diff --git a/cpu-exec.c b/cpu-exec.c
index 4879c7deff..e9b50a6b30 100644
--- a/cpu-exec.c
+++ b/cpu-exec.c
@@ -211,15 +211,21 @@ static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
     if (max_cycles > CF_COUNT_MASK)
         max_cycles = CF_COUNT_MASK;
 
+    tb_lock();
     tb = tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base, orig_tb->flags,
                      max_cycles | CF_NOCACHE
                          | (ignore_icount ? CF_IGNORE_ICOUNT : 0));
     tb->orig_tb = orig_tb;
+    tb_unlock();
+
     /* execute the generated code */
     trace_exec_tb_nocache(tb, tb->pc);
     cpu_tb_exec(cpu, tb);
+
+    tb_lock();
     tb_phys_invalidate(tb, -1);
     tb_free(tb);
+    tb_unlock();
 }
 #endif
 
diff --git a/exec.c b/exec.c
index 4c84389b56..ab30629367 100644
--- a/exec.c
+++ b/exec.c
@@ -2064,6 +2064,12 @@ static void check_watchpoint(int offset, int len, MemTxAttrs attrs, int flags)
                     continue;
                 }
                 cpu->watchpoint_hit = wp;
+
+                /* The tb_lock will be reset when cpu_loop_exit or
+                 * cpu_loop_exit_noexc longjmp back into the cpu_exec
+                 * main loop.
+                 */
+                tb_lock();
                 tb_check_watchpoint(cpu);
                 if (wp->flags & BP_STOP_BEFORE_ACCESS) {
                     cpu->exception_index = EXCP_DEBUG;
diff --git a/hw/i386/kvmvapic.c b/hw/i386/kvmvapic.c
index 74a549becf..4448253c58 100644
--- a/hw/i386/kvmvapic.c
+++ b/hw/i386/kvmvapic.c
@@ -17,6 +17,7 @@
 #include "sysemu/kvm.h"
 #include "hw/i386/apic_internal.h"
 #include "hw/sysbus.h"
+#include "tcg/tcg.h"
 
 #define VAPIC_IO_PORT           0x7e
 
@@ -449,6 +450,9 @@ static void patch_instruction(VAPICROMState *s, X86CPU *cpu, target_ulong ip)
     resume_all_vcpus();
 
     if (!kvm_enabled()) {
+        /* tb_lock will be reset when cpu_loop_exit_noexc longjmps
+         * back into the cpu_exec loop. */
+        tb_lock();
         tb_gen_code(cs, current_pc, current_cs_base, current_flags, 1);
         cpu_loop_exit_noexc(cs);
     }
diff --git a/translate-all.c b/translate-all.c
index 3ff43ec2e2..874f4159c0 100644
--- a/translate-all.c
+++ b/translate-all.c
@@ -363,7 +363,9 @@ static int cpu_restore_state_from_tb(CPUState *cpu, TranslationBlock *tb,
 bool cpu_restore_state(CPUState *cpu, uintptr_t retaddr)
 {
     TranslationBlock *tb;
+    bool r = false;
 
+    tb_lock();
     tb = tb_find_pc(retaddr);
     if (tb) {
         cpu_restore_state_from_tb(cpu, tb, retaddr);
@@ -372,9 +374,11 @@ bool cpu_restore_state(CPUState *cpu, uintptr_t retaddr)
             tb_phys_invalidate(tb, -1);
             tb_free(tb);
         }
-        return true;
+        r = true;
     }
-    return false;
+    tb_unlock();
+
+    return r;
 }
 
 void page_size_init(void)
@@ -1456,6 +1460,7 @@ void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end,
     /* we remove all the TBs in the range [start, end[ */
     /* XXX: see if in some cases it could be faster to invalidate all
        the code */
+    tb_lock();
     tb = p->first_tb;
     while (tb != NULL) {
         n = (uintptr_t)tb & 3;
@@ -1515,6 +1520,7 @@ void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end,
         cpu_loop_exit_noexc(cpu);
     }
 #endif
+    tb_unlock();
 }
 
 #ifdef CONFIG_SOFTMMU
@@ -1584,6 +1590,8 @@ static bool tb_invalidate_phys_page(tb_page_addr_t addr, uintptr_t pc)
     if (!p) {
         return false;
     }
+
+    tb_lock();
     tb = p->first_tb;
 #ifdef TARGET_HAS_PRECISE_SMC
     if (tb && pc != 0) {
@@ -1621,9 +1629,13 @@ static bool tb_invalidate_phys_page(tb_page_addr_t addr, uintptr_t pc)
            modifying the memory. It will ensure that it cannot modify
            itself */
         tb_gen_code(cpu, current_pc, current_cs_base, current_flags, 1);
+        /* tb_lock will be reset after cpu_loop_exit_noexc longjmps
+         * back into the cpu_exec loop. */
         return true;
     }
 #endif
+    tb_unlock();
+
     return false;
 }
 #endif
@@ -1718,6 +1730,7 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
     target_ulong pc, cs_base;
     uint32_t flags;
 
+    tb_lock();
     tb = tb_find_pc(retaddr);
     if (!tb) {
         cpu_abort(cpu, "cpu_io_recompile: could not find TB for pc=%p",
@@ -1769,11 +1782,16 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
     /* FIXME: In theory this could raise an exception.  In practice
        we have already translated the block once so it's probably ok.  */
     tb_gen_code(cpu, pc, cs_base, flags, cflags);
+
     /* TODO: If env->pc != tb->pc (i.e. the faulting instruction was not
-       the first in the TB) then we end up generating a whole new TB and
-       repeating the fault, which is horribly inefficient.
-       Better would be to execute just this insn uncached, or generate a
-       second new TB.  */
+     * the first in the TB) then we end up generating a whole new TB and
+     *  repeating the fault, which is horribly inefficient.
+     *  Better would be to execute just this insn uncached, or generate a
+     *  second new TB.
+     *
+     * cpu_loop_exit_noexc will longjmp back to cpu_exec where the
+     * tb_lock gets reset.
+     */
     cpu_loop_exit_noexc(cpu);
 }
 
@@ -1837,6 +1855,8 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fprintf)
     TranslationBlock *tb;
     struct qht_stats hst;
 
+    tb_lock();
+
     target_code_size = 0;
     max_target_code_size = 0;
     cross_page = 0;
@@ -1898,6 +1918,8 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fprintf)
             tcg_ctx.tb_ctx.tb_phys_invalidate_count);
     cpu_fprintf(f, "TLB flush count     %d\n", tlb_flush_count);
     tcg_dump_info(f, cpu_fprintf);
+
+    tb_unlock();
 }
 
 void dump_opcount_info(FILE *f, fprintf_function cpu_fprintf)