All of lore.kernel.org
 help / color / mirror / Atom feed
From: Gleb Natapov <gleb@redhat.com>
To: kvm@vger.kernel.org
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, avi@redhat.com,
	mingo@elte.hu, a.p.zijlstra@chello.nl, tglx@linutronix.de,
	hpa@zytor.com, riel@redhat.com, cl@linux-foundation.org,
	mtosatti@redhat.com
Subject: [PATCH v4 10/12] Handle async PF in non preemptable context
Date: Tue,  6 Jul 2010 19:24:58 +0300	[thread overview]
Message-ID: <1278433500-29884-11-git-send-email-gleb@redhat.com> (raw)
In-Reply-To: <1278433500-29884-1-git-send-email-gleb@redhat.com>

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.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 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 fa9f520..f4d87b3 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 = percpu_read(cpu_tlbstate.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.
+			 */
+			native_safe_halt();
+			local_irq_disable();
+		}
 	}
-	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
-- 
1.7.1


WARNING: multiple messages have this Message-ID (diff)
From: Gleb Natapov <gleb@redhat.com>
To: kvm@vger.kernel.org
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, avi@redhat.com,
	mingo@elte.hu, a.p.zijlstra@chello.nl, tglx@linutronix.de,
	hpa@zytor.com, riel@redhat.com, cl@linux-foundation.org,
	mtosatti@redhat.com
Subject: [PATCH v4 10/12] Handle async PF in non preemptable context
Date: Tue,  6 Jul 2010 19:24:58 +0300	[thread overview]
Message-ID: <1278433500-29884-11-git-send-email-gleb@redhat.com> (raw)
In-Reply-To: <1278433500-29884-1-git-send-email-gleb@redhat.com>

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.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 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 fa9f520..f4d87b3 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 = percpu_read(cpu_tlbstate.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.
+			 */
+			native_safe_halt();
+			local_irq_disable();
+		}
 	}
-	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
-- 
1.7.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2010-07-06 16:25 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-07-06 16:24 [PATCH v4 00/12] KVM: Add host swap event notifications for PV guest Gleb Natapov
2010-07-06 16:24 ` Gleb Natapov
2010-07-06 16:24 ` [PATCH v4 01/12] Move kvm_smp_prepare_boot_cpu() from kvmclock.c to kvm.c Gleb Natapov
2010-07-06 16:24   ` Gleb Natapov
2010-07-07 16:17   ` Rik van Riel
2010-07-07 16:17     ` Rik van Riel
2010-07-06 16:24 ` [PATCH v4 02/12] Add PV MSR to enable asynchronous page faults delivery Gleb Natapov
2010-07-06 16:24   ` Gleb Natapov
2010-07-07 18:13   ` Rik van Riel
2010-07-07 18:13     ` Rik van Riel
2010-07-06 16:24 ` [PATCH v4 03/12] Add async PF initialization to PV guest Gleb Natapov
2010-07-06 16:24   ` Gleb Natapov
2010-07-07 15:41   ` Peter Zijlstra
2010-07-07 15:41     ` Peter Zijlstra
2010-07-07 15:41     ` Peter Zijlstra
2010-07-08 13:24     ` Gleb Natapov
2010-07-08 13:24       ` Gleb Natapov
2010-07-06 16:24 ` [PATCH v4 04/12] Provide special async page fault handler when async PF capability is detected Gleb Natapov
2010-07-06 16:24   ` Gleb Natapov
2010-07-07 22:38   ` Rik van Riel
2010-07-07 22:38     ` Rik van Riel
2010-07-06 16:24 ` [PATCH v4 05/12] Export __get_user_pages_fast Gleb Natapov
2010-07-06 16:24   ` Gleb Natapov
2010-07-07 22:45   ` Rik van Riel
2010-07-07 22:45     ` Rik van Riel
2010-07-06 16:24 ` [PATCH v4 06/12] Add get_user_pages() variant that fails if major fault is required Gleb Natapov
2010-07-06 16:24   ` Gleb Natapov
2010-07-06 16:24 ` [PATCH v4 07/12] Maintain memslot version number Gleb Natapov
2010-07-06 16:24   ` Gleb Natapov
2010-07-08  0:19   ` Rik van Riel
2010-07-08  0:19     ` Rik van Riel
2010-07-06 16:24 ` [PATCH v4 08/12] Inject asynchronous page fault into a guest if page is swapped out Gleb Natapov
2010-07-06 16:24   ` Gleb Natapov
2010-07-08  4:09   ` Rik van Riel
2010-07-08  4:09     ` Rik van Riel
2010-07-08 15:59   ` Marcelo Tosatti
2010-07-08 15:59     ` Marcelo Tosatti
2010-07-08 18:05     ` Gleb Natapov
2010-07-08 18:05       ` Gleb Natapov
2010-07-08 18:09       ` Peter Zijlstra
2010-07-08 18:09         ` Peter Zijlstra
2010-07-08 18:09         ` Peter Zijlstra
2010-07-08 18:10         ` Peter Zijlstra
2010-07-08 18:10           ` Peter Zijlstra
2010-07-08 18:10           ` Peter Zijlstra
2010-07-09 15:50           ` Gleb Natapov
2010-07-09 15:50             ` Gleb Natapov
2010-07-06 16:24 ` [PATCH v4 09/12] Retry fault before vmentry Gleb Natapov
2010-07-06 16:24   ` Gleb Natapov
2010-07-08  4:21   ` Rik van Riel
2010-07-08  4:21     ` Rik van Riel
2010-07-08 16:17   ` Marcelo Tosatti
2010-07-08 16:17     ` Marcelo Tosatti
2010-07-06 16:24 ` Gleb Natapov [this message]
2010-07-06 16:24   ` [PATCH v4 10/12] Handle async PF in non preemptable context Gleb Natapov
2010-07-08  4:22   ` Rik van Riel
2010-07-08  4:22     ` Rik van Riel
2010-07-06 16:24 ` [PATCH v4 11/12] Let host know whether the guest can handle async PF in non-userspace context Gleb Natapov
2010-07-06 16:24   ` Gleb Natapov
2010-07-08  4:28   ` Rik van Riel
2010-07-08  4:28     ` Rik van Riel
2010-07-08 13:35     ` Gleb Natapov
2010-07-08 13:35       ` Gleb Natapov
2010-07-06 16:25 ` [PATCH v4 12/12] Send async PF when guest is not in userspace too Gleb Natapov
2010-07-06 16:25   ` Gleb Natapov
2010-07-08  4:29   ` Rik van Riel
2010-07-08  4:29     ` Rik van Riel

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1278433500-29884-11-git-send-email-gleb@redhat.com \
    --to=gleb@redhat.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=avi@redhat.com \
    --cc=cl@linux-foundation.org \
    --cc=hpa@zytor.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mingo@elte.hu \
    --cc=mtosatti@redhat.com \
    --cc=riel@redhat.com \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.