diff options
| author | Eric Dumazet <edumazet@google.com> | 2024-05-15 19:33:58 +0300 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2024-06-12 12:12:12 +0300 |
| commit | ee3577c5d33c279a804b256287fbc360fc6d430c (patch) | |
| tree | 9dc1cee28f2dc98d67869b3fce32b68145016de0 /net | |
| parent | f28bdc2ee5d9300cc77bd3d97b5b3cdd14960fd8 (diff) | |
| download | linux-ee3577c5d33c279a804b256287fbc360fc6d430c.tar.xz | |
af_packet: do not call packet_read_pending() from tpacket_destruct_skb()
[ Upstream commit 581073f626e387d3e7eed55c48c8495584ead7ba ]
trafgen performance considerably sank on hosts with many cores
after the blamed commit.
packet_read_pending() is very expensive, and calling it
in af_packet fast path defeats Daniel intent in commit
b013840810c2 ("packet: use percpu mmap tx frame pending refcount")
tpacket_destruct_skb() makes room for one packet, we can immediately
wakeup a producer, no need to completely drain the tx ring.
Fixes: 89ed5b519004 ("af_packet: Block execution of tasks waiting for transmit to complete in AF_PACKET")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20240515163358.4105915-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Diffstat (limited to 'net')
| -rw-r--r-- | net/packet/af_packet.c | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f017d7d33da3..ff1ddf544e17 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2528,8 +2528,7 @@ static void tpacket_destruct_skb(struct sk_buff *skb) ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); - if (!packet_read_pending(&po->tx_ring)) - complete(&po->skb_completion); + complete(&po->skb_completion); } sock_wfree(skb); |