RDMA/umem: Use dma-buf locked API to solve deadlock

The cited commit moves umem to call the unlocked versions of dmabuf
unmap/map attachment, but the lock is held while calling to these
functions, hence move back to the locked versions of these APIs.

Fixes: 21c9c5c078 ("RDMA/umem: Prepare to dynamic dma-buf locking specification")
Link: https://lore.kernel.org/r/311c2cb791f8af75486df446819071357353db1b.1675088709.git.leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
This commit is contained in:
Maor Gottlieb 2023-01-30 16:25:50 +02:00 committed by Jason Gunthorpe
parent b7e08a5a63
commit c956940a4a

View File

@ -26,8 +26,8 @@ int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf)
if (umem_dmabuf->sgt)
goto wait_fence;
sgt = dma_buf_map_attachment_unlocked(umem_dmabuf->attach,
DMA_BIDIRECTIONAL);
sgt = dma_buf_map_attachment(umem_dmabuf->attach,
DMA_BIDIRECTIONAL);
if (IS_ERR(sgt))
return PTR_ERR(sgt);
@ -103,8 +103,8 @@ void ib_umem_dmabuf_unmap_pages(struct ib_umem_dmabuf *umem_dmabuf)
umem_dmabuf->last_sg_trim = 0;
}
dma_buf_unmap_attachment_unlocked(umem_dmabuf->attach, umem_dmabuf->sgt,
DMA_BIDIRECTIONAL);
dma_buf_unmap_attachment(umem_dmabuf->attach, umem_dmabuf->sgt,
DMA_BIDIRECTIONAL);
umem_dmabuf->sgt = NULL;
}