diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index b66c53bdc039..0f0c45665dbd 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -295,9 +295,12 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 
 static void a3xx_recover(struct msm_gpu *gpu)
 {
+	adreno_dump_info(gpu);
+
 	/* dump registers before resetting gpu, if enabled: */
 	if (hang_debug)
 		a3xx_dump(gpu);
+
 	gpu_write(gpu, REG_A3XX_RBBM_SW_RESET_CMD, 1);
 	gpu_read(gpu, REG_A3XX_RBBM_SW_RESET_CMD);
 	gpu_write(gpu, REG_A3XX_RBBM_SW_RESET_CMD, 0);
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 91221836c5ad..a53f1be05f75 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -268,6 +268,8 @@ static int a4xx_hw_init(struct msm_gpu *gpu)
 
 static void a4xx_recover(struct msm_gpu *gpu)
 {
+	adreno_dump_info(gpu);
+
 	/* dump registers before resetting gpu, if enabled: */
 	if (hang_debug)
 		a4xx_dump(gpu);
@@ -505,7 +507,6 @@ static const unsigned int a4xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 
 static void a4xx_dump(struct msm_gpu *gpu)
 {
-	adreno_dump(gpu);
 	printk("status:   %08x\n",
 			gpu_read(gpu, REG_A4XX_RBBM_STATUS));
 	adreno_dump(gpu);
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index bbdcab0a56c1..a1e861316590 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -249,8 +249,13 @@ void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
 }
 #endif
 
-/* would be nice to not have to duplicate the _show() stuff with printk(): */
-void adreno_dump(struct msm_gpu *gpu)
+/* Dump common gpu status and scratch registers on any hang, to make
+ * the hangcheck logs more useful.  The scratch registers seem always
+ * safe to read when GPU has hung (unlike some other regs, depending
+ * on how the GPU hung), and they are useful to match up to cmdstream
+ * dumps when debugging hangs:
+ */
+void adreno_dump_info(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int i;
@@ -266,6 +271,18 @@ void adreno_dump(struct msm_gpu *gpu)
 	printk("wptr:     %d\n", adreno_gpu->memptrs->wptr);
 	printk("rb wptr:  %d\n", get_wptr(gpu->rb));
 
+	for (i = 0; i < 8; i++) {
+		printk("CP_SCRATCH_REG%d: %u\n", i,
+			gpu_read(gpu, REG_AXXX_CP_SCRATCH_REG0 + i));
+	}
+}
+
+/* would be nice to not have to duplicate the _show() stuff with printk(): */
+void adreno_dump(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	int i;
+
 	/* dump these out in a form that can be parsed by demsm: */
 	printk("IO:region %s 00000000 00020000\n", gpu->name);
 	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index a0cc30977e67..2b6b57baf6fd 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -233,6 +233,7 @@ void adreno_idle(struct msm_gpu *gpu);
 #ifdef CONFIG_DEBUG_FS
 void adreno_show(struct msm_gpu *gpu, struct seq_file *m);
 #endif
+void adreno_dump_info(struct msm_gpu *gpu);
 void adreno_dump(struct msm_gpu *gpu);
 void adreno_wait_ring(struct msm_gpu *gpu, uint32_t ndwords);