replace spinlock by QemuMutex.

spinlock is only used in two cases:
  * cpu-exec.c: to protect TranslationBlock
  * mem_helper.c: for lock helper in target-i386 (which seems broken).

It's a pthread_mutex_t in user-mode, so we can use QemuMutex directly,
with an #ifdef.  The #ifdef will be removed when multithreaded TCG
will need the mutex as well.

Signed-off-by: KONRAD Frederic <fred.konrad@greensocs.com>
Message-Id: <1439220437-23957-5-git-send-email-fred.konrad@greensocs.com>
Signed-off-by: Emilio G. Cota <cota@braap.org>
[Merge Emilio G. Cota's patch to remove volatile. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

cpu-exec.c

@@ -357,9 +357,6 @@ int cpu_exec(CPUState *cpu)
     uintptr_t next_tb;
     SyncClocks sc;
 
-    /* This must be volatile so it is not trashed by longjmp() */
-    volatile bool have_tb_lock = false;
-
     if (cpu->halted) {
         if (!cpu_has_work(cpu)) {
             return EXCP_HALTED;
@@ -468,8 +465,7 @@ int cpu_exec(CPUState *cpu)
                     cpu->exception_index = EXCP_INTERRUPT;
                     cpu_loop_exit(cpu);
                 }
-                spin_lock(&tcg_ctx.tb_ctx.tb_lock);
+                tb_lock();
-                have_tb_lock = true;
                 tb = tb_find_fast(cpu);
                 /* Note: we do it here to avoid a gcc bug on Mac OS X when
                    doing it in tb_find_slow */
@@ -491,8 +487,7 @@ int cpu_exec(CPUState *cpu)
                     tb_add_jump((TranslationBlock *)(next_tb & ~TB_EXIT_MASK),
                                 next_tb & TB_EXIT_MASK, tb);
                 }
-                have_tb_lock = false;
+                tb_unlock();
-                spin_unlock(&tcg_ctx.tb_ctx.tb_lock);
                 if (likely(!cpu->exit_request)) {
                     trace_exec_tb(tb, tb->pc);
                     tc_ptr = tb->tc_ptr;
@@ -558,10 +553,7 @@ int cpu_exec(CPUState *cpu)
             x86_cpu = X86_CPU(cpu);
             env = &x86_cpu->env;
 #endif
-            if (have_tb_lock) {
+            tb_lock_reset();
-                spin_unlock(&tcg_ctx.tb_ctx.tb_lock);
-                have_tb_lock = false;
-            }
         }
     } /* for(;;) */
 

include/exec/exec-all.h

@@ -225,7 +225,7 @@ struct TranslationBlock {
     struct TranslationBlock *jmp_first;
 };
 
-#include "exec/spinlock.h"
+#include "qemu/thread.h"
 
 typedef struct TBContext TBContext;
 
@@ -235,7 +235,7 @@ struct TBContext {
     TranslationBlock *tb_phys_hash[CODE_GEN_PHYS_HASH_SIZE];
     int nb_tbs;
     /* any access to the tbs or the page table must use this lock */
-    spinlock_t tb_lock;
+    QemuMutex tb_lock;
 
     /* statistics */
     int tb_flush_count;

linux-user/main.c

@@ -105,7 +105,7 @@ static int pending_cpus;
 /* Make sure everything is in a consistent state for calling fork().  */
 void fork_start(void)
 {
-    pthread_mutex_lock(&tcg_ctx.tb_ctx.tb_lock);
+    qemu_mutex_lock(&tcg_ctx.tb_ctx.tb_lock);
     pthread_mutex_lock(&exclusive_lock);
     mmap_fork_start();
 }
@@ -127,11 +127,11 @@ void fork_end(int child)
         pthread_mutex_init(&cpu_list_mutex, NULL);
         pthread_cond_init(&exclusive_cond, NULL);
         pthread_cond_init(&exclusive_resume, NULL);
-        pthread_mutex_init(&tcg_ctx.tb_ctx.tb_lock, NULL);
+        qemu_mutex_init(&tcg_ctx.tb_ctx.tb_lock);
         gdbserver_fork(thread_cpu);
     } else {
         pthread_mutex_unlock(&exclusive_lock);
-        pthread_mutex_unlock(&tcg_ctx.tb_ctx.tb_lock);
+        qemu_mutex_unlock(&tcg_ctx.tb_ctx.tb_lock);
     }
 }
 

target-i386/cpu.h

@@ -1318,6 +1318,9 @@ static inline MemTxAttrs cpu_get_mem_attrs(CPUX86State *env)
 void cpu_set_mxcsr(CPUX86State *env, uint32_t val);
 void cpu_set_fpuc(CPUX86State *env, uint16_t val);
 
+/* mem_helper.c */
+void helper_lock_init(void);
+
 /* svm_helper.c */
 void cpu_svm_check_intercept_param(CPUX86State *env1, uint32_t type,
                                    uint64_t param);

target-i386/mem_helper.c

@@ -23,18 +23,37 @@
 
 /* broken thread support */
 
-static spinlock_t global_cpu_lock = SPIN_LOCK_UNLOCKED;
+#if defined(CONFIG_USER_ONLY)
+QemuMutex global_cpu_lock;
 
 void helper_lock(void)
 {
-    spin_lock(&global_cpu_lock);
+    qemu_mutex_lock(&global_cpu_lock);
 }
 
 void helper_unlock(void)
 {
-    spin_unlock(&global_cpu_lock);
+    qemu_mutex_unlock(&global_cpu_lock);
 }
 
+void helper_lock_init(void)
+{
+    qemu_mutex_init(&global_cpu_lock);
+}
+#else
+void helper_lock(void)
+{
+}
+
+void helper_unlock(void)
+{
+}
+
+void helper_lock_init(void)
+{
+}
+#endif
+
 void helper_cmpxchg8b(CPUX86State *env, target_ulong a0)
 {
     uint64_t d;

target-i386/translate.c

@@ -7899,6 +7899,8 @@ void optimize_flags_init(void)
                                          offsetof(CPUX86State, regs[i]),
                                          reg_names[i]);
     }
+
+    helper_lock_init();
 }
 
 /* generate intermediate code in gen_opc_buf and gen_opparam_buf for

tcg/tcg.h

@@ -595,6 +595,10 @@ void *tcg_malloc_internal(TCGContext *s, int size);
 void tcg_pool_reset(TCGContext *s);
 void tcg_pool_delete(TCGContext *s);
 
+void tb_lock(void);
+void tb_unlock(void);
+void tb_lock_reset(void);
+
 static inline void *tcg_malloc(int size)
 {
     TCGContext *s = &tcg_ctx;

translate-all.c

@@ -128,6 +128,39 @@ static void *l1_map[V_L1_SIZE];
 /* code generation context */
 TCGContext tcg_ctx;
 
+/* translation block context */
+#ifdef CONFIG_USER_ONLY
+__thread int have_tb_lock;
+#endif
+
+void tb_lock(void)
+{
+#ifdef CONFIG_USER_ONLY
+    assert(!have_tb_lock);
+    qemu_mutex_lock(&tcg_ctx.tb_ctx.tb_lock);
+    have_tb_lock++;
+#endif
+}
+
+void tb_unlock(void)
+{
+#ifdef CONFIG_USER_ONLY
+    assert(have_tb_lock);
+    have_tb_lock--;
+    qemu_mutex_unlock(&tcg_ctx.tb_ctx.tb_lock);
+#endif
+}
+
+void tb_lock_reset(void)
+{
+#ifdef CONFIG_USER_ONLY
+    if (have_tb_lock) {
+        qemu_mutex_unlock(&tcg_ctx.tb_ctx.tb_lock);
+        have_tb_lock = 0;
+    }
+#endif
+}
+
 static void tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
                          tb_page_addr_t phys_page2);
 static TranslationBlock *tb_find_pc(uintptr_t tc_ptr);
@@ -675,6 +708,7 @@ static inline void code_gen_alloc(size_t tb_size)
             CODE_GEN_AVG_BLOCK_SIZE;
     tcg_ctx.tb_ctx.tbs =
             g_malloc(tcg_ctx.code_gen_max_blocks * sizeof(TranslationBlock));
+    qemu_mutex_init(&tcg_ctx.tb_ctx.tb_lock);
 }
 
 /* Must be called before using the QEMU cpus. 'tb_size' is the size