Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-25 13:41:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

KVM: emulate: speed up emulated moves

Browse Source 
We can just blindly move all 16 bytes of ctxt->src's value to ctxt->dst.
write_register_operand will take care of writing only the lower bytes.

Avoiding a call to memcpy (the compiler optimizes it out) gains about
200 cycles on kvm-unit-tests for register-to-register moves, and makes
them about as fast as arithmetic instructions.

We could perhaps get a larger speedup by moving all instructions _except_
moves out of x86_emulate_insn, removing opcode_len, and replacing the
switch statement with an inlined em_mov.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This commit is contained in:
Paolo Bonzini 2014-03-27 11:36:25 +01:00
parent d40a6898e5
commit 54cfdb3e95
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
arch/x86/include/asm/kvm_emulate.h
View File

@ -233,7 +233,7 @@ struct operand {
union { union {
unsigned long val; unsigned long val;
u64 val64; u64 val64;
char valptr[sizeof(unsigned long) + 2]; char valptr[sizeof(sse128_t)];
sse128_t vec_val; sse128_t vec_val;
u64 mm_val; u64 mm_val;
void *data; void *data;

2
arch/x86/kvm/emulate.c
View File

@ -2990,7 +2990,7 @@ static int em_rdpmc(struct x86_emulate_ctxt *ctxt)
static int em_mov(struct x86_emulate_ctxt *ctxt) static int em_mov(struct x86_emulate_ctxt *ctxt)
{ {
memcpy(ctxt->dst.valptr, ctxt->src.valptr, ctxt->op_bytes); memcpy(ctxt->dst.valptr, ctxt->src.valptr, sizeof(ctxt->src.valptr));
return X86EMUL_CONTINUE; return X86EMUL_CONTINUE;
} }