On Tue, Jul 01, 2025 at 07:28:09PM +0200, Magnus Kulke wrote:
> Introduce a new helper function to decode x86 instructions from a
> raw instruction byte stream. MSHV delivers an instruction stream in a
> buffer of the vm_exit message. It can be used to speed up MMIO
> emulation, since instructions do not have to be fetched and translated.
>
> Added "fetch_instruction()" op to x86_emul_ops() to improve
> traceability.
>
> Signed-off-by: Magnus Kulke <[email protected]>
> ---
> target/i386/emulate/x86_decode.c | 31 +++++++++++++++++++++++++++----
> target/i386/emulate/x86_decode.h | 10 ++++++++++
> target/i386/emulate/x86_emu.c | 3 ++-
> target/i386/emulate/x86_emu.h | 1 +
> 4 files changed, 40 insertions(+), 5 deletions(-)
>
> diff --git a/target/i386/emulate/x86_decode.c
> b/target/i386/emulate/x86_decode.c
> index 2eca39802e..133065b50a 100644
> --- a/target/i386/emulate/x86_decode.c
> +++ b/target/i386/emulate/x86_decode.c
> @@ -60,6 +60,7 @@ static inline uint64_t decode_bytes(CPUX86State *env,
> struct x86_decode *decode,
> int size)
> {
> uint64_t val = 0;
> + target_ulong va;
This can be moved inside the else branch to limit the scope of the
variable.
>
> switch (size) {
> case 1:
> @@ -71,10 +72,17 @@ static inline uint64_t decode_bytes(CPUX86State *env,
> struct x86_decode *decode,
> VM_PANIC_EX("%s invalid size %d\n", __func__, size);
> break;
> }
> - target_ulong va = linear_rip(env_cpu(env), env->eip) + decode->len;
> - emul_ops->read_mem(env_cpu(env), &val, va, size);
> +
> + /* copy the bytes from the instruction stream, if available */
> + if (decode->stream && decode->len + size <= decode->stream->len) {
> + memcpy(&val, decode->stream->bytes + decode->len, size);
> + } else {
> + va = linear_rip(env_cpu(env), env->eip) + decode->len;
target_ulong va = linear_rip(env_cpu(env), env->eip) + decode->len;
> + emul_ops->fetch_instruction(env_cpu(env), &val, va, size);
> + }
> decode->len += size;
> -
> +
> +
Extraneous blank line here.
> return val;
> }
>
> @@ -2076,9 +2084,10 @@ static void decode_opcodes(CPUX86State *env, struct
> x86_decode *decode)
> }
> }
>
> -uint32_t decode_instruction(CPUX86State *env, struct x86_decode *decode)
> +static uint32_t decode_opcode(CPUX86State *env, struct x86_decode *decode)
> {
> memset(decode, 0, sizeof(*decode));
> +
> decode_prefix(env, decode);
> set_addressing_size(env, decode);
> set_operand_size(env, decode);
> @@ -2088,6 +2097,20 @@ uint32_t decode_instruction(CPUX86State *env, struct
> x86_decode *decode)
> return decode->len;
> }
>
> +uint32_t decode_instruction(CPUX86State *env, struct x86_decode *decode)
> +{
> + return decode_opcode(env, decode);
> +}
> +
> +uint32_t decode_instruction_stream(CPUX86State *env, struct x86_decode
> *decode,
> + struct x86_insn_stream *stream)
> +{
> + if (stream != NULL) {
> + decode->stream = stream;
> + }
This can be simplified as
decode->stream = stream;
> + return decode_opcode(env, decode);
> +}
> +
> void init_decoder(void)
> {
> int i;
> diff --git a/target/i386/emulate/x86_decode.h
> b/target/i386/emulate/x86_decode.h
> index 927645af1a..f5e9738914 100644
> --- a/target/i386/emulate/x86_decode.h
> +++ b/target/i386/emulate/x86_decode.h
> @@ -272,6 +272,11 @@ typedef struct x86_decode_op {
> };
> } x86_decode_op;
>
> +typedef struct x86_insn_stream {
> + const uint8_t *bytes;
> + size_t len;
> +} x86_insn_stream;
> +
> typedef struct x86_decode {
> int len;
> uint8_t opcode[4];
> @@ -298,11 +303,16 @@ typedef struct x86_decode {
> struct x86_modrm modrm;
> struct x86_decode_op op[4];
> bool is_fpu;
> +
> + x86_insn_stream *stream;
Tab here.
> } x86_decode;
>
> uint64_t sign(uint64_t val, int size);
>
> uint32_t decode_instruction(CPUX86State *env, struct x86_decode *decode);
> +uint32_t decode_instruction_stream(CPUX86State *env,
> + struct
> x86_decode *decode,
> + struct x86_insn_stream *stream);
Mixing spaces and tabs.
Wei
