diff options
Diffstat (limited to 'net/packet/af_packet.c')
| -rw-r--r-- | net/packet/af_packet.c | 134 |
1 files changed, 40 insertions, 94 deletions
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a7017d7f0927..173e6edda08f 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -203,8 +203,7 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *, static int prb_queue_frozen(struct tpacket_kbdq_core *); static void prb_open_block(struct tpacket_kbdq_core *, struct tpacket_block_desc *); -static void prb_retire_rx_blk_timer_expired(struct timer_list *); -static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *); +static enum hrtimer_restart prb_retire_rx_blk_timer_expired(struct hrtimer *); static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_clear_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); @@ -579,33 +578,13 @@ static __be16 vlan_get_protocol_dgram(const struct sk_buff *skb) return proto; } -static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) -{ - timer_delete_sync(&pkc->retire_blk_timer); -} - static void prb_shutdown_retire_blk_timer(struct packet_sock *po, struct sk_buff_head *rb_queue) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); - - spin_lock_bh(&rb_queue->lock); - pkc->delete_blk_timer = 1; - spin_unlock_bh(&rb_queue->lock); - - prb_del_retire_blk_timer(pkc); -} - -static void prb_setup_retire_blk_timer(struct packet_sock *po) -{ - struct tpacket_kbdq_core *pkc; - - pkc = GET_PBDQC_FROM_RB(&po->rx_ring); - timer_setup(&pkc->retire_blk_timer, prb_retire_rx_blk_timer_expired, - 0); - pkc->retire_blk_timer.expires = jiffies; + hrtimer_cancel(&pkc->retire_blk_timer); } static int prb_calc_retire_blk_tmo(struct packet_sock *po, @@ -669,57 +648,36 @@ static void init_prb_bdqc(struct packet_sock *po, p1->knum_blocks = req_u->req3.tp_block_nr; p1->hdrlen = po->tp_hdrlen; p1->version = po->tp_version; - p1->last_kactive_blk_num = 0; po->stats.stats3.tp_freeze_q_cnt = 0; if (req_u->req3.tp_retire_blk_tov) - p1->retire_blk_tov = req_u->req3.tp_retire_blk_tov; + p1->interval_ktime = ms_to_ktime(req_u->req3.tp_retire_blk_tov); else - p1->retire_blk_tov = prb_calc_retire_blk_tmo(po, - req_u->req3.tp_block_size); - p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov); + p1->interval_ktime = ms_to_ktime(prb_calc_retire_blk_tmo(po, + req_u->req3.tp_block_size)); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; rwlock_init(&p1->blk_fill_in_prog_lock); p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); - prb_setup_retire_blk_timer(po); + hrtimer_setup(&p1->retire_blk_timer, prb_retire_rx_blk_timer_expired, + CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + hrtimer_start(&p1->retire_blk_timer, p1->interval_ktime, + HRTIMER_MODE_REL_SOFT); prb_open_block(p1, pbd); } -/* Do NOT update the last_blk_num first. - * Assumes sk_buff_head lock is held. - */ -static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc) -{ - mod_timer(&pkc->retire_blk_timer, - jiffies + pkc->tov_in_jiffies); - pkc->last_kactive_blk_num = pkc->kactive_blk_num; -} - /* - * Timer logic: - * 1) We refresh the timer only when we open a block. - * By doing this we don't waste cycles refreshing the timer - * on packet-by-packet basis. - * * With a 1MB block-size, on a 1Gbps line, it will take * i) ~8 ms to fill a block + ii) memcpy etc. * In this cut we are not accounting for the memcpy time. * - * So, if the user sets the 'tmo' to 10ms then the timer - * will never fire while the block is still getting filled - * (which is what we want). However, the user could choose - * to close a block early and that's fine. - * - * But when the timer does fire, we check whether or not to refresh it. * Since the tmo granularity is in msecs, it is not too expensive * to refresh the timer, lets say every '8' msecs. * Either the user can set the 'tmo' or we can derive it based on * a) line-speed and b) block-size. * prb_calc_retire_blk_tmo() calculates the tmo. - * */ -static void prb_retire_rx_blk_timer_expired(struct timer_list *t) +static enum hrtimer_restart prb_retire_rx_blk_timer_expired(struct hrtimer *t) { struct packet_sock *po = timer_container_of(po, t, rx_ring.prb_bdqc.retire_blk_timer); @@ -732,9 +690,6 @@ static void prb_retire_rx_blk_timer_expired(struct timer_list *t) frozen = prb_queue_frozen(pkc); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); - if (unlikely(pkc->delete_blk_timer)) - goto out; - /* We only need to plug the race when the block is partially filled. * tpacket_rcv: * lock(); increment BLOCK_NUM_PKTS; unlock() @@ -750,46 +705,31 @@ static void prb_retire_rx_blk_timer_expired(struct timer_list *t) write_unlock(&pkc->blk_fill_in_prog_lock); } - if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) { - if (!frozen) { - if (!BLOCK_NUM_PKTS(pbd)) { - /* An empty block. Just refresh the timer. */ - goto refresh_timer; - } + if (!frozen) { + if (BLOCK_NUM_PKTS(pbd)) { + /* Not an empty block. Need retire the block. */ prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO); - if (!prb_dispatch_next_block(pkc, po)) - goto refresh_timer; - else - goto out; - } else { - /* Case 1. Queue was frozen because user-space was - * lagging behind. + prb_dispatch_next_block(pkc, po); + } + } else { + /* Case 1. Queue was frozen because user-space was + * lagging behind. + */ + if (!prb_curr_blk_in_use(pbd)) { + /* Case 2. queue was frozen,user-space caught up, + * now the link went idle && the timer fired. + * We don't have a block to close.So we open this + * block and restart the timer. + * opening a block thaws the queue,restarts timer + * Thawing/timer-refresh is a side effect. */ - if (prb_curr_blk_in_use(pbd)) { - /* - * Ok, user-space is still behind. - * So just refresh the timer. - */ - goto refresh_timer; - } else { - /* Case 2. queue was frozen,user-space caught up, - * now the link went idle && the timer fired. - * We don't have a block to close.So we open this - * block and restart the timer. - * opening a block thaws the queue,restarts timer - * Thawing/timer-refresh is a side effect. - */ - prb_open_block(pkc, pbd); - goto out; - } + prb_open_block(pkc, pbd); } } -refresh_timer: - _prb_refresh_rx_retire_blk_timer(pkc); - -out: + hrtimer_forward_now(&pkc->retire_blk_timer, pkc->interval_ktime); spin_unlock(&po->sk.sk_receive_queue.lock); + return HRTIMER_RESTART; } static void prb_flush_block(struct tpacket_kbdq_core *pkc1, @@ -883,11 +823,18 @@ static void prb_thaw_queue(struct tpacket_kbdq_core *pkc) } /* - * Side effect of opening a block: + * prb_open_block is called by tpacket_rcv or timer callback. * - * 1) prb_queue is thawed. - * 2) retire_blk_timer is refreshed. + * Reasons why NOT update hrtimer in prb_open_block: + * 1) It will increase complexity to distinguish the two caller scenario. + * 2) hrtimer_cancel and hrtimer_start need to be called if you want to update + * TMO of an already enqueued hrtimer, leading to complex shutdown logic. * + * One side effect of NOT update hrtimer when called by tpacket_rcv is that + * a newly opened block triggered by tpacket_rcv may be retired earlier than + * expected. On the other hand, if timeout is updated in prb_open_block, the + * frequent reception of network packets that leads to prb_open_block being + * called may cause hrtimer to be removed and enqueued repeatedly. */ static void prb_open_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1) @@ -921,7 +868,6 @@ static void prb_open_block(struct tpacket_kbdq_core *pkc1, pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size; prb_thaw_queue(pkc1); - _prb_refresh_rx_retire_blk_timer(pkc1); smp_wmb(); } @@ -2265,7 +2211,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, drop_n_acct: atomic_inc(&po->tp_drops); - atomic_inc(&sk->sk_drops); + sk_drops_inc(sk); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; drop_n_restore: |