target/arm: Fix VLDR_SG helper load alignment checks

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 <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-7-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index 9587f2da7daac566da9cf4ef6b1358b308116008..633f511a7e665a3d4caf10118bea078447781b56 100644 (file)
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -218,7 +218,7 @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t)
  * For loads, predicated lanes are zeroed instead of retaining
  * their previous values.
  */
-#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB)        \
+#define DO_VLDR_SG(OP, MFLAG, MTYPE, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB)\
     void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm,         \
                           uint32_t base)                                \
     {                                                                   \
@@ -228,13 +228,15 @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 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(MFLAG | 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;         \
+                (MTYPE)cpu_##LDTYPE##_mmu(env, addr, oi, GETPC()) : 0;  \
             if (WB) {                                                   \
                 m[H##ESIZE(e)] = addr;                                  \
             }                                                           \
@@ -286,13 +288,15 @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 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;                               \
             }                                                           \
@@ -331,22 +335,26 @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 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, MO_SB, int8_t, ldb, 2, int16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_sw, MO_SB, int8_t, ldb, 4, int32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_sw, MO_TESW, int16_t, ldw, 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, MO_UB, uint8_t, ldb, 1, uint8_t, uint8_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_uh, MO_UB, uint8_t, ldb, 2, uint16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrb_sg_uw, MO_UB, uint8_t, ldb, 4, uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uh, MO_TEUW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrh_sg_uw, MO_TEUW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD, false)
+DO_VLDR_SG(vldrw_sg_uw, MO_TEUL, uint32_t, ldl, 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, MO_TESW, int16_t, ldw, 4,
+           int32_t, uint32_t, ADDR_ADD_OSH, false)
+DO_VLDR_SG(vldrh_sg_os_uh, MO_TEUW, uint16_t, ldw, 2,
+           uint16_t, uint16_t, ADDR_ADD_OSH, false)
+DO_VLDR_SG(vldrh_sg_os_uw, MO_TEUW, uint16_t, ldw, 4,
+           uint32_t, uint32_t, ADDR_ADD_OSH, false)
+DO_VLDR_SG(vldrw_sg_os_uw, MO_TEUL, uint32_t, ldl, 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)
@@ -362,7 +370,7 @@ 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, MO_TEUL, uint32_t, ldl, 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)