Quoting Matthew Auld (2020-10-21 10:49:57)
> We are incorrectly limiting the max allocation size as per the mm
> max_order, which is effectively the largest power-of-two that we can fit
> in the region size. However, it's normal to setup the region or
> allocator with a non-power-of-two size(for example 3G), which we should
> already handle correctly, except it seems for the early too-big-check.
>
> Fixes: b908be543e44 ("drm/i915: support creating LMEM objects")
> Signed-off-by: Matthew Auld <matthew.auld@xxxxxxxxx>
> Cc: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
> Cc: CQ Tang <cq.tang@xxxxxxxxx>
> ---
> drivers/gpu/drm/i915/intel_memory_region.c | 2 +-
> .../drm/i915/selftests/intel_memory_region.c | 50 +++++++++++++++++++
> drivers/gpu/drm/i915/selftests/mock_region.c | 2 +-
> 3 files changed, 52 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
> index 6b5e9d88646d..180e1078ef7c 100644
> --- a/drivers/gpu/drm/i915/intel_memory_region.c
> +++ b/drivers/gpu/drm/i915/intel_memory_region.c
> @@ -87,7 +87,7 @@ __intel_memory_region_get_pages_buddy(struct intel_memory_region *mem,
> min_order = ilog2(size) - ilog2(mem->mm.chunk_size);
> }
>
> - if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size)
> + if (size > mem->mm.size)
> return -E2BIG;
>
> n_pages = size >> ilog2(mem->mm.chunk_size);
> diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
> index 334b0648e253..34d6de916b3e 100644
> --- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
> +++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
> @@ -261,6 +261,55 @@ static int igt_mock_contiguous(void *arg)
> return err;
> }
>
> +static int igt_mock_splintered_region(void *arg)
> +{
> + struct intel_memory_region *mem = arg;
> + struct drm_i915_private *i915 = mem->i915;
> + struct drm_i915_gem_object *obj;
> + unsigned int expected_order;
> + LIST_HEAD(objects);
> + u64 size;
> + int err = 0;
> +
> + /*
> + * Sanity check we can still allocate everything even if the
> + * mm.max_order != mm.size. i.e our starting address space size is not a
> + * power-of-two.
> + */
> +
> + size = (SZ_4G - 1) & PAGE_MASK;
> + mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0);
> + if (IS_ERR(mem))
> + return PTR_ERR(mem);
> +
> + if (mem->mm.size != size) {
> + pr_err("%s size mismatch(%llu != %llu)\n",
> + __func__, mem->mm.size, size);
> + err = -EINVAL;
> + goto out_put;
> + }
> +
> + expected_order = get_order(rounddown_pow_of_two(size));
> + if (mem->mm.max_order != expected_order) {
> + pr_err("%s order mismatch(%u != %u)\n",
> + __func__, mem->mm.max_order, expected_order);
> + err = -EINVAL;
> + goto out_put;
> + }
> +
> + obj = igt_object_create(mem, &objects, size, 0);
> + if (IS_ERR(obj)) {
> + err = PTR_ERR(obj);
> + goto out_close;
> + }
A second pass to see if we correctly reject an attempt to allocate a
contiguous object larger than max chunk size (but still within
mem_size)?
+1 for splintered!
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
