This patch adds alignment checks in the load operations in the VLDR_SG
instructions.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1154
Signed-off-by: William Kosasih <kosasihwilli...@gmail.com>
---
 target/arm/tcg/mve_helper.c | 41 ++++++++++++++++++++++---------------
 1 file changed, 24 insertions(+), 17 deletions(-)

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index a49b8842e3..f1e9c87e6a 100644
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -247,13 +247,18 @@ DO_VSTR(vstrh_w, 2, w, 4, int32_t)
         uint16_t eci_mask = mve_eci_mask(env);                          \
         unsigned e;                                                     \
         uint32_t addr;                                                  \
-        for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { 
\
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MFLAG(LDTYPE) | MO_ALIGN, mmu_idx);\
+        for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) {\
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
             }                                                           \
             addr = ADDRFN(base, m[H##ESIZE(e)]);                        \
             d[H##ESIZE(e)] = (mask & 1) ?                               \
-                cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0;         \
+                SIGN_EXT(cpu_ld##LDTYPE##_mmu(env, addr, oi, GETPC()),  \
+                         TYPE,                                          \
+                         MSIZE(LDTYPE) * 8)                             \
+                : 0;                                                    \
             if (WB) {                                                   \
                 m[H##ESIZE(e)] = addr;                                  \
             }                                                           \
@@ -305,13 +310,15 @@ DO_VSTR(vstrh_w, 2, w, 4, int32_t)
         uint16_t eci_mask = mve_eci_mask(env);                          \
         unsigned e;                                                     \
         uint32_t addr;                                                  \
+        int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env));            \
+        MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx);      \
         for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) {      \
             if (!(eci_mask & 1)) {                                      \
                 continue;                                               \
             }                                                           \
             addr = ADDRFN(base, m[H4(e & ~1)]);                         \
             addr += 4 * (e & 1);                                        \
-            d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \
+            d[H4(e)] = (mask & 1) ? cpu_ldl_mmu(env, addr, oi, GETPC()) : 0;\
             if (WB && (e & 1)) {                                        \
                 m[H4(e & ~1)] = addr - 4;                               \
             }                                                           \
@@ -350,22 +357,22 @@ DO_VSTR(vstrh_w, 2, w, 4, int32_t)
 #define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2))
 #define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3))
 
-DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_sh, b, 2, int16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_sw, b, 4, int32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_sw, w, 4, int32_t, uint32_t, ADDR_ADD, false)
 
-DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD, false)
-DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_ub, b, 1, uint8_t, uint8_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_uh, b, 2, uint16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_uw, b, 4, uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uh, w, 2, uint16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uw, w, 4, uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrw_sg_uw, l, 4, uint32_t, uint32_t, ADDR_ADD, false)
 DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false)
 
-DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false)
-DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false)
+DO_VLDR_SG(vldrh_sg_os_sw, w, 4, int32_t, uint32_t, ADDR_ADD_OSH, false)
+DO_VLDR_SG(vldrh_sg_os_uh, w, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false)
+DO_VLDR_SG(vldrh_sg_os_uw, w, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false)
+DO_VLDR_SG(vldrw_sg_os_uw, l, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false)
 DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false)
 
 DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD, false)
@@ -381,7 +388,7 @@ DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH, 
false)
 DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW, false)
 DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false)
 
-DO_VLDR_SG(vldrw_sg_wb_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true)
+DO_VLDR_SG(vldrw_sg_wb_uw, l, 4, uint32_t, uint32_t, ADDR_ADD, true)
 DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true)
 DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true)
 DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true)
-- 
2.48.1


Reply via email to