diff --git a/docs/rm/custom_instructions.md b/docs/rm/custom_instructions.md
index f7fcfbd0d..0e834b33a 100644
--- a/docs/rm/custom_instructions.md
+++ b/docs/rm/custom_instructions.md
@@ -104,7 +104,7 @@ The DMSTATI instruction can be used to implement a blocking wait for the complet
 
         dmcpyi a0, ...
     1:  dmstati t0, 0
-        bltu a0, t0, 1b
+        bltu t0, a0, 1b
 
 Similarly, waiting for the completion of *all* DMA transfers:
 
diff --git a/sw/snRuntime/src/dma.h b/sw/snRuntime/src/dma.h
index 21d2adedc..29d5d226c 100644
--- a/sw/snRuntime/src/dma.h
+++ b/sw/snRuntime/src/dma.h
@@ -151,8 +151,7 @@ inline void snrt_dma_wait(snrt_dma_txid_t tid) {
                (    0b000 << 12) | \
                (      (5) <<  7) | \
                (0b0101011 <<  0)   \n"
-        "sub t0, t0, %0 \n"
-        "blez t0, 1b \n" ::"r"(tid)
+        "bltu t0, %0, 1b \n" ::"r"(tid)
         : "t0");
 }
 
diff --git a/sw/tests/dma_simple.c b/sw/tests/dma_simple.c
index 5260236e7..a9388f978 100644
--- a/sw/tests/dma_simple.c
+++ b/sw/tests/dma_simple.c
@@ -21,8 +21,8 @@ int main() {
     }
 
     // Copy data to main memory.
-    snrt_dma_start_1d(buffer, buffer_src, sizeof(buffer));
-    snrt_dma_wait_all();
+    snrt_dma_txid_t id = snrt_dma_start_1d(buffer, buffer_src, sizeof(buffer));
+    snrt_dma_wait(id);
 
     // Check that the main memory buffer contains the correct data.
     for (uint32_t i = 0; i < 32; i++) {