diff options
| author | Eric Dumazet <edumazet@google.com> | 2023-09-21 22:28:15 +0200 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2023-10-01 20:09:54 +0200 |
| commit | 28b24f90020fed8e8e3e8e20575f08c1cd06e54f (patch) | |
| tree | 3fc7b7bd080580d56131a0a3b46468b1b1eea6f2 /net/sched | |
| parent | net: lockless implementation of SO_BUSY_POLL, SO_PREFER_BUSY_POLL, SO_BUSY_PO... (diff) | |
| download | linux-28b24f90020fed8e8e3e8e20575f08c1cd06e54f.tar.xz linux-28b24f90020fed8e8e3e8e20575f08c1cd06e54f.zip | |
net: implement lockless SO_MAX_PACING_RATE
SO_MAX_PACING_RATE setsockopt() does not need to hold
the socket lock, because sk->sk_pacing_rate readers
can run fine if the value is changed by other threads,
after adding READ_ONCE() accessors.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/sched')
| -rw-r--r-- | net/sched/sch_fq.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 681bbf34b707..d35419db7b94 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -668,7 +668,7 @@ begin: */ if (!skb->tstamp) { if (skb->sk) - rate = min(skb->sk->sk_pacing_rate, rate); + rate = min(READ_ONCE(skb->sk->sk_pacing_rate), rate); if (rate <= q->low_rate_threshold) { f->credit = 0; |