target/ppc: Improve helper_dcbz for user-only

Mark the reserve_addr check unlikely.  Use tlb_vaddr_to_host
instead of probe_write, relying on the memset itself to test
for page writability.  Use set/clear_helper_retaddr so that
we can properly unwind on segfault.

With this, a trivial loop around guest memset will no longer
spend nearly 25% of runtime within page_get_flags.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c
index 24bae3b80c6c30f1ad07067a992c7f64dddb1213..953dd08d5ddc2bf9766580dd41c89d19cab39498 100644 (file)
--- a/target/ppc/mem_helper.c
+++ b/target/ppc/mem_helper.c
@@ -280,20 +280,27 @@ static void dcbz_common(CPUPPCState *env, target_ulong addr,
     addr &= mask;
 
     /* Check reservation */
-    if ((env->reserve_addr & mask) == addr)  {
+    if (unlikely((env->reserve_addr & mask) == addr))  {
         env->reserve_addr = (target_ulong)-1ULL;
     }
 
     /* Try fast path translate */
+#ifdef CONFIG_USER_ONLY
+    haddr = tlb_vaddr_to_host(env, addr, MMU_DATA_STORE, mmu_idx);
+#else
     haddr = probe_write(env, addr, dcbz_size, mmu_idx, retaddr);
-    if (haddr) {
-        memset(haddr, 0, dcbz_size);
-    } else {
+    if (unlikely(!haddr)) {
         /* Slow path */
         for (int i = 0; i < dcbz_size; i += 8) {
             cpu_stq_mmuidx_ra(env, addr + i, 0, mmu_idx, retaddr);
         }
+        return;
     }
+#endif
+
+    set_helper_retaddr(retaddr);
+    memset(haddr, 0, dcbz_size);
+    clear_helper_retaddr();
 }
 
 void helper_dcbz(CPUPPCState *env, target_ulong addr, int mmu_idx)