linux/kernel/smp.c

426 lines
10 KiB
C
Raw Normal View History

/*
* Generic helpers for smp ipi calls
*
* (C) Jens Axboe <jens.axboe@oracle.com> 2008
*
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/rcupdate.h>
#include <linux/rculist.h>
#include <linux/smp.h>
static DEFINE_PER_CPU(struct call_single_queue, call_single_queue);
static LIST_HEAD(call_function_queue);
__cacheline_aligned_in_smp DEFINE_SPINLOCK(call_function_lock);
enum {
CSD_FLAG_WAIT = 0x01,
CSD_FLAG_ALLOC = 0x02,
};
struct call_function_data {
struct call_single_data csd;
spinlock_t lock;
unsigned int refs;
cpumask_t cpumask;
struct rcu_head rcu_head;
};
struct call_single_queue {
struct list_head list;
spinlock_t lock;
};
static int __cpuinit init_call_single_data(void)
{
int i;
for_each_possible_cpu(i) {
struct call_single_queue *q = &per_cpu(call_single_queue, i);
spin_lock_init(&q->lock);
INIT_LIST_HEAD(&q->list);
}
return 0;
}
early_initcall(init_call_single_data);
static void csd_flag_wait(struct call_single_data *data)
{
/* Wait for response */
do {
/*
* We need to see the flags store in the IPI handler
*/
smp_mb();
if (!(data->flags & CSD_FLAG_WAIT))
break;
cpu_relax();
} while (1);
}
/*
* Insert a previously allocated call_single_data element for execution
* on the given CPU. data must already have ->func, ->info, and ->flags set.
*/
static void generic_exec_single(int cpu, struct call_single_data *data)
{
struct call_single_queue *dst = &per_cpu(call_single_queue, cpu);
int wait = data->flags & CSD_FLAG_WAIT, ipi;
unsigned long flags;
spin_lock_irqsave(&dst->lock, flags);
ipi = list_empty(&dst->list);
list_add_tail(&data->list, &dst->list);
spin_unlock_irqrestore(&dst->lock, flags);
if (ipi)
arch_send_call_function_single_ipi(cpu);
if (wait)
csd_flag_wait(data);
}
static void rcu_free_call_data(struct rcu_head *head)
{
struct call_function_data *data;
data = container_of(head, struct call_function_data, rcu_head);
kfree(data);
}
/*
* Invoked by arch to handle an IPI for call function. Must be called with
* interrupts disabled.
*/
void generic_smp_call_function_interrupt(void)
{
struct call_function_data *data;
int cpu = get_cpu();
/*
* It's ok to use list_for_each_rcu() here even though we may delete
* 'pos', since list_del_rcu() doesn't clear ->next
*/
rcu_read_lock();
list_for_each_entry_rcu(data, &call_function_queue, csd.list) {
int refs;
if (!cpu_isset(cpu, data->cpumask))
continue;
data->csd.func(data->csd.info);
spin_lock(&data->lock);
cpu_clear(cpu, data->cpumask);
WARN_ON(data->refs == 0);
data->refs--;
refs = data->refs;
spin_unlock(&data->lock);
if (refs)
continue;
spin_lock(&call_function_lock);
list_del_rcu(&data->csd.list);
spin_unlock(&call_function_lock);
if (data->csd.flags & CSD_FLAG_WAIT) {
/*
* serialize stores to data with the flag clear
* and wakeup
*/
smp_wmb();
data->csd.flags &= ~CSD_FLAG_WAIT;
} else
call_rcu(&data->rcu_head, rcu_free_call_data);
}
rcu_read_unlock();
put_cpu();
}
/*
* Invoked by arch to handle an IPI for call function single. Must be called
* from the arch with interrupts disabled.
*/
void generic_smp_call_function_single_interrupt(void)
{
struct call_single_queue *q = &__get_cpu_var(call_single_queue);
LIST_HEAD(list);
/*
* Need to see other stores to list head for checking whether
* list is empty without holding q->lock
*/
smp_mb();
while (!list_empty(&q->list)) {
unsigned int data_flags;
spin_lock(&q->lock);
list_replace_init(&q->list, &list);
spin_unlock(&q->lock);
while (!list_empty(&list)) {
struct call_single_data *data;
data = list_entry(list.next, struct call_single_data,
list);
list_del(&data->list);
/*
* 'data' can be invalid after this call if
* flags == 0 (when called through
* generic_exec_single(), so save them away before
* making the call.
*/
data_flags = data->flags;
data->func(data->info);
if (data_flags & CSD_FLAG_WAIT) {
smp_wmb();
data->flags &= ~CSD_FLAG_WAIT;
} else if (data_flags & CSD_FLAG_ALLOC)
kfree(data);
}
/*
* See comment on outer loop
*/
smp_mb();
}
}
/*
* smp_call_function_single - Run a function on a specific CPU
* @func: The function to run. This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to the function.
* @wait: If true, wait until function has completed on other CPUs.
*
* Returns 0 on success, else a negative status code. Note that @wait
* will be implicitly turned on in case of allocation failures, since
* we fall back to on-stack allocation.
*/
int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
int wait)
{
struct call_single_data d;
unsigned long flags;
/* prevent preemption and reschedule on another processor */
int me = get_cpu();
/* Can deadlock when called with interrupts disabled */
WARN_ON(irqs_disabled());
if (cpu == me) {
local_irq_save(flags);
func(info);
local_irq_restore(flags);
} else {
struct call_single_data *data = NULL;
if (!wait) {
data = kmalloc(sizeof(*data), GFP_ATOMIC);
if (data)
data->flags = CSD_FLAG_ALLOC;
}
if (!data) {
data = &d;
data->flags = CSD_FLAG_WAIT;
}
data->func = func;
data->info = info;
generic_exec_single(cpu, data);
}
put_cpu();
return 0;
}
EXPORT_SYMBOL(smp_call_function_single);
/**
* __smp_call_function_single(): Run a function on another CPU
* @cpu: The CPU to run on.
* @data: Pre-allocated and setup data structure
*
* Like smp_call_function_single(), but allow caller to pass in a pre-allocated
* data structure. Useful for embedding @data inside other structures, for
* instance.
*
*/
void __smp_call_function_single(int cpu, struct call_single_data *data)
{
/* Can deadlock when called with interrupts disabled */
WARN_ON((data->flags & CSD_FLAG_WAIT) && irqs_disabled());
generic_exec_single(cpu, data);
}
generic-ipi: fix stack and rcu interaction bug in smp_call_function_mask() * Venki Pallipadi <venkatesh.pallipadi@intel.com> wrote: > Found a OOPS on a big SMP box during an overnight reboot test with > upstream git. > > Suresh and I looked at the oops and looks like the root cause is in > generic_smp_call_function_interrupt() and smp_call_function_mask() with > wait parameter. > > The actual oops looked like > > [ 11.277260] BUG: unable to handle kernel paging request at ffff8802ffffffff > [ 11.277815] IP: [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.278155] PGD 202063 PUD 0 > [ 11.278576] Oops: 0010 [1] SMP > [ 11.279006] CPU 5 > [ 11.279336] Modules linked in: > [ 11.279752] Pid: 0, comm: swapper Not tainted 2.6.27-rc2-00020-g685d87f #290 > [ 11.280039] RIP: 0010:[<ffff8802ffffffff>] [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.280692] RSP: 0018:ffff88027f1f7f70 EFLAGS: 00010086 > [ 11.280976] RAX: 00000000ffffffff RBX: 0000000000000000 RCX: 0000000000000000 > [ 11.281264] RDX: 0000000000004f4e RSI: 0000000000000001 RDI: 0000000000000000 > [ 11.281624] RBP: ffff88027f1f7f98 R08: 0000000000000001 R09: ffffffff802509af > [ 11.281925] R10: ffff8800280c2780 R11: 0000000000000000 R12: ffff88027f097d48 > [ 11.282214] R13: ffff88027f097d70 R14: 0000000000000005 R15: ffff88027e571000 > [ 11.282502] FS: 0000000000000000(0000) GS:ffff88027f1c3340(0000) knlGS:0000000000000000 > [ 11.283096] CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b > [ 11.283382] CR2: ffff8802ffffffff CR3: 0000000000201000 CR4: 00000000000006e0 > [ 11.283760] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 11.284048] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > [ 11.284337] Process swapper (pid: 0, threadinfo ffff88027f1f2000, task ffff88027f1f0640) > [ 11.284936] Stack: ffffffff80250963 0000000000000212 0000000000ee8c78 0000000000ee8a66 > [ 11.285802] ffff88027e571550 ffff88027f1f7fa8 ffffffff8021adb5 ffff88027f1f3e40 > [ 11.286599] ffffffff8020bdd6 ffff88027f1f3e40 <EOI> ffff88027f1f3ef8 0000000000000000 > [ 11.287120] Call Trace: > [ 11.287768] <IRQ> [<ffffffff80250963>] ? generic_smp_call_function_interrupt+0x61/0x12c > [ 11.288354] [<ffffffff8021adb5>] smp_call_function_interrupt+0x17/0x27 > [ 11.288744] [<ffffffff8020bdd6>] call_function_interrupt+0x66/0x70 > [ 11.289030] <EOI> [<ffffffff8024ab3b>] ? clockevents_notify+0x19/0x73 > [ 11.289380] [<ffffffff803b9b75>] ? acpi_idle_enter_simple+0x18b/0x1fa > [ 11.289760] [<ffffffff803b9b6b>] ? acpi_idle_enter_simple+0x181/0x1fa > [ 11.290051] [<ffffffff8053aeca>] ? cpuidle_idle_call+0x70/0xa2 > [ 11.290338] [<ffffffff80209f61>] ? cpu_idle+0x5f/0x7d > [ 11.290723] [<ffffffff8060224a>] ? start_secondary+0x14d/0x152 > [ 11.291010] > [ 11.291287] > [ 11.291654] Code: Bad RIP value. > [ 11.292041] RIP [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.292380] RSP <ffff88027f1f7f70> > [ 11.292741] CR2: ffff8802ffffffff > [ 11.310951] ---[ end trace 137c54d525305f1c ]--- > > The problem is with the following sequence of events: > > - CPU A calls smp_call_function_mask() for CPU B with wait parameter > - CPU A sets up the call_function_data on the stack and does an rcu add to > call_function_queue > - CPU A waits until the WAIT flag is cleared > - CPU B gets the call function interrupt and starts going through the > call_function_queue > - CPU C also gets some other call function interrupt and starts going through > the call_function_queue > - CPU C, which is also going through the call_function_queue, starts referencing > CPU A's stack, as that element is still in call_function_queue > - CPU B finishes the function call that CPU A set up and as there are no other > references to it, rcu deletes the call_function_data (which was from CPU A > stack) > - CPU B sees the wait flag and just clears the flag (no call_rcu to free) > - CPU A which was waiting on the flag continues executing and the stack > contents change > > - CPU C is still in rcu_read section accessing the CPU A's stack sees > inconsistent call_funation_data and can try to execute > function with some random pointer, causing stack corruption for A > (by clearing the bits in mask field) and oops. Nice debugging work. I'd suggest something like the attached (boot tested) patch as the simple fix for now. I expect the benefits from the less synchronized, multiple-in-flight-data global queue will still outweigh the costs of dynamic allocations. But if worst comes to worst then we just go back to a globally synchronous one-at-a-time implementation, but that would be pretty sad! Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-11 03:49:30 +00:00
/* Dummy function */
static void quiesce_dummy(void *unused)
{
}
/*
* Ensure stack based data used in call function mask is safe to free.
*
* This is needed by smp_call_function_mask when using on-stack data, because
* a single call function queue is shared by all CPUs, and any CPU may pick up
* the data item on the queue at any time before it is deleted. So we need to
* ensure that all CPUs have transitioned through a quiescent state after
* this call.
*
* This is a very slow function, implemented by sending synchronous IPIs to
* all possible CPUs. For this reason, we have to alloc data rather than use
* stack based data even in the case of synchronous calls. The stack based
* data is then just used for deadlock/oom fallback which will be very rare.
*
* If a faster scheme can be made, we could go back to preferring stack based
* data -- the data allocation/free is non-zero cost.
*/
static void smp_call_function_mask_quiesce_stack(cpumask_t mask)
{
struct call_single_data data;
int cpu;
data.func = quiesce_dummy;
data.info = NULL;
data.flags = CSD_FLAG_WAIT;
for_each_cpu_mask(cpu, mask)
generic_exec_single(cpu, &data);
}
/**
* smp_call_function_mask(): Run a function on a set of other CPUs.
* @mask: The set of cpus to run on.
* @func: The function to run. This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to the function.
* @wait: If true, wait (atomically) until function has completed on other CPUs.
*
* Returns 0 on success, else a negative status code.
*
* If @wait is true, then returns once @func has returned. Note that @wait
* will be implicitly turned on in case of allocation failures, since
* we fall back to on-stack allocation.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler. Preemption
* must be disabled when calling this function.
*/
int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
int wait)
{
struct call_function_data d;
struct call_function_data *data = NULL;
cpumask_t allbutself;
unsigned long flags;
int cpu, num_cpus;
generic-ipi: fix stack and rcu interaction bug in smp_call_function_mask() * Venki Pallipadi <venkatesh.pallipadi@intel.com> wrote: > Found a OOPS on a big SMP box during an overnight reboot test with > upstream git. > > Suresh and I looked at the oops and looks like the root cause is in > generic_smp_call_function_interrupt() and smp_call_function_mask() with > wait parameter. > > The actual oops looked like > > [ 11.277260] BUG: unable to handle kernel paging request at ffff8802ffffffff > [ 11.277815] IP: [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.278155] PGD 202063 PUD 0 > [ 11.278576] Oops: 0010 [1] SMP > [ 11.279006] CPU 5 > [ 11.279336] Modules linked in: > [ 11.279752] Pid: 0, comm: swapper Not tainted 2.6.27-rc2-00020-g685d87f #290 > [ 11.280039] RIP: 0010:[<ffff8802ffffffff>] [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.280692] RSP: 0018:ffff88027f1f7f70 EFLAGS: 00010086 > [ 11.280976] RAX: 00000000ffffffff RBX: 0000000000000000 RCX: 0000000000000000 > [ 11.281264] RDX: 0000000000004f4e RSI: 0000000000000001 RDI: 0000000000000000 > [ 11.281624] RBP: ffff88027f1f7f98 R08: 0000000000000001 R09: ffffffff802509af > [ 11.281925] R10: ffff8800280c2780 R11: 0000000000000000 R12: ffff88027f097d48 > [ 11.282214] R13: ffff88027f097d70 R14: 0000000000000005 R15: ffff88027e571000 > [ 11.282502] FS: 0000000000000000(0000) GS:ffff88027f1c3340(0000) knlGS:0000000000000000 > [ 11.283096] CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b > [ 11.283382] CR2: ffff8802ffffffff CR3: 0000000000201000 CR4: 00000000000006e0 > [ 11.283760] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 11.284048] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > [ 11.284337] Process swapper (pid: 0, threadinfo ffff88027f1f2000, task ffff88027f1f0640) > [ 11.284936] Stack: ffffffff80250963 0000000000000212 0000000000ee8c78 0000000000ee8a66 > [ 11.285802] ffff88027e571550 ffff88027f1f7fa8 ffffffff8021adb5 ffff88027f1f3e40 > [ 11.286599] ffffffff8020bdd6 ffff88027f1f3e40 <EOI> ffff88027f1f3ef8 0000000000000000 > [ 11.287120] Call Trace: > [ 11.287768] <IRQ> [<ffffffff80250963>] ? generic_smp_call_function_interrupt+0x61/0x12c > [ 11.288354] [<ffffffff8021adb5>] smp_call_function_interrupt+0x17/0x27 > [ 11.288744] [<ffffffff8020bdd6>] call_function_interrupt+0x66/0x70 > [ 11.289030] <EOI> [<ffffffff8024ab3b>] ? clockevents_notify+0x19/0x73 > [ 11.289380] [<ffffffff803b9b75>] ? acpi_idle_enter_simple+0x18b/0x1fa > [ 11.289760] [<ffffffff803b9b6b>] ? acpi_idle_enter_simple+0x181/0x1fa > [ 11.290051] [<ffffffff8053aeca>] ? cpuidle_idle_call+0x70/0xa2 > [ 11.290338] [<ffffffff80209f61>] ? cpu_idle+0x5f/0x7d > [ 11.290723] [<ffffffff8060224a>] ? start_secondary+0x14d/0x152 > [ 11.291010] > [ 11.291287] > [ 11.291654] Code: Bad RIP value. > [ 11.292041] RIP [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.292380] RSP <ffff88027f1f7f70> > [ 11.292741] CR2: ffff8802ffffffff > [ 11.310951] ---[ end trace 137c54d525305f1c ]--- > > The problem is with the following sequence of events: > > - CPU A calls smp_call_function_mask() for CPU B with wait parameter > - CPU A sets up the call_function_data on the stack and does an rcu add to > call_function_queue > - CPU A waits until the WAIT flag is cleared > - CPU B gets the call function interrupt and starts going through the > call_function_queue > - CPU C also gets some other call function interrupt and starts going through > the call_function_queue > - CPU C, which is also going through the call_function_queue, starts referencing > CPU A's stack, as that element is still in call_function_queue > - CPU B finishes the function call that CPU A set up and as there are no other > references to it, rcu deletes the call_function_data (which was from CPU A > stack) > - CPU B sees the wait flag and just clears the flag (no call_rcu to free) > - CPU A which was waiting on the flag continues executing and the stack > contents change > > - CPU C is still in rcu_read section accessing the CPU A's stack sees > inconsistent call_funation_data and can try to execute > function with some random pointer, causing stack corruption for A > (by clearing the bits in mask field) and oops. Nice debugging work. I'd suggest something like the attached (boot tested) patch as the simple fix for now. I expect the benefits from the less synchronized, multiple-in-flight-data global queue will still outweigh the costs of dynamic allocations. But if worst comes to worst then we just go back to a globally synchronous one-at-a-time implementation, but that would be pretty sad! Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-11 03:49:30 +00:00
int slowpath = 0;
/* Can deadlock when called with interrupts disabled */
WARN_ON(irqs_disabled());
cpu = smp_processor_id();
allbutself = cpu_online_map;
cpu_clear(cpu, allbutself);
cpus_and(mask, mask, allbutself);
num_cpus = cpus_weight(mask);
/*
* If zero CPUs, return. If just a single CPU, turn this request
* into a targetted single call instead since it's faster.
*/
if (!num_cpus)
return 0;
else if (num_cpus == 1) {
cpu = first_cpu(mask);
return smp_call_function_single(cpu, func, info, wait);
}
generic-ipi: fix stack and rcu interaction bug in smp_call_function_mask() * Venki Pallipadi <venkatesh.pallipadi@intel.com> wrote: > Found a OOPS on a big SMP box during an overnight reboot test with > upstream git. > > Suresh and I looked at the oops and looks like the root cause is in > generic_smp_call_function_interrupt() and smp_call_function_mask() with > wait parameter. > > The actual oops looked like > > [ 11.277260] BUG: unable to handle kernel paging request at ffff8802ffffffff > [ 11.277815] IP: [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.278155] PGD 202063 PUD 0 > [ 11.278576] Oops: 0010 [1] SMP > [ 11.279006] CPU 5 > [ 11.279336] Modules linked in: > [ 11.279752] Pid: 0, comm: swapper Not tainted 2.6.27-rc2-00020-g685d87f #290 > [ 11.280039] RIP: 0010:[<ffff8802ffffffff>] [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.280692] RSP: 0018:ffff88027f1f7f70 EFLAGS: 00010086 > [ 11.280976] RAX: 00000000ffffffff RBX: 0000000000000000 RCX: 0000000000000000 > [ 11.281264] RDX: 0000000000004f4e RSI: 0000000000000001 RDI: 0000000000000000 > [ 11.281624] RBP: ffff88027f1f7f98 R08: 0000000000000001 R09: ffffffff802509af > [ 11.281925] R10: ffff8800280c2780 R11: 0000000000000000 R12: ffff88027f097d48 > [ 11.282214] R13: ffff88027f097d70 R14: 0000000000000005 R15: ffff88027e571000 > [ 11.282502] FS: 0000000000000000(0000) GS:ffff88027f1c3340(0000) knlGS:0000000000000000 > [ 11.283096] CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b > [ 11.283382] CR2: ffff8802ffffffff CR3: 0000000000201000 CR4: 00000000000006e0 > [ 11.283760] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 11.284048] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > [ 11.284337] Process swapper (pid: 0, threadinfo ffff88027f1f2000, task ffff88027f1f0640) > [ 11.284936] Stack: ffffffff80250963 0000000000000212 0000000000ee8c78 0000000000ee8a66 > [ 11.285802] ffff88027e571550 ffff88027f1f7fa8 ffffffff8021adb5 ffff88027f1f3e40 > [ 11.286599] ffffffff8020bdd6 ffff88027f1f3e40 <EOI> ffff88027f1f3ef8 0000000000000000 > [ 11.287120] Call Trace: > [ 11.287768] <IRQ> [<ffffffff80250963>] ? generic_smp_call_function_interrupt+0x61/0x12c > [ 11.288354] [<ffffffff8021adb5>] smp_call_function_interrupt+0x17/0x27 > [ 11.288744] [<ffffffff8020bdd6>] call_function_interrupt+0x66/0x70 > [ 11.289030] <EOI> [<ffffffff8024ab3b>] ? clockevents_notify+0x19/0x73 > [ 11.289380] [<ffffffff803b9b75>] ? acpi_idle_enter_simple+0x18b/0x1fa > [ 11.289760] [<ffffffff803b9b6b>] ? acpi_idle_enter_simple+0x181/0x1fa > [ 11.290051] [<ffffffff8053aeca>] ? cpuidle_idle_call+0x70/0xa2 > [ 11.290338] [<ffffffff80209f61>] ? cpu_idle+0x5f/0x7d > [ 11.290723] [<ffffffff8060224a>] ? start_secondary+0x14d/0x152 > [ 11.291010] > [ 11.291287] > [ 11.291654] Code: Bad RIP value. > [ 11.292041] RIP [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.292380] RSP <ffff88027f1f7f70> > [ 11.292741] CR2: ffff8802ffffffff > [ 11.310951] ---[ end trace 137c54d525305f1c ]--- > > The problem is with the following sequence of events: > > - CPU A calls smp_call_function_mask() for CPU B with wait parameter > - CPU A sets up the call_function_data on the stack and does an rcu add to > call_function_queue > - CPU A waits until the WAIT flag is cleared > - CPU B gets the call function interrupt and starts going through the > call_function_queue > - CPU C also gets some other call function interrupt and starts going through > the call_function_queue > - CPU C, which is also going through the call_function_queue, starts referencing > CPU A's stack, as that element is still in call_function_queue > - CPU B finishes the function call that CPU A set up and as there are no other > references to it, rcu deletes the call_function_data (which was from CPU A > stack) > - CPU B sees the wait flag and just clears the flag (no call_rcu to free) > - CPU A which was waiting on the flag continues executing and the stack > contents change > > - CPU C is still in rcu_read section accessing the CPU A's stack sees > inconsistent call_funation_data and can try to execute > function with some random pointer, causing stack corruption for A > (by clearing the bits in mask field) and oops. Nice debugging work. I'd suggest something like the attached (boot tested) patch as the simple fix for now. I expect the benefits from the less synchronized, multiple-in-flight-data global queue will still outweigh the costs of dynamic allocations. But if worst comes to worst then we just go back to a globally synchronous one-at-a-time implementation, but that would be pretty sad! Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-11 03:49:30 +00:00
data = kmalloc(sizeof(*data), GFP_ATOMIC);
if (data) {
data->csd.flags = CSD_FLAG_ALLOC;
if (wait)
data->csd.flags |= CSD_FLAG_WAIT;
} else {
data = &d;
data->csd.flags = CSD_FLAG_WAIT;
wait = 1;
generic-ipi: fix stack and rcu interaction bug in smp_call_function_mask() * Venki Pallipadi <venkatesh.pallipadi@intel.com> wrote: > Found a OOPS on a big SMP box during an overnight reboot test with > upstream git. > > Suresh and I looked at the oops and looks like the root cause is in > generic_smp_call_function_interrupt() and smp_call_function_mask() with > wait parameter. > > The actual oops looked like > > [ 11.277260] BUG: unable to handle kernel paging request at ffff8802ffffffff > [ 11.277815] IP: [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.278155] PGD 202063 PUD 0 > [ 11.278576] Oops: 0010 [1] SMP > [ 11.279006] CPU 5 > [ 11.279336] Modules linked in: > [ 11.279752] Pid: 0, comm: swapper Not tainted 2.6.27-rc2-00020-g685d87f #290 > [ 11.280039] RIP: 0010:[<ffff8802ffffffff>] [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.280692] RSP: 0018:ffff88027f1f7f70 EFLAGS: 00010086 > [ 11.280976] RAX: 00000000ffffffff RBX: 0000000000000000 RCX: 0000000000000000 > [ 11.281264] RDX: 0000000000004f4e RSI: 0000000000000001 RDI: 0000000000000000 > [ 11.281624] RBP: ffff88027f1f7f98 R08: 0000000000000001 R09: ffffffff802509af > [ 11.281925] R10: ffff8800280c2780 R11: 0000000000000000 R12: ffff88027f097d48 > [ 11.282214] R13: ffff88027f097d70 R14: 0000000000000005 R15: ffff88027e571000 > [ 11.282502] FS: 0000000000000000(0000) GS:ffff88027f1c3340(0000) knlGS:0000000000000000 > [ 11.283096] CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b > [ 11.283382] CR2: ffff8802ffffffff CR3: 0000000000201000 CR4: 00000000000006e0 > [ 11.283760] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 11.284048] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > [ 11.284337] Process swapper (pid: 0, threadinfo ffff88027f1f2000, task ffff88027f1f0640) > [ 11.284936] Stack: ffffffff80250963 0000000000000212 0000000000ee8c78 0000000000ee8a66 > [ 11.285802] ffff88027e571550 ffff88027f1f7fa8 ffffffff8021adb5 ffff88027f1f3e40 > [ 11.286599] ffffffff8020bdd6 ffff88027f1f3e40 <EOI> ffff88027f1f3ef8 0000000000000000 > [ 11.287120] Call Trace: > [ 11.287768] <IRQ> [<ffffffff80250963>] ? generic_smp_call_function_interrupt+0x61/0x12c > [ 11.288354] [<ffffffff8021adb5>] smp_call_function_interrupt+0x17/0x27 > [ 11.288744] [<ffffffff8020bdd6>] call_function_interrupt+0x66/0x70 > [ 11.289030] <EOI> [<ffffffff8024ab3b>] ? clockevents_notify+0x19/0x73 > [ 11.289380] [<ffffffff803b9b75>] ? acpi_idle_enter_simple+0x18b/0x1fa > [ 11.289760] [<ffffffff803b9b6b>] ? acpi_idle_enter_simple+0x181/0x1fa > [ 11.290051] [<ffffffff8053aeca>] ? cpuidle_idle_call+0x70/0xa2 > [ 11.290338] [<ffffffff80209f61>] ? cpu_idle+0x5f/0x7d > [ 11.290723] [<ffffffff8060224a>] ? start_secondary+0x14d/0x152 > [ 11.291010] > [ 11.291287] > [ 11.291654] Code: Bad RIP value. > [ 11.292041] RIP [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.292380] RSP <ffff88027f1f7f70> > [ 11.292741] CR2: ffff8802ffffffff > [ 11.310951] ---[ end trace 137c54d525305f1c ]--- > > The problem is with the following sequence of events: > > - CPU A calls smp_call_function_mask() for CPU B with wait parameter > - CPU A sets up the call_function_data on the stack and does an rcu add to > call_function_queue > - CPU A waits until the WAIT flag is cleared > - CPU B gets the call function interrupt and starts going through the > call_function_queue > - CPU C also gets some other call function interrupt and starts going through > the call_function_queue > - CPU C, which is also going through the call_function_queue, starts referencing > CPU A's stack, as that element is still in call_function_queue > - CPU B finishes the function call that CPU A set up and as there are no other > references to it, rcu deletes the call_function_data (which was from CPU A > stack) > - CPU B sees the wait flag and just clears the flag (no call_rcu to free) > - CPU A which was waiting on the flag continues executing and the stack > contents change > > - CPU C is still in rcu_read section accessing the CPU A's stack sees > inconsistent call_funation_data and can try to execute > function with some random pointer, causing stack corruption for A > (by clearing the bits in mask field) and oops. Nice debugging work. I'd suggest something like the attached (boot tested) patch as the simple fix for now. I expect the benefits from the less synchronized, multiple-in-flight-data global queue will still outweigh the costs of dynamic allocations. But if worst comes to worst then we just go back to a globally synchronous one-at-a-time implementation, but that would be pretty sad! Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-11 03:49:30 +00:00
slowpath = 1;
}
spin_lock_init(&data->lock);
data->csd.func = func;
data->csd.info = info;
data->refs = num_cpus;
data->cpumask = mask;
spin_lock_irqsave(&call_function_lock, flags);
list_add_tail_rcu(&data->csd.list, &call_function_queue);
spin_unlock_irqrestore(&call_function_lock, flags);
/* Send a message to all CPUs in the map */
arch_send_call_function_ipi(mask);
/* optionally wait for the CPUs to complete */
generic-ipi: fix stack and rcu interaction bug in smp_call_function_mask() * Venki Pallipadi <venkatesh.pallipadi@intel.com> wrote: > Found a OOPS on a big SMP box during an overnight reboot test with > upstream git. > > Suresh and I looked at the oops and looks like the root cause is in > generic_smp_call_function_interrupt() and smp_call_function_mask() with > wait parameter. > > The actual oops looked like > > [ 11.277260] BUG: unable to handle kernel paging request at ffff8802ffffffff > [ 11.277815] IP: [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.278155] PGD 202063 PUD 0 > [ 11.278576] Oops: 0010 [1] SMP > [ 11.279006] CPU 5 > [ 11.279336] Modules linked in: > [ 11.279752] Pid: 0, comm: swapper Not tainted 2.6.27-rc2-00020-g685d87f #290 > [ 11.280039] RIP: 0010:[<ffff8802ffffffff>] [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.280692] RSP: 0018:ffff88027f1f7f70 EFLAGS: 00010086 > [ 11.280976] RAX: 00000000ffffffff RBX: 0000000000000000 RCX: 0000000000000000 > [ 11.281264] RDX: 0000000000004f4e RSI: 0000000000000001 RDI: 0000000000000000 > [ 11.281624] RBP: ffff88027f1f7f98 R08: 0000000000000001 R09: ffffffff802509af > [ 11.281925] R10: ffff8800280c2780 R11: 0000000000000000 R12: ffff88027f097d48 > [ 11.282214] R13: ffff88027f097d70 R14: 0000000000000005 R15: ffff88027e571000 > [ 11.282502] FS: 0000000000000000(0000) GS:ffff88027f1c3340(0000) knlGS:0000000000000000 > [ 11.283096] CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b > [ 11.283382] CR2: ffff8802ffffffff CR3: 0000000000201000 CR4: 00000000000006e0 > [ 11.283760] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 11.284048] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > [ 11.284337] Process swapper (pid: 0, threadinfo ffff88027f1f2000, task ffff88027f1f0640) > [ 11.284936] Stack: ffffffff80250963 0000000000000212 0000000000ee8c78 0000000000ee8a66 > [ 11.285802] ffff88027e571550 ffff88027f1f7fa8 ffffffff8021adb5 ffff88027f1f3e40 > [ 11.286599] ffffffff8020bdd6 ffff88027f1f3e40 <EOI> ffff88027f1f3ef8 0000000000000000 > [ 11.287120] Call Trace: > [ 11.287768] <IRQ> [<ffffffff80250963>] ? generic_smp_call_function_interrupt+0x61/0x12c > [ 11.288354] [<ffffffff8021adb5>] smp_call_function_interrupt+0x17/0x27 > [ 11.288744] [<ffffffff8020bdd6>] call_function_interrupt+0x66/0x70 > [ 11.289030] <EOI> [<ffffffff8024ab3b>] ? clockevents_notify+0x19/0x73 > [ 11.289380] [<ffffffff803b9b75>] ? acpi_idle_enter_simple+0x18b/0x1fa > [ 11.289760] [<ffffffff803b9b6b>] ? acpi_idle_enter_simple+0x181/0x1fa > [ 11.290051] [<ffffffff8053aeca>] ? cpuidle_idle_call+0x70/0xa2 > [ 11.290338] [<ffffffff80209f61>] ? cpu_idle+0x5f/0x7d > [ 11.290723] [<ffffffff8060224a>] ? start_secondary+0x14d/0x152 > [ 11.291010] > [ 11.291287] > [ 11.291654] Code: Bad RIP value. > [ 11.292041] RIP [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.292380] RSP <ffff88027f1f7f70> > [ 11.292741] CR2: ffff8802ffffffff > [ 11.310951] ---[ end trace 137c54d525305f1c ]--- > > The problem is with the following sequence of events: > > - CPU A calls smp_call_function_mask() for CPU B with wait parameter > - CPU A sets up the call_function_data on the stack and does an rcu add to > call_function_queue > - CPU A waits until the WAIT flag is cleared > - CPU B gets the call function interrupt and starts going through the > call_function_queue > - CPU C also gets some other call function interrupt and starts going through > the call_function_queue > - CPU C, which is also going through the call_function_queue, starts referencing > CPU A's stack, as that element is still in call_function_queue > - CPU B finishes the function call that CPU A set up and as there are no other > references to it, rcu deletes the call_function_data (which was from CPU A > stack) > - CPU B sees the wait flag and just clears the flag (no call_rcu to free) > - CPU A which was waiting on the flag continues executing and the stack > contents change > > - CPU C is still in rcu_read section accessing the CPU A's stack sees > inconsistent call_funation_data and can try to execute > function with some random pointer, causing stack corruption for A > (by clearing the bits in mask field) and oops. Nice debugging work. I'd suggest something like the attached (boot tested) patch as the simple fix for now. I expect the benefits from the less synchronized, multiple-in-flight-data global queue will still outweigh the costs of dynamic allocations. But if worst comes to worst then we just go back to a globally synchronous one-at-a-time implementation, but that would be pretty sad! Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-11 03:49:30 +00:00
if (wait) {
csd_flag_wait(&data->csd);
generic-ipi: fix stack and rcu interaction bug in smp_call_function_mask() * Venki Pallipadi <venkatesh.pallipadi@intel.com> wrote: > Found a OOPS on a big SMP box during an overnight reboot test with > upstream git. > > Suresh and I looked at the oops and looks like the root cause is in > generic_smp_call_function_interrupt() and smp_call_function_mask() with > wait parameter. > > The actual oops looked like > > [ 11.277260] BUG: unable to handle kernel paging request at ffff8802ffffffff > [ 11.277815] IP: [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.278155] PGD 202063 PUD 0 > [ 11.278576] Oops: 0010 [1] SMP > [ 11.279006] CPU 5 > [ 11.279336] Modules linked in: > [ 11.279752] Pid: 0, comm: swapper Not tainted 2.6.27-rc2-00020-g685d87f #290 > [ 11.280039] RIP: 0010:[<ffff8802ffffffff>] [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.280692] RSP: 0018:ffff88027f1f7f70 EFLAGS: 00010086 > [ 11.280976] RAX: 00000000ffffffff RBX: 0000000000000000 RCX: 0000000000000000 > [ 11.281264] RDX: 0000000000004f4e RSI: 0000000000000001 RDI: 0000000000000000 > [ 11.281624] RBP: ffff88027f1f7f98 R08: 0000000000000001 R09: ffffffff802509af > [ 11.281925] R10: ffff8800280c2780 R11: 0000000000000000 R12: ffff88027f097d48 > [ 11.282214] R13: ffff88027f097d70 R14: 0000000000000005 R15: ffff88027e571000 > [ 11.282502] FS: 0000000000000000(0000) GS:ffff88027f1c3340(0000) knlGS:0000000000000000 > [ 11.283096] CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b > [ 11.283382] CR2: ffff8802ffffffff CR3: 0000000000201000 CR4: 00000000000006e0 > [ 11.283760] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 11.284048] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > [ 11.284337] Process swapper (pid: 0, threadinfo ffff88027f1f2000, task ffff88027f1f0640) > [ 11.284936] Stack: ffffffff80250963 0000000000000212 0000000000ee8c78 0000000000ee8a66 > [ 11.285802] ffff88027e571550 ffff88027f1f7fa8 ffffffff8021adb5 ffff88027f1f3e40 > [ 11.286599] ffffffff8020bdd6 ffff88027f1f3e40 <EOI> ffff88027f1f3ef8 0000000000000000 > [ 11.287120] Call Trace: > [ 11.287768] <IRQ> [<ffffffff80250963>] ? generic_smp_call_function_interrupt+0x61/0x12c > [ 11.288354] [<ffffffff8021adb5>] smp_call_function_interrupt+0x17/0x27 > [ 11.288744] [<ffffffff8020bdd6>] call_function_interrupt+0x66/0x70 > [ 11.289030] <EOI> [<ffffffff8024ab3b>] ? clockevents_notify+0x19/0x73 > [ 11.289380] [<ffffffff803b9b75>] ? acpi_idle_enter_simple+0x18b/0x1fa > [ 11.289760] [<ffffffff803b9b6b>] ? acpi_idle_enter_simple+0x181/0x1fa > [ 11.290051] [<ffffffff8053aeca>] ? cpuidle_idle_call+0x70/0xa2 > [ 11.290338] [<ffffffff80209f61>] ? cpu_idle+0x5f/0x7d > [ 11.290723] [<ffffffff8060224a>] ? start_secondary+0x14d/0x152 > [ 11.291010] > [ 11.291287] > [ 11.291654] Code: Bad RIP value. > [ 11.292041] RIP [<ffff8802ffffffff>] 0xffff8802ffffffff > [ 11.292380] RSP <ffff88027f1f7f70> > [ 11.292741] CR2: ffff8802ffffffff > [ 11.310951] ---[ end trace 137c54d525305f1c ]--- > > The problem is with the following sequence of events: > > - CPU A calls smp_call_function_mask() for CPU B with wait parameter > - CPU A sets up the call_function_data on the stack and does an rcu add to > call_function_queue > - CPU A waits until the WAIT flag is cleared > - CPU B gets the call function interrupt and starts going through the > call_function_queue > - CPU C also gets some other call function interrupt and starts going through > the call_function_queue > - CPU C, which is also going through the call_function_queue, starts referencing > CPU A's stack, as that element is still in call_function_queue > - CPU B finishes the function call that CPU A set up and as there are no other > references to it, rcu deletes the call_function_data (which was from CPU A > stack) > - CPU B sees the wait flag and just clears the flag (no call_rcu to free) > - CPU A which was waiting on the flag continues executing and the stack > contents change > > - CPU C is still in rcu_read section accessing the CPU A's stack sees > inconsistent call_funation_data and can try to execute > function with some random pointer, causing stack corruption for A > (by clearing the bits in mask field) and oops. Nice debugging work. I'd suggest something like the attached (boot tested) patch as the simple fix for now. I expect the benefits from the less synchronized, multiple-in-flight-data global queue will still outweigh the costs of dynamic allocations. But if worst comes to worst then we just go back to a globally synchronous one-at-a-time implementation, but that would be pretty sad! Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-11 03:49:30 +00:00
if (unlikely(slowpath))
smp_call_function_mask_quiesce_stack(allbutself);
}
return 0;
}
EXPORT_SYMBOL(smp_call_function_mask);
/**
* smp_call_function(): Run a function on all other CPUs.
* @func: The function to run. This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to the function.
* @wait: If true, wait (atomically) until function has completed on other CPUs.
*
* Returns 0 on success, else a negative status code.
*
* If @wait is true, then returns once @func has returned; otherwise
* it returns just before the target cpu calls @func. In case of allocation
* failure, @wait will be implicitly turned on.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler.
*/
int smp_call_function(void (*func)(void *), void *info, int wait)
{
int ret;
preempt_disable();
ret = smp_call_function_mask(cpu_online_map, func, info, wait);
preempt_enable();
return ret;
}
EXPORT_SYMBOL(smp_call_function);
void ipi_call_lock(void)
{
spin_lock(&call_function_lock);
}
void ipi_call_unlock(void)
{
spin_unlock(&call_function_lock);
}
void ipi_call_lock_irq(void)
{
spin_lock_irq(&call_function_lock);
}
void ipi_call_unlock_irq(void)
{
spin_unlock_irq(&call_function_lock);
}