drm/msm/gpu: Capture the GPU state on a GPU hang

Capture the GPU state on a GPU hang and store it for later playback
via the devcoredump facility. Only one crash state is stored at a
time on the assumption that the first hang is usually the most
interesting. The existing crash state can be cleared after capturing
it and then a new one will be captured on the next hang.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>

5 files changed, 32 insertions, 18 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 4cffec2b6adc..fc502e412132 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -454,7 +454,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = adreno_active_ring,
 		.irq = a3xx_irq,
 		.destroy = a3xx_destroy,
-#ifdef CONFIG_DEBUG_FS
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 		.show = adreno_show,
 #endif
 		.gpu_state_get = a3xx_gpu_state_get,
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 95f08c22e8d7..8129cf037db1 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -540,7 +540,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = adreno_active_ring,
 		.irq = a4xx_irq,
 		.destroy = a4xx_destroy,
-#ifdef CONFIG_DEBUG_FS
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 		.show = adreno_show,
 #endif
 		.gpu_state_get = a4xx_gpu_state_get,
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 5f1aab3c1cb1..16074fa6bf1e 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1243,8 +1243,10 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = a5xx_active_ring,
 		.irq = a5xx_irq,
 		.destroy = a5xx_destroy,
-#ifdef CONFIG_DEBUG_FS
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 		.show = adreno_show,
+#endif
+#if defined(CONFIG_DEBUG_FS)
 		.debugfs_init = a5xx_debugfs_init,
 #endif
 		.gpu_busy = a5xx_gpu_busy,
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 42828253ede5..c72e3afc43a8 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -378,6 +378,8 @@ struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu)
 	if (!state)
 		return ERR_PTR(-ENOMEM);
 
+	kref_init(&state->ref);
+
 	do_gettimeofday(&state->time);
 
 	for (i = 0; i < gpu->nr_rings; i++) {
@@ -414,18 +416,28 @@ struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu)
 	return state;
 }
 
-void adreno_gpu_state_put(struct msm_gpu_state *state)
+static void adreno_gpu_state_destroy(struct kref *kref)
 {
-	if (IS_ERR_OR_NULL(state))
-		return;
+	struct msm_gpu_state *state = container_of(kref,
+		struct msm_gpu_state, ref);
 
+	kfree(state->comm);
+	kfree(state->cmd);
 	kfree(state->registers);
 	kfree(state);
 }
 
-#ifdef CONFIG_DEBUG_FS
+int adreno_gpu_state_put(struct msm_gpu_state *state)
+{
+	if (IS_ERR_OR_NULL(state))
+		return 1;
+
+	return kref_put(&state->ref, adreno_gpu_state_destroy);
+}
+
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
-		struct seq_file *m)
+		struct drm_printer *p)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int i;
@@ -433,23 +445,23 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 	if (IS_ERR_OR_NULL(state))
 		return;
 
-	seq_printf(m, "status:   %08x\n", state->rbbm_status);
-	seq_printf(m, "revision: %d (%d.%d.%d.%d)\n",
+	drm_printf(p, "status:   %08x\n", state->rbbm_status);
+	drm_printf(p, "revision: %d (%d.%d.%d.%d)\n",
 			adreno_gpu->info->revn, adreno_gpu->rev.core,
 			adreno_gpu->rev.major, adreno_gpu->rev.minor,
 			adreno_gpu->rev.patchid);
 
 	for (i = 0; i < gpu->nr_rings; i++) {
-		seq_printf(m, "rb %d: fence:    %d/%d\n", i,
+		drm_printf(p, "rb %d: fence:    %d/%d\n", i,
 			state->ring[i].fence, state->ring[i].seqno);
 
-		seq_printf(m, "      rptr:     %d\n", state->ring[i].rptr);
-		seq_printf(m, "rb wptr:  %d\n", state->ring[i].wptr);
+		drm_printf(p, "      rptr:     %d\n", state->ring[i].rptr);
+		drm_printf(p, "rb wptr:  %d\n", state->ring[i].wptr);
 	}
 
-	seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name);
+	drm_printf(p, "IO:region %s 00000000 00020000\n", gpu->name);
 	for (i = 0; i < state->nr_registers; i++) {
-		seq_printf(m, "IO:R %08x %08x\n",
+		drm_printf(p, "IO:R %08x %08x\n",
 			state->registers[i * 2] << 2,
 			state->registers[(i * 2) + 1]);
 	}
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 90b6b59252af..4a868aaf1a70 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -215,9 +215,9 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		struct msm_file_private *ctx);
 void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
 bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
-#ifdef CONFIG_DEBUG_FS
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
-		struct seq_file *m);
+		struct drm_printer *p);
 #endif
 void adreno_dump_info(struct msm_gpu *gpu);
 void adreno_dump(struct msm_gpu *gpu);
@@ -231,7 +231,7 @@ void adreno_gpu_cleanup(struct adreno_gpu *gpu);
 
 
 struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu);
-void adreno_gpu_state_put(struct msm_gpu_state *state);
+int adreno_gpu_state_put(struct msm_gpu_state *state);
 
 /* ringbuffer helpers (the parts that are adreno specific) */