Signed-off-by: Alan D. Brunelle <[email protected]>
---
arch/ia64/kernel/smp.c | 8 ++++++--
arch/x86/kernel/smp_32.c | 8 ++++++--
arch/x86/kernel/smp_64.c | 8 ++++++--
include/linux/smp.h | 1 +
kernel/smp.c | 34 ++++++++++++++++++++--------------
5 files changed, 39 insertions(+), 20 deletions(-)
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index 04ba9f8..52225bb 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -364,7 +364,8 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
{
struct call_single_queue *dst;
unsigned long flags;
- int ipi, wait_done = data->flags & CSD_FLAG_WAIT;
+ int ipi = 0;
+ int wait_done = data->flags & CSD_FLAG_WAIT;
/* Can deadlock when called with interrupts disabled */
WARN_ON((data->flags & CSD_FLAG_WAIT) && irqs_disabled());
@@ -373,8 +374,11 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
dst = &per_cpu(call_single_queue, cpu);
spin_lock_irqsave(&dst->lock, flags);
- ipi = list_empty(&dst->list);
list_add_tail(&data->list, &dst->list);
+ if (!dst->activated) {
+ dst->activated = 1;
+ ipi = 1;
+ }
spin_unlock_irqrestore(&dst->lock, flags);
if (ipi)
diff --git a/arch/x86/kernel/smp_32.c b/arch/x86/kernel/smp_32.c
index be0f6cb..d166f13 100644
--- a/arch/x86/kernel/smp_32.c
+++ b/arch/x86/kernel/smp_32.c
@@ -629,7 +629,8 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
cpumask_t mask = cpumask_of_cpu(cpu);
struct call_single_queue *dst;
unsigned long flags;
- int ipi, wait_done = data->flags & CSD_FLAG_WAIT;
+ int ipi = 0;
+ int wait_done = data->flags & CSD_FLAG_WAIT;
/* Can deadlock when called with interrupts disabled */
WARN_ON((data->flags & CSD_FLAG_WAIT) && irqs_disabled());
@@ -638,8 +639,11 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
dst = &per_cpu(call_single_queue, cpu);
spin_lock_irqsave(&dst->lock, flags);
- ipi = list_empty(&dst->list);
list_add_tail(&data->list, &dst->list);
+ if (!dst->activated) {
+ dst->activated = 1;
+ ipi = 1;
+ }
spin_unlock_irqrestore(&dst->lock, flags);
if (ipi)
diff --git a/arch/x86/kernel/smp_64.c b/arch/x86/kernel/smp_64.c
index 5bef2a6..fbfcdce 100644
--- a/arch/x86/kernel/smp_64.c
+++ b/arch/x86/kernel/smp_64.c
@@ -449,7 +449,8 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
cpumask_t mask = cpumask_of_cpu(cpu);
struct call_single_queue *dst;
unsigned long flags;
- int ipi, wait_done = data->flags & CSD_FLAG_WAIT;
+ int ipi = 0;
+ int wait_done = data->flags & CSD_FLAG_WAIT;
/* Can deadlock when called with interrupts disabled */
WARN_ON((data->flags & CSD_FLAG_WAIT) && irqs_disabled());
@@ -458,8 +459,11 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
dst = &per_cpu(call_single_queue, cpu);
spin_lock_irqsave(&dst->lock, flags);
- ipi = list_empty(&dst->list);
list_add_tail(&data->list, &dst->list);
+ if (!dst->activated) {
+ dst->activated = 1;
+ ipi = 1;
+ }
spin_unlock_irqrestore(&dst->lock, flags);
if (ipi)
diff --git a/include/linux/smp.h b/include/linux/smp.h
index c471d77..1e96f03 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -65,6 +65,7 @@ extern void smp_cpus_done(unsigned int max_cpus);
struct call_single_queue {
spinlock_t lock;
struct list_head list;
+ int activated;
};
/*
diff --git a/kernel/smp.c b/kernel/smp.c
index 7232e1c..f7ec401 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -23,28 +23,34 @@ void __cpuinit generic_init_call_single_data(void)
void generic_smp_call_function_single_interrupt(void)
{
- struct call_single_queue *q;
unsigned long flags;
LIST_HEAD(list);
+ struct call_single_queue *q = &__get_cpu_var(call_single_queue);
- q = &__get_cpu_var(call_single_queue);
spin_lock_irqsave(&q->lock, flags);
- list_replace_init(&q->list, &list);
- spin_unlock_irqrestore(&q->lock, flags);
+ while (!list_empty(&q->list)) {
+ list_replace_init(&q->list, &list);
+ spin_unlock_irqrestore(&q->lock, flags);
- while (!list_empty(&list)) {
- struct call_single_data *data;
+ do {
+ struct call_single_data *data;
- data = list_entry(list.next, struct call_single_data, list);
- list_del(&data->list);
+ data = list_entry(list.next, struct call_single_data,
+ list);
+ list_del(&data->list);
- data->func(data->info);
- if (data->flags & CSD_FLAG_WAIT) {
- smp_wmb();
- data->flags = 0;
- } else if (data->flags & CSD_FLAG_ALLOC)
- kfree(data);
+ data->func(data->info);
+ if (data->flags & CSD_FLAG_WAIT) {
+ smp_wmb();
+ data->flags = 0;
+ } else if (data->flags & CSD_FLAG_ALLOC)
+ kfree(data);
+ } while (!list_empty(&list));
+
+ spin_lock_irqsave(&q->lock, flags);
}
+ q->activated = 0;
+ spin_unlock_irqrestore(&q->lock, flags);
}
int generic_smp_call_function_single(int cpu, void (*func) (void *info),
--
1.5.2.5
On Mon, Mar 17 2008, Alan D. Brunelle wrote:
> diff --git a/kernel/smp.c b/kernel/smp.c
> index 7232e1c..f7ec401 100644
> --- a/kernel/smp.c
> +++ b/kernel/smp.c
> @@ -23,28 +23,34 @@ void __cpuinit generic_init_call_single_data(void)
>
> void generic_smp_call_function_single_interrupt(void)
> {
> - struct call_single_queue *q;
> unsigned long flags;
> LIST_HEAD(list);
> + struct call_single_queue *q = &__get_cpu_var(call_single_queue);
>
> - q = &__get_cpu_var(call_single_queue);
> spin_lock_irqsave(&q->lock, flags);
> - list_replace_init(&q->list, &list);
> - spin_unlock_irqrestore(&q->lock, flags);
> + while (!list_empty(&q->list)) {
> + list_replace_init(&q->list, &list);
> + spin_unlock_irqrestore(&q->lock, flags);
>
> - while (!list_empty(&list)) {
> - struct call_single_data *data;
> + do {
> + struct call_single_data *data;
>
> - data = list_entry(list.next, struct call_single_data, list);
> - list_del(&data->list);
> + data = list_entry(list.next, struct call_single_data,
> + list);
> + list_del(&data->list);
>
> - data->func(data->info);
> - if (data->flags & CSD_FLAG_WAIT) {
> - smp_wmb();
> - data->flags = 0;
> - } else if (data->flags & CSD_FLAG_ALLOC)
> - kfree(data);
> + data->func(data->info);
> + if (data->flags & CSD_FLAG_WAIT) {
> + smp_wmb();
> + data->flags = 0;
> + } else if (data->flags & CSD_FLAG_ALLOC)
> + kfree(data);
> + } while (!list_empty(&list));
> +
> + spin_lock_irqsave(&q->lock, flags);
> }
> + q->activated = 0;
> + spin_unlock_irqrestore(&q->lock, flags);
> }
I agree with doing it this way, re-checking and doing another run (or
more). However I think we can improve it a bit so we don't always have
to grab the dst lock at least twice - it should be safe enough to
include the lock only inside the first loop, doing an smp_mb() before
the list_empty() check and again at the bottom before looping around and
doing the list_empty() check again.
I've rolled a new patch series here:
http://git.kernel.dk/?p=linux-2.6-block.git;a=shortlog;h=io-cpu-affinity
(or just pull the io-cpu-affinity branch), it also includes a bunch of
other cleanups like porting the faster smp_call_function() to ia64 and
powerpc as well. So the kernel/smp.c generic helpers have grown a bit,
while the arch bits are smaller.
I'm curious if it now boots on ia64, since I killed the hack to manually
call the __init manually there. If you could check, I would appreciate
it ;-)
I've built all 4 supported archs and they compile and link fine, but
nothing has been booted yet.
--
Jens Axboe
On Mon, Mar 17 2008, Jens Axboe wrote:
> On Mon, Mar 17 2008, Alan D. Brunelle wrote:
> > diff --git a/kernel/smp.c b/kernel/smp.c
> > index 7232e1c..f7ec401 100644
> > --- a/kernel/smp.c
> > +++ b/kernel/smp.c
> > @@ -23,28 +23,34 @@ void __cpuinit generic_init_call_single_data(void)
> >
> > void generic_smp_call_function_single_interrupt(void)
> > {
> > - struct call_single_queue *q;
> > unsigned long flags;
> > LIST_HEAD(list);
> > + struct call_single_queue *q = &__get_cpu_var(call_single_queue);
> >
> > - q = &__get_cpu_var(call_single_queue);
> > spin_lock_irqsave(&q->lock, flags);
> > - list_replace_init(&q->list, &list);
> > - spin_unlock_irqrestore(&q->lock, flags);
> > + while (!list_empty(&q->list)) {
> > + list_replace_init(&q->list, &list);
> > + spin_unlock_irqrestore(&q->lock, flags);
> >
> > - while (!list_empty(&list)) {
> > - struct call_single_data *data;
> > + do {
> > + struct call_single_data *data;
> >
> > - data = list_entry(list.next, struct call_single_data, list);
> > - list_del(&data->list);
> > + data = list_entry(list.next, struct call_single_data,
> > + list);
> > + list_del(&data->list);
> >
> > - data->func(data->info);
> > - if (data->flags & CSD_FLAG_WAIT) {
> > - smp_wmb();
> > - data->flags = 0;
> > - } else if (data->flags & CSD_FLAG_ALLOC)
> > - kfree(data);
> > + data->func(data->info);
> > + if (data->flags & CSD_FLAG_WAIT) {
> > + smp_wmb();
> > + data->flags = 0;
> > + } else if (data->flags & CSD_FLAG_ALLOC)
> > + kfree(data);
> > + } while (!list_empty(&list));
> > +
> > + spin_lock_irqsave(&q->lock, flags);
> > }
> > + q->activated = 0;
> > + spin_unlock_irqrestore(&q->lock, flags);
> > }
>
> I agree with doing it this way, re-checking and doing another run (or
> more). However I think we can improve it a bit so we don't always have
> to grab the dst lock at least twice - it should be safe enough to
> include the lock only inside the first loop, doing an smp_mb() before
> the list_empty() check and again at the bottom before looping around and
> doing the list_empty() check again.
>
> I've rolled a new patch series here:
>
> http://git.kernel.dk/?p=linux-2.6-block.git;a=shortlog;h=io-cpu-affinity
>
> (or just pull the io-cpu-affinity branch), it also includes a bunch of
> other cleanups like porting the faster smp_call_function() to ia64 and
> powerpc as well. So the kernel/smp.c generic helpers have grown a bit,
> while the arch bits are smaller.
>
> I'm curious if it now boots on ia64, since I killed the hack to manually
> call the __init manually there. If you could check, I would appreciate
> it ;-)
>
> I've built all 4 supported archs and they compile and link fine, but
> nothing has been booted yet.
x86 and x86-64 boot just fine, so powerpc should work as well (will do
performance testing on a 4-way ppc tomorrow). ia64 should also work, as
long as the init_call_single_data() gets called correctly.
If it doesn't work on tha ia64, try and change the core_initcall() to a
postcore_initcall() or even an arch_initcall(). It now resides in
kernel/smp.c.
--
Jens Axboe