[Qemu-devel] [RFC v8 02/14] softmmu: Simplify helper_*_st_name, wrap unaligned code

[Alvise Rigo <a.rigo@virtualopensystems.com>]

Attempting to simplify the helper_*_st_name, wrap the
do_unaligned_access code into an shared inline function. As this also
removes the goto statement the inline code is expanded twice in each
helper.

>From Message-id 1452268394-31252-2-git-send-email-alex.bennee@linaro.org:
There is a minor wrinkle that we need to use a unique name for each
inline fragment as the template is included multiple times. For this the
smmu_helper macro does the appropriate glue magic.

I've tested the result with no change to functionality. Comparing the
the objdump of cputlb.o shows minimal changes in probe_write and
everything else is identical.

Suggested-by: Jani Kokkonen <jani.kokkonen@huawei.com>
Suggested-by: Claudio Fontana <claudio.fontana@huawei.com>
CC: Alvise Rigo <a.rigo@virtualopensystems.com>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
[Alex Bennée: define smmu_helper and unified logic between be/le]

Signed-off-by: Alvise Rigo <a.rigo@virtualopensystems.com>
---
 softmmu_template.h | 82 ++++++++++++++++++++++++++++++------------------------
 1 file changed, 46 insertions(+), 36 deletions(-)

diff --git a/softmmu_template.h b/softmmu_template.h
index 208f808..3eb54f8 100644
--- a/softmmu_template.h
+++ b/softmmu_template.h
@@ -370,6 +370,46 @@ static inline void glue(io_write, SUFFIX)(CPUArchState *env,
                                  iotlbentry->attrs);
 }
 
+/* Inline helper functions for SoftMMU
+ *
+ * These functions help reduce code duplication in the various main
+ * helper functions. Constant arguments (like endian state) will allow
+ * the compiler to skip code which is never called in a given inline.
+ */
+#define smmu_helper(name) glue(glue(glue(smmu_helper_, SUFFIX), \
+                                                    MMUSUFFIX), _##name)
+static inline void smmu_helper(do_unl_store)(CPUArchState *env,
+                                             bool little_endian,
+                                             DATA_TYPE val,
+                                             target_ulong addr,
+                                             TCGMemOpIdx oi,
+                                             unsigned mmu_idx,
+                                             uintptr_t retaddr)
+{
+    int i;
+
+    if ((get_memop(oi) & MO_AMASK) == MO_ALIGN) {
+        cpu_unaligned_access(ENV_GET_CPU(env), addr, MMU_DATA_STORE,
+                             mmu_idx, retaddr);
+    }
+    /* Note: relies on the fact that tlb_fill() does not remove the
+     * previous page from the TLB cache.  */
+    for (i = DATA_SIZE - 1; i >= 0; i--) {
+        uint8_t val8;
+        if (little_endian) {
+            /* Little-endian extract.  */
+            val8 = val >> (i * 8);
+        } else {
+            /* Big-endian extract.  */
+            val8 = val >> (((DATA_SIZE - 1) * 8) - (i * 8));
+        }
+        /* Note the adjustment at the beginning of the function.
+           Undo that for the recursion.  */
+        glue(helper_ret_stb, MMUSUFFIX)(env, addr + i, val8,
+                                        oi, retaddr + GETPC_ADJ);
+    }
+}
+
 void helper_le_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
                        TCGMemOpIdx oi, uintptr_t retaddr)
 {
@@ -399,7 +439,8 @@ void helper_le_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
     if (unlikely(tlb_addr & ~TARGET_PAGE_MASK)) {
         CPUIOTLBEntry *iotlbentry;
         if ((addr & (DATA_SIZE - 1)) != 0) {
-            goto do_unaligned_access;
+            smmu_helper(do_unl_store)(env, false, val, addr, oi, mmu_idx, retaddr);
+            return;
         }
         iotlbentry = &env->iotlb[mmu_idx][index];
 
@@ -414,23 +455,7 @@ void helper_le_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
     if (DATA_SIZE > 1
         && unlikely((addr & ~TARGET_PAGE_MASK) + DATA_SIZE - 1
                      >= TARGET_PAGE_SIZE)) {
-        int i;
-    do_unaligned_access:
-        if ((get_memop(oi) & MO_AMASK) == MO_ALIGN) {
-            cpu_unaligned_access(ENV_GET_CPU(env), addr, MMU_DATA_STORE,
-                                 mmu_idx, retaddr);
-        }
-        /* XXX: not efficient, but simple */
-        /* Note: relies on the fact that tlb_fill() does not remove the
-         * previous page from the TLB cache.  */
-        for (i = DATA_SIZE - 1; i >= 0; i--) {
-            /* Little-endian extract.  */
-            uint8_t val8 = val >> (i * 8);
-            /* Note the adjustment at the beginning of the function.
-               Undo that for the recursion.  */
-            glue(helper_ret_stb, MMUSUFFIX)(env, addr + i, val8,
-                                            oi, retaddr + GETPC_ADJ);
-        }
+        smmu_helper(do_unl_store)(env, true, val, addr, oi, mmu_idx, retaddr);
         return;
     }
 
@@ -479,7 +504,8 @@ void helper_be_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
     if (unlikely(tlb_addr & ~TARGET_PAGE_MASK)) {
         CPUIOTLBEntry *iotlbentry;
         if ((addr & (DATA_SIZE - 1)) != 0) {
-            goto do_unaligned_access;
+            smmu_helper(do_unl_store)(env, true, val, addr, oi, mmu_idx, retaddr);
+            return;
         }
         iotlbentry = &env->iotlb[mmu_idx][index];
 
@@ -494,23 +520,7 @@ void helper_be_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
     if (DATA_SIZE > 1
         && unlikely((addr & ~TARGET_PAGE_MASK) + DATA_SIZE - 1
                      >= TARGET_PAGE_SIZE)) {
-        int i;
-    do_unaligned_access:
-        if ((get_memop(oi) & MO_AMASK) == MO_ALIGN) {
-            cpu_unaligned_access(ENV_GET_CPU(env), addr, MMU_DATA_STORE,
-                                 mmu_idx, retaddr);
-        }
-        /* XXX: not efficient, but simple */
-        /* Note: relies on the fact that tlb_fill() does not remove the
-         * previous page from the TLB cache.  */
-        for (i = DATA_SIZE - 1; i >= 0; i--) {
-            /* Big-endian extract.  */
-            uint8_t val8 = val >> (((DATA_SIZE - 1) * 8) - (i * 8));
-            /* Note the adjustment at the beginning of the function.
-               Undo that for the recursion.  */
-            glue(helper_ret_stb, MMUSUFFIX)(env, addr + i, val8,
-                                            oi, retaddr + GETPC_ADJ);
-        }
+        smmu_helper(do_unl_store)(env, false, val, addr, oi, mmu_idx, retaddr);
         return;
     }
 
-- 
2.8.0