Re: [PATCH v5 10/12] Handle async PF in non preemptable context

From: Gleb Natapov
Date: Tue Aug 24 2010 - 05:37:32 EST


On Tue, Aug 24, 2010 at 12:30:25PM +0300, Avi Kivity wrote:
> On 07/19/2010 06:31 PM, Gleb Natapov wrote:
> >If async page fault is received by idle task or when preemp_count is
> >not zero guest cannot reschedule, so do sti; hlt and wait for page to be
> >ready. vcpu can still process interrupts while it waits for the page to
> >be ready.
> >
> >Acked-by: Rik van Riel<riel@xxxxxxxxxx>
> >Signed-off-by: Gleb Natapov<gleb@xxxxxxxxxx>
> >---
> > arch/x86/kernel/kvm.c | 36 ++++++++++++++++++++++++++++++++----
> > 1 files changed, 32 insertions(+), 4 deletions(-)
> >
> >diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
> >index a6db92e..914b0fc 100644
> >--- a/arch/x86/kernel/kvm.c
> >+++ b/arch/x86/kernel/kvm.c
> >@@ -37,6 +37,7 @@
> > #include<asm/cpu.h>
> > #include<asm/traps.h>
> > #include<asm/desc.h>
> >+#include<asm/tlbflush.h>
> >
> > #define MMU_QUEUE_SIZE 1024
> >
> >@@ -68,6 +69,8 @@ struct kvm_task_sleep_node {
> > wait_queue_head_t wq;
> > u32 token;
> > int cpu;
> >+ bool halted;
> >+ struct mm_struct *mm;
> > };
> >
> > static struct kvm_task_sleep_head {
> >@@ -96,6 +99,11 @@ static void apf_task_wait(struct task_struct *tsk, u32 token)
> > struct kvm_task_sleep_head *b =&async_pf_sleepers[key];
> > struct kvm_task_sleep_node n, *e;
> > DEFINE_WAIT(wait);
> >+ int cpu, idle;
> >+
> >+ cpu = get_cpu();
> >+ idle = idle_cpu(cpu);
> >+ put_cpu();
> >
> > spin_lock(&b->lock);
> > e = _find_apf_task(b, token);
> >@@ -109,17 +117,31 @@ static void apf_task_wait(struct task_struct *tsk, u32 token)
> >
> > n.token = token;
> > n.cpu = smp_processor_id();
> >+ n.mm = current->active_mm;
> >+ n.halted = idle || preempt_count()> 1;
> >+ atomic_inc(&n.mm->mm_count);
> > init_waitqueue_head(&n.wq);
> > hlist_add_head(&n.link,&b->list);
> > spin_unlock(&b->lock);
> >
> > for (;;) {
> >- prepare_to_wait(&n.wq,&wait, TASK_UNINTERRUPTIBLE);
> >+ if (!n.halted)
> >+ prepare_to_wait(&n.wq,&wait, TASK_UNINTERRUPTIBLE);
> > if (hlist_unhashed(&n.link))
> > break;
> >- schedule();
> >+
> >+ if (!n.halted) {
> >+ schedule();
> >+ } else {
> >+ /*
> >+ * We cannot reschedule. So halt.
> >+ */
>
> If we get the wakeup here, we'll halt and never wake up again.
>
We will not. IRQs are disabled here. native_safe_halt() enables them.

> >+ native_safe_halt();
> >+ local_irq_disable();
>
> So we need a local_irq_disable() before the hlish_unhashed() check.
We are still in exception handler, so IRQ should be off.

>
> >+ }
> > }
> >- finish_wait(&n.wq,&wait);
> >+ if (!n.halted)
> >+ finish_wait(&n.wq,&wait);
> >
> > return;
> > }
> >@@ -127,7 +149,12 @@ static void apf_task_wait(struct task_struct *tsk, u32 token)
> > static void apf_task_wake_one(struct kvm_task_sleep_node *n)
> > {
> > hlist_del_init(&n->link);
> >- if (waitqueue_active(&n->wq))
> >+ if (!n->mm)
> >+ return;
> >+ mmdrop(n->mm);
> >+ if (n->halted)
> >+ smp_send_reschedule(n->cpu);
> >+ else if (waitqueue_active(&n->wq))
> > wake_up(&n->wq);
> > }
> >
> >@@ -157,6 +184,7 @@ again:
> > }
> > n->token = token;
> > n->cpu = smp_processor_id();
> >+ n->mm = NULL;
> > init_waitqueue_head(&n->wq);
> > hlist_add_head(&n->link,&b->list);
> > } else
>
>
> --
> error compiling committee.c: too many arguments to function

--
Gleb.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/