drm/msm/adreno: dump scratch regs and other info on hang

Dump a bit more info when the GPU hangs, without having hang_debug
enabled (which dumps a *lot* of registers).  Also dump the scratch
registers, as they are useful for determining where in the cmdstream
the GPU hung (and they seem always safe to read when GPU has hung).

Note that the freedreno gallium driver emits increasing counter values
to SCRATCH6 (to identify tile #) and SCRATCH7 (to identify draw #), so
these two in particular can be used to "triangulate" where in the
cmdstream the GPU hung.
Signed-off-by: Rob Clark <robdclark@gmail.com>

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);

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);

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) {

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);