diff --git a/cpus.c b/cpus.c
index b5844b7103..a5ea3eef80 100644
--- a/cpus.c
+++ b/cpus.c
@@ -1762,10 +1762,16 @@ bool qemu_mutex_iothread_locked(void)
     return iothread_locked;
 }
 
-void qemu_mutex_lock_iothread(void)
+/*
+ * The BQL is taken from so many places that it is worth profiling the
+ * callers directly, instead of funneling them all through a single function.
+ */
+void qemu_mutex_lock_iothread_impl(const char *file, int line)
 {
+    QemuMutexLockFunc bql_lock = atomic_read(&qemu_bql_mutex_lock_func);
+
     g_assert(!qemu_mutex_iothread_locked());
-    qemu_mutex_lock(&qemu_global_mutex);
+    bql_lock(&qemu_global_mutex, file, line);
     iothread_locked = true;
 }
 
diff --git a/include/qemu/main-loop.h b/include/qemu/main-loop.h
index 721aa2416a..e59f9ae1e9 100644
--- a/include/qemu/main-loop.h
+++ b/include/qemu/main-loop.h
@@ -276,7 +276,9 @@ bool qemu_mutex_iothread_locked(void);
  * NOTE: tools currently are single-threaded and qemu_mutex_lock_iothread
  * is a no-op there.
  */
-void qemu_mutex_lock_iothread(void);
+#define qemu_mutex_lock_iothread()                      \
+    qemu_mutex_lock_iothread_impl(__FILE__, __LINE__)
+void qemu_mutex_lock_iothread_impl(const char *file, int line);
 
 /**
  * qemu_mutex_unlock_iothread: Unlock the main loop mutex.
diff --git a/include/qemu/thread.h b/include/qemu/thread.h
index c90ea4783f..dacebcfff0 100644
--- a/include/qemu/thread.h
+++ b/include/qemu/thread.h
@@ -35,6 +35,7 @@ typedef int (*QemuRecMutexTrylockFunc)(QemuRecMutex *m, const char *f, int l);
 typedef void (*QemuCondWaitFunc)(QemuCond *c, QemuMutex *m, const char *f,
                                  int l);
 
+extern QemuMutexLockFunc qemu_bql_mutex_lock_func;
 extern QemuMutexLockFunc qemu_mutex_lock_func;
 extern QemuMutexTrylockFunc qemu_mutex_trylock_func;
 extern QemuRecMutexLockFunc qemu_rec_mutex_lock_func;
diff --git a/stubs/iothread-lock.c b/stubs/iothread-lock.c
index 9b6db2e740..eb745d7d6a 100644
--- a/stubs/iothread-lock.c
+++ b/stubs/iothread-lock.c
@@ -7,7 +7,7 @@ bool qemu_mutex_iothread_locked(void)
     return true;
 }
 
-void qemu_mutex_lock_iothread(void)
+void qemu_mutex_lock_iothread_impl(const char *file, int line)
 {
 }
 
diff --git a/util/qsp.c b/util/qsp.c
index 4dc851e456..b0c2575d10 100644
--- a/util/qsp.c
+++ b/util/qsp.c
@@ -65,6 +65,7 @@
 
 enum QSPType {
     QSP_MUTEX,
+    QSP_BQL_MUTEX,
     QSP_REC_MUTEX,
     QSP_CONDVAR,
 };
@@ -123,10 +124,12 @@ static bool qsp_initialized, qsp_initializing;
 
 static const char * const qsp_typenames[] = {
     [QSP_MUTEX]     = "mutex",
+    [QSP_BQL_MUTEX] = "BQL mutex",
     [QSP_REC_MUTEX] = "rec_mutex",
     [QSP_CONDVAR]   = "condvar",
 };
 
+QemuMutexLockFunc qemu_bql_mutex_lock_func = qemu_mutex_lock_impl;
 QemuMutexLockFunc qemu_mutex_lock_func = qemu_mutex_lock_impl;
 QemuMutexTrylockFunc qemu_mutex_trylock_func = qemu_mutex_trylock_impl;
 QemuRecMutexLockFunc qemu_rec_mutex_lock_func = qemu_rec_mutex_lock_impl;
@@ -419,6 +422,7 @@ static inline void qsp_entry_record(QSPEntry *e, int64_t delta)
         return err;                                                     \
     }
 
+QSP_GEN_VOID(QemuMutex, QSP_BQL_MUTEX, qsp_bql_mutex_lock, qemu_mutex_lock_impl)
 QSP_GEN_VOID(QemuMutex, QSP_MUTEX, qsp_mutex_lock, qemu_mutex_lock_impl)
 QSP_GEN_RET1(QemuMutex, QSP_MUTEX, qsp_mutex_trylock, qemu_mutex_trylock_impl)
 
@@ -453,6 +457,7 @@ void qsp_enable(void)
 {
     atomic_set(&qemu_mutex_lock_func, qsp_mutex_lock);
     atomic_set(&qemu_mutex_trylock_func, qsp_mutex_trylock);
+    atomic_set(&qemu_bql_mutex_lock_func, qsp_bql_mutex_lock);
     atomic_set(&qemu_rec_mutex_lock_func, qsp_rec_mutex_lock);
     atomic_set(&qemu_rec_mutex_trylock_func, qsp_rec_mutex_trylock);
     atomic_set(&qemu_cond_wait_func, qsp_cond_wait);
@@ -462,6 +467,7 @@ void qsp_disable(void)
 {
     atomic_set(&qemu_mutex_lock_func, qemu_mutex_lock_impl);
     atomic_set(&qemu_mutex_trylock_func, qemu_mutex_trylock_impl);
+    atomic_set(&qemu_bql_mutex_lock_func, qemu_mutex_lock_impl);
     atomic_set(&qemu_rec_mutex_lock_func, qemu_rec_mutex_lock_impl);
     atomic_set(&qemu_rec_mutex_trylock_func, qemu_rec_mutex_trylock_impl);
     atomic_set(&qemu_cond_wait_func, qemu_cond_wait_impl);