From 79c537998d143b127c8c662a403c3356cb885f1c Mon Sep 17 00:00:00 2001 From: Dmitry Adamushko Date: Sun, 29 Jun 2008 00:16:56 +0200 Subject: sched: fix cpu hotplug the CPU hotplug problems (crashes under high-volume unplug+replug tests) seem to be related to migrate_dead_tasks(). Firstly I added traces to see all tasks being migrated with migrate_live_tasks() and migrate_dead_tasks(). On my setup the problem pops up (the one with "se == NULL" in the loop of pick_next_task_fair()) shortly after the traces indicate that some has been migrated with migrate_dead_tasks()). btw., I can reproduce it much faster now with just a plain cpu down/up loop. [disclaimer] Well, unless I'm really missing something important in this late hour [/desclaimer] pick_next_task() is not something appropriate for migrate_dead_tasks() :-) the following change seems to eliminate the problem on my setup (although, I kept it running only for a few minutes to get a few messages indicating migrate_dead_tasks() does move tasks and the system is still ok) Signed-off-by: Ingo Molnar --- kernel/sched.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 3aaa5c8cb42..a66e85639de 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5887,6 +5887,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu) next = pick_next_task(rq, rq->curr); if (!next) break; + next->sched_class->put_prev_task(rq, next); migrate_dead(dead_cpu, next); } -- cgit v1.2.3 From 619b0488038224391e64fa03854651ca0f5efe56 Mon Sep 17 00:00:00 2001 From: Raistlin Date: Thu, 26 Jun 2008 18:54:09 +0200 Subject: sched: fix divide error when trying to configure rt_period to zero Here it is another little Oops we found while configuring invalid values via cgroups: echo 0 > /dev/cgroups/0/cpu.rt_period_us or echo 4294967296 > /dev/cgroups/0/cpu.rt_period_us [ 205.509825] divide error: 0000 [#1] [ 205.510151] Modules linked in: [ 205.510151] [ 205.510151] Pid: 2339, comm: bash Not tainted (2.6.26-rc8 #33) [ 205.510151] EIP: 0060:[] EFLAGS: 00000293 CPU: 0 [ 205.510151] EIP is at div64_u64+0x5f/0x70 [ 205.510151] EAX: 0000389f EBX: 00000000 ECX: 00000000 EDX: 00000000 [ 205.510151] ESI: d9800000 EDI: 00000000 EBP: c6cede60 ESP: c6cede50 [ 205.510151] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 0068 [ 205.510151] Process bash (pid: 2339, ti=c6cec000 task=c79be370 task.ti=c6cec000) [ 205.510151] Stack: d9800000 0000389f c05971a0 d9800000 c6cedeb4 c0214dbd 00000000 00000000 [ 205.510151] c6cede88 c0242bd8 c05377c0 c7a41b40 00000000 00000000 00000000 c05971a0 [ 205.510151] c780ed20 c7508494 c7a41b40 00000000 00000002 c6cedebc c05971a0 ffffffea [ 205.510151] Call Trace: [ 205.510151] [] ? __rt_schedulable+0x1cd/0x240 [ 205.510151] [] ? cgroup_file_open+0x18/0xe0 [ 205.510151] [] ? tg_set_bandwidth+0xa4/0xf0 [ 205.510151] [] ? sched_group_set_rt_period+0x36/0x50 [ 205.510151] [] ? cpu_rt_period_write_uint+0xe/0x10 [ 205.510151] [] ? cgroup_file_write+0x125/0x160 [ 205.510151] [] ? hrtimer_interrupt+0x155/0x190 [ 205.510151] [] ? security_file_permission+0xf/0x20 [ 205.510151] [] ? rw_verify_area+0x48/0xc0 [ 205.510151] [] ? dupfd+0x104/0x130 [ 205.510151] [] ? vfs_write+0x9c/0x160 [ 205.510151] [] ? cgroup_file_write+0x0/0x160 [ 205.510151] [] ? sys_write+0x3d/0x70 [ 205.510151] [] ? sysenter_past_esp+0x6a/0x91 [ 205.510151] ======================= [ 205.510151] Code: 0f 45 de 31 f6 0f ad d0 d3 ea f6 c1 20 0f 45 c2 0f 45 d6 89 45 f0 89 55 f4 8b 55 f4 31 c9 8b 45 f0 39 d3 89 c6 77 08 89 d0 31 d2 f3 89 c1 83 c4 08 89 f0 f7 f3 89 ca 5b 5e 5d c3 55 89 e5 56 [ 205.510151] EIP: [] div64_u64+0x5f/0x70 SS:ESP 0068:c6cede50 The attached patch solves the issue for me. I'm checking as soon as possible for the period not being zero since, if it is, going ahead is useless. This way we also save a mutex_lock() and a read_lock() wrt doing it inside tg_set_bandwidth() or __rt_schedulable(). Signed-off-by: Dario Faggioli Signed-off-by: Michael Trimarchi Signed-off-by: Ingo Molnar --- kernel/sched.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index a66e85639de..94ead43eda6 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -8502,6 +8502,9 @@ int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) rt_period = (u64)rt_period_us * NSEC_PER_USEC; rt_runtime = tg->rt_bandwidth.rt_runtime; + if (rt_period == 0) + return -EINVAL; + return tg_set_bandwidth(tg, rt_period, rt_runtime); } -- cgit v1.2.3