From: William Kosasih <kosasihwilli...@gmail.com> This patch adds alignment checks in the load operations in the VLD4 instruction.
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154 Signed-off-by: William Kosasih <kosasihwilli...@gmail.com> Reviewed-by: Richard Henderson <richard.hender...@linaro.org> Message-id: 20250703085604.154449-9-kosasihwilli...@gmail.com Signed-off-by: Peter Maydell <peter.mayd...@linaro.org> --- target/arm/tcg/mve_helper.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index 2d21625f244..7069910db4a 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -403,13 +403,15 @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint16_t mask = mve_eci_mask(env); \ static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 4; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ for (e = 0; e < 4; e++, data >>= 8) { \ uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ qd[H1(off[beat])] = data; \ @@ -427,13 +429,15 @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint32_t addr, data; \ int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 8 + (beat & 1) * 4; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y); \ qd[H2(off[beat])] = data; \ data >>= 16; \ @@ -452,13 +456,15 @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint32_t addr, data; \ uint32_t *qd; \ int y; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 4; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ y = (beat + (O1 & 2)) & 3; \ qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ qd[H4(off[beat] >> 2)] = data; \ -- 2.43.0