[igt-dev] [PATCH i-g-t] i915/gem_tiled_fence_blits: Fix softpinned version of the test

[Kamil Konieczny]

Hi Zbigniew,

On 2023-01-26 at 13:18:24 +0100, Zbigniew Kempczyński wrote:
> Working with larger set on mappable apperture for softpinned version
> of the test we might hit situation buffers randomly taken to blit
> might overlap. Since reloc allocator is keeping offset per handle
> only thing we can do is to pick another pair of buffers until we get
> two non-overlapping ones.
> 
> Due to extremely long execution time on RKL I've limited number
> of cores used to blit and verify buffer contents to four. It seems
> ggtt mapping is very slow on this platform comparing to older gens
> (Skylake for example).
> 
> Fixes: https://gitlab.freedesktop.org/drm/intel/-/issues/7675
> 
> Signed-off-by: Zbigniew Kempczyński <zbigniew.kempczynski at intel.com>
> Cc: Kamil Konieczny <kamil.konieczny at linux.intel.com>
> ---
>  tests/i915/gem_tiled_fence_blits.c | 45 ++++++++++++++++++++++++------
>  1 file changed, 36 insertions(+), 9 deletions(-)
> 
> diff --git a/tests/i915/gem_tiled_fence_blits.c b/tests/i915/gem_tiled_fence_blits.c
> index 1c621d1e3a..b1105ffa9f 100644
> --- a/tests/i915/gem_tiled_fence_blits.c
> +++ b/tests/i915/gem_tiled_fence_blits.c
> @@ -154,22 +154,29 @@ static void run_test(int fd, int count, uint64_t end)
>  	uint32_t *src_order, *dst_order;
>  	uint32_t *bo, *bo_start_val;
>  	uint32_t start = 0;
> -	uint64_t ahnd = 0;
> +	uint64_t ahnd = 0, ahndbb = 0;
>  
> -	if (!gem_has_relocations(fd))
> +	if (!gem_has_relocations(fd)) {
>  		ahnd = intel_allocator_open_full(fd, 0, 0, end,
>  						 INTEL_ALLOCATOR_RELOC,
>  						 ALLOC_STRATEGY_LOW_TO_HIGH, 0);
> +
> +		/* Use separated vm range for bb */
> +		ahndbb = intel_allocator_open_full(fd, 1, end, 0,
------------------------------------------------------ ^
This is context id, could we run bb with work done in context 0 ?

> +						   INTEL_ALLOCATOR_RELOC,
> +						   ALLOC_STRATEGY_LOW_TO_HIGH, 0);
> +	}
> +
>  	memset(reloc, 0, sizeof(reloc));
>  	memset(obj, 0, sizeof(obj));
>  	obj[0].flags = EXEC_OBJECT_NEEDS_FENCE;
>  	obj[1].flags = EXEC_OBJECT_NEEDS_FENCE;
>  	obj[2].handle = gem_create(fd, 4096);
> -	obj[2].offset = get_offset(ahnd, obj[2].handle, 4096, 0);
> +	obj[2].offset = get_offset(ahndbb, obj[2].handle, 4096, 0);
>  	if (ahnd) {
>  		obj[0].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_WRITE;
>  		obj[1].flags |= EXEC_OBJECT_PINNED;
> -		obj[2].flags |= EXEC_OBJECT_PINNED;
> +		obj[2].flags |= EXEC_OBJECT_PINNED | EXEC_OBJECT_SUPPORTS_48B_ADDRESS;
>  	}
>  	obj[2].relocs_ptr = to_user_pointer(reloc);
>  	obj[2].relocation_count = !ahnd ? ARRAY_SIZE(reloc) : 0;
> @@ -206,6 +213,7 @@ static void run_test(int fd, int count, uint64_t end)
>  		for (int i = 0; i < count; i++) {
>  			int src = src_order[i];
>  			int dst = dst_order[i];
> +			int ret;
>  
>  			if (src == dst)
>  				continue;
> @@ -218,19 +226,33 @@ static void run_test(int fd, int count, uint64_t end)
>  						sizeof(linear), 0);
>  				obj[1].offset = get_offset(ahnd, obj[1].handle,
>  						sizeof(linear), 0);
> -				obj[2].offset = get_offset(ahnd, obj[2].handle,
> +				obj[2].offset = get_offset(ahndbb, obj[2].handle,
>  						4096, 0);
>  				update_batch(fd, obj[2].handle, reloc,
>  					     obj[0].offset, obj[1].offset);
>  			}
>  
> -			gem_execbuf(fd, &eb);
> -			if (ahnd) {
> +			ret = __gem_execbuf(fd, &eb);
> +
> +			/*
> +			 * 1. For relocations execbuf must succeed.
> +			 * 2. For softpinning we might hit situation two buffers
> +			 * would overlap (buffers picked to blit are randomized
> +			 * and we use more buffers aperture can hold).
> +			 * For such situation (ENOSPC) we just repeat pick
> +			 * and execute.
> +			 */
> +			if (!ahnd) {
> +				igt_assert_eq(ret, 0);
> +			} else {
> +				igt_assert(ret == 0 || ret == -ENOSPC);
>  				gem_close(fd, obj[2].handle);
> +				put_offset(ahndbb, obj[2].handle);
>  				obj[2].handle = gem_create(fd, 4096);
>  			}
>  
> -			bo_start_val[dst] = bo_start_val[src];
> +			if (!ret)
> +				bo_start_val[dst] = bo_start_val[src];

Could you also count here how many times you hit retry ?
Also count number of runs and print them with igt_debug after loop end ?

>  		}
>  	}
>  
> @@ -242,13 +264,18 @@ static void run_test(int fd, int count, uint64_t end)
>  
>  	gem_close(fd, obj[2].handle);
>  	put_ahnd(ahnd);
> +	put_ahnd(ahndbb);
>  }
>  
>  #define MAX_32b ((1ull << 32) - 4096)
>  
>  igt_main
>  {
> -	const int ncpus = sysconf(_SC_NPROCESSORS_ONLN);
> +	/*
> +	 * For machines with many cpu cores buffer verification can take
> +	 * almost minute, limitation to 4 cores keeps this time in seconds.
> +	 */
> +	const int ncpus = min_t(int, sysconf(_SC_NPROCESSORS_ONLN), 4);

I also looked at end of first igt_fixture and there seems
igt_debug could be improved and print a little more info.

Regards,
Kamil

>  	uint64_t count = 0, end;
>  	int fd;
>  
> -- 
> 2.34.1
>