From d467d80dc399ba77875d647f2f37b7d1a70d94c2 Mon Sep 17 00:00:00 2001 From: Tian Tao Date: Wed, 16 Dec 2020 10:47:15 +0800 Subject: bpf: Remove unused including Remove including that don't need it. Signed-off-by: Tian Tao Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/1608086835-54523-1-git-send-email-tiantao6@hisilicon.com --- kernel/bpf/syscall.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 287be337d5f6..bb2700ec5bf3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From e7e518053c267bb6be3799520d9f4a34c7264a2e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 21 Dec 2020 11:25:06 -0800 Subject: bpf: Add schedule point in htab_init_buckets() We noticed that with a LOCKDEP enabled kernel, allocating a hash table with 65536 buckets would use more than 60ms. htab_init_buckets() runs from process context, it is safe to schedule to avoid latency spikes. Fixes: c50eb518e262 ("bpf: Use separate lockdep class for each hashtab") Reported-by: John Sperbeck Signed-off-by: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20201221192506.707584-1-eric.dumazet@gmail.com --- kernel/bpf/hashtab.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 7e848200cd26..c1ac7f964bc9 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -152,6 +152,7 @@ static void htab_init_buckets(struct bpf_htab *htab) lockdep_set_class(&htab->buckets[i].lock, &htab->lockdep_key); } + cond_resched(); } } -- cgit v1.2.3 From 69ca310f34168eae0ada434796bfc22fb4a0fa26 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Fri, 18 Dec 2020 10:50:30 -0800 Subject: bpf: Save correct stopping point in file seq iteration 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: 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 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: 00000000004283c0 If 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. Fixes: eaaacd23910f ("bpf: Add task and task/file iterator targets") Signed-off-by: Jonathan Lemon Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20201218185032.2464558-2-jonathan.lemon@gmail.com --- kernel/bpf/task_iter.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 0458a40edf10..8033ab19138a 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -158,13 +158,14 @@ again: 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; } -- cgit v1.2.3 From a61daaf351da7c8493f2586437617d60c24350b0 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Fri, 18 Dec 2020 10:50:31 -0800 Subject: bpf: Use thread_group_leader() 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. Signed-off-by: Jonathan Lemon Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20201218185032.2464558-3-jonathan.lemon@gmail.com --- kernel/bpf/task_iter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 8033ab19138a..dc4007f1843b 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -37,7 +37,7 @@ retry: 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; -- cgit v1.2.3