On 2024-01-29 05:06, Christian König
wrote:
Am 26.01.24 um 20:47 schrieb Philip Yang:
This is to work around a bug in function drm_prime_pages_to_sg if length
of nr_pages >= 4GB, by doing the same check for max_segment and then
calling sg_alloc_table_from_pages_segment directly instead.
This issue shows up on APU because VRAM is allocated as GTT memory. It
also fixes >=4GB GTT memory mapping for mGPUs with IOMMU isolation mode.
Well that was talked about before and rejected. If we really want more than 4GiB in DMA-bufs we need to fix drm_prime_pages_to_sg() instead.
I sent a patch to fix drm_prime_pages_to_sg but the patch was rejected.
This issue happens on APU, as VRAM is allocated as GTT memory, get to this patch only if IOMMU is isolation mode, with IOMMU off or pt mode, multiple GPUs share the same dma mapping.
Even with the fix patch accepted by drm, we still need this patch to workaround the issue on old kernel version.
Regards,
Philip
Regards,
Christian.
Signed-off-by: Philip Yang <Philip.Yang@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 50 ++++++++++++++-------
1 file changed, 34 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 055ba2ea4c12..a203633fd629 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -171,18 +171,41 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
}
switch (bo->tbo.resource->mem_type) {
- case TTM_PL_TT:
- sgt = drm_prime_pages_to_sg(obj->dev,
- bo->tbo.ttm->pages,
- bo->tbo.ttm->num_pages);
- if (IS_ERR(sgt))
- return sgt;
-
- if (dma_map_sgtable(attach->dev, sgt, dir,
- DMA_ATTR_SKIP_CPU_SYNC))
- goto error_free;
- break;
+ case TTM_PL_TT: {
+ size_t max_segment = 0;
+ u64 num_pages;
+ int err;
+
+ sgt = kmalloc(sizeof(*sgt), GFP_KERNEL);
+ if (!sgt)
+ return ERR_PTR(-ENOMEM);
+
+ if (obj->dev)
+ max_segment = dma_max_mapping_size(obj->dev->dev);
+ if (max_segment == 0)
+ max_segment = UINT_MAX;
+
+ /*
+ * Use u64, otherwise if length of num_pages >= 4GB then size
+ * (num_pages << PAGE_SHIFT) becomes 0
+ */
+ num_pages = bo->tbo.ttm->num_pages;
+ err = sg_alloc_table_from_pages_segment(sgt, bo->tbo.ttm->pages,
+ num_pages, 0,
+ num_pages << PAGE_SHIFT,
+ max_segment, GFP_KERNEL);
+ if (err) {
+ kfree(sgt);
+ return ERR_PTR(err);
+ }
+ if (dma_map_sgtable(attach->dev, sgt, dir, DMA_ATTR_SKIP_CPU_SYNC)) {
+ sg_free_table(sgt);
+ kfree(sgt);
+ return ERR_PTR(-EBUSY);
+ }
+ break;
+ }
case TTM_PL_VRAM:
r = amdgpu_vram_mgr_alloc_sgt(adev, bo->tbo.resource, 0,
bo->tbo.base.size, attach->dev,
@@ -195,11 +218,6 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
}
return sgt;
-
-error_free:
- sg_free_table(sgt);
- kfree(sgt);
- return ERR_PTR(-EBUSY);
}
/**
