target/arm: Bring VLSTM/VLLDM helper store/load closer to the ARM pseudocode

This patch brings the VLSTM and VLLDM helper functions closer to the ARM
pseudocode by adding MO_ALIGN to the MemOpIdx of the associated store
(`cpu_stl_mmu`) operations and load (`cpu_ldl_mmu`) operations.

Note that this is not a bug fix: an 8-byte alignment check already exists
and remains in place, enforcing stricter alignment than the 4 bytes
requirement in the individual loads and stores. This change merely makes the
helper implementations closer to the ARM pseudocode.

That said, as a side effect, the MMU index is now resolved once instead of
on every `cpu_*_data_ra` call, reducing redundant lookups

Signed-off-by: William Kosasih <kosasihwilliam4@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250703085604.154449-2-kosasihwilliam4@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c
index 6614719832e0b7f21fa5c4fa45aa50a2295c11cd..251e12edf9cb96d9712e1fc6cd1a4aa520e3ec18 100644 (file)
--- a/target/arm/tcg/m_helper.c
+++ b/target/arm/tcg/m_helper.c
@@ -1048,6 +1048,9 @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr)
     bool s = env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_S_MASK;
     bool lspact = env->v7m.fpccr[s] & R_V7M_FPCCR_LSPACT_MASK;
     uintptr_t ra = GETPC();
+    ARMMMUIdx mmu_idx = arm_mmu_idx(env);
+    MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN,
+                                 arm_to_core_mmu_idx(mmu_idx));
 
     assert(env->v7m.secure);
 
@@ -1073,7 +1076,7 @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr)
      * Note that we do not use v7m_stack_write() here, because the
      * accesses should not set the FSR bits for stacking errors if they
      * fail. (In pseudocode terms, they are AccType_NORMAL, not AccType_STACK
-     * or AccType_LAZYFP). Faults in cpu_stl_data_ra() will throw exceptions
+     * or AccType_LAZYFP). Faults in cpu_stl_mmu() will throw exceptions
      * and longjmp out.
      */
     if (!(env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_LSPEN_MASK)) {
@@ -1089,12 +1092,12 @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr)
             if (i >= 16) {
                 faddr += 8; /* skip the slot for the FPSCR */
             }
-            cpu_stl_data_ra(env, faddr, slo, ra);
-            cpu_stl_data_ra(env, faddr + 4, shi, ra);
+            cpu_stl_mmu(env, faddr, slo, oi, ra);
+            cpu_stl_mmu(env, faddr + 4, shi, oi, ra);
         }
-        cpu_stl_data_ra(env, fptr + 0x40, vfp_get_fpscr(env), ra);
+        cpu_stl_mmu(env, fptr + 0x40, vfp_get_fpscr(env), oi, ra);
         if (cpu_isar_feature(aa32_mve, cpu)) {
-            cpu_stl_data_ra(env, fptr + 0x44, env->v7m.vpr, ra);
+            cpu_stl_mmu(env, fptr + 0x44, env->v7m.vpr, oi, ra);
         }
 
         /*
@@ -1121,6 +1124,9 @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr)
 {
     ARMCPU *cpu = env_archcpu(env);
     uintptr_t ra = GETPC();
+    ARMMMUIdx mmu_idx = arm_mmu_idx(env);
+    MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN,
+                                 arm_to_core_mmu_idx(mmu_idx));
 
     /* fptr is the value of Rn, the frame pointer we load the FP regs from */
     assert(env->v7m.secure);
@@ -1155,16 +1161,16 @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr)
                 faddr += 8; /* skip the slot for the FPSCR and VPR */
             }
 
-            slo = cpu_ldl_data_ra(env, faddr, ra);
-            shi = cpu_ldl_data_ra(env, faddr + 4, ra);
+            slo = cpu_ldl_mmu(env, faddr, oi, ra);
+            shi = cpu_ldl_mmu(env, faddr + 4, oi, ra);
 
             dn = (uint64_t) shi << 32 | slo;
             *aa32_vfp_dreg(env, i / 2) = dn;
         }
-        fpscr = cpu_ldl_data_ra(env, fptr + 0x40, ra);
+        fpscr = cpu_ldl_mmu(env, fptr + 0x40, oi, ra);
         vfp_set_fpscr(env, fpscr);
         if (cpu_isar_feature(aa32_mve, cpu)) {
-            env->v7m.vpr = cpu_ldl_data_ra(env, fptr + 0x44, ra);
+            env->v7m.vpr = cpu_ldl_mmu(env, fptr + 0x44, oi, ra);
         }
     }