RDMA/mthca: Use correct sizing on buffers holding page DMA addresses

The buffer that holds the page DMA addresses is sized off umem->nmap.
This can potentially cause out of bound accesses on the PBL array when
iterating the umem DMA-mapped SGL. This is because if umem pages are
combined, umem->nmap can be much lower than the number of system pages
in umem.

Use ib_umem_num_pages() to size this buffer.

Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This commit is contained in:
Shiraz Saleem 2019-03-28 11:49:45 -05:00 committed by Jason Gunthorpe
parent 5f818d676a
commit 41d34865b2

View File

@ -914,7 +914,7 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
goto err;
}
n = mr->umem->nmap;
n = ib_umem_num_pages(mr->umem);
mr->mtt = mthca_alloc_mtt(dev, n);
if (IS_ERR(mr->mtt)) {