diff options
| author | Vitaliy Makkoveev <mvs@cvs.openbsd.org> | 2024-07-12 17:20:19 +0000 |
|---|---|---|
| committer | Vitaliy Makkoveev <mvs@cvs.openbsd.org> | 2024-07-12 17:20:19 +0000 |
| commit | e3daaa046926cc1a80d1db22554bd479e81e2a32 (patch) | |
| tree | 975e82d8693178ea9c65df7372c814f25e1ab049 /sys/nfs | |
| parent | 4eced7c1ad4c0354f4f30729abcb079291417876 (diff) | |
Switch `so_snd' of udp(4) sockets to the new locking scheme.
udp_send() and following udp{,6}_output() do not append packets to
`so_snd' socket buffer. This mean the sosend() and sosplice() sending
paths are dummy pru_send() and there is no problems to simultaneously
run them on the same socket.
Push shared solock() deep down to sesend() and take it only around
pru_send(), but keep somove() running unedr exclusive solock(). Since
sosend() doesn't modify `so_snd' the unlocked `so_snd' space checks
within somove() are safe. Corresponding `sb_state' and `sb_flags'
modifications are protected by `sb_mtx' mutex(9).
Tested and OK bluhm.
Diffstat (limited to 'sys/nfs')
| -rw-r--r-- | sys/nfs/nfs_socket.c | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/sys/nfs/nfs_socket.c b/sys/nfs/nfs_socket.c index c6ec74e1cc3..f75122ed20d 100644 --- a/sys/nfs/nfs_socket.c +++ b/sys/nfs/nfs_socket.c @@ -1,4 +1,4 @@ -/* $OpenBSD: nfs_socket.c,v 1.150 2024/04/30 17:05:20 miod Exp $ */ +/* $OpenBSD: nfs_socket.c,v 1.151 2024/07/12 17:20:18 mvs Exp $ */ /* $NetBSD: nfs_socket.c,v 1.27 1996/04/15 20:20:00 thorpej Exp $ */ /* @@ -374,7 +374,9 @@ nfs_connect(struct nfsmount *nmp, struct nfsreq *rep) mtx_enter(&so->so_rcv.sb_mtx); so->so_rcv.sb_flags |= SB_NOINTR; mtx_leave(&so->so_rcv.sb_mtx); + mtx_enter(&so->so_snd.sb_mtx); so->so_snd.sb_flags |= SB_NOINTR; + mtx_leave(&so->so_snd.sb_mtx); sounlock(so); m_freem(mopt); |