diff options
| author | Chuck Lever <chuck.lever@oracle.com> | 2022-04-29 10:06:21 -0400 |
|---|---|---|
| committer | Chuck Lever <chuck.lever@oracle.com> | 2022-05-23 11:06:29 -0400 |
| commit | 28df0988815f63e2af5e6718193c9f68681ad7ff (patch) | |
| tree | 63b9934813d5d24e8c90c65b396935abb8a722b2 /net/sunrpc/svcsock.c | |
| parent | bb283ca18d1e67c82d22a329c96c9d6036a74790 (diff) | |
| download | linux-28df0988815f63e2af5e6718193c9f68681ad7ff.tar.bz2 | |
SUNRPC: Use RMW bitops in single-threaded hot paths
I noticed CPU pipeline stalls while using perf.
Once an svc thread is scheduled and executing an RPC, no other
processes will touch svc_rqst::rq_flags. Thus bus-locked atomics are
not needed outside the svc thread scheduler.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Diffstat (limited to 'net/sunrpc/svcsock.c')
| -rw-r--r-- | net/sunrpc/svcsock.c | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 05452318afec..b3c9740cfd35 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -298,9 +298,9 @@ static void svc_sock_setbufsize(struct svc_sock *svsk, unsigned int nreqs) static void svc_sock_secure_port(struct svc_rqst *rqstp) { if (svc_port_is_privileged(svc_addr(rqstp))) - set_bit(RQ_SECURE, &rqstp->rq_flags); + __set_bit(RQ_SECURE, &rqstp->rq_flags); else - clear_bit(RQ_SECURE, &rqstp->rq_flags); + __clear_bit(RQ_SECURE, &rqstp->rq_flags); } /* @@ -1008,9 +1008,9 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) rqstp->rq_xprt_ctxt = NULL; rqstp->rq_prot = IPPROTO_TCP; if (test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags)) - set_bit(RQ_LOCAL, &rqstp->rq_flags); + __set_bit(RQ_LOCAL, &rqstp->rq_flags); else - clear_bit(RQ_LOCAL, &rqstp->rq_flags); + __clear_bit(RQ_LOCAL, &rqstp->rq_flags); p = (__be32 *)rqstp->rq_arg.head[0].iov_base; calldir = p[1]; |