cputlb: Make store_helper less fragile to compiler optimizations

This has no functional change.

The current function structure is:

    inline QEMU_ALWAYSINLINE
    store_memop() {
        switch () {
            ...
        default:
            qemu_build_not_reached();
        }
    }
    inline QEMU_ALWAYSINLINE
    store_helper() {
        ...
        if (span_two_pages_or_io) {
            ...
            helper_ret_stb_mmu();
        }
        store_memop();
    }
    helper_ret_stb_mmu() {
        store_helper();
    }

Whereas GCC will generate an error at compile-time when an always_inline
function is not inlined, Clang does not.  Nor does Clang prioritize the
inlining of always_inline functions.  Both of these are arguably bugs.

Both `store_memop` and `store_helper` need to be inlined and allow
constant propogations to eliminate the `qemu_build_not_reached` call.

However, if the compiler instead chooses to inline helper_ret_stb_mmu
into store_helper, then store_helper is now self-recursive and the
compiler is no longer able to propagate the constant in the same way.

This does not produce at current QEMU head, but was reproducible
at v4.2.0 with `clang-10 -O2 -fexperimental-new-pass-manager`.

The inline recursion problem can be fixed solely by marking
helper_ret_stb_mmu as noinline, so the compiler does not make an
incorrect decision about which functions to inline.

In addition, extract store_helper_unaligned as a noinline subroutine
that can be shared by all of the helpers.  This saves about 6k code
size in an optimized x86_64 build.

Reported-by: Shu-Chun Weng <scw@google.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

accel/tcg/cputlb.c

@@ -2009,6 +2009,80 @@ store_memop(void *haddr, uint64_t val, MemOp op)
     }
 }
 
+static void __attribute__((noinline))
+store_helper_unaligned(CPUArchState *env, target_ulong addr, uint64_t val,
+                       uintptr_t retaddr, size_t size, uintptr_t mmu_idx,
+                       bool big_endian)
+{
+    const size_t tlb_off = offsetof(CPUTLBEntry, addr_write);
+    uintptr_t index, index2;
+    CPUTLBEntry *entry, *entry2;
+    target_ulong page2, tlb_addr, tlb_addr2;
+    TCGMemOpIdx oi;
+    size_t size2;
+    int i;
+
+    /*
+     * Ensure the second page is in the TLB.  Note that the first page
+     * is already guaranteed to be filled, and that the second page
+     * cannot evict the first.
+     */
+    page2 = (addr + size) & TARGET_PAGE_MASK;
+    size2 = (addr + size) & ~TARGET_PAGE_MASK;
+    index2 = tlb_index(env, mmu_idx, page2);
+    entry2 = tlb_entry(env, mmu_idx, page2);
+
+    tlb_addr2 = tlb_addr_write(entry2);
+    if (!tlb_hit_page(tlb_addr2, page2)) {
+        if (!victim_tlb_hit(env, mmu_idx, index2, tlb_off, page2)) {
+            tlb_fill(env_cpu(env), page2, size2, MMU_DATA_STORE,
+                     mmu_idx, retaddr);
+            index2 = tlb_index(env, mmu_idx, page2);
+            entry2 = tlb_entry(env, mmu_idx, page2);
+        }
+        tlb_addr2 = tlb_addr_write(entry2);
+    }
+
+    index = tlb_index(env, mmu_idx, addr);
+    entry = tlb_entry(env, mmu_idx, addr);
+    tlb_addr = tlb_addr_write(entry);
+
+    /*
+     * Handle watchpoints.  Since this may trap, all checks
+     * must happen before any store.
+     */
+    if (unlikely(tlb_addr & TLB_WATCHPOINT)) {
+        cpu_check_watchpoint(env_cpu(env), addr, size - size2,
+                             env_tlb(env)->d[mmu_idx].iotlb[index].attrs,
+                             BP_MEM_WRITE, retaddr);
+    }
+    if (unlikely(tlb_addr2 & TLB_WATCHPOINT)) {
+        cpu_check_watchpoint(env_cpu(env), page2, size2,
+                             env_tlb(env)->d[mmu_idx].iotlb[index2].attrs,
+                             BP_MEM_WRITE, retaddr);
+    }
+
+    /*
+     * XXX: not efficient, but simple.
+     * This loop must go in the forward direction to avoid issues
+     * with self-modifying code in Windows 64-bit.
+     */
+    oi = make_memop_idx(MO_UB, mmu_idx);
+    if (big_endian) {
+        for (i = 0; i < size; ++i) {
+            /* Big-endian extract.  */
+            uint8_t val8 = val >> (((size - 1) * 8) - (i * 8));
+            helper_ret_stb_mmu(env, addr + i, val8, oi, retaddr);
+        }
+    } else {
+        for (i = 0; i < size; ++i) {
+            /* Little-endian extract.  */
+            uint8_t val8 = val >> (i * 8);
+            helper_ret_stb_mmu(env, addr + i, val8, oi, retaddr);
+        }
+    }
+}
+
 static inline void QEMU_ALWAYS_INLINE
 store_helper(CPUArchState *env, target_ulong addr, uint64_t val,
              TCGMemOpIdx oi, uintptr_t retaddr, MemOp op)
@@ -2097,64 +2171,9 @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val,
     if (size > 1
         && unlikely((addr & ~TARGET_PAGE_MASK) + size - 1
                      >= TARGET_PAGE_SIZE)) {
-        int i;
-        uintptr_t index2;
-        CPUTLBEntry *entry2;
-        target_ulong page2, tlb_addr2;
-        size_t size2;
-
     do_unaligned_access:
-        /*
+        store_helper_unaligned(env, addr, val, retaddr, size,
-         * Ensure the second page is in the TLB.  Note that the first page
+                               mmu_idx, memop_big_endian(op));
-         * is already guaranteed to be filled, and that the second page
-         * cannot evict the first.
-         */
-        page2 = (addr + size) & TARGET_PAGE_MASK;
-        size2 = (addr + size) & ~TARGET_PAGE_MASK;
-        index2 = tlb_index(env, mmu_idx, page2);
-        entry2 = tlb_entry(env, mmu_idx, page2);
-        tlb_addr2 = tlb_addr_write(entry2);
-        if (!tlb_hit_page(tlb_addr2, page2)) {
-            if (!victim_tlb_hit(env, mmu_idx, index2, tlb_off, page2)) {
-                tlb_fill(env_cpu(env), page2, size2, MMU_DATA_STORE,
-                         mmu_idx, retaddr);
-                index2 = tlb_index(env, mmu_idx, page2);
-                entry2 = tlb_entry(env, mmu_idx, page2);
-            }
-            tlb_addr2 = tlb_addr_write(entry2);
-        }
-
-        /*
-         * Handle watchpoints.  Since this may trap, all checks
-         * must happen before any store.
-         */
-        if (unlikely(tlb_addr & TLB_WATCHPOINT)) {
-            cpu_check_watchpoint(env_cpu(env), addr, size - size2,
-                                 env_tlb(env)->d[mmu_idx].iotlb[index].attrs,
-                                 BP_MEM_WRITE, retaddr);
-        }
-        if (unlikely(tlb_addr2 & TLB_WATCHPOINT)) {
-            cpu_check_watchpoint(env_cpu(env), page2, size2,
-                                 env_tlb(env)->d[mmu_idx].iotlb[index2].attrs,
-                                 BP_MEM_WRITE, retaddr);
-        }
-
-        /*
-         * XXX: not efficient, but simple.
-         * This loop must go in the forward direction to avoid issues
-         * with self-modifying code in Windows 64-bit.
-         */
-        for (i = 0; i < size; ++i) {
-            uint8_t val8;
-            if (memop_big_endian(op)) {
-                /* Big-endian extract.  */
-                val8 = val >> (((size - 1) * 8) - (i * 8));
-            } else {
-                /* Little-endian extract.  */
-                val8 = val >> (i * 8);
-            }
-            helper_ret_stb_mmu(env, addr + i, val8, oi, retaddr);
-        }
         return;
     }
 
@@ -2162,7 +2181,8 @@ store_helper(CPUArchState *env, target_ulong addr, uint64_t val,
     store_memop(haddr, val, op);
 }
 
-void helper_ret_stb_mmu(CPUArchState *env, target_ulong addr, uint8_t val,
+void __attribute__((noinline))
+helper_ret_stb_mmu(CPUArchState *env, target_ulong addr, uint8_t val,
                    TCGMemOpIdx oi, uintptr_t retaddr)
 {
     store_helper(env, addr, val, oi, retaddr, MO_UB);