From 64709686dbb38f32045e117ec5a1aaf2e3a0a3c4 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Mon, 7 May 2018 16:47:50 -0600
Subject: drm/msm/gpu: Increase the pm runtime autosuspend for 5xx

Experimentation shows that resuming power quickly after suspending
ends up forcing a system hang for unknown reasons on 5xx targets.
To avoid cycling the power too much (especially during init)
turn up the autosuspend time for a5xx to 250ms and use
pm_runtime_put_autosuspend() when applicable.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/adreno/adreno_gpu.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/gpu/drm/msm/adreno/adreno_gpu.h')

diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index d6b0e7b813f4..bc9ec27e9ed8 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -84,6 +84,7 @@ struct adreno_info {
 	enum adreno_quirks quirks;
 	struct msm_gpu *(*init)(struct drm_device *dev);
 	const char *zapfw;
+	u32 inactive_period;
 };
 
 const struct adreno_info *adreno_info(struct adreno_rev rev);
-- 
cgit v1.2.3


From e00e473d9817e03cddbaf181a491c42ae8373482 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:24 -0600
Subject: drm/msm/gpu: Capture the state of the GPU

Add the infrastructure to capture the current state of the GPU and
store it in memory so that it can be dumped later.

For now grab the same basic ringbuffer information and registers
that are provided by the debugfs 'gpu' node but obviously this should
be extended to capture a much larger set of GPU information.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/adreno/a3xx_gpu.c   | 15 +++++++++
 drivers/gpu/drm/msm/adreno/a4xx_gpu.c   | 14 +++++++++
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c   | 22 +++++++++++++
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 55 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/msm/adreno/adreno_gpu.h |  3 ++
 drivers/gpu/drm/msm/msm_gpu.h           | 20 ++++++++++++
 6 files changed, 129 insertions(+)

(limited to 'drivers/gpu/drm/msm/adreno/adreno_gpu.h')

diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 3ebbeb3a9b68..b707b5bca9ab 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -427,6 +427,19 @@ static void a3xx_dump(struct msm_gpu *gpu)
 			gpu_read(gpu, REG_A3XX_RBBM_STATUS));
 	adreno_dump(gpu);
 }
+
+static struct msm_gpu_state *a3xx_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state = adreno_gpu_state_get(gpu);
+
+	if (IS_ERR(state))
+		return state;
+
+	state->rbbm_status = gpu_read(gpu, REG_A3XX_RBBM_STATUS);
+
+	return state;
+}
+
 /* Register offset defines for A3XX */
 static const unsigned int a3xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_AXXX_CP_RB_BASE),
@@ -453,6 +466,8 @@ static const struct adreno_gpu_funcs funcs = {
 #ifdef CONFIG_DEBUG_FS
 		.show = a3xx_show,
 #endif
+		.gpu_state_get = a3xx_gpu_state_get,
+		.gpu_state_put = adreno_gpu_state_put,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 16d3d596638e..17e97ebc1077 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -465,6 +465,18 @@ static void a4xx_show(struct msm_gpu *gpu, struct seq_file *m)
 }
 #endif
 
+static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state = adreno_gpu_state_get(gpu);
+
+	if (IS_ERR(state))
+		return state;
+
+	state->rbbm_status = gpu_read(gpu, REG_A4XX_RBBM_STATUS);
+
+	return state;
+}
+
 /* Register offset defines for A4XX, in order of enum adreno_regs */
 static const unsigned int a4xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_A4XX_CP_RB_BASE),
@@ -541,6 +553,8 @@ static const struct adreno_gpu_funcs funcs = {
 #ifdef CONFIG_DEBUG_FS
 		.show = a4xx_show,
 #endif
+		.gpu_state_get = a4xx_gpu_state_get,
+		.gpu_state_put = adreno_gpu_state_put,
 	},
 	.get_timestamp = a4xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index d39400e5bc42..9e85e4f7016d 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1195,6 +1195,26 @@ static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 	return 0;
 }
 
+static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state;
+
+	/*
+	 * Temporarily disable hardware clock gating before going into
+	 * adreno_show to avoid issues while reading the registers
+	 */
+	a5xx_set_hwcg(gpu, false);
+
+	state = adreno_gpu_state_get(gpu);
+
+	if (!IS_ERR(state))
+		state->rbbm_status = gpu_read(gpu, REG_A5XX_RBBM_STATUS);
+
+	a5xx_set_hwcg(gpu, true);
+
+	return state;
+}
+
 #ifdef CONFIG_DEBUG_FS
 static void a5xx_show(struct msm_gpu *gpu, struct seq_file *m)
 {
@@ -1244,6 +1264,8 @@ static const struct adreno_gpu_funcs funcs = {
 		.debugfs_init = a5xx_debugfs_init,
 #endif
 		.gpu_busy = a5xx_gpu_busy,
+		.gpu_state_get = a5xx_gpu_state_get,
+		.gpu_state_put = adreno_gpu_state_put,
 	},
 	.get_timestamp = a5xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index bcbf9f2a29f9..4286a539f40a 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -368,6 +368,61 @@ bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	return false;
 }
 
+struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct msm_gpu_state *state;
+	int i, count = 0;
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+
+	do_gettimeofday(&state->time);
+
+	for (i = 0; i < gpu->nr_rings; i++) {
+		state->ring[i].fence = gpu->rb[i]->memptrs->fence;
+		state->ring[i].iova = gpu->rb[i]->iova;
+		state->ring[i].seqno = gpu->rb[i]->seqno;
+		state->ring[i].rptr = get_rptr(adreno_gpu, gpu->rb[i]);
+		state->ring[i].wptr = get_wptr(gpu->rb[i]);
+	}
+
+	/* Count the number of registers */
+	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2)
+		count += adreno_gpu->registers[i + 1] -
+			adreno_gpu->registers[i] + 1;
+
+	state->registers = kcalloc(count * 2, sizeof(u32), GFP_KERNEL);
+	if (state->registers) {
+		int pos = 0;
+
+		for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
+			u32 start = adreno_gpu->registers[i];
+			u32 end   = adreno_gpu->registers[i + 1];
+			u32 addr;
+
+			for (addr = start; addr <= end; addr++) {
+				state->registers[pos++] = addr;
+				state->registers[pos++] = gpu_read(gpu, addr);
+			}
+		}
+
+		state->nr_registers = count;
+	}
+
+	return state;
+}
+
+void adreno_gpu_state_put(struct msm_gpu_state *state)
+{
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	kfree(state->registers);
+	kfree(state);
+}
+
 #ifdef CONFIG_DEBUG_FS
 void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
 {
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index bc9ec27e9ed8..734e31a9631f 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -229,6 +229,9 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 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);
+
 /* ringbuffer helpers (the parts that are adreno specific) */
 
 static inline void
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index b8241179175a..de71cc04ecf3 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -27,6 +27,7 @@
 
 struct msm_gem_submit;
 struct msm_gpu_perfcntr;
+struct msm_gpu_state;
 
 struct msm_gpu_config {
 	const char *ioname;
@@ -69,6 +70,8 @@ struct msm_gpu_funcs {
 	int (*debugfs_init)(struct msm_gpu *gpu, struct drm_minor *minor);
 #endif
 	int (*gpu_busy)(struct msm_gpu *gpu, uint64_t *value);
+	struct msm_gpu_state *(*gpu_state_get)(struct msm_gpu *gpu);
+	void (*gpu_state_put)(struct msm_gpu_state *state);
 };
 
 struct msm_gpu {
@@ -175,6 +178,23 @@ struct msm_gpu_submitqueue {
 	struct kref ref;
 };
 
+struct msm_gpu_state {
+	struct timeval time;
+
+	struct {
+		u64 iova;
+		u32 fence;
+		u32 seqno;
+		u32 rptr;
+		u32 wptr;
+	} ring[MSM_GPU_MAX_RINGS];
+
+	int nr_registers;
+	u32 *registers;
+
+	u32 rbbm_status;
+};
+
 static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data)
 {
 	msm_writel(data, gpu->mmio + (reg << 2));
-- 
cgit v1.2.3


From 4f776f4511c7f7b6576dfc38c609b168b9188d72 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:25 -0600
Subject: drm/msm/gpu: Convert the GPU show function to use the GPU state

Convert the existing GPU show function to use the GPU state to
dump the information rather than reading it directly from the hardware.
This will require an additional step to capture the state before
dumping it for the existing nodes but it will greatly facilitate reusing
the same code for dumping a previously captured state from a GPU hang.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/adreno/a3xx_gpu.c   | 11 +---
 drivers/gpu/drm/msm/adreno/a4xx_gpu.c   | 12 +----
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c   | 18 +------
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 30 +++++------
 drivers/gpu/drm/msm/adreno/adreno_gpu.h |  3 +-
 drivers/gpu/drm/msm/msm_debugfs.c       | 92 ++++++++++++++++++++++++++++++---
 drivers/gpu/drm/msm/msm_gpu.h           |  3 +-
 7 files changed, 104 insertions(+), 65 deletions(-)

(limited to 'drivers/gpu/drm/msm/adreno/adreno_gpu.h')

diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index b707b5bca9ab..4cffec2b6adc 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -411,15 +411,6 @@ static const unsigned int a3xx_registers[] = {
 	~0   /* sentinel */
 };
 
-#ifdef CONFIG_DEBUG_FS
-static void a3xx_show(struct msm_gpu *gpu, struct seq_file *m)
-{
-	seq_printf(m, "status:   %08x\n",
-			gpu_read(gpu, REG_A3XX_RBBM_STATUS));
-	adreno_show(gpu, m);
-}
-#endif
-
 /* would be nice to not have to duplicate the _show() stuff with printk(): */
 static void a3xx_dump(struct msm_gpu *gpu)
 {
@@ -464,7 +455,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.irq = a3xx_irq,
 		.destroy = a3xx_destroy,
 #ifdef CONFIG_DEBUG_FS
-		.show = a3xx_show,
+		.show = adreno_show,
 #endif
 		.gpu_state_get = a3xx_gpu_state_get,
 		.gpu_state_put = adreno_gpu_state_put,
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 17e97ebc1077..95f08c22e8d7 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -455,16 +455,6 @@ static const unsigned int a4xx_registers[] = {
 	~0 /* sentinel */
 };
 
-#ifdef CONFIG_DEBUG_FS
-static void a4xx_show(struct msm_gpu *gpu, struct seq_file *m)
-{
-	seq_printf(m, "status:   %08x\n",
-			gpu_read(gpu, REG_A4XX_RBBM_STATUS));
-	adreno_show(gpu, m);
-
-}
-#endif
-
 static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu)
 {
 	struct msm_gpu_state *state = adreno_gpu_state_get(gpu);
@@ -551,7 +541,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.irq = a4xx_irq,
 		.destroy = a4xx_destroy,
 #ifdef CONFIG_DEBUG_FS
-		.show = a4xx_show,
+		.show = adreno_show,
 #endif
 		.gpu_state_get = a4xx_gpu_state_get,
 		.gpu_state_put = adreno_gpu_state_put,
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 9e85e4f7016d..5f1aab3c1cb1 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1215,22 +1215,6 @@ static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
 	return state;
 }
 
-#ifdef CONFIG_DEBUG_FS
-static void a5xx_show(struct msm_gpu *gpu, struct seq_file *m)
-{
-	seq_printf(m, "status:   %08x\n",
-			gpu_read(gpu, REG_A5XX_RBBM_STATUS));
-
-	/*
-	 * Temporarily disable hardware clock gating before going into
-	 * adreno_show to avoid issues while reading the registers
-	 */
-	a5xx_set_hwcg(gpu, false);
-	adreno_show(gpu, m);
-	a5xx_set_hwcg(gpu, true);
-}
-#endif
-
 static struct msm_ringbuffer *a5xx_active_ring(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -1260,7 +1244,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.irq = a5xx_irq,
 		.destroy = a5xx_destroy,
 #ifdef CONFIG_DEBUG_FS
-		.show = a5xx_show,
+		.show = adreno_show,
 		.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 4286a539f40a..42828253ede5 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -424,38 +424,34 @@ void adreno_gpu_state_put(struct msm_gpu_state *state)
 }
 
 #ifdef CONFIG_DEBUG_FS
-void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
+void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct seq_file *m)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int i;
 
+	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",
 			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++) {
-		struct msm_ringbuffer *ring = gpu->rb[i];
-
 		seq_printf(m, "rb %d: fence:    %d/%d\n", i,
-			ring->memptrs->fence, ring->seqno);
+			state->ring[i].fence, state->ring[i].seqno);
 
-		seq_printf(m, "      rptr:     %d\n",
-			get_rptr(adreno_gpu, ring));
-		seq_printf(m, "rb wptr:  %d\n", get_wptr(ring));
+		seq_printf(m, "      rptr:     %d\n", state->ring[i].rptr);
+		seq_printf(m, "rb wptr:  %d\n", state->ring[i].wptr);
 	}
 
-	/* dump these out in a form that can be parsed by demsm: */
 	seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name);
-	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
-		uint32_t start = adreno_gpu->registers[i];
-		uint32_t end   = adreno_gpu->registers[i+1];
-		uint32_t addr;
-
-		for (addr = start; addr <= end; addr++) {
-			uint32_t val = gpu_read(gpu, addr);
-			seq_printf(m, "IO:R %08x %08x\n", addr<<2, val);
-		}
+	for (i = 0; i < state->nr_registers; i++) {
+		seq_printf(m, "IO:R %08x %08x\n",
+			state->registers[i * 2] << 2,
+			state->registers[(i * 2) + 1]);
 	}
 }
 #endif
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 734e31a9631f..90b6b59252af 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -216,7 +216,8 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 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
-void adreno_show(struct msm_gpu *gpu, struct seq_file *m);
+void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct seq_file *m);
 #endif
 void adreno_dump_info(struct msm_gpu *gpu);
 void adreno_dump(struct msm_gpu *gpu);
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index 1ff3fda245d1..c3da12179888 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -16,26 +16,100 @@
  */
 
 #ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
 #include "msm_drv.h"
 #include "msm_gpu.h"
 #include "msm_kms.h"
 #include "msm_debugfs.h"
 
-static int msm_gpu_show(struct drm_device *dev, struct seq_file *m)
+struct msm_gpu_show_priv {
+	struct msm_gpu_state *state;
+	struct drm_device *dev;
+};
+
+static int msm_gpu_show(struct seq_file *m, void *arg)
+{
+	struct msm_gpu_show_priv *show_priv = m->private;
+	struct msm_drm_private *priv = show_priv->dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+	int ret;
+
+	ret = mutex_lock_interruptible(&show_priv->dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	seq_printf(m, "%s Status:\n", gpu->name);
+	gpu->funcs->show(gpu, show_priv->state, m);
+
+	mutex_unlock(&show_priv->dev->struct_mutex);
+
+	return 0;
+}
+
+static int msm_gpu_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *m = file->private_data;
+	struct msm_gpu_show_priv *show_priv = m->private;
+	struct msm_drm_private *priv = show_priv->dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+	int ret;
+
+	ret = mutex_lock_interruptible(&show_priv->dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	gpu->funcs->gpu_state_put(show_priv->state);
+	mutex_unlock(&show_priv->dev->struct_mutex);
+
+	kfree(show_priv);
+
+	return single_release(inode, file);
+}
+
+static int msm_gpu_open(struct inode *inode, struct file *file)
 {
+	struct drm_device *dev = inode->i_private;
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gpu *gpu = priv->gpu;
+	struct msm_gpu_show_priv *show_priv;
+	int ret;
 
-	if (gpu) {
-		seq_printf(m, "%s Status:\n", gpu->name);
-		pm_runtime_get_sync(&gpu->pdev->dev);
-		gpu->funcs->show(gpu, m);
-		pm_runtime_put_sync(&gpu->pdev->dev);
+	if (!gpu)
+		return -ENODEV;
+
+	show_priv = kmalloc(sizeof(*show_priv), GFP_KERNEL);
+	if (!show_priv)
+		return -ENOMEM;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	pm_runtime_get_sync(&gpu->pdev->dev);
+	show_priv->state = gpu->funcs->gpu_state_get(gpu);
+	pm_runtime_put_sync(&gpu->pdev->dev);
+
+	mutex_unlock(&dev->struct_mutex);
+
+	if (IS_ERR(show_priv->state)) {
+		ret = PTR_ERR(show_priv->state);
+		kfree(show_priv);
+		return ret;
 	}
 
-	return 0;
+	show_priv->dev = dev;
+
+	return single_open(file, msm_gpu_show, show_priv);
 }
 
+static const struct file_operations msm_gpu_fops = {
+	.owner = THIS_MODULE,
+	.open = msm_gpu_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = msm_gpu_release,
+};
+
 static int msm_gem_show(struct drm_device *dev, struct seq_file *m)
 {
 	struct msm_drm_private *priv = dev->dev_private;
@@ -105,7 +179,6 @@ static int show_locked(struct seq_file *m, void *arg)
 }
 
 static struct drm_info_list msm_debugfs_list[] = {
-		{"gpu", show_locked, 0, msm_gpu_show},
 		{"gem", show_locked, 0, msm_gem_show},
 		{ "mm", show_locked, 0, msm_mm_show },
 		{ "fb", show_locked, 0, msm_fb_show },
@@ -158,6 +231,9 @@ int msm_debugfs_init(struct drm_minor *minor)
 		return ret;
 	}
 
+	debugfs_create_file("gpu", S_IRUSR, minor->debugfs_root,
+		dev, &msm_gpu_fops);
+
 	if (priv->kms->funcs->debugfs_init) {
 		ret = priv->kms->funcs->debugfs_init(priv->kms, minor);
 		if (ret)
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index de71cc04ecf3..d204eca8518e 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -65,7 +65,8 @@ struct msm_gpu_funcs {
 	void (*destroy)(struct msm_gpu *gpu);
 #ifdef CONFIG_DEBUG_FS
 	/* show GPU status in debugfs: */
-	void (*show)(struct msm_gpu *gpu, struct seq_file *m);
+	void (*show)(struct msm_gpu *gpu, struct msm_gpu_state *state,
+			struct seq_file *m);
 	/* for generation specific debugfs: */
 	int (*debugfs_init)(struct msm_gpu *gpu, struct drm_minor *minor);
 #endif
-- 
cgit v1.2.3


From c0fec7f562ec76404ef0f074a89113a703587f3d Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:27 -0600
Subject: 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>
---
 drivers/gpu/drm/msm/Kconfig             |  1 +
 drivers/gpu/drm/msm/adreno/a3xx_gpu.c   |  2 +-
 drivers/gpu/drm/msm/adreno/a4xx_gpu.c   |  2 +-
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c   |  4 +-
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 36 +++++++++-----
 drivers/gpu/drm/msm/adreno/adreno_gpu.h |  6 +--
 drivers/gpu/drm/msm/msm_debugfs.c       |  5 +-
 drivers/gpu/drm/msm/msm_gpu.c           | 83 ++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/msm/msm_gpu.h           | 38 ++++++++++++++-
 9 files changed, 154 insertions(+), 23 deletions(-)

(limited to 'drivers/gpu/drm/msm/adreno/adreno_gpu.h')

diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 38cbde971b48..843a9d40c05e 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -12,6 +12,7 @@ config DRM_MSM
 	select SHMEM
 	select TMPFS
 	select QCOM_SCM
+	select WANT_DEV_COREDUMP
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	select SYNC_FILE
 	select PM_OPP
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) */
 
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index c3da12179888..f0da0d3c8a80 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -29,6 +29,7 @@ struct msm_gpu_show_priv {
 
 static int msm_gpu_show(struct seq_file *m, void *arg)
 {
+	struct drm_printer p = drm_seq_file_printer(m);
 	struct msm_gpu_show_priv *show_priv = m->private;
 	struct msm_drm_private *priv = show_priv->dev->dev_private;
 	struct msm_gpu *gpu = priv->gpu;
@@ -38,8 +39,8 @@ static int msm_gpu_show(struct seq_file *m, void *arg)
 	if (ret)
 		return ret;
 
-	seq_printf(m, "%s Status:\n", gpu->name);
-	gpu->funcs->show(gpu, show_priv->state, m);
+	drm_printf(&p, "%s Status:\n", gpu->name);
+	gpu->funcs->show(gpu, show_priv->state, &p);
 
 	mutex_unlock(&show_priv->dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 03ba8872cc99..5f39549d9a8b 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -20,10 +20,11 @@
 #include "msm_mmu.h"
 #include "msm_fence.h"
 
+#include <generated/utsrelease.h>
 #include <linux/string_helpers.h>
 #include <linux/pm_opp.h>
 #include <linux/devfreq.h>
-
+#include <linux/devcoredump.h>
 
 /*
  * Power Management:
@@ -273,6 +274,81 @@ int msm_gpu_hw_init(struct msm_gpu *gpu)
 	return ret;
 }
 
+#ifdef CONFIG_DEV_COREDUMP
+static ssize_t msm_gpu_devcoredump_read(char *buffer, loff_t offset,
+		size_t count, void *data, size_t datalen)
+{
+	struct msm_gpu *gpu = data;
+	struct drm_print_iterator iter;
+	struct drm_printer p;
+	struct msm_gpu_state *state;
+
+	state = msm_gpu_crashstate_get(gpu);
+	if (!state)
+		return 0;
+
+	iter.data = buffer;
+	iter.offset = 0;
+	iter.start = offset;
+	iter.remain = count;
+
+	p = drm_coredump_printer(&iter);
+
+	drm_printf(&p, "---\n");
+	drm_printf(&p, "kernel: " UTS_RELEASE "\n");
+	drm_printf(&p, "module: " KBUILD_MODNAME "\n");
+	drm_printf(&p, "time: %ld.%ld\n",
+		state->time.tv_sec, state->time.tv_usec);
+	if (state->comm)
+		drm_printf(&p, "comm: %s\n", state->comm);
+	if (state->cmd)
+		drm_printf(&p, "cmdline: %s\n", state->cmd);
+
+	gpu->funcs->show(gpu, state, &p);
+
+	msm_gpu_crashstate_put(gpu);
+
+	return count - iter.remain;
+}
+
+static void msm_gpu_devcoredump_free(void *data)
+{
+	struct msm_gpu *gpu = data;
+
+	msm_gpu_crashstate_put(gpu);
+}
+
+static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, char *comm,
+		char *cmd)
+{
+	struct msm_gpu_state *state;
+
+	/* Only save one crash state at a time */
+	if (gpu->crashstate)
+		return;
+
+	state = gpu->funcs->gpu_state_get(gpu);
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	/* Fill in the additional crash state information */
+	state->comm = kstrdup(comm, GFP_KERNEL);
+	state->cmd = kstrdup(cmd, GFP_KERNEL);
+
+	/* Set the active crash state to be dumped on failure */
+	gpu->crashstate = state;
+
+	/* FIXME: Release the crashstate if this errors out? */
+	dev_coredumpm(gpu->dev->dev, THIS_MODULE, gpu, 0, GFP_KERNEL,
+		msm_gpu_devcoredump_read, msm_gpu_devcoredump_free);
+}
+#else
+static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, char *comm,
+		char *cmd)
+{
+}
+#endif
+
 /*
  * Hangcheck detection for locked gpu:
  */
@@ -356,6 +432,11 @@ static void recover_worker(struct work_struct *work)
 			msm_rd_dump_submit(priv->hangrd, submit, NULL);
 	}
 
+	/* Record the crash state */
+	pm_runtime_get_sync(&gpu->pdev->dev);
+	msm_gpu_crashstate_capture(gpu, comm, cmd);
+	pm_runtime_put_sync(&gpu->pdev->dev);
+
 	kfree(cmd);
 	kfree(comm);
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index d204eca8518e..b1cb44922441 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -66,13 +66,13 @@ struct msm_gpu_funcs {
 #ifdef CONFIG_DEBUG_FS
 	/* show GPU status in debugfs: */
 	void (*show)(struct msm_gpu *gpu, struct msm_gpu_state *state,
-			struct seq_file *m);
+			struct drm_printer *p);
 	/* for generation specific debugfs: */
 	int (*debugfs_init)(struct msm_gpu *gpu, struct drm_minor *minor);
 #endif
 	int (*gpu_busy)(struct msm_gpu *gpu, uint64_t *value);
 	struct msm_gpu_state *(*gpu_state_get)(struct msm_gpu *gpu);
-	void (*gpu_state_put)(struct msm_gpu_state *state);
+	int (*gpu_state_put)(struct msm_gpu_state *state);
 };
 
 struct msm_gpu {
@@ -133,6 +133,8 @@ struct msm_gpu {
 		u64 busy_cycles;
 		ktime_t time;
 	} devfreq;
+
+	struct msm_gpu_state *crashstate;
 };
 
 /* It turns out that all targets use the same ringbuffer size */
@@ -180,6 +182,7 @@ struct msm_gpu_submitqueue {
 };
 
 struct msm_gpu_state {
+	struct kref ref;
 	struct timeval time;
 
 	struct {
@@ -194,6 +197,9 @@ struct msm_gpu_state {
 	u32 *registers;
 
 	u32 rbbm_status;
+
+	char *comm;
+	char *cmd;
 };
 
 static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data)
@@ -275,4 +281,32 @@ static inline void msm_submitqueue_put(struct msm_gpu_submitqueue *queue)
 		kref_put(&queue->ref, msm_submitqueue_destroy);
 }
 
+static inline struct msm_gpu_state *msm_gpu_crashstate_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state = NULL;
+
+	mutex_lock(&gpu->dev->struct_mutex);
+
+	if (gpu->crashstate) {
+		kref_get(&gpu->crashstate->ref);
+		state = gpu->crashstate;
+	}
+
+	mutex_unlock(&gpu->dev->struct_mutex);
+
+	return state;
+}
+
+static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
+{
+	mutex_lock(&gpu->dev->struct_mutex);
+
+	if (gpu->crashstate) {
+		if (gpu->funcs->gpu_state_put(gpu->crashstate))
+			gpu->crashstate = NULL;
+	}
+
+	mutex_unlock(&gpu->dev->struct_mutex);
+}
+
 #endif /* __MSM_GPU_H__ */
-- 
cgit v1.2.3


From 50f8d21863b9b774b198e631d2b14878f6a54b5b Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:30 -0600
Subject: drm/msm/adreno: Add a5xx specific registers for the GPU state

HLSQ, SP and TP registers are only accessible from a special
aperture and to make matters worse the aperture is blocked from
the CPU on targets that can support secure rendering. Luckily the
GPU hardware has its own purpose built register dumper that can
access the registers from the aperture. Add a5xx specific code
to program the crashdumper and retrieve the wayward registers
and dump them for the crash state.

Also, remove a block of registers the regular CPU accessible
list that aren't useful for debug which helps reduce the size
of the crash state file by a goodly amount.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 Documentation/gpu/msm-crash-dump.rst    |   4 +
 drivers/gpu/drm/msm/adreno/a3xx_gpu.c   |   8 +-
 drivers/gpu/drm/msm/adreno/a4xx_gpu.c   |   8 +-
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c   | 236 ++++++++++++++++++++++++++++++--
 drivers/gpu/drm/msm/adreno/adreno_gpu.c |  23 ++--
 drivers/gpu/drm/msm/adreno/adreno_gpu.h |   4 +-
 6 files changed, 252 insertions(+), 31 deletions(-)

(limited to 'drivers/gpu/drm/msm/adreno/adreno_gpu.h')

diff --git a/Documentation/gpu/msm-crash-dump.rst b/Documentation/gpu/msm-crash-dump.rst
index 35e87004e006..7943f43f70d6 100644
--- a/Documentation/gpu/msm-crash-dump.rst
+++ b/Documentation/gpu/msm-crash-dump.rst
@@ -76,3 +76,7 @@ registers
 
 	value
 		Hexadecimal value of the register.
+
+registers-hlsq
+		(5xx only) Register values from the HLSQ aperture.
+		Same format as the register section.
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index fc502e412132..669c2d4b070d 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -421,10 +421,12 @@ static void a3xx_dump(struct msm_gpu *gpu)
 
 static struct msm_gpu_state *a3xx_gpu_state_get(struct msm_gpu *gpu)
 {
-	struct msm_gpu_state *state = adreno_gpu_state_get(gpu);
+	struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
 
-	if (IS_ERR(state))
-		return state;
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+
+	adreno_gpu_state_get(gpu, state);
 
 	state->rbbm_status = gpu_read(gpu, REG_A3XX_RBBM_STATUS);
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 8129cf037db1..7c4e6dc1ed59 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -457,10 +457,12 @@ static const unsigned int a4xx_registers[] = {
 
 static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu)
 {
-	struct msm_gpu_state *state = adreno_gpu_state_get(gpu);
+	struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
 
-	if (IS_ERR(state))
-		return state;
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+
+	adreno_gpu_state_get(gpu, state);
 
 	state->rbbm_status = gpu_read(gpu, REG_A4XX_RBBM_STATUS);
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 16074fa6bf1e..bd84f71d27d8 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -19,6 +19,7 @@
 #include <linux/soc/qcom/mdt_loader.h>
 #include <linux/pm_opp.h>
 #include <linux/nvmem-consumer.h>
+#include <linux/iopoll.h>
 #include "msm_gem.h"
 #include "msm_mmu.h"
 #include "a5xx_gpu.h"
@@ -1123,8 +1124,9 @@ static const u32 a5xx_registers[] = {
 	0xE800, 0xE806, 0xE810, 0xE89A, 0xE8A0, 0xE8A4, 0xE8AA, 0xE8EB,
 	0xE900, 0xE905, 0xEB80, 0xEB8F, 0xEBB0, 0xEBB0, 0xEC00, 0xEC05,
 	0xEC08, 0xECE9, 0xECF0, 0xECF0, 0xEA80, 0xEA80, 0xEA82, 0xEAA3,
-	0xEAA5, 0xEAC2, 0xA800, 0xA8FF, 0xAC60, 0xAC60, 0xB000, 0xB97F,
-	0xB9A0, 0xB9BF, ~0
+	0xEAA5, 0xEAC2, 0xA800, 0xA800, 0xA820, 0xA828, 0xA840, 0xA87D,
+	0XA880, 0xA88D, 0xA890, 0xA8A3, 0xA8D0, 0xA8D8, 0xA8E0, 0xA8F5,
+	0xAC60, 0xAC60, ~0,
 };
 
 static void a5xx_dump(struct msm_gpu *gpu)
@@ -1195,25 +1197,233 @@ static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 	return 0;
 }
 
+struct a5xx_crashdumper {
+	void *ptr;
+	struct drm_gem_object *bo;
+	u64 iova;
+};
+
+struct a5xx_gpu_state {
+	struct msm_gpu_state base;
+	u32 *hlsqregs;
+};
+
+#define gpu_poll_timeout(gpu, addr, val, cond, interval, timeout) \
+	readl_poll_timeout((gpu)->mmio + ((addr) << 2), val, cond, \
+		interval, timeout)
+
+static int a5xx_crashdumper_init(struct msm_gpu *gpu,
+		struct a5xx_crashdumper *dumper)
+{
+	dumper->ptr = msm_gem_kernel_new_locked(gpu->dev,
+		SZ_1M, MSM_BO_UNCACHED, gpu->aspace,
+		&dumper->bo, &dumper->iova);
+
+	if (IS_ERR(dumper->ptr))
+		return PTR_ERR(dumper->ptr);
+
+	return 0;
+}
+
+static void a5xx_crashdumper_free(struct msm_gpu *gpu,
+		struct a5xx_crashdumper *dumper)
+{
+	msm_gem_put_iova(dumper->bo, gpu->aspace);
+	msm_gem_put_vaddr(dumper->bo);
+
+	drm_gem_object_unreference(dumper->bo);
+}
+
+static int a5xx_crashdumper_run(struct msm_gpu *gpu,
+		struct a5xx_crashdumper *dumper)
+{
+	u32 val;
+
+	if (IS_ERR_OR_NULL(dumper->ptr))
+		return -EINVAL;
+
+	gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO,
+		REG_A5XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova);
+
+	gpu_write(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, 1);
+
+	return gpu_poll_timeout(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, val,
+		val & 0x04, 100, 10000);
+}
+
+/*
+ * These are a list of the registers that need to be read through the HLSQ
+ * aperture through the crashdumper.  These are not nominally accessible from
+ * the CPU on a secure platform.
+ */
+static const struct {
+	u32 type;
+	u32 regoffset;
+	u32 count;
+} a5xx_hlsq_aperture_regs[] = {
+	{ 0x35, 0xe00, 0x32 },   /* HSLQ non-context */
+	{ 0x31, 0x2080, 0x1 },   /* HLSQ 2D context 0 */
+	{ 0x33, 0x2480, 0x1 },   /* HLSQ 2D context 1 */
+	{ 0x32, 0xe780, 0x62 },  /* HLSQ 3D context 0 */
+	{ 0x34, 0xef80, 0x62 },  /* HLSQ 3D context 1 */
+	{ 0x3f, 0x0ec0, 0x40 },  /* SP non-context */
+	{ 0x3d, 0x2040, 0x1 },   /* SP 2D context 0 */
+	{ 0x3b, 0x2440, 0x1 },   /* SP 2D context 1 */
+	{ 0x3e, 0xe580, 0x170 }, /* SP 3D context 0 */
+	{ 0x3c, 0xed80, 0x170 }, /* SP 3D context 1 */
+	{ 0x3a, 0x0f00, 0x1c },  /* TP non-context */
+	{ 0x38, 0x2000, 0xa },   /* TP 2D context 0 */
+	{ 0x36, 0x2400, 0xa },   /* TP 2D context 1 */
+	{ 0x39, 0xe700, 0x80 },  /* TP 3D context 0 */
+	{ 0x37, 0xef00, 0x80 },  /* TP 3D context 1 */
+};
+
+static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
+		struct a5xx_gpu_state *a5xx_state)
+{
+	struct a5xx_crashdumper dumper = { 0 };
+	u32 offset, count = 0;
+	u64 *ptr;
+	int i;
+
+	if (a5xx_crashdumper_init(gpu, &dumper))
+		return;
+
+	/* The script will be written at offset 0 */
+	ptr = dumper.ptr;
+
+	/* Start writing the data at offset 256k */
+	offset = dumper.iova + (256 * SZ_1K);
+
+	/* Count how many additional registers to get from the HLSQ aperture */
+	for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++)
+		count += a5xx_hlsq_aperture_regs[i].count;
+
+	a5xx_state->hlsqregs = kcalloc(count, sizeof(u32), GFP_KERNEL);
+	if (!a5xx_state->hlsqregs)
+		return;
+
+	/* Build the crashdump script */
+	for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++) {
+		u32 type = a5xx_hlsq_aperture_regs[i].type;
+		u32 c = a5xx_hlsq_aperture_regs[i].count;
+
+		/* Write the register to select the desired bank */
+		*ptr++ = ((u64) type << 8);
+		*ptr++ = (((u64) REG_A5XX_HLSQ_DBG_READ_SEL) << 44) |
+			(1 << 21) | 1;
+
+		*ptr++ = offset;
+		*ptr++ = (((u64) REG_A5XX_HLSQ_DBG_AHB_READ_APERTURE) << 44)
+			| c;
+
+		offset += c * sizeof(u32);
+	}
+
+	/* Write two zeros to close off the script */
+	*ptr++ = 0;
+	*ptr++ = 0;
+
+	if (a5xx_crashdumper_run(gpu, &dumper)) {
+		kfree(a5xx_state->hlsqregs);
+		a5xx_crashdumper_free(gpu, &dumper);
+		return;
+	}
+
+	/* Copy the data from the crashdumper to the state */
+	memcpy(a5xx_state->hlsqregs, dumper.ptr + (256 * SZ_1K),
+		count * sizeof(u32));
+
+	a5xx_crashdumper_free(gpu, &dumper);
+}
+
 static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
 {
-	struct msm_gpu_state *state;
+	struct a5xx_gpu_state *a5xx_state = kzalloc(sizeof(*a5xx_state),
+			GFP_KERNEL);
 
-	/*
-	 * Temporarily disable hardware clock gating before going into
-	 * adreno_show to avoid issues while reading the registers
-	 */
+	if (!a5xx_state)
+		return ERR_PTR(-ENOMEM);
+
+	/* Temporarily disable hardware clock gating before reading the hw */
 	a5xx_set_hwcg(gpu, false);
 
-	state = adreno_gpu_state_get(gpu);
+	/* First get the generic state from the adreno core */
+	adreno_gpu_state_get(gpu, &(a5xx_state->base));
+
+	a5xx_state->base.rbbm_status = gpu_read(gpu, REG_A5XX_RBBM_STATUS);
 
-	if (!IS_ERR(state))
-		state->rbbm_status = gpu_read(gpu, REG_A5XX_RBBM_STATUS);
+	/* Get the HLSQ regs with the help of the crashdumper */
+	a5xx_gpu_state_get_hlsq_regs(gpu, a5xx_state);
 
 	a5xx_set_hwcg(gpu, true);
 
-	return state;
+	return &a5xx_state->base;
+}
+
+static void a5xx_gpu_state_destroy(struct kref *kref)
+{
+	struct msm_gpu_state *state = container_of(kref,
+		struct msm_gpu_state, ref);
+	struct a5xx_gpu_state *a5xx_state = container_of(state,
+		struct a5xx_gpu_state, base);
+
+	kfree(a5xx_state->hlsqregs);
+
+	adreno_gpu_state_destroy(state);
+	kfree(a5xx_state);
+}
+
+int a5xx_gpu_state_put(struct msm_gpu_state *state)
+{
+	if (IS_ERR_OR_NULL(state))
+		return 1;
+
+	return kref_put(&state->ref, a5xx_gpu_state_destroy);
+}
+
+
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+void a5xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct drm_printer *p)
+{
+	int i, j;
+	u32 pos = 0;
+	struct a5xx_gpu_state *a5xx_state = container_of(state,
+		struct a5xx_gpu_state, base);
+
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	adreno_show(gpu, state, p);
+
+	/* Dump the additional a5xx HLSQ registers */
+	if (!a5xx_state->hlsqregs)
+		return;
+
+	drm_printf(p, "registers-hlsq:\n");
+
+	for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++) {
+		u32 o = a5xx_hlsq_aperture_regs[i].regoffset;
+		u32 c = a5xx_hlsq_aperture_regs[i].count;
+
+		for (j = 0; j < c; j++, pos++, o++) {
+			/*
+			 * To keep the crashdump simple we pull the entire range
+			 * for each register type but not all of the registers
+			 * in the range are valid. Fortunately invalid registers
+			 * stick out like a sore thumb with a value of
+			 * 0xdeadbeef
+			 */
+			if (a5xx_state->hlsqregs[pos] == 0xdeadbeef)
+				continue;
+
+			drm_printf(p, "  - { offset: 0x%04x, value: 0x%08x }\n",
+				o << 2, a5xx_state->hlsqregs[pos]);
+		}
+	}
 }
+#endif
 
 static struct msm_ringbuffer *a5xx_active_ring(struct msm_gpu *gpu)
 {
@@ -1244,14 +1454,14 @@ static const struct adreno_gpu_funcs funcs = {
 		.irq = a5xx_irq,
 		.destroy = a5xx_destroy,
 #if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
-		.show = adreno_show,
+		.show = a5xx_show,
 #endif
 #if defined(CONFIG_DEBUG_FS)
 		.debugfs_init = a5xx_debugfs_init,
 #endif
 		.gpu_busy = a5xx_gpu_busy,
 		.gpu_state_get = a5xx_gpu_state_get,
-		.gpu_state_put = adreno_gpu_state_put,
+		.gpu_state_put = a5xx_gpu_state_put,
 	},
 	.get_timestamp = a5xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 808d4fc9c4a1..cd418dab7a62 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -369,16 +369,11 @@ bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	return false;
 }
 
-struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu)
+int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	struct msm_gpu_state *state;
 	int i, count = 0;
 
-	state = kzalloc(sizeof(*state), GFP_KERNEL);
-	if (!state)
-		return ERR_PTR(-ENOMEM);
-
 	kref_init(&state->ref);
 
 	do_gettimeofday(&state->time);
@@ -432,14 +427,12 @@ struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu)
 		state->nr_registers = count;
 	}
 
-	return state;
+	return 0;
 }
 
-static void adreno_gpu_state_destroy(struct kref *kref)
+void adreno_gpu_state_destroy(struct msm_gpu_state *state)
 {
 	int i;
-	struct msm_gpu_state *state = container_of(kref,
-		struct msm_gpu_state, ref);
 
 	for (i = 0; i < ARRAY_SIZE(state->ring); i++)
 		kfree(state->ring[i].data);
@@ -447,6 +440,14 @@ static void adreno_gpu_state_destroy(struct kref *kref)
 	kfree(state->comm);
 	kfree(state->cmd);
 	kfree(state->registers);
+}
+
+static void adreno_gpu_state_kref_destroy(struct kref *kref)
+{
+	struct msm_gpu_state *state = container_of(kref,
+		struct msm_gpu_state, ref);
+
+	adreno_gpu_state_destroy(state);
 	kfree(state);
 }
 
@@ -455,7 +456,7 @@ 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);
+	return kref_put(&state->ref, adreno_gpu_state_kref_destroy);
 }
 
 #if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 4a868aaf1a70..4406776597fd 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -230,7 +230,9 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 void adreno_gpu_cleanup(struct adreno_gpu *gpu);
 
 
-struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu);
+void adreno_gpu_state_destroy(struct msm_gpu_state *state);
+
+int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state);
 int adreno_gpu_state_put(struct msm_gpu_state *state);
 
 /* ringbuffer helpers (the parts that are adreno specific) */
-- 
cgit v1.2.3