bpf: increment and use correct thread iterator
Subsystems (4)
v4 cover bpf: increment and use correct thread iterator
From: Jonathan Lemon <[email protected]>
v3->v4:
Split commit into separate patches.v2->v3:
Add splat to commitlog descriptionsv1->v2
Use Fixes: shas from correct tree
Jonathan Lemon (3):
bpf: save correct stopping point in file seq iteration.
bpf: Use thread_group_leader()
bpf: optimize task iteration
kernel/bpf/task_iter.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
Signature · 1 line
2.24.1
PATCH v4 1/3 bpf: save correct stopping point in file seq iteration.
From: Jonathan Lemon <[email protected]>
On some systems, some variant of the following splat is repeatedly seen. The common factor in all traces seems to be the entry point to task_file_seq_next(). With the patch, all warnings go away.
rcu: INFO: rcu_sched self-detected stall on CPU
rcu: \x0926-....: (20992 ticks this GP) idle=d7e/1/0x4000000000000002 softirq=81556231/81556231 fqs=4876
\x09(t=21033 jiffies g=159148529 q=223125)
NMI backtrace for cpu 26
CPU: 26 PID: 2015853 Comm: bpftool Kdump: loaded Not tainted 5.6.13-0_fbk4_3876_gd8d1f9bf80bb #1
Hardware name: Quanta Twin Lakes MP/Twin Lakes Passive MP, BIOS F09_3A12 10/08/2018
Call Trace:
<IRQ>
dump_stack+0x50/0x70
nmi_cpu_backtrace.cold.6+0x13/0x50
? lapic_can_unplug_cpu.cold.30+0x40/0x40
nmi_trigger_cpumask_backtrace+0xba/0xca
rcu_dump_cpu_stacks+0x99/0xc7
rcu_sched_clock_irq.cold.90+0x1b4/0x3aa
? tick_sched_do_timer+0x60/0x60
update_process_times+0x24/0x50
tick_sched_timer+0x37/0x70
__hrtimer_run_queues+0xfe/0x270
hrtimer_interrupt+0xf4/0x210
smp_apic_timer_interrupt+0x5e/0x120
apic_timer_interrupt+0xf/0x20
</IRQ>
RIP: 0010:get_pid_task+0x38/0x80
Code: 89 f6 48 8d 44 f7 08 48 8b 00 48 85 c0 74 2b 48 83 c6 55 48 c1 e6 04 48 29 f0 74 19 48 8d 78 20 ba 01 00 00 00 f0 0f c1 50 20 <85> d2 74 27 78 11 83 c2 01 78 0c 48 83 c4 08 c3 31 c0 48 83 c4 08
RSP: 0018:ffffc9000d293dc8 EFLAGS: 00000202 ORIG_RAX: ffffffffffffff13
RAX: ffff888637c05600 RBX: ffffc9000d293e0c RCX: 0000000000000000
RDX: 0000000000000001 RSI: 0000000000000550 RDI: ffff888637c05620
RBP: ffffffff8284eb80 R08: ffff88831341d300 R09: ffff88822ffd8248
R10: ffff88822ffd82d0 R11: 00000000003a93c0 R12: 0000000000000001
R13: 00000000ffffffff R14: ffff88831341d300 R15: 0000000000000000
? find_ge_pid+0x1b/0x20
task_seq_get_next+0x52/0xc0
task_file_seq_get_next+0x159/0x220
task_file_seq_next+0x4f/0xa0
bpf_seq_read+0x159/0x390
vfs_read+0x8a/0x140
ksys_read+0x59/0xd0
do_syscall_64+0x42/0x110
entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7f95ae73e76e
Code: Bad RIP value.
RSP: 002b:00007ffc02c1dbf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
RAX: ffffffffffffffda RBX: 000000000170faa0 RCX: 00007f95ae73e76e
RDX: 0000000000001000 RSI: 00007ffc02c1dc30 RDI: 0000000000000007
RBP: 00007ffc02c1ec70 R08: 0000000000000005 R09: 0000000000000006
R10: fffffffffffff20b R11: 0000000000000246 R12: 00000000019112a0
R13: 0000000000000000 R14: 0000000000000007 R15: 00000000004283c0If unable to obtain the file structure for the current task, proceed to the next task number after the one returned from task_seq_get_next(), instead of the next task number from the original iterator.
Also, save the stopping task number from task_seq_get_next() on failure in case of restarts.
--- kernel/bpf/task_iter.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/bpf/task_iter.c +2 -1
@@ -158,13 +158,14 @@ task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info)if (!curr_task) { info->task =NULL ; info->files =NULL ; + info->tid = curr_tid;return NULL ; } curr_files =get_files_struct (curr_task);if (!curr_files) {put_task_struct (curr_task); - curr_tid = ++(info->tid); + curr_tid = curr_tid +1 ; info->fd =0 ; goto again; }
Signature · 1 line
2.24.1
Re: [PATCH 1/3 v4 bpf-next] bpf: save correct stopping point in file seq iteration.
Quoted 61 lines · Jonathan Lemon
From: Jonathan Lemon <[email protected]>
On some systems, some variant of the following splat is repeatedly seen. The common factor in all traces seems to be the entry point to
task_file_seq_next(). With the patch, all warnings go away.rcu: INFO: rcu_sched self-detected stall on CPU rcu: \x0926-....: (20992 ticks this GP) idle=d7e/1/0x4000000000000002 softirq=81556231/81556231 fqs=4876 \x09(t=21033 jiffies g=159148529 q=223125) NMI backtrace for cpu 26 CPU: 26 PID: 2015853 Comm: bpftool Kdump: loaded Not tainted 5.6.13-0_fbk4_3876_gd8d1f9bf80bb #1 Hardware name: Quanta Twin Lakes MP/Twin Lakes Passive MP, BIOS F09_3A12 10/08/2018 Call Trace: <IRQ> dump_stack+0x50/0x70 nmi_cpu_backtrace.cold.6+0x13/0x50 ? lapic_can_unplug_cpu.cold.30+0x40/0x40 nmi_trigger_cpumask_backtrace+0xba/0xca rcu_dump_cpu_stacks+0x99/0xc7 rcu_sched_clock_irq.cold.90+0x1b4/0x3aa ? tick_sched_do_timer+0x60/0x60 update_process_times+0x24/0x50 tick_sched_timer+0x37/0x70 __hrtimer_run_queues+0xfe/0x270 hrtimer_interrupt+0xf4/0x210 smp_apic_timer_interrupt+0x5e/0x120 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:get_pid_task+0x38/0x80 Code: 89 f6 48 8d 44 f7 08 48 8b 00 48 85 c0 74 2b 48 83 c6 55 48 c1 e6 04 48 29 f0 74 19 48 8d 78 20 ba 01 00 00 00 f0 0f c1 50 20 <85> d2 74 27 78 11 83 c2 01 78 0c 48 83 c4 08 c3 31 c0 48 83 c4 08 RSP: 0018:ffffc9000d293dc8 EFLAGS: 00000202 ORIG_RAX: ffffffffffffff13 RAX: ffff888637c05600 RBX: ffffc9000d293e0c RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000550 RDI: ffff888637c05620 RBP: ffffffff8284eb80 R08: ffff88831341d300 R09: ffff88822ffd8248 R10: ffff88822ffd82d0 R11: 00000000003a93c0 R12: 0000000000000001 R13: 00000000ffffffff R14: ffff88831341d300 R15: 0000000000000000 ? find_ge_pid+0x1b/0x20 task_seq_get_next+0x52/0xc0 task_file_seq_get_next+0x159/0x220 task_file_seq_next+0x4f/0xa0 bpf_seq_read+0x159/0x390 vfs_read+0x8a/0x140 ksys_read+0x59/0xd0 do_syscall_64+0x42/0x110 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f95ae73e76e Code: Bad RIP value. RSP: 002b:00007ffc02c1dbf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: 000000000170faa0 RCX: 00007f95ae73e76e RDX: 0000000000001000 RSI: 00007ffc02c1dc30 RDI: 0000000000000007 RBP: 00007ffc02c1ec70 R08: 0000000000000005 R09: 0000000000000006 R10: fffffffffffff20b R11: 0000000000000246 R12: 00000000019112a0 R13: 0000000000000000 R14: 0000000000000007 R15: 00000000004283c0If unable to obtain the file structure for the current task, proceed to the next task number after the one returned from
task_seq_get_next(), instead of the next task number from the original iterator.
Quoted 6 lines
Also, save the stopping task number from
task_seq_get_next()on failure in case of restarts.Fixes a650da2ee52a ("bpf: Add task and task/file iterator targets")Signed-off-by Jonathan Lemon <[email protected]>---
LGTM, thanks!
Quoted 26 lines
kernel/bpf/task_iter.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)kernel/bpf/task_iter.c +2
-2@@ -158,13 +158,14 @@ task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info)if (!curr_task) { info->task =NULL ; info->files =NULL ; + info->tid = curr_tid;return NULL ; } curr_files =get_files_struct (curr_task);if (!curr_files) {put_task_struct (curr_task); - curr_tid = ++(info->tid); + curr_tid = curr_tid +1 ; info->fd =0 ; goto again; } --2.24.1
Daniel Borkmann
maintainerRe: [PATCH 1/3 v4 bpf-next] bpf: save correct stopping point in file seq iteration.
Quoted 63 lines · Andrii Nakryiko
Quoted 61 lines · Jonathan Lemon
From: Jonathan Lemon <[email protected]>
On some systems, some variant of the following splat is repeatedly seen. The common factor in all traces seems to be the entry point to
task_file_seq_next(). With the patch, all warnings go away.rcu: INFO: rcu_sched self-detected stall on CPU rcu: \x0926-....: (20992 ticks this GP) idle=d7e/1/0x4000000000000002 softirq=81556231/81556231 fqs=4876 \x09(t=21033 jiffies g=159148529 q=223125) NMI backtrace for cpu 26 CPU: 26 PID: 2015853 Comm: bpftool Kdump: loaded Not tainted 5.6.13-0_fbk4_3876_gd8d1f9bf80bb #1 Hardware name: Quanta Twin Lakes MP/Twin Lakes Passive MP, BIOS F09_3A12 10/08/2018 Call Trace: <IRQ> dump_stack+0x50/0x70 nmi_cpu_backtrace.cold.6+0x13/0x50 ? lapic_can_unplug_cpu.cold.30+0x40/0x40 nmi_trigger_cpumask_backtrace+0xba/0xca rcu_dump_cpu_stacks+0x99/0xc7 rcu_sched_clock_irq.cold.90+0x1b4/0x3aa ? tick_sched_do_timer+0x60/0x60 update_process_times+0x24/0x50 tick_sched_timer+0x37/0x70 __hrtimer_run_queues+0xfe/0x270 hrtimer_interrupt+0xf4/0x210 smp_apic_timer_interrupt+0x5e/0x120 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0010:get_pid_task+0x38/0x80 Code: 89 f6 48 8d 44 f7 08 48 8b 00 48 85 c0 74 2b 48 83 c6 55 48 c1 e6 04 48 29 f0 74 19 48 8d 78 20 ba 01 00 00 00 f0 0f c1 50 20 <85> d2 74 27 78 11 83 c2 01 78 0c 48 83 c4 08 c3 31 c0 48 83 c4 08 RSP: 0018:ffffc9000d293dc8 EFLAGS: 00000202 ORIG_RAX: ffffffffffffff13 RAX: ffff888637c05600 RBX: ffffc9000d293e0c RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000550 RDI: ffff888637c05620 RBP: ffffffff8284eb80 R08: ffff88831341d300 R09: ffff88822ffd8248 R10: ffff88822ffd82d0 R11: 00000000003a93c0 R12: 0000000000000001 R13: 00000000ffffffff R14: ffff88831341d300 R15: 0000000000000000 ? find_ge_pid+0x1b/0x20 task_seq_get_next+0x52/0xc0 task_file_seq_get_next+0x159/0x220 task_file_seq_next+0x4f/0xa0 bpf_seq_read+0x159/0x390 vfs_read+0x8a/0x140 ksys_read+0x59/0xd0 do_syscall_64+0x42/0x110 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f95ae73e76e Code: Bad RIP value. RSP: 002b:00007ffc02c1dbf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: ffffffffffffffda RBX: 000000000170faa0 RCX: 00007f95ae73e76e RDX: 0000000000001000 RSI: 00007ffc02c1dc30 RDI: 0000000000000007 RBP: 00007ffc02c1ec70 R08: 0000000000000005 R09: 0000000000000006 R10: fffffffffffff20b R11: 0000000000000246 R12: 00000000019112a0 R13: 0000000000000000 R14: 0000000000000007 R15: 00000000004283c0If unable to obtain the file structure for the current task, proceed to the next task number after the one returned from
task_seq_get_next(), instead of the next task number from the original iterator.
Quoted 4 lines
Quoted 4 lines
Also, save the stopping task number from
task_seq_get_next()on failure in case of restarts.Fixes a650da2ee52a ("bpf: Add task and task/file iterator targets")
Commit sha is non-existent, I fixed it up. Took first 2 into bpf given first in particular is a fix. Please submit 3/3 individually once we synced trees back.
Quoted 6 lines
Quoted 2 lines
Signed-off-by Jonathan Lemon <[email protected]>---
LGTM, thanks!
Acked-by Andrii Nakryiko <[email protected]>
PATCH v4 2/3 bpf: Use thread_group_leader()
In reply to Jonathan LemonFrom: Jonathan Lemon <[email protected]>
Instead of directly comparing task->tgid and task->pid, use the thread_group_leader() helper. This helps with readability, and there should be no functional change.
--- kernel/bpf/task_iter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/bpf/task_iter.c +1 -1
@@ -37,7 +37,7 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns,if (!task) { ++*tid; goto retry; - }else if (skip_if_dup_files && task->tgid != task->pid && + }else if (skip_if_dup_files && !thread_group_leader (task) && task->files == task->group_leader->files) {put_task_struct (task); task =NULL ;
Signature · 1 line
2.24.1
Re: [PATCH 2/3 v4 bpf-next] bpf: Use thread_group_leader()
Quoted 9 lines · Jonathan Lemon
From: Jonathan Lemon <[email protected]>
Instead of directly comparing
task->tgidandtask->pid, use thethread_group_leader()helper. This helps with readability, and there should be no functional change.Signed-off-by Jonathan Lemon <[email protected]>---
Quoted 19 lines
kernel/bpf/task_iter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)kernel/bpf/task_iter.c +1
-2@@ -37,7 +37,7 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns,if (!task) { ++*tid; goto retry; - }else if (skip_if_dup_files && task->tgid != task->pid && + }else if (skip_if_dup_files && !thread_group_leader (task) && task->files == task->group_leader->files) {put_task_struct (task); task =NULL ; --2.24.1
PATCH v4 3/3 bpf: optimize task iteration
In reply to Jonathan LemonFrom: Jonathan Lemon <[email protected]>
Only obtain the task reference count at the end of the RCU section instead of repeatedly obtaining/releasing it when iterating though a thread group.
Jump to the correct branch when it is known that the task is NULL.
--- kernel/bpf/task_iter.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
kernel/bpf/task_iter.c +3 -2
@@ -33,7 +33,7 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns, pid =find_ge_pid (*tid, ns);if (pid) { *tid =pid_nr_ns (pid, ns); - task =get_pid_task (pid,PIDTYPE_PID ); + task =pid_task (pid,PIDTYPE_PID );if (!task) { ++*tid; goto retry;
@@ -44,6 +44,7 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns, ++*tid; goto retry; } +get_task_struct (task); }rcu_read_unlock ();
@@ -148,12 +149,12 @@ task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info)* it held a reference to the task/files_struct/file. * Otherwise, it does not hold any reference. */ -again:if (info->task) { curr_task = info->task; curr_files = info->files; curr_fd = info->fd; }else { +again: curr_task =task_seq_get_next (ns, &curr_tid, true);if (!curr_task) { info->task =NULL ;
Signature · 1 line
2.24.1
Re: [PATCH 3/3 v4 bpf-next] bpf: optimize task iteration
Quoted 11 lines · Jonathan Lemon
From: Jonathan Lemon <[email protected]>
Only obtain the task reference count at the end of the RCU section instead of repeatedly obtaining/releasing it when iterating though a thread group.
Jump to the correct branch when it is known that the task is NULL.
Signed-off-by Jonathan Lemon <[email protected]>---
Quoted 41 lines
kernel/bpf/task_iter.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)kernel/bpf/task_iter.c +3
-3@@ -33,7 +33,7 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns, pid =find_ge_pid (*tid, ns);if (pid) { *tid =pid_nr_ns (pid, ns); - task =get_pid_task (pid,PIDTYPE_PID ); + task =pid_task (pid,PIDTYPE_PID );if (!task) { ++*tid; goto retry;@@ -44,6 +44,7 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns, ++*tid; goto retry; } +get_task_struct (task); }rcu_read_unlock ();@@ -148,12 +149,12 @@ task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info)* it held a reference to the task/files_struct/file. * Otherwise, it does not hold any reference. */ -again:if (info->task) { curr_task = info->task; curr_files = info->files; curr_fd = info->fd; }else { +again: curr_task =task_seq_get_next (ns, &curr_tid, true);if (!curr_task) { info->task =NULL ; --2.24.1