[PATCH 00/04] kvm-s390 updates

[PATCH 00/04] kvm-s390 updates

[Carsten Otte]

Hi Avi,

looks like Heiko played around with kvm a bit :-):
01/04: cosmetics, including part of Arnd's review feedback
02/04: bugfix, if KVM_VCPU_IOCTL_RUN got interrupted by signal
03/04: performance improvement with our pgste memory handling
04/04: resolve merge conflict in linux-next kvm.git versus git-s390
       that was reported by Stephen Rothwell today (thanks, Stephen!)

I think it's save to queue all for 2.6.26, #2 and #4 seem crucial to me.

thanks,
Carsten


-------------------------------------------------------------------------
Check out the new SourceForge.net Marketplace.
It's the best place to buy or sell services for
just about anything Open Source.
http://ad.doubleclick.net/clk;164216239;13503038;w?http://sf.net/marketplace

[PATCH 03/04 v2] kvm-s390: Improve pgste accesses

[Carsten Otte]

From: Heiko Carstens <heiko.carstens@de.ibm.com>

There is no need to use interlocked updates when the rcp
lock is held. Therefore the simple bitops variants can be
used. This should improve performance.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
---
 include/asm-s390/pgtable.h |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

Index: kvm/include/asm-s390/pgtable.h
===================================================================
--- kvm.orig/include/asm-s390/pgtable.h
+++ kvm/include/asm-s390/pgtable.h
@@ -553,12 +553,12 @@ static inline void ptep_rcp_copy(pte_t *
 
 	skey = page_get_storage_key(page_to_phys(page));
 	if (skey & _PAGE_CHANGED)
-		set_bit(RCP_GC_BIT, pgste);
+		set_bit_simple(RCP_GC_BIT, pgste);
 	if (skey & _PAGE_REFERENCED)
-		set_bit(RCP_GR_BIT, pgste);
-	if (test_and_clear_bit(RCP_HC_BIT, pgste))
+		set_bit_simple(RCP_GR_BIT, pgste);
+	if (test_and_clear_bit_simple(RCP_HC_BIT, pgste))
 		SetPageDirty(page);
-	if (test_and_clear_bit(RCP_HR_BIT, pgste))
+	if (test_and_clear_bit_simple(RCP_HR_BIT, pgste))
 		SetPageReferenced(page);
 #endif
 }
@@ -732,8 +732,8 @@ static inline int ptep_test_and_clear_yo
 	young = ((page_get_storage_key(physpage) & _PAGE_REFERENCED) != 0);
 	rcp_lock(ptep);
 	if (young)
-		set_bit(RCP_GR_BIT, pgste);
-	young |= test_and_clear_bit(RCP_HR_BIT, pgste);
+		set_bit_simple(RCP_GR_BIT, pgste);
+	young |= test_and_clear_bit_simple(RCP_HR_BIT, pgste);
 	rcp_unlock(ptep);
 	return young;
 #endif



-------------------------------------------------------------------------
Check out the new SourceForge.net Marketplace.
It's the best place to buy or sell services for
just about anything Open Source.
http://ad.doubleclick.net/clk;164216239;13503038;w?http://sf.net/marketplace

Re: [PATCH 03/04 v2] kvm-s390: Improve pgste accesses

[Avi Kivity]

Carsten Otte wrote:
> From: Heiko Carstens <heiko.carstens@de.ibm.com>
>
> There is no need to use interlocked updates when the rcp
> lock is held. Therefore the simple bitops variants can be
> used. This should improve performance.
>
>   
Applied this fixed patch as well, thanks.

-- 
Any sufficiently difficult bug is indistinguishable from a feature.


-------------------------------------------------------------------------
Check out the new SourceForge.net Marketplace.
It's the best place to buy or sell services for
just about anything Open Source.
http://ad.doubleclick.net/clk;164216239;13503038;w?http://sf.net/marketplace

Re: [PATCH 00/04] kvm-s390 updates

[Avi Kivity]

Carsten Otte wrote:
> Hi Avi,
>
> looks like Heiko played around with kvm a bit :-):
> 01/04: cosmetics, including part of Arnd's review feedback
> 02/04: bugfix, if KVM_VCPU_IOCTL_RUN got interrupted by signal
> 03/04: performance improvement with our pgste memory handling
> 04/04: resolve merge conflict in linux-next kvm.git versus git-s390
>        that was reported by Stephen Rothwell today (thanks, Stephen!)
>
> I think it's save to queue all for 2.6.26, #2 and #4 seem crucial to me.
>
>   
I applied 1, 2, and 4 (3 is broken).  Will fold into the other s390 
patches before submitting upstream.

-- 
Any sufficiently difficult bug is indistinguishable from a feature.


-------------------------------------------------------------------------
Check out the new SourceForge.net Marketplace.
It's the best place to buy or sell services for
just about anything Open Source.
http://ad.doubleclick.net/clk;164216239;13503038;w?http://sf.net/marketplace