +0000 (08:51 -0800)
committerDaniel Borkmann <daniel@iogearbox.net>
Thu, 17 Jan 2019 23:30:34 +0000 (00:30 +0100)
commite224c390a6259c529f7b2a6bd215a087b3344f5c
tree493ddd94dadde65ab3e817df33fd653ca24c4c8f
parentf4924f24da8c7ef64195096817f3cde324091d97
bpf: fix SO_MAX_PACING_RATE to support TCP internal pacing

If sch_fq packet scheduler is not used, TCP can fallback to
internal pacing, but this requires sk_pacing_status to
be properly set.

Fixes: 8c4b4c7e9ff0 ("bpf: Add setsockopt helper function to bpf")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
net/core/filter.c