summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
authorGleb Natapov <gleb@redhat.com>2010-03-18 15:20:27 +0200
committerAvi Kivity <avi@redhat.com>2010-05-17 12:16:31 +0300
commit7b262e90fc20a49fddf3dad94c8cead1f0439751 (patch)
treec64306065ff392590cf89808807fb82a65499650 /arch/x86
parent5cd21917da245fbe98bd443de2c7f519b3df6814 (diff)
downloadop-kernel-dev-7b262e90fc20a49fddf3dad94c8cead1f0439751.zip
op-kernel-dev-7b262e90fc20a49fddf3dad94c8cead1f0439751.tar.gz
KVM: x86 emulator: introduce pio in string read ahead.
To optimize "rep ins" instruction do IO in big chunks ahead of time instead of doing it only when required during instruction emulation. Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/include/asm/kvm_emulate.h7
-rw-r--r--arch/x86/kvm/emulate.c46
2 files changed, 48 insertions, 5 deletions
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 7fda16f..b5e12c5 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -151,6 +151,12 @@ struct fetch_cache {
unsigned long end;
};
+struct read_cache {
+ u8 data[1024];
+ unsigned long pos;
+ unsigned long end;
+};
+
struct decode_cache {
u8 twobyte;
u8 b;
@@ -178,6 +184,7 @@ struct decode_cache {
void *modrm_ptr;
unsigned long modrm_val;
struct fetch_cache fetch;
+ struct read_cache io_read;
};
struct x86_emulate_ctxt {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 6de6ad1..ab3fff5 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1257,6 +1257,36 @@ done:
return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
}
+static int pio_in_emulated(struct x86_emulate_ctxt *ctxt,
+ struct x86_emulate_ops *ops,
+ unsigned int size, unsigned short port,
+ void *dest)
+{
+ struct read_cache *rc = &ctxt->decode.io_read;
+
+ if (rc->pos == rc->end) { /* refill pio read ahead */
+ struct decode_cache *c = &ctxt->decode;
+ unsigned int in_page, n;
+ unsigned int count = c->rep_prefix ?
+ address_mask(c, c->regs[VCPU_REGS_RCX]) : 1;
+ in_page = (ctxt->eflags & EFLG_DF) ?
+ offset_in_page(c->regs[VCPU_REGS_RDI]) :
+ PAGE_SIZE - offset_in_page(c->regs[VCPU_REGS_RDI]);
+ n = min(min(in_page, (unsigned int)sizeof(rc->data)) / size,
+ count);
+ if (n == 0)
+ n = 1;
+ rc->pos = rc->end = 0;
+ if (!ops->pio_in_emulated(size, port, rc->data, n, ctxt->vcpu))
+ return 0;
+ rc->end = n * size;
+ }
+
+ memcpy(dest, rc->data + rc->pos, size);
+ rc->pos += size;
+ return 1;
+}
+
static u32 desc_limit_scaled(struct desc_struct *desc)
{
u32 limit = get_desc_limit(desc);
@@ -2622,8 +2652,8 @@ special_insn:
kvm_inject_gp(ctxt->vcpu, 0);
goto done;
}
- if (!ops->pio_in_emulated(c->dst.bytes, c->regs[VCPU_REGS_RDX],
- &c->dst.val, 1, ctxt->vcpu))
+ if (!pio_in_emulated(ctxt, ops, c->dst.bytes,
+ c->regs[VCPU_REGS_RDX], &c->dst.val))
goto done; /* IO is needed, skip writeback */
break;
case 0x6e: /* outsb */
@@ -2839,8 +2869,8 @@ special_insn:
kvm_inject_gp(ctxt->vcpu, 0);
goto done;
}
- if (!ops->pio_in_emulated(c->dst.bytes, c->src.val,
- &c->dst.val, 1, ctxt->vcpu))
+ if (!pio_in_emulated(ctxt, ops, c->dst.bytes, c->src.val,
+ &c->dst.val))
goto done; /* IO is needed */
break;
case 0xee: /* out al,dx */
@@ -2928,8 +2958,14 @@ writeback:
string_addr_inc(ctxt, es_base(ctxt), VCPU_REGS_RDI, &c->dst);
if (c->rep_prefix && (c->d & String)) {
+ struct read_cache *rc = &ctxt->decode.io_read;
register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1);
- if (!(c->regs[VCPU_REGS_RCX] & 0x3ff))
+ /*
+ * Re-enter guest when pio read ahead buffer is empty or,
+ * if it is not used, after each 1024 iteration.
+ */
+ if ((rc->end == 0 && !(c->regs[VCPU_REGS_RCX] & 0x3ff)) ||
+ (rc->end != 0 && rc->end == rc->pos))
ctxt->restart = false;
}
OpenPOWER on IntegriCloud