The kcalloc() in nouveau_dmem_evict_chunk() will return null if
the physical memory has run out. As a result, if we dereference
src_pfns, dst_pfns or dma_addrs, the null pointer dereference bugs
will happen.

Moreover, the GPU is going away. If the kcalloc() fails, we could not
evict all pages mapping a chunk. So this patch adds a __GFP_NOFAIL
flag in kcalloc().

Finally, as there is no need to have physically contiguous memory,
this patch switches kcalloc() to kvcalloc() in order to avoid
failing allocations.

Fixes: 249881232e14 ("nouveau/dmem: evict device private memory during release")
Suggested-by: Danilo Krummrich <dakr@redhat.com>
Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
---
Changes in v3:
  - Switch kcalloc() to kvcalloc().

 drivers/gpu/drm/nouveau/nouveau_dmem.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 12feecf71e7..6fb65b01d77 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -378,9 +378,9 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
 	dma_addr_t *dma_addrs;
 	struct nouveau_fence *fence;
 
-	src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL);
-	dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL);
-	dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL);
+	src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL);
+	dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL);
+	dma_addrs = kvcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL | __GFP_NOFAIL);
 
 	migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT,
 			npages);
@@ -406,11 +406,11 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
 	migrate_device_pages(src_pfns, dst_pfns, npages);
 	nouveau_dmem_fence_done(&fence);
 	migrate_device_finalize(src_pfns, dst_pfns, npages);
-	kfree(src_pfns);
-	kfree(dst_pfns);
+	kvfree(src_pfns);
+	kvfree(dst_pfns);
 	for (i = 0; i < npages; i++)
 		dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL);
-	kfree(dma_addrs);
+	kvfree(dma_addrs);
 }
 
 void
-- 
2.17.1

On 3/6/24 06:01, Duoming Zhou wrote:
> The kcalloc() in nouveau_dmem_evict_chunk() will return null if
> the physical memory has run out. As a result, if we dereference
> src_pfns, dst_pfns or dma_addrs, the null pointer dereference bugs
> will happen.
> 
> Moreover, the GPU is going away. If the kcalloc() fails, we could not
> evict all pages mapping a chunk. So this patch adds a __GFP_NOFAIL
> flag in kcalloc().
> 
> Finally, as there is no need to have physically contiguous memory,
> this patch switches kcalloc() to kvcalloc() in order to avoid
> failing allocations.
> 
> Fixes: 249881232e14 ("nouveau/dmem: evict device private memory during release")
> Suggested-by: Danilo Krummrich <dakr@redhat.com>
> Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>

Applied to drm-misc-fixes, thanks!

> ---
> Changes in v3:
>    - Switch kcalloc() to kvcalloc().
> 
>   drivers/gpu/drm/nouveau/nouveau_dmem.c | 12 ++++++------
>   1 file changed, 6 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
> index 12feecf71e7..6fb65b01d77 100644
> --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
> +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
> @@ -378,9 +378,9 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
>   	dma_addr_t *dma_addrs;
>   	struct nouveau_fence *fence;
>   
> -	src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL);
> -	dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL);
> -	dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL);
> +	src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL);
> +	dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL);
> +	dma_addrs = kvcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL | __GFP_NOFAIL);
>   
>   	migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT,
>   			npages);
> @@ -406,11 +406,11 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
>   	migrate_device_pages(src_pfns, dst_pfns, npages);
>   	nouveau_dmem_fence_done(&fence);
>   	migrate_device_finalize(src_pfns, dst_pfns, npages);
> -	kfree(src_pfns);
> -	kfree(dst_pfns);
> +	kvfree(src_pfns);
> +	kvfree(dst_pfns);
>   	for (i = 0; i < npages; i++)
>   		dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL);
> -	kfree(dma_addrs);
> +	kvfree(dma_addrs);
>   }
>   
>   void