linux/lib/percpu_counter.c

230 lines
5.5 KiB
C
Raw Normal View History

/*
* Fast batching percpu counters.
*/
#include <linux/percpu_counter.h>
#include <linux/notifier.h>
#include <linux/mutex.h>
#include <linux/init.h>
#include <linux/cpu.h>
#include <linux/module.h>
percpu_counter: add debugobj support All percpu counters are linked to a global list on initialization and removed from it on destruction. The list is walked during CPU up/down. If a percpu counter is freed without being properly destroyed, the system will oops only on the next CPU up/down making it pretty nasty to track down. This patch adds debugobj support for percpu counters so that such problems can be found easily. As percpu counters don't make sense on stack and can't be statically initialized, debugobj support is pretty simple. It's initialized and activated on counter initialization, and deactivatd and destroyed on counter destruction. With this patch applied, the bug fixed by commit 602586a83b719df0fbd94196a1359ed35aeb2df3 (shmem: put_super must percpu_counter_destroy) triggers the following warning on tmpfs unmount and the system won't oops on the next cpu up/down operation. ------------[ cut here ]------------ WARNING: at lib/debugobjects.c:259 debug_print_object+0x5c/0x70() Hardware name: Bochs ODEBUG: free active (active state 0) object type: percpu_counter Modules linked in: Pid: 3999, comm: umount Not tainted 2.6.36-rc2-work+ #5 Call Trace: [<ffffffff81083f7f>] warn_slowpath_common+0x7f/0xc0 [<ffffffff81084076>] warn_slowpath_fmt+0x46/0x50 [<ffffffff813b45cc>] debug_print_object+0x5c/0x70 [<ffffffff813b50e5>] debug_check_no_obj_freed+0x125/0x210 [<ffffffff811577d3>] kfree+0xb3/0x2f0 [<ffffffff81132edd>] shmem_put_super+0x1d/0x30 [<ffffffff81162e96>] generic_shutdown_super+0x56/0xe0 [<ffffffff81162f86>] kill_anon_super+0x16/0x60 [<ffffffff81162ff7>] kill_litter_super+0x27/0x30 [<ffffffff81163295>] deactivate_locked_super+0x45/0x60 [<ffffffff81163cfa>] deactivate_super+0x4a/0x70 [<ffffffff8117d446>] mntput_no_expire+0x86/0xe0 [<ffffffff8117df7f>] sys_umount+0x6f/0x360 [<ffffffff8103f01b>] system_call_fastpath+0x16/0x1b ---[ end trace cce2a341ba3611a7 ]--- Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Thomas Gleixner <tglxlinutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 21:23:05 +00:00
#include <linux/debugobjects.h>
#ifdef CONFIG_HOTPLUG_CPU
static LIST_HEAD(percpu_counters);
static DEFINE_SPINLOCK(percpu_counters_lock);
#endif
percpu_counter: add debugobj support All percpu counters are linked to a global list on initialization and removed from it on destruction. The list is walked during CPU up/down. If a percpu counter is freed without being properly destroyed, the system will oops only on the next CPU up/down making it pretty nasty to track down. This patch adds debugobj support for percpu counters so that such problems can be found easily. As percpu counters don't make sense on stack and can't be statically initialized, debugobj support is pretty simple. It's initialized and activated on counter initialization, and deactivatd and destroyed on counter destruction. With this patch applied, the bug fixed by commit 602586a83b719df0fbd94196a1359ed35aeb2df3 (shmem: put_super must percpu_counter_destroy) triggers the following warning on tmpfs unmount and the system won't oops on the next cpu up/down operation. ------------[ cut here ]------------ WARNING: at lib/debugobjects.c:259 debug_print_object+0x5c/0x70() Hardware name: Bochs ODEBUG: free active (active state 0) object type: percpu_counter Modules linked in: Pid: 3999, comm: umount Not tainted 2.6.36-rc2-work+ #5 Call Trace: [<ffffffff81083f7f>] warn_slowpath_common+0x7f/0xc0 [<ffffffff81084076>] warn_slowpath_fmt+0x46/0x50 [<ffffffff813b45cc>] debug_print_object+0x5c/0x70 [<ffffffff813b50e5>] debug_check_no_obj_freed+0x125/0x210 [<ffffffff811577d3>] kfree+0xb3/0x2f0 [<ffffffff81132edd>] shmem_put_super+0x1d/0x30 [<ffffffff81162e96>] generic_shutdown_super+0x56/0xe0 [<ffffffff81162f86>] kill_anon_super+0x16/0x60 [<ffffffff81162ff7>] kill_litter_super+0x27/0x30 [<ffffffff81163295>] deactivate_locked_super+0x45/0x60 [<ffffffff81163cfa>] deactivate_super+0x4a/0x70 [<ffffffff8117d446>] mntput_no_expire+0x86/0xe0 [<ffffffff8117df7f>] sys_umount+0x6f/0x360 [<ffffffff8103f01b>] system_call_fastpath+0x16/0x1b ---[ end trace cce2a341ba3611a7 ]--- Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Thomas Gleixner <tglxlinutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 21:23:05 +00:00
#ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER
static struct debug_obj_descr percpu_counter_debug_descr;
static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state)
percpu_counter: add debugobj support All percpu counters are linked to a global list on initialization and removed from it on destruction. The list is walked during CPU up/down. If a percpu counter is freed without being properly destroyed, the system will oops only on the next CPU up/down making it pretty nasty to track down. This patch adds debugobj support for percpu counters so that such problems can be found easily. As percpu counters don't make sense on stack and can't be statically initialized, debugobj support is pretty simple. It's initialized and activated on counter initialization, and deactivatd and destroyed on counter destruction. With this patch applied, the bug fixed by commit 602586a83b719df0fbd94196a1359ed35aeb2df3 (shmem: put_super must percpu_counter_destroy) triggers the following warning on tmpfs unmount and the system won't oops on the next cpu up/down operation. ------------[ cut here ]------------ WARNING: at lib/debugobjects.c:259 debug_print_object+0x5c/0x70() Hardware name: Bochs ODEBUG: free active (active state 0) object type: percpu_counter Modules linked in: Pid: 3999, comm: umount Not tainted 2.6.36-rc2-work+ #5 Call Trace: [<ffffffff81083f7f>] warn_slowpath_common+0x7f/0xc0 [<ffffffff81084076>] warn_slowpath_fmt+0x46/0x50 [<ffffffff813b45cc>] debug_print_object+0x5c/0x70 [<ffffffff813b50e5>] debug_check_no_obj_freed+0x125/0x210 [<ffffffff811577d3>] kfree+0xb3/0x2f0 [<ffffffff81132edd>] shmem_put_super+0x1d/0x30 [<ffffffff81162e96>] generic_shutdown_super+0x56/0xe0 [<ffffffff81162f86>] kill_anon_super+0x16/0x60 [<ffffffff81162ff7>] kill_litter_super+0x27/0x30 [<ffffffff81163295>] deactivate_locked_super+0x45/0x60 [<ffffffff81163cfa>] deactivate_super+0x4a/0x70 [<ffffffff8117d446>] mntput_no_expire+0x86/0xe0 [<ffffffff8117df7f>] sys_umount+0x6f/0x360 [<ffffffff8103f01b>] system_call_fastpath+0x16/0x1b ---[ end trace cce2a341ba3611a7 ]--- Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Thomas Gleixner <tglxlinutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 21:23:05 +00:00
{
struct percpu_counter *fbc = addr;
switch (state) {
case ODEBUG_STATE_ACTIVE:
percpu_counter_destroy(fbc);
debug_object_free(fbc, &percpu_counter_debug_descr);
return true;
percpu_counter: add debugobj support All percpu counters are linked to a global list on initialization and removed from it on destruction. The list is walked during CPU up/down. If a percpu counter is freed without being properly destroyed, the system will oops only on the next CPU up/down making it pretty nasty to track down. This patch adds debugobj support for percpu counters so that such problems can be found easily. As percpu counters don't make sense on stack and can't be statically initialized, debugobj support is pretty simple. It's initialized and activated on counter initialization, and deactivatd and destroyed on counter destruction. With this patch applied, the bug fixed by commit 602586a83b719df0fbd94196a1359ed35aeb2df3 (shmem: put_super must percpu_counter_destroy) triggers the following warning on tmpfs unmount and the system won't oops on the next cpu up/down operation. ------------[ cut here ]------------ WARNING: at lib/debugobjects.c:259 debug_print_object+0x5c/0x70() Hardware name: Bochs ODEBUG: free active (active state 0) object type: percpu_counter Modules linked in: Pid: 3999, comm: umount Not tainted 2.6.36-rc2-work+ #5 Call Trace: [<ffffffff81083f7f>] warn_slowpath_common+0x7f/0xc0 [<ffffffff81084076>] warn_slowpath_fmt+0x46/0x50 [<ffffffff813b45cc>] debug_print_object+0x5c/0x70 [<ffffffff813b50e5>] debug_check_no_obj_freed+0x125/0x210 [<ffffffff811577d3>] kfree+0xb3/0x2f0 [<ffffffff81132edd>] shmem_put_super+0x1d/0x30 [<ffffffff81162e96>] generic_shutdown_super+0x56/0xe0 [<ffffffff81162f86>] kill_anon_super+0x16/0x60 [<ffffffff81162ff7>] kill_litter_super+0x27/0x30 [<ffffffff81163295>] deactivate_locked_super+0x45/0x60 [<ffffffff81163cfa>] deactivate_super+0x4a/0x70 [<ffffffff8117d446>] mntput_no_expire+0x86/0xe0 [<ffffffff8117df7f>] sys_umount+0x6f/0x360 [<ffffffff8103f01b>] system_call_fastpath+0x16/0x1b ---[ end trace cce2a341ba3611a7 ]--- Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Thomas Gleixner <tglxlinutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 21:23:05 +00:00
default:
return false;
percpu_counter: add debugobj support All percpu counters are linked to a global list on initialization and removed from it on destruction. The list is walked during CPU up/down. If a percpu counter is freed without being properly destroyed, the system will oops only on the next CPU up/down making it pretty nasty to track down. This patch adds debugobj support for percpu counters so that such problems can be found easily. As percpu counters don't make sense on stack and can't be statically initialized, debugobj support is pretty simple. It's initialized and activated on counter initialization, and deactivatd and destroyed on counter destruction. With this patch applied, the bug fixed by commit 602586a83b719df0fbd94196a1359ed35aeb2df3 (shmem: put_super must percpu_counter_destroy) triggers the following warning on tmpfs unmount and the system won't oops on the next cpu up/down operation. ------------[ cut here ]------------ WARNING: at lib/debugobjects.c:259 debug_print_object+0x5c/0x70() Hardware name: Bochs ODEBUG: free active (active state 0) object type: percpu_counter Modules linked in: Pid: 3999, comm: umount Not tainted 2.6.36-rc2-work+ #5 Call Trace: [<ffffffff81083f7f>] warn_slowpath_common+0x7f/0xc0 [<ffffffff81084076>] warn_slowpath_fmt+0x46/0x50 [<ffffffff813b45cc>] debug_print_object+0x5c/0x70 [<ffffffff813b50e5>] debug_check_no_obj_freed+0x125/0x210 [<ffffffff811577d3>] kfree+0xb3/0x2f0 [<ffffffff81132edd>] shmem_put_super+0x1d/0x30 [<ffffffff81162e96>] generic_shutdown_super+0x56/0xe0 [<ffffffff81162f86>] kill_anon_super+0x16/0x60 [<ffffffff81162ff7>] kill_litter_super+0x27/0x30 [<ffffffff81163295>] deactivate_locked_super+0x45/0x60 [<ffffffff81163cfa>] deactivate_super+0x4a/0x70 [<ffffffff8117d446>] mntput_no_expire+0x86/0xe0 [<ffffffff8117df7f>] sys_umount+0x6f/0x360 [<ffffffff8103f01b>] system_call_fastpath+0x16/0x1b ---[ end trace cce2a341ba3611a7 ]--- Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Thomas Gleixner <tglxlinutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 21:23:05 +00:00
}
}
static struct debug_obj_descr percpu_counter_debug_descr = {
.name = "percpu_counter",
.fixup_free = percpu_counter_fixup_free,
};
static inline void debug_percpu_counter_activate(struct percpu_counter *fbc)
{
debug_object_init(fbc, &percpu_counter_debug_descr);
debug_object_activate(fbc, &percpu_counter_debug_descr);
}
static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc)
{
debug_object_deactivate(fbc, &percpu_counter_debug_descr);
debug_object_free(fbc, &percpu_counter_debug_descr);
}
#else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */
static inline void debug_percpu_counter_activate(struct percpu_counter *fbc)
{ }
static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc)
{ }
#endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */
void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
{
int cpu;
unsigned long flags;
raw_spin_lock_irqsave(&fbc->lock, flags);
for_each_possible_cpu(cpu) {
s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
*pcount = 0;
}
fbc->count = amount;
raw_spin_unlock_irqrestore(&fbc->lock, flags);
}
EXPORT_SYMBOL(percpu_counter_set);
void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
{
s64 count;
preempt_disable();
percpucounter: Optimize __percpu_counter_add a bit through the use of this_cpu() options. The this_cpu_* options can be used to optimize __percpu_counter_add a bit. Avoids some address arithmetic and saves 12 bytes. Before: 00000000000001d3 <__percpu_counter_add>: 1d3: 55 push %rbp 1d4: 48 89 e5 mov %rsp,%rbp 1d7: 41 55 push %r13 1d9: 41 54 push %r12 1db: 53 push %rbx 1dc: 48 89 fb mov %rdi,%rbx 1df: 48 83 ec 08 sub $0x8,%rsp 1e3: 4c 8b 67 30 mov 0x30(%rdi),%r12 1e7: 65 4c 03 24 25 00 00 add %gs:0x0,%r12 1ee: 00 00 1f0: 4d 63 2c 24 movslq (%r12),%r13 1f4: 48 63 c2 movslq %edx,%rax 1f7: 49 01 f5 add %rsi,%r13 1fa: 49 39 c5 cmp %rax,%r13 1fd: 7d 0a jge 209 <__percpu_counter_add+0x36> 1ff: f7 da neg %edx 201: 48 63 d2 movslq %edx,%rdx 204: 49 39 d5 cmp %rdx,%r13 207: 7f 1e jg 227 <__percpu_counter_add+0x54> 209: 48 89 df mov %rbx,%rdi 20c: e8 00 00 00 00 callq 211 <__percpu_counter_add+0x3e> 211: 4c 01 6b 18 add %r13,0x18(%rbx) 215: 48 89 df mov %rbx,%rdi 218: 41 c7 04 24 00 00 00 movl $0x0,(%r12) 21f: 00 220: e8 00 00 00 00 callq 225 <__percpu_counter_add+0x52> 225: eb 04 jmp 22b <__percpu_counter_add+0x58> 227: 45 89 2c 24 mov %r13d,(%r12) 22b: 5b pop %rbx 22c: 5b pop %rbx 22d: 41 5c pop %r12 22f: 41 5d pop %r13 231: c9 leaveq 232: c3 retq After: 00000000000001d3 <__percpu_counter_add>: 1d3: 55 push %rbp 1d4: 48 63 ca movslq %edx,%rcx 1d7: 48 89 e5 mov %rsp,%rbp 1da: 41 54 push %r12 1dc: 53 push %rbx 1dd: 48 89 fb mov %rdi,%rbx 1e0: 48 8b 47 30 mov 0x30(%rdi),%rax 1e4: 65 44 8b 20 mov %gs:(%rax),%r12d 1e8: 4d 63 e4 movslq %r12d,%r12 1eb: 49 01 f4 add %rsi,%r12 1ee: 49 39 cc cmp %rcx,%r12 1f1: 7d 0a jge 1fd <__percpu_counter_add+0x2a> 1f3: f7 da neg %edx 1f5: 48 63 d2 movslq %edx,%rdx 1f8: 49 39 d4 cmp %rdx,%r12 1fb: 7f 21 jg 21e <__percpu_counter_add+0x4b> 1fd: 48 89 df mov %rbx,%rdi 200: e8 00 00 00 00 callq 205 <__percpu_counter_add+0x32> 205: 4c 01 63 18 add %r12,0x18(%rbx) 209: 48 8b 43 30 mov 0x30(%rbx),%rax 20d: 48 89 df mov %rbx,%rdi 210: 65 c7 00 00 00 00 00 movl $0x0,%gs:(%rax) 217: e8 00 00 00 00 callq 21c <__percpu_counter_add+0x49> 21c: eb 04 jmp 222 <__percpu_counter_add+0x4f> 21e: 65 44 89 20 mov %r12d,%gs:(%rax) 222: 5b pop %rbx 223: 41 5c pop %r12 225: c9 leaveq 226: c3 retq Reviewed-by: Pekka Enberg <penberg@kernel.org> Reviewed-by: Tejun Heo <tj@kernel.org> Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Acked-by: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2010-12-06 17:16:19 +00:00
count = __this_cpu_read(*fbc->counters) + amount;
if (count >= batch || count <= -batch) {
unsigned long flags;
raw_spin_lock_irqsave(&fbc->lock, flags);
fbc->count += count;
__this_cpu_sub(*fbc->counters, count - amount);
raw_spin_unlock_irqrestore(&fbc->lock, flags);
} else {
this_cpu_add(*fbc->counters, amount);
}
preempt_enable();
}
EXPORT_SYMBOL(__percpu_counter_add);
/*
* Add up all the per-cpu counts, return the result. This is a more accurate
* but much slower version of percpu_counter_read_positive()
*/
s64 __percpu_counter_sum(struct percpu_counter *fbc)
{
s64 ret;
int cpu;
unsigned long flags;
raw_spin_lock_irqsave(&fbc->lock, flags);
ret = fbc->count;
for_each_online_cpu(cpu) {
s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
ret += *pcount;
}
raw_spin_unlock_irqrestore(&fbc->lock, flags);
return ret;
}
EXPORT_SYMBOL(__percpu_counter_sum);
int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp,
struct lock_class_key *key)
{
unsigned long flags __maybe_unused;
raw_spin_lock_init(&fbc->lock);
lockdep_set_class(&fbc->lock, key);
fbc->count = amount;
fbc->counters = alloc_percpu_gfp(s32, gfp);
if (!fbc->counters)
return -ENOMEM;
percpu_counter: add debugobj support All percpu counters are linked to a global list on initialization and removed from it on destruction. The list is walked during CPU up/down. If a percpu counter is freed without being properly destroyed, the system will oops only on the next CPU up/down making it pretty nasty to track down. This patch adds debugobj support for percpu counters so that such problems can be found easily. As percpu counters don't make sense on stack and can't be statically initialized, debugobj support is pretty simple. It's initialized and activated on counter initialization, and deactivatd and destroyed on counter destruction. With this patch applied, the bug fixed by commit 602586a83b719df0fbd94196a1359ed35aeb2df3 (shmem: put_super must percpu_counter_destroy) triggers the following warning on tmpfs unmount and the system won't oops on the next cpu up/down operation. ------------[ cut here ]------------ WARNING: at lib/debugobjects.c:259 debug_print_object+0x5c/0x70() Hardware name: Bochs ODEBUG: free active (active state 0) object type: percpu_counter Modules linked in: Pid: 3999, comm: umount Not tainted 2.6.36-rc2-work+ #5 Call Trace: [<ffffffff81083f7f>] warn_slowpath_common+0x7f/0xc0 [<ffffffff81084076>] warn_slowpath_fmt+0x46/0x50 [<ffffffff813b45cc>] debug_print_object+0x5c/0x70 [<ffffffff813b50e5>] debug_check_no_obj_freed+0x125/0x210 [<ffffffff811577d3>] kfree+0xb3/0x2f0 [<ffffffff81132edd>] shmem_put_super+0x1d/0x30 [<ffffffff81162e96>] generic_shutdown_super+0x56/0xe0 [<ffffffff81162f86>] kill_anon_super+0x16/0x60 [<ffffffff81162ff7>] kill_litter_super+0x27/0x30 [<ffffffff81163295>] deactivate_locked_super+0x45/0x60 [<ffffffff81163cfa>] deactivate_super+0x4a/0x70 [<ffffffff8117d446>] mntput_no_expire+0x86/0xe0 [<ffffffff8117df7f>] sys_umount+0x6f/0x360 [<ffffffff8103f01b>] system_call_fastpath+0x16/0x1b ---[ end trace cce2a341ba3611a7 ]--- Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Thomas Gleixner <tglxlinutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 21:23:05 +00:00
debug_percpu_counter_activate(fbc);
#ifdef CONFIG_HOTPLUG_CPU
percpu: fix list_head init bug in __percpu_counter_init() WARNING: at lib/list_debug.c:26 __list_add+0x3f/0x81() Hardware name: Express5800/B120a [N8400-085] list_add corruption. next->prev should be prev (ffffffff81a7ea00), but was dead000000200200. (next=ffff88080b872d58). Modules linked in: aoe ipt_MASQUERADE iptable_nat nf_nat autofs4 sunrpc bridge 8021q garp stp llc ipv6 cpufreq_ondemand acpi_cpufreq freq_table dm_round_robin dm_multipath kvm_intel kvm uinput lpfc scsi_transport_fc igb ioatdma scsi_tgt i2c_i801 i2c_core dca iTCO_wdt iTCO_vendor_support pcspkr shpchp megaraid_sas [last unloaded: aoe] Pid: 54, comm: events/3 Tainted: G W 2.6.34-vanilla1 #1 Call Trace: [<ffffffff8104bd77>] warn_slowpath_common+0x7c/0x94 [<ffffffff8104bde6>] warn_slowpath_fmt+0x41/0x43 [<ffffffff8120fd2e>] __list_add+0x3f/0x81 [<ffffffff81212a12>] __percpu_counter_init+0x59/0x6b [<ffffffff810d8499>] bdi_init+0x118/0x17e [<ffffffff811f2c50>] blk_alloc_queue_node+0x79/0x143 [<ffffffff811f2d2b>] blk_alloc_queue+0x11/0x13 [<ffffffffa02a931d>] aoeblk_gdalloc+0x8e/0x1c9 [aoe] [<ffffffffa02aa655>] aoecmd_sleepwork+0x25/0xa8 [aoe] [<ffffffff8106186c>] worker_thread+0x1a9/0x237 [<ffffffffa02aa630>] ? aoecmd_sleepwork+0x0/0xa8 [aoe] [<ffffffff81065827>] ? autoremove_wake_function+0x0/0x39 [<ffffffff810616c3>] ? worker_thread+0x0/0x237 [<ffffffff810653ad>] kthread+0x7f/0x87 [<ffffffff8100aa24>] kernel_thread_helper+0x4/0x10 [<ffffffff8106532e>] ? kthread+0x0/0x87 [<ffffffff8100aa20>] ? kernel_thread_helper+0x0/0x10 It's because there is no initialization code for a list_head contained in the struct backing_dev_info under CONFIG_HOTPLUG_CPU, and the bug comes up when block device drivers calling blk_alloc_queue() are used. In case of me, I got them by using aoe. Signed-off-by: Masanori Itoh <itoumsn@nttdata.co.jp> Cc: Tejun Heo <tj@kernel.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 21:21:20 +00:00
INIT_LIST_HEAD(&fbc->list);
spin_lock_irqsave(&percpu_counters_lock, flags);
list_add(&fbc->list, &percpu_counters);
spin_unlock_irqrestore(&percpu_counters_lock, flags);
#endif
return 0;
}
EXPORT_SYMBOL(__percpu_counter_init);
void percpu_counter_destroy(struct percpu_counter *fbc)
{
unsigned long flags __maybe_unused;
if (!fbc->counters)
return;
percpu_counter: add debugobj support All percpu counters are linked to a global list on initialization and removed from it on destruction. The list is walked during CPU up/down. If a percpu counter is freed without being properly destroyed, the system will oops only on the next CPU up/down making it pretty nasty to track down. This patch adds debugobj support for percpu counters so that such problems can be found easily. As percpu counters don't make sense on stack and can't be statically initialized, debugobj support is pretty simple. It's initialized and activated on counter initialization, and deactivatd and destroyed on counter destruction. With this patch applied, the bug fixed by commit 602586a83b719df0fbd94196a1359ed35aeb2df3 (shmem: put_super must percpu_counter_destroy) triggers the following warning on tmpfs unmount and the system won't oops on the next cpu up/down operation. ------------[ cut here ]------------ WARNING: at lib/debugobjects.c:259 debug_print_object+0x5c/0x70() Hardware name: Bochs ODEBUG: free active (active state 0) object type: percpu_counter Modules linked in: Pid: 3999, comm: umount Not tainted 2.6.36-rc2-work+ #5 Call Trace: [<ffffffff81083f7f>] warn_slowpath_common+0x7f/0xc0 [<ffffffff81084076>] warn_slowpath_fmt+0x46/0x50 [<ffffffff813b45cc>] debug_print_object+0x5c/0x70 [<ffffffff813b50e5>] debug_check_no_obj_freed+0x125/0x210 [<ffffffff811577d3>] kfree+0xb3/0x2f0 [<ffffffff81132edd>] shmem_put_super+0x1d/0x30 [<ffffffff81162e96>] generic_shutdown_super+0x56/0xe0 [<ffffffff81162f86>] kill_anon_super+0x16/0x60 [<ffffffff81162ff7>] kill_litter_super+0x27/0x30 [<ffffffff81163295>] deactivate_locked_super+0x45/0x60 [<ffffffff81163cfa>] deactivate_super+0x4a/0x70 [<ffffffff8117d446>] mntput_no_expire+0x86/0xe0 [<ffffffff8117df7f>] sys_umount+0x6f/0x360 [<ffffffff8103f01b>] system_call_fastpath+0x16/0x1b ---[ end trace cce2a341ba3611a7 ]--- Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Thomas Gleixner <tglxlinutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 21:23:05 +00:00
debug_percpu_counter_deactivate(fbc);
#ifdef CONFIG_HOTPLUG_CPU
spin_lock_irqsave(&percpu_counters_lock, flags);
list_del(&fbc->list);
spin_unlock_irqrestore(&percpu_counters_lock, flags);
#endif
free_percpu(fbc->counters);
fbc->counters = NULL;
}
EXPORT_SYMBOL(percpu_counter_destroy);
int percpu_counter_batch __read_mostly = 32;
EXPORT_SYMBOL(percpu_counter_batch);
static void compute_batch_value(void)
{
int nr = num_online_cpus();
percpu_counter_batch = max(32, nr*2);
}
static int percpu_counter_hotcpu_callback(struct notifier_block *nb,
unsigned long action, void *hcpu)
{
#ifdef CONFIG_HOTPLUG_CPU
unsigned int cpu;
struct percpu_counter *fbc;
compute_batch_value();
lib/percpu_counter.c: fix bad percpu counter state during suspend I got a bug report yesterday from Laszlo Ersek in which he states that his kvm instance fails to suspend. Laszlo bisected it down to this commit 1cf7e9c68fe8 ("virtio_blk: blk-mq support") where virtio-blk is converted to use the blk-mq infrastructure. After digging a bit, it became clear that the issue was with the queue drain. blk-mq tracks queue usage in a percpu counter, which is incremented on request alloc and decremented when the request is freed. The initial hunt was for an inconsistency in blk-mq, but everything seemed fine. In fact, the counter only returned crazy values when suspend was in progress. When a CPU is unplugged, the percpu counters merges that CPU state with the general state. blk-mq takes care to register a hotcpu notifier with the appropriate priority, so we know it runs after the percpu counter notifier. However, the percpu counter notifier only merges the state when the CPU is fully gone. This leaves a state transition where the CPU going away is no longer in the online mask, yet it still holds private values. This means that in this state, percpu_counter_sum() returns invalid results, and the suspend then hangs waiting for abs(dead-cpu-value) requests to complete which of course will never happen. Fix this by clearing the state earlier, so we never have a case where the CPU isn't in online mask but still holds private state. This bug has been there since forever, I guess we don't have a lot of users where percpu counters needs to be reliable during the suspend cycle. Signed-off-by: Jens Axboe <axboe@fb.com> Reported-by: Laszlo Ersek <lersek@redhat.com> Tested-by: Laszlo Ersek <lersek@redhat.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-08 23:04:12 +00:00
if (action != CPU_DEAD && action != CPU_DEAD_FROZEN)
return NOTIFY_OK;
cpu = (unsigned long)hcpu;
spin_lock_irq(&percpu_counters_lock);
list_for_each_entry(fbc, &percpu_counters, list) {
s32 *pcount;
unsigned long flags;
raw_spin_lock_irqsave(&fbc->lock, flags);
pcount = per_cpu_ptr(fbc->counters, cpu);
fbc->count += *pcount;
*pcount = 0;
raw_spin_unlock_irqrestore(&fbc->lock, flags);
}
spin_unlock_irq(&percpu_counters_lock);
#endif
return NOTIFY_OK;
}
/*
* Compare counter against given value.
* Return 1 if greater, 0 if equal and -1 if less
*/
int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
{
s64 count;
count = percpu_counter_read(fbc);
/* Check to see if rough count will be sufficient for comparison */
if (abs(count - rhs) > (batch * num_online_cpus())) {
if (count > rhs)
return 1;
else
return -1;
}
/* Need to use precise count */
count = percpu_counter_sum(fbc);
if (count > rhs)
return 1;
else if (count < rhs)
return -1;
else
return 0;
}
EXPORT_SYMBOL(__percpu_counter_compare);
static int __init percpu_counter_startup(void)
{
compute_batch_value();
hotcpu_notifier(percpu_counter_hotcpu_callback, 0);
return 0;
}
module_init(percpu_counter_startup);