aboutsummaryrefslogtreecommitdiff
path: root/tcg
diff options
context:
space:
mode:
Diffstat (limited to 'tcg')
-rw-r--r--tcg/arm/tcg-target.h2
-rw-r--r--tcg/hppa/tcg-target.h2
-rw-r--r--tcg/i386/tcg-target.h2
-rw-r--r--tcg/ia64/tcg-target.h3
-rw-r--r--tcg/mips/tcg-target.h3
-rw-r--r--tcg/optimize.c471
-rw-r--r--tcg/ppc/tcg-target.h2
-rw-r--r--tcg/ppc64/tcg-target.h1
-rw-r--r--tcg/s390/tcg-target.h2
-rw-r--r--tcg/sparc/tcg-target.h2
-rw-r--r--tcg/tcg-op.h11
-rw-r--r--tcg/tcg.c57
-rw-r--r--tcg/tcg.h2
-rw-r--r--tcg/tci/tcg-target.h3
14 files changed, 378 insertions, 185 deletions
diff --git a/tcg/arm/tcg-target.h b/tcg/arm/tcg-target.h
index 0df33520f8..98fa11b286 100644
--- a/tcg/arm/tcg-target.h
+++ b/tcg/arm/tcg-target.h
@@ -75,8 +75,6 @@ typedef enum {
#define TCG_TARGET_HAS_deposit_i32 0
#define TCG_TARGET_HAS_movcond_i32 1
-#define TCG_TARGET_HAS_GUEST_BASE
-
enum {
TCG_AREG0 = TCG_REG_R6,
};
diff --git a/tcg/hppa/tcg-target.h b/tcg/hppa/tcg-target.h
index 5351353719..f43fb419ae 100644
--- a/tcg/hppa/tcg-target.h
+++ b/tcg/hppa/tcg-target.h
@@ -103,8 +103,6 @@ typedef enum {
#define TCG_TARGET_HAS_ext8u_i32 0 /* and rd, rs, 0xff */
#define TCG_TARGET_HAS_ext16u_i32 0 /* and rd, rs, 0xffff */
-#define TCG_TARGET_HAS_GUEST_BASE
-
#define TCG_AREG0 TCG_REG_R17
diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h
index ace63ba37b..dbc6756414 100644
--- a/tcg/i386/tcg-target.h
+++ b/tcg/i386/tcg-target.h
@@ -125,8 +125,6 @@ typedef enum {
((ofs) == 0 && (len) == 16))
#define TCG_TARGET_deposit_i64_valid TCG_TARGET_deposit_i32_valid
-#define TCG_TARGET_HAS_GUEST_BASE
-
#if TCG_TARGET_REG_BITS == 64
# define TCG_AREG0 TCG_REG_R14
#else
diff --git a/tcg/ia64/tcg-target.h b/tcg/ia64/tcg-target.h
index 4255ca5225..91fe7a3b06 100644
--- a/tcg/ia64/tcg-target.h
+++ b/tcg/ia64/tcg-target.h
@@ -147,9 +147,6 @@ typedef enum {
#define TCG_AREG0 TCG_REG_R7
-/* Guest base is supported */
-#define TCG_TARGET_HAS_GUEST_BASE
-
static inline void flush_icache_range(tcg_target_ulong start,
tcg_target_ulong stop)
{
diff --git a/tcg/mips/tcg-target.h b/tcg/mips/tcg-target.h
index 7020d65845..65b5c59e89 100644
--- a/tcg/mips/tcg-target.h
+++ b/tcg/mips/tcg-target.h
@@ -116,9 +116,6 @@ typedef enum {
#define TCG_AREG0 TCG_REG_S0
-/* guest base is supported */
-#define TCG_TARGET_HAS_GUEST_BASE
-
#ifdef __OpenBSD__
#include <machine/sysarch.h>
#else
diff --git a/tcg/optimize.c b/tcg/optimize.c
index edb2b0ea90..a06c8eb43e 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -292,6 +292,82 @@ static TCGArg do_constant_folding(TCGOpcode op, TCGArg x, TCGArg y)
return res;
}
+static bool do_constant_folding_cond_32(uint32_t x, uint32_t y, TCGCond c)
+{
+ switch (c) {
+ case TCG_COND_EQ:
+ return x == y;
+ case TCG_COND_NE:
+ return x != y;
+ case TCG_COND_LT:
+ return (int32_t)x < (int32_t)y;
+ case TCG_COND_GE:
+ return (int32_t)x >= (int32_t)y;
+ case TCG_COND_LE:
+ return (int32_t)x <= (int32_t)y;
+ case TCG_COND_GT:
+ return (int32_t)x > (int32_t)y;
+ case TCG_COND_LTU:
+ return x < y;
+ case TCG_COND_GEU:
+ return x >= y;
+ case TCG_COND_LEU:
+ return x <= y;
+ case TCG_COND_GTU:
+ return x > y;
+ default:
+ tcg_abort();
+ }
+}
+
+static bool do_constant_folding_cond_64(uint64_t x, uint64_t y, TCGCond c)
+{
+ switch (c) {
+ case TCG_COND_EQ:
+ return x == y;
+ case TCG_COND_NE:
+ return x != y;
+ case TCG_COND_LT:
+ return (int64_t)x < (int64_t)y;
+ case TCG_COND_GE:
+ return (int64_t)x >= (int64_t)y;
+ case TCG_COND_LE:
+ return (int64_t)x <= (int64_t)y;
+ case TCG_COND_GT:
+ return (int64_t)x > (int64_t)y;
+ case TCG_COND_LTU:
+ return x < y;
+ case TCG_COND_GEU:
+ return x >= y;
+ case TCG_COND_LEU:
+ return x <= y;
+ case TCG_COND_GTU:
+ return x > y;
+ default:
+ tcg_abort();
+ }
+}
+
+static bool do_constant_folding_cond_eq(TCGCond c)
+{
+ switch (c) {
+ case TCG_COND_GT:
+ case TCG_COND_LTU:
+ case TCG_COND_LT:
+ case TCG_COND_GTU:
+ case TCG_COND_NE:
+ return 0;
+ case TCG_COND_GE:
+ case TCG_COND_GEU:
+ case TCG_COND_LE:
+ case TCG_COND_LEU:
+ case TCG_COND_EQ:
+ return 1;
+ default:
+ tcg_abort();
+ }
+}
+
/* Return 2 if the condition can't be simplified, and the result
of the condition (0 or 1) if it can */
static TCGArg do_constant_folding_cond(TCGOpcode op, TCGArg x,
@@ -300,75 +376,14 @@ static TCGArg do_constant_folding_cond(TCGOpcode op, TCGArg x,
if (temps[x].state == TCG_TEMP_CONST && temps[y].state == TCG_TEMP_CONST) {
switch (op_bits(op)) {
case 32:
- switch (c) {
- case TCG_COND_EQ:
- return (uint32_t)temps[x].val == (uint32_t)temps[y].val;
- case TCG_COND_NE:
- return (uint32_t)temps[x].val != (uint32_t)temps[y].val;
- case TCG_COND_LT:
- return (int32_t)temps[x].val < (int32_t)temps[y].val;
- case TCG_COND_GE:
- return (int32_t)temps[x].val >= (int32_t)temps[y].val;
- case TCG_COND_LE:
- return (int32_t)temps[x].val <= (int32_t)temps[y].val;
- case TCG_COND_GT:
- return (int32_t)temps[x].val > (int32_t)temps[y].val;
- case TCG_COND_LTU:
- return (uint32_t)temps[x].val < (uint32_t)temps[y].val;
- case TCG_COND_GEU:
- return (uint32_t)temps[x].val >= (uint32_t)temps[y].val;
- case TCG_COND_LEU:
- return (uint32_t)temps[x].val <= (uint32_t)temps[y].val;
- case TCG_COND_GTU:
- return (uint32_t)temps[x].val > (uint32_t)temps[y].val;
- default:
- break;
- }
- break;
+ return do_constant_folding_cond_32(temps[x].val, temps[y].val, c);
case 64:
- switch (c) {
- case TCG_COND_EQ:
- return (uint64_t)temps[x].val == (uint64_t)temps[y].val;
- case TCG_COND_NE:
- return (uint64_t)temps[x].val != (uint64_t)temps[y].val;
- case TCG_COND_LT:
- return (int64_t)temps[x].val < (int64_t)temps[y].val;
- case TCG_COND_GE:
- return (int64_t)temps[x].val >= (int64_t)temps[y].val;
- case TCG_COND_LE:
- return (int64_t)temps[x].val <= (int64_t)temps[y].val;
- case TCG_COND_GT:
- return (int64_t)temps[x].val > (int64_t)temps[y].val;
- case TCG_COND_LTU:
- return (uint64_t)temps[x].val < (uint64_t)temps[y].val;
- case TCG_COND_GEU:
- return (uint64_t)temps[x].val >= (uint64_t)temps[y].val;
- case TCG_COND_LEU:
- return (uint64_t)temps[x].val <= (uint64_t)temps[y].val;
- case TCG_COND_GTU:
- return (uint64_t)temps[x].val > (uint64_t)temps[y].val;
- default:
- break;
- }
- break;
- }
- } else if (temps_are_copies(x, y)) {
- switch (c) {
- case TCG_COND_GT:
- case TCG_COND_LTU:
- case TCG_COND_LT:
- case TCG_COND_GTU:
- case TCG_COND_NE:
- return 0;
- case TCG_COND_GE:
- case TCG_COND_GEU:
- case TCG_COND_LE:
- case TCG_COND_LEU:
- case TCG_COND_EQ:
- return 1;
+ return do_constant_folding_cond_64(temps[x].val, temps[y].val, c);
default:
- break;
+ tcg_abort();
}
+ } else if (temps_are_copies(x, y)) {
+ return do_constant_folding_cond_eq(c);
} else if (temps[y].state == TCG_TEMP_CONST && temps[y].val == 0) {
switch (c) {
case TCG_COND_LTU:
@@ -381,11 +396,73 @@ static TCGArg do_constant_folding_cond(TCGOpcode op, TCGArg x,
} else {
return 2;
}
+}
- fprintf(stderr,
- "Unrecognized bitness %d or condition %d in "
- "do_constant_folding_cond.\n", op_bits(op), c);
- tcg_abort();
+/* Return 2 if the condition can't be simplified, and the result
+ of the condition (0 or 1) if it can */
+static TCGArg do_constant_folding_cond2(TCGArg *p1, TCGArg *p2, TCGCond c)
+{
+ TCGArg al = p1[0], ah = p1[1];
+ TCGArg bl = p2[0], bh = p2[1];
+
+ if (temps[bl].state == TCG_TEMP_CONST
+ && temps[bh].state == TCG_TEMP_CONST) {
+ uint64_t b = ((uint64_t)temps[bh].val << 32) | (uint32_t)temps[bl].val;
+
+ if (temps[al].state == TCG_TEMP_CONST
+ && temps[ah].state == TCG_TEMP_CONST) {
+ uint64_t a;
+ a = ((uint64_t)temps[ah].val << 32) | (uint32_t)temps[al].val;
+ return do_constant_folding_cond_64(a, b, c);
+ }
+ if (b == 0) {
+ switch (c) {
+ case TCG_COND_LTU:
+ return 0;
+ case TCG_COND_GEU:
+ return 1;
+ default:
+ break;
+ }
+ }
+ }
+ if (temps_are_copies(al, bl) && temps_are_copies(ah, bh)) {
+ return do_constant_folding_cond_eq(c);
+ }
+ return 2;
+}
+
+static bool swap_commutative(TCGArg dest, TCGArg *p1, TCGArg *p2)
+{
+ TCGArg a1 = *p1, a2 = *p2;
+ int sum = 0;
+ sum += temps[a1].state == TCG_TEMP_CONST;
+ sum -= temps[a2].state == TCG_TEMP_CONST;
+
+ /* Prefer the constant in second argument, and then the form
+ op a, a, b, which is better handled on non-RISC hosts. */
+ if (sum > 0 || (sum == 0 && dest == a2)) {
+ *p1 = a2;
+ *p2 = a1;
+ return true;
+ }
+ return false;
+}
+
+static bool swap_commutative2(TCGArg *p1, TCGArg *p2)
+{
+ int sum = 0;
+ sum += temps[p1[0]].state == TCG_TEMP_CONST;
+ sum += temps[p1[1]].state == TCG_TEMP_CONST;
+ sum -= temps[p2[0]].state == TCG_TEMP_CONST;
+ sum -= temps[p2[1]].state == TCG_TEMP_CONST;
+ if (sum > 0) {
+ TCGArg t;
+ t = p1[0], p1[0] = p2[0], p2[0] = t;
+ t = p1[1], p1[1] = p2[1], p2[1] = t;
+ return true;
+ }
+ return false;
}
/* Propagate constants and copies, fold constant expressions. */
@@ -397,7 +474,6 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
const TCGOpDef *def;
TCGArg *gen_args;
TCGArg tmp;
- TCGCond cond;
/* Array VALS has an element for each temp.
If this temp holds a constant then its value is kept in VALS' element.
@@ -440,52 +516,46 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
CASE_OP_32_64(eqv):
CASE_OP_32_64(nand):
CASE_OP_32_64(nor):
- /* Prefer the constant in second argument, and then the form
- op a, a, b, which is better handled on non-RISC hosts. */
- if (temps[args[1]].state == TCG_TEMP_CONST || (args[0] == args[2]
- && temps[args[2]].state != TCG_TEMP_CONST)) {
- tmp = args[1];
- args[1] = args[2];
- args[2] = tmp;
- }
+ swap_commutative(args[0], &args[1], &args[2]);
break;
CASE_OP_32_64(brcond):
- if (temps[args[0]].state == TCG_TEMP_CONST
- && temps[args[1]].state != TCG_TEMP_CONST) {
- tmp = args[0];
- args[0] = args[1];
- args[1] = tmp;
+ if (swap_commutative(-1, &args[0], &args[1])) {
args[2] = tcg_swap_cond(args[2]);
}
break;
CASE_OP_32_64(setcond):
- if (temps[args[1]].state == TCG_TEMP_CONST
- && temps[args[2]].state != TCG_TEMP_CONST) {
- tmp = args[1];
- args[1] = args[2];
- args[2] = tmp;
+ if (swap_commutative(args[0], &args[1], &args[2])) {
args[3] = tcg_swap_cond(args[3]);
}
break;
CASE_OP_32_64(movcond):
- cond = args[5];
- if (temps[args[1]].state == TCG_TEMP_CONST
- && temps[args[2]].state != TCG_TEMP_CONST) {
- tmp = args[1];
- args[1] = args[2];
- args[2] = tmp;
- cond = tcg_swap_cond(cond);
+ if (swap_commutative(-1, &args[1], &args[2])) {
+ args[5] = tcg_swap_cond(args[5]);
}
/* For movcond, we canonicalize the "false" input reg to match
the destination reg so that the tcg backend can implement
a "move if true" operation. */
- if (args[0] == args[3]) {
- tmp = args[3];
- args[3] = args[4];
- args[4] = tmp;
- cond = tcg_invert_cond(cond);
+ if (swap_commutative(args[0], &args[4], &args[3])) {
+ args[5] = tcg_invert_cond(args[5]);
}
- args[5] = cond;
+ break;
+ case INDEX_op_add2_i32:
+ swap_commutative(args[0], &args[2], &args[4]);
+ swap_commutative(args[1], &args[3], &args[5]);
+ break;
+ case INDEX_op_mulu2_i32:
+ swap_commutative(args[0], &args[2], &args[3]);
+ break;
+ case INDEX_op_brcond2_i32:
+ if (swap_commutative2(&args[0], &args[2])) {
+ args[4] = tcg_swap_cond(args[4]);
+ }
+ break;
+ case INDEX_op_setcond2_i32:
+ if (swap_commutative2(&args[1], &args[3])) {
+ args[5] = tcg_swap_cond(args[5]);
+ }
+ break;
default:
break;
}
@@ -622,6 +692,7 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
gen_args += 2;
args += 2;
break;
+
CASE_OP_32_64(not):
CASE_OP_32_64(neg):
CASE_OP_32_64(ext8s):
@@ -634,14 +705,12 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
gen_opc_buf[op_index] = op_to_movi(op);
tmp = do_constant_folding(op, temps[args[1]].val, 0);
tcg_opt_gen_movi(gen_args, args[0], tmp);
- } else {
- reset_temp(args[0]);
- gen_args[0] = args[0];
- gen_args[1] = args[1];
+ gen_args += 2;
+ args += 2;
+ break;
}
- gen_args += 2;
- args += 2;
- break;
+ goto do_default;
+
CASE_OP_32_64(add):
CASE_OP_32_64(sub):
CASE_OP_32_64(mul):
@@ -665,15 +734,11 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
temps[args[2]].val);
tcg_opt_gen_movi(gen_args, args[0], tmp);
gen_args += 2;
- } else {
- reset_temp(args[0]);
- gen_args[0] = args[0];
- gen_args[1] = args[1];
- gen_args[2] = args[2];
- gen_args += 3;
+ args += 3;
+ break;
}
- args += 3;
- break;
+ goto do_default;
+
CASE_OP_32_64(deposit):
if (temps[args[1]].state == TCG_TEMP_CONST
&& temps[args[2]].state == TCG_TEMP_CONST) {
@@ -683,33 +748,22 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
| ((temps[args[2]].val & tmp) << args[3]);
tcg_opt_gen_movi(gen_args, args[0], tmp);
gen_args += 2;
- } else {
- reset_temp(args[0]);
- gen_args[0] = args[0];
- gen_args[1] = args[1];
- gen_args[2] = args[2];
- gen_args[3] = args[3];
- gen_args[4] = args[4];
- gen_args += 5;
+ args += 5;
+ break;
}
- args += 5;
- break;
+ goto do_default;
+
CASE_OP_32_64(setcond):
tmp = do_constant_folding_cond(op, args[1], args[2], args[3]);
if (tmp != 2) {
gen_opc_buf[op_index] = op_to_movi(op);
tcg_opt_gen_movi(gen_args, args[0], tmp);
gen_args += 2;
- } else {
- reset_temp(args[0]);
- gen_args[0] = args[0];
- gen_args[1] = args[1];
- gen_args[2] = args[2];
- gen_args[3] = args[3];
- gen_args += 4;
+ args += 4;
+ break;
}
- args += 4;
- break;
+ goto do_default;
+
CASE_OP_32_64(brcond):
tmp = do_constant_folding_cond(op, args[0], args[1], args[2]);
if (tmp != 2) {
@@ -721,17 +775,11 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
} else {
gen_opc_buf[op_index] = INDEX_op_nop;
}
- } else {
- memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
- reset_temp(args[0]);
- gen_args[0] = args[0];
- gen_args[1] = args[1];
- gen_args[2] = args[2];
- gen_args[3] = args[3];
- gen_args += 4;
+ args += 4;
+ break;
}
- args += 4;
- break;
+ goto do_default;
+
CASE_OP_32_64(movcond):
tmp = do_constant_folding_cond(op, args[1], args[2], args[5]);
if (tmp != 2) {
@@ -746,18 +794,125 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
tcg_opt_gen_mov(s, gen_args, args[0], args[4-tmp]);
gen_args += 2;
}
+ args += 6;
+ break;
+ }
+ goto do_default;
+
+ case INDEX_op_add2_i32:
+ case INDEX_op_sub2_i32:
+ if (temps[args[2]].state == TCG_TEMP_CONST
+ && temps[args[3]].state == TCG_TEMP_CONST
+ && temps[args[4]].state == TCG_TEMP_CONST
+ && temps[args[5]].state == TCG_TEMP_CONST) {
+ uint32_t al = temps[args[2]].val;
+ uint32_t ah = temps[args[3]].val;
+ uint32_t bl = temps[args[4]].val;
+ uint32_t bh = temps[args[5]].val;
+ uint64_t a = ((uint64_t)ah << 32) | al;
+ uint64_t b = ((uint64_t)bh << 32) | bl;
+ TCGArg rl, rh;
+
+ if (op == INDEX_op_add2_i32) {
+ a += b;
+ } else {
+ a -= b;
+ }
+
+ /* We emit the extra nop when we emit the add2/sub2. */
+ assert(gen_opc_buf[op_index + 1] == INDEX_op_nop);
+
+ rl = args[0];
+ rh = args[1];
+ gen_opc_buf[op_index] = INDEX_op_movi_i32;
+ gen_opc_buf[++op_index] = INDEX_op_movi_i32;
+ tcg_opt_gen_movi(&gen_args[0], rl, (uint32_t)a);
+ tcg_opt_gen_movi(&gen_args[2], rh, (uint32_t)(a >> 32));
+ gen_args += 4;
+ args += 6;
+ break;
+ }
+ goto do_default;
+
+ case INDEX_op_mulu2_i32:
+ if (temps[args[2]].state == TCG_TEMP_CONST
+ && temps[args[3]].state == TCG_TEMP_CONST) {
+ uint32_t a = temps[args[2]].val;
+ 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(gen_opc_buf[op_index + 1] == INDEX_op_nop);
+
+ rl = args[0];
+ rh = args[1];
+ gen_opc_buf[op_index] = INDEX_op_movi_i32;
+ gen_opc_buf[++op_index] = INDEX_op_movi_i32;
+ tcg_opt_gen_movi(&gen_args[0], rl, (uint32_t)r);
+ tcg_opt_gen_movi(&gen_args[2], rh, (uint32_t)(r >> 32));
+ gen_args += 4;
+ args += 4;
+ break;
+ }
+ goto do_default;
+
+ case INDEX_op_brcond2_i32:
+ tmp = do_constant_folding_cond2(&args[0], &args[2], args[4]);
+ if (tmp != 2) {
+ if (tmp) {
+ memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
+ gen_opc_buf[op_index] = INDEX_op_br;
+ gen_args[0] = args[5];
+ gen_args += 1;
+ } else {
+ gen_opc_buf[op_index] = INDEX_op_nop;
+ }
+ } else if ((args[4] == TCG_COND_LT || args[4] == TCG_COND_GE)
+ && temps[args[2]].state == TCG_TEMP_CONST
+ && temps[args[3]].state == TCG_TEMP_CONST
+ && temps[args[2]].val == 0
+ && temps[args[3]].val == 0) {
+ /* Simplify LT/GE comparisons vs zero to a single compare
+ vs the high word of the input. */
+ memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
+ 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;
} else {
- reset_temp(args[0]);
+ 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) {
+ gen_opc_buf[op_index] = INDEX_op_movi_i32;
+ tcg_opt_gen_movi(gen_args, args[0], tmp);
+ gen_args += 2;
+ } 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
+ && temps[args[3]].val == 0
+ && temps[args[4]].val == 0) {
+ /* Simplify LT/GE comparisons vs zero to a single compare
+ vs the high word of the input. */
+ gen_opc_buf[op_index] = INDEX_op_setcond_i32;
gen_args[0] = args[0];
- gen_args[1] = args[1];
- gen_args[2] = args[2];
- gen_args[3] = args[3];
- gen_args[4] = args[4];
- gen_args[5] = args[5];
- gen_args += 6;
+ gen_args[1] = args[2];
+ gen_args[2] = args[4];
+ gen_args[3] = args[5];
+ gen_args += 4;
+ } else {
+ goto do_default;
}
args += 6;
break;
+
case INDEX_op_call:
nb_call_args = (args[0] >> 16) + (args[0] & 0xffff);
if (!(args[nb_call_args + 1] & (TCG_CALL_CONST | TCG_CALL_PURE))) {
@@ -776,11 +931,13 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
i--;
}
break;
+
default:
- /* Default case: we do know nothing about operation so no
- propagation is done. We trash everything if the operation
- is the end of a basic block, otherwise we only trash the
- output args. */
+ do_default:
+ /* Default case: we know nothing about operation (or were unable
+ to compute the operation result) so no propagation is done.
+ We trash everything if the operation is the end of a basic
+ block, otherwise we only trash the output args. */
if (def->flags & TCG_OPF_BB_END) {
memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
} else {
diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
index 3259d898ab..ad433ae5bb 100644
--- a/tcg/ppc/tcg-target.h
+++ b/tcg/ppc/tcg-target.h
@@ -96,8 +96,6 @@ typedef enum {
#define TCG_AREG0 TCG_REG_R27
-#define TCG_TARGET_HAS_GUEST_BASE
-
#define tcg_qemu_tb_exec(env, tb_ptr) \
((long __attribute__ ((longcall)) \
(*)(void *, void *))code_gen_prologue)(env, tb_ptr)
diff --git a/tcg/ppc64/tcg-target.h b/tcg/ppc64/tcg-target.h
index 57569e8938..97fc5c9885 100644
--- a/tcg/ppc64/tcg-target.h
+++ b/tcg/ppc64/tcg-target.h
@@ -108,5 +108,4 @@ typedef enum {
#define TCG_AREG0 TCG_REG_R27
-#define TCG_TARGET_HAS_GUEST_BASE
#define TCG_TARGET_EXTEND_ARGS 1
diff --git a/tcg/s390/tcg-target.h b/tcg/s390/tcg-target.h
index ed55c331c6..a0181aef74 100644
--- a/tcg/s390/tcg-target.h
+++ b/tcg/s390/tcg-target.h
@@ -88,8 +88,6 @@ typedef enum TCGReg {
#define TCG_TARGET_HAS_movcond_i64 0
#endif
-#define TCG_TARGET_HAS_GUEST_BASE
-
/* used for function call generation */
#define TCG_REG_CALL_STACK TCG_REG_R15
#define TCG_TARGET_STACK_ALIGN 8
diff --git a/tcg/sparc/tcg-target.h b/tcg/sparc/tcg-target.h
index c2fbb23abb..0e7d398a41 100644
--- a/tcg/sparc/tcg-target.h
+++ b/tcg/sparc/tcg-target.h
@@ -125,8 +125,6 @@ typedef enum {
#define TCG_TARGET_HAS_movcond_i64 1
#endif
-#define TCG_TARGET_HAS_GUEST_BASE
-
#define TCG_AREG0 TCG_REG_I0
static inline void flush_icache_range(tcg_target_ulong start,
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index 551845801d..8100a5a2e0 100644
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -25,6 +25,11 @@
int gen_new_label(void);
+static inline void tcg_gen_op0(TCGOpcode opc)
+{
+ *gen_opc_ptr++ = opc;
+}
+
static inline void tcg_gen_op1_i32(TCGOpcode opc, TCGv_i32 arg1)
{
*gen_opc_ptr++ = opc;
@@ -886,6 +891,8 @@ static inline void tcg_gen_add_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
tcg_gen_op6_i32(INDEX_op_add2_i32, TCGV_LOW(ret), TCGV_HIGH(ret),
TCGV_LOW(arg1), TCGV_HIGH(arg1), TCGV_LOW(arg2),
TCGV_HIGH(arg2));
+ /* Allow the optimizer room to replace add2 with two moves. */
+ tcg_gen_op0(INDEX_op_nop);
}
static inline void tcg_gen_sub_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
@@ -893,6 +900,8 @@ static inline void tcg_gen_sub_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
tcg_gen_op6_i32(INDEX_op_sub2_i32, TCGV_LOW(ret), TCGV_HIGH(ret),
TCGV_LOW(arg1), TCGV_HIGH(arg1), TCGV_LOW(arg2),
TCGV_HIGH(arg2));
+ /* Allow the optimizer room to replace sub2 with two moves. */
+ tcg_gen_op0(INDEX_op_nop);
}
static inline void tcg_gen_and_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
@@ -1018,6 +1027,8 @@ static inline void tcg_gen_mul_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
tcg_gen_op4_i32(INDEX_op_mulu2_i32, TCGV_LOW(t0), TCGV_HIGH(t0),
TCGV_LOW(arg1), TCGV_LOW(arg2));
+ /* Allow the optimizer room to replace mulu2 with two moves. */
+ tcg_gen_op0(INDEX_op_nop);
tcg_gen_mul_i32(t1, TCGV_LOW(arg1), TCGV_HIGH(arg2));
tcg_gen_add_i32(TCGV_HIGH(t0), TCGV_HIGH(t0), t1);
diff --git a/tcg/tcg.c b/tcg/tcg.c
index 32cd0c6b65..5faaca5ebf 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -62,10 +62,6 @@
#include "elf.h"
-#if defined(CONFIG_USE_GUEST_BASE) && !defined(TCG_TARGET_HAS_GUEST_BASE)
-#error GUEST_BASE not supported on this host.
-#endif
-
/* Forward declarations for functions declared in tcg-target.c and used here. */
static void tcg_target_init(TCGContext *s);
static void tcg_target_qemu_prologue(TCGContext *s);
@@ -1307,8 +1303,58 @@ static void tcg_liveness_analysis(TCGContext *s)
break;
case INDEX_op_end:
break;
- /* XXX: optimize by hardcoding common cases (e.g. triadic ops) */
+
+ case INDEX_op_add2_i32:
+ case INDEX_op_sub2_i32:
+ args -= 6;
+ nb_iargs = 4;
+ nb_oargs = 2;
+ /* Test if the high part of the operation is dead, but not
+ the low part. The result can be optimized to a simple
+ add or sub. This happens often for x86_64 guest when the
+ cpu mode is set to 32 bit. */
+ if (dead_temps[args[1]]) {
+ if (dead_temps[args[0]]) {
+ goto do_remove;
+ }
+ /* Create the single operation plus nop. */
+ if (op == INDEX_op_add2_i32) {
+ op = INDEX_op_add_i32;
+ } else {
+ op = INDEX_op_sub_i32;
+ }
+ gen_opc_buf[op_index] = op;
+ args[1] = args[2];
+ args[2] = args[4];
+ assert(gen_opc_buf[op_index + 1] == INDEX_op_nop);
+ tcg_set_nop(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;
+ }
+ goto do_not_remove;
+
+ case INDEX_op_mulu2_i32:
+ args -= 4;
+ nb_iargs = 2;
+ nb_oargs = 2;
+ /* Likewise, test for the high part of the operation dead. */
+ if (dead_temps[args[1]]) {
+ if (dead_temps[args[0]]) {
+ goto do_remove;
+ }
+ gen_opc_buf[op_index] = op = INDEX_op_mul_i32;
+ args[1] = args[2];
+ args[2] = args[3];
+ assert(gen_opc_buf[op_index + 1] == INDEX_op_nop);
+ tcg_set_nop(s, gen_opc_buf + op_index + 1, args + 3, 1);
+ /* Fall through and 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;
@@ -1322,6 +1368,7 @@ static void tcg_liveness_analysis(TCGContext *s)
if (!dead_temps[arg])
goto do_not_remove;
}
+ do_remove:
tcg_set_nop(s, gen_opc_buf + op_index, args, def->nb_args);
#ifdef CONFIG_PROFILER
s->del_op_count++;
diff --git a/tcg/tcg.h b/tcg/tcg.h
index 7bafe0eeb6..45e94f536c 100644
--- a/tcg/tcg.h
+++ b/tcg/tcg.h
@@ -616,7 +616,7 @@ TCGv_i64 tcg_const_i64(int64_t val);
TCGv_i32 tcg_const_local_i32(int32_t val);
TCGv_i64 tcg_const_local_i64(int64_t val);
-extern uint8_t code_gen_prologue[];
+extern uint8_t *code_gen_prologue;
/* TCG targets may use a different definition of tcg_qemu_tb_exec. */
#if !defined(tcg_qemu_tb_exec)
diff --git a/tcg/tci/tcg-target.h b/tcg/tci/tcg-target.h
index 6d894953aa..37f28c0522 100644
--- a/tcg/tci/tcg-target.h
+++ b/tcg/tci/tcg-target.h
@@ -102,9 +102,6 @@
#define TCG_TARGET_HAS_movcond_i64 0
#endif /* TCG_TARGET_REG_BITS == 64 */
-/* Offset to user memory in user mode. */
-#define TCG_TARGET_HAS_GUEST_BASE
-
/* Number of registers available.
For 32 bit hosts, we need more than 8 registers (call arguments). */
/* #define TCG_TARGET_NB_REGS 8 */
generated by cgit v1.2.3 (git 2.26.2) at 2025-01-05 19:52:01 +0000