Similar to the ARM64, LoongArch has PC-relative instructions such as
PCADDU18I. These instructions can be used to support direct jump for
LoongArch. Additionally, if instruction "B offset" can cover the target
address(target is within ±128MB range), a single "B offset" plus a nop
will be used by "tb_target_set_jump_target".
Signed-off-by: Qi Hu <h...@loongson.cn>
---
tcg/loongarch64/tcg-target.c.inc | 56 +++++++++++++++++++++++++++++---
tcg/loongarch64/tcg-target.h | 5 ++-
2 files changed, 53 insertions(+), 8 deletions(-)
diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index f5a214a17f..2a068a52cc 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1031,6 +1031,35 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg
*args)
#endif
}
+/* LoongArch use `andi zero, zero, 0` as NOP. */
+#define NOP OPC_ANDI
+static void tcg_out_nop(TCGContext *s)
+{
+ tcg_out32(s, NOP);
+}
+
+void tb_target_set_jmp_target(uintptr_t tc_ptr, uintptr_t jmp_rx,
+ uintptr_t jmp_rw, uintptr_t addr)
+{
+ tcg_insn_unit i1, i2;
+ ptrdiff_t upper, lower;
+ ptrdiff_t offset = (addr - jmp_rx) >> 2;
+
+ if (offset == sextreg(offset, 0, 28)) {
+ i1 = encode_sd10k16_insn(OPC_B, offset);
+ i2 = NOP;
+ } else {
+ lower = (int16_t)offset;
+ upper = (offset - lower) >> 16;
+
+ i1 = encode_dsj20_insn(OPC_PCADDU18I, TCG_REG_T0, upper);
+ i2 = encode_djsk16_insn(OPC_JIRL, TCG_REG_ZERO, TCG_REG_T0, lower);
+ }
+ uint64_t pair = ((uint64_t)i2 << 32) | i1;
+ qatomic_set((uint64_t *)jmp_rw, pair);
+ flush_idcache_range(jmp_rx, jmp_rw, 8);
+}
+
/*
* Entry-points
*/
@@ -1058,11 +1087,28 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
break;
case INDEX_op_goto_tb:
- assert(s->tb_jmp_insn_offset == 0);
- /* indirect jump method */
- tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP0, TCG_REG_ZERO,
- (uintptr_t)(s->tb_jmp_target_addr + a0));
- tcg_out_opc_jirl(s, TCG_REG_ZERO, TCG_REG_TMP0, 0);
+ if (s->tb_jmp_insn_offset != NULL) {
+ /* TCG_TARGET_HAS_direct_jump */
+ /*
+ * Ensure that "patch area" are 8-byte aligned so that an
+ * atomic write can be used to patch the target address.
+ */
+ if ((uintptr_t)s->code_ptr & 7) {
+ tcg_out_nop(s);
+ }
+ s->tb_jmp_insn_offset[a0] = tcg_current_code_size(s);
+ /*
+ * actual branch destination will be patched by
+ * tb_target_set_jmp_target later
+ */
+ tcg_out_opc_pcaddu18i(s, TCG_REG_TMP0, 0);
+ tcg_out_opc_jirl(s, TCG_REG_ZERO, TCG_REG_TMP0, 0);
+ } else {
+ /* !TCG_TARGET_HAS_direct_jump */
+ tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP0, TCG_REG_ZERO,
+ (uintptr_t)(s->tb_jmp_target_addr + a0));
+ tcg_out_opc_jirl(s, TCG_REG_ZERO, TCG_REG_TMP0, 0);
+ }
set_jmp_reset_offset(s, a0);
break;
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 67380b2432..ee207ec32c 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -42,7 +42,7 @@
#define TCG_TARGET_INSN_UNIT_SIZE 4
#define TCG_TARGET_NB_REGS 32
-#define MAX_CODE_GEN_BUFFER_SIZE SIZE_MAX
+#define MAX_CODE_GEN_BUFFER_SIZE (128 * GiB)
typedef enum {
TCG_REG_ZERO,
@@ -123,7 +123,7 @@ typedef enum {
#define TCG_TARGET_HAS_clz_i32 1
#define TCG_TARGET_HAS_ctz_i32 1
#define TCG_TARGET_HAS_ctpop_i32 0
-#define TCG_TARGET_HAS_direct_jump 0
+#define TCG_TARGET_HAS_direct_jump 1
#define TCG_TARGET_HAS_brcond2 0
#define TCG_TARGET_HAS_setcond2 0
#define TCG_TARGET_HAS_qemu_st8_i32 0
@@ -166,7 +166,6 @@ typedef enum {
#define TCG_TARGET_HAS_muluh_i64 1
#define TCG_TARGET_HAS_mulsh_i64 1
-/* not defined -- call should be eliminated at compile time */
void tb_target_set_jmp_target(uintptr_t, uintptr_t, uintptr_t, uintptr_t);
#define TCG_TARGET_DEFAULT_MO (0)
--
2.37.3
