target-mips: implement unaligned loads using TCG

Load/store from helpers should be avoided as they are quite
inefficient. Rewrite unaligned loads instructions using TCG and
aligned loads. The number of actual loads operations to implement
an unaligned load instruction is reduced from up to 8 to 1.

Note: As we can't rely on shift by 32 or 64 undefined behaviour,
the code loads already shift by one constants.

Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
This commit is contained in:
Aurelien Jarno 2012-10-09 21:53:21 +02:00
parent 18bba4dc78
commit fc40787abc
3 changed files with 62 additions and 159 deletions

View File

@ -4,13 +4,9 @@ DEF_HELPER_3(raise_exception_err, noreturn, env, i32, int)
DEF_HELPER_2(raise_exception, noreturn, env, i32) DEF_HELPER_2(raise_exception, noreturn, env, i32)
#ifdef TARGET_MIPS64 #ifdef TARGET_MIPS64
DEF_HELPER_4(ldl, tl, env, tl, tl, int)
DEF_HELPER_4(ldr, tl, env, tl, tl, int)
DEF_HELPER_4(sdl, void, env, tl, tl, int) DEF_HELPER_4(sdl, void, env, tl, tl, int)
DEF_HELPER_4(sdr, void, env, tl, tl, int) DEF_HELPER_4(sdr, void, env, tl, tl, int)
#endif #endif
DEF_HELPER_4(lwl, tl, env, tl, tl, int)
DEF_HELPER_4(lwr, tl, env, tl, tl, int)
DEF_HELPER_4(swl, void, env, tl, tl, int) DEF_HELPER_4(swl, void, env, tl, tl, int)
DEF_HELPER_4(swr, void, env, tl, tl, int) DEF_HELPER_4(swr, void, env, tl, tl, int)

View File

@ -350,56 +350,6 @@ HELPER_ST_ATOMIC(scd, ld, sd, 0x7)
#define GET_OFFSET(addr, offset) (addr - (offset)) #define GET_OFFSET(addr, offset) (addr - (offset))
#endif #endif
target_ulong helper_lwl(CPUMIPSState *env, target_ulong arg1,
target_ulong arg2, int mem_idx)
{
target_ulong tmp;
tmp = do_lbu(env, arg2, mem_idx);
arg1 = (arg1 & 0x00FFFFFF) | (tmp << 24);
if (GET_LMASK(arg2) <= 2) {
tmp = do_lbu(env, GET_OFFSET(arg2, 1), mem_idx);
arg1 = (arg1 & 0xFF00FFFF) | (tmp << 16);
}
if (GET_LMASK(arg2) <= 1) {
tmp = do_lbu(env, GET_OFFSET(arg2, 2), mem_idx);
arg1 = (arg1 & 0xFFFF00FF) | (tmp << 8);
}
if (GET_LMASK(arg2) == 0) {
tmp = do_lbu(env, GET_OFFSET(arg2, 3), mem_idx);
arg1 = (arg1 & 0xFFFFFF00) | tmp;
}
return (int32_t)arg1;
}
target_ulong helper_lwr(CPUMIPSState *env, target_ulong arg1,
target_ulong arg2, int mem_idx)
{
target_ulong tmp;
tmp = do_lbu(env, arg2, mem_idx);
arg1 = (arg1 & 0xFFFFFF00) | tmp;
if (GET_LMASK(arg2) >= 1) {
tmp = do_lbu(env, GET_OFFSET(arg2, -1), mem_idx);
arg1 = (arg1 & 0xFFFF00FF) | (tmp << 8);
}
if (GET_LMASK(arg2) >= 2) {
tmp = do_lbu(env, GET_OFFSET(arg2, -2), mem_idx);
arg1 = (arg1 & 0xFF00FFFF) | (tmp << 16);
}
if (GET_LMASK(arg2) == 3) {
tmp = do_lbu(env, GET_OFFSET(arg2, -3), mem_idx);
arg1 = (arg1 & 0x00FFFFFF) | (tmp << 24);
}
return (int32_t)arg1;
}
void helper_swl(CPUMIPSState *env, target_ulong arg1, target_ulong arg2, void helper_swl(CPUMIPSState *env, target_ulong arg1, target_ulong arg2,
int mem_idx) int mem_idx)
{ {
@ -440,98 +390,6 @@ void helper_swr(CPUMIPSState *env, target_ulong arg1, target_ulong arg2,
#define GET_LMASK64(v) (((v) & 7) ^ 7) #define GET_LMASK64(v) (((v) & 7) ^ 7)
#endif #endif
target_ulong helper_ldl(CPUMIPSState *env, target_ulong arg1,
target_ulong arg2, int mem_idx)
{
uint64_t tmp;
tmp = do_lbu(env, arg2, mem_idx);
arg1 = (arg1 & 0x00FFFFFFFFFFFFFFULL) | (tmp << 56);
if (GET_LMASK64(arg2) <= 6) {
tmp = do_lbu(env, GET_OFFSET(arg2, 1), mem_idx);
arg1 = (arg1 & 0xFF00FFFFFFFFFFFFULL) | (tmp << 48);
}
if (GET_LMASK64(arg2) <= 5) {
tmp = do_lbu(env, GET_OFFSET(arg2, 2), mem_idx);
arg1 = (arg1 & 0xFFFF00FFFFFFFFFFULL) | (tmp << 40);
}
if (GET_LMASK64(arg2) <= 4) {
tmp = do_lbu(env, GET_OFFSET(arg2, 3), mem_idx);
arg1 = (arg1 & 0xFFFFFF00FFFFFFFFULL) | (tmp << 32);
}
if (GET_LMASK64(arg2) <= 3) {
tmp = do_lbu(env, GET_OFFSET(arg2, 4), mem_idx);
arg1 = (arg1 & 0xFFFFFFFF00FFFFFFULL) | (tmp << 24);
}
if (GET_LMASK64(arg2) <= 2) {
tmp = do_lbu(env, GET_OFFSET(arg2, 5), mem_idx);
arg1 = (arg1 & 0xFFFFFFFFFF00FFFFULL) | (tmp << 16);
}
if (GET_LMASK64(arg2) <= 1) {
tmp = do_lbu(env, GET_OFFSET(arg2, 6), mem_idx);
arg1 = (arg1 & 0xFFFFFFFFFFFF00FFULL) | (tmp << 8);
}
if (GET_LMASK64(arg2) == 0) {
tmp = do_lbu(env, GET_OFFSET(arg2, 7), mem_idx);
arg1 = (arg1 & 0xFFFFFFFFFFFFFF00ULL) | tmp;
}
return arg1;
}
target_ulong helper_ldr(CPUMIPSState *env, target_ulong arg1,
target_ulong arg2, int mem_idx)
{
uint64_t tmp;
tmp = do_lbu(env, arg2, mem_idx);
arg1 = (arg1 & 0xFFFFFFFFFFFFFF00ULL) | tmp;
if (GET_LMASK64(arg2) >= 1) {
tmp = do_lbu(env, GET_OFFSET(arg2, -1), mem_idx);
arg1 = (arg1 & 0xFFFFFFFFFFFF00FFULL) | (tmp << 8);
}
if (GET_LMASK64(arg2) >= 2) {
tmp = do_lbu(env, GET_OFFSET(arg2, -2), mem_idx);
arg1 = (arg1 & 0xFFFFFFFFFF00FFFFULL) | (tmp << 16);
}
if (GET_LMASK64(arg2) >= 3) {
tmp = do_lbu(env, GET_OFFSET(arg2, -3), mem_idx);
arg1 = (arg1 & 0xFFFFFFFF00FFFFFFULL) | (tmp << 24);
}
if (GET_LMASK64(arg2) >= 4) {
tmp = do_lbu(env, GET_OFFSET(arg2, -4), mem_idx);
arg1 = (arg1 & 0xFFFFFF00FFFFFFFFULL) | (tmp << 32);
}
if (GET_LMASK64(arg2) >= 5) {
tmp = do_lbu(env, GET_OFFSET(arg2, -5), mem_idx);
arg1 = (arg1 & 0xFFFF00FFFFFFFFFFULL) | (tmp << 40);
}
if (GET_LMASK64(arg2) >= 6) {
tmp = do_lbu(env, GET_OFFSET(arg2, -6), mem_idx);
arg1 = (arg1 & 0xFF00FFFFFFFFFFFFULL) | (tmp << 48);
}
if (GET_LMASK64(arg2) == 7) {
tmp = do_lbu(env, GET_OFFSET(arg2, -7), mem_idx);
arg1 = (arg1 & 0x00FFFFFFFFFFFFFFULL) | (tmp << 56);
}
return arg1;
}
void helper_sdl(CPUMIPSState *env, target_ulong arg1, target_ulong arg2, void helper_sdl(CPUMIPSState *env, target_ulong arg1, target_ulong arg2,
int mem_idx) int mem_idx)
{ {

View File

@ -1580,7 +1580,7 @@ static void gen_ld (CPUMIPSState *env, DisasContext *ctx, uint32_t opc,
int rt, int base, int16_t offset) int rt, int base, int16_t offset)
{ {
const char *opn = "ld"; const char *opn = "ld";
TCGv t0, t1; TCGv t0, t1, t2;
if (rt == 0 && env->insn_flags & (INSN_LOONGSON2E | INSN_LOONGSON2F)) { if (rt == 0 && env->insn_flags & (INSN_LOONGSON2E | INSN_LOONGSON2F)) {
/* Loongson CPU uses a load to zero register for prefetch. /* Loongson CPU uses a load to zero register for prefetch.
@ -1612,21 +1612,45 @@ static void gen_ld (CPUMIPSState *env, DisasContext *ctx, uint32_t opc,
opn = "lld"; opn = "lld";
break; break;
case OPC_LDL: case OPC_LDL:
save_cpu_state(ctx, 1);
t1 = tcg_temp_new(); t1 = tcg_temp_new();
tcg_gen_andi_tl(t1, t0, 7);
#ifndef TARGET_WORDS_BIGENDIAN
tcg_gen_xori_tl(t1, t1, 7);
#endif
tcg_gen_shli_tl(t1, t1, 3);
tcg_gen_andi_tl(t0, t0, ~7);
tcg_gen_qemu_ld64(t0, t0, ctx->mem_idx);
tcg_gen_shl_tl(t0, t0, t1);
tcg_gen_xori_tl(t1, t1, 63);
t2 = tcg_const_tl(0x7fffffffffffffffull);
tcg_gen_shr_tl(t2, t2, t1);
gen_load_gpr(t1, rt); gen_load_gpr(t1, rt);
gen_helper_1e2i(ldl, t1, t1, t0, ctx->mem_idx); tcg_gen_and_tl(t1, t1, t2);
gen_store_gpr(t1, rt); tcg_temp_free(t2);
tcg_gen_or_tl(t0, t0, t1);
tcg_temp_free(t1); tcg_temp_free(t1);
gen_store_gpr(t0, rt);
opn = "ldl"; opn = "ldl";
break; break;
case OPC_LDR: case OPC_LDR:
save_cpu_state(ctx, 1);
t1 = tcg_temp_new(); t1 = tcg_temp_new();
tcg_gen_andi_tl(t1, t0, 7);
#ifdef TARGET_WORDS_BIGENDIAN
tcg_gen_xori_tl(t1, t1, 7);
#endif
tcg_gen_shli_tl(t1, t1, 3);
tcg_gen_andi_tl(t0, t0, ~7);
tcg_gen_qemu_ld64(t0, t0, ctx->mem_idx);
tcg_gen_shr_tl(t0, t0, t1);
tcg_gen_xori_tl(t1, t1, 63);
t2 = tcg_const_tl(0xfffffffffffffffeull);
tcg_gen_shl_tl(t2, t2, t1);
gen_load_gpr(t1, rt); gen_load_gpr(t1, rt);
gen_helper_1e2i(ldr, t1, t1, t0, ctx->mem_idx); tcg_gen_and_tl(t1, t1, t2);
gen_store_gpr(t1, rt); tcg_temp_free(t2);
tcg_gen_or_tl(t0, t0, t1);
tcg_temp_free(t1); tcg_temp_free(t1);
gen_store_gpr(t0, rt);
opn = "ldr"; opn = "ldr";
break; break;
case OPC_LDPC: case OPC_LDPC:
@ -1672,21 +1696,46 @@ static void gen_ld (CPUMIPSState *env, DisasContext *ctx, uint32_t opc,
opn = "lbu"; opn = "lbu";
break; break;
case OPC_LWL: case OPC_LWL:
save_cpu_state(ctx, 1);
t1 = tcg_temp_new(); t1 = tcg_temp_new();
tcg_gen_andi_tl(t1, t0, 3);
#ifndef TARGET_WORDS_BIGENDIAN
tcg_gen_xori_tl(t1, t1, 3);
#endif
tcg_gen_shli_tl(t1, t1, 3);
tcg_gen_andi_tl(t0, t0, ~3);
tcg_gen_qemu_ld32u(t0, t0, ctx->mem_idx);
tcg_gen_shl_tl(t0, t0, t1);
tcg_gen_xori_tl(t1, t1, 31);
t2 = tcg_const_tl(0x7fffffffull);
tcg_gen_shr_tl(t2, t2, t1);
gen_load_gpr(t1, rt); gen_load_gpr(t1, rt);
gen_helper_1e2i(lwl, t1, t1, t0, ctx->mem_idx); tcg_gen_and_tl(t1, t1, t2);
gen_store_gpr(t1, rt); tcg_temp_free(t2);
tcg_gen_or_tl(t0, t0, t1);
tcg_temp_free(t1); tcg_temp_free(t1);
tcg_gen_ext32s_tl(t0, t0);
gen_store_gpr(t0, rt);
opn = "lwl"; opn = "lwl";
break; break;
case OPC_LWR: case OPC_LWR:
save_cpu_state(ctx, 1);
t1 = tcg_temp_new(); t1 = tcg_temp_new();
tcg_gen_andi_tl(t1, t0, 3);
#ifdef TARGET_WORDS_BIGENDIAN
tcg_gen_xori_tl(t1, t1, 3);
#endif
tcg_gen_shli_tl(t1, t1, 3);
tcg_gen_andi_tl(t0, t0, ~3);
tcg_gen_qemu_ld32u(t0, t0, ctx->mem_idx);
tcg_gen_shr_tl(t0, t0, t1);
tcg_gen_xori_tl(t1, t1, 31);
t2 = tcg_const_tl(0xfffffffeull);
tcg_gen_shl_tl(t2, t2, t1);
gen_load_gpr(t1, rt); gen_load_gpr(t1, rt);
gen_helper_1e2i(lwr, t1, t1, t0, ctx->mem_idx); tcg_gen_and_tl(t1, t1, t2);
gen_store_gpr(t1, rt); tcg_temp_free(t2);
tcg_gen_or_tl(t0, t0, t1);
tcg_temp_free(t1); tcg_temp_free(t1);
gen_store_gpr(t0, rt);
opn = "lwr"; opn = "lwr";
break; break;
case OPC_LL: case OPC_LL: