tcg: define CF_PARALLEL and use it for TB hashing along with CF_COUNT_MASK

This will enable us to decouple code translation from the value
of parallel_cpus at any given time. It will also help us minimize
TB flushes when generating code via EXCP_ATOMIC.

Note that the declaration of parallel_cpus is brought to exec-all.h
to be able to define there the "curr_cflags" inline.

Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

4 files changed, 30 insertions, 9 deletions

diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index 53f1835..352abc7 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -325,6 +325,9 @@ struct TranslationBlock {
 #define CF_USE_ICOUNT  0x20000
 #define CF_IGNORE_ICOUNT 0x40000 /* Do not generate icount code */
 #define CF_INVALID     0x80000 /* TB is stale. Setters must acquire tb_lock */
+#define CF_PARALLEL    0x100000 /* Generate code for a parallel context */
+/* cflags' mask for hashing/comparison */
+#define CF_HASH_MASK (CF_PARALLEL)
 
     /* Per-vCPU dynamic tracing state used to generate this TB */
     uint32_t trace_vcpu_dstate;
@@ -365,11 +368,26 @@ struct TranslationBlock {
     uintptr_t jmp_list_first;
 };
 
+extern bool parallel_cpus;
+
+/* Hide the atomic_read to make code a little easier on the eyes */
+static inline uint32_t tb_cflags(const TranslationBlock *tb)
+{
+    return atomic_read(&tb->cflags);
+}
+
+/* current cflags for hashing/comparison */
+static inline uint32_t curr_cflags(void)
+{
+    return parallel_cpus ? CF_PARALLEL : 0;
+}
+
 void tb_free(TranslationBlock *tb);
 void tb_flush(CPUState *cpu);
 void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr);
 TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
-                                   target_ulong cs_base, uint32_t flags);
+                                   target_ulong cs_base, uint32_t flags,
+                                   uint32_t cf_mask);
 void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr);
 
 /* GETPC is the true target of the return instruction that we'll execute.  */
diff --git a/include/exec/tb-hash-xx.h b/include/exec/tb-hash-xx.h
index 6cd3022..747a9a6 100644
--- a/include/exec/tb-hash-xx.h
+++ b/include/exec/tb-hash-xx.h
@@ -48,8 +48,8 @@
  * xxhash32, customized for input variables that are not guaranteed to be
  * contiguous in memory.
  */
-static inline
-uint32_t tb_hash_func6(uint64_t a0, uint64_t b0, uint32_t e, uint32_t f)
+static inline uint32_t
+tb_hash_func7(uint64_t a0, uint64_t b0, uint32_t e, uint32_t f, uint32_t g)
 {
     uint32_t v1 = TB_HASH_XX_SEED + PRIME32_1 + PRIME32_2;
     uint32_t v2 = TB_HASH_XX_SEED + PRIME32_2;
@@ -78,7 +78,7 @@ uint32_t tb_hash_func6(uint64_t a0, uint64_t b0, uint32_t e, uint32_t f)
     v4 *= PRIME32_1;
 
     h32 = rol32(v1, 1) + rol32(v2, 7) + rol32(v3, 12) + rol32(v4, 18);
-    h32 += 24;
+    h32 += 28;
 
     h32 += e * PRIME32_3;
     h32  = rol32(h32, 17) * PRIME32_4;
@@ -86,6 +86,9 @@ uint32_t tb_hash_func6(uint64_t a0, uint64_t b0, uint32_t e, uint32_t f)
     h32 += f * PRIME32_3;
     h32  = rol32(h32, 17) * PRIME32_4;
 
+    h32 += g * PRIME32_3;
+    h32  = rol32(h32, 17) * PRIME32_4;
+
     h32 ^= h32 >> 15;
     h32 *= PRIME32_2;
     h32 ^= h32 >> 13;
diff --git a/include/exec/tb-hash.h b/include/exec/tb-hash.h
index 17b5ee0..0526c4f 100644
--- a/include/exec/tb-hash.h
+++ b/include/exec/tb-hash.h
@@ -59,9 +59,9 @@ static inline unsigned int tb_jmp_cache_hash_func(target_ulong pc)
 
 static inline
 uint32_t tb_hash_func(tb_page_addr_t phys_pc, target_ulong pc, uint32_t flags,
-                      uint32_t trace_vcpu_dstate)
+                      uint32_t cf_mask, uint32_t trace_vcpu_dstate)
 {
-    return tb_hash_func6(phys_pc, pc, flags, trace_vcpu_dstate);
+    return tb_hash_func7(phys_pc, pc, flags, cf_mask, trace_vcpu_dstate);
 }
 
 #endif
diff --git a/include/exec/tb-lookup.h b/include/exec/tb-lookup.h
index 436b6d5..2961385 100644
--- a/include/exec/tb-lookup.h
+++ b/include/exec/tb-lookup.h
@@ -21,7 +21,7 @@
 /* Might cause an exception, so have a longjmp destination ready */
 static inline TranslationBlock *
 tb_lookup__cpu_state(CPUState *cpu, target_ulong *pc, target_ulong *cs_base,
-                     uint32_t *flags)
+                     uint32_t *flags, uint32_t cf_mask)
 {
     CPUArchState *env = (CPUArchState *)cpu->env_ptr;
     TranslationBlock *tb;
@@ -35,10 +35,10 @@ tb_lookup__cpu_state(CPUState *cpu, target_ulong *pc, target_ulong *cs_base,
                tb->cs_base == *cs_base &&
                tb->flags == *flags &&
                tb->trace_vcpu_dstate == *cpu->trace_dstate &&
-               !(atomic_read(&tb->cflags) & CF_INVALID))) {
+               (tb_cflags(tb) & (CF_HASH_MASK | CF_INVALID)) == cf_mask)) {
         return tb;
     }
-    tb = tb_htable_lookup(cpu, *pc, *cs_base, *flags);
+    tb = tb_htable_lookup(cpu, *pc, *cs_base, *flags, cf_mask);
     if (tb == NULL) {
         return NULL;
     }