xemu-project/xemu
1
0
Fork 0
mirror of https://github.com/xemu-project/xemu.git synced 2024-11-23 19:49:43 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Convert to linked list.

Browse Source 
-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJU3Y5ZAAoJEK0ScMxN0CebuvYH/iQa+ZA1yavKsOa2xtB4tq0K
 gwS0hwCmAtS7CV6iM8Wrte/3HJr4xtnQGeBQgatmM7PrDx6o6cjnxwga2mBx6EQv
 fIhWlNPlctAgd11ocuhXXUdGv2yL8TWf+WLTDcO6CS6zbdYp+42sOvrWGKL1UQbz
 RAJhiK5BZsDHv2DodqZBk7JZr9l4hAohARs627xG7uq/j6vggEHo6y/9Z6mETcRX
 fkIwx/qjUmDJbBlFgtgEPBYMX/AWDu7XbhU1kT+EjcrFwEjEd0mxi52NN8uEyGQ9
 xgAekmPvcNR0UpkVl5pIr64/wTkd+m2mBG8CVENG3ryDKePJk64jVth+I/8Z/Qo=
 =+mGW
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/rth/tags/pull-tcg-20150212' into staging

Convert to linked list.

# gpg: Signature made Fri 13 Feb 2015 05:40:41 GMT using RSA key ID 4DD0279B
# gpg: Good signature from "Richard Henderson <rth7680@gmail.com>"
# gpg:                 aka "Richard Henderson <rth@redhat.com>"
# gpg:                 aka "Richard Henderson <rth@twiddle.net>"

* remotes/rth/tags/pull-tcg-20150212:
  tcg: Remove unused opcodes
  tcg: Implement insert_op_before
  tcg: Remove opcodes instead of noping them out
  tcg: Put opcodes in a linked list
  tcg: Introduce tcg_op_buf_count and tcg_op_buf_full
  tcg: Move emit of INDEX_op_end into gen_tb_end
  tcg: Reduce ifdefs in tcg-op.c
  tcg: Move some opcode generation functions out of line

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Peter Maydell 2015-02-13 11:44:49 +00:00
commit cd2d554127
27 changed files with 2736 additions and 2822 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile.target
View File

@ -83,7 +83,7 @@ all: $(PROGS) stap
#########################################################
# cpu emulator library
obj-y = exec.o translate-all.o cpu-exec.o
obj-y += tcg/tcg.o tcg/optimize.o
obj-y += tcg/tcg.o tcg/tcg-op.o tcg/optimize.o
obj-$(CONFIG_TCG_INTERPRETER) += tci.o
obj-$(CONFIG_TCG_INTERPRETER) += disas/tci.o
obj-y += fpu/softfloat.o

22
include/exec/gen-icount.h
View File

@ -11,8 +11,8 @@ static int exitreq_label;
static inline void gen_tb_start(TranslationBlock *tb)
{
TCGv_i32 count;
TCGv_i32 flag;
TCGv_i32 count, flag, imm;
int i;
exitreq_label = gen_new_label();
flag = tcg_temp_new_i32();
@ -21,16 +21,25 @@ static inline void gen_tb_start(TranslationBlock *tb)
tcg_gen_brcondi_i32(TCG_COND_NE, flag, 0, exitreq_label);
tcg_temp_free_i32(flag);
if (!(tb->cflags & CF_USE_ICOUNT))
if (!(tb->cflags & CF_USE_ICOUNT)) {
return;
}
icount_label = gen_new_label();
count = tcg_temp_local_new_i32();
tcg_gen_ld_i32(count, cpu_env,
-ENV_OFFSET + offsetof(CPUState, icount_decr.u32));
imm = tcg_temp_new_i32();
tcg_gen_movi_i32(imm, 0xdeadbeef);
/* This is a horrid hack to allow fixing up the value later. */
icount_arg = tcg_ctx.gen_opparam_ptr + 1;
tcg_gen_subi_i32(count, count, 0xdeadbeef);
i = tcg_ctx.gen_last_op_idx;
i = tcg_ctx.gen_op_buf[i].args;
icount_arg = &tcg_ctx.gen_opparam_buf[i + 1];
tcg_gen_sub_i32(count, count, imm);
tcg_temp_free_i32(imm);
tcg_gen_brcondi_i32(TCG_COND_LT, count, 0, icount_label);
tcg_gen_st16_i32(count, cpu_env,
@ -48,6 +57,9 @@ static void gen_tb_end(TranslationBlock *tb, int num_insns)
gen_set_label(icount_label);
tcg_gen_exit_tb((uintptr_t)tb + TB_EXIT_ICOUNT_EXPIRED);
}
/* Terminate the linked list. */
tcg_ctx.gen_op_buf[tcg_ctx.gen_last_op_idx].next = -1;
}
static inline void gen_io_start(void)

16
target-alpha/translate.c
View File

@ -2790,7 +2790,6 @@ static inline void gen_intermediate_code_internal(AlphaCPU *cpu,
target_ulong pc_start;
target_ulong pc_mask;
uint32_t insn;
uint16_t *gen_opc_end;
CPUBreakpoint *bp;
int j, lj = -1;
ExitStatus ret;
@ -2798,7 +2797,6 @@ static inline void gen_intermediate_code_internal(AlphaCPU *cpu,
int max_insns;
pc_start = tb->pc;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
ctx.tb = tb;
ctx.pc = pc_start;
@ -2839,11 +2837,12 @@ static inline void gen_intermediate_code_internal(AlphaCPU *cpu,
}
}
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j)
while (lj < j) {
tcg_ctx.gen_opc_instr_start[lj++] = 0;
}
}
tcg_ctx.gen_opc_pc[lj] = ctx.pc;
tcg_ctx.gen_opc_instr_start[lj] = 1;
@ -2881,7 +2880,7 @@ static inline void gen_intermediate_code_internal(AlphaCPU *cpu,
or exhaust instruction count, stop generation. */
if (ret == NO_EXIT
&& ((ctx.pc & pc_mask) == 0
|| tcg_ctx.gen_opc_ptr >= gen_opc_end
|| tcg_op_buf_full()
|| num_insns >= max_insns
|| singlestep
|| ctx.singlestep_enabled)) {
@ -2912,12 +2911,13 @@ static inline void gen_intermediate_code_internal(AlphaCPU *cpu,
}
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j)
while (lj <= j) {
tcg_ctx.gen_opc_instr_start[lj++] = 0;
}
} else {
tb->size = ctx.pc - pc_start;
tb->icount = num_insns;

10
target-arm/translate-a64.c
View File

@ -10920,7 +10920,6 @@ void gen_intermediate_code_internal_a64(ARMCPU *cpu,
CPUARMState *env = &cpu->env;
DisasContext dc1, *dc = &dc1;
CPUBreakpoint *bp;
uint16_t *gen_opc_end;
int j, lj;
target_ulong pc_start;
target_ulong next_page_start;
@ -10931,8 +10930,6 @@ void gen_intermediate_code_internal_a64(ARMCPU *cpu,
dc->tb = tb;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
dc->is_jmp = DISAS_NEXT;
dc->pc = pc_start;
dc->singlestep_enabled = cs->singlestep_enabled;
@ -11002,7 +10999,7 @@ void gen_intermediate_code_internal_a64(ARMCPU *cpu,
}
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j) {
@ -11052,7 +11049,7 @@ void gen_intermediate_code_internal_a64(ARMCPU *cpu,
* ensures prefetch aborts occur at the right place.
*/
num_insns++;
} while (!dc->is_jmp && tcg_ctx.gen_opc_ptr < gen_opc_end &&
} while (!dc->is_jmp && !tcg_op_buf_full() &&
!cs->singlestep_enabled &&
!singlestep &&
!dc->ss_active &&
@ -11112,7 +11109,6 @@ void gen_intermediate_code_internal_a64(ARMCPU *cpu,
done_generating:
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
#ifdef DEBUG_DISAS
if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)) {
@ -11124,7 +11120,7 @@ done_generating:
}
#endif
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j) {
tcg_ctx.gen_opc_instr_start[lj++] = 0;

10
target-arm/translate.c
View File

@ -11025,7 +11025,6 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu,
CPUARMState *env = &cpu->env;
DisasContext dc1, *dc = &dc1;
CPUBreakpoint *bp;
uint16_t *gen_opc_end;
int j, lj;
target_ulong pc_start;
target_ulong next_page_start;
@ -11046,8 +11045,6 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu,
dc->tb = tb;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
dc->is_jmp = DISAS_NEXT;
dc->pc = pc_start;
dc->singlestep_enabled = cs->singlestep_enabled;
@ -11182,7 +11179,7 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu,
}
}
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j)
@ -11248,7 +11245,7 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu,
* Also stop translation when a page boundary is reached. This
* ensures prefetch aborts occur at the right place. */
num_insns ++;
} while (!dc->is_jmp && tcg_ctx.gen_opc_ptr < gen_opc_end &&
} while (!dc->is_jmp && !tcg_op_buf_full() &&
!cs->singlestep_enabled &&
!singlestep &&
!dc->ss_active &&
@ -11357,7 +11354,6 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu,
done_generating:
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
#ifdef DEBUG_DISAS
if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)) {
@ -11369,7 +11365,7 @@ done_generating:
}
#endif
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j)
tcg_ctx.gen_opc_instr_start[lj++] = 0;

15
target-cris/translate.c
View File

@ -3116,7 +3116,6 @@ gen_intermediate_code_internal(CRISCPU *cpu, TranslationBlock *tb,
{
CPUState *cs = CPU(cpu);
CPUCRISState *env = &cpu->env;
uint16_t *gen_opc_end;
uint32_t pc_start;
unsigned int insn_len;
int j, lj;
@ -3142,8 +3141,6 @@ gen_intermediate_code_internal(CRISCPU *cpu, TranslationBlock *tb,
dc->cpu = cpu;
dc->tb = tb;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
dc->is_jmp = DISAS_NEXT;
dc->ppc = pc_start;
dc->pc = pc_start;
@ -3207,7 +3204,7 @@ gen_intermediate_code_internal(CRISCPU *cpu, TranslationBlock *tb,
check_breakpoint(env, dc);
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j) {
@ -3291,7 +3288,7 @@ gen_intermediate_code_internal(CRISCPU *cpu, TranslationBlock *tb,
break;
}
} while (!dc->is_jmp && !dc->cpustate_changed
&& tcg_ctx.gen_opc_ptr < gen_opc_end
&& !tcg_op_buf_full()
&& !singlestep
&& (dc->pc < next_page_start)
&& num_insns < max_insns);
@ -3344,9 +3341,9 @@ gen_intermediate_code_internal(CRISCPU *cpu, TranslationBlock *tb,
}
}
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j) {
tcg_ctx.gen_opc_instr_start[lj++] = 0;
@ -3361,8 +3358,8 @@ gen_intermediate_code_internal(CRISCPU *cpu, TranslationBlock *tb,
if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)) {
log_target_disas(env, pc_start, dc->pc - pc_start,
env->pregs[PR_VR]);
qemu_log("\nisize=%d osize=%td\n",
dc->pc - pc_start, tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf);
qemu_log("\nisize=%d osize=%d\n",
dc->pc - pc_start, tcg_op_buf_count());
}
#endif
#endif

11
target-i386/translate.c
View File

@ -7913,7 +7913,6 @@ static inline void gen_intermediate_code_internal(X86CPU *cpu,
CPUX86State *env = &cpu->env;
DisasContext dc1, *dc = &dc1;
target_ulong pc_ptr;
uint16_t *gen_opc_end;
CPUBreakpoint *bp;
int j, lj;
uint64_t flags;
@ -7993,8 +7992,6 @@ static inline void gen_intermediate_code_internal(X86CPU *cpu,
cpu_ptr1 = tcg_temp_new_ptr();
cpu_cc_srcT = tcg_temp_local_new();
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
dc->is_jmp = DISAS_NEXT;
pc_ptr = pc_start;
lj = -1;
@ -8015,7 +8012,7 @@ static inline void gen_intermediate_code_internal(X86CPU *cpu,
}
}
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j)
@ -8060,7 +8057,7 @@ static inline void gen_intermediate_code_internal(X86CPU *cpu,
break;
}
/* if too long translation, stop generation too */
if (tcg_ctx.gen_opc_ptr >= gen_opc_end ||
if (tcg_op_buf_full() ||
(pc_ptr - pc_start) >= (TARGET_PAGE_SIZE - 32) ||
num_insns >= max_insns) {
gen_jmp_im(pc_ptr - dc->cs_base);
@ -8077,10 +8074,10 @@ static inline void gen_intermediate_code_internal(X86CPU *cpu,
gen_io_end();
done_generating:
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
/* we don't forget to fill the last values */
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j)
tcg_ctx.gen_opc_instr_start[lj++] = 0;

16
target-lm32/translate.c
View File

@ -1062,7 +1062,6 @@ void gen_intermediate_code_internal(LM32CPU *cpu,
CPUState *cs = CPU(cpu);
CPULM32State *env = &cpu->env;
struct DisasContext ctx, *dc = &ctx;
uint16_t *gen_opc_end;
uint32_t pc_start;
int j, lj;
uint32_t next_page_start;
@ -1075,8 +1074,6 @@ void gen_intermediate_code_internal(LM32CPU *cpu,
dc->num_watchpoints = cpu->num_watchpoints;
dc->tb = tb;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
dc->is_jmp = DISAS_NEXT;
dc->pc = pc_start;
dc->singlestep_enabled = cs->singlestep_enabled;
@ -1100,7 +1097,7 @@ void gen_intermediate_code_internal(LM32CPU *cpu,
check_breakpoint(env, dc);
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j) {
@ -1124,7 +1121,7 @@ void gen_intermediate_code_internal(LM32CPU *cpu,
num_insns++;
} while (!dc->is_jmp
&& tcg_ctx.gen_opc_ptr < gen_opc_end
&& !tcg_op_buf_full()
&& !cs->singlestep_enabled
&& !singlestep
&& (dc->pc < next_page_start)
@ -1158,9 +1155,9 @@ void gen_intermediate_code_internal(LM32CPU *cpu,
}
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j) {
tcg_ctx.gen_opc_instr_start[lj++] = 0;
@ -1174,9 +1171,8 @@ void gen_intermediate_code_internal(LM32CPU *cpu,
if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)) {
qemu_log("\n");
log_target_disas(env, pc_start, dc->pc - pc_start, 0);
qemu_log("\nisize=%d osize=%td\n",
dc->pc - pc_start, tcg_ctx.gen_opc_ptr -
tcg_ctx.gen_opc_buf);
qemu_log("\nisize=%d osize=%d\n",
dc->pc - pc_start, tcg_op_buf_count());
}
#endif
}

10
target-m68k/translate.c
View File

@ -2980,7 +2980,6 @@ gen_intermediate_code_internal(M68kCPU *cpu, TranslationBlock *tb,
CPUState *cs = CPU(cpu);
CPUM68KState *env = &cpu->env;
DisasContext dc1, *dc = &dc1;
uint16_t *gen_opc_end;
CPUBreakpoint *bp;
int j, lj;
target_ulong pc_start;
@ -2993,8 +2992,6 @@ gen_intermediate_code_internal(M68kCPU *cpu, TranslationBlock *tb,
dc->tb = tb;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
dc->env = env;
dc->is_jmp = DISAS_NEXT;
dc->pc = pc_start;
@ -3026,7 +3023,7 @@ gen_intermediate_code_internal(M68kCPU *cpu, TranslationBlock *tb,
break;
}
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j)
@ -3041,7 +3038,7 @@ gen_intermediate_code_internal(M68kCPU *cpu, TranslationBlock *tb,
dc->insn_pc = dc->pc;
disas_m68k_insn(env, dc);
num_insns++;
} while (!dc->is_jmp && tcg_ctx.gen_opc_ptr < gen_opc_end &&
} while (!dc->is_jmp && !tcg_op_buf_full() &&
!cs->singlestep_enabled &&
!singlestep &&
(pc_offset) < (TARGET_PAGE_SIZE - 32) &&
@ -3075,7 +3072,6 @@ gen_intermediate_code_internal(M68kCPU *cpu, TranslationBlock *tb,
}
}
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
#ifdef DEBUG_DISAS
if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)) {
@ -3086,7 +3082,7 @@ gen_intermediate_code_internal(M68kCPU *cpu, TranslationBlock *tb,
}
#endif
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j)
tcg_ctx.gen_opc_instr_start[lj++] = 0;

22
target-microblaze/translate.c
View File

@ -1673,7 +1673,6 @@ gen_intermediate_code_internal(MicroBlazeCPU *cpu, TranslationBlock *tb,
{
CPUState *cs = CPU(cpu);
CPUMBState *env = &cpu->env;
uint16_t *gen_opc_end;
uint32_t pc_start;
int j, lj;
struct DisasContext ctx;
@ -1688,8 +1687,6 @@ gen_intermediate_code_internal(MicroBlazeCPU *cpu, TranslationBlock *tb,
dc->tb = tb;
org_flags = dc->synced_flags = dc->tb_flags = tb->flags;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
dc->is_jmp = DISAS_NEXT;
dc->jmp = 0;
dc->delayed_branch = !!(dc->tb_flags & D_FLAG);
@ -1732,7 +1729,7 @@ gen_intermediate_code_internal(MicroBlazeCPU *cpu, TranslationBlock *tb,
check_breakpoint(env, dc);
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j)
@ -1795,10 +1792,10 @@ gen_intermediate_code_internal(MicroBlazeCPU *cpu, TranslationBlock *tb,
break;
}
} while (!dc->is_jmp && !dc->cpustate_changed
&& tcg_ctx.gen_opc_ptr < gen_opc_end
&& !singlestep
&& (dc->pc < next_page_start)
&& num_insns < max_insns);
&& !tcg_op_buf_full()
&& !singlestep
&& (dc->pc < next_page_start)
&& num_insns < max_insns);
npc = dc->pc;
if (dc->jmp == JMP_DIRECT || dc->jmp == JMP_DIRECT_CC) {
@ -1846,9 +1843,9 @@ gen_intermediate_code_internal(MicroBlazeCPU *cpu, TranslationBlock *tb,
}
}
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j)
tcg_ctx.gen_opc_instr_start[lj++] = 0;
@ -1864,9 +1861,8 @@ gen_intermediate_code_internal(MicroBlazeCPU *cpu, TranslationBlock *tb,
#if DISAS_GNU
log_target_disas(env, pc_start, dc->pc - pc_start, 0);
#endif
qemu_log("\nisize=%d osize=%td\n",
dc->pc - pc_start, tcg_ctx.gen_opc_ptr -
tcg_ctx.gen_opc_buf);
qemu_log("\nisize=%d osize=%d\n",
dc->pc - pc_start, tcg_op_buf_count());
}
#endif
#endif

10
target-mips/translate.c
View File

@ -19095,7 +19095,6 @@ gen_intermediate_code_internal(MIPSCPU *cpu, TranslationBlock *tb,
CPUMIPSState *env = &cpu->env;
DisasContext ctx;
target_ulong pc_start;
uint16_t *gen_opc_end;
CPUBreakpoint *bp;
int j, lj = -1;
int num_insns;
@ -19107,7 +19106,6 @@ gen_intermediate_code_internal(MIPSCPU *cpu, TranslationBlock *tb,
qemu_log("search pc %d\n", search_pc);
pc_start = tb->pc;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
ctx.pc = pc_start;
ctx.saved_pc = -1;
ctx.singlestep_enabled = cs->singlestep_enabled;
@ -19151,7 +19149,7 @@ gen_intermediate_code_internal(MIPSCPU *cpu, TranslationBlock *tb,
}
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j)
@ -19209,7 +19207,7 @@ gen_intermediate_code_internal(MIPSCPU *cpu, TranslationBlock *tb,
if ((ctx.pc & (TARGET_PAGE_SIZE - 1)) == 0)
break;
if (tcg_ctx.gen_opc_ptr >= gen_opc_end) {
if (tcg_op_buf_full()) {
break;
}
@ -19244,9 +19242,9 @@ gen_intermediate_code_internal(MIPSCPU *cpu, TranslationBlock *tb,
}
done_generating:
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j)
tcg_ctx.gen_opc_instr_start[lj++] = 0;

10
target-moxie/translate.c
View File

@ -827,14 +827,12 @@ gen_intermediate_code_internal(MoxieCPU *cpu, TranslationBlock *tb,
CPUState *cs = CPU(cpu);
DisasContext ctx;
target_ulong pc_start;
uint16_t *gen_opc_end;
CPUBreakpoint *bp;
int j, lj = -1;
CPUMoxieState *env = &cpu->env;
int num_insns;
pc_start = tb->pc;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
ctx.pc = pc_start;
ctx.saved_pc = -1;
ctx.tb = tb;
@ -857,7 +855,7 @@ gen_intermediate_code_internal(MoxieCPU *cpu, TranslationBlock *tb,
}
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j) {
@ -879,7 +877,7 @@ gen_intermediate_code_internal(MoxieCPU *cpu, TranslationBlock *tb,
if ((ctx.pc & (TARGET_PAGE_SIZE - 1)) == 0) {
break;
}
} while (ctx.bstate == BS_NONE && tcg_ctx.gen_opc_ptr < gen_opc_end);
} while (ctx.bstate == BS_NONE && !tcg_op_buf_full());
if (cs->singlestep_enabled) {
tcg_gen_movi_tl(cpu_pc, ctx.pc);
@ -900,9 +898,9 @@ gen_intermediate_code_internal(MoxieCPU *cpu, TranslationBlock *tb,
}
done_generating:
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j) {
tcg_ctx.gen_opc_instr_start[lj++] = 0;

15
target-openrisc/translate.c
View File

@ -1642,7 +1642,6 @@ static inline void gen_intermediate_code_internal(OpenRISCCPU *cpu,
{
CPUState *cs = CPU(cpu);
struct DisasContext ctx, *dc = &ctx;
uint16_t *gen_opc_end;
uint32_t pc_start;
int j, k;
uint32_t next_page_start;
@ -1652,7 +1651,6 @@ static inline void gen_intermediate_code_internal(OpenRISCCPU *cpu,
pc_start = tb->pc;
dc->tb = tb;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
dc->is_jmp = DISAS_NEXT;
dc->ppc = pc_start;
dc->pc = pc_start;
@ -1680,7 +1678,7 @@ static inline void gen_intermediate_code_internal(OpenRISCCPU *cpu,
do {
check_breakpoint(cpu, dc);
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (k < j) {
k++;
while (k < j) {
@ -1721,7 +1719,7 @@ static inline void gen_intermediate_code_internal(OpenRISCCPU *cpu,
}
}
} while (!dc->is_jmp
&& tcg_ctx.gen_opc_ptr < gen_opc_end
&& !tcg_op_buf_full()
&& !cs->singlestep_enabled
&& !singlestep
&& (dc->pc < next_page_start)
@ -1759,9 +1757,9 @@ static inline void gen_intermediate_code_internal(OpenRISCCPU *cpu,
}
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
k++;
while (k <= j) {
tcg_ctx.gen_opc_instr_start[k++] = 0;
@ -1775,9 +1773,8 @@ static inline void gen_intermediate_code_internal(OpenRISCCPU *cpu,
if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)) {
qemu_log("\n");
log_target_disas(&cpu->env, pc_start, dc->pc - pc_start, 0);
qemu_log("\nisize=%d osize=%td\n",
dc->pc - pc_start, tcg_ctx.gen_opc_ptr -
tcg_ctx.gen_opc_buf);
qemu_log("\nisize=%d osize=%d\n",
dc->pc - pc_start, tcg_op_buf_count());
}
#endif
}

11
target-ppc/translate.c
View File

@ -11415,14 +11415,12 @@ static inline void gen_intermediate_code_internal(PowerPCCPU *cpu,
DisasContext ctx, *ctxp = &ctx;
opc_handler_t **table, *handler;
target_ulong pc_start;
uint16_t *gen_opc_end;
CPUBreakpoint *bp;
int j, lj = -1;
int num_insns;
int max_insns;
pc_start = tb->pc;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
ctx.nip = pc_start;
ctx.tb = tb;
ctx.exception = POWERPC_EXCP_NONE;
@ -11481,8 +11479,7 @@ static inline void gen_intermediate_code_internal(PowerPCCPU *cpu,
gen_tb_start(tb);
tcg_clear_temp_count();
/* Set env in case of segfault during code fetch */
while (ctx.exception == POWERPC_EXCP_NONE
&& tcg_ctx.gen_opc_ptr < gen_opc_end) {
while (ctx.exception == POWERPC_EXCP_NONE && !tcg_op_buf_full()) {
if (unlikely(!QTAILQ_EMPTY(&cs->breakpoints))) {
QTAILQ_FOREACH(bp, &cs->breakpoints, entry) {
if (bp->pc == ctx.nip) {
@ -11492,7 +11489,7 @@ static inline void gen_intermediate_code_internal(PowerPCCPU *cpu,
}
}
if (unlikely(search_pc)) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j)
@ -11598,9 +11595,9 @@ static inline void gen_intermediate_code_internal(PowerPCCPU *cpu,
tcg_gen_exit_tb(0);
}
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
if (unlikely(search_pc)) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j)
tcg_ctx.gen_opc_instr_start[lj++] = 0;

11
target-s390x/translate.c
View File

@ -4832,7 +4832,6 @@ static inline void gen_intermediate_code_internal(S390CPU *cpu,
DisasContext dc;
target_ulong pc_start;
uint64_t next_page_start;
uint16_t *gen_opc_end;
int j, lj = -1;
int num_insns, max_insns;
CPUBreakpoint *bp;
@ -4851,8 +4850,6 @@ static inline void gen_intermediate_code_internal(S390CPU *cpu,
dc.cc_op = CC_OP_DYNAMIC;
do_debug = dc.singlestep_enabled = cs->singlestep_enabled;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
next_page_start = (pc_start & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE;
num_insns = 0;
@ -4865,7 +4862,7 @@ static inline void gen_intermediate_code_internal(S390CPU *cpu,
do {
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j) {
@ -4903,7 +4900,7 @@ static inline void gen_intermediate_code_internal(S390CPU *cpu,
or exhaust instruction count, stop generation. */
if (status == NO_EXIT
&& (dc.pc >= next_page_start
|| tcg_ctx.gen_opc_ptr >= gen_opc_end
|| tcg_op_buf_full()
|| num_insns >= max_insns
|| singlestep
|| cs->singlestep_enabled)) {
@ -4938,9 +4935,9 @@ static inline void gen_intermediate_code_internal(S390CPU *cpu,
}
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j) {
tcg_ctx.gen_opc_instr_start[lj++] = 0;

10
target-sh4/translate.c
View File

@ -1865,14 +1865,12 @@ gen_intermediate_code_internal(SuperHCPU *cpu, TranslationBlock *tb,
CPUSH4State *env = &cpu->env;
DisasContext ctx;
target_ulong pc_start;
static uint16_t *gen_opc_end;
CPUBreakpoint *bp;
int i, ii;
int num_insns;
int max_insns;
pc_start = tb->pc;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
ctx.pc = pc_start;
ctx.flags = (uint32_t)tb->flags;
ctx.bstate = BS_NONE;
@ -1891,7 +1889,7 @@ gen_intermediate_code_internal(SuperHCPU *cpu, TranslationBlock *tb,
if (max_insns == 0)
max_insns = CF_COUNT_MASK;
gen_tb_start(tb);
while (ctx.bstate == BS_NONE && tcg_ctx.gen_opc_ptr < gen_opc_end) {
while (ctx.bstate == BS_NONE && !tcg_op_buf_full()) {
if (unlikely(!QTAILQ_EMPTY(&cs->breakpoints))) {
QTAILQ_FOREACH(bp, &cs->breakpoints, entry) {
if (ctx.pc == bp->pc) {
@ -1904,7 +1902,7 @@ gen_intermediate_code_internal(SuperHCPU *cpu, TranslationBlock *tb,
}
}
if (search_pc) {
i = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
i = tcg_op_buf_count();
if (ii < i) {
ii++;
while (ii < i)
@ -1962,9 +1960,9 @@ gen_intermediate_code_internal(SuperHCPU *cpu, TranslationBlock *tb,
}
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
if (search_pc) {
i = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
i = tcg_op_buf_count();
ii++;
while (ii <= i)
tcg_ctx.gen_opc_instr_start[ii++] = 0;

10
target-sparc/translate.c
View File

@ -5223,7 +5223,6 @@ static inline void gen_intermediate_code_internal(SPARCCPU *cpu,
CPUState *cs = CPU(cpu);
CPUSPARCState *env = &cpu->env;
target_ulong pc_start, last_pc;
uint16_t *gen_opc_end;
DisasContext dc1, *dc = &dc1;
CPUBreakpoint *bp;
int j, lj = -1;
@ -5243,7 +5242,6 @@ static inline void gen_intermediate_code_internal(SPARCCPU *cpu,
dc->fpu_enabled = tb_fpu_enabled(tb->flags);
dc->address_mask_32bit = tb_am_enabled(tb->flags);
dc->singlestep = (cs->singlestep_enabled || singlestep);
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
num_insns = 0;
max_insns = tb->cflags & CF_COUNT_MASK;
@ -5265,7 +5263,7 @@ static inline void gen_intermediate_code_internal(SPARCCPU *cpu,
}
if (spc) {
qemu_log("Search PC...\n");
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j)
@ -5298,7 +5296,7 @@ static inline void gen_intermediate_code_internal(SPARCCPU *cpu,
if (dc->singlestep) {
break;
}
} while ((tcg_ctx.gen_opc_ptr < gen_opc_end) &&
} while (!tcg_op_buf_full() &&
(dc->pc - pc_start) < (TARGET_PAGE_SIZE - 32) &&
num_insns < max_insns);
@ -5320,9 +5318,9 @@ static inline void gen_intermediate_code_internal(SPARCCPU *cpu,
}
}
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
if (spc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j)
tcg_ctx.gen_opc_instr_start[lj++] = 0;

5
target-tricore/translate.c
View File

@ -5500,7 +5500,6 @@ gen_intermediate_code_internal(TriCoreCPU *cpu, struct TranslationBlock *tb,
DisasContext ctx;
target_ulong pc_start;
int num_insns;
uint16_t *gen_opc_end;
if (search_pc) {
qemu_log("search pc %d\n", search_pc);
@ -5508,7 +5507,6 @@ gen_intermediate_code_internal(TriCoreCPU *cpu, struct TranslationBlock *tb,
num_insns = 0;
pc_start = tb->pc;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
ctx.pc = pc_start;
ctx.saved_pc = -1;
ctx.tb = tb;
@ -5524,7 +5522,7 @@ gen_intermediate_code_internal(TriCoreCPU *cpu, struct TranslationBlock *tb,
num_insns++;
if (tcg_ctx.gen_opc_ptr >= gen_opc_end) {
if (tcg_op_buf_full()) {
gen_save_pc(ctx.next_pc);
tcg_gen_exit_tb(0);
break;
@ -5538,7 +5536,6 @@ gen_intermediate_code_internal(TriCoreCPU *cpu, struct TranslationBlock *tb,
}
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
if (search_pc) {
printf("done_generating search pc\n");
} else {

10
target-unicore32/translate.c
View File

@ -1877,7 +1877,6 @@ static inline void gen_intermediate_code_internal(UniCore32CPU *cpu,
CPUUniCore32State *env = &cpu->env;
DisasContext dc1, *dc = &dc1;
CPUBreakpoint *bp;
uint16_t *gen_opc_end;
int j, lj;
target_ulong pc_start;
uint32_t next_page_start;
@ -1891,8 +1890,6 @@ static inline void gen_intermediate_code_internal(UniCore32CPU *cpu,
dc->tb = tb;
gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
dc->is_jmp = DISAS_NEXT;
dc->pc = pc_start;
dc->singlestep_enabled = cs->singlestep_enabled;
@ -1933,7 +1930,7 @@ static inline void gen_intermediate_code_internal(UniCore32CPU *cpu,
}
}
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j) {
@ -1965,7 +1962,7 @@ static inline void gen_intermediate_code_internal(UniCore32CPU *cpu,
* Also stop translation when a page boundary is reached. This
* ensures prefetch aborts occur at the right place. */
num_insns++;
} while (!dc->is_jmp && tcg_ctx.gen_opc_ptr < gen_opc_end &&
} while (!dc->is_jmp && !tcg_op_buf_full() &&
!cs->singlestep_enabled &&
!singlestep &&
dc->pc < next_page_start &&
@ -2037,7 +2034,6 @@ static inline void gen_intermediate_code_internal(UniCore32CPU *cpu,
done_generating:
gen_tb_end(tb, num_insns);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
#ifdef DEBUG_DISAS
if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)) {
@ -2048,7 +2044,7 @@ done_generating:
}
#endif
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
lj++;
while (lj <= j) {
tcg_ctx.gen_opc_instr_start[lj++] = 0;

8
target-xtensa/translate.c
View File

@ -3021,7 +3021,6 @@ void gen_intermediate_code_internal(XtensaCPU *cpu,
DisasContext dc;
int insn_count = 0;
int j, lj = -1;
uint16_t *gen_opc_end = tcg_ctx.gen_opc_buf + OPC_MAX_SIZE;
int max_insns = tb->cflags & CF_COUNT_MASK;
uint32_t pc_start = tb->pc;
uint32_t next_page_start =
@ -3065,7 +3064,7 @@ void gen_intermediate_code_internal(XtensaCPU *cpu,
check_breakpoint(env, &dc);
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
if (lj < j) {
lj++;
while (lj < j) {
@ -3117,7 +3116,7 @@ void gen_intermediate_code_internal(XtensaCPU *cpu,
insn_count < max_insns &&
dc.pc < next_page_start &&
dc.pc + xtensa_insn_len(env, &dc) <= next_page_start &&
tcg_ctx.gen_opc_ptr < gen_opc_end);
!tcg_op_buf_full());
reset_litbase(&dc);
reset_sar_tracker(&dc);
@ -3133,7 +3132,6 @@ void gen_intermediate_code_internal(XtensaCPU *cpu,
gen_jumpi(&dc, dc.pc, 0);
}
gen_tb_end(tb, insn_count);
*tcg_ctx.gen_opc_ptr = INDEX_op_end;
#ifdef DEBUG_DISAS
if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)) {
@ -3144,7 +3142,7 @@ void gen_intermediate_code_internal(XtensaCPU *cpu,
}
#endif
if (search_pc) {
j = tcg_ctx.gen_opc_ptr - tcg_ctx.gen_opc_buf;
j = tcg_op_buf_count();
memset(tcg_ctx.gen_opc_instr_start + lj + 1, 0,
(j - lj) * sizeof(tcg_ctx.gen_opc_instr_start[0]));
} else {

307
tcg/optimize.c
View File

@ -67,6 +67,37 @@ static void reset_temp(TCGArg temp)
temps[temp].mask = -1;
}
static TCGOp *insert_op_before(TCGContext *s, TCGOp *old_op,
TCGOpcode opc, int nargs)
{
int oi = s->gen_next_op_idx;
int pi = s->gen_next_parm_idx;
int prev = old_op->prev;
int next = old_op - s->gen_op_buf;
TCGOp *new_op;
tcg_debug_assert(oi < OPC_BUF_SIZE);
tcg_debug_assert(pi + nargs <= OPPARAM_BUF_SIZE);
s->gen_next_op_idx = oi + 1;
s->gen_next_parm_idx = pi + nargs;
new_op = &s->gen_op_buf[oi];
*new_op = (TCGOp){
.opc = opc,
.args = pi,
.prev = prev,
.next = next
};
if (prev >= 0) {
s->gen_op_buf[prev].next = oi;
} else {
s->gen_first_op_idx = oi;
}
old_op->prev = oi;
return new_op;
}
/* Reset all temporaries, given that there are NB_TEMPS of them. */
static void reset_all_temps(int nb_temps)
{
@ -162,13 +193,13 @@ static bool temps_are_copies(TCGArg arg1, TCGArg arg2)
return false;
}
static void tcg_opt_gen_mov(TCGContext *s, int op_index, TCGArg *gen_args,
static void tcg_opt_gen_mov(TCGContext *s, TCGOp *op, TCGArg *args,
TCGOpcode old_op, TCGArg dst, TCGArg src)
{
TCGOpcode new_op = op_to_mov(old_op);
tcg_target_ulong mask;
s->gen_opc_buf[op_index] = new_op;
op->opc = new_op;
reset_temp(dst);
mask = temps[src].mask;
@ -193,17 +224,17 @@ static void tcg_opt_gen_mov(TCGContext *s, int op_index, TCGArg *gen_args,
temps[src].next_copy = dst;
}
gen_args[0] = dst;
gen_args[1] = src;
args[0] = dst;
args[1] = src;
}
static void tcg_opt_gen_movi(TCGContext *s, int op_index, TCGArg *gen_args,
static void tcg_opt_gen_movi(TCGContext *s, TCGOp *op, TCGArg *args,
TCGOpcode old_op, TCGArg dst, TCGArg val)
{
TCGOpcode new_op = op_to_movi(old_op);
tcg_target_ulong mask;
s->gen_opc_buf[op_index] = new_op;
op->opc = new_op;
reset_temp(dst);
temps[dst].state = TCG_TEMP_CONST;
@ -215,8 +246,8 @@ static void tcg_opt_gen_movi(TCGContext *s, int op_index, TCGArg *gen_args,
}
temps[dst].mask = mask;
gen_args[0] = dst;
gen_args[1] = val;
args[0] = dst;
args[1] = val;
}
static TCGArg do_constant_folding_2(TCGOpcode op, TCGArg x, TCGArg y)
@ -533,11 +564,9 @@ static bool swap_commutative2(TCGArg *p1, TCGArg *p2)
}
/* Propagate constants and copies, fold constant expressions. */
static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
TCGArg *args, TCGOpDef *tcg_op_defs)
static void tcg_constant_folding(TCGContext *s)
{
int nb_ops, op_index, nb_temps, nb_globals;
TCGArg *gen_args;
int oi, oi_next, nb_temps, nb_globals;
/* Array VALS has an element for each temp.
If this temp holds a constant then its value is kept in VALS' element.
@ -548,24 +577,23 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
nb_globals = s->nb_globals;
reset_all_temps(nb_temps);
nb_ops = tcg_opc_ptr - s->gen_opc_buf;
gen_args = args;
for (op_index = 0; op_index < nb_ops; op_index++) {
TCGOpcode op = s->gen_opc_buf[op_index];
const TCGOpDef *def = &tcg_op_defs[op];
for (oi = s->gen_first_op_idx; oi >= 0; oi = oi_next) {
tcg_target_ulong mask, partmask, affected;
int nb_oargs, nb_iargs, nb_args, i;
int nb_oargs, nb_iargs, i;
TCGArg tmp;
if (op == INDEX_op_call) {
*gen_args++ = tmp = *args++;
nb_oargs = tmp >> 16;
nb_iargs = tmp & 0xffff;
nb_args = nb_oargs + nb_iargs + def->nb_cargs;
TCGOp * const op = &s->gen_op_buf[oi];
TCGArg * const args = &s->gen_opparam_buf[op->args];
TCGOpcode opc = op->opc;
const TCGOpDef *def = &tcg_op_defs[opc];
oi_next = op->next;
if (opc == INDEX_op_call) {
nb_oargs = op->callo;
nb_iargs = op->calli;
} else {
nb_oargs = def->nb_oargs;
nb_iargs = def->nb_iargs;
nb_args = def->nb_args;
}
/* Do copy propagation */
@ -576,7 +604,7 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
}
/* For commutative operations make constant second argument */
switch (op) {
switch (opc) {
CASE_OP_32_64(add):
CASE_OP_32_64(mul):
CASE_OP_32_64(and):
@ -634,7 +662,7 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
/* Simplify expressions for "shift/rot r, 0, a => movi r, 0",
and "sub r, 0, a => neg r, a" case. */
switch (op) {
switch (opc) {
CASE_OP_32_64(shl):
CASE_OP_32_64(shr):
CASE_OP_32_64(sar):
@ -642,9 +670,7 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
CASE_OP_32_64(rotr):
if (temps[args[1]].state == TCG_TEMP_CONST
&& temps[args[1]].val == 0) {
tcg_opt_gen_movi(s, op_index, gen_args, op, args[0], 0);
args += 3;
gen_args += 2;
tcg_opt_gen_movi(s, op, args, opc, args[0], 0);
continue;
}
break;
@ -657,7 +683,7 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
/* Proceed with possible constant folding. */
break;
}
if (op == INDEX_op_sub_i32) {
if (opc == INDEX_op_sub_i32) {
neg_op = INDEX_op_neg_i32;
have_neg = TCG_TARGET_HAS_neg_i32;
} else {
@ -669,12 +695,9 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
}
if (temps[args[1]].state == TCG_TEMP_CONST
&& temps[args[1]].val == 0) {
s->gen_opc_buf[op_index] = neg_op;
op->opc = neg_op;
reset_temp(args[0]);
gen_args[0] = args[0];
gen_args[1] = args[2];
args += 3;
gen_args += 2;
args[1] = args[2];
continue;
}
}
@ -728,12 +751,9 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
if (!have_not) {
break;
}
s->gen_opc_buf[op_index] = not_op;
op->opc = not_op;
reset_temp(args[0]);
gen_args[0] = args[0];
gen_args[1] = args[i];
args += 3;
gen_args += 2;
args[1] = args[i];
continue;
}
default:
@ -741,7 +761,7 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
}
/* Simplify expression for "op r, a, const => mov r, a" cases */
switch (op) {
switch (opc) {
CASE_OP_32_64(add):
CASE_OP_32_64(sub):
CASE_OP_32_64(shl):
@ -769,12 +789,10 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
break;
do_mov3:
if (temps_are_copies(args[0], args[1])) {
s->gen_opc_buf[op_index] = INDEX_op_nop;
tcg_op_remove(s, op);
} else {
tcg_opt_gen_mov(s, op_index, gen_args, op, args[0], args[1]);
gen_args += 2;
tcg_opt_gen_mov(s, op, args, opc, args[0], args[1]);
}
args += 3;
continue;
default:
break;
@ -784,7 +802,7 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
output argument is supported. */
mask = -1;
affected = -1;
switch (op) {
switch (opc) {
CASE_OP_32_64(ext8s):
if ((temps[args[1]].mask & 0x80) != 0) {
break;
@ -923,38 +941,31 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
if (partmask == 0) {
assert(nb_oargs == 1);
tcg_opt_gen_movi(s, op_index, gen_args, op, args[0], 0);
args += nb_args;
gen_args += 2;
tcg_opt_gen_movi(s, op, args, opc, args[0], 0);
continue;
}
if (affected == 0) {
assert(nb_oargs == 1);
if (temps_are_copies(args[0], args[1])) {
s->gen_opc_buf[op_index] = INDEX_op_nop;
tcg_op_remove(s, op);
} else if (temps[args[1]].state != TCG_TEMP_CONST) {
tcg_opt_gen_mov(s, op_index, gen_args, op, args[0], args[1]);
gen_args += 2;
tcg_opt_gen_mov(s, op, args, opc, args[0], args[1]);
} else {
tcg_opt_gen_movi(s, op_index, gen_args, op,
tcg_opt_gen_movi(s, op, args, opc,
args[0], temps[args[1]].val);
gen_args += 2;
}
args += nb_args;
continue;
}
/* Simplify expression for "op r, a, 0 => movi r, 0" cases */
switch (op) {
switch (opc) {
CASE_OP_32_64(and):
CASE_OP_32_64(mul):
CASE_OP_32_64(muluh):
CASE_OP_32_64(mulsh):
if ((temps[args[2]].state == TCG_TEMP_CONST
&& temps[args[2]].val == 0)) {
tcg_opt_gen_movi(s, op_index, gen_args, op, args[0], 0);
args += 3;
gen_args += 2;
tcg_opt_gen_movi(s, op, args, opc, args[0], 0);
continue;
}
break;
@ -963,18 +974,15 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
}
/* Simplify expression for "op r, a, a => mov r, a" cases */
switch (op) {
switch (opc) {
CASE_OP_32_64(or):
CASE_OP_32_64(and):
if (temps_are_copies(args[1], args[2])) {
if (temps_are_copies(args[0], args[1])) {
s->gen_opc_buf[op_index] = INDEX_op_nop;
tcg_op_remove(s, op);
} else {
tcg_opt_gen_mov(s, op_index, gen_args, op,
args[0], args[1]);
gen_args += 2;
tcg_opt_gen_mov(s, op, args, opc, args[0], args[1]);
}
args += 3;
continue;
}
break;
@ -983,14 +991,12 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
}
/* Simplify expression for "op r, a, a => movi r, 0" cases */
switch (op) {
switch (opc) {
CASE_OP_32_64(andc):
CASE_OP_32_64(sub):
CASE_OP_32_64(xor):
if (temps_are_copies(args[1], args[2])) {
tcg_opt_gen_movi(s, op_index, gen_args, op, args[0], 0);
gen_args += 2;
args += 3;
tcg_opt_gen_movi(s, op, args, opc, args[0], 0);
continue;
}
break;
@ -1001,17 +1007,14 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
/* Propagate constants through copy operations and do constant
folding. Constants will be substituted to arguments by register
allocator where needed and possible. Also detect copies. */
switch (op) {
switch (opc) {
CASE_OP_32_64(mov):
if (temps_are_copies(args[0], args[1])) {
args += 2;
s->gen_opc_buf[op_index] = INDEX_op_nop;
tcg_op_remove(s, op);
break;
}
if (temps[args[1]].state != TCG_TEMP_CONST) {
tcg_opt_gen_mov(s, op_index, gen_args, op, args[0], args[1]);
gen_args += 2;
args += 2;
tcg_opt_gen_mov(s, op, args, opc, args[0], args[1]);
break;
}
/* Source argument is constant. Rewrite the operation and
@ -1019,9 +1022,7 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
args[1] = temps[args[1]].val;
/* fallthrough */
CASE_OP_32_64(movi):
tcg_opt_gen_movi(s, op_index, gen_args, op, args[0], args[1]);
gen_args += 2;
args += 2;
tcg_opt_gen_movi(s, op, args, opc, args[0], args[1]);
break;
CASE_OP_32_64(not):
@ -1033,20 +1034,16 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
case INDEX_op_ext32s_i64:
case INDEX_op_ext32u_i64:
if (temps[args[1]].state == TCG_TEMP_CONST) {
tmp = do_constant_folding(op, temps[args[1]].val, 0);
tcg_opt_gen_movi(s, op_index, gen_args, op, args[0], tmp);
gen_args += 2;
args += 2;
tmp = do_constant_folding(opc, temps[args[1]].val, 0);
tcg_opt_gen_movi(s, op, args, opc, args[0], tmp);
break;
}
goto do_default;
case INDEX_op_trunc_shr_i32:
if (temps[args[1]].state == TCG_TEMP_CONST) {
tmp = do_constant_folding(op, temps[args[1]].val, args[2]);
tcg_opt_gen_movi(s, op_index, gen_args, op, args[0], tmp);
gen_args += 2;
args += 3;
tmp = do_constant_folding(opc, temps[args[1]].val, args[2]);
tcg_opt_gen_movi(s, op, args, opc, args[0], tmp);
break;
}
goto do_default;
@ -1075,11 +1072,9 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
CASE_OP_32_64(remu):
if (temps[args[1]].state == TCG_TEMP_CONST
&& temps[args[2]].state == TCG_TEMP_CONST) {
tmp = do_constant_folding(op, temps[args[1]].val,
tmp = do_constant_folding(opc, temps[args[1]].val,
temps[args[2]].val);
tcg_opt_gen_movi(s, op_index, gen_args, op, args[0], tmp);
gen_args += 2;
args += 3;
tcg_opt_gen_movi(s, op, args, opc, args[0], tmp);
break;
}
goto do_default;
@ -1089,54 +1084,44 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
&& temps[args[2]].state == TCG_TEMP_CONST) {
tmp = deposit64(temps[args[1]].val, args[3], args[4],
temps[args[2]].val);
tcg_opt_gen_movi(s, op_index, gen_args, op, args[0], tmp);
gen_args += 2;
args += 5;
tcg_opt_gen_movi(s, op, args, opc, args[0], tmp);
break;
}
goto do_default;
CASE_OP_32_64(setcond):
tmp = do_constant_folding_cond(op, args[1], args[2], args[3]);
tmp = do_constant_folding_cond(opc, args[1], args[2], args[3]);
if (tmp != 2) {
tcg_opt_gen_movi(s, op_index, gen_args, op, args[0], tmp);
gen_args += 2;
args += 4;
tcg_opt_gen_movi(s, op, args, opc, args[0], tmp);
break;
}
goto do_default;
CASE_OP_32_64(brcond):
tmp = do_constant_folding_cond(op, args[0], args[1], args[2]);
tmp = do_constant_folding_cond(opc, args[0], args[1], args[2]);
if (tmp != 2) {
if (tmp) {
reset_all_temps(nb_temps);
s->gen_opc_buf[op_index] = INDEX_op_br;
gen_args[0] = args[3];
gen_args += 1;
op->opc = INDEX_op_br;
args[0] = args[3];
} else {
s->gen_opc_buf[op_index] = INDEX_op_nop;
tcg_op_remove(s, op);
}
args += 4;
break;
}
goto do_default;
CASE_OP_32_64(movcond):
tmp = do_constant_folding_cond(op, args[1], args[2], args[5]);
tmp = do_constant_folding_cond(opc, args[1], args[2], args[5]);
if (tmp != 2) {
if (temps_are_copies(args[0], args[4-tmp])) {
s->gen_opc_buf[op_index] = INDEX_op_nop;
tcg_op_remove(s, op);
} else if (temps[args[4-tmp]].state == TCG_TEMP_CONST) {
tcg_opt_gen_movi(s, op_index, gen_args, op,
tcg_opt_gen_movi(s, op, args, opc,
args[0], temps[args[4-tmp]].val);
gen_args += 2;
} else {
tcg_opt_gen_mov(s, op_index, gen_args, op,
args[0], args[4-tmp]);
gen_args += 2;
tcg_opt_gen_mov(s, op, args, opc, args[0], args[4-tmp]);
}
args += 6;
break;
}
goto do_default;
@ -1154,24 +1139,22 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
uint64_t a = ((uint64_t)ah << 32) | al;
uint64_t b = ((uint64_t)bh << 32) | bl;
TCGArg rl, rh;
TCGOp *op2 = insert_op_before(s, op, INDEX_op_movi_i32, 2);
TCGArg *args2 = &s->gen_opparam_buf[op2->args];
if (op == INDEX_op_add2_i32) {
if (opc == INDEX_op_add2_i32) {
a += b;
} else {
a -= b;
}
/* We emit the extra nop when we emit the add2/sub2. */
assert(s->gen_opc_buf[op_index + 1] == INDEX_op_nop);
rl = args[0];
rh = args[1];
tcg_opt_gen_movi(s, op_index, &gen_args[0],
op, rl, (uint32_t)a);
tcg_opt_gen_movi(s, ++op_index, &gen_args[2],
op, rh, (uint32_t)(a >> 32));
gen_args += 4;
args += 6;
tcg_opt_gen_movi(s, op, args, opc, rl, (uint32_t)a);
tcg_opt_gen_movi(s, op2, args2, opc, rh, (uint32_t)(a >> 32));
/* We've done all we need to do with the movi. Skip it. */
oi_next = op2->next;
break;
}
goto do_default;
@ -1183,18 +1166,16 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
uint32_t b = temps[args[3]].val;
uint64_t r = (uint64_t)a * b;
TCGArg rl, rh;
/* We emit the extra nop when we emit the mulu2. */
assert(s->gen_opc_buf[op_index + 1] == INDEX_op_nop);
TCGOp *op2 = insert_op_before(s, op, INDEX_op_movi_i32, 2);
TCGArg *args2 = &s->gen_opparam_buf[op2->args];
rl = args[0];
rh = args[1];
tcg_opt_gen_movi(s, op_index, &gen_args[0],
op, rl, (uint32_t)r);
tcg_opt_gen_movi(s, ++op_index, &gen_args[2],
op, rh, (uint32_t)(r >> 32));
gen_args += 4;
args += 4;
tcg_opt_gen_movi(s, op, args, opc, rl, (uint32_t)r);
tcg_opt_gen_movi(s, op2, args2, opc, rh, (uint32_t)(r >> 32));
/* We've done all we need to do with the movi. Skip it. */
oi_next = op2->next;
break;
}
goto do_default;
@ -1205,12 +1186,11 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
if (tmp) {
do_brcond_true:
reset_all_temps(nb_temps);
s->gen_opc_buf[op_index] = INDEX_op_br;
gen_args[0] = args[5];
gen_args += 1;
op->opc = INDEX_op_br;
args[0] = args[5];
} else {
do_brcond_false:
s->gen_opc_buf[op_index] = INDEX_op_nop;
tcg_op_remove(s, op);
}
} else if ((args[4] == TCG_COND_LT || args[4] == TCG_COND_GE)
&& temps[args[2]].state == TCG_TEMP_CONST
@ -1221,12 +1201,11 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
vs the high word of the input. */
do_brcond_high:
reset_all_temps(nb_temps);
s->gen_opc_buf[op_index] = INDEX_op_brcond_i32;
gen_args[0] = args[1];
gen_args[1] = args[3];
gen_args[2] = args[4];
gen_args[3] = args[5];
gen_args += 4;
op->opc = INDEX_op_brcond_i32;
args[0] = args[1];
args[1] = args[3];
args[2] = args[4];
args[3] = args[5];
} else if (args[4] == TCG_COND_EQ) {
/* Simplify EQ comparisons where one of the pairs
can be simplified. */
@ -1246,12 +1225,10 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
}
do_brcond_low:
reset_all_temps(nb_temps);
s->gen_opc_buf[op_index] = INDEX_op_brcond_i32;
gen_args[0] = args[0];
gen_args[1] = args[2];
gen_args[2] = args[4];
gen_args[3] = args[5];
gen_args += 4;
op->opc = INDEX_op_brcond_i32;
args[1] = args[2];
args[2] = args[4];
args[3] = args[5];
} else if (args[4] == TCG_COND_NE) {
/* Simplify NE comparisons where one of the pairs
can be simplified. */
@ -1273,15 +1250,13 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
} else {
goto do_default;
}
args += 6;
break;
case INDEX_op_setcond2_i32:
tmp = do_constant_folding_cond2(&args[1], &args[3], args[5]);
if (tmp != 2) {
do_setcond_const:
tcg_opt_gen_movi(s, op_index, gen_args, op, args[0], tmp);
gen_args += 2;
tcg_opt_gen_movi(s, op, args, opc, args[0], tmp);
} else if ((args[5] == TCG_COND_LT || args[5] == TCG_COND_GE)
&& temps[args[3]].state == TCG_TEMP_CONST
&& temps[args[4]].state == TCG_TEMP_CONST
@ -1290,14 +1265,12 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
/* Simplify LT/GE comparisons vs zero to a single compare
vs the high word of the input. */
do_setcond_high:
s->gen_opc_buf[op_index] = INDEX_op_setcond_i32;
reset_temp(args[0]);
temps[args[0]].mask = 1;
gen_args[0] = args[0];
gen_args[1] = args[2];
gen_args[2] = args[4];
gen_args[3] = args[5];
gen_args += 4;
op->opc = INDEX_op_setcond_i32;
args[1] = args[2];
args[2] = args[4];
args[3] = args[5];
} else if (args[5] == TCG_COND_EQ) {
/* Simplify EQ comparisons where one of the pairs
can be simplified. */
@ -1318,12 +1291,9 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
do_setcond_low:
reset_temp(args[0]);
temps[args[0]].mask = 1;
s->gen_opc_buf[op_index] = INDEX_op_setcond_i32;
gen_args[0] = args[0];
gen_args[1] = args[1];
gen_args[2] = args[3];
gen_args[3] = args[5];
gen_args += 4;
op->opc = INDEX_op_setcond_i32;
args[2] = args[3];
args[3] = args[5];
} else if (args[5] == TCG_COND_NE) {
/* Simplify NE comparisons where one of the pairs
can be simplified. */
@ -1345,7 +1315,6 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
} else {
goto do_default;
}
args += 6;
break;
case INDEX_op_call:
@ -1377,22 +1346,12 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
}
}
}
for (i = 0; i < nb_args; i++) {
gen_args[i] = args[i];
}
args += nb_args;
gen_args += nb_args;
break;
}
}
return gen_args;
}
TCGArg *tcg_optimize(TCGContext *s, uint16_t *tcg_opc_ptr,
TCGArg *args, TCGOpDef *tcg_op_defs)
void tcg_optimize(TCGContext *s)
{
TCGArg *res;
res = tcg_constant_folding(s, tcg_opc_ptr, args, tcg_op_defs);
return res;
tcg_constant_folding(s);
}

1934
tcg/tcg-op.c Normal file
View File

File diff suppressed because it is too large Load Diff

2453
tcg/tcg-op.h
View File

File diff suppressed because it is too large Load Diff

9
tcg/tcg-opc.h
View File

@ -27,15 +27,6 @@
*/
/* predefined ops */
DEF(end, 0, 0, 0, TCG_OPF_NOT_PRESENT) /* must be kept first */
DEF(nop, 0, 0, 0, TCG_OPF_NOT_PRESENT)
DEF(nop1, 0, 0, 1, TCG_OPF_NOT_PRESENT)
DEF(nop2, 0, 0, 2, TCG_OPF_NOT_PRESENT)
DEF(nop3, 0, 0, 3, TCG_OPF_NOT_PRESENT)
/* variable number of parameters */
DEF(nopn, 0, 0, 1, TCG_OPF_NOT_PRESENT)
DEF(discard, 1, 0, 0, TCG_OPF_NOT_PRESENT)
DEF(set_label, 0, 0, 1, TCG_OPF_BB_END | TCG_OPF_NOT_PRESENT)

536
tcg/tcg.c
View File

@ -407,7 +407,6 @@ void tcg_func_start(TCGContext *s)
/* No temps have been previously allocated for size or locality. */
memset(s->free_temps, 0, sizeof(s->free_temps));
s->labels = tcg_malloc(sizeof(TCGLabel) * TCG_MAX_LABELS);
s->nb_labels = 0;
s->current_frame_offset = s->frame_start;
@ -415,8 +414,10 @@ void tcg_func_start(TCGContext *s)
s->goto_tb_issue_mask = 0;
#endif
s->gen_opc_ptr = s->gen_opc_buf;
s->gen_opparam_ptr = s->gen_opparam_buf;
s->gen_first_op_idx = 0;
s->gen_last_op_idx = -1;
s->gen_next_op_idx = 0;
s->gen_next_parm_idx = 0;
s->be = tcg_malloc(sizeof(TCGBackendData));
}
@ -703,9 +704,8 @@ int tcg_check_temp_count(void)
void tcg_gen_callN(TCGContext *s, void *func, TCGArg ret,
int nargs, TCGArg *args)
{
int i, real_args, nb_rets;
int i, real_args, nb_rets, pi, pi_first;
unsigned sizemask, flags;
TCGArg *nparam;
TCGHelperInfo *info;
info = g_hash_table_lookup(s->helpers, (gpointer)func);
@ -758,8 +758,7 @@ void tcg_gen_callN(TCGContext *s, void *func, TCGArg ret,
}
#endif /* TCG_TARGET_EXTEND_ARGS */
*s->gen_opc_ptr++ = INDEX_op_call;
nparam = s->gen_opparam_ptr++;
pi_first = pi = s->gen_next_parm_idx;
if (ret != TCG_CALL_DUMMY_ARG) {
#if defined(__sparc__) && !defined(__arch64__) \
&& !defined(CONFIG_TCG_INTERPRETER)
@ -769,25 +768,25 @@ void tcg_gen_callN(TCGContext *s, void *func, TCGArg ret,
two return temporaries, and reassemble below. */
retl = tcg_temp_new_i64();
reth = tcg_temp_new_i64();
*s->gen_opparam_ptr++ = GET_TCGV_I64(reth);
*s->gen_opparam_ptr++ = GET_TCGV_I64(retl);
s->gen_opparam_buf[pi++] = GET_TCGV_I64(reth);
s->gen_opparam_buf[pi++] = GET_TCGV_I64(retl);
nb_rets = 2;
} else {
*s->gen_opparam_ptr++ = ret;
s->gen_opparam_buf[pi++] = ret;
nb_rets = 1;
}
#else
if (TCG_TARGET_REG_BITS < 64 && (sizemask & 1)) {
#ifdef HOST_WORDS_BIGENDIAN
*s->gen_opparam_ptr++ = ret + 1;
*s->gen_opparam_ptr++ = ret;
s->gen_opparam_buf[pi++] = ret + 1;
s->gen_opparam_buf[pi++] = ret;
#else
*s->gen_opparam_ptr++ = ret;
*s->gen_opparam_ptr++ = ret + 1;
s->gen_opparam_buf[pi++] = ret;
s->gen_opparam_buf[pi++] = ret + 1;
#endif
nb_rets = 2;
} else {
*s->gen_opparam_ptr++ = ret;
s->gen_opparam_buf[pi++] = ret;
nb_rets = 1;
}
#endif
@ -801,7 +800,7 @@ void tcg_gen_callN(TCGContext *s, void *func, TCGArg ret,
#ifdef TCG_TARGET_CALL_ALIGN_ARGS
/* some targets want aligned 64 bit args */
if (real_args & 1) {
*s->gen_opparam_ptr++ = TCG_CALL_DUMMY_ARG;
s->gen_opparam_buf[pi++] = TCG_CALL_DUMMY_ARG;
real_args++;
}
#endif
@ -816,26 +815,42 @@ void tcg_gen_callN(TCGContext *s, void *func, TCGArg ret,
have to get more complicated to differentiate between
stack arguments and register arguments. */
#if defined(HOST_WORDS_BIGENDIAN) != defined(TCG_TARGET_STACK_GROWSUP)
*s->gen_opparam_ptr++ = args[i] + 1;
*s->gen_opparam_ptr++ = args[i];
s->gen_opparam_buf[pi++] = args[i] + 1;
s->gen_opparam_buf[pi++] = args[i];
#else
*s->gen_opparam_ptr++ = args[i];
*s->gen_opparam_ptr++ = args[i] + 1;
s->gen_opparam_buf[pi++] = args[i];
s->gen_opparam_buf[pi++] = args[i] + 1;
#endif
real_args += 2;
continue;
}
*s->gen_opparam_ptr++ = args[i];
s->gen_opparam_buf[pi++] = args[i];
real_args++;
}
*s->gen_opparam_ptr++ = (uintptr_t)func;
*s->gen_opparam_ptr++ = flags;
s->gen_opparam_buf[pi++] = (uintptr_t)func;
s->gen_opparam_buf[pi++] = flags;
*nparam = (nb_rets << 16) | real_args;
i = s->gen_next_op_idx;
tcg_debug_assert(i < OPC_BUF_SIZE);
tcg_debug_assert(pi <= OPPARAM_BUF_SIZE);
/* total parameters, needed to go backward in the instruction stream */
*s->gen_opparam_ptr++ = 1 + nb_rets + real_args + 3;
/* Set links for sequential allocation during translation. */
s->gen_op_buf[i] = (TCGOp){
.opc = INDEX_op_call,
.callo = nb_rets,
.calli = real_args,
.args = pi_first,
.prev = i - 1,
.next = i + 1
};
/* Make sure the calli field didn't overflow. */
tcg_debug_assert(s->gen_op_buf[i].calli == real_args);
s->gen_last_op_idx = i;
s->gen_next_op_idx = i + 1;
s->gen_next_parm_idx = pi;
#if defined(__sparc__) && !defined(__arch64__) \
&& !defined(CONFIG_TCG_INTERPRETER)
@ -870,143 +885,6 @@ void tcg_gen_callN(TCGContext *s, void *func, TCGArg ret,
#endif /* TCG_TARGET_EXTEND_ARGS */
}
#if TCG_TARGET_REG_BITS == 32
void tcg_gen_shifti_i64(TCGv_i64 ret, TCGv_i64 arg1,
int c, int right, int arith)
{
if (c == 0) {
tcg_gen_mov_i32(TCGV_LOW(ret), TCGV_LOW(arg1));
tcg_gen_mov_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1));
} else if (c >= 32) {
c -= 32;
if (right) {
if (arith) {
tcg_gen_sari_i32(TCGV_LOW(ret), TCGV_HIGH(arg1), c);
tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), 31);
} else {
tcg_gen_shri_i32(TCGV_LOW(ret), TCGV_HIGH(arg1), c);
tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
}
} else {
tcg_gen_shli_i32(TCGV_HIGH(ret), TCGV_LOW(arg1), c);
tcg_gen_movi_i32(TCGV_LOW(ret), 0);
}
} else {
TCGv_i32 t0, t1;
t0 = tcg_temp_new_i32();
t1 = tcg_temp_new_i32();
if (right) {
tcg_gen_shli_i32(t0, TCGV_HIGH(arg1), 32 - c);
if (arith)
tcg_gen_sari_i32(t1, TCGV_HIGH(arg1), c);
else
tcg_gen_shri_i32(t1, TCGV_HIGH(arg1), c);
tcg_gen_shri_i32(TCGV_LOW(ret), TCGV_LOW(arg1), c);
tcg_gen_or_i32(TCGV_LOW(ret), TCGV_LOW(ret), t0);
tcg_gen_mov_i32(TCGV_HIGH(ret), t1);
} else {
tcg_gen_shri_i32(t0, TCGV_LOW(arg1), 32 - c);
/* Note: ret can be the same as arg1, so we use t1 */
tcg_gen_shli_i32(t1, TCGV_LOW(arg1), c);
tcg_gen_shli_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), c);
tcg_gen_or_i32(TCGV_HIGH(ret), TCGV_HIGH(ret), t0);
tcg_gen_mov_i32(TCGV_LOW(ret), t1);
}
tcg_temp_free_i32(t0);
tcg_temp_free_i32(t1);
}
}
#endif
static inline TCGMemOp tcg_canonicalize_memop(TCGMemOp op, bool is64, bool st)
{
switch (op & MO_SIZE) {
case MO_8:
op &= ~MO_BSWAP;
break;
case MO_16:
break;
case MO_32:
if (!is64) {
op &= ~MO_SIGN;
}
break;
case MO_64:
if (!is64) {
tcg_abort();
}
break;
}
if (st) {
op &= ~MO_SIGN;
}
return op;
}
void tcg_gen_qemu_ld_i32(TCGv_i32 val, TCGv addr, TCGArg idx, TCGMemOp memop)
{
memop = tcg_canonicalize_memop(memop, 0, 0);
*tcg_ctx.gen_opc_ptr++ = INDEX_op_qemu_ld_i32;
tcg_add_param_i32(val);
tcg_add_param_tl(addr);
*tcg_ctx.gen_opparam_ptr++ = memop;
*tcg_ctx.gen_opparam_ptr++ = idx;
}
void tcg_gen_qemu_st_i32(TCGv_i32 val, TCGv addr, TCGArg idx, TCGMemOp memop)
{
memop = tcg_canonicalize_memop(memop, 0, 1);
*tcg_ctx.gen_opc_ptr++ = INDEX_op_qemu_st_i32;
tcg_add_param_i32(val);
tcg_add_param_tl(addr);
*tcg_ctx.gen_opparam_ptr++ = memop;
*tcg_ctx.gen_opparam_ptr++ = idx;
}
void tcg_gen_qemu_ld_i64(TCGv_i64 val, TCGv addr, TCGArg idx, TCGMemOp memop)
{
memop = tcg_canonicalize_memop(memop, 1, 0);
#if TCG_TARGET_REG_BITS == 32
if ((memop & MO_SIZE) < MO_64) {
tcg_gen_qemu_ld_i32(TCGV_LOW(val), addr, idx, memop);
if (memop & MO_SIGN) {
tcg_gen_sari_i32(TCGV_HIGH(val), TCGV_LOW(val), 31);
} else {
tcg_gen_movi_i32(TCGV_HIGH(val), 0);
}
return;
}
#endif
*tcg_ctx.gen_opc_ptr++ = INDEX_op_qemu_ld_i64;
tcg_add_param_i64(val);
tcg_add_param_tl(addr);
*tcg_ctx.gen_opparam_ptr++ = memop;
*tcg_ctx.gen_opparam_ptr++ = idx;
}
void tcg_gen_qemu_st_i64(TCGv_i64 val, TCGv addr, TCGArg idx, TCGMemOp memop)
{
memop = tcg_canonicalize_memop(memop, 1, 1);
#if TCG_TARGET_REG_BITS == 32
if ((memop & MO_SIZE) < MO_64) {
tcg_gen_qemu_st_i32(TCGV_LOW(val), addr, idx, memop);
return;
}
#endif
*tcg_ctx.gen_opc_ptr++ = INDEX_op_qemu_st_i64;
tcg_add_param_i64(val);
tcg_add_param_tl(addr);
*tcg_ctx.gen_opparam_ptr++ = memop;
*tcg_ctx.gen_opparam_ptr++ = idx;
}
static void tcg_reg_alloc_start(TCGContext *s)
{
int i;
@ -1109,20 +987,21 @@ static const char * const ldst_name[] =
void tcg_dump_ops(TCGContext *s)
{
const uint16_t *opc_ptr;
const TCGArg *args;
TCGArg arg;
TCGOpcode c;
int i, k, nb_oargs, nb_iargs, nb_cargs, first_insn;
const TCGOpDef *def;
char buf[128];
TCGOp *op;
int oi;
first_insn = 1;
opc_ptr = s->gen_opc_buf;
args = s->gen_opparam_buf;
while (opc_ptr < s->gen_opc_ptr) {
c = *opc_ptr++;
for (oi = s->gen_first_op_idx; oi >= 0; oi = op->next) {
int i, k, nb_oargs, nb_iargs, nb_cargs;
const TCGOpDef *def;
const TCGArg *args;
TCGOpcode c;
op = &s->gen_op_buf[oi];
c = op->opc;
def = &tcg_op_defs[c];
args = &s->gen_opparam_buf[op->args];
if (c == INDEX_op_debug_insn_start) {
uint64_t pc;
#if TARGET_LONG_BITS > TCG_TARGET_REG_BITS
@ -1130,21 +1009,14 @@ void tcg_dump_ops(TCGContext *s)
#else
pc = args[0];
#endif
if (!first_insn) {
if (oi != s->gen_first_op_idx) {
qemu_log("\n");
}
qemu_log(" ---- 0x%" PRIx64, pc);
first_insn = 0;
nb_oargs = def->nb_oargs;
nb_iargs = def->nb_iargs;
nb_cargs = def->nb_cargs;
} else if (c == INDEX_op_call) {
TCGArg arg;
/* variable number of arguments */
arg = *args++;
nb_oargs = arg >> 16;
nb_iargs = arg & 0xffff;
nb_oargs = op->callo;
nb_iargs = op->calli;
nb_cargs = def->nb_cargs;
/* function name, flags, out args */
@ -1165,26 +1037,20 @@ void tcg_dump_ops(TCGContext *s)
}
} else {
qemu_log(" %s ", def->name);
if (c == INDEX_op_nopn) {
/* variable number of arguments */
nb_cargs = *args;
nb_oargs = 0;
nb_iargs = 0;
} else {
nb_oargs = def->nb_oargs;
nb_iargs = def->nb_iargs;
nb_cargs = def->nb_cargs;
}
nb_oargs = def->nb_oargs;
nb_iargs = def->nb_iargs;
nb_cargs = def->nb_cargs;
k = 0;
for(i = 0; i < nb_oargs; i++) {
for (i = 0; i < nb_oargs; i++) {
if (k != 0) {
qemu_log(",");
}
qemu_log("%s", tcg_get_arg_str_idx(s, buf, sizeof(buf),
args[k++]));
}
for(i = 0; i < nb_iargs; i++) {
for (i = 0; i < nb_iargs; i++) {
if (k != 0) {
qemu_log(",");
}
@ -1222,16 +1088,14 @@ void tcg_dump_ops(TCGContext *s)
i = 0;
break;
}
for(; i < nb_cargs; i++) {
for (; i < nb_cargs; i++) {
if (k != 0) {
qemu_log(",");
}
arg = args[k++];
qemu_log("$0x%" TCG_PRIlx, arg);
qemu_log("$0x%" TCG_PRIlx, args[k++]);
}
}
qemu_log("\n");
args += nb_iargs + nb_oargs + nb_cargs;
}
}
@ -1380,21 +1244,30 @@ void tcg_add_target_add_op_defs(const TCGTargetOpDef *tdefs)
#endif
}
#ifdef USE_LIVENESS_ANALYSIS
/* set a nop for an operation using 'nb_args' */
static inline void tcg_set_nop(TCGContext *s, uint16_t *opc_ptr,
TCGArg *args, int nb_args)
void tcg_op_remove(TCGContext *s, TCGOp *op)
{
if (nb_args == 0) {
*opc_ptr = INDEX_op_nop;
int next = op->next;
int prev = op->prev;
if (next >= 0) {
s->gen_op_buf[next].prev = prev;
} else {
*opc_ptr = INDEX_op_nopn;
args[0] = nb_args;
args[nb_args - 1] = nb_args;
s->gen_last_op_idx = prev;
}
if (prev >= 0) {
s->gen_op_buf[prev].next = next;
} else {
s->gen_first_op_idx = next;
}
memset(op, -1, sizeof(*op));
#ifdef CONFIG_PROFILER
s->del_op_count++;
#endif
}
#ifdef USE_LIVENESS_ANALYSIS
/* liveness analysis: end of function: all temps are dead, and globals
should be in memory. */
static inline void tcg_la_func_end(TCGContext *s, uint8_t *dead_temps,
@ -1424,19 +1297,10 @@ static inline void tcg_la_bb_end(TCGContext *s, uint8_t *dead_temps,
temporaries are removed. */
static void tcg_liveness_analysis(TCGContext *s)
{
int i, op_index, nb_args, nb_iargs, nb_oargs, nb_ops;
TCGOpcode op, op_new, op_new2;
TCGArg *args, arg;
const TCGOpDef *def;
uint8_t *dead_temps, *mem_temps;
uint16_t dead_args;
uint8_t sync_args;
bool have_op_new2;
s->gen_opc_ptr++; /* skip end */
nb_ops = s->gen_opc_ptr - s->gen_opc_buf;
int oi, oi_prev, nb_ops;
nb_ops = s->gen_next_op_idx;
s->op_dead_args = tcg_malloc(nb_ops * sizeof(uint16_t));
s->op_sync_args = tcg_malloc(nb_ops * sizeof(uint8_t));
@ -1444,25 +1308,31 @@ static void tcg_liveness_analysis(TCGContext *s)
mem_temps = tcg_malloc(s->nb_temps);
tcg_la_func_end(s, dead_temps, mem_temps);
args = s->gen_opparam_ptr;
op_index = nb_ops - 1;
while (op_index >= 0) {
op = s->gen_opc_buf[op_index];
def = &tcg_op_defs[op];
switch(op) {
for (oi = s->gen_last_op_idx; oi >= 0; oi = oi_prev) {
int i, nb_iargs, nb_oargs;
TCGOpcode opc_new, opc_new2;
bool have_opc_new2;
uint16_t dead_args;
uint8_t sync_args;
TCGArg arg;
TCGOp * const op = &s->gen_op_buf[oi];
TCGArg * const args = &s->gen_opparam_buf[op->args];
TCGOpcode opc = op->opc;
const TCGOpDef *def = &tcg_op_defs[opc];
oi_prev = op->prev;
switch (opc) {
case INDEX_op_call:
{
int call_flags;
nb_args = args[-1];
args -= nb_args;
arg = *args++;
nb_iargs = arg & 0xffff;
nb_oargs = arg >> 16;
nb_oargs = op->callo;
nb_iargs = op->calli;
call_flags = args[nb_oargs + nb_iargs + 1];
/* pure functions can be removed if their result is not
used */
/* pure functions can be removed if their result is unused */
if (call_flags & TCG_CALL_NO_SIDE_EFFECTS) {
for (i = 0; i < nb_oargs; i++) {
arg = args[i];
@ -1470,8 +1340,7 @@ static void tcg_liveness_analysis(TCGContext *s)
goto do_not_remove_call;
}
}
tcg_set_nop(s, s->gen_opc_buf + op_index,
args - 1, nb_args);
goto do_remove;
} else {
do_not_remove_call:
@ -1510,41 +1379,31 @@ static void tcg_liveness_analysis(TCGContext *s)
dead_temps[arg] = 0;
}
}
s->op_dead_args[op_index] = dead_args;
s->op_sync_args[op_index] = sync_args;
s->op_dead_args[oi] = dead_args;
s->op_sync_args[oi] = sync_args;
}
args--;
}
break;
case INDEX_op_debug_insn_start:
args -= def->nb_args;
break;
case INDEX_op_nopn:
nb_args = args[-1];
args -= nb_args;
break;
case INDEX_op_discard:
args--;
/* mark the temporary as dead */
dead_temps[args[0]] = 1;
mem_temps[args[0]] = 0;
break;
case INDEX_op_end:
break;
case INDEX_op_add2_i32:
op_new = INDEX_op_add_i32;
opc_new = INDEX_op_add_i32;
goto do_addsub2;
case INDEX_op_sub2_i32:
op_new = INDEX_op_sub_i32;
opc_new = INDEX_op_sub_i32;
goto do_addsub2;
case INDEX_op_add2_i64:
op_new = INDEX_op_add_i64;
opc_new = INDEX_op_add_i64;
goto do_addsub2;
case INDEX_op_sub2_i64:
op_new = INDEX_op_sub_i64;
opc_new = INDEX_op_sub_i64;
do_addsub2:
args -= 6;
nb_iargs = 4;
nb_oargs = 2;
/* Test if the high part of the operation is dead, but not
@ -1555,12 +1414,11 @@ static void tcg_liveness_analysis(TCGContext *s)
if (dead_temps[args[0]] && !mem_temps[args[0]]) {
goto do_remove;
}
/* Create the single operation plus nop. */
s->gen_opc_buf[op_index] = op = op_new;
/* Replace the opcode and adjust the args in place,
leaving 3 unused args at the end. */
op->opc = opc = opc_new;
args[1] = args[2];
args[2] = args[4];
assert(s->gen_opc_buf[op_index + 1] == INDEX_op_nop);
tcg_set_nop(s, s->gen_opc_buf + op_index + 1, args + 3, 3);
/* Fall through and mark the single-word operation live. */
nb_iargs = 2;
nb_oargs = 1;
@ -1568,27 +1426,26 @@ static void tcg_liveness_analysis(TCGContext *s)
goto do_not_remove;
case INDEX_op_mulu2_i32:
op_new = INDEX_op_mul_i32;
op_new2 = INDEX_op_muluh_i32;
have_op_new2 = TCG_TARGET_HAS_muluh_i32;
opc_new = INDEX_op_mul_i32;
opc_new2 = INDEX_op_muluh_i32;
have_opc_new2 = TCG_TARGET_HAS_muluh_i32;
goto do_mul2;
case INDEX_op_muls2_i32:
op_new = INDEX_op_mul_i32;
op_new2 = INDEX_op_mulsh_i32;
have_op_new2 = TCG_TARGET_HAS_mulsh_i32;
opc_new = INDEX_op_mul_i32;
opc_new2 = INDEX_op_mulsh_i32;
have_opc_new2 = TCG_TARGET_HAS_mulsh_i32;
goto do_mul2;
case INDEX_op_mulu2_i64:
op_new = INDEX_op_mul_i64;
op_new2 = INDEX_op_muluh_i64;
have_op_new2 = TCG_TARGET_HAS_muluh_i64;
opc_new = INDEX_op_mul_i64;
opc_new2 = INDEX_op_muluh_i64;
have_opc_new2 = TCG_TARGET_HAS_muluh_i64;
goto do_mul2;
case INDEX_op_muls2_i64:
op_new = INDEX_op_mul_i64;
op_new2 = INDEX_op_mulsh_i64;
have_op_new2 = TCG_TARGET_HAS_mulsh_i64;
opc_new = INDEX_op_mul_i64;
opc_new2 = INDEX_op_mulsh_i64;
have_opc_new2 = TCG_TARGET_HAS_mulsh_i64;
goto do_mul2;
do_mul2:
args -= 4;
nb_iargs = 2;
nb_oargs = 2;
if (dead_temps[args[1]] && !mem_temps[args[1]]) {
@ -1597,28 +1454,25 @@ static void tcg_liveness_analysis(TCGContext *s)
goto do_remove;
}
/* The high part of the operation is dead; generate the low. */
s->gen_opc_buf[op_index] = op = op_new;
op->opc = opc = opc_new;
args[1] = args[2];
args[2] = args[3];
} else if (have_op_new2 && dead_temps[args[0]]
} else if (have_opc_new2 && dead_temps[args[0]]
&& !mem_temps[args[0]]) {
/* The low part of the operation is dead; generate the high. */
s->gen_opc_buf[op_index] = op = op_new2;
/* The low part of the operation is dead; generate the high. */
op->opc = opc = opc_new2;
args[0] = args[1];
args[1] = args[2];
args[2] = args[3];
} else {
goto do_not_remove;
}
assert(s->gen_opc_buf[op_index + 1] == INDEX_op_nop);
tcg_set_nop(s, s->gen_opc_buf + op_index + 1, args + 3, 1);
/* Mark the single-word operation live. */
nb_oargs = 1;
goto do_not_remove;
default:
/* XXX: optimize by hardcoding common cases (e.g. triadic ops) */
args -= def->nb_args;
nb_iargs = def->nb_iargs;
nb_oargs = def->nb_oargs;
@ -1626,24 +1480,20 @@ static void tcg_liveness_analysis(TCGContext *s)
its outputs are dead. We assume that nb_oargs == 0
implies side effects */
if (!(def->flags & TCG_OPF_SIDE_EFFECTS) && nb_oargs != 0) {
for(i = 0; i < nb_oargs; i++) {
for (i = 0; i < nb_oargs; i++) {
arg = args[i];
if (!dead_temps[arg] || mem_temps[arg]) {
goto do_not_remove;
}
}
do_remove:
tcg_set_nop(s, s->gen_opc_buf + op_index, args, def->nb_args);
#ifdef CONFIG_PROFILER
s->del_op_count++;
#endif
tcg_op_remove(s, op);
} else {
do_not_remove:
/* output args are dead */
dead_args = 0;
sync_args = 0;
for(i = 0; i < nb_oargs; i++) {
for (i = 0; i < nb_oargs; i++) {
arg = args[i];
if (dead_temps[arg]) {
dead_args |= (1 << i);
@ -1664,23 +1514,18 @@ static void tcg_liveness_analysis(TCGContext *s)
}
/* input args are live */
for(i = nb_oargs; i < nb_oargs + nb_iargs; i++) {
for (i = nb_oargs; i < nb_oargs + nb_iargs; i++) {
arg = args[i];
if (dead_temps[arg]) {
dead_args |= (1 << i);
}
dead_temps[arg] = 0;
}
s->op_dead_args[op_index] = dead_args;
s->op_sync_args[op_index] = sync_args;
s->op_dead_args[oi] = dead_args;
s->op_sync_args[oi] = sync_args;
}
break;
}
op_index--;
}
if (args != s->gen_opparam_buf) {
tcg_abort();
}
}
#else
@ -2247,11 +2092,11 @@ static void tcg_reg_alloc_op(TCGContext *s,
#define STACK_DIR(x) (x)
#endif
static int tcg_reg_alloc_call(TCGContext *s, const TCGOpDef *def,
TCGOpcode opc, const TCGArg *args,
uint16_t dead_args, uint8_t sync_args)
static void tcg_reg_alloc_call(TCGContext *s, int nb_oargs, int nb_iargs,
const TCGArg * const args, uint16_t dead_args,
uint8_t sync_args)
{
int nb_iargs, nb_oargs, flags, nb_regs, i, reg, nb_params;
int flags, nb_regs, i, reg;
TCGArg arg;
TCGTemp *ts;
intptr_t stack_offset;
@ -2260,22 +2105,16 @@ static int tcg_reg_alloc_call(TCGContext *s, const TCGOpDef *def,
int allocate_args;
TCGRegSet allocated_regs;
arg = *args++;
nb_oargs = arg >> 16;
nb_iargs = arg & 0xffff;
nb_params = nb_iargs;
func_addr = (tcg_insn_unit *)(intptr_t)args[nb_oargs + nb_iargs];
flags = args[nb_oargs + nb_iargs + 1];
nb_regs = ARRAY_SIZE(tcg_target_call_iarg_regs);
if (nb_regs > nb_params) {
nb_regs = nb_params;
if (nb_regs > nb_iargs) {
nb_regs = nb_iargs;
}
/* assign stack slots first */
call_stack_size = (nb_params - nb_regs) * sizeof(tcg_target_long);
call_stack_size = (nb_iargs - nb_regs) * sizeof(tcg_target_long);
call_stack_size = (call_stack_size + TCG_TARGET_STACK_ALIGN - 1) &
~(TCG_TARGET_STACK_ALIGN - 1);
allocate_args = (call_stack_size > TCG_STATIC_CALL_ARGS_SIZE);
@ -2286,7 +2125,7 @@ static int tcg_reg_alloc_call(TCGContext *s, const TCGOpDef *def,
}
stack_offset = TCG_TARGET_CALL_STACK_OFFSET;
for(i = nb_regs; i < nb_params; i++) {
for(i = nb_regs; i < nb_iargs; i++) {
arg = args[nb_oargs + i];
#ifdef TCG_TARGET_STACK_GROWSUP
stack_offset -= sizeof(tcg_target_long);
@ -2393,8 +2232,6 @@ static int tcg_reg_alloc_call(TCGContext *s, const TCGOpDef *def,
}
}
}
return nb_iargs + nb_oargs + def->nb_cargs + 1;
}
#ifdef CONFIG_PROFILER
@ -2405,7 +2242,7 @@ void tcg_dump_op_count(FILE *f, fprintf_function cpu_fprintf)
{
int i;
for(i = INDEX_op_end; i < NB_OPS; i++) {
for (i = 0; i < NB_OPS; i++) {
cpu_fprintf(f, "%s %" PRId64 "\n", tcg_op_defs[i].name,
tcg_table_op_count[i]);
}
@ -2422,10 +2259,7 @@ static inline int tcg_gen_code_common(TCGContext *s,
tcg_insn_unit *gen_code_buf,
long search_pc)
{
TCGOpcode opc;
int op_index;
const TCGOpDef *def;
const TCGArg *args;
int oi, oi_next;
#ifdef DEBUG_DISAS
if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP))) {
@ -2440,8 +2274,7 @@ static inline int tcg_gen_code_common(TCGContext *s,
#endif
#ifdef USE_TCG_OPTIMIZATIONS
s->gen_opparam_ptr =
tcg_optimize(s, s->gen_opc_ptr, s->gen_opparam_buf, tcg_op_defs);
tcg_optimize(s);
#endif
#ifdef CONFIG_PROFILER
@ -2470,42 +2303,30 @@ static inline int tcg_gen_code_common(TCGContext *s,
tcg_out_tb_init(s);
args = s->gen_opparam_buf;
op_index = 0;
for (oi = s->gen_first_op_idx; oi >= 0; oi = oi_next) {
TCGOp * const op = &s->gen_op_buf[oi];
TCGArg * const args = &s->gen_opparam_buf[op->args];
TCGOpcode opc = op->opc;
const TCGOpDef *def = &tcg_op_defs[opc];
uint16_t dead_args = s->op_dead_args[oi];
uint8_t sync_args = s->op_sync_args[oi];
for(;;) {
opc = s->gen_opc_buf[op_index];
oi_next = op->next;
#ifdef CONFIG_PROFILER
tcg_table_op_count[opc]++;
#endif
def = &tcg_op_defs[opc];
#if 0
printf("%s: %d %d %d\n", def->name,
def->nb_oargs, def->nb_iargs, def->nb_cargs);
// dump_regs(s);
#endif
switch(opc) {
switch (opc) {
case INDEX_op_mov_i32:
case INDEX_op_mov_i64:
tcg_reg_alloc_mov(s, def, args, s->op_dead_args[op_index],
s->op_sync_args[op_index]);
tcg_reg_alloc_mov(s, def, args, dead_args, sync_args);
break;
case INDEX_op_movi_i32:
case INDEX_op_movi_i64:
tcg_reg_alloc_movi(s, args, s->op_dead_args[op_index],
s->op_sync_args[op_index]);
tcg_reg_alloc_movi(s, args, dead_args, sync_args);
break;
case INDEX_op_debug_insn_start:
/* debug instruction */
break;
case INDEX_op_nop:
case INDEX_op_nop1:
case INDEX_op_nop2:
case INDEX_op_nop3:
break;
case INDEX_op_nopn:
args += args[0];
goto next;
case INDEX_op_discard:
temp_dead(s, args[0]);
break;
@ -2514,12 +2335,9 @@ static inline int tcg_gen_code_common(TCGContext *s,
tcg_out_label(s, args[0], s->code_ptr);
break;
case INDEX_op_call:
args += tcg_reg_alloc_call(s, def, opc, args,
s->op_dead_args[op_index],
s->op_sync_args[op_index]);
goto next;
case INDEX_op_end:
goto the_end;
tcg_reg_alloc_call(s, op->callo, op->calli, args,
dead_args, sync_args);
break;
default:
/* Sanity check that we've not introduced any unhandled opcodes. */
if (def->flags & TCG_OPF_NOT_PRESENT) {
@ -2528,21 +2346,17 @@ static inline int tcg_gen_code_common(TCGContext *s,
/* Note: in order to speed up the code, it would be much
faster to have specialized register allocator functions for
some common argument patterns */
tcg_reg_alloc_op(s, def, opc, args, s->op_dead_args[op_index],
s->op_sync_args[op_index]);
tcg_reg_alloc_op(s, def, opc, args, dead_args, sync_args);
break;
}
args += def->nb_args;
next:
if (search_pc >= 0 && search_pc < tcg_current_code_size(s)) {
return op_index;
return oi;
}
op_index++;
#ifndef NDEBUG
check_regs(s);
#endif
}
the_end:
/* Generate TB finalization at the end of block */
tcg_out_tb_finalize(s);
return -1;
@ -2553,14 +2367,18 @@ int tcg_gen_code(TCGContext *s, tcg_insn_unit *gen_code_buf)
#ifdef CONFIG_PROFILER
{
int n;
n = (s->gen_opc_ptr - s->gen_opc_buf);
s->op_count += n;
if (n > s->op_count_max)
s->op_count_max = n;
s->temp_count += s->nb_temps;
if (s->nb_temps > s->temp_count_max)
s->temp_count_max = s->nb_temps;
n = s->gen_last_op_idx + 1;
s->op_count += n;
if (n > s->op_count_max) {
s->op_count_max = n;
}
n = s->nb_temps;
s->temp_count += n;
if (n > s->temp_count_max) {
s->temp_count_max = n;
}
}
#endif

72
tcg/tcg.h
View File

@ -448,10 +448,28 @@ typedef struct TCGTempSet {
unsigned long l[BITS_TO_LONGS(TCG_MAX_TEMPS)];
} TCGTempSet;
typedef struct TCGOp {
TCGOpcode opc : 8;
/* The number of out and in parameter for a call. */
unsigned callo : 2;
unsigned calli : 6;
/* Index of the arguments for this op, or -1 for zero-operand ops. */
signed args : 16;
/* Index of the prex/next op, or -1 for the end of the list. */
signed prev : 16;
signed next : 16;
} TCGOp;
QEMU_BUILD_BUG_ON(NB_OPS > 0xff);
QEMU_BUILD_BUG_ON(OPC_BUF_SIZE >= 0x7fff);
QEMU_BUILD_BUG_ON(OPPARAM_BUF_SIZE >= 0x7fff);
struct TCGContext {
uint8_t *pool_cur, *pool_end;
TCGPool *pool_first, *pool_current, *pool_first_large;
TCGLabel *labels;
int nb_labels;
int nb_globals;
int nb_temps;
@ -469,9 +487,6 @@ struct TCGContext {
corresponding output argument needs to be
sync to memory. */
/* tells in which temporary a given register is. It does not take
into account fixed registers */
int reg_to_temp[TCG_TARGET_NB_REGS];
TCGRegSet reserved_regs;
intptr_t current_frame_offset;
intptr_t frame_start;
@ -479,8 +494,6 @@ struct TCGContext {
int frame_reg;
tcg_insn_unit *code_ptr;
TCGTemp temps[TCG_MAX_TEMPS]; /* globals first, temps after */
TCGTempSet free_temps[TCG_TYPE_COUNT * 2];
GHashTable *helpers;
@ -508,14 +521,10 @@ struct TCGContext {
int goto_tb_issue_mask;
#endif
uint16_t gen_opc_buf[OPC_BUF_SIZE];
TCGArg gen_opparam_buf[OPPARAM_BUF_SIZE];
uint16_t *gen_opc_ptr;
TCGArg *gen_opparam_ptr;
target_ulong gen_opc_pc[OPC_BUF_SIZE];
uint16_t gen_opc_icount[OPC_BUF_SIZE];
uint8_t gen_opc_instr_start[OPC_BUF_SIZE];
int gen_first_op_idx;
int gen_last_op_idx;
int gen_next_op_idx;
int gen_next_parm_idx;
/* Code generation. Note that we specifically do not use tcg_insn_unit
here, because there's too much arithmetic throughout that relies
@ -533,10 +542,38 @@ struct TCGContext {
/* The TCGBackendData structure is private to tcg-target.c. */
struct TCGBackendData *be;
TCGTempSet free_temps[TCG_TYPE_COUNT * 2];
TCGTemp temps[TCG_MAX_TEMPS]; /* globals first, temps after */
/* tells in which temporary a given register is. It does not take
into account fixed registers */
int reg_to_temp[TCG_TARGET_NB_REGS];
TCGOp gen_op_buf[OPC_BUF_SIZE];
TCGArg gen_opparam_buf[OPPARAM_BUF_SIZE];
target_ulong gen_opc_pc[OPC_BUF_SIZE];
uint16_t gen_opc_icount[OPC_BUF_SIZE];
uint8_t gen_opc_instr_start[OPC_BUF_SIZE];
TCGLabel labels[TCG_MAX_LABELS];
};
extern TCGContext tcg_ctx;
/* The number of opcodes emitted so far. */
static inline int tcg_op_buf_count(void)
{
return tcg_ctx.gen_next_op_idx;
}
/* Test for whether to terminate the TB for using too many opcodes. */
static inline bool tcg_op_buf_full(void)
{
return tcg_op_buf_count() >= OPC_MAX_SIZE;
}
/* pool based memory allocation */
void *tcg_malloc_internal(TCGContext *s, int size);
@ -706,11 +743,8 @@ void tcg_add_target_add_op_defs(const TCGTargetOpDef *tdefs);
void tcg_gen_callN(TCGContext *s, void *func,
TCGArg ret, int nargs, TCGArg *args);
void tcg_gen_shifti_i64(TCGv_i64 ret, TCGv_i64 arg1,
int c, int right, int arith);
TCGArg *tcg_optimize(TCGContext *s, uint16_t *tcg_opc_ptr, TCGArg *args,
TCGOpDef *tcg_op_def);
void tcg_op_remove(TCGContext *s, TCGOp *op);
void tcg_optimize(TCGContext *s);
/* only used for debugging purposes */
void tcg_dump_ops(TCGContext *s);

13
tci.c
View File

@ -506,19 +506,6 @@ uintptr_t tcg_qemu_tb_exec(CPUArchState *env, uint8_t *tb_ptr)
tb_ptr += 2;
switch (opc) {
case INDEX_op_end:
case INDEX_op_nop:
break;
case INDEX_op_nop1:
case INDEX_op_nop2:
case INDEX_op_nop3:
case INDEX_op_nopn:
case INDEX_op_discard:
TODO();
break;
case INDEX_op_set_label:
TODO();
break;
case INDEX_op_call:
t0 = tci_read_ri(&tb_ptr);
#if TCG_TARGET_REG_BITS == 32