diff options
author | Maxim Mikityanskiy <maximmi@nvidia.com> | 2022-10-01 21:56:24 -0700 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2022-10-03 16:55:28 -0700 |
commit | 139213451046eb6653a058a8922796f29b267b0f (patch) | |
tree | 486a8445dd408299b05c710dcbc0d351df3d1914 /drivers/net/ethernet/mellanox/mlx5/core/en/xsk | |
parent | 9f123f740428e96ef2eae8b5e2876b675b6a4605 (diff) | |
download | linux-stable-139213451046eb6653a058a8922796f29b267b0f.tar.gz linux-stable-139213451046eb6653a058a8922796f29b267b0f.tar.bz2 linux-stable-139213451046eb6653a058a8922796f29b267b0f.zip |
net/mlx5e: xsk: Use KLM to protect frame overrun in unaligned mode
XSK RQs support striding RQ linear mode, but the stride size may be
bigger than the XSK frame size, because:
1. The stride size must be a power of two.
2. The stride size must be equal to the UMR page size. Each XSK frame is
treated as a separate page, because they aren't necessarily adjacent in
physical memory, so the driver can't put more than one stride per page.
3. The minimal MTT page size is 4096 on older firmware.
That means that if XSK frame size is 2048 or not a power of two, the
strides may be bigger than XSK frames. Normally, it's not a problem if
the hardware enforces the MTU. However, traffic between vports skips the
hardware MTU check, and oversized packets may be received.
If an oversized packet is bigger than the XSK frame but not bigger than
the stride, it will cause overwriting of the adjacent UMEM region. If
the packet takes more than one stride, they can be recycled for reuse,
so it's not a problem when the XSK frame size matches the stride size.
Work around the above issue by leveraging KLM to make a more
fine-grained mapping. The beginning of each stride is mapped to the
frame memory, and the padding up to the closest power of two is mapped
to the overflow page that doesn't belong to UMEM. This way, application
data corruption won't happen upon receiving packets bigger than MTU.
Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5/core/en/xsk')
-rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c | 27 |
1 files changed, 24 insertions, 3 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index 4b2df2895505..78d746704345 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -41,7 +41,15 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi); memcpy(umr_wqe, &rq->mpwqe.umr_wqe, sizeof(struct mlx5e_umr_wqe)); - if (unlikely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_UNALIGNED)) { + if (likely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_ALIGNED)) { + for (i = 0; i < batch; i++) { + dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk); + + umr_wqe->inline_mtts[i] = (struct mlx5_mtt) { + .ptag = cpu_to_be64(addr | MLX5_EN_WR), + }; + } + } else if (unlikely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_UNALIGNED)) { for (i = 0; i < batch; i++) { dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk); @@ -51,11 +59,22 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) }; } } else { + __be32 pad_size = cpu_to_be32((1 << rq->mpwqe.page_shift) - + rq->xsk_pool->chunk_size); + __be32 frame_size = cpu_to_be32(rq->xsk_pool->chunk_size); + for (i = 0; i < batch; i++) { dma_addr_t addr = xsk_buff_xdp_get_frame_dma(wi->alloc_units[i].xsk); - umr_wqe->inline_mtts[i] = (struct mlx5_mtt) { - .ptag = cpu_to_be64(addr | MLX5_EN_WR), + umr_wqe->inline_klms[i << 1] = (struct mlx5_klm) { + .key = rq->mkey_be, + .va = cpu_to_be64(addr), + .bcount = frame_size, + }; + umr_wqe->inline_klms[(i << 1) + 1] = (struct mlx5_klm) { + .key = rq->mkey_be, + .va = cpu_to_be64(rq->wqe_overflow.addr), + .bcount = pad_size, }; } } @@ -70,6 +89,8 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) offset = ix * rq->mpwqe.mtts_per_wqe; if (likely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_ALIGNED)) offset = offset * sizeof(struct mlx5_mtt) / MLX5_OCTWORD; + else if (unlikely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_OVERSIZED)) + offset = offset * sizeof(struct mlx5_klm) * 2 / MLX5_OCTWORD; umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset); icosq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) { |