packet: don't unconditionally schedule() in case of MSG_DONTWAIT
In tpacket_snd(), when we've discovered a first frame that is
not in status TP_STATUS_SEND_REQUEST, and return a NULL buffer,
we exit the send routine in case of MSG_DONTWAIT, since we've
finished traversing the mmaped send ring buffer and don't care
about pending frames.
While doing so, we still unconditionally call an expensive
schedule() in the packet_current_frame() "error" path, which
is unnecessary in this case since it's enough to just quit
the function.
Also, in case MSG_DONTWAIT is not set, we should rather test
for need_resched() first and do schedule() only if necessary
since meanwhile pending frames could already have finished
processing and called skb destructor.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 85bb38c..d5495d8 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2156,6 +2156,7 @@
int err, reserve = 0;
void *ph;
struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
+ bool need_wait = !(msg->msg_flags & MSG_DONTWAIT);
int tp_len, size_max;
unsigned char *addr;
int len_sum = 0;
@@ -2198,10 +2199,10 @@
do {
ph = packet_current_frame(po, &po->tx_ring,
- TP_STATUS_SEND_REQUEST);
-
+ TP_STATUS_SEND_REQUEST);
if (unlikely(ph == NULL)) {
- schedule();
+ if (need_wait && need_resched())
+ schedule();
continue;
}
@@ -2255,10 +2256,8 @@
}
packet_increment_head(&po->tx_ring);
len_sum += tp_len;
- } while (likely((ph != NULL) ||
- ((!(msg->msg_flags & MSG_DONTWAIT)) &&
- (atomic_read(&po->tx_ring.pending))))
- );
+ } while (likely((ph != NULL) || (need_wait &&
+ atomic_read(&po->tx_ring.pending))));
err = len_sum;
goto out_put;