diff options
| -rw-r--r-- | target-i386/cc_helper.c | 217 | ||||
| -rw-r--r-- | target-i386/cc_helper_template.h | 245 |
2 files changed, 180 insertions, 282 deletions
diff --git a/target-i386/cc_helper.c b/target-i386/cc_helper.c index 9422003f24..61427ddeac 100644 --- a/target-i386/cc_helper.c +++ b/target-i386/cc_helper.c @@ -75,125 +75,108 @@ const uint8_t parity_table[256] = { #endif -static int compute_all_eflags(CPUX86State *env) -{ - return CC_SRC; -} - -static int compute_c_eflags(CPUX86State *env) -{ - return CC_SRC & CC_C; -} - uint32_t helper_cc_compute_all(CPUX86State *env, int op) { + target_ulong dst = CC_DST, src1 = CC_SRC; + switch (op) { default: /* should never happen */ return 0; case CC_OP_EFLAGS: - return compute_all_eflags(env); + return src1; case CC_OP_MULB: - return compute_all_mulb(env); + return compute_all_mulb(dst, src1); case CC_OP_MULW: - return compute_all_mulw(env); + return compute_all_mulw(dst, src1); case CC_OP_MULL: - return compute_all_mull(env); + return compute_all_mull(dst, src1); case CC_OP_ADDB: - return compute_all_addb(env); + return compute_all_addb(dst, src1); case CC_OP_ADDW: - return compute_all_addw(env); + return compute_all_addw(dst, src1); case CC_OP_ADDL: - return compute_all_addl(env); + return compute_all_addl(dst, src1); case CC_OP_ADCB: - return compute_all_adcb(env); + return compute_all_adcb(dst, src1); case CC_OP_ADCW: - return compute_all_adcw(env); + return compute_all_adcw(dst, src1); case CC_OP_ADCL: - return compute_all_adcl(env); + return compute_all_adcl(dst, src1); case CC_OP_SUBB: - return compute_all_subb(env); + return compute_all_subb(dst, src1); case CC_OP_SUBW: - return compute_all_subw(env); + return compute_all_subw(dst, src1); case CC_OP_SUBL: - return compute_all_subl(env); + return compute_all_subl(dst, src1); case CC_OP_SBBB: - return compute_all_sbbb(env); + return compute_all_sbbb(dst, src1); case CC_OP_SBBW: - return compute_all_sbbw(env); + return compute_all_sbbw(dst, src1); case CC_OP_SBBL: - return compute_all_sbbl(env); + return compute_all_sbbl(dst, src1); case CC_OP_LOGICB: - return compute_all_logicb(env); + return compute_all_logicb(dst, src1); case CC_OP_LOGICW: - return compute_all_logicw(env); + return compute_all_logicw(dst, src1); case CC_OP_LOGICL: - return compute_all_logicl(env); + return compute_all_logicl(dst, src1); case CC_OP_INCB: - return compute_all_incb(env); + return compute_all_incb(dst, src1); case CC_OP_INCW: - return compute_all_incw(env); + return compute_all_incw(dst, src1); case CC_OP_INCL: - return compute_all_incl(env); + return compute_all_incl(dst, src1); case CC_OP_DECB: - return compute_all_decb(env); + return compute_all_decb(dst, src1); case CC_OP_DECW: - return compute_all_decw(env); + return compute_all_decw(dst, src1); case CC_OP_DECL: - return compute_all_decl(env); + return compute_all_decl(dst, src1); case CC_OP_SHLB: - return compute_all_shlb(env); + return compute_all_shlb(dst, src1); case CC_OP_SHLW: - return compute_all_shlw(env); + return compute_all_shlw(dst, src1); case CC_OP_SHLL: - return compute_all_shll(env); + return compute_all_shll(dst, src1); case CC_OP_SARB: - return compute_all_sarb(env); + return compute_all_sarb(dst, src1); case CC_OP_SARW: - return compute_all_sarw(env); + return compute_all_sarw(dst, src1); case CC_OP_SARL: - return compute_all_sarl(env); + return compute_all_sarl(dst, src1); #ifdef TARGET_X86_64 case CC_OP_MULQ: - return compute_all_mulq(env); - + return compute_all_mulq(dst, src1); case CC_OP_ADDQ: - return compute_all_addq(env); - + return compute_all_addq(dst, src1); case CC_OP_ADCQ: - return compute_all_adcq(env); - + return compute_all_adcq(dst, src1); case CC_OP_SUBQ: - return compute_all_subq(env); - + return compute_all_subq(dst, src1); case CC_OP_SBBQ: - return compute_all_sbbq(env); - + return compute_all_sbbq(dst, src1); case CC_OP_LOGICQ: - return compute_all_logicq(env); - + return compute_all_logicq(dst, src1); case CC_OP_INCQ: - return compute_all_incq(env); - + return compute_all_incq(dst, src1); case CC_OP_DECQ: - return compute_all_decq(env); - + return compute_all_decq(dst, src1); case CC_OP_SHLQ: - return compute_all_shlq(env); - + return compute_all_shlq(dst, src1); case CC_OP_SARQ: - return compute_all_sarq(env); + return compute_all_sarq(dst, src1); #endif } } @@ -205,113 +188,85 @@ uint32_t cpu_cc_compute_all(CPUX86State *env, int op) uint32_t helper_cc_compute_c(CPUX86State *env, int op) { + target_ulong dst = CC_DST, src1 = CC_SRC; + switch (op) { default: /* should never happen */ + case CC_OP_LOGICB: + case CC_OP_LOGICW: + case CC_OP_LOGICL: + case CC_OP_LOGICQ: return 0; case CC_OP_EFLAGS: - return compute_c_eflags(env); + case CC_OP_SARB: + case CC_OP_SARW: + case CC_OP_SARL: + case CC_OP_SARQ: + return src1 & 1; + + case CC_OP_INCB: + case CC_OP_INCW: + case CC_OP_INCL: + case CC_OP_INCQ: + case CC_OP_DECB: + case CC_OP_DECW: + case CC_OP_DECL: + case CC_OP_DECQ: + return src1; case CC_OP_MULB: - return compute_c_mull(env); case CC_OP_MULW: - return compute_c_mull(env); case CC_OP_MULL: - return compute_c_mull(env); + case CC_OP_MULQ: + return src1 != 0; case CC_OP_ADDB: - return compute_c_addb(env); + return compute_c_addb(dst, src1); case CC_OP_ADDW: - return compute_c_addw(env); + return compute_c_addw(dst, src1); case CC_OP_ADDL: - return compute_c_addl(env); + return compute_c_addl(dst, src1); case CC_OP_ADCB: - return compute_c_adcb(env); + return compute_c_adcb(dst, src1); case CC_OP_ADCW: - return compute_c_adcw(env); + return compute_c_adcw(dst, src1); case CC_OP_ADCL: - return compute_c_adcl(env); + return compute_c_adcl(dst, src1); case CC_OP_SUBB: - return compute_c_subb(env); + return compute_c_subb(dst, src1); case CC_OP_SUBW: - return compute_c_subw(env); + return compute_c_subw(dst, src1); case CC_OP_SUBL: - return compute_c_subl(env); + return compute_c_subl(dst, src1); case CC_OP_SBBB: - return compute_c_sbbb(env); + return compute_c_sbbb(dst, src1); case CC_OP_SBBW: - return compute_c_sbbw(env); + return compute_c_sbbw(dst, src1); case CC_OP_SBBL: - return compute_c_sbbl(env); - - case CC_OP_LOGICB: - return compute_c_logicb(); - case CC_OP_LOGICW: - return compute_c_logicw(); - case CC_OP_LOGICL: - return compute_c_logicl(); - - case CC_OP_INCB: - return compute_c_incl(env); - case CC_OP_INCW: - return compute_c_incl(env); - case CC_OP_INCL: - return compute_c_incl(env); - - case CC_OP_DECB: - return compute_c_incl(env); - case CC_OP_DECW: - return compute_c_incl(env); - case CC_OP_DECL: - return compute_c_incl(env); + return compute_c_sbbl(dst, src1); case CC_OP_SHLB: - return compute_c_shlb(env); + return compute_c_shlb(dst, src1); case CC_OP_SHLW: - return compute_c_shlw(env); + return compute_c_shlw(dst, src1); case CC_OP_SHLL: - return compute_c_shll(env); - - case CC_OP_SARB: - return compute_c_sarl(env); - case CC_OP_SARW: - return compute_c_sarl(env); - case CC_OP_SARL: - return compute_c_sarl(env); + return compute_c_shll(dst, src1); #ifdef TARGET_X86_64 - case CC_OP_MULQ: - return compute_c_mull(env); - case CC_OP_ADDQ: - return compute_c_addq(env); - + return compute_c_addq(dst, src1); case CC_OP_ADCQ: - return compute_c_adcq(env); - + return compute_c_adcq(dst, src1); case CC_OP_SUBQ: - return compute_c_subq(env); - + return compute_c_subq(dst, src1); case CC_OP_SBBQ: - return compute_c_sbbq(env); - - case CC_OP_LOGICQ: - return compute_c_logicq(); - - case CC_OP_INCQ: - return compute_c_incl(env); - - case CC_OP_DECQ: - return compute_c_incl(env); - + return compute_c_sbbq(dst, src1); case CC_OP_SHLQ: - return compute_c_shlq(env); - - case CC_OP_SARQ: - return compute_c_sarl(env); + return compute_c_shlq(dst, src1); #endif } } diff --git a/target-i386/cc_helper_template.h b/target-i386/cc_helper_template.h index 1f94e11dcf..522b462285 100644 --- a/target-i386/cc_helper_template.h +++ b/target-i386/cc_helper_template.h @@ -18,255 +18,198 @@ */ #define DATA_BITS (1 << (3 + SHIFT)) -#define SIGN_MASK (((target_ulong)1) << (DATA_BITS - 1)) #if DATA_BITS == 8 #define SUFFIX b #define DATA_TYPE uint8_t -#define DATA_MASK 0xff #elif DATA_BITS == 16 #define SUFFIX w #define DATA_TYPE uint16_t -#define DATA_MASK 0xffff #elif DATA_BITS == 32 #define SUFFIX l #define DATA_TYPE uint32_t -#define DATA_MASK 0xffffffff #elif DATA_BITS == 64 #define SUFFIX q #define DATA_TYPE uint64_t -#define DATA_MASK 0xffffffffffffffffULL #else #error unhandled operand size #endif +#define SIGN_MASK (((DATA_TYPE)1) << (DATA_BITS - 1)) + /* dynamic flags computation */ -static int glue(compute_all_add, SUFFIX)(CPUX86State *env) +static int glue(compute_all_add, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1) { int cf, pf, af, zf, sf, of; - target_long src1, src2; - - src1 = CC_SRC; - src2 = CC_DST - CC_SRC; - cf = (DATA_TYPE)CC_DST < (DATA_TYPE)src1; - pf = parity_table[(uint8_t)CC_DST]; - af = (CC_DST ^ src1 ^ src2) & 0x10; - zf = ((DATA_TYPE)CC_DST == 0) << 6; - sf = lshift(CC_DST, 8 - DATA_BITS) & 0x80; - of = lshift((src1 ^ src2 ^ -1) & (src1 ^ CC_DST), 12 - DATA_BITS) & CC_O; + DATA_TYPE src2 = dst - src1; + + cf = dst < src1; + pf = parity_table[(uint8_t)dst]; + af = (dst ^ src1 ^ src2) & CC_A; + zf = (dst == 0) * CC_Z; + sf = lshift(dst, 8 - DATA_BITS) & CC_S; + of = lshift((src1 ^ src2 ^ -1) & (src1 ^ dst), 12 - DATA_BITS) & CC_O; return cf | pf | af | zf | sf | of; } -static int glue(compute_c_add, SUFFIX)(CPUX86State *env) +static int glue(compute_c_add, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1) { - int cf; - target_long src1; - - src1 = CC_SRC; - cf = (DATA_TYPE)CC_DST < (DATA_TYPE)src1; - return cf; + return dst < src1; } -static int glue(compute_all_adc, SUFFIX)(CPUX86State *env) +static int glue(compute_all_adc, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1) { int cf, pf, af, zf, sf, of; - target_long src1, src2; - - src1 = CC_SRC; - src2 = CC_DST - CC_SRC - 1; - cf = (DATA_TYPE)CC_DST <= (DATA_TYPE)src1; - pf = parity_table[(uint8_t)CC_DST]; - af = (CC_DST ^ src1 ^ src2) & 0x10; - zf = ((DATA_TYPE)CC_DST == 0) << 6; - sf = lshift(CC_DST, 8 - DATA_BITS) & 0x80; - of = lshift((src1 ^ src2 ^ -1) & (src1 ^ CC_DST), 12 - DATA_BITS) & CC_O; + DATA_TYPE src2 = dst - src1 - 1; + + cf = dst <= src1; + pf = parity_table[(uint8_t)dst]; + af = (dst ^ src1 ^ src2) & 0x10; + zf = (dst == 0) << 6; + sf = lshift(dst, 8 - DATA_BITS) & 0x80; + of = lshift((src1 ^ src2 ^ -1) & (src1 ^ dst), 12 - DATA_BITS) & CC_O; return cf | pf | af | zf | sf | of; } -static int glue(compute_c_adc, SUFFIX)(CPUX86State *env) +static int glue(compute_c_adc, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1) { - int cf; - target_long src1; - - src1 = CC_SRC; - cf = (DATA_TYPE)CC_DST <= (DATA_TYPE)src1; - return cf; + return dst <= src1; } -static int glue(compute_all_sub, SUFFIX)(CPUX86State *env) +static int glue(compute_all_sub, SUFFIX)(DATA_TYPE dst, DATA_TYPE src2) { int cf, pf, af, zf, sf, of; - target_long src1, src2; - - src1 = CC_DST + CC_SRC; - src2 = CC_SRC; - cf = (DATA_TYPE)src1 < (DATA_TYPE)src2; - pf = parity_table[(uint8_t)CC_DST]; - af = (CC_DST ^ src1 ^ src2) & 0x10; - zf = ((DATA_TYPE)CC_DST == 0) << 6; - sf = lshift(CC_DST, 8 - DATA_BITS) & 0x80; - of = lshift((src1 ^ src2) & (src1 ^ CC_DST), 12 - DATA_BITS) & CC_O; + DATA_TYPE src1 = dst + src2; + + cf = src1 < src2; + pf = parity_table[(uint8_t)dst]; + af = (dst ^ src1 ^ src2) & CC_A; + zf = (dst == 0) * CC_Z; + sf = lshift(dst, 8 - DATA_BITS) & CC_S; + of = lshift((src1 ^ src2) & (src1 ^ dst), 12 - DATA_BITS) & CC_O; return cf | pf | af | zf | sf | of; } -static int glue(compute_c_sub, SUFFIX)(CPUX86State *env) +static int glue(compute_c_sub, SUFFIX)(DATA_TYPE dst, DATA_TYPE src2) { - int cf; - target_long src1, src2; + DATA_TYPE src1 = dst + src2; - src1 = CC_DST + CC_SRC; - src2 = CC_SRC; - cf = (DATA_TYPE)src1 < (DATA_TYPE)src2; - return cf; + return src1 < src2; } -static int glue(compute_all_sbb, SUFFIX)(CPUX86State *env) +static int glue(compute_all_sbb, SUFFIX)(DATA_TYPE dst, DATA_TYPE src2) { int cf, pf, af, zf, sf, of; - target_long src1, src2; - - src1 = CC_DST + CC_SRC + 1; - src2 = CC_SRC; - cf = (DATA_TYPE)src1 <= (DATA_TYPE)src2; - pf = parity_table[(uint8_t)CC_DST]; - af = (CC_DST ^ src1 ^ src2) & 0x10; - zf = ((DATA_TYPE)CC_DST == 0) << 6; - sf = lshift(CC_DST, 8 - DATA_BITS) & 0x80; - of = lshift((src1 ^ src2) & (src1 ^ CC_DST), 12 - DATA_BITS) & CC_O; + DATA_TYPE src1 = dst + src2 + 1; + + cf = src1 <= src2; + pf = parity_table[(uint8_t)dst]; + af = (dst ^ src1 ^ src2) & 0x10; + zf = (dst == 0) << 6; + sf = lshift(dst, 8 - DATA_BITS) & 0x80; + of = lshift((src1 ^ src2) & (src1 ^ dst), 12 - DATA_BITS) & CC_O; return cf | pf | af | zf | sf | of; } -static int glue(compute_c_sbb, SUFFIX)(CPUX86State *env) +static int glue(compute_c_sbb, SUFFIX)(DATA_TYPE dst, DATA_TYPE src2) { - int cf; - target_long src1, src2; + DATA_TYPE src1 = dst + src2 + 1; - src1 = CC_DST + CC_SRC + 1; - src2 = CC_SRC; - cf = (DATA_TYPE)src1 <= (DATA_TYPE)src2; - return cf; + return src1 <= src2; } -static int glue(compute_all_logic, SUFFIX)(CPUX86State *env) +static int glue(compute_all_logic, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1) { int cf, pf, af, zf, sf, of; cf = 0; - pf = parity_table[(uint8_t)CC_DST]; + pf = parity_table[(uint8_t)dst]; af = 0; - zf = ((DATA_TYPE)CC_DST == 0) << 6; - sf = lshift(CC_DST, 8 - DATA_BITS) & 0x80; + zf = (dst == 0) * CC_Z; + sf = lshift(dst, 8 - DATA_BITS) & CC_S; of = 0; return cf | pf | af | zf | sf | of; } -static int glue(compute_c_logic, SUFFIX)(void) -{ - return 0; -} - -static int glue(compute_all_inc, SUFFIX)(CPUX86State *env) +static int glue(compute_all_inc, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1) { int cf, pf, af, zf, sf, of; - target_long src1, src2; + DATA_TYPE src2; - src1 = CC_DST - 1; + cf = src1; + src1 = dst - 1; src2 = 1; - cf = CC_SRC; - pf = parity_table[(uint8_t)CC_DST]; - af = (CC_DST ^ src1 ^ src2) & 0x10; - zf = ((DATA_TYPE)CC_DST == 0) << 6; - sf = lshift(CC_DST, 8 - DATA_BITS) & 0x80; - of = ((CC_DST & DATA_MASK) == SIGN_MASK) << 11; + pf = parity_table[(uint8_t)dst]; + af = (dst ^ src1 ^ src2) & CC_A; + zf = (dst == 0) * CC_Z; + sf = lshift(dst, 8 - DATA_BITS) & CC_S; + of = (dst == SIGN_MASK) * CC_O; return cf | pf | af | zf | sf | of; } -#if DATA_BITS == 32 -static int glue(compute_c_inc, SUFFIX)(CPUX86State *env) -{ - return CC_SRC; -} -#endif - -static int glue(compute_all_dec, SUFFIX)(CPUX86State *env) +static int glue(compute_all_dec, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1) { int cf, pf, af, zf, sf, of; - target_long src1, src2; + DATA_TYPE src2; - src1 = CC_DST + 1; + cf = src1; + src1 = dst + 1; src2 = 1; - cf = CC_SRC; - pf = parity_table[(uint8_t)CC_DST]; - af = (CC_DST ^ src1 ^ src2) & 0x10; - zf = ((DATA_TYPE)CC_DST == 0) << 6; - sf = lshift(CC_DST, 8 - DATA_BITS) & 0x80; - of = ((CC_DST & DATA_MASK) == ((target_ulong)SIGN_MASK - 1)) << 11; + pf = parity_table[(uint8_t)dst]; + af = (dst ^ src1 ^ src2) & CC_A; + zf = (dst == 0) * CC_Z; + sf = lshift(dst, 8 - DATA_BITS) & CC_S; + of = (dst == SIGN_MASK - 1) * CC_O; return cf | pf | af | zf | sf | of; } -static int glue(compute_all_shl, SUFFIX)(CPUX86State *env) +static int glue(compute_all_shl, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1) { int cf, pf, af, zf, sf, of; - cf = (CC_SRC >> (DATA_BITS - 1)) & CC_C; - pf = parity_table[(uint8_t)CC_DST]; + cf = (src1 >> (DATA_BITS - 1)) & CC_C; + pf = parity_table[(uint8_t)dst]; af = 0; /* undefined */ - zf = ((DATA_TYPE)CC_DST == 0) << 6; - sf = lshift(CC_DST, 8 - DATA_BITS) & 0x80; - /* of is defined if shift count == 1 */ - of = lshift(CC_SRC ^ CC_DST, 12 - DATA_BITS) & CC_O; + zf = (dst == 0) * CC_Z; + sf = lshift(dst, 8 - DATA_BITS) & CC_S; + /* of is defined iff shift count == 1 */ + of = lshift(src1 ^ dst, 12 - DATA_BITS) & CC_O; return cf | pf | af | zf | sf | of; } -static int glue(compute_c_shl, SUFFIX)(CPUX86State *env) +static int glue(compute_c_shl, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1) { - return (CC_SRC >> (DATA_BITS - 1)) & CC_C; + return (src1 >> (DATA_BITS - 1)) & CC_C; } -#if DATA_BITS == 32 -static int glue(compute_c_sar, SUFFIX)(CPUX86State *env) -{ - return CC_SRC & 1; -} -#endif - -static int glue(compute_all_sar, SUFFIX)(CPUX86State *env) +static int glue(compute_all_sar, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1) { int cf, pf, af, zf, sf, of; - cf = CC_SRC & 1; - pf = parity_table[(uint8_t)CC_DST]; + cf = src1 & 1; + pf = parity_table[(uint8_t)dst]; af = 0; /* undefined */ - zf = ((DATA_TYPE)CC_DST == 0) << 6; - sf = lshift(CC_DST, 8 - DATA_BITS) & 0x80; - /* of is defined if shift count == 1 */ - of = lshift(CC_SRC ^ CC_DST, 12 - DATA_BITS) & CC_O; + zf = (dst == 0) * CC_Z; + sf = lshift(dst, 8 - DATA_BITS) & CC_S; + /* of is defined iff shift count == 1 */ + of = lshift(src1 ^ dst, 12 - DATA_BITS) & CC_O; return cf | pf | af | zf | sf | of; } -#if DATA_BITS == 32 -static int glue(compute_c_mul, SUFFIX)(CPUX86State *env) -{ - int cf; - - cf = (CC_SRC != 0); - return cf; -} -#endif - /* NOTE: we compute the flags like the P4. On olders CPUs, only OF and - CF are modified and it is slower to do that. */ -static int glue(compute_all_mul, SUFFIX)(CPUX86State *env) + CF are modified and it is slower to do that. Note as well that we + don't truncate SRC1 for computing carry to DATA_TYPE. */ +static int glue(compute_all_mul, SUFFIX)(DATA_TYPE dst, target_long src1) { int cf, pf, af, zf, sf, of; - cf = (CC_SRC != 0); - pf = parity_table[(uint8_t)CC_DST]; + cf = (src1 != 0); + pf = parity_table[(uint8_t)dst]; af = 0; /* undefined */ - zf = ((DATA_TYPE)CC_DST == 0) << 6; - sf = lshift(CC_DST, 8 - DATA_BITS) & 0x80; - of = cf << 11; + zf = (dst == 0) * CC_Z; + sf = lshift(dst, 8 - DATA_BITS) & CC_S; + of = cf * CC_O; return cf | pf | af | zf | sf | of; } |