From: "Jan Beulich" <JBeulich@suse.com>
To: "H. Peter Anvin" <hpa@zytor.com>
Cc: <mingo@elte.hu>, <tglx@linutronix.de>,
"Konrad Rzeszutek Wilk" <konrad.wilk@oracle.com>,
<linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 3/3, v2] x86/xor: make virtualization friendly
Date: Mon, 05 Nov 2012 09:10:24 +0000 [thread overview]
Message-ID: <5097909002000078000A64C2@nat28.tlf.novell.com> (raw)
In-Reply-To: <c9840e69-aa7f-4ba5-a981-e330f4fba297@email.android.com>
>>> On 02.11.12 at 18:30, "H. Peter Anvin" <hpa@zytor.com> wrote:
> Aren't we actually talking just about PV here?
>
> If so the test is wrong.
No - this equally can affect "fully" virtualized guests (where the
CR0.TS accesses can involve VMEXIT-s).
Jan
> Jan Beulich <JBeulich@suse.com> wrote:
>
>>In virtualized environments, the CR0.TS management needed here can be a
>>lot slower than anticipated by the original authors of this code, which
>>particularly means that in such cases forcing the use of SSE- (or MMX-)
>>based implementations is not desirable - actual measurements should
>>always be done in that case.
>>
>>For consistency, pull into the shared (32- and 64-bit) header not only
>>the inclusion of the generic code, but also that of the AVX variants.
>>
>>Signed-off-by: Jan Beulich <jbeulich@suse.com>
>>Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
>>
>>---
>> arch/x86/include/asm/xor.h | 8 +++++++-
>> arch/x86/include/asm/xor_32.h | 22 ++++++++++------------
>> arch/x86/include/asm/xor_64.h | 10 ++++++----
>> 3 files changed, 23 insertions(+), 17 deletions(-)
>>
>>--- 3.7-rc3-x86-xor.orig/arch/x86/include/asm/xor.h
>>+++ 3.7-rc3-x86-xor/arch/x86/include/asm/xor.h
>>@@ -487,6 +487,12 @@ static struct xor_block_template xor_blo
>>
>> #undef XOR_CONSTANT_CONSTRAINT
>>
>>+/* Also try the AVX routines */
>>+#include <asm/xor_avx.h>
>>+
>>+/* Also try the generic routines. */
>>+#include <asm-generic/xor.h>
>>+
>> #ifdef CONFIG_X86_32
>> # include <asm/xor_32.h>
>> #else
>>@@ -494,6 +500,6 @@ static struct xor_block_template xor_blo
>> #endif
>>
>> #define XOR_SELECT_TEMPLATE(FASTEST) \
>>- AVX_SELECT(FASTEST)
>>+ (cpu_has_hypervisor ? (FASTEST) : AVX_SELECT(FASTEST))
>>
>> #endif /* _ASM_X86_XOR_H */
>>--- 3.7-rc3-x86-xor.orig/arch/x86/include/asm/xor_32.h
>>+++ 3.7-rc3-x86-xor/arch/x86/include/asm/xor_32.h
>>@@ -537,12 +537,6 @@ static struct xor_block_template xor_blo
>> .do_5 = xor_sse_5,
>> };
>>
>>-/* Also try the AVX routines */
>>-#include <asm/xor_avx.h>
>>-
>>-/* Also try the generic routines. */
>>-#include <asm-generic/xor.h>
>>-
>>/* We force the use of the SSE xor block because it can write around
>>L2.
>> We may also be able to load into the L1 only depending on how the cpu
>> deals with a load to a line that is being prefetched. */
>>@@ -553,15 +547,19 @@ do { \
>> if (cpu_has_xmm) { \
>> xor_speed(&xor_block_pIII_sse); \
>> xor_speed(&xor_block_sse_pf64); \
>>- } else if (cpu_has_mmx) { \
>>+ if (!cpu_has_hypervisor) \
>>+ break; \
>>+ } \
>>+ if (cpu_has_mmx) { \
>> xor_speed(&xor_block_pII_mmx); \
>> xor_speed(&xor_block_p5_mmx); \
>>- } else { \
>>- xor_speed(&xor_block_8regs); \
>>- xor_speed(&xor_block_8regs_p); \
>>- xor_speed(&xor_block_32regs); \
>>- xor_speed(&xor_block_32regs_p); \
>>+ if (!cpu_has_hypervisor) \
>>+ break; \
>> } \
>>+ xor_speed(&xor_block_8regs); \
>>+ xor_speed(&xor_block_8regs_p); \
>>+ xor_speed(&xor_block_32regs); \
>>+ xor_speed(&xor_block_32regs_p); \
>> } while (0)
>>
>> #endif /* _ASM_X86_XOR_32_H */
>>--- 3.7-rc3-x86-xor.orig/arch/x86/include/asm/xor_64.h
>>+++ 3.7-rc3-x86-xor/arch/x86/include/asm/xor_64.h
>>@@ -9,10 +9,6 @@ static struct xor_block_template xor_blo
>> .do_5 = xor_sse_5,
>> };
>>
>>-
>>-/* Also try the AVX routines */
>>-#include <asm/xor_avx.h>
>>-
>>/* We force the use of the SSE xor block because it can write around
>>L2.
>> We may also be able to load into the L1 only depending on how the cpu
>> deals with a load to a line that is being prefetched. */
>>@@ -22,6 +18,12 @@ do { \
>> AVX_XOR_SPEED; \
>> xor_speed(&xor_block_sse_pf64); \
>> xor_speed(&xor_block_sse); \
>>+ if (cpu_has_hypervisor) { \
>>+ xor_speed(&xor_block_8regs); \
>>+ xor_speed(&xor_block_8regs_p); \
>>+ xor_speed(&xor_block_32regs); \
>>+ xor_speed(&xor_block_32regs_p); \
>>+ } \
>> } while (0)
>>
>> #endif /* _ASM_X86_XOR_64_H */
>
> --
> Sent from my mobile phone. Please excuse brevity and lack of formatting.
next prev parent reply other threads:[~2012-11-05 9:10 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-11-02 14:21 Jan Beulich
2012-11-02 17:30 ` H. Peter Anvin
2012-11-05 9:10 ` Jan Beulich [this message]
2013-01-25 10:43 ` [tip:x86/asm] x86/xor: Make " tip-bot for Jan Beulich
2013-01-25 22:11 ` H. Peter Anvin
2013-01-25 22:15 ` H. Peter Anvin
2013-01-26 1:05 ` H. Peter Anvin
2013-01-26 16:49 ` KY Srinivasan
2013-01-26 12:10 ` Ingo Molnar
2013-01-28 9:04 ` Jan Beulich
2013-01-28 15:26 ` H. Peter Anvin
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=5097909002000078000A64C2@nat28.tlf.novell.com \
--to=jbeulich@suse.com \
--cc=hpa@zytor.com \
--cc=konrad.wilk@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®