[PULL 21/43] target/arm: Adjust gen_aa32_{ld, st}_i32 for align+endianness

[Peter Maydell <peter.maydell@linaro.org>]

From: Richard Henderson <richard.henderson@linaro.org>

Create a finalize_memop function that computes alignment and
endianness and returns the final MemOp for the operation.

Split out gen_aa32_{ld,st}_internal_i32 which bypasses any special
handling of endianness or alignment.  Adjust gen_aa32_{ld,st}_i32
so that s->be_data is not added by the callers.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210419202257.161730-12-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/translate.h          |  24 ++++++++
 target/arm/translate.c          | 100 +++++++++++++++++---------------
 target/arm/translate-neon.c.inc |   9 +--
 3 files changed, 79 insertions(+), 54 deletions(-)

diff --git a/target/arm/translate.h b/target/arm/translate.h
index b185c14a035..0c60b83b3d4 100644
--- a/target/arm/translate.h
+++ b/target/arm/translate.h
@@ -459,4 +459,28 @@ static inline TCGv_ptr fpstatus_ptr(ARMFPStatusFlavour flavour)
     return statusptr;
 }
 
+/**
+ * finalize_memop:
+ * @s: DisasContext
+ * @opc: size+sign+align of the memory operation
+ *
+ * Build the complete MemOp for a memory operation, including alignment
+ * and endianness.
+ *
+ * If (op & MO_AMASK) then the operation already contains the required
+ * alignment, e.g. for AccType_ATOMIC.  Otherwise, this an optionally
+ * unaligned operation, e.g. for AccType_NORMAL.
+ *
+ * In the latter case, there are configuration bits that require alignment,
+ * and this is applied here.  Note that there is no way to indicate that
+ * no alignment should ever be enforced; this must be handled manually.
+ */
+static inline MemOp finalize_memop(DisasContext *s, MemOp opc)
+{
+    if (s->align_mem && !(opc & MO_AMASK)) {
+        opc |= MO_ALIGN;
+    }
+    return opc | s->be_data;
+}
+
 #endif /* TARGET_ARM_TRANSLATE_H */
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 970e537eae0..5bf68b782a1 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -908,7 +908,8 @@ static inline void store_reg_from_load(DisasContext *s, int reg, TCGv_i32 var)
 #define IS_USER_ONLY 0
 #endif
 
-/* Abstractions of "generate code to do a guest load/store for
+/*
+ * Abstractions of "generate code to do a guest load/store for
  * AArch32", where a vaddr is always 32 bits (and is zero
  * extended if we're a 64 bit core) and  data is also
  * 32 bits unless specifically doing a 64 bit access.
@@ -916,7 +917,7 @@ static inline void store_reg_from_load(DisasContext *s, int reg, TCGv_i32 var)
  * that the address argument is TCGv_i32 rather than TCGv.
  */
 
-static inline TCGv gen_aa32_addr(DisasContext *s, TCGv_i32 a32, MemOp op)
+static TCGv gen_aa32_addr(DisasContext *s, TCGv_i32 a32, MemOp op)
 {
     TCGv addr = tcg_temp_new();
     tcg_gen_extu_i32_tl(addr, a32);
@@ -928,47 +929,51 @@ static inline TCGv gen_aa32_addr(DisasContext *s, TCGv_i32 a32, MemOp op)
     return addr;
 }
 
+/*
+ * Internal routines are used for NEON cases where the endianness
+ * and/or alignment has already been taken into account and manipulated.
+ */
+static void gen_aa32_ld_internal_i32(DisasContext *s, TCGv_i32 val,
+                                     TCGv_i32 a32, int index, MemOp opc)
+{
+    TCGv addr = gen_aa32_addr(s, a32, opc);
+    tcg_gen_qemu_ld_i32(val, addr, index, opc);
+    tcg_temp_free(addr);
+}
+
+static void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val,
+                                     TCGv_i32 a32, int index, MemOp opc)
+{
+    TCGv addr = gen_aa32_addr(s, a32, opc);
+    tcg_gen_qemu_st_i32(val, addr, index, opc);
+    tcg_temp_free(addr);
+}
+
 static void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32,
                             int index, MemOp opc)
 {
-    TCGv addr;
-
-    if (s->align_mem) {
-        opc |= MO_ALIGN;
-    }
-
-    addr = gen_aa32_addr(s, a32, opc);
-    tcg_gen_qemu_ld_i32(val, addr, index, opc);
-    tcg_temp_free(addr);
+    gen_aa32_ld_internal_i32(s, val, a32, index, finalize_memop(s, opc));
 }
 
 static void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32,
                             int index, MemOp opc)
 {
-    TCGv addr;
+    gen_aa32_st_internal_i32(s, val, a32, index, finalize_memop(s, opc));
+}
 
-    if (s->align_mem) {
-        opc |= MO_ALIGN;
+#define DO_GEN_LD(SUFF, OPC)                                            \
+    static inline void gen_aa32_ld##SUFF(DisasContext *s, TCGv_i32 val, \
+                                         TCGv_i32 a32, int index)       \
+    {                                                                   \
+        gen_aa32_ld_i32(s, val, a32, index, OPC);                       \
     }
 
-    addr = gen_aa32_addr(s, a32, opc);
-    tcg_gen_qemu_st_i32(val, addr, index, opc);
-    tcg_temp_free(addr);
-}
-
-#define DO_GEN_LD(SUFF, OPC)                                             \
-static inline void gen_aa32_ld##SUFF(DisasContext *s, TCGv_i32 val,      \
-                                     TCGv_i32 a32, int index)            \
-{                                                                        \
-    gen_aa32_ld_i32(s, val, a32, index, OPC | s->be_data);               \
-}
-
-#define DO_GEN_ST(SUFF, OPC)                                             \
-static inline void gen_aa32_st##SUFF(DisasContext *s, TCGv_i32 val,      \
-                                     TCGv_i32 a32, int index)            \
-{                                                                        \
-    gen_aa32_st_i32(s, val, a32, index, OPC | s->be_data);               \
-}
+#define DO_GEN_ST(SUFF, OPC)                                            \
+    static inline void gen_aa32_st##SUFF(DisasContext *s, TCGv_i32 val, \
+                                         TCGv_i32 a32, int index)       \
+    {                                                                   \
+        gen_aa32_st_i32(s, val, a32, index, OPC);                       \
+    }
 
 static inline void gen_aa32_frob64(DisasContext *s, TCGv_i64 val)
 {
@@ -6456,7 +6461,7 @@ static bool op_load_rr(DisasContext *s, arg_ldst_rr *a,
     addr = op_addr_rr_pre(s, a);
 
     tmp = tcg_temp_new_i32();
-    gen_aa32_ld_i32(s, tmp, addr, mem_idx, mop | s->be_data);
+    gen_aa32_ld_i32(s, tmp, addr, mem_idx, mop);
     disas_set_da_iss(s, mop, issinfo);
 
     /*
@@ -6485,7 +6490,7 @@ static bool op_store_rr(DisasContext *s, arg_ldst_rr *a,
     addr = op_addr_rr_pre(s, a);
 
     tmp = load_reg(s, a->rt);
-    gen_aa32_st_i32(s, tmp, addr, mem_idx, mop | s->be_data);
+    gen_aa32_st_i32(s, tmp, addr, mem_idx, mop);
     disas_set_da_iss(s, mop, issinfo);
     tcg_temp_free_i32(tmp);
 
@@ -6508,13 +6513,13 @@ static bool trans_LDRD_rr(DisasContext *s, arg_ldst_rr *a)
     addr = op_addr_rr_pre(s, a);
 
     tmp = tcg_temp_new_i32();
-    gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data);
+    gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL);
     store_reg(s, a->rt, tmp);
 
     tcg_gen_addi_i32(addr, addr, 4);
 
     tmp = tcg_temp_new_i32();
-    gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data);
+    gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL);
     store_reg(s, a->rt + 1, tmp);
 
     /* LDRD w/ base writeback is undefined if the registers overlap.  */
@@ -6537,13 +6542,13 @@ static bool trans_STRD_rr(DisasContext *s, arg_ldst_rr *a)
     addr = op_addr_rr_pre(s, a);
 
     tmp = load_reg(s, a->rt);
-    gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data);
+    gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL);
     tcg_temp_free_i32(tmp);
 
     tcg_gen_addi_i32(addr, addr, 4);
 
     tmp = load_reg(s, a->rt + 1);
-    gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data);
+    gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL);
     tcg_temp_free_i32(tmp);
 
     op_addr_rr_post(s, a, addr, -4);
@@ -6608,7 +6613,7 @@ static bool op_load_ri(DisasContext *s, arg_ldst_ri *a,
     addr = op_addr_ri_pre(s, a);
 
     tmp = tcg_temp_new_i32();
-    gen_aa32_ld_i32(s, tmp, addr, mem_idx, mop | s->be_data);
+    gen_aa32_ld_i32(s, tmp, addr, mem_idx, mop);
     disas_set_da_iss(s, mop, issinfo);
 
     /*
@@ -6637,7 +6642,7 @@ static bool op_store_ri(DisasContext *s, arg_ldst_ri *a,
     addr = op_addr_ri_pre(s, a);
 
     tmp = load_reg(s, a->rt);
-    gen_aa32_st_i32(s, tmp, addr, mem_idx, mop | s->be_data);
+    gen_aa32_st_i32(s, tmp, addr, mem_idx, mop);
     disas_set_da_iss(s, mop, issinfo);
     tcg_temp_free_i32(tmp);
 
@@ -6653,13 +6658,13 @@ static bool op_ldrd_ri(DisasContext *s, arg_ldst_ri *a, int rt2)
     addr = op_addr_ri_pre(s, a);
 
     tmp = tcg_temp_new_i32();
-    gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data);
+    gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL);
     store_reg(s, a->rt, tmp);
 
     tcg_gen_addi_i32(addr, addr, 4);
 
     tmp = tcg_temp_new_i32();
-    gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data);
+    gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL);
     store_reg(s, rt2, tmp);
 
     /* LDRD w/ base writeback is undefined if the registers overlap.  */
@@ -6692,13 +6697,13 @@ static bool op_strd_ri(DisasContext *s, arg_ldst_ri *a, int rt2)
     addr = op_addr_ri_pre(s, a);
 
     tmp = load_reg(s, a->rt);
-    gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data);
+    gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL);
     tcg_temp_free_i32(tmp);
 
     tcg_gen_addi_i32(addr, addr, 4);
 
     tmp = load_reg(s, rt2);
-    gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data);
+    gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL);
     tcg_temp_free_i32(tmp);
 
     op_addr_ri_post(s, a, addr, -4);
@@ -6924,7 +6929,7 @@ static bool op_stl(DisasContext *s, arg_STL *a, MemOp mop)
     addr = load_reg(s, a->rn);
     tmp = load_reg(s, a->rt);
     tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL);
-    gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), mop | s->be_data);
+    gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), mop);
     disas_set_da_iss(s, mop, a->rt | ISSIsAcqRel | ISSIsWrite);
 
     tcg_temp_free_i32(tmp);
@@ -7080,7 +7085,7 @@ static bool op_lda(DisasContext *s, arg_LDA *a, MemOp mop)
 
     addr = load_reg(s, a->rn);
     tmp = tcg_temp_new_i32();
-    gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), mop | s->be_data);
+    gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), mop);
     disas_set_da_iss(s, mop, a->rt | ISSIsAcqRel);
     tcg_temp_free_i32(addr);
 
@@ -8264,8 +8269,7 @@ static bool op_tbranch(DisasContext *s, arg_tbranch *a, bool half)
     addr = load_reg(s, a->rn);
     tcg_gen_add_i32(addr, addr, tmp);
 
-    gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s),
-                    half ? MO_UW | s->be_data : MO_UB);
+    gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), half ? MO_UW : MO_UB);
     tcg_temp_free_i32(addr);
 
     tcg_gen_add_i32(tmp, tmp, tmp);
diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
index 0e5828744bb..c82aa1412e2 100644
--- a/target/arm/translate-neon.c.inc
+++ b/target/arm/translate-neon.c.inc
@@ -559,8 +559,7 @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a)
     addr = tcg_temp_new_i32();
     load_reg_var(s, addr, a->rn);
     for (reg = 0; reg < nregs; reg++) {
-        gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s),
-                        s->be_data | size);
+        gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), size);
         if ((vd & 1) && vec_size == 16) {
             /*
              * We cannot write 16 bytes at once because the
@@ -650,13 +649,11 @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a)
      */
     for (reg = 0; reg < nregs; reg++) {
         if (a->l) {
-            gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s),
-                            s->be_data | a->size);
+            gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), a->size);
             neon_store_element(vd, a->reg_idx, a->size, tmp);
         } else { /* Store */
             neon_load_element(tmp, vd, a->reg_idx, a->size);
-            gen_aa32_st_i32(s, tmp, addr, get_mem_index(s),
-                            s->be_data | a->size);
+            gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), a->size);
         }
         vd += a->stride;
         tcg_gen_addi_i32(addr, addr, 1 << a->size);
-- 
2.20.1