KVM: x86: Enable support for emulating AVX MOV instructions

Some users of KVM have emulated devices (typically added to private
forks of QEMU) that execute AVX instructions on PCI BARs.  Whenever
the guest OS tries to do that, an illegal instruction exception or
emulation failure is triggered.

Add the Avx flag to move instructions:
- (66) 0f 10 - MOVUPS/MOVUPD from memory
- (66) 0f 11 - MOVUPS/MOVUPD to memory
- 66 0f 6f - MOVDQA from memory
- 66 0f 7f - MOVDQA to memory
- f3 0f 6f - MOVDQU from memory
- f3 0f 7f - MOVDQU to memory
- (66) 0f 28 - MOVAPS/MOVAPD from memory
- (66) 0f 29 - MOVAPS/MOVAPD to memory
- (66) 0f 2b - MOVNTPS/MOVNTPD to memory
- 66 0f e7 - MOVNTDQ to memory
- 66 0f 38 2a - MOVNTDQA to memory

Co-developed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/kvm/BD108C42-0382-4B17-B601-434A4BD038E7@fb.com/T/
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://patch.msgid.link/20251114003633.60689-11-pbonzini@redhat.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 63b83a2e0e87059c564eacd33104fd6e8b984da2..c8e292e9a24dfee3d46c5553de1231b05a58da3b 100644 (file)
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4121,7 +4121,7 @@ static const struct group_dual group15 = { {
 } };
 
 static const struct gprefix pfx_0f_6f_0f_7f = {
-       I(Mmx, em_mov), I(Sse | Aligned, em_mov), N, I(Sse | Unaligned, em_mov),
+       I(Mmx, em_mov), I(Sse | Avx | Aligned, em_mov), N, I(Sse | Avx | Unaligned, em_mov),
 };
 
 static const struct instr_dual instr_dual_0f_2b = {
@@ -4141,7 +4141,7 @@ static const struct gprefix pfx_0f_28_0f_29 = {
 };
 
 static const struct gprefix pfx_0f_e7_0f_38_2a = {
-       N, I(Sse, em_mov), N, N,
+       N, I(Sse | Avx, em_mov), N, N,
 };
 
 static const struct escape escape_d9 = { {
@@ -4354,8 +4354,8 @@ static const struct opcode twobyte_table[256] = {
        DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N,
        N, D(ImplicitOps | ModRM | SrcMem | NoAccess), N, N,
        /* 0x10 - 0x1F */
-       GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_10_0f_11),
-       GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_10_0f_11),
+       GP(ModRM | DstReg | SrcMem | Mov | Sse | Avx, &pfx_0f_10_0f_11),
+       GP(ModRM | DstMem | SrcReg | Mov | Sse | Avx, &pfx_0f_10_0f_11),
        N, N, N, N, N, N,
        D(ImplicitOps | ModRM | SrcMem | NoAccess), /* 4 * prefetch + 4 * reserved NOP */
        D(ImplicitOps | ModRM | SrcMem | NoAccess), N, N,
@@ -4371,9 +4371,9 @@ static const struct opcode twobyte_table[256] = {
        IIP(ModRM | SrcMem | Priv | Op3264 | NoMod, em_dr_write, dr_write,
                                                check_dr_write),
        N, N, N, N,
-       GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_28_0f_29),
-       GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_28_0f_29),
-       N, GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_2b),
+       GP(ModRM | DstReg | SrcMem | Mov | Sse | Avx, &pfx_0f_28_0f_29),
+       GP(ModRM | DstMem | SrcReg | Mov | Sse | Avx, &pfx_0f_28_0f_29),
+       N, GP(ModRM | DstMem | SrcReg | Mov | Sse | Avx, &pfx_0f_2b),
        N, N, N, N,
        /* 0x30 - 0x3F */
        II(ImplicitOps | Priv, em_wrmsr, wrmsr),