ppc: Speed up dcbz

Use tlb_vaddr_to_host to do a fast path single translate for
the whole cache line. Also make the reservation check match
the entire range.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

diff --git a/target-ppc/mem_helper.c b/target-ppc/mem_helper.c
index 92a594c8944f2f8a483df9b1a8302aa513116efa..6548715831b7d3a6d9dea2580eb1c86004ba0f6c 100644 (file)
--- a/target-ppc/mem_helper.c
+++ b/target-ppc/mem_helper.c
@@ -141,35 +141,39 @@ void helper_stsw(CPUPPCState *env, target_ulong addr, uint32_t nb,
     }
 }
 
-static void do_dcbz(CPUPPCState *env, target_ulong addr, int dcache_line_size,
-                    uintptr_t raddr)
+void helper_dcbz(CPUPPCState *env, target_ulong addr, uint32_t opcode)
 {
-    int i;
-
-    addr &= ~(dcache_line_size - 1);
-    for (i = 0; i < dcache_line_size; i += 4) {
-        cpu_stl_data_ra(env, addr + i, 0, raddr);
-    }
-    if (env->reserve_addr == addr) {
-        env->reserve_addr = (target_ulong)-1ULL;
-    }
-}
-
-void helper_dcbz(CPUPPCState *env, target_ulong addr, uint32_t is_dcbzl)
-{
-    int dcbz_size = env->dcache_line_size;
+    target_ulong mask, dcbz_size = env->dcache_line_size;
+    uint32_t i;
+    void *haddr;
 
 #if defined(TARGET_PPC64)
-    if (!is_dcbzl &&
-        (env->excp_model == POWERPC_EXCP_970) &&
-        ((env->spr[SPR_970_HID5] >> 7) & 0x3) == 1) {
+    /* Check for dcbz vs dcbzl on 970 */
+    if (env->excp_model == POWERPC_EXCP_970 &&
+        !(opcode & 0x00200000) && ((env->spr[SPR_970_HID5] >> 7) & 0x3) == 1) {
         dcbz_size = 32;
     }
 #endif
 
-    /* XXX add e500mc support */
+    /* Align address */
+    mask = ~(dcbz_size - 1);
+    addr &= mask;
+
+    /* Check reservation */
+    if ((env->reserve_addr & mask) == (addr & mask))  {
+        env->reserve_addr = (target_ulong)-1ULL;
+    }
 
-    do_dcbz(env, addr, dcbz_size, GETPC());
+    /* Try fast path translate */
+    haddr = tlb_vaddr_to_host(env, addr, MMU_DATA_STORE, env->dmmu_idx);
+    if (haddr) {
+        memset(haddr, 0, dcbz_size);
+    } else {
+        /* Slow path */
+        for (i = 0; i < dcbz_size; i += 8) {
+            cpu_stq_data_ra(env, addr + i, 0, GETPC());
+        }
+    }
 }
 
 void helper_icbi(CPUPPCState *env, target_ulong addr)

diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index 7aa8d779728caf1067edb7a0745051b86efc0a94..ac2c79bf28697dea848f347c4f6de602fee6aad2 100644 (file)
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -4088,18 +4088,15 @@ static void gen_dcbtls(DisasContext *ctx)
 static void gen_dcbz(DisasContext *ctx)
 {
     TCGv tcgv_addr;
-    TCGv_i32 tcgv_is_dcbzl;
-    int is_dcbzl = ctx->opcode & 0x00200000 ? 1 : 0;
+    TCGv_i32 tcgv_op;
 
     gen_set_access_type(ctx, ACCESS_CACHE);
     tcgv_addr = tcg_temp_new();
-    tcgv_is_dcbzl = tcg_const_i32(is_dcbzl);
-
+    tcgv_op = tcg_const_i32(ctx->opcode & 0x03FF000);
     gen_addr_reg_index(ctx, tcgv_addr);
-    gen_helper_dcbz(cpu_env, tcgv_addr, tcgv_is_dcbzl);
-
+    gen_helper_dcbz(cpu_env, tcgv_addr, tcgv_op);
     tcg_temp_free(tcgv_addr);
-    tcg_temp_free_i32(tcgv_is_dcbzl);
+    tcg_temp_free_i32(tcgv_op);
 }
 
 /* dst / dstt */