net/packet/af_packet.c | 40 +++++++++++++++++++++++----------------- net/packet/diag.c | 2 +- net/packet/internal.h | 5 ++--- 3 files changed, 26 insertions(+), 21 deletions(-)
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 <jackzxcui1989@163.com>
---
Changes in v6:
- Use hrtimer_is_queued instead to check whether it is within the callback function.
So do not need to add 'bool callback' parameter to _prb_refresh_rx_retire_blk_timer
as suggested by Willem de Bruijn;
- Do not need local_irq_save and local_irq_restore to protect the race of the timer
callback running in softirq context or the open_block from tpacket_rcv in process
context
as suggested by Willem de Bruijn;
Changes in v5:
- Remove the unnecessary comments at the top of the _prb_refresh_rx_retire_blk_timer,
branch is self-explanatory enough
as suggested by Willem de Bruijn;
- Indentation of _prb_refresh_rx_retire_blk_timer, align with first argument on
previous line
as suggested by Willem de Bruijn;
- Do not call hrtimer_start within the hrtimer callback
as suggested by Willem de Bruijn
So add 'bool callback' parameter to _prb_refresh_rx_retire_blk_timer to indicate
whether it is within the callback function. Use hrtimer_forward_now instead of
hrtimer_start when it is in the callback function and is doing prb_open_block.
- Link to v5: https://lore.kernel.org/all/20250819091447.1199980-1-jackzxcui1989@163.com/
Changes in v4:
- Add 'bool start' to distinguish whether the call to _prb_refresh_rx_retire_blk_timer
is for prb_open_block. When it is for prb_open_block, execute hrtimer_start to
(re)start the hrtimer; otherwise, use hrtimer_forward_now to set the expiration
time as it is more commonly used compared to hrtimer_set_expires.
as suggested by Willem de Bruijn;
- Delete the comments to explain why hrtimer_set_expires(not hrtimer_forward_now)
is used, as we do not use hrtimer_set_expires any more;
- Link to v4: https://lore.kernel.org/all/20250818050233.155344-1-jackzxcui1989@163.com/
Changes in v3:
- return HRTIMER_NORESTART when pkc->delete_blk_timer is true
as suggested by Willem de Bruijn;
- Drop the retire_blk_tov field of tpacket_kbdq_core, add interval_ktime instead
as suggested by Willem de Bruijn;
- Add comments to explain why hrtimer_set_expires(not hrtimer_forward_now) is used in
_prb_refresh_rx_retire_blk_timer
as suggested by Willem de Bruijn;
- Link to v3: https://lore.kernel.org/all/20250816170130.3969354-1-jackzxcui1989@163.com/
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 | 40 +++++++++++++++++++++++-----------------
net/packet/diag.c | 2 +-
net/packet/internal.h | 5 ++---
3 files changed, 26 insertions(+), 21 deletions(-)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a7017d7f0..9b13939a6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -203,8 +203,8 @@ 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_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *, bool);
static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *);
static void prb_clear_rxhash(struct tpacket_kbdq_core *,
struct tpacket3_hdr *);
@@ -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 +603,8 @@ 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);
}
static int prb_calc_retire_blk_tmo(struct packet_sock *po,
@@ -672,11 +671,10 @@ static void init_prb_bdqc(struct packet_sock *po,
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);
@@ -689,10 +687,14 @@ static void init_prb_bdqc(struct packet_sock *po,
/* 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)
+static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc,
+ bool start)
{
- mod_timer(&pkc->retire_blk_timer,
- jiffies + pkc->tov_in_jiffies);
+ if (start && !hrtimer_is_queued(&pkc->retire_blk_timer))
+ hrtimer_start(&pkc->retire_blk_timer, pkc->interval_ktime,
+ HRTIMER_MODE_REL_SOFT);
+ else
+ hrtimer_forward_now(&pkc->retire_blk_timer, pkc->interval_ktime);
pkc->last_kactive_blk_num = pkc->kactive_blk_num;
}
@@ -719,8 +721,9 @@ 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 +735,10 @@ 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:
@@ -786,10 +791,11 @@ static void prb_retire_rx_blk_timer_expired(struct timer_list *t)
}
refresh_timer:
- _prb_refresh_rx_retire_blk_timer(pkc);
+ _prb_refresh_rx_retire_blk_timer(pkc, false);
out:
spin_unlock(&po->sk.sk_receive_queue.lock);
+ return ret;
}
static void prb_flush_block(struct tpacket_kbdq_core *pkc1,
@@ -921,7 +927,7 @@ 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);
+ _prb_refresh_rx_retire_blk_timer(pkc1, true);
smp_wmb();
}
diff --git a/net/packet/diag.c b/net/packet/diag.c
index 6ce1dcc28..c8f43e0c1 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -83,7 +83,7 @@ static int pdiag_put_ring(struct packet_ring_buffer *ring, int ver, int nl_type,
pdr.pdr_frame_nr = ring->frame_max + 1;
if (ver > TPACKET_V2) {
- pdr.pdr_retire_tmo = ring->prb_bdqc.retire_blk_tov;
+ pdr.pdr_retire_tmo = ktime_to_ms(ring->prb_bdqc.interval_ktime);
pdr.pdr_sizeof_priv = ring->prb_bdqc.blk_sizeof_priv;
pdr.pdr_features = ring->prb_bdqc.feature_req_word;
} else {
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 1e743d031..19d4f0b73 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -45,12 +45,11 @@ struct tpacket_kbdq_core {
/* Default is set to 8ms */
#define DEFAULT_PRB_RETIRE_TOV (8)
- unsigned short retire_blk_tov;
+ ktime_t interval_ktime;
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 {
--
2.34.1syzbot ci has tested the following series [v6] net: af_packet: Use hrtimer to do the retire operation https://lore.kernel.org/all/20250820092925.2115372-1-jackzxcui1989@163.com * [PATCH net-next v6] net: af_packet: Use hrtimer to do the retire operation and found the following issue: WARNING in hrtimer_forward Full report is available here: https://ci.syzbot.org/series/81b08fd6-a740-4520-9c88-b7dcdc7953a1 *** WARNING in hrtimer_forward tree: net-next URL: https://kernel.googlesource.com/pub/scm/linux/kernel/git/netdev/net-next.git base: da114122b83149d1f1db0586b1d67947b651aa20 arch: amd64 compiler: Debian clang version 20.1.7 (++20250616065708+6146a88f6049-1~exp1~20250616065826.132), Debian LLD 20.1.7 config: https://ci.syzbot.org/builds/0ebac6ed-b7ae-4c3d-9edc-db3a521ad7a0/config C repro: https://ci.syzbot.org/findings/c3421800-7bbc-4097-a1cf-36e97a4dea98/c_repro syz repro: https://ci.syzbot.org/findings/c3421800-7bbc-4097-a1cf-36e97a4dea98/syz_repro ------------[ cut here ]------------ WARNING: CPU: 1 PID: 6012 at kernel/time/hrtimer.c:1052 hrtimer_forward+0x1d6/0x2b0 kernel/time/hrtimer.c:1052 Modules linked in: CPU: 1 UID: 0 PID: 6012 Comm: syz.0.20 Not tainted syzkaller #0 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 RIP: 0010:hrtimer_forward+0x1d6/0x2b0 kernel/time/hrtimer.c:1052 Code: 4c 89 33 48 8b 04 24 eb 07 e8 66 30 12 00 31 c0 48 83 c4 18 5b 41 5c 41 5d 41 5e 41 5f 5d e9 01 b0 ce 09 cc e8 4b 30 12 00 90 <0f> 0b 90 eb df 48 89 e8 4c 09 f8 48 c1 e8 20 74 0a 48 89 e8 31 d2 RSP: 0018:ffffc900029def90 EFLAGS: 00010293 RAX: ffffffff81ad7be5 RBX: ffff888028782648 RCX: ffff88810e88d640 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: 000000000000116b R08: ffffffff8fa37e37 R09: 1ffffffff1f46fc6 R10: dffffc0000000000 R11: ffffffff81724e10 R12: ffff888028782660 R13: 00000000007a1200 R14: 1ffff110050f04cc R15: 0000000000000001 FS: 000055555f6cd500(0000) GS:ffff8881a3c1c000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffcf1be3d88 CR3: 0000000023c86000 CR4: 00000000000006f0 Call Trace: <TASK> hrtimer_forward_now include/linux/hrtimer.h:366 [inline] _prb_refresh_rx_retire_blk_timer net/packet/af_packet.c:697 [inline] prb_open_block+0x3a7/0x5e0 net/packet/af_packet.c:930 prb_dispatch_next_block net/packet/af_packet.c:994 [inline] __packet_lookup_frame_in_block net/packet/af_packet.c:1152 [inline] packet_current_rx_frame net/packet/af_packet.c:1178 [inline] tpacket_rcv+0x1229/0x2f40 net/packet/af_packet.c:2409 deliver_skb net/core/dev.c:2472 [inline] deliver_ptype_list_skb net/core/dev.c:2487 [inline] __netif_receive_skb_core+0x3107/0x4020 net/core/dev.c:5923 __netif_receive_skb_list_core+0x23f/0x800 net/core/dev.c:6054 __netif_receive_skb_list net/core/dev.c:6121 [inline] netif_receive_skb_list_internal+0x975/0xcc0 net/core/dev.c:6212 netif_receive_skb_list+0x54/0x450 net/core/dev.c:6264 xdp_recv_frames net/bpf/test_run.c:280 [inline] xdp_test_run_batch net/bpf/test_run.c:361 [inline] bpf_test_run_xdp_live+0x1786/0x1b10 net/bpf/test_run.c:390 bpf_prog_test_run_xdp+0x713/0x1000 net/bpf/test_run.c:1322 bpf_prog_test_run+0x2c7/0x340 kernel/bpf/syscall.c:4590 __sys_bpf+0x581/0x870 kernel/bpf/syscall.c:6047 __do_sys_bpf kernel/bpf/syscall.c:6139 [inline] __se_sys_bpf kernel/bpf/syscall.c:6137 [inline] __x64_sys_bpf+0x7c/0x90 kernel/bpf/syscall.c:6137 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f31da38ebe9 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffcf1be5358 EFLAGS: 00000246 ORIG_RAX: 0000000000000141 RAX: ffffffffffffffda RBX: 00007f31da5b5fa0 RCX: 00007f31da38ebe9 RDX: 0000000000000050 RSI: 0000200000000600 RDI: 000000000000000a RBP: 00007f31da411e19 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f31da5b5fa0 R14: 00007f31da5b5fa0 R15: 0000000000000003 </TASK> *** If these findings have caused you to resend the series or submit a separate fix, please add the following tag to your commit message: Tested-by: syzbot@syzkaller.appspotmail.com --- This report is generated by a bot. It may contain errors. syzbot ci engineers can be reached at syzkaller@googlegroups.com.
Xin Zhao wrote:
> 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 <jackzxcui1989@163.com>
>
> ---
> Changes in v6:
> - Use hrtimer_is_queued instead to check whether it is within the callback function.
> So do not need to add 'bool callback' parameter to _prb_refresh_rx_retire_blk_timer
> as suggested by Willem de Bruijn;
> - Do not need local_irq_save and local_irq_restore to protect the race of the timer
> callback running in softirq context or the open_block from tpacket_rcv in process
> context
> as suggested by Willem de Bruijn;
>
> Changes in v5:
> - Remove the unnecessary comments at the top of the _prb_refresh_rx_retire_blk_timer,
> branch is self-explanatory enough
> as suggested by Willem de Bruijn;
> - Indentation of _prb_refresh_rx_retire_blk_timer, align with first argument on
> previous line
> as suggested by Willem de Bruijn;
> - Do not call hrtimer_start within the hrtimer callback
> as suggested by Willem de Bruijn
> So add 'bool callback' parameter to _prb_refresh_rx_retire_blk_timer to indicate
> whether it is within the callback function. Use hrtimer_forward_now instead of
> hrtimer_start when it is in the callback function and is doing prb_open_block.
> - Link to v5: https://lore.kernel.org/all/20250819091447.1199980-1-jackzxcui1989@163.com/
>
> Changes in v4:
> - Add 'bool start' to distinguish whether the call to _prb_refresh_rx_retire_blk_timer
> is for prb_open_block. When it is for prb_open_block, execute hrtimer_start to
> (re)start the hrtimer; otherwise, use hrtimer_forward_now to set the expiration
> time as it is more commonly used compared to hrtimer_set_expires.
> as suggested by Willem de Bruijn;
> - Delete the comments to explain why hrtimer_set_expires(not hrtimer_forward_now)
> is used, as we do not use hrtimer_set_expires any more;
> - Link to v4: https://lore.kernel.org/all/20250818050233.155344-1-jackzxcui1989@163.com/
>
> Changes in v3:
> - return HRTIMER_NORESTART when pkc->delete_blk_timer is true
> as suggested by Willem de Bruijn;
> - Drop the retire_blk_tov field of tpacket_kbdq_core, add interval_ktime instead
> as suggested by Willem de Bruijn;
> - Add comments to explain why hrtimer_set_expires(not hrtimer_forward_now) is used in
> _prb_refresh_rx_retire_blk_timer
> as suggested by Willem de Bruijn;
> - Link to v3: https://lore.kernel.org/all/20250816170130.3969354-1-jackzxcui1989@163.com/
>
> 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 | 40 +++++++++++++++++++++++-----------------
> net/packet/diag.c | 2 +-
> net/packet/internal.h | 5 ++---
> 3 files changed, 26 insertions(+), 21 deletions(-)
>
> diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
> index a7017d7f0..9b13939a6 100644
> --- a/net/packet/af_packet.c
> +++ b/net/packet/af_packet.c
> @@ -203,8 +203,8 @@ 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_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *, bool);
> static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *);
> static void prb_clear_rxhash(struct tpacket_kbdq_core *,
> struct tpacket3_hdr *);
> @@ -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 +603,8 @@ 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);
> }
>
> static int prb_calc_retire_blk_tmo(struct packet_sock *po,
> @@ -672,11 +671,10 @@ static void init_prb_bdqc(struct packet_sock *po,
> 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);
>
> @@ -689,10 +687,14 @@ static void init_prb_bdqc(struct packet_sock *po,
> /* 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)
> +static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc,
> + bool start)
> {
> - mod_timer(&pkc->retire_blk_timer,
> - jiffies + pkc->tov_in_jiffies);
> + if (start && !hrtimer_is_queued(&pkc->retire_blk_timer))
> + hrtimer_start(&pkc->retire_blk_timer, pkc->interval_ktime,
> + HRTIMER_MODE_REL_SOFT);
> + else
> + hrtimer_forward_now(&pkc->retire_blk_timer, pkc->interval_ktime);
Is the hrtimer still queued when prb_retire_rx_blk_timer_expired
fires? Based on the existence of hrtimer_forward_now, I assume so. But
have not checked yet. If so, hrtimer_is_queued alone suffices to
detect the other callstack from tpacket_rcv where hrtimer_start is
needed. No need for bool start?
> pkc->last_kactive_blk_num = pkc->kactive_blk_num;
> }
© 2016 - 2025 Red Hat, Inc.