[PATCH 1/2] drm/radeon/benchmark: make sure bo blit copy exists before using it

[PATCH 1/2] drm/radeon/benchmark: make sure bo blit copy exists before using it

[alexdeucher]

From: Alex Deucher <alexander.deucher@amd.com>

Fixes a segfault on asics without a blit callback.

Fixes:
https://bugs.freedesktop.org/show_bug.cgi?id=62239

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/radeon/radeon_benchmark.c |   16 +++++++++-------
 1 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
index bedda9c..a2f0c24 100644
--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -135,13 +135,15 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
 						     sdomain, ddomain, "dma");
 	}
 
-	time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
-					RADEON_BENCHMARK_COPY_BLIT, n);
-	if (time < 0)
-		goto out_cleanup;
-	if (time > 0)
-		radeon_benchmark_log_results(n, size, time,
-					     sdomain, ddomain, "blit");
+	if (rdev->asic->copy.blit) {
+		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
+						RADEON_BENCHMARK_COPY_BLIT, n);
+		if (time < 0)
+			goto out_cleanup;
+		if (time > 0)
+			radeon_benchmark_log_results(n, size, time,
+						     sdomain, ddomain, "blit");
+	}
 
 out_cleanup:
 	if (sobj) {
-- 
1.7.7.5

[PATCH 2/2] drm/radeon/benchmark: allow same domains for dma copy

[alexdeucher]

From: Alex Deucher <alexander.deucher@amd.com>

Remove old comment and allow benchmarking moves within the
same memory domain for both dma and blit methods.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_benchmark.c |    5 +----
 1 files changed, 1 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
index a2f0c24..6e05a2e 100644
--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -122,10 +122,7 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
 		goto out_cleanup;
 	}
 
-	/* r100 doesn't have dma engine so skip the test */
-	/* also, VRAM-to-VRAM test doesn't make much sense for DMA */
-	/* skip it as well if domains are the same */
-	if ((rdev->asic->copy.dma) && (sdomain != ddomain)) {
+	if (rdev->asic->copy.dma) {
 		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
 						RADEON_BENCHMARK_COPY_DMA, n);
 		if (time < 0)
-- 
1.7.7.5

Re: [PATCH 1/2] drm/radeon/benchmark: make sure bo blit copy exists before using it

[Michel Dänzer]

On Mit, 2013-03-13 at 12:38 -0400, alexdeucher@gmail.com wrote: 
> From: Alex Deucher <alexander.deucher@amd.com>
> 
> Fixes a segfault on asics without a blit callback.
> 
> Fixes:
> https://bugs.freedesktop.org/show_bug.cgi?id=62239
> 
> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
> Cc: stable@vger.kernel.org

For the series:

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>


-- 
Earthling Michel Dänzer           |                   http://www.amd.com
Libre software enthusiast         |          Debian, X and DRI developer

Re: [PATCH 1/2] drm/radeon/benchmark: make sure bo blit copy exists before using it

[Paul Menzel]

[-- Attachment #1: Type: text/plain, Size: 582 bytes --]

Dear Alex,


Am Mittwoch, den 13.03.2013, 12:38 -0400 schrieb alexdeucher@gmail.com:
> From: Alex Deucher <alexander.deucher@amd.com>
> 
> Fixes a segfault on asics without a blit callback.

so as a result this is not benchmarked for these ASICS, right?

> Fixes:
> https://bugs.freedesktop.org/show_bug.cgi?id=62239
> 
> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
> Cc: stable@vger.kernel.org
> ---
>  drivers/gpu/drm/radeon/radeon_benchmark.c |   16 +++++++++-------
>  1 files changed, 9 insertions(+), 7 deletions(-)

[…]


Thanks,

Paul

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 198 bytes --]

Re: [PATCH 2/2] drm/radeon/benchmark: allow same domains for dma copy

[Paul Menzel]

[-- Attachment #1.1: Type: text/plain, Size: 1287 bytes --]

Dear Alex,


Am Mittwoch, den 13.03.2013, 12:38 -0400 schrieb alexdeucher@gmail.com:
> From: Alex Deucher <alexander.deucher@amd.com>
> 
> Remove old comment and allow benchmarking moves within the
> same memory domain for both dma and blit methods.
>
> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
> ---
>  drivers/gpu/drm/radeon/radeon_benchmark.c |    5 +----
>  1 files changed, 1 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
> index a2f0c24..6e05a2e 100644
> --- a/drivers/gpu/drm/radeon/radeon_benchmark.c
> +++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
> @@ -122,10 +122,7 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
>  		goto out_cleanup;
>  	}
>  
> -	/* r100 doesn't have dma engine so skip the test */
> -	/* also, VRAM-to-VRAM test doesn't make much sense for DMA */
> -	/* skip it as well if domains are the same */
> -	if ((rdev->asic->copy.dma) && (sdomain != ddomain)) {
> +	if (rdev->asic->copy.dma) {

why is the comment not valid anymore? What changed?

>  		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
>  						RADEON_BENCHMARK_COPY_DMA, n);
>  		if (time < 0)


Thanks,

Paul

[-- Attachment #1.2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 198 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH 1/2] drm/radeon/benchmark: make sure bo blit copy exists before using it

[Alex Deucher]

On Thu, Mar 14, 2013 at 9:06 AM, Paul Menzel
<paulepanter@users.sourceforge.net> wrote:
> Dear Alex,
>
>
> Am Mittwoch, den 13.03.2013, 12:38 -0400 schrieb alexdeucher@gmail.com:
>> From: Alex Deucher <alexander.deucher@amd.com>
>>
>> Fixes a segfault on asics without a blit callback.
>
> so as a result this is not benchmarked for these ASICS, right?

Yes.  it's not benchmarked, but there nothing to benchmark if the
callback doesn't exist :)

Alex

Re: [PATCH 2/2] drm/radeon/benchmark: allow same domains for dma copy

[Alex Deucher]

On Thu, Mar 14, 2013 at 9:07 AM, Paul Menzel
<paulepanter@users.sourceforge.net> wrote:
> Dear Alex,
>
>
> Am Mittwoch, den 13.03.2013, 12:38 -0400 schrieb alexdeucher@gmail.com:
>> From: Alex Deucher <alexander.deucher@amd.com>
>>
>> Remove old comment and allow benchmarking moves within the
>> same memory domain for both dma and blit methods.
>>
>> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
>> ---
>>  drivers/gpu/drm/radeon/radeon_benchmark.c |    5 +----
>>  1 files changed, 1 insertions(+), 4 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
>> index a2f0c24..6e05a2e 100644
>> --- a/drivers/gpu/drm/radeon/radeon_benchmark.c
>> +++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
>> @@ -122,10 +122,7 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
>>               goto out_cleanup;
>>       }
>>
>> -     /* r100 doesn't have dma engine so skip the test */
>> -     /* also, VRAM-to-VRAM test doesn't make much sense for DMA */
>> -     /* skip it as well if domains are the same */
>> -     if ((rdev->asic->copy.dma) && (sdomain != ddomain)) {
>> +     if (rdev->asic->copy.dma) {
>
> why is the comment not valid anymore? What changed?

In my opinion it was never valid.

Alex