[v2] KVM: x86: Swap the dst and src operand for MOVNTDQA

[PATCH v2] KVM: x86: Swap the dst and src operand for MOVNTDQA

Posted by Sean Christopherson 3 weeks, 2 days ago

Swap the MOVNTDQA operands, as MOVNTDQA does NOT in fact have "the same
characteristics as 0F E7 (MOVNTDQ)"; MOVNTDQA loads from memory and stores
to registers, while MOVNTDQ loads from registers and stores to memory.

Per the SDM:

 MOVNTDQ - Move packed integer values in xmm1 to m128 using non-temporal
           hint.

 MOVNTDQA - Move double quadword from m128 to xmm1 using non-temporal hint
            if WC memory type.

Reported-by: Josh Eads <josheads@google.com>
Fixes: c57d9bafbd0b ("KVM: x86: Add support for emulating MOVNTDQA")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
---

v2: Suck less. [Josh]

v1: https://lore.kernel.org/all/20260506185510.2723091-1-seanjc@google.com

 arch/x86/kvm/emulate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index c8c6cc0406d6..8013dccb3110 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4481,7 +4481,7 @@ static const struct opcode opcode_map_0f_38[256] = {
 	X16(N), X16(N),
 	/* 0x20 - 0x2f */
 	X8(N),
-	X2(N), GP(SrcReg | DstMem | ModRM | Mov | Aligned, &pfx_0f_e7_0f_38_2a), N, N, N, N, N,
+	X2(N), GP(SrcMem | DstReg | ModRM | Mov | Aligned, &pfx_0f_e7_0f_38_2a), N, N, N, N, N,
 	/* 0x30 - 0x7f */
 	X16(N), X16(N), X16(N), X16(N), X16(N),
 	/* 0x80 - 0xef */

base-commit: 6d35786de28116ecf78797a62b84e6bf3c45aa5a
-- 
2.54.0.545.g6539524ca2-goog

Re: [PATCH v2] KVM: x86: Swap the dst and src operand for MOVNTDQA

Posted by Paolo Bonzini 2 weeks, 3 days ago

Queued, thanks.

Paolo

Re: [PATCH v2] KVM: x86: Swap the dst and src operand for MOVNTDQA

Posted by Jim Mattson 3 weeks, 2 days ago

On Wed, May 6, 2026 at 2:35 PM Sean Christopherson <seanjc@google.com> wrote:
>
> Swap the MOVNTDQA operands, as MOVNTDQA does NOT in fact have "the same
> characteristics as 0F E7 (MOVNTDQ)"; MOVNTDQA loads from memory and stores
> to registers, while MOVNTDQ loads from registers and stores to memory.
>
> Per the SDM:
>
>  MOVNTDQ - Move packed integer values in xmm1 to m128 using non-temporal
>            hint.
>
>  MOVNTDQA - Move double quadword from m128 to xmm1 using non-temporal hint
>             if WC memory type.
>
> Reported-by: Josh Eads <josheads@google.com>
> Fixes: c57d9bafbd0b ("KVM: x86: Add support for emulating MOVNTDQA")
> Cc: stable@vger.kernel.org
> Signed-off-by: Sean Christopherson <seanjc@google.com>
> ---
>
> v2: Suck less. [Josh]
>
> v1: https://lore.kernel.org/all/20260506185510.2723091-1-seanjc@google.com
>
>  arch/x86/kvm/emulate.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
> index c8c6cc0406d6..8013dccb3110 100644
> --- a/arch/x86/kvm/emulate.c
> +++ b/arch/x86/kvm/emulate.c
> @@ -4481,7 +4481,7 @@ static const struct opcode opcode_map_0f_38[256] = {
>         X16(N), X16(N),
>         /* 0x20 - 0x2f */
>         X8(N),
> -       X2(N), GP(SrcReg | DstMem | ModRM | Mov | Aligned, &pfx_0f_e7_0f_38_2a), N, N, N, N, N,
> +       X2(N), GP(SrcMem | DstReg | ModRM | Mov | Aligned, &pfx_0f_e7_0f_38_2a), N, N, N, N, N,

Ten Ns starting at 0x20 leaves you at 0x2a, so I buy it. :)

Reviewed-by: Jim Mattson <jmattson@google.com>

>         /* 0x30 - 0x7f */
>         X16(N), X16(N), X16(N), X16(N), X16(N),
>         /* 0x80 - 0xef */
>
> base-commit: 6d35786de28116ecf78797a62b84e6bf3c45aa5a
> --
> 2.54.0.545.g6539524ca2-goog
>
>