cpu-exec: fix lock hierarchy for user-mode emulation

tb_lock has to be taken inside the mmap_lock (example:
tb_invalidate_phys_range is called by target_mmap), but
tb_link_page is taking the mmap_lock and it is called
with the tb_lock held.

To fix this, take the mmap_lock in tb_find_slow, not
in tb_link_page.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
diff --git a/cpu-exec.c b/cpu-exec.c
index 2c0a6f6..cb0c75d 100644
--- a/cpu-exec.c
+++ b/cpu-exec.c
@@ -249,10 +249,10 @@
     tb_free(tb);
 }
 
-static TranslationBlock *tb_find_slow(CPUState *cpu,
-                                      target_ulong pc,
-                                      target_ulong cs_base,
-                                      uint64_t flags)
+static TranslationBlock *tb_find_physical(CPUState *cpu,
+                                          target_ulong pc,
+                                          target_ulong cs_base,
+                                          uint64_t flags)
 {
     CPUArchState *env = (CPUArchState *)cpu->env_ptr;
     TranslationBlock *tb, **ptb1;
@@ -269,8 +269,9 @@
     ptb1 = &tcg_ctx.tb_ctx.tb_phys_hash[h];
     for(;;) {
         tb = *ptb1;
-        if (!tb)
-            goto not_found;
+        if (!tb) {
+            return NULL;
+        }
         if (tb->pc == pc &&
             tb->page_addr[0] == phys_page1 &&
             tb->cs_base == cs_base &&
@@ -282,25 +283,59 @@
                 virt_page2 = (pc & TARGET_PAGE_MASK) +
                     TARGET_PAGE_SIZE;
                 phys_page2 = get_page_addr_code(env, virt_page2);
-                if (tb->page_addr[1] == phys_page2)
-                    goto found;
+                if (tb->page_addr[1] == phys_page2) {
+                    break;
+                }
             } else {
-                goto found;
+                break;
             }
         }
         ptb1 = &tb->phys_hash_next;
     }
- not_found:
-   /* if no translated code available, then translate it now */
+
+    /* Move the TB to the head of the list */
+    *ptb1 = tb->phys_hash_next;
+    tb->phys_hash_next = tcg_ctx.tb_ctx.tb_phys_hash[h];
+    tcg_ctx.tb_ctx.tb_phys_hash[h] = tb;
+    return tb;
+}
+
+static TranslationBlock *tb_find_slow(CPUState *cpu,
+                                      target_ulong pc,
+                                      target_ulong cs_base,
+                                      uint64_t flags)
+{
+    TranslationBlock *tb;
+
+    tb = tb_find_physical(cpu, pc, cs_base, flags);
+    if (tb) {
+        goto found;
+    }
+
+#ifdef CONFIG_USER_ONLY
+    /* mmap_lock is needed by tb_gen_code, and mmap_lock must be
+     * taken outside tb_lock.  Since we're momentarily dropping
+     * tb_lock, there's a chance that our desired tb has been
+     * translated.
+     */
+    tb_unlock();
+    mmap_lock();
+    tb_lock();
+    tb = tb_find_physical(cpu, pc, cs_base, flags);
+    if (tb) {
+        mmap_unlock();
+        goto found;
+    }
+#endif
+
+    /* if no translated code available, then translate it now */
     tb = tb_gen_code(cpu, pc, cs_base, flags, 0);
 
- found:
-    /* Move the last found TB to the head of the list */
-    if (likely(*ptb1)) {
-        *ptb1 = tb->phys_hash_next;
-        tb->phys_hash_next = tcg_ctx.tb_ctx.tb_phys_hash[h];
-        tcg_ctx.tb_ctx.tb_phys_hash[h] = tb;
-    }
+#ifdef CONFIG_USER_ONLY
+    mmap_unlock();
+#endif
+
+found:
     /* we add the TB in the virtual pc hash table */
     cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)] = tb;
     return tb;