sched/fair: fix find_idlest_cpu return -1
Subsystems (2)
PATCH v2 1/1 sched/fair: fix find_idlest_cpu return -1
From: zhang jun <[email protected]>
in function select_task_rq_fair, when find_idlest_cpu return -1 and sd->child == NULL select_task_rq_fair return -1, system panic.
[ 0.738326] BUG: unable to handle kernel paging request at ffff8800997ea928 [ 0.746138] IP: [<ffffffff810b15d3>] wake_up_new_task+0x43/0x1b0 [ 0.752886] PGD 25df067 PUD 0 [ 0.756321] Oops: 0000 1 PREEMPT SMP [ 0.760743] Modules linked in: [ 0.764179] CPU: 0 PID: 6 Comm: kworker/u8:0 Not tainted 3.14.19-quilt-b27ac761 #2 [ 0.772651] Hardware name: Intel Corporation CHERRYVIEW B1 PLATFORM/Cherry Trail CR, BIOS CHTTRVP1.X64.0003.R08.1411110453 11/11/2014 [ 0.786084] Workqueue: khelper __call_usermodehelper [ 0.791649] task: ffff88007955a150 ti: ffff88007955c000 task.ti: ffff88007955c000 [ 0.800021] RIP: 0010:[<ffffffff810b15d3>] [<ffffffff810b15d3>] wake_up_new_task+0x43/0x1b0 [ 0.809478] RSP: 0000:ffff88007955dd58 EFLAGS: 00010092 [ 0.815422] RAX: 00000000ffffffff RBX: 0000000000000001 RCX: 0000000000000020 [ 0.823404] RDX: 00000000ffffffff RSI: 0000000000000020 RDI: 0000000000000020 [ 0.831386] RBP: ffff88007955dd80 R08: ffff880079604b58 R09: 00000000ffffffff [ 0.839368] R10: 0000000000000004 R11: eae0000000000000 R12: ffff8800797ea650 [ 0.847350] R13: 0000000000004000 R14: ffff8800797ead52 R15: 0000000000000206 [ 0.855335] FS: 0000000000000000(0000) GS:ffff88007aa00000(0000) knlGS:0000000000000000 [ 0.864387] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 0.870817] CR2: ffff8800997ea928 CR3: 000000000220b000 CR4: 00000000001007f0 [ 0.878796] Stack: [ 0.881046] 0000000000000001 ffff8800797ea650 0000000000004000 0000000000000000 [ 0.889363] 000000000000003c ffff88007955ddf0 ffffffff8107ddfd ffffffff810b6a95 [ 0.897680] 0000000000000000 ffff8800796beb00 ffff880000000000 ffffffff81000000 [ 0.905998] Call Trace: [ 0.908752] [<ffffffff8107ddfd>] do_fork+0x12d/0x3b0 [ 0.914416] [<ffffffff810b6a95>] ? set_next_entity+0x95/0xb0 [ 0.920856] [<ffffffff8107e0a6>] kernel_thread+0x26/0x30 [ 0.926903] [<ffffffff8109703e>] __call_usermodehelper+0x2e/0x90 [ 0.933730] [<ffffffff8109ad31>] process_one_work+0x171/0x490 [ 0.940264] [<ffffffff8109ba4b>] worker_thread+0x11b/0x3a0 [ 0.946508] [<ffffffff8109b930>] ? manage_workers.isra.27+0x2b0/0x2b0 [ 0.953821] [<ffffffff810a1802>] kthread+0xd2/0xf0 [ 0.959289] [<ffffffff810a1730>] ? kthread_create_on_node+0x170/0x170 [ 0.966602] [<ffffffff81af81ac>] ret_from_fork+0x7c/0xb0 [ 0.972652] [<ffffffff810a1730>] ? kthread_create_on_node+0x170/0x170 [ 0.979956] Code: 49 89 fc 4c 89 f7 53 e8 bc 5c a4 00 49 8b 54 24 08 31 c9 49 89 c7 49 8b 44 24 60 4c 89 e7 8b 72 18 ba 08 00 00 00 ff 50 40 89 c2 <49> 0f a3 94 24 e0 02 00 00 19 c9 85 c9 0f 84 34 01 00 00 48 8b [ 1.001809] RIP [<ffffffff810b15d3>] wake_up_new_task+0x43/0x1b0 [ 1.008641] RSP <ffff88007955dd58> [ 1.012544] CR2: ffff8800997ea928 [ 1.016279] --[ end trace 9737aaa337a5ca10 ]--
Signed-off-by zhang jun <[email protected]>
Signed-off-by Chuansheng Liu <[email protected]>
Signed-off-by Changcheng Liu <[email protected]>
Signed-off-by zhang jun <[email protected]>
--- kernel/sched/fair.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
kernel/sched/fair.c +2 -2
@@ -4151,7 +4151,7 @@ static int find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) { unsigned long load, min_load = ULONG_MAX; -int idlest =-1 ; +int idlest = this_cpu;int i;/* Traverse only the allowed CPUs */
@@ -4284,7 +4284,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f } new_cpu =find_idlest_cpu (group, p, cpu); -if (new_cpu ==-1 || new_cpu == cpu) { +if (new_cpu == cpu) {/* Now try balancing at a lower domain level of cpu */ sd = sd->child;continue ;
Signature · 1 line
1.7.9.5
Vincent Guittot
maintainerQuoted 4 lines · On 4 December 2014 at 12:43, <[email protected]> wrote:
From: zhang jun <[email protected]>
in function
select_task_rq_fair, whenfind_idlest_cpureturn -1 andsd->child== NULLselect_task_rq_fairreturn -1, system panic.
you forgot to add on which kernel version this patch applies.
We don't have such issue on 3.18-rc7 as find_idlest_cpu don't return -1. We only need a cleanup of the test against -1 for 3.18-rc
Vincent
Quoted 75 lines
[ 0.738326] BUG: unable to handle kernel paging request at ffff8800997ea928 [ 0.746138] IP: [<ffffffff810b15d3>] wake_up_new_task+0x43/0x1b0 [ 0.752886] PGD 25df067 PUD 0 [ 0.756321] Oops: 0000 1 PREEMPT SMP [ 0.760743] Modules linked in: [ 0.764179] CPU: 0 PID: 6 Comm: kworker/u8:0 Not tainted 3.14.19-quilt-b27ac761 #2 [ 0.772651] Hardware name: Intel Corporation CHERRYVIEW B1 PLATFORM/Cherry Trail CR, BIOS CHTTRVP1.X64.0003.R08.1411110453 11/11/2014 [ 0.786084] Workqueue: khelper __call_usermodehelper [ 0.791649] task: ffff88007955a150 ti: ffff88007955c000 task.ti: ffff88007955c000 [ 0.800021] RIP: 0010:[<ffffffff810b15d3>] [<ffffffff810b15d3>] wake_up_new_task+0x43/0x1b0 [ 0.809478] RSP: 0000:ffff88007955dd58 EFLAGS: 00010092 [ 0.815422] RAX: 00000000ffffffff RBX: 0000000000000001 RCX: 0000000000000020 [ 0.823404] RDX: 00000000ffffffff RSI: 0000000000000020 RDI: 0000000000000020 [ 0.831386] RBP: ffff88007955dd80 R08: ffff880079604b58 R09: 00000000ffffffff [ 0.839368] R10: 0000000000000004 R11: eae0000000000000 R12: ffff8800797ea650 [ 0.847350] R13: 0000000000004000 R14: ffff8800797ead52 R15: 0000000000000206 [ 0.855335] FS: 0000000000000000(0000) GS:ffff88007aa00000(0000) knlGS:0000000000000000 [ 0.864387] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 0.870817] CR2: ffff8800997ea928 CR3: 000000000220b000 CR4: 00000000001007f0 [ 0.878796] Stack: [ 0.881046] 0000000000000001 ffff8800797ea650 0000000000004000 0000000000000000 [ 0.889363] 000000000000003c ffff88007955ddf0 ffffffff8107ddfd ffffffff810b6a95 [ 0.897680] 0000000000000000 ffff8800796beb00 ffff880000000000 ffffffff81000000 [ 0.905998] Call Trace: [ 0.908752] [<ffffffff8107ddfd>] do_fork+0x12d/0x3b0 [ 0.914416] [<ffffffff810b6a95>] ? set_next_entity+0x95/0xb0 [ 0.920856] [<ffffffff8107e0a6>] kernel_thread+0x26/0x30 [ 0.926903] [<ffffffff8109703e>] __call_usermodehelper+0x2e/0x90 [ 0.933730] [<ffffffff8109ad31>] process_one_work+0x171/0x490 [ 0.940264] [<ffffffff8109ba4b>] worker_thread+0x11b/0x3a0 [ 0.946508] [<ffffffff8109b930>] ? manage_workers.isra.27+0x2b0/0x2b0 [ 0.953821] [<ffffffff810a1802>] kthread+0xd2/0xf0 [ 0.959289] [<ffffffff810a1730>] ? kthread_create_on_node+0x170/0x170 [ 0.966602] [<ffffffff81af81ac>] ret_from_fork+0x7c/0xb0 [ 0.972652] [<ffffffff810a1730>] ? kthread_create_on_node+0x170/0x170 [ 0.979956] Code: 49 89 fc 4c 89 f7 53 e8 bc 5c a4 00 49 8b 54 24 08 31 c9 49 89 c7 49 8b 44 24 60 4c 89 e7 8b 72 18 ba 08 00 00 00 ff 50 40 89 c2 <49> 0f a3 94 24 e0 02 00 00 19 c9 85 c9 0f 84 34 01 00 00 48 8b [ 1.001809] RIP [<ffffffff810b15d3>] wake_up_new_task+0x43/0x1b0 [ 1.008641] RSP <ffff88007955dd58> [ 1.012544] CR2: ffff8800997ea928 [ 1.016279] --[ end trace 9737aaa337a5ca10 ]--Signed-off-by zhang jun <[email protected]>Signed-off-by Chuansheng Liu <[email protected]>Signed-off-by Changcheng Liu <[email protected]>Signed-off-by zhang jun <[email protected]>--- kernel/sched/fair.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)kernel/sched/fair.c +2
-3@@ -4151,7 +4151,7 @@ static int find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) { unsigned long load, min_load = ULONG_MAX; -int idlest =-1 ; +int idlest = this_cpu;int i;/* Traverse only the allowed CPUs */ @@ -4284,7 +4284,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f } new_cpu =find_idlest_cpu (group, p, cpu); -if (new_cpu ==-1 || new_cpu == cpu) { +if (new_cpu == cpu) {/* Now try balancing at a lower domain level of cpu */ sd = sd->child;continue ; --1.7.9.5
Quoted 14 lines
-----Original Message-----
From: Vincent Guittot [mailto:[email protected]]
Sent: Thursday, December 04, 2014 8:15 PM
To: Zhang, Jun
Cc: [email protected]; Peter Zijlstra; [email protected]; Hillf Danton; linux-kernel; [email protected]; Liu, Chuansheng; Liu, Changcheng
Subject: Re: [PATCH v2] sched/fair: fixfind_idlest_cpureturn -1Quoted 2 lines · On 4 December 2014 at 12:43, <[email protected]> wrote:
From: zhang jun <[email protected]>
Quoted 9 lines
Quoted 1 line
in function
select_task_rq_fair, whenfind_idlest_cpureturn -1 andsd->child== NULL
Quoted 1 line
select_task_rq_fairreturn -1, system panic.you forgot to add on which kernel version this patch applies.
We don't have such issue on 3.18-rc7 as
find_idlest_cpudon't return -1. We only need a cleanup of the test against -1 for 3.18-rc
Agreed, so Jun can make two patches:
The first one patch is in find_idlest_cpu() to not return -1 and based on stable-branch such as 3.14.x; The second patch is one cleanup for new_cpu == -1 judgment against the 3.18-rc, since it is no possibility now;
Best Regards
Chuansheng