Re: [PATCH] mmu notifiers #v3

2008-01-22 Thread Hugh Dickins
On Tue, 22 Jan 2008, Andrea Arcangeli wrote: > > Then I will have to update KVM so that it will free the kvm structure > after waiting a quiescent point to avoid kernel crashing memory > corruption after applying your changes to the mmu notifier. It may not be suitable (I've not looked into your

Re: [PATCH] mmu notifiers #v3

2008-01-22 Thread Christoph Lameter
On Tue, 22 Jan 2008, Peter Zijlstra wrote: > I think we can get rid of this rwlock as I think this will seriously > hurt larger machines. Correct. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at

Re: [PATCH] mmu notifiers #v3

2008-01-22 Thread Andrea Arcangeli
On Tue, Jan 22, 2008 at 08:28:47PM +0100, Peter Zijlstra wrote: > I think we can get rid of this rwlock as I think this will seriously > hurt larger machines. Yep, I initially considered it, nevertheless given you solved part of the complication I can add it now ;). The only technical reason for

Re: [PATCH] mmu notifiers #v3

2008-01-22 Thread Peter Zijlstra
On Mon, 2008-01-21 at 13:52 +0100, Andrea Arcangeli wrote: > diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h > new file mode 100644 > --- /dev/null > +++ b/include/linux/mmu_notifier.h > @@ -0,0 +1,79 @@ > +#ifndef _LINUX_MMU_NOTIFIER_H > +#define _LINUX_MMU_NOTIFIER_H >

Re: [kvm-devel] [PATCH] mmu notifiers #v3

2008-01-22 Thread Andrea Arcangeli
On Tue, Jan 22, 2008 at 04:12:34PM +0200, Avi Kivity wrote: > Andrea Arcangeli wrote: >> diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h >> --- a/include/asm-generic/pgtable.h >> +++ b/include/asm-generic/pgtable.h >> @@ -44,8 +44,10 @@ >> ({

Re: [kvm-devel] [PATCH] mmu notifiers #v3

2008-01-22 Thread Avi Kivity
Andrea Arcangeli wrote: diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -44,8 +44,10 @@ ({ \ int __young;

Re: [kvm-devel] [PATCH] mmu notifiers #v3

2008-01-22 Thread Avi Kivity
Andrea Arcangeli wrote: diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -44,8 +44,10 @@ ({ \ int __young;

Re: [kvm-devel] [PATCH] mmu notifiers #v3

2008-01-22 Thread Andrea Arcangeli
On Tue, Jan 22, 2008 at 04:12:34PM +0200, Avi Kivity wrote: Andrea Arcangeli wrote: diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -44,8 +44,10 @@ ({

Re: [PATCH] mmu notifiers #v3

2008-01-22 Thread Peter Zijlstra
On Mon, 2008-01-21 at 13:52 +0100, Andrea Arcangeli wrote: diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h new file mode 100644 --- /dev/null +++ b/include/linux/mmu_notifier.h @@ -0,0 +1,79 @@ +#ifndef _LINUX_MMU_NOTIFIER_H +#define _LINUX_MMU_NOTIFIER_H +

Re: [PATCH] mmu notifiers #v3

2008-01-22 Thread Christoph Lameter
On Tue, 22 Jan 2008, Peter Zijlstra wrote: I think we can get rid of this rwlock as I think this will seriously hurt larger machines. Correct. -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to [EMAIL PROTECTED] More majordomo info at

Re: [PATCH] mmu notifiers #v3

2008-01-22 Thread Andrea Arcangeli
On Tue, Jan 22, 2008 at 08:28:47PM +0100, Peter Zijlstra wrote: I think we can get rid of this rwlock as I think this will seriously hurt larger machines. Yep, I initially considered it, nevertheless given you solved part of the complication I can add it now ;). The only technical reason for

Re: [PATCH] mmu notifiers #v3

2008-01-22 Thread Hugh Dickins
On Tue, 22 Jan 2008, Andrea Arcangeli wrote: Then I will have to update KVM so that it will free the kvm structure after waiting a quiescent point to avoid kernel crashing memory corruption after applying your changes to the mmu notifier. It may not be suitable (I've not looked into your

Re: [PATCH] mmu notifiers #v3

2008-01-21 Thread Rik van Riel
On Mon, 21 Jan 2008 13:52:04 +0100 Andrea Arcangeli <[EMAIL PROTECTED]> wrote: > Signed-off-by: Andrea Arcangeli <[EMAIL PROTECTED]> Reviewed-by: Rik van Riel <[EMAIL PROTECTED]> -- All rights reversed. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a

[PATCH] mmu notifiers #v3

2008-01-21 Thread Andrea Arcangeli
On Thu, Jan 17, 2008 at 08:32:52PM +0100, Andrea Arcangeli wrote: > To make this work we still need notification from the VM about memory > pressure [..] Ok I thought some more at the aging issue of the hot kvm pages (to prevent the guest-OS very-hot working set to be swapped out). So I now

[PATCH] mmu notifiers #v3

2008-01-21 Thread Andrea Arcangeli
On Thu, Jan 17, 2008 at 08:32:52PM +0100, Andrea Arcangeli wrote: To make this work we still need notification from the VM about memory pressure [..] Ok I thought some more at the aging issue of the hot kvm pages (to prevent the guest-OS very-hot working set to be swapped out). So I now hooked

Re: [PATCH] mmu notifiers #v3

2008-01-21 Thread Rik van Riel
On Mon, 21 Jan 2008 13:52:04 +0100 Andrea Arcangeli [EMAIL PROTECTED] wrote: Signed-off-by: Andrea Arcangeli [EMAIL PROTECTED] Reviewed-by: Rik van Riel [EMAIL PROTECTED] -- All rights reversed. -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message