@@ -204,6 +204,7 @@ void arm_test_cc(DisasCompare *cmp, int cc);
void arm_free_cc(DisasCompare *cmp);
void arm_jump_cc(DisasCompare *cmp, TCGLabel *label);
void arm_gen_test_cc(int cc, TCGLabel *label);
+MemOp pow2_align(unsigned i);
/* Return state of Alternate Half-precision flag, caller frees result */
static inline TCGv_i32 get_ahp_flag(void)
@@ -875,6 +875,21 @@ static inline void store_reg_from_load(DisasContext *s, int reg, TCGv_i32 var)
#define IS_USER_ONLY 0
#endif
+MemOp pow2_align(unsigned i)
+{
+ static const MemOp mop_align[] = {
+ 0, MO_ALIGN_2, MO_ALIGN_4, MO_ALIGN_8, MO_ALIGN_16,
+ /*
+ * FIXME: TARGET_PAGE_BITS_MIN affects TLB_FLAGS_MASK such
+ * that 256-bit alignment (MO_ALIGN_32) cannot be supported:
+ * see get_alignment_bits(). Enforce only 128-bit alignment for now.
+ */
+ MO_ALIGN_16
+ };
+ g_assert(i < ARRAY_SIZE(mop_align));
+ return mop_align[i];
+}
+
/*
* Abstractions of "generate code to do a guest load/store for
* AArch32", where a vaddr is always 32 bits (and is zero
@@ -429,7 +429,7 @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a)
{
/* Neon load/store multiple structures */
int nregs, interleave, spacing, reg, n;
- MemOp endian = s->be_data;
+ MemOp mop, align, endian;
int mmu_idx = get_mem_index(s);
int size = a->size;
TCGv_i64 tmp64;
@@ -473,20 +473,36 @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a)
}
/* For our purposes, bytes are always little-endian. */
+ endian = s->be_data;
if (size == 0) {
endian = MO_LE;
}
+
+ /* Enforce alignment requested by the instruction */
+ if (a->align) {
+ align = pow2_align(a->align + 2); /* 4 ** a->align */
+ } else {
+ align = s->align_mem ? MO_ALIGN : 0;
+ }
+
/*
* Consecutive little-endian elements from a single register
* can be promoted to a larger little-endian operation.
*/
if (interleave == 1 && endian == MO_LE) {
+ /* Retain any natural alignment. */
+ if (align == MO_ALIGN) {
+ align = pow2_align(size);
+ }
size = 3;
}
+
tmp64 = tcg_temp_new_i64();
addr = tcg_temp_new_i32();
tmp = tcg_const_i32(1 << size);
load_reg_var(s, addr, a->rn);
+
+ mop = endian | size | align;
for (reg = 0; reg < nregs; reg++) {
for (n = 0; n < 8 >> size; n++) {
int xs;
@@ -494,15 +510,16 @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a)
int tt = a->vd + reg + spacing * xs;
if (a->l) {
- gen_aa32_ld_internal_i64(s, tmp64, addr, mmu_idx,
- endian | size);
+ gen_aa32_ld_internal_i64(s, tmp64, addr, mmu_idx, mop);
neon_store_element64(tt, n, size, tmp64);
} else {
neon_load_element64(tmp64, tt, n, size);
- gen_aa32_st_internal_i64(s, tmp64, addr, mmu_idx,
- endian | size);
+ gen_aa32_st_internal_i64(s, tmp64, addr, mmu_idx, mop);
}
tcg_gen_add_i32(addr, addr, tmp);
+
+ /* Subsequent memory operations inherit alignment */
+ mop &= ~MO_AMASK;
}
}
}
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate.h | 1 + target/arm/translate.c | 15 +++++++++++++++ target/arm/translate-neon.c.inc | 27 ++++++++++++++++++++++----- 3 files changed, 38 insertions(+), 5 deletions(-) -- 2.25.1