From: Alaa Hleihel alaa@nvidia.com
commit 2ba0aa2feebda680ecfc3c552e867cf4d1b05a3a upstream.
The function init_cq_frag_buf() can be called to initialize the current CQ fragments buffer cq->buf, or the temporary cq->resize_buf that is filled during CQ resize operation.
However, the offending commit started to use function get_cqe() for getting the CQEs, the issue with this change is that get_cqe() always returns CQEs from cq->buf, which leads us to initialize the wrong buffer, and in case of enlarging the CQ we try to access elements beyond the size of the current cq->buf and eventually hit a kernel panic.
[exception RIP: init_cq_frag_buf+103] [ffff9f799ddcbcd8] mlx5_ib_resize_cq at ffffffffc0835d60 [mlx5_ib] [ffff9f799ddcbdb0] ib_resize_cq at ffffffffc05270df [ib_core] [ffff9f799ddcbdc0] llt_rdma_setup_qp at ffffffffc0a6a712 [llt] [ffff9f799ddcbe10] llt_rdma_cc_event_action at ffffffffc0a6b411 [llt] [ffff9f799ddcbe98] llt_rdma_client_conn_thread at ffffffffc0a6bb75 [llt] [ffff9f799ddcbec8] kthread at ffffffffa66c5da1 [ffff9f799ddcbf50] ret_from_fork_nospec_begin at ffffffffa6d95ddd
Fix it by getting the needed CQE by calling mlx5_frag_buf_get_wqe() that takes the correct source buffer as a parameter.
Fixes: 388ca8be0037 ("IB/mlx5: Implement fragmented completion queue (CQ)") Link: https://lore.kernel.org/r/90a0e8c924093cfa50a482880ad7e7edb73dc19a.162330997... Signed-off-by: Alaa Hleihel alaa@nvidia.com Signed-off-by: Leon Romanovsky leonro@nvidia.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/infiniband/hw/mlx5/cq.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 088205d7f1a19..872985e4eebec 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -896,15 +896,14 @@ static void destroy_cq_user(struct mlx5_ib_cq *cq, struct ib_ucontext *context) ib_umem_release(cq->buf.umem); }
-static void init_cq_frag_buf(struct mlx5_ib_cq *cq, - struct mlx5_ib_cq_buf *buf) +static void init_cq_frag_buf(struct mlx5_ib_cq_buf *buf) { int i; void *cqe; struct mlx5_cqe64 *cqe64;
for (i = 0; i < buf->nent; i++) { - cqe = get_cqe(cq, i); + cqe = mlx5_frag_buf_get_wqe(&buf->fbc, i); cqe64 = buf->cqe_size == 64 ? cqe : cqe + 64; cqe64->op_own = MLX5_CQE_INVALID << 4; } @@ -930,7 +929,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, if (err) goto err_db;
- init_cq_frag_buf(cq, &cq->buf); + init_cq_frag_buf(&cq->buf);
*inlen = MLX5_ST_SZ_BYTES(create_cq_in) + MLX5_FLD_SZ_BYTES(create_cq_in, pas[0]) * @@ -1253,7 +1252,7 @@ static int resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, if (err) goto ex;
- init_cq_frag_buf(cq, cq->resize_buf); + init_cq_frag_buf(cq->resize_buf);
return 0;