[Qemu-devel] [PATCH v4 07/12] tcg: Prepare TB invalidation for lockless TB lookup

[Sergey Fedorov]

From: Sergey Fedorov <address@hidden>

When invalidating a translation block, set an invalid CPU state into the
TranslationBlock structure first.

As soon as the TB is marked with an invalid CPU state, there is no need
to remove it from CPU's 'tb_jmp_cache'. However it will be necessary to
recheck whether the target TB is still valid after acquiring 'tb_lock'
but before calling tb_add_jump() since TB lookup is to be performed out
of 'tb_lock' in future. Note that we don't have to check 'last_tb' since
it is safe to patch an already invalidated TB since it will not be
executed anyway.

Suggested-by: Paolo Bonzini <address@hidden>
Signed-off-by: Sergey Fedorov <address@hidden>
Signed-off-by: Sergey Fedorov <address@hidden>
Reviewed-by: Alex Bennée <address@hidden>

---
Changes in v4:
 - smp_wmb() removed after tb_mark_invalid()
 - atomic access to TB CPU state
---
 cpu-exec.c              |  7 ++++---
 include/exec/exec-all.h |  8 +++++++-
 translate-all.c         | 11 ++---------
 3 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/cpu-exec.c b/cpu-exec.c
index c973e3b85922..e16df762f50a 100644
--- a/cpu-exec.c
+++ b/cpu-exec.c
@@ -334,8 +334,9 @@ static inline TranslationBlock *tb_find_fast(CPUState *cpu,
     cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
     tb_lock();
     tb = atomic_read(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)]);
-    if (unlikely(!tb || tb->pc != pc || tb->cs_base != cs_base ||
-                 tb->flags != flags)) {
+    if (unlikely(!tb || atomic_read(&tb->pc) != pc ||
+                 atomic_read(&tb->cs_base) != cs_base ||
+                 atomic_read(&b->flags) != flags)) {
         tb = tb_find_slow(cpu, pc, cs_base, flags);
     }
 #ifndef CONFIG_USER_ONLY
@@ -352,7 +353,7 @@ static inline TranslationBlock *tb_find_fast(CPUState *cpu,
         /* Check if translation buffer has been flushed */
         if (cpu->tb_flushed) {
             cpu->tb_flushed = false;
-        } else {
+        } else if (!tb_is_invalid(tb)) {
             tb_add_jump(last_tb, tb_exit, tb);
         }
     }
diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index a499c7c56eef..8f0afcdbd62a 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -258,7 +258,13 @@ void tb_phys_invalidate(TranslationBlock *tb, 
tb_page_addr_t page_addr);
 
 static inline void tb_mark_invalid(TranslationBlock *tb)
 {
-    cpu_get_invalid_tb_cpu_state(&tb->pc, &tb->cs_base, &tb->flags);
+    target_ulong pc = 0, cs_base = 0;
+    uint32_t flags = 0;
+
+    cpu_get_invalid_tb_cpu_state(&pc, &cs_base, &flags);
+    atomic_set(&tb->pc, pc);
+    atomic_set(&tb->cs_base, cs_base);
+    atomic_set(&tb->flags, flags);
 }
 
 static inline bool tb_is_invalid(TranslationBlock *tb)
diff --git a/translate-all.c b/translate-all.c
index 788fed1e0765..9db72e8982b1 100644
--- a/translate-all.c
+++ b/translate-all.c
@@ -986,11 +986,12 @@ static inline void tb_jmp_unlink(TranslationBlock *tb)
 /* invalidate one TB */
 void tb_phys_invalidate(TranslationBlock *tb, tb_page_addr_t page_addr)
 {
-    CPUState *cpu;
     PageDesc *p;
     uint32_t h;
     tb_page_addr_t phys_pc;
 
+    tb_mark_invalid(tb);
+
     /* remove the TB from the hash list */
     phys_pc = tb->page_addr[0] + (tb->pc & ~TARGET_PAGE_MASK);
     h = tb_hash_func(phys_pc, tb->pc, tb->flags);
@@ -1008,14 +1009,6 @@ void tb_phys_invalidate(TranslationBlock *tb, 
tb_page_addr_t page_addr)
         invalidate_page_bitmap(p);
     }
 
-    /* remove the TB from the hash list */
-    h = tb_jmp_cache_hash_func(tb->pc);
-    CPU_FOREACH(cpu) {
-        if (atomic_read(&cpu->tb_jmp_cache[h]) == tb) {
-            atomic_set(&cpu->tb_jmp_cache[h], NULL);
-        }
-    }
-
     /* suppress this TB from the two jump lists */
     tb_remove_from_jmp_list(tb, 0);
     tb_remove_from_jmp_list(tb, 1);
-- 
2.9.1