@@ -957,25 +957,33 @@ static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr,
static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size)
{
/* This writes the bottom N bits of a 128 bit wide vector to memory */
- TCGv_i64 tmp = tcg_temp_new_i64();
- tcg_gen_ld_i64(tmp, cpu_env, fp_reg_offset(s, srcidx, MO_64));
+ TCGv_i64 tmplo = tcg_temp_new_i64();
+ MemOp mop;
+
+ tcg_gen_ld_i64(tmplo, cpu_env, fp_reg_offset(s, srcidx, MO_64));
+
if (size < 4) {
- tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s),
- s->be_data + size);
+ mop = finalize_memop(s, size);
+ tcg_gen_qemu_st_i64(tmplo, tcg_addr, get_mem_index(s), mop);
} else {
bool be = s->be_data == MO_BE;
TCGv_i64 tcg_hiaddr = tcg_temp_new_i64();
+ TCGv_i64 tmphi = tcg_temp_new_i64();
+ tcg_gen_ld_i64(tmphi, cpu_env, fp_reg_hi_offset(s, srcidx));
+
+ mop = s->be_data | MO_Q;
+ tcg_gen_qemu_st_i64(be ? tmphi : tmplo, tcg_addr, get_mem_index(s),
+ mop | (s->align_mem ? MO_ALIGN_16 : 0));
tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
- tcg_gen_qemu_st_i64(tmp, be ? tcg_hiaddr : tcg_addr, get_mem_index(s),
- s->be_data | MO_Q);
- tcg_gen_ld_i64(tmp, cpu_env, fp_reg_hi_offset(s, srcidx));
- tcg_gen_qemu_st_i64(tmp, be ? tcg_addr : tcg_hiaddr, get_mem_index(s),
- s->be_data | MO_Q);
+ tcg_gen_qemu_st_i64(be ? tmplo : tmphi, tcg_hiaddr,
+ get_mem_index(s), mop);
+
tcg_temp_free_i64(tcg_hiaddr);
+ tcg_temp_free_i64(tmphi);
}
- tcg_temp_free_i64(tmp);
+ tcg_temp_free_i64(tmplo);
}
/*
@@ -986,10 +994,11 @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
/* This always zero-extends and writes to a full 128 bit wide vector */
TCGv_i64 tmplo = tcg_temp_new_i64();
TCGv_i64 tmphi = NULL;
+ MemOp mop;
if (size < 4) {
- MemOp memop = s->be_data + size;
- tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), memop);
+ mop = finalize_memop(s, size);
+ tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), mop);
} else {
bool be = s->be_data == MO_BE;
TCGv_i64 tcg_hiaddr;
@@ -997,11 +1006,12 @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
tmphi = tcg_temp_new_i64();
tcg_hiaddr = tcg_temp_new_i64();
+ mop = s->be_data | MO_Q;
+ tcg_gen_qemu_ld_i64(be ? tmphi : tmplo, tcg_addr, get_mem_index(s),
+ mop | (s->align_mem ? MO_ALIGN_16 : 0));
tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
- tcg_gen_qemu_ld_i64(tmplo, be ? tcg_hiaddr : tcg_addr, get_mem_index(s),
- s->be_data | MO_Q);
- tcg_gen_qemu_ld_i64(tmphi, be ? tcg_addr : tcg_hiaddr, get_mem_index(s),
- s->be_data | MO_Q);
+ tcg_gen_qemu_ld_i64(be ? tmplo : tmphi, tcg_hiaddr,
+ get_mem_index(s), mop);
tcg_temp_free_i64(tcg_hiaddr);
}
For 128-bit load/store, use 16-byte alignment. This requires that we perform the two operations in the correct order so that we generate the alignment fault before modifying memory. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-a64.c | 42 +++++++++++++++++++++++--------------- 1 file changed, 26 insertions(+), 16 deletions(-) -- 2.25.1