summaryrefslogtreecommitdiffstats
path: root/arch/s390
diff options
context:
space:
mode:
authorHeiko Carstens <heiko.carstens@de.ibm.com>2008-04-30 13:38:41 +0200
committerMartin Schwidefsky <schwidefsky@de.ibm.com>2008-04-30 13:38:45 +0200
commitfd781fa25c9e9c6fd1599df060b05e7c4ad724e5 (patch)
tree9a35f2ab5f0bb8471345fb827f33b3042eb6c91f /arch/s390
parentd00aa4e7d0129983fc4389c85e15a066eb4e69a9 (diff)
downloadop-kernel-dev-fd781fa25c9e9c6fd1599df060b05e7c4ad724e5.zip
op-kernel-dev-fd781fa25c9e9c6fd1599df060b05e7c4ad724e5.tar.gz
[S390] cpu topology: Fix possible deadlock.
When we get a notification that cpu topology changed, we schedule a work struct which just calls arch_reinit_sched_domains. This function in turn calls get_online_cpus() which results int the lockdep warning below. After all it turnded out that it's not legal to call get_online_cpus() from the context of a multi-threaded work queue. It could deadlock this way: process 0 (events/cpu-x): -> run_workqueue -> removes my work_struct from the work queue -> calls work_struct->fn -> get_online_cpus() -> locks on cpu_hotplug.lock since process 1 below is doing cpu hotplug process 1: -> cpu_down (for cpu-x) -> cpu_hotplug_begin (holds cpu_hotplug.lock now) -> cpu-x dead -> notifier_call_chain with CPU_DEAD -> cleanup_workqueue_thread -> flush_cpu_workqueue (succeeds) -> kthread_stop for events/cpu-x -> now kthread_stop waits for my work_struct to complete from within process 0. -> dead. A single threaded workqueue wouldn't have such problems, however there is no such common queue available and it's not worth to create one for the very rare calls to arch_reinit_sched_domains. So we just create a kernel thread from our work struct which calls arch_reinit_sched_domains and are done with it. Thanks to Oleg Nesterov and Peter Zijlstra for helping me figuring out that this isn't a false positive lockdep warning: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.25-03562-g3dc5063-dirty #12 ------------------------------------------------------- events/3/14 is trying to acquire lock: (&cpu_hotplug.lock){--..}, at: [<0000000000076094>] get_online_cpus+0x50/0x78 but task is already holding lock: (topology_work){--..}, at: [<0000000000059cde>] run_workqueue+0x106/0x278 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (topology_work){--..}: [<000000000006fc74>] __lock_acquire+0x1010/0x111c [<000000000006fe40>] lock_acquire+0xc0/0xf8 [<0000000000059d48>] run_workqueue+0x170/0x278 [<0000000000059edc>] worker_thread+0x8c/0xf0 [<000000000005f5bc>] kthread+0x68/0xa0 [<000000000001a33e>] kernel_thread_starter+0x6/0xc [<000000000001a338>] kernel_thread_starter+0x0/0xc -> #1 (events){--..}: [<000000000006fc74>] __lock_acquire+0x1010/0x111c [<000000000006fe40>] lock_acquire+0xc0/0xf8 [<000000000005a23c>] cleanup_workqueue_thread+0x60/0xa8 [<00000000003b2ab8>] workqueue_cpu_callback+0xbc/0x170 [<00000000003bba80>] notifier_call_chain+0x5c/0xa4 [<00000000000655a2>] __raw_notifier_call_chain+0x26/0x38 [<00000000000655e2>] raw_notifier_call_chain+0x2e/0x40 [<0000000000075e00>] cpu_down+0x228/0x31c [<00000000003b1dd8>] store_online+0x64/0xb8 [<00000000001e7128>] sysdev_store+0x48/0x58 [<0000000000121cd2>] sysfs_write_file+0x126/0x1c0 [<00000000000c1944>] vfs_write+0xb0/0x15c [<00000000000c20e6>] sys_write+0x56/0x88 [<0000000000027a68>] sys32_write+0x34/0x4c [<0000000000023f70>] sysc_noemu+0x10/0x16 [<0000000077f3f186>] 0x77f3f186 -> #0 (&cpu_hotplug.lock){--..}: [<000000000006fa84>] __lock_acquire+0xe20/0x111c [<000000000006fe40>] lock_acquire+0xc0/0xf8 [<00000000003b701c>] mutex_lock_nested+0xd0/0x364 [<0000000000076094>] get_online_cpus+0x50/0x78 [<000000000003a03e>] arch_reinit_sched_domains+0x26/0x58 [<000000000002700e>] topology_work_fn+0x26/0x34 [<0000000000059d4e>] run_workqueue+0x176/0x278 [<0000000000059edc>] worker_thread+0x8c/0xf0 [<000000000005f5bc>] kthread+0x68/0xa0 [<000000000001a33e>] kernel_thread_starter+0x6/0xc [<000000000001a338>] kernel_thread_starter+0x0/0xc other info that might help us debug this: 2 locks held by events/3/14: #0: (events){--..}, at: [<0000000000059cde>] run_workqueue+0x106/0x278 #1: (topology_work){--..}, at: [<0000000000059cde>] run_workqueue+0x106/0x278 stack backtrace: CPU: 3 Not tainted 2.6.25-03562-g3dc5063-dirty #12 Process events/3 (pid: 14, task: 000000002fb04038, ksp: 000000002fb0bd70) 0400000000000000 000000002fb0ba40 0000000000000002 0000000000000000 000000002fb0bae0 000000002fb0ba58 000000002fb0ba58 0000000000016488 0000000000000000 000000002fb0bd70 0000000000000000 0000000000000000 000000002fb0ba40 000000000000000c 000000002fb0ba40 000000002fb0bab0 00000000003c99e0 0000000000016488 000000002fb0ba40 000000002fb0ba90 Call Trace: ([<00000000000163fc>] show_trace+0x138/0x158) [<00000000000164e2>] show_stack+0xc6/0xf8 [<0000000000016624>] dump_stack+0xb0/0xc0 [<000000000006cd36>] print_circular_bug_tail+0xa2/0xb4 [<000000000006fa84>] __lock_acquire+0xe20/0x111c [<000000000006fe40>] lock_acquire+0xc0/0xf8 [<00000000003b701c>] mutex_lock_nested+0xd0/0x364 [<0000000000076094>] get_online_cpus+0x50/0x78 [<000000000003a03e>] arch_reinit_sched_domains+0x26/0x58 [<000000000002700e>] topology_work_fn+0x26/0x34 [<0000000000059d4e>] run_workqueue+0x176/0x278 [<0000000000059edc>] worker_thread+0x8c/0xf0 [<000000000005f5bc>] kthread+0x68/0xa0 [<000000000001a33e>] kernel_thread_starter+0x6/0xc [<000000000001a338>] kernel_thread_starter+0x0/0xc INFO: lockdep is turned off. Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Diffstat (limited to 'arch/s390')
-rw-r--r--arch/s390/kernel/topology.c14
1 files changed, 13 insertions, 1 deletions
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 0becefc..661a072 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -9,6 +9,7 @@
#include <linux/device.h>
#include <linux/bootmem.h>
#include <linux/sched.h>
+#include <linux/kthread.h>
#include <linux/workqueue.h>
#include <linux/cpu.h>
#include <linux/smp.h>
@@ -229,9 +230,20 @@ void arch_update_cpu_topology(void)
}
}
-static void topology_work_fn(struct work_struct *work)
+static int topology_kthread(void *data)
{
arch_reinit_sched_domains();
+ return 0;
+}
+
+static void topology_work_fn(struct work_struct *work)
+{
+ /* We can't call arch_reinit_sched_domains() from a multi-threaded
+ * workqueue context since it may deadlock in case of cpu hotplug.
+ * So we have to create a kernel thread in order to call
+ * arch_reinit_sched_domains().
+ */
+ kthread_run(topology_kthread, NULL, "topology_update");
}
void topology_schedule_update(void)
OpenPOWER on IntegriCloud