This issue is introduced in commit 27f6c573e0. I forget to
execute put_cpu_var operation after get_cpu_var.
Signed-off-by: Chen, Gong <[email protected]>
---
arch/x86/kernel/cpu/mcheck/mce.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index eeee23f..26eaf3b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -620,6 +620,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
v = &get_cpu_var(mce_polled_error);
set_bit(0, v);
+ put_cpu_var(mce_polled_error);
/*
* Uncorrected or signalled events are handled by the exception
* handler when it is enabled, so don't process those here.
--
1.9.0
According to Peter's suggestion, use this_cpu_* instead of
__get_cpu_var. BTW, remove bitmask ops to avoid unnecessary
overhead.
Signed-off-by: Chen, Gong <[email protected]>
Suggested-by: H. Peter Anvin <[email protected]>
---
arch/x86/kernel/cpu/mcheck/mce.c | 36 ++++++++++++++++++------------------
1 file changed, 18 insertions(+), 18 deletions(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 26eaf3b..a44506e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -402,7 +402,7 @@ static u64 mce_rdmsrl(u32 msr)
if (offset < 0)
return 0;
- return *(u64 *)((char *)&__get_cpu_var(injectm) + offset);
+ return *(u64 *)((char *)this_cpu_ptr(&injectm) + offset);
}
if (rdmsrl_safe(msr, &v)) {
@@ -424,7 +424,7 @@ static void mce_wrmsrl(u32 msr, u64 v)
int offset = msr_to_offset(msr);
if (offset >= 0)
- *(u64 *)((char *)&__get_cpu_var(injectm) + offset) = v;
+ *(u64 *)((char *)this_cpu_ptr(&injectm) + offset) = v;
return;
}
wrmsrl(msr, v);
@@ -480,7 +480,7 @@ static DEFINE_PER_CPU(struct mce_ring, mce_ring);
/* Runs with CPU affinity in workqueue */
static int mce_ring_empty(void)
{
- struct mce_ring *r = &__get_cpu_var(mce_ring);
+ struct mce_ring *r = this_cpu_ptr(&mce_ring);
return r->start == r->end;
}
@@ -492,7 +492,7 @@ static int mce_ring_get(unsigned long *pfn)
*pfn = 0;
get_cpu();
- r = &__get_cpu_var(mce_ring);
+ r = this_cpu_ptr(&mce_ring);
if (r->start == r->end)
goto out;
*pfn = r->ring[r->start];
@@ -506,7 +506,7 @@ out:
/* Always runs in MCE context with preempt off */
static int mce_ring_add(unsigned long pfn)
{
- struct mce_ring *r = &__get_cpu_var(mce_ring);
+ struct mce_ring *r = this_cpu_ptr(&mce_ring);
unsigned next;
next = (r->end + 1) % MCE_RING_SIZE;
@@ -528,7 +528,7 @@ int mce_available(struct cpuinfo_x86 *c)
static void mce_schedule_work(void)
{
if (!mce_ring_empty())
- schedule_work(&__get_cpu_var(mce_work));
+ schedule_work(this_cpu_ptr(&mce_work));
}
DEFINE_PER_CPU(struct irq_work, mce_irq_work);
@@ -553,7 +553,7 @@ static void mce_report_event(struct pt_regs *regs)
return;
}
- irq_work_queue(&__get_cpu_var(mce_irq_work));
+ irq_work_queue(this_cpu_ptr(&mce_irq_work));
}
/*
@@ -619,7 +619,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
continue;
v = &get_cpu_var(mce_polled_error);
- set_bit(0, v);
+ *v = 1;
put_cpu_var(mce_polled_error);
/*
* Uncorrected or signalled events are handled by the exception
@@ -1053,7 +1053,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
mce_gather_info(&m, regs);
- final = &__get_cpu_var(mces_seen);
+ final = this_cpu_ptr(&mces_seen);
*final = m;
memset(valid_banks, 0, sizeof(valid_banks));
@@ -1287,14 +1287,14 @@ static unsigned long (*mce_adjust_timer)(unsigned long interval) =
static int cmc_error_seen(void)
{
- unsigned long *v = &__get_cpu_var(mce_polled_error);
+ unsigned long *v = this_cpu_ptr(&mce_polled_error);
- return test_and_clear_bit(0, v);
+ return this_cpu_xchg(*v, 0);
}
static void mce_timer_fn(unsigned long data)
{
- struct timer_list *t = &__get_cpu_var(mce_timer);
+ struct timer_list *t = this_cpu_ptr(&mce_timer);
unsigned long iv;
int notify;
@@ -1302,7 +1302,7 @@ static void mce_timer_fn(unsigned long data)
if (mce_available(__this_cpu_ptr(&cpu_info))) {
machine_check_poll(MCP_TIMESTAMP,
- &__get_cpu_var(mce_poll_banks));
+ this_cpu_ptr(&mce_poll_banks));
mce_intel_cmci_poll();
}
@@ -1332,7 +1332,7 @@ static void mce_timer_fn(unsigned long data)
*/
void mce_timer_kick(unsigned long interval)
{
- struct timer_list *t = &__get_cpu_var(mce_timer);
+ struct timer_list *t = this_cpu_ptr(&mce_timer);
unsigned long when = jiffies + interval;
unsigned long iv = __this_cpu_read(mce_next_interval);
@@ -1668,7 +1668,7 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t)
static void __mcheck_cpu_init_timer(void)
{
- struct timer_list *t = &__get_cpu_var(mce_timer);
+ struct timer_list *t = this_cpu_ptr(&mce_timer);
unsigned int cpu = smp_processor_id();
setup_timer(t, mce_timer_fn, cpu);
@@ -1711,8 +1711,8 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(c);
__mcheck_cpu_init_timer();
- INIT_WORK(&__get_cpu_var(mce_work), mce_process_work);
- init_irq_work(&__get_cpu_var(mce_irq_work), &mce_irq_work_cb);
+ INIT_WORK(this_cpu_ptr(&mce_work), mce_process_work);
+ init_irq_work(this_cpu_ptr(&mce_irq_work), &mce_irq_work_cb);
}
/*
@@ -1964,7 +1964,7 @@ static struct miscdevice mce_chrdev_device = {
static void __mce_disable_bank(void *arg)
{
int bank = *((int *)arg);
- __clear_bit(bank, __get_cpu_var(mce_poll_banks));
+ __clear_bit(bank, *this_cpu_ptr(&mce_poll_banks));
cmci_disable_bank(bank);
}
--
1.9.0
On 04/14/2014 01:39 AM, Chen, Gong wrote:
> @@ -619,7 +619,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
> continue;
>
> v = &get_cpu_var(mce_polled_error);
> - set_bit(0, v);
> + *v = 1;
> put_cpu_var(mce_polled_error);
> /*
> * Uncorrected or signalled events are handled by the exception
The amazing thing is that you managed to miss the one place where you
could actively elide a pointer.
The above should simply be:
this_cpu_write(mce_polled_error, 1);
-hpa
On 04/14/2014 01:39 AM, Chen, Gong wrote:
> @@ -1287,14 +1287,14 @@ static unsigned long (*mce_adjust_timer)(unsigned long interval) =
>
> static int cmc_error_seen(void)
> {
> - unsigned long *v = &__get_cpu_var(mce_polled_error);
> + unsigned long *v = this_cpu_ptr(&mce_polled_error);
>
> - return test_and_clear_bit(0, v);
> + return this_cpu_xchg(*v, 0);
> }
>
Here you produce a pointer and *then* passing it through a this_cpu_
function... this is actively wrong.
It should simply be:
return this_cpu_xchg(mce_polled_error, 0);
-hpa
Please read Documentation/this_cpu_ops.txt for reference for how to use
these functions. However, you want to avoid forming a pointer if you
can; it is relatively expensive to do so.
-hpa
On Mon, Apr 14, 2014 at 09:23:08AM -0700, H. Peter Anvin wrote:
> Please read Documentation/this_cpu_ops.txt for reference for how to use
> these functions. However, you want to avoid forming a pointer if you
> can; it is relatively expensive to do so.
>
:-). I just found your comment yesterday so that I was eager to finish it.
I should do more homework as you told and send it again. Thanks very much
for your patience.