@@ -165,4 +165,7 @@ void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
uint32_t rm_ofs, int64_t shift,
uint32_t opr_sz, uint32_t max_sz);
+void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm);
+void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm);
+
#endif /* TARGET_ARM_TRANSLATE_A64_H */
@@ -4294,7 +4294,8 @@ TRANS_FEAT(UCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz,
* The load should begin at the address Rn + IMM.
*/
-static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm)
+void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
+ int len, int rn, int imm)
{
int len_align = QEMU_ALIGN_DOWN(len, 8);
int len_remain = len % 8;
@@ -4320,7 +4321,7 @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm)
t0 = tcg_temp_new_i64();
for (i = 0; i < len_align; i += 8) {
tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ);
- tcg_gen_st_i64(t0, cpu_env, vofs + i);
+ tcg_gen_st_i64(t0, base, vofs + i);
tcg_gen_addi_i64(clean_addr, clean_addr, 8);
}
tcg_temp_free_i64(t0);
@@ -4333,6 +4334,12 @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm)
clean_addr = new_tmp_a64_local(s);
tcg_gen_mov_i64(clean_addr, t0);
+ if (base != cpu_env) {
+ TCGv_ptr b = tcg_temp_local_new_ptr();
+ tcg_gen_mov_ptr(b, base);
+ base = b;
+ }
+
gen_set_label(loop);
t0 = tcg_temp_new_i64();
@@ -4340,7 +4347,7 @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm)
tcg_gen_addi_i64(clean_addr, clean_addr, 8);
tp = tcg_temp_new_ptr();
- tcg_gen_add_ptr(tp, cpu_env, i);
+ tcg_gen_add_ptr(tp, base, i);
tcg_gen_addi_ptr(i, i, 8);
tcg_gen_st_i64(t0, tp, vofs);
tcg_temp_free_ptr(tp);
@@ -4348,6 +4355,11 @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm)
tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop);
tcg_temp_free_ptr(i);
+
+ if (base != cpu_env) {
+ tcg_temp_free_ptr(base);
+ assert(len_remain == 0);
+ }
}
/*
@@ -4376,13 +4388,14 @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm)
default:
g_assert_not_reached();
}
- tcg_gen_st_i64(t0, cpu_env, vofs + len_align);
+ tcg_gen_st_i64(t0, base, vofs + len_align);
tcg_temp_free_i64(t0);
}
}
/* Similarly for stores. */
-static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm)
+void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
+ int len, int rn, int imm)
{
int len_align = QEMU_ALIGN_DOWN(len, 8);
int len_remain = len % 8;
@@ -4408,7 +4421,7 @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm)
t0 = tcg_temp_new_i64();
for (i = 0; i < len_align; i += 8) {
- tcg_gen_ld_i64(t0, cpu_env, vofs + i);
+ tcg_gen_ld_i64(t0, base, vofs + i);
tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ);
tcg_gen_addi_i64(clean_addr, clean_addr, 8);
}
@@ -4422,11 +4435,17 @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm)
clean_addr = new_tmp_a64_local(s);
tcg_gen_mov_i64(clean_addr, t0);
+ if (base != cpu_env) {
+ TCGv_ptr b = tcg_temp_local_new_ptr();
+ tcg_gen_mov_ptr(b, base);
+ base = b;
+ }
+
gen_set_label(loop);
t0 = tcg_temp_new_i64();
tp = tcg_temp_new_ptr();
- tcg_gen_add_ptr(tp, cpu_env, i);
+ tcg_gen_add_ptr(tp, base, i);
tcg_gen_ld_i64(t0, tp, vofs);
tcg_gen_addi_ptr(i, i, 8);
tcg_temp_free_ptr(tp);
@@ -4437,12 +4456,17 @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm)
tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop);
tcg_temp_free_ptr(i);
+
+ if (base != cpu_env) {
+ tcg_temp_free_ptr(base);
+ assert(len_remain == 0);
+ }
}
/* Predicate register stores can be any multiple of 2. */
if (len_remain) {
t0 = tcg_temp_new_i64();
- tcg_gen_ld_i64(t0, cpu_env, vofs + len_align);
+ tcg_gen_ld_i64(t0, base, vofs + len_align);
switch (len_remain) {
case 2:
@@ -4474,7 +4498,7 @@ static bool trans_LDR_zri(DisasContext *s, arg_rri *a)
if (sve_access_check(s)) {
int size = vec_full_reg_size(s);
int off = vec_full_reg_offset(s, a->rd);
- do_ldr(s, off, size, a->rn, a->imm * size);
+ gen_sve_ldr(s, cpu_env, off, size, a->rn, a->imm * size);
}
return true;
}
@@ -4487,7 +4511,7 @@ static bool trans_LDR_pri(DisasContext *s, arg_rri *a)
if (sve_access_check(s)) {
int size = pred_full_reg_size(s);
int off = pred_full_reg_offset(s, a->rd);
- do_ldr(s, off, size, a->rn, a->imm * size);
+ gen_sve_ldr(s, cpu_env, off, size, a->rn, a->imm * size);
}
return true;
}
@@ -4500,7 +4524,7 @@ static bool trans_STR_zri(DisasContext *s, arg_rri *a)
if (sve_access_check(s)) {
int size = vec_full_reg_size(s);
int off = vec_full_reg_offset(s, a->rd);
- do_str(s, off, size, a->rn, a->imm * size);
+ gen_sve_str(s, cpu_env, off, size, a->rn, a->imm * size);
}
return true;
}
@@ -4513,7 +4537,7 @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a)
if (sve_access_check(s)) {
int size = pred_full_reg_size(s);
int off = pred_full_reg_offset(s, a->rd);
- do_str(s, off, size, a->rn, a->imm * size);
+ gen_sve_str(s, cpu_env, off, size, a->rn, a->imm * size);
}
return true;
}
Add a TCGv_ptr base argument, which will be cpu_env for SVE. We will reuse this for SME save and restore array insns. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-a64.h | 3 +++ target/arm/translate-sve.c | 48 ++++++++++++++++++++++++++++---------- 2 files changed, 39 insertions(+), 12 deletions(-)