diff --git a/dma-helpers.c b/dma-helpers.c
index bdcd38cd27..9d6b6fa1fd 100644
--- a/dma-helpers.c
+++ b/dma-helpers.c
@@ -9,6 +9,7 @@
 
 #include "dma.h"
 #include "block_int.h"
+#include "trace.h"
 
 void qemu_sglist_init(QEMUSGList *qsg, int alloc_hint)
 {
@@ -83,6 +84,8 @@ static void dma_bdrv_unmap(DMAAIOCB *dbs)
 
 static void dma_complete(DMAAIOCB *dbs, int ret)
 {
+    trace_dma_complete(dbs, ret, dbs->common.cb);
+
     dma_bdrv_unmap(dbs);
     if (dbs->common.cb) {
         dbs->common.cb(dbs->common.opaque, ret);
@@ -106,6 +109,8 @@ static void dma_bdrv_cb(void *opaque, int ret)
     target_phys_addr_t cur_addr, cur_len;
     void *mem;
 
+    trace_dma_bdrv_cb(dbs, ret);
+
     dbs->acb = NULL;
     dbs->sector_num += dbs->iov.size / 512;
     dma_bdrv_unmap(dbs);
@@ -130,6 +135,7 @@ static void dma_bdrv_cb(void *opaque, int ret)
     }
 
     if (dbs->iov.size == 0) {
+        trace_dma_map_wait(dbs);
         cpu_register_map_client(dbs, continue_after_map_failure);
         return;
     }
@@ -145,6 +151,8 @@ static void dma_aio_cancel(BlockDriverAIOCB *acb)
 {
     DMAAIOCB *dbs = container_of(acb, DMAAIOCB, common);
 
+    trace_dma_aio_cancel(dbs);
+
     if (dbs->acb) {
         BlockDriverAIOCB *acb = dbs->acb;
         dbs->acb = NULL;
@@ -168,6 +176,8 @@ BlockDriverAIOCB *dma_bdrv_io(
 {
     DMAAIOCB *dbs = qemu_aio_get(&dma_aio_pool, bs, cb, opaque);
 
+    trace_dma_bdrv_io(dbs, bs, sector_num, to_dev);
+
     dbs->acb = NULL;
     dbs->bs = bs;
     dbs->sg = sg;
diff --git a/trace-events b/trace-events
index 518b76b137..bf1cf57032 100644
--- a/trace-events
+++ b/trace-events
@@ -632,3 +632,10 @@ win_helper_no_switch_pstate(uint32_t new_pstate_regs) "change_pstate: regs new=%
 win_helper_wrpil(uint32_t psrpil, uint32_t new_pil) "old=%x new=%x"
 win_helper_done(uint32_t tl) "tl=%d"
 win_helper_retry(uint32_t tl) "tl=%d"
+
+# dma-helpers.c
+dma_bdrv_io(void *dbs, void *bs, int64_t sector_num, bool to_dev) "dbs=%p bs=%p sector_num=%" PRId64 " to_dev=%d"
+dma_aio_cancel(void *dbs) "dbs=%p"
+dma_complete(void *dbs, int ret, void *cb) "dbs=%p ret=%d cb=%p"
+dma_bdrv_cb(void *dbs, int ret) "dbs=%p ret=%d"
+dma_map_wait(void *dbs) "dbs=%p"