* THE SOFTWARE.
*/
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+#include "cpu.h"
+#include "exec/exec-all.h"
#include "tcg.h"
#include "tcg-op.h"
+#include "trace-tcg.h"
+#include "trace/mem.h"
/* Reduce the number of ifdefs below. This assumes that all uses of
TCGV_HIGH and TCGV_LOW are properly protected by a conditional that
int pi = oi - 1;
tcg_debug_assert(oi < OPC_BUF_SIZE);
- ctx->gen_last_op_idx = oi;
+ ctx->gen_op_buf[0].prev = oi;
ctx->gen_next_op_idx = ni;
ctx->gen_op_buf[oi] = (TCGOp){
tcg_emit_op(ctx, opc, pi);
}
+void tcg_gen_mb(TCGBar mb_type)
+{
+ if (parallel_cpus) {
+ tcg_gen_op1(&tcg_ctx, INDEX_op_mb, mb_type);
+ }
+}
+
/* 32 bit ops */
void tcg_gen_addi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2)
TCGv_i32 t1;
tcg_debug_assert(ofs < 32);
+ tcg_debug_assert(len > 0);
tcg_debug_assert(len <= 32);
tcg_debug_assert(ofs + len <= 32);
- if (ofs == 0 && len == 32) {
+ if (len == 32) {
tcg_gen_mov_i32(ret, arg2);
return;
}
tcg_temp_free_i32(t1);
}
+void tcg_gen_deposit_z_i32(TCGv_i32 ret, TCGv_i32 arg,
+ unsigned int ofs, unsigned int len)
+{
+ tcg_debug_assert(ofs < 32);
+ tcg_debug_assert(len > 0);
+ tcg_debug_assert(len <= 32);
+ tcg_debug_assert(ofs + len <= 32);
+
+ if (ofs + len == 32) {
+ tcg_gen_shli_i32(ret, arg, ofs);
+ } else if (ofs == 0) {
+ tcg_gen_andi_i32(ret, arg, (1u << len) - 1);
+ } else if (TCG_TARGET_HAS_deposit_i32
+ && TCG_TARGET_deposit_i32_valid(ofs, len)) {
+ TCGv_i32 zero = tcg_const_i32(0);
+ tcg_gen_op5ii_i32(INDEX_op_deposit_i32, ret, zero, arg, ofs, len);
+ tcg_temp_free_i32(zero);
+ } else {
+ /* To help two-operand hosts we prefer to zero-extend first,
+ which allows ARG to stay live. */
+ switch (len) {
+ case 16:
+ if (TCG_TARGET_HAS_ext16u_i32) {
+ tcg_gen_ext16u_i32(ret, arg);
+ tcg_gen_shli_i32(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8u_i32) {
+ tcg_gen_ext8u_i32(ret, arg);
+ tcg_gen_shli_i32(ret, ret, ofs);
+ return;
+ }
+ break;
+ }
+ /* Otherwise prefer zero-extension over AND for code size. */
+ switch (ofs + len) {
+ case 16:
+ if (TCG_TARGET_HAS_ext16u_i32) {
+ tcg_gen_shli_i32(ret, arg, ofs);
+ tcg_gen_ext16u_i32(ret, ret);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8u_i32) {
+ tcg_gen_shli_i32(ret, arg, ofs);
+ tcg_gen_ext8u_i32(ret, ret);
+ return;
+ }
+ break;
+ }
+ tcg_gen_andi_i32(ret, arg, (1u << len) - 1);
+ tcg_gen_shli_i32(ret, ret, ofs);
+ }
+}
+
+void tcg_gen_extract_i32(TCGv_i32 ret, TCGv_i32 arg,
+ unsigned int ofs, unsigned int len)
+{
+ tcg_debug_assert(ofs < 32);
+ tcg_debug_assert(len > 0);
+ tcg_debug_assert(len <= 32);
+ tcg_debug_assert(ofs + len <= 32);
+
+ /* Canonicalize certain special cases, even if extract is supported. */
+ if (ofs + len == 32) {
+ tcg_gen_shri_i32(ret, arg, 32 - len);
+ return;
+ }
+ if (ofs == 0) {
+ tcg_gen_andi_i32(ret, arg, (1u << len) - 1);
+ return;
+ }
+
+ if (TCG_TARGET_HAS_extract_i32
+ && TCG_TARGET_extract_i32_valid(ofs, len)) {
+ tcg_gen_op4ii_i32(INDEX_op_extract_i32, ret, arg, ofs, len);
+ return;
+ }
+
+ /* Assume that zero-extension, if available, is cheaper than a shift. */
+ switch (ofs + len) {
+ case 16:
+ if (TCG_TARGET_HAS_ext16u_i32) {
+ tcg_gen_ext16u_i32(ret, arg);
+ tcg_gen_shri_i32(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8u_i32) {
+ tcg_gen_ext8u_i32(ret, arg);
+ tcg_gen_shri_i32(ret, ret, ofs);
+ return;
+ }
+ break;
+ }
+
+ /* ??? Ideally we'd know what values are available for immediate AND.
+ Assume that 8 bits are available, plus the special case of 16,
+ so that we get ext8u, ext16u. */
+ switch (len) {
+ case 1 ... 8: case 16:
+ tcg_gen_shri_i32(ret, arg, ofs);
+ tcg_gen_andi_i32(ret, ret, (1u << len) - 1);
+ break;
+ default:
+ tcg_gen_shli_i32(ret, arg, 32 - len - ofs);
+ tcg_gen_shri_i32(ret, ret, 32 - len);
+ break;
+ }
+}
+
+void tcg_gen_sextract_i32(TCGv_i32 ret, TCGv_i32 arg,
+ unsigned int ofs, unsigned int len)
+{
+ tcg_debug_assert(ofs < 32);
+ tcg_debug_assert(len > 0);
+ tcg_debug_assert(len <= 32);
+ tcg_debug_assert(ofs + len <= 32);
+
+ /* Canonicalize certain special cases, even if extract is supported. */
+ if (ofs + len == 32) {
+ tcg_gen_sari_i32(ret, arg, 32 - len);
+ return;
+ }
+ if (ofs == 0) {
+ switch (len) {
+ case 16:
+ tcg_gen_ext16s_i32(ret, arg);
+ return;
+ case 8:
+ tcg_gen_ext8s_i32(ret, arg);
+ return;
+ }
+ }
+
+ if (TCG_TARGET_HAS_sextract_i32
+ && TCG_TARGET_extract_i32_valid(ofs, len)) {
+ tcg_gen_op4ii_i32(INDEX_op_sextract_i32, ret, arg, ofs, len);
+ return;
+ }
+
+ /* Assume that sign-extension, if available, is cheaper than a shift. */
+ switch (ofs + len) {
+ case 16:
+ if (TCG_TARGET_HAS_ext16s_i32) {
+ tcg_gen_ext16s_i32(ret, arg);
+ tcg_gen_sari_i32(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8s_i32) {
+ tcg_gen_ext8s_i32(ret, arg);
+ tcg_gen_sari_i32(ret, ret, ofs);
+ return;
+ }
+ break;
+ }
+ switch (len) {
+ case 16:
+ if (TCG_TARGET_HAS_ext16s_i32) {
+ tcg_gen_shri_i32(ret, arg, ofs);
+ tcg_gen_ext16s_i32(ret, ret);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8s_i32) {
+ tcg_gen_shri_i32(ret, arg, ofs);
+ tcg_gen_ext8s_i32(ret, ret);
+ return;
+ }
+ break;
+ }
+
+ tcg_gen_shli_i32(ret, arg, 32 - len - ofs);
+ tcg_gen_sari_i32(ret, ret, 32 - len);
+}
+
void tcg_gen_movcond_i32(TCGCond cond, TCGv_i32 ret, TCGv_i32 c1,
TCGv_i32 c2, TCGv_i32 v1, TCGv_i32 v2)
{
}
}
+void tcg_gen_mulsu2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+ if (TCG_TARGET_REG_BITS == 32) {
+ TCGv_i32 t0 = tcg_temp_new_i32();
+ TCGv_i32 t1 = tcg_temp_new_i32();
+ TCGv_i32 t2 = tcg_temp_new_i32();
+ tcg_gen_mulu2_i32(t0, t1, arg1, arg2);
+ /* Adjust for negative input for the signed arg1. */
+ tcg_gen_sari_i32(t2, arg1, 31);
+ tcg_gen_and_i32(t2, t2, arg2);
+ tcg_gen_sub_i32(rh, t1, t2);
+ tcg_gen_mov_i32(rl, t0);
+ tcg_temp_free_i32(t0);
+ tcg_temp_free_i32(t1);
+ tcg_temp_free_i32(t2);
+ } else {
+ TCGv_i64 t0 = tcg_temp_new_i64();
+ TCGv_i64 t1 = tcg_temp_new_i64();
+ tcg_gen_ext_i32_i64(t0, arg1);
+ tcg_gen_extu_i32_i64(t1, arg2);
+ tcg_gen_mul_i64(t0, t0, t1);
+ tcg_gen_extr_i64_i32(rl, rh, t0);
+ tcg_temp_free_i64(t0);
+ tcg_temp_free_i64(t1);
+ }
+}
+
void tcg_gen_ext8s_i32(TCGv_i32 ret, TCGv_i32 arg)
{
if (TCG_TARGET_HAS_ext8s_i32) {
void tcg_gen_ld8s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset)
{
tcg_gen_ld8s_i32(TCGV_LOW(ret), arg2, offset);
- tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_HIGH(ret), 31);
+ tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
}
void tcg_gen_ld16u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset)
TCGv_i64 t1;
tcg_debug_assert(ofs < 64);
+ tcg_debug_assert(len > 0);
tcg_debug_assert(len <= 64);
tcg_debug_assert(ofs + len <= 64);
- if (ofs == 0 && len == 64) {
+ if (len == 64) {
tcg_gen_mov_i64(ret, arg2);
return;
}
tcg_temp_free_i64(t1);
}
+void tcg_gen_deposit_z_i64(TCGv_i64 ret, TCGv_i64 arg,
+ unsigned int ofs, unsigned int len)
+{
+ tcg_debug_assert(ofs < 64);
+ tcg_debug_assert(len > 0);
+ tcg_debug_assert(len <= 64);
+ tcg_debug_assert(ofs + len <= 64);
+
+ if (ofs + len == 64) {
+ tcg_gen_shli_i64(ret, arg, ofs);
+ } else if (ofs == 0) {
+ tcg_gen_andi_i64(ret, arg, (1ull << len) - 1);
+ } else if (TCG_TARGET_HAS_deposit_i64
+ && TCG_TARGET_deposit_i64_valid(ofs, len)) {
+ TCGv_i64 zero = tcg_const_i64(0);
+ tcg_gen_op5ii_i64(INDEX_op_deposit_i64, ret, zero, arg, ofs, len);
+ tcg_temp_free_i64(zero);
+ } else {
+ if (TCG_TARGET_REG_BITS == 32) {
+ if (ofs >= 32) {
+ tcg_gen_deposit_z_i32(TCGV_HIGH(ret), TCGV_LOW(arg),
+ ofs - 32, len);
+ tcg_gen_movi_i32(TCGV_LOW(ret), 0);
+ return;
+ }
+ if (ofs + len <= 32) {
+ tcg_gen_deposit_z_i32(TCGV_LOW(ret), TCGV_LOW(arg), ofs, len);
+ tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+ return;
+ }
+ }
+ /* To help two-operand hosts we prefer to zero-extend first,
+ which allows ARG to stay live. */
+ switch (len) {
+ case 32:
+ if (TCG_TARGET_HAS_ext32u_i64) {
+ tcg_gen_ext32u_i64(ret, arg);
+ tcg_gen_shli_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 16:
+ if (TCG_TARGET_HAS_ext16u_i64) {
+ tcg_gen_ext16u_i64(ret, arg);
+ tcg_gen_shli_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8u_i64) {
+ tcg_gen_ext8u_i64(ret, arg);
+ tcg_gen_shli_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ }
+ /* Otherwise prefer zero-extension over AND for code size. */
+ switch (ofs + len) {
+ case 32:
+ if (TCG_TARGET_HAS_ext32u_i64) {
+ tcg_gen_shli_i64(ret, arg, ofs);
+ tcg_gen_ext32u_i64(ret, ret);
+ return;
+ }
+ break;
+ case 16:
+ if (TCG_TARGET_HAS_ext16u_i64) {
+ tcg_gen_shli_i64(ret, arg, ofs);
+ tcg_gen_ext16u_i64(ret, ret);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8u_i64) {
+ tcg_gen_shli_i64(ret, arg, ofs);
+ tcg_gen_ext8u_i64(ret, ret);
+ return;
+ }
+ break;
+ }
+ tcg_gen_andi_i64(ret, arg, (1ull << len) - 1);
+ tcg_gen_shli_i64(ret, ret, ofs);
+ }
+}
+
+void tcg_gen_extract_i64(TCGv_i64 ret, TCGv_i64 arg,
+ unsigned int ofs, unsigned int len)
+{
+ tcg_debug_assert(ofs < 64);
+ tcg_debug_assert(len > 0);
+ tcg_debug_assert(len <= 64);
+ tcg_debug_assert(ofs + len <= 64);
+
+ /* Canonicalize certain special cases, even if extract is supported. */
+ if (ofs + len == 64) {
+ tcg_gen_shri_i64(ret, arg, 64 - len);
+ return;
+ }
+ if (ofs == 0) {
+ tcg_gen_andi_i64(ret, arg, (1ull << len) - 1);
+ return;
+ }
+
+ if (TCG_TARGET_REG_BITS == 32) {
+ /* Look for a 32-bit extract within one of the two words. */
+ if (ofs >= 32) {
+ tcg_gen_extract_i32(TCGV_LOW(ret), TCGV_HIGH(arg), ofs - 32, len);
+ tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+ return;
+ }
+ if (ofs + len <= 32) {
+ tcg_gen_extract_i32(TCGV_LOW(ret), TCGV_LOW(arg), ofs, len);
+ tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+ return;
+ }
+ /* The field is split across two words. One double-word
+ shift is better than two double-word shifts. */
+ goto do_shift_and;
+ }
+
+ if (TCG_TARGET_HAS_extract_i64
+ && TCG_TARGET_extract_i64_valid(ofs, len)) {
+ tcg_gen_op4ii_i64(INDEX_op_extract_i64, ret, arg, ofs, len);
+ return;
+ }
+
+ /* Assume that zero-extension, if available, is cheaper than a shift. */
+ switch (ofs + len) {
+ case 32:
+ if (TCG_TARGET_HAS_ext32u_i64) {
+ tcg_gen_ext32u_i64(ret, arg);
+ tcg_gen_shri_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 16:
+ if (TCG_TARGET_HAS_ext16u_i64) {
+ tcg_gen_ext16u_i64(ret, arg);
+ tcg_gen_shri_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8u_i64) {
+ tcg_gen_ext8u_i64(ret, arg);
+ tcg_gen_shri_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ }
+
+ /* ??? Ideally we'd know what values are available for immediate AND.
+ Assume that 8 bits are available, plus the special cases of 16 and 32,
+ so that we get ext8u, ext16u, and ext32u. */
+ switch (len) {
+ case 1 ... 8: case 16: case 32:
+ do_shift_and:
+ tcg_gen_shri_i64(ret, arg, ofs);
+ tcg_gen_andi_i64(ret, ret, (1ull << len) - 1);
+ break;
+ default:
+ tcg_gen_shli_i64(ret, arg, 64 - len - ofs);
+ tcg_gen_shri_i64(ret, ret, 64 - len);
+ break;
+ }
+}
+
+void tcg_gen_sextract_i64(TCGv_i64 ret, TCGv_i64 arg,
+ unsigned int ofs, unsigned int len)
+{
+ tcg_debug_assert(ofs < 64);
+ tcg_debug_assert(len > 0);
+ tcg_debug_assert(len <= 64);
+ tcg_debug_assert(ofs + len <= 64);
+
+ /* Canonicalize certain special cases, even if sextract is supported. */
+ if (ofs + len == 64) {
+ tcg_gen_sari_i64(ret, arg, 64 - len);
+ return;
+ }
+ if (ofs == 0) {
+ switch (len) {
+ case 32:
+ tcg_gen_ext32s_i64(ret, arg);
+ return;
+ case 16:
+ tcg_gen_ext16s_i64(ret, arg);
+ return;
+ case 8:
+ tcg_gen_ext8s_i64(ret, arg);
+ return;
+ }
+ }
+
+ if (TCG_TARGET_REG_BITS == 32) {
+ /* Look for a 32-bit extract within one of the two words. */
+ if (ofs >= 32) {
+ tcg_gen_sextract_i32(TCGV_LOW(ret), TCGV_HIGH(arg), ofs - 32, len);
+ } else if (ofs + len <= 32) {
+ tcg_gen_sextract_i32(TCGV_LOW(ret), TCGV_LOW(arg), ofs, len);
+ } else if (ofs == 0) {
+ tcg_gen_mov_i32(TCGV_LOW(ret), TCGV_LOW(arg));
+ tcg_gen_sextract_i32(TCGV_HIGH(ret), TCGV_HIGH(arg), 0, len - 32);
+ return;
+ } else if (len > 32) {
+ TCGv_i32 t = tcg_temp_new_i32();
+ /* Extract the bits for the high word normally. */
+ tcg_gen_sextract_i32(t, TCGV_HIGH(arg), ofs + 32, len - 32);
+ /* Shift the field down for the low part. */
+ tcg_gen_shri_i64(ret, arg, ofs);
+ /* Overwrite the shift into the high part. */
+ tcg_gen_mov_i32(TCGV_HIGH(ret), t);
+ tcg_temp_free_i32(t);
+ return;
+ } else {
+ /* Shift the field down for the low part, such that the
+ field sits at the MSB. */
+ tcg_gen_shri_i64(ret, arg, ofs + len - 32);
+ /* Shift the field down from the MSB, sign extending. */
+ tcg_gen_sari_i32(TCGV_LOW(ret), TCGV_LOW(ret), 32 - len);
+ }
+ /* Sign-extend the field from 32 bits. */
+ tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
+ return;
+ }
+
+ if (TCG_TARGET_HAS_sextract_i64
+ && TCG_TARGET_extract_i64_valid(ofs, len)) {
+ tcg_gen_op4ii_i64(INDEX_op_sextract_i64, ret, arg, ofs, len);
+ return;
+ }
+
+ /* Assume that sign-extension, if available, is cheaper than a shift. */
+ switch (ofs + len) {
+ case 32:
+ if (TCG_TARGET_HAS_ext32s_i64) {
+ tcg_gen_ext32s_i64(ret, arg);
+ tcg_gen_sari_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 16:
+ if (TCG_TARGET_HAS_ext16s_i64) {
+ tcg_gen_ext16s_i64(ret, arg);
+ tcg_gen_sari_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8s_i64) {
+ tcg_gen_ext8s_i64(ret, arg);
+ tcg_gen_sari_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ }
+ switch (len) {
+ case 32:
+ if (TCG_TARGET_HAS_ext32s_i64) {
+ tcg_gen_shri_i64(ret, arg, ofs);
+ tcg_gen_ext32s_i64(ret, ret);
+ return;
+ }
+ break;
+ case 16:
+ if (TCG_TARGET_HAS_ext16s_i64) {
+ tcg_gen_shri_i64(ret, arg, ofs);
+ tcg_gen_ext16s_i64(ret, ret);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8s_i64) {
+ tcg_gen_shri_i64(ret, arg, ofs);
+ tcg_gen_ext8s_i64(ret, ret);
+ return;
+ }
+ break;
+ }
+ tcg_gen_shli_i64(ret, arg, 64 - len - ofs);
+ tcg_gen_sari_i64(ret, ret, 64 - len);
+}
+
void tcg_gen_movcond_i64(TCGCond cond, TCGv_i64 ret, TCGv_i64 c1,
TCGv_i64 c2, TCGv_i64 v1, TCGv_i64 v2)
{
}
}
+void tcg_gen_mulsu2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+ TCGv_i64 t0 = tcg_temp_new_i64();
+ TCGv_i64 t1 = tcg_temp_new_i64();
+ TCGv_i64 t2 = tcg_temp_new_i64();
+ tcg_gen_mulu2_i64(t0, t1, arg1, arg2);
+ /* Adjust for negative input for the signed arg1. */
+ tcg_gen_sari_i64(t2, arg1, 63);
+ tcg_gen_and_i64(t2, t2, arg2);
+ tcg_gen_sub_i64(rh, t1, t2);
+ tcg_gen_mov_i64(rl, t0);
+ tcg_temp_free_i64(t0);
+ tcg_temp_free_i64(t1);
+ tcg_temp_free_i64(t2);
+}
+
/* Size changing operations. */
-void tcg_gen_trunc_shr_i64_i32(TCGv_i32 ret, TCGv_i64 arg, unsigned count)
+void tcg_gen_extrl_i64_i32(TCGv_i32 ret, TCGv_i64 arg)
{
- tcg_debug_assert(count < 64);
if (TCG_TARGET_REG_BITS == 32) {
- if (count >= 32) {
- tcg_gen_shri_i32(ret, TCGV_HIGH(arg), count - 32);
- } else if (count == 0) {
- tcg_gen_mov_i32(ret, TCGV_LOW(arg));
- } else {
- TCGv_i64 t = tcg_temp_new_i64();
- tcg_gen_shri_i64(t, arg, count);
- tcg_gen_mov_i32(ret, TCGV_LOW(t));
- tcg_temp_free_i64(t);
- }
- } else if (TCG_TARGET_HAS_trunc_shr_i32) {
- tcg_gen_op3i_i32(INDEX_op_trunc_shr_i32, ret,
- MAKE_TCGV_I32(GET_TCGV_I64(arg)), count);
- } else if (count == 0) {
+ tcg_gen_mov_i32(ret, TCGV_LOW(arg));
+ } else if (TCG_TARGET_HAS_extrl_i64_i32) {
+ tcg_gen_op2(&tcg_ctx, INDEX_op_extrl_i64_i32,
+ GET_TCGV_I32(ret), GET_TCGV_I64(arg));
+ } else {
tcg_gen_mov_i32(ret, MAKE_TCGV_I32(GET_TCGV_I64(arg)));
+ }
+}
+
+void tcg_gen_extrh_i64_i32(TCGv_i32 ret, TCGv_i64 arg)
+{
+ if (TCG_TARGET_REG_BITS == 32) {
+ tcg_gen_mov_i32(ret, TCGV_HIGH(arg));
+ } else if (TCG_TARGET_HAS_extrh_i64_i32) {
+ tcg_gen_op2(&tcg_ctx, INDEX_op_extrh_i64_i32,
+ GET_TCGV_I32(ret), GET_TCGV_I64(arg));
} else {
TCGv_i64 t = tcg_temp_new_i64();
- tcg_gen_shri_i64(t, arg, count);
+ tcg_gen_shri_i64(t, arg, 32);
tcg_gen_mov_i32(ret, MAKE_TCGV_I32(GET_TCGV_I64(t)));
tcg_temp_free_i64(t);
}
tcg_gen_mov_i32(TCGV_LOW(ret), arg);
tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
} else {
- /* Note: we assume the target supports move between
- 32 and 64 bit registers. */
- tcg_gen_ext32u_i64(ret, MAKE_TCGV_I64(GET_TCGV_I32(arg)));
+ tcg_gen_op2(&tcg_ctx, INDEX_op_extu_i32_i64,
+ GET_TCGV_I64(ret), GET_TCGV_I32(arg));
}
}
tcg_gen_mov_i32(TCGV_LOW(ret), arg);
tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
} else {
- /* Note: we assume the target supports move between
- 32 and 64 bit registers. */
- tcg_gen_ext32s_i64(ret, MAKE_TCGV_I64(GET_TCGV_I32(arg)));
+ tcg_gen_op2(&tcg_ctx, INDEX_op_ext_i32_i64,
+ GET_TCGV_I64(ret), GET_TCGV_I32(arg));
}
}
tcg_gen_mov_i32(lo, TCGV_LOW(arg));
tcg_gen_mov_i32(hi, TCGV_HIGH(arg));
} else {
- tcg_gen_trunc_shr_i64_i32(lo, arg, 0);
- tcg_gen_trunc_shr_i64_i32(hi, arg, 32);
+ tcg_gen_extrl_i64_i32(lo, arg);
+ tcg_gen_extrh_i64_i32(hi, arg);
}
}
static inline TCGMemOp tcg_canonicalize_memop(TCGMemOp op, bool is64, bool st)
{
+ /* Trigger the asserts within as early as possible. */
+ (void)get_alignment_bits(op);
+
switch (op & MO_SIZE) {
case MO_8:
op &= ~MO_BSWAP;
void tcg_gen_qemu_ld_i32(TCGv_i32 val, TCGv addr, TCGArg idx, TCGMemOp memop)
{
memop = tcg_canonicalize_memop(memop, 0, 0);
+ trace_guest_mem_before_tcg(tcg_ctx.cpu, tcg_ctx.tcg_env,
+ addr, trace_mem_get_info(memop, 0));
gen_ldst_i32(INDEX_op_qemu_ld_i32, val, addr, memop, idx);
}
void tcg_gen_qemu_st_i32(TCGv_i32 val, TCGv addr, TCGArg idx, TCGMemOp memop)
{
memop = tcg_canonicalize_memop(memop, 0, 1);
+ trace_guest_mem_before_tcg(tcg_ctx.cpu, tcg_ctx.tcg_env,
+ addr, trace_mem_get_info(memop, 1));
gen_ldst_i32(INDEX_op_qemu_st_i32, val, addr, memop, idx);
}
}
memop = tcg_canonicalize_memop(memop, 1, 0);
+ trace_guest_mem_before_tcg(tcg_ctx.cpu, tcg_ctx.tcg_env,
+ addr, trace_mem_get_info(memop, 0));
gen_ldst_i64(INDEX_op_qemu_ld_i64, val, addr, memop, idx);
}
}
memop = tcg_canonicalize_memop(memop, 1, 1);
+ trace_guest_mem_before_tcg(tcg_ctx.cpu, tcg_ctx.tcg_env,
+ addr, trace_mem_get_info(memop, 1));
gen_ldst_i64(INDEX_op_qemu_st_i64, val, addr, memop, idx);
}
+
+static void tcg_gen_ext_i32(TCGv_i32 ret, TCGv_i32 val, TCGMemOp opc)
+{
+ switch (opc & MO_SSIZE) {
+ case MO_SB:
+ tcg_gen_ext8s_i32(ret, val);
+ break;
+ case MO_UB:
+ tcg_gen_ext8u_i32(ret, val);
+ break;
+ case MO_SW:
+ tcg_gen_ext16s_i32(ret, val);
+ break;
+ case MO_UW:
+ tcg_gen_ext16u_i32(ret, val);
+ break;
+ default:
+ tcg_gen_mov_i32(ret, val);
+ break;
+ }
+}
+
+static void tcg_gen_ext_i64(TCGv_i64 ret, TCGv_i64 val, TCGMemOp opc)
+{
+ switch (opc & MO_SSIZE) {
+ case MO_SB:
+ tcg_gen_ext8s_i64(ret, val);
+ break;
+ case MO_UB:
+ tcg_gen_ext8u_i64(ret, val);
+ break;
+ case MO_SW:
+ tcg_gen_ext16s_i64(ret, val);
+ break;
+ case MO_UW:
+ tcg_gen_ext16u_i64(ret, val);
+ break;
+ case MO_SL:
+ tcg_gen_ext32s_i64(ret, val);
+ break;
+ case MO_UL:
+ tcg_gen_ext32u_i64(ret, val);
+ break;
+ default:
+ tcg_gen_mov_i64(ret, val);
+ break;
+ }
+}
+
+#ifdef CONFIG_SOFTMMU
+typedef void (*gen_atomic_cx_i32)(TCGv_i32, TCGv_env, TCGv,
+ TCGv_i32, TCGv_i32, TCGv_i32);
+typedef void (*gen_atomic_cx_i64)(TCGv_i64, TCGv_env, TCGv,
+ TCGv_i64, TCGv_i64, TCGv_i32);
+typedef void (*gen_atomic_op_i32)(TCGv_i32, TCGv_env, TCGv,
+ TCGv_i32, TCGv_i32);
+typedef void (*gen_atomic_op_i64)(TCGv_i64, TCGv_env, TCGv,
+ TCGv_i64, TCGv_i32);
+#else
+typedef void (*gen_atomic_cx_i32)(TCGv_i32, TCGv_env, TCGv, TCGv_i32, TCGv_i32);
+typedef void (*gen_atomic_cx_i64)(TCGv_i64, TCGv_env, TCGv, TCGv_i64, TCGv_i64);
+typedef void (*gen_atomic_op_i32)(TCGv_i32, TCGv_env, TCGv, TCGv_i32);
+typedef void (*gen_atomic_op_i64)(TCGv_i64, TCGv_env, TCGv, TCGv_i64);
+#endif
+
+#ifdef CONFIG_ATOMIC64
+# define WITH_ATOMIC64(X) X,
+#else
+# define WITH_ATOMIC64(X)
+#endif
+
+static void * const table_cmpxchg[16] = {
+ [MO_8] = gen_helper_atomic_cmpxchgb,
+ [MO_16 | MO_LE] = gen_helper_atomic_cmpxchgw_le,
+ [MO_16 | MO_BE] = gen_helper_atomic_cmpxchgw_be,
+ [MO_32 | MO_LE] = gen_helper_atomic_cmpxchgl_le,
+ [MO_32 | MO_BE] = gen_helper_atomic_cmpxchgl_be,
+ WITH_ATOMIC64([MO_64 | MO_LE] = gen_helper_atomic_cmpxchgq_le)
+ WITH_ATOMIC64([MO_64 | MO_BE] = gen_helper_atomic_cmpxchgq_be)
+};
+
+void tcg_gen_atomic_cmpxchg_i32(TCGv_i32 retv, TCGv addr, TCGv_i32 cmpv,
+ TCGv_i32 newv, TCGArg idx, TCGMemOp memop)
+{
+ memop = tcg_canonicalize_memop(memop, 0, 0);
+
+ if (!parallel_cpus) {
+ TCGv_i32 t1 = tcg_temp_new_i32();
+ TCGv_i32 t2 = tcg_temp_new_i32();
+
+ tcg_gen_ext_i32(t2, cmpv, memop & MO_SIZE);
+
+ tcg_gen_qemu_ld_i32(t1, addr, idx, memop & ~MO_SIGN);
+ tcg_gen_movcond_i32(TCG_COND_EQ, t2, t1, t2, newv, t1);
+ tcg_gen_qemu_st_i32(t2, addr, idx, memop);
+ tcg_temp_free_i32(t2);
+
+ if (memop & MO_SIGN) {
+ tcg_gen_ext_i32(retv, t1, memop);
+ } else {
+ tcg_gen_mov_i32(retv, t1);
+ }
+ tcg_temp_free_i32(t1);
+ } else {
+ gen_atomic_cx_i32 gen;
+
+ gen = table_cmpxchg[memop & (MO_SIZE | MO_BSWAP)];
+ tcg_debug_assert(gen != NULL);
+
+#ifdef CONFIG_SOFTMMU
+ {
+ TCGv_i32 oi = tcg_const_i32(make_memop_idx(memop & ~MO_SIGN, idx));
+ gen(retv, tcg_ctx.tcg_env, addr, cmpv, newv, oi);
+ tcg_temp_free_i32(oi);
+ }
+#else
+ gen(retv, tcg_ctx.tcg_env, addr, cmpv, newv);
+#endif
+
+ if (memop & MO_SIGN) {
+ tcg_gen_ext_i32(retv, retv, memop);
+ }
+ }
+}
+
+void tcg_gen_atomic_cmpxchg_i64(TCGv_i64 retv, TCGv addr, TCGv_i64 cmpv,
+ TCGv_i64 newv, TCGArg idx, TCGMemOp memop)
+{
+ memop = tcg_canonicalize_memop(memop, 1, 0);
+
+ if (!parallel_cpus) {
+ TCGv_i64 t1 = tcg_temp_new_i64();
+ TCGv_i64 t2 = tcg_temp_new_i64();
+
+ tcg_gen_ext_i64(t2, cmpv, memop & MO_SIZE);
+
+ tcg_gen_qemu_ld_i64(t1, addr, idx, memop & ~MO_SIGN);
+ tcg_gen_movcond_i64(TCG_COND_EQ, t2, t1, t2, newv, t1);
+ tcg_gen_qemu_st_i64(t2, addr, idx, memop);
+ tcg_temp_free_i64(t2);
+
+ if (memop & MO_SIGN) {
+ tcg_gen_ext_i64(retv, t1, memop);
+ } else {
+ tcg_gen_mov_i64(retv, t1);
+ }
+ tcg_temp_free_i64(t1);
+ } else if ((memop & MO_SIZE) == MO_64) {
+#ifdef CONFIG_ATOMIC64
+ gen_atomic_cx_i64 gen;
+
+ gen = table_cmpxchg[memop & (MO_SIZE | MO_BSWAP)];
+ tcg_debug_assert(gen != NULL);
+
+#ifdef CONFIG_SOFTMMU
+ {
+ TCGv_i32 oi = tcg_const_i32(make_memop_idx(memop, idx));
+ gen(retv, tcg_ctx.tcg_env, addr, cmpv, newv, oi);
+ tcg_temp_free_i32(oi);
+ }
+#else
+ gen(retv, tcg_ctx.tcg_env, addr, cmpv, newv);
+#endif
+#else
+ gen_helper_exit_atomic(tcg_ctx.tcg_env);
+#endif /* CONFIG_ATOMIC64 */
+ } else {
+ TCGv_i32 c32 = tcg_temp_new_i32();
+ TCGv_i32 n32 = tcg_temp_new_i32();
+ TCGv_i32 r32 = tcg_temp_new_i32();
+
+ tcg_gen_extrl_i64_i32(c32, cmpv);
+ tcg_gen_extrl_i64_i32(n32, newv);
+ tcg_gen_atomic_cmpxchg_i32(r32, addr, c32, n32, idx, memop & ~MO_SIGN);
+ tcg_temp_free_i32(c32);
+ tcg_temp_free_i32(n32);
+
+ tcg_gen_extu_i32_i64(retv, r32);
+ tcg_temp_free_i32(r32);
+
+ if (memop & MO_SIGN) {
+ tcg_gen_ext_i64(retv, retv, memop);
+ }
+ }
+}
+
+static void do_nonatomic_op_i32(TCGv_i32 ret, TCGv addr, TCGv_i32 val,
+ TCGArg idx, TCGMemOp memop, bool new_val,
+ void (*gen)(TCGv_i32, TCGv_i32, TCGv_i32))
+{
+ TCGv_i32 t1 = tcg_temp_new_i32();
+ TCGv_i32 t2 = tcg_temp_new_i32();
+
+ memop = tcg_canonicalize_memop(memop, 0, 0);
+
+ tcg_gen_qemu_ld_i32(t1, addr, idx, memop & ~MO_SIGN);
+ gen(t2, t1, val);
+ tcg_gen_qemu_st_i32(t2, addr, idx, memop);
+
+ tcg_gen_ext_i32(ret, (new_val ? t2 : t1), memop);
+ tcg_temp_free_i32(t1);
+ tcg_temp_free_i32(t2);
+}
+
+static void do_atomic_op_i32(TCGv_i32 ret, TCGv addr, TCGv_i32 val,
+ TCGArg idx, TCGMemOp memop, void * const table[])
+{
+ gen_atomic_op_i32 gen;
+
+ memop = tcg_canonicalize_memop(memop, 0, 0);
+
+ gen = table[memop & (MO_SIZE | MO_BSWAP)];
+ tcg_debug_assert(gen != NULL);
+
+#ifdef CONFIG_SOFTMMU
+ {
+ TCGv_i32 oi = tcg_const_i32(make_memop_idx(memop & ~MO_SIGN, idx));
+ gen(ret, tcg_ctx.tcg_env, addr, val, oi);
+ tcg_temp_free_i32(oi);
+ }
+#else
+ gen(ret, tcg_ctx.tcg_env, addr, val);
+#endif
+
+ if (memop & MO_SIGN) {
+ tcg_gen_ext_i32(ret, ret, memop);
+ }
+}
+
+static void do_nonatomic_op_i64(TCGv_i64 ret, TCGv addr, TCGv_i64 val,
+ TCGArg idx, TCGMemOp memop, bool new_val,
+ void (*gen)(TCGv_i64, TCGv_i64, TCGv_i64))
+{
+ TCGv_i64 t1 = tcg_temp_new_i64();
+ TCGv_i64 t2 = tcg_temp_new_i64();
+
+ memop = tcg_canonicalize_memop(memop, 1, 0);
+
+ tcg_gen_qemu_ld_i64(t1, addr, idx, memop & ~MO_SIGN);
+ gen(t2, t1, val);
+ tcg_gen_qemu_st_i64(t2, addr, idx, memop);
+
+ tcg_gen_ext_i64(ret, (new_val ? t2 : t1), memop);
+ tcg_temp_free_i64(t1);
+ tcg_temp_free_i64(t2);
+}
+
+static void do_atomic_op_i64(TCGv_i64 ret, TCGv addr, TCGv_i64 val,
+ TCGArg idx, TCGMemOp memop, void * const table[])
+{
+ memop = tcg_canonicalize_memop(memop, 1, 0);
+
+ if ((memop & MO_SIZE) == MO_64) {
+#ifdef CONFIG_ATOMIC64
+ gen_atomic_op_i64 gen;
+
+ gen = table[memop & (MO_SIZE | MO_BSWAP)];
+ tcg_debug_assert(gen != NULL);
+
+#ifdef CONFIG_SOFTMMU
+ {
+ TCGv_i32 oi = tcg_const_i32(make_memop_idx(memop & ~MO_SIGN, idx));
+ gen(ret, tcg_ctx.tcg_env, addr, val, oi);
+ tcg_temp_free_i32(oi);
+ }
+#else
+ gen(ret, tcg_ctx.tcg_env, addr, val);
+#endif
+#else
+ gen_helper_exit_atomic(tcg_ctx.tcg_env);
+#endif /* CONFIG_ATOMIC64 */
+ } else {
+ TCGv_i32 v32 = tcg_temp_new_i32();
+ TCGv_i32 r32 = tcg_temp_new_i32();
+
+ tcg_gen_extrl_i64_i32(v32, val);
+ do_atomic_op_i32(r32, addr, v32, idx, memop & ~MO_SIGN, table);
+ tcg_temp_free_i32(v32);
+
+ tcg_gen_extu_i32_i64(ret, r32);
+ tcg_temp_free_i32(r32);
+
+ if (memop & MO_SIGN) {
+ tcg_gen_ext_i64(ret, ret, memop);
+ }
+ }
+}
+
+#define GEN_ATOMIC_HELPER(NAME, OP, NEW) \
+static void * const table_##NAME[16] = { \
+ [MO_8] = gen_helper_atomic_##NAME##b, \
+ [MO_16 | MO_LE] = gen_helper_atomic_##NAME##w_le, \
+ [MO_16 | MO_BE] = gen_helper_atomic_##NAME##w_be, \
+ [MO_32 | MO_LE] = gen_helper_atomic_##NAME##l_le, \
+ [MO_32 | MO_BE] = gen_helper_atomic_##NAME##l_be, \
+ WITH_ATOMIC64([MO_64 | MO_LE] = gen_helper_atomic_##NAME##q_le) \
+ WITH_ATOMIC64([MO_64 | MO_BE] = gen_helper_atomic_##NAME##q_be) \
+}; \
+void tcg_gen_atomic_##NAME##_i32 \
+ (TCGv_i32 ret, TCGv addr, TCGv_i32 val, TCGArg idx, TCGMemOp memop) \
+{ \
+ if (parallel_cpus) { \
+ do_atomic_op_i32(ret, addr, val, idx, memop, table_##NAME); \
+ } else { \
+ do_nonatomic_op_i32(ret, addr, val, idx, memop, NEW, \
+ tcg_gen_##OP##_i32); \
+ } \
+} \
+void tcg_gen_atomic_##NAME##_i64 \
+ (TCGv_i64 ret, TCGv addr, TCGv_i64 val, TCGArg idx, TCGMemOp memop) \
+{ \
+ if (parallel_cpus) { \
+ do_atomic_op_i64(ret, addr, val, idx, memop, table_##NAME); \
+ } else { \
+ do_nonatomic_op_i64(ret, addr, val, idx, memop, NEW, \
+ tcg_gen_##OP##_i64); \
+ } \
+}
+
+GEN_ATOMIC_HELPER(fetch_add, add, 0)
+GEN_ATOMIC_HELPER(fetch_and, and, 0)
+GEN_ATOMIC_HELPER(fetch_or, or, 0)
+GEN_ATOMIC_HELPER(fetch_xor, xor, 0)
+
+GEN_ATOMIC_HELPER(add_fetch, add, 1)
+GEN_ATOMIC_HELPER(and_fetch, and, 1)
+GEN_ATOMIC_HELPER(or_fetch, or, 1)
+GEN_ATOMIC_HELPER(xor_fetch, xor, 1)
+
+static void tcg_gen_mov2_i32(TCGv_i32 r, TCGv_i32 a, TCGv_i32 b)
+{
+ tcg_gen_mov_i32(r, b);
+}
+
+static void tcg_gen_mov2_i64(TCGv_i64 r, TCGv_i64 a, TCGv_i64 b)
+{
+ tcg_gen_mov_i64(r, b);
+}
+
+GEN_ATOMIC_HELPER(xchg, mov2, 0)
+
+#undef GEN_ATOMIC_HELPER
projects / qemu.git / blobdiff