linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mathias Krause <minipli@googlemail.com>
To: Avi Kivity <avi@redhat.com>, Marcelo Tosatti <mtosatti@redhat.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	Mathias Krause <minipli@googlemail.com>
Subject: [PATCH 2/8] KVM: x86 emulator: use aligned variants of SSE register ops
Date: Thu, 30 Aug 2012 01:30:14 +0200	[thread overview]
Message-ID: <1346283020-22385-3-git-send-email-minipli@googlemail.com> (raw)
In-Reply-To: <1346283020-22385-1-git-send-email-minipli@googlemail.com>

As the the compiler ensures that the memory operand is always aligned
to a 16 byte memory location, use the aligned variant of MOVDQ for
read_sse_reg() and write_sse_reg().

Signed-off-by: Mathias Krause <minipli@googlemail.com>
---
 arch/x86/kvm/emulate.c |   64 ++++++++++++++++++++++++------------------------
 1 file changed, 32 insertions(+), 32 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 1451cff..5a0fee1 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -909,23 +909,23 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 {
 	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
-	case 0: asm("movdqu %%xmm0, %0" : "=m"(*data)); break;
-	case 1: asm("movdqu %%xmm1, %0" : "=m"(*data)); break;
-	case 2: asm("movdqu %%xmm2, %0" : "=m"(*data)); break;
-	case 3: asm("movdqu %%xmm3, %0" : "=m"(*data)); break;
-	case 4: asm("movdqu %%xmm4, %0" : "=m"(*data)); break;
-	case 5: asm("movdqu %%xmm5, %0" : "=m"(*data)); break;
-	case 6: asm("movdqu %%xmm6, %0" : "=m"(*data)); break;
-	case 7: asm("movdqu %%xmm7, %0" : "=m"(*data)); break;
+	case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break;
+	case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break;
+	case 2: asm("movdqa %%xmm2, %0" : "=m"(*data)); break;
+	case 3: asm("movdqa %%xmm3, %0" : "=m"(*data)); break;
+	case 4: asm("movdqa %%xmm4, %0" : "=m"(*data)); break;
+	case 5: asm("movdqa %%xmm5, %0" : "=m"(*data)); break;
+	case 6: asm("movdqa %%xmm6, %0" : "=m"(*data)); break;
+	case 7: asm("movdqa %%xmm7, %0" : "=m"(*data)); break;
 #ifdef CONFIG_X86_64
-	case 8: asm("movdqu %%xmm8, %0" : "=m"(*data)); break;
-	case 9: asm("movdqu %%xmm9, %0" : "=m"(*data)); break;
-	case 10: asm("movdqu %%xmm10, %0" : "=m"(*data)); break;
-	case 11: asm("movdqu %%xmm11, %0" : "=m"(*data)); break;
-	case 12: asm("movdqu %%xmm12, %0" : "=m"(*data)); break;
-	case 13: asm("movdqu %%xmm13, %0" : "=m"(*data)); break;
-	case 14: asm("movdqu %%xmm14, %0" : "=m"(*data)); break;
-	case 15: asm("movdqu %%xmm15, %0" : "=m"(*data)); break;
+	case 8: asm("movdqa %%xmm8, %0" : "=m"(*data)); break;
+	case 9: asm("movdqa %%xmm9, %0" : "=m"(*data)); break;
+	case 10: asm("movdqa %%xmm10, %0" : "=m"(*data)); break;
+	case 11: asm("movdqa %%xmm11, %0" : "=m"(*data)); break;
+	case 12: asm("movdqa %%xmm12, %0" : "=m"(*data)); break;
+	case 13: asm("movdqa %%xmm13, %0" : "=m"(*data)); break;
+	case 14: asm("movdqa %%xmm14, %0" : "=m"(*data)); break;
+	case 15: asm("movdqa %%xmm15, %0" : "=m"(*data)); break;
 #endif
 	default: BUG();
 	}
@@ -937,23 +937,23 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 {
 	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
-	case 0: asm("movdqu %0, %%xmm0" : : "m"(*data)); break;
-	case 1: asm("movdqu %0, %%xmm1" : : "m"(*data)); break;
-	case 2: asm("movdqu %0, %%xmm2" : : "m"(*data)); break;
-	case 3: asm("movdqu %0, %%xmm3" : : "m"(*data)); break;
-	case 4: asm("movdqu %0, %%xmm4" : : "m"(*data)); break;
-	case 5: asm("movdqu %0, %%xmm5" : : "m"(*data)); break;
-	case 6: asm("movdqu %0, %%xmm6" : : "m"(*data)); break;
-	case 7: asm("movdqu %0, %%xmm7" : : "m"(*data)); break;
+	case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break;
+	case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break;
+	case 2: asm("movdqa %0, %%xmm2" : : "m"(*data)); break;
+	case 3: asm("movdqa %0, %%xmm3" : : "m"(*data)); break;
+	case 4: asm("movdqa %0, %%xmm4" : : "m"(*data)); break;
+	case 5: asm("movdqa %0, %%xmm5" : : "m"(*data)); break;
+	case 6: asm("movdqa %0, %%xmm6" : : "m"(*data)); break;
+	case 7: asm("movdqa %0, %%xmm7" : : "m"(*data)); break;
 #ifdef CONFIG_X86_64
-	case 8: asm("movdqu %0, %%xmm8" : : "m"(*data)); break;
-	case 9: asm("movdqu %0, %%xmm9" : : "m"(*data)); break;
-	case 10: asm("movdqu %0, %%xmm10" : : "m"(*data)); break;
-	case 11: asm("movdqu %0, %%xmm11" : : "m"(*data)); break;
-	case 12: asm("movdqu %0, %%xmm12" : : "m"(*data)); break;
-	case 13: asm("movdqu %0, %%xmm13" : : "m"(*data)); break;
-	case 14: asm("movdqu %0, %%xmm14" : : "m"(*data)); break;
-	case 15: asm("movdqu %0, %%xmm15" : : "m"(*data)); break;
+	case 8: asm("movdqa %0, %%xmm8" : : "m"(*data)); break;
+	case 9: asm("movdqa %0, %%xmm9" : : "m"(*data)); break;
+	case 10: asm("movdqa %0, %%xmm10" : : "m"(*data)); break;
+	case 11: asm("movdqa %0, %%xmm11" : : "m"(*data)); break;
+	case 12: asm("movdqa %0, %%xmm12" : : "m"(*data)); break;
+	case 13: asm("movdqa %0, %%xmm13" : : "m"(*data)); break;
+	case 14: asm("movdqa %0, %%xmm14" : : "m"(*data)); break;
+	case 15: asm("movdqa %0, %%xmm15" : : "m"(*data)); break;
 #endif
 	default: BUG();
 	}
-- 
1.7.10.4


  parent reply	other threads:[~2012-08-29 23:32 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-08-29 23:30 [PATCH 0/8] KVM: minor cleanups and optimizations Mathias Krause
2012-08-29 23:30 ` [PATCH 1/8] KVM: x86: minor size optimization Mathias Krause
2012-08-29 23:30 ` Mathias Krause [this message]
2012-09-04 12:09   ` [PATCH 2/8] KVM: x86 emulator: use aligned variants of SSE register ops Avi Kivity
2012-09-04 12:13     ` Avi Kivity
2012-09-04 12:51       ` Mathias Krause
2012-09-05  9:43         ` Avi Kivity
2012-08-29 23:30 ` [PATCH 3/8] KVM: x86: mark opcode tables const Mathias Krause
2012-08-29 23:30 ` [PATCH 4/8] KVM: x86: constify emulate_ops Mathias Krause
2012-08-29 23:30 ` [PATCH 5/8] KVM: x86: constify read_write_emulator_ops Mathias Krause
2012-08-29 23:30 ` [PATCH 6/8] KVM: x86: more constification Mathias Krause
2012-08-29 23:30 ` [PATCH 7/8] KVM: VMX: constify lookup tables Mathias Krause
2012-08-29 23:30 ` [PATCH 8/8] KVM: SVM: " Mathias Krause

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=1346283020-22385-3-git-send-email-minipli@googlemail.com \
    --to=minipli@googlemail.com \
    --cc=avi@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mtosatti@redhat.com \
    --subject='Re: [PATCH 2/8] KVM: x86 emulator: use aligned variants of SSE register ops' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).