packet: Fixed TPACKET V3 to signal poll when block is closed rather than every packet

Make TPACKET_V3 signal poll when block is closed rather than for every
packet. Side effect is that poll will be signaled when block retire
timer expires which didn't previously happen. Issue was visible when
sending packets at a very low frequency such that all blocks are retired
before packets are received by TPACKET_V3. This caused avoidable packet
loss. The fix ensures that the signal is sent when blocks are closed
which covers the normal path where the block is filled as well as the
path where the timer expires. The case where a block is filled without
moving to the next block (ie. all blocks are full) will still cause poll
to be signaled.

Signed-off-by: Dan Collins <dan@dcollins.co.nz>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e52a4478568198e88d1d8f8ee6a8506284c36323..6880f34a529a56510b1145e14d41ed04803dd6a7 100644 (file)
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -785,6 +785,7 @@ static void prb_close_block(struct tpacket_kbdq_core *pkc1,
 
        struct tpacket3_hdr *last_pkt;
        struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1;
+       struct sock *sk = &po->sk;
 
        if (po->stats.stats3.tp_drops)
                status |= TP_STATUS_LOSING;
@@ -809,6 +810,8 @@ static void prb_close_block(struct tpacket_kbdq_core *pkc1,
        /* Flush the block */
        prb_flush_block(pkc1, pbd1, status);
 
+       sk->sk_data_ready(sk);
+
        pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1);
 }
 
@@ -2052,12 +2055,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
        smp_wmb();
 #endif
 
-       if (po->tp_version <= TPACKET_V2)
+       if (po->tp_version <= TPACKET_V2) {
                __packet_set_status(po, h.raw, status);
-       else
+               sk->sk_data_ready(sk);
+       } else {
                prb_clear_blk_fill_status(&po->rx_ring);
-
-       sk->sk_data_ready(sk);
+       }
 
 drop_n_restore:
        if (skb_head != skb->data && skb_shared(skb)) {