In a system with high real-time requirements, the timeout mechanism of ordinary timers with jiffies granularity is insufficient to meet the demands for real-time performance. Meanwhile, the optimization of CPU usage with af_packet is quite significant. Use hrtimer instead of timer to help compensate for the shortcomings in real-time performance. In HZ=100 or HZ=250 system, the update of TP_STATUS_USER is not real-time enough, with fluctuations reaching over 8ms (on a system with HZ=250). This is unacceptable in some high real-time systems that require timely processing of network packets. By replacing it with hrtimer, if a timeout of 2ms is set, the update of TP_STATUS_USER can be stabilized to within 3 ms. Signed-off-by: Xin Zhao --- Changes in v3: - return HRTIMER_NORESTART when pkc->delete_blk_timer is true as suggested by Willem de Bruijn; Changes in v2: - Drop the tov_in_msecs field of tpacket_kbdq_core added by the patch as suggested by Willem de Bruijn; - Link to v2: https://lore.kernel.org/all/20250815044141.1374446-1-jackzxcui1989@163.com/ Changes in v1: - Do not add another config for the current changes as suggested by Eric Dumazet; - Mention the beneficial cases 'HZ=100 or HZ=250' in the changelog as suggested by Eric Dumazet; - Add some performance details to the changelog as suggested by Ferenc Fejes; - Delete the 'pkc->tov_in_msecs == 0' bounds check which is not necessary as suggested by Willem de Bruijn; - Use hrtimer_set_expires instead of hrtimer_start_range_ns when retire timer needs update as suggested by Willem de Bruijn. Start the hrtimer in prb_setup_retire_blk_timer; - Just return HRTIMER_RESTART directly as all cases return the same value as suggested by Willem de Bruijn; - Link to v1: https://lore.kernel.org/all/20250813165201.1492779-1-jackzxcui1989@163.com/ - Link to v0: https://lore.kernel.org/all/20250806055210.1530081-1-jackzxcui1989@163.com/ --- --- net/packet/af_packet.c | 24 ++++++++++++++---------- net/packet/internal.h | 3 +-- 2 files changed, 15 insertions(+), 12 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a7017d7f0..763b0c968 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -203,7 +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 enum hrtimer_restart prb_retire_rx_blk_timer_expired(struct hrtimer *); static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *); static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_clear_rxhash(struct tpacket_kbdq_core *, @@ -581,7 +581,7 @@ static __be16 vlan_get_protocol_dgram(const struct sk_buff *skb) static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) { - timer_delete_sync(&pkc->retire_blk_timer); + hrtimer_cancel(&pkc->retire_blk_timer); } static void prb_shutdown_retire_blk_timer(struct packet_sock *po, @@ -603,9 +603,10 @@ 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_setup(&pkc->retire_blk_timer, prb_retire_rx_blk_timer_expired, + CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + hrtimer_start(&pkc->retire_blk_timer, ms_to_ktime(pkc->retire_blk_tov), + HRTIMER_MODE_REL_SOFT); } static int prb_calc_retire_blk_tmo(struct packet_sock *po, @@ -676,7 +677,6 @@ static void init_prb_bdqc(struct packet_sock *po, 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->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; rwlock_init(&p1->blk_fill_in_prog_lock); @@ -691,8 +691,8 @@ static void init_prb_bdqc(struct packet_sock *po, */ static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc) { - mod_timer(&pkc->retire_blk_timer, - jiffies + pkc->tov_in_jiffies); + hrtimer_set_expires(&pkc->retire_blk_timer, + ktime_add(ktime_get(), ms_to_ktime(pkc->retire_blk_tov))); pkc->last_kactive_blk_num = pkc->kactive_blk_num; } @@ -719,8 +719,9 @@ static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc) * 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) { + enum hrtimer_restart ret = HRTIMER_RESTART; struct packet_sock *po = timer_container_of(po, t, rx_ring.prb_bdqc.retire_blk_timer); struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring); @@ -732,8 +733,10 @@ 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)) + if (unlikely(pkc->delete_blk_timer)) { + ret = HRTIMER_NORESTART; goto out; + } /* We only need to plug the race when the block is partially filled. * tpacket_rcv: @@ -790,6 +793,7 @@ static void prb_retire_rx_blk_timer_expired(struct timer_list *t) out: spin_unlock(&po->sk.sk_receive_queue.lock); + return ret; } static void prb_flush_block(struct tpacket_kbdq_core *pkc1, diff --git a/net/packet/internal.h b/net/packet/internal.h index 1e743d031..9812feb3d 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -47,10 +47,9 @@ struct tpacket_kbdq_core { unsigned short retire_blk_tov; unsigned short version; - unsigned long tov_in_jiffies; /* timer to retire an outstanding block */ - struct timer_list retire_blk_timer; + struct hrtimer retire_blk_timer; }; struct pgv { -- 2.34.1