diff mbox

[10/13] drm/msm/adreno: Convert the show/crash file format

Message ID 20180712185930.2492-11-jcrouse@codeaurora.org (mailing list archive)
State New, archived
Headers show

Commit Message

Jordan Crouse July 12, 2018, 6:59 p.m. UTC
Convert the format of the 'show' debugfs file and the crash
dump to a  format resembling YAML. This should be easier to
parse and be more flexible for future changes and expansions.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
---
 Documentation/gpu/drm-msm-crash-dump.txt | 46 ++++++++++++++++++++++++
 drivers/gpu/drm/msm/adreno/adreno_gpu.c  | 20 ++++++-----
 2 files changed, 58 insertions(+), 8 deletions(-)
 create mode 100644 Documentation/gpu/drm-msm-crash-dump.txt

Comments

Daniel Vetter July 12, 2018, 7:51 p.m. UTC | #1
On Thu, Jul 12, 2018 at 12:59:27PM -0600, Jordan Crouse wrote:
> Convert the format of the 'show' debugfs file and the crash
> dump to a  format resembling YAML. This should be easier to
> parse and be more flexible for future changes and expansions.
> 
> Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
> ---
>  Documentation/gpu/drm-msm-crash-dump.txt | 46 ++++++++++++++++++++++++

.rst would be  nice, plus including it some msm.rst overview file like we
have for other drivers. For drivers we also tend to omit the drm prefix in
the documentation.
-Daniel

>  drivers/gpu/drm/msm/adreno/adreno_gpu.c  | 20 ++++++-----
>  2 files changed, 58 insertions(+), 8 deletions(-)
>  create mode 100644 Documentation/gpu/drm-msm-crash-dump.txt
> 
> diff --git a/Documentation/gpu/drm-msm-crash-dump.txt b/Documentation/gpu/drm-msm-crash-dump.txt
> new file mode 100644
> index 000000000000..930e4c970a62
> --- /dev/null
> +++ b/Documentation/gpu/drm-msm-crash-dump.txt
> @@ -0,0 +1,46 @@
> +# drm/msm GPU crash dump format
> +#
> +# This is a description of the format of the drm/msm GPU crash dump format that
> +# can be read from /sys/kernel/dri/X/show or from devcoredump following a GPU
> +# hang or fault
> +
> +---
> +kernel:		# [string] The kernel version as printed by UTS_RELEASE
> +module:		# [string] The module that generated the crash dump
> +time:		# [seconds.microseconds] The kernel time at crash
> +comm:		# [string] comm string for the binary that generated the fault
> +		# (if known)
> +cmdline:	# [string] the cmdline for the binary that generated the fault
> +		# (if known)
> +revision:	# [ id core.major.minor.patchlevel] The GPU id followed by the
> +		# individual components of the id separated by dots
> +rbbm-status:	# [hex] The current value of RBBM_STATUS which shows what GPU
> +		# components were in use at the time of the crash
> +ringbuffer:	# Ringbuffer data. There will be a sequence for each ringbuffer
> +  -id:			# [decimal] Ringbuffer identifier (0 based index)
> +   last-fence:		# [decimal] The last fence issued on the ring
> +   retired-fence:	# [decimal] THe last fence retired on the ring
> +   rptr:		# [decimal] The current read pointer (rptr) for the ring
> +   wptr:		# [decimal] The current write pointer (wptr) for the
> +			# ring
> +   size:		# [decimal] The maximum size of the ring programmed in
> +			# the hardware
> +   data:		# [ascii85] The contents of the ring encoded as ascii85.
> +			# Only the unused portions of the ring will be printed
> +			# (up to a maximum of 'size' bytes)
> +bos:		# List of buffers from the hanging submission (if known)
> +  -iova:		# [hex] GPU address of the buffer
> +   size:		# [decimal] Size of the buffer (in bytes)
> +   data:		# [ascii85] The contents of the buffer encoded as
> +			# ascii85. Only the contents of buffers marked as
> +			# readable are dumped. Trailing zeros at the end of the
> +			# buffer won't be dumped.
> +registers:	# Sets of register values. This section can be used multiple
> +		# times for different ranges of registers. Each register will be
> +		# on its own line.
> +  - [offset, value]	# offset: [hex] byte offset of the register
> +			# value: [hex] value of the register
> +
> +registers-hlsq: # (5xx only) Same format as registers. Register data that
> +		# only accessible from the HLSQ aperture captured by the
> +		# HW based crashdumper
> diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
> index 163542487e2c..15fe0d029ba6 100644
> --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
> @@ -444,23 +444,27 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
>  	if (IS_ERR_OR_NULL(state))
>  		return;
>  
> -	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++) {
> -		drm_printf(p, "rb %d: fence:    %d/%d\n", i,
> -			state->ring[i].fence, state->ring[i].seqno);
> +	drm_printf(p, "rbbm-status: 0x%08x\n", state->rbbm_status);
> +
> +	drm_puts(p, "ringbuffer:\n");
>  
> -		drm_printf(p, "      rptr:     %d\n", state->ring[i].rptr);
> -		drm_printf(p, "rb wptr:  %d\n", state->ring[i].wptr);
> +	for (i = 0; i < gpu->nr_rings; i++) {
> +		drm_printf(p, "  - id: %d\n", i);
> +		drm_printf(p, "    last-fence: %d\n", state->ring[i].seqno);
> +		drm_printf(p, "    retired-fence: %d\n", state->ring[i].fence);
> +		drm_printf(p, "    rptr: %d\n", state->ring[i].rptr);
> +		drm_printf(p, "    wptr: %d\n", state->ring[i].wptr);
>  	}
>  
> -	drm_printf(p, "IO:region %s 00000000 00020000\n", gpu->name);
> +	drm_puts(p, "registers:\n");
> +
>  	for (i = 0; i < state->nr_registers; i++) {
> -		drm_printf(p, "IO:R %08x %08x\n",
> +		drm_printf(p, "  - { offset: 0x%04x, value: 0x%08x }\n",
>  			state->registers[i * 2] << 2,
>  			state->registers[(i * 2) + 1]);
>  	}
> -- 
> 2.17.1
> 
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/dri-devel
diff mbox

Patch

diff --git a/Documentation/gpu/drm-msm-crash-dump.txt b/Documentation/gpu/drm-msm-crash-dump.txt
new file mode 100644
index 000000000000..930e4c970a62
--- /dev/null
+++ b/Documentation/gpu/drm-msm-crash-dump.txt
@@ -0,0 +1,46 @@ 
+# drm/msm GPU crash dump format
+#
+# This is a description of the format of the drm/msm GPU crash dump format that
+# can be read from /sys/kernel/dri/X/show or from devcoredump following a GPU
+# hang or fault
+
+---
+kernel:		# [string] The kernel version as printed by UTS_RELEASE
+module:		# [string] The module that generated the crash dump
+time:		# [seconds.microseconds] The kernel time at crash
+comm:		# [string] comm string for the binary that generated the fault
+		# (if known)
+cmdline:	# [string] the cmdline for the binary that generated the fault
+		# (if known)
+revision:	# [ id core.major.minor.patchlevel] The GPU id followed by the
+		# individual components of the id separated by dots
+rbbm-status:	# [hex] The current value of RBBM_STATUS which shows what GPU
+		# components were in use at the time of the crash
+ringbuffer:	# Ringbuffer data. There will be a sequence for each ringbuffer
+  -id:			# [decimal] Ringbuffer identifier (0 based index)
+   last-fence:		# [decimal] The last fence issued on the ring
+   retired-fence:	# [decimal] THe last fence retired on the ring
+   rptr:		# [decimal] The current read pointer (rptr) for the ring
+   wptr:		# [decimal] The current write pointer (wptr) for the
+			# ring
+   size:		# [decimal] The maximum size of the ring programmed in
+			# the hardware
+   data:		# [ascii85] The contents of the ring encoded as ascii85.
+			# Only the unused portions of the ring will be printed
+			# (up to a maximum of 'size' bytes)
+bos:		# List of buffers from the hanging submission (if known)
+  -iova:		# [hex] GPU address of the buffer
+   size:		# [decimal] Size of the buffer (in bytes)
+   data:		# [ascii85] The contents of the buffer encoded as
+			# ascii85. Only the contents of buffers marked as
+			# readable are dumped. Trailing zeros at the end of the
+			# buffer won't be dumped.
+registers:	# Sets of register values. This section can be used multiple
+		# times for different ranges of registers. Each register will be
+		# on its own line.
+  - [offset, value]	# offset: [hex] byte offset of the register
+			# value: [hex] value of the register
+
+registers-hlsq: # (5xx only) Same format as registers. Register data that
+		# only accessible from the HLSQ aperture captured by the
+		# HW based crashdumper
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 163542487e2c..15fe0d029ba6 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -444,23 +444,27 @@  void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 	if (IS_ERR_OR_NULL(state))
 		return;
 
-	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++) {
-		drm_printf(p, "rb %d: fence:    %d/%d\n", i,
-			state->ring[i].fence, state->ring[i].seqno);
+	drm_printf(p, "rbbm-status: 0x%08x\n", state->rbbm_status);
+
+	drm_puts(p, "ringbuffer:\n");
 
-		drm_printf(p, "      rptr:     %d\n", state->ring[i].rptr);
-		drm_printf(p, "rb wptr:  %d\n", state->ring[i].wptr);
+	for (i = 0; i < gpu->nr_rings; i++) {
+		drm_printf(p, "  - id: %d\n", i);
+		drm_printf(p, "    last-fence: %d\n", state->ring[i].seqno);
+		drm_printf(p, "    retired-fence: %d\n", state->ring[i].fence);
+		drm_printf(p, "    rptr: %d\n", state->ring[i].rptr);
+		drm_printf(p, "    wptr: %d\n", state->ring[i].wptr);
 	}
 
-	drm_printf(p, "IO:region %s 00000000 00020000\n", gpu->name);
+	drm_puts(p, "registers:\n");
+
 	for (i = 0; i < state->nr_registers; i++) {
-		drm_printf(p, "IO:R %08x %08x\n",
+		drm_printf(p, "  - { offset: 0x%04x, value: 0x%08x }\n",
 			state->registers[i * 2] << 2,
 			state->registers[(i * 2) + 1]);
 	}