All of lore.kernel.org
 help / color / mirror / Atom feed
From: Saeed Mahameed <saeed@kernel.org>
To: "David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Eric Dumazet <edumazet@google.com>
Cc: Saeed Mahameed <saeedm@nvidia.com>,
	netdev@vger.kernel.org, Tariq Toukan <tariqt@nvidia.com>,
	Carolina Jubran <cjubran@nvidia.com>
Subject: [net 09/15] net/mlx5e: XDP, Drop fragmented packets larger than MTU size
Date: Wed, 13 Dec 2023 17:24:59 -0800	[thread overview]
Message-ID: <20231214012505.42666-10-saeed@kernel.org> (raw)
In-Reply-To: <20231214012505.42666-1-saeed@kernel.org>

From: Carolina Jubran <cjubran@nvidia.com>

XDP transmits fragmented packets that are larger than MTU size instead of
dropping those packets. The drop check that checks whether a packet is larger
than MTU is comparing MTU size against the linear part length only.

Adjust the drop check to compare MTU size against both linear and non-linear
part lengths to avoid transmitting fragmented packets larger than MTU size.

Fixes: 39a1665d16a2 ("net/mlx5e: Implement sending multi buffer XDP frames")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 7decc81ed33a..13c7ed1bb37e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -493,6 +493,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 	dma_addr_t dma_addr = xdptxd->dma_addr;
 	u32 dma_len = xdptxd->len;
 	u16 ds_cnt, inline_hdr_sz;
+	unsigned int frags_size;
 	u8 num_wqebbs = 1;
 	int num_frags = 0;
 	bool inline_ok;
@@ -503,8 +504,9 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 
 	inline_ok = sq->min_inline_mode == MLX5_INLINE_MODE_NONE ||
 		dma_len >= MLX5E_XDP_MIN_INLINE;
+	frags_size = xdptxd->has_frags ? xdptxdf->sinfo->xdp_frags_size : 0;
 
-	if (unlikely(!inline_ok || sq->hw_mtu < dma_len)) {
+	if (unlikely(!inline_ok || sq->hw_mtu < dma_len + frags_size)) {
 		stats->err++;
 		return false;
 	}
-- 
2.43.0


  parent reply	other threads:[~2023-12-14  1:25 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-12-14  1:24 [pull request][net 00/15] mlx5 fixes 2023-12-13 Saeed Mahameed
2023-12-14  1:24 ` [net 01/15] Revert "net/mlx5e: fix double free of encap_header in update funcs" Saeed Mahameed
2023-12-15  3:10   ` patchwork-bot+netdevbpf
2023-12-14  1:24 ` [net 02/15] Revert "net/mlx5e: fix double free of encap_header" Saeed Mahameed
2023-12-14  1:24 ` [net 03/15] net/mlx5e: fix double free of encap_header Saeed Mahameed
2023-12-14  1:24 ` [net 04/15] net/mlx5e: Fix slab-out-of-bounds in mlx5_query_nic_vport_mac_list() Saeed Mahameed
2023-12-14  1:24 ` [net 05/15] net/mlx5e: Fix a race in command alloc flow Saeed Mahameed
2023-12-14  1:24 ` [net 06/15] net/mlx5e: fix a potential double-free in fs_udp_create_groups Saeed Mahameed
2023-12-14  1:24 ` [net 07/15] net/mlx5e: Fix overrun reported by coverity Saeed Mahameed
2023-12-14  1:24 ` [net 08/15] net/mlx5e: Decrease num_block_tc when unblock tc offload Saeed Mahameed
2023-12-14  1:24 ` Saeed Mahameed [this message]
2023-12-14  1:25 ` [net 10/15] net/mlx5: Fix fw tracer first block check Saeed Mahameed
2023-12-14  1:25 ` [net 11/15] net/mlx5: Refactor mlx5_flow_destination->rep pointer to vport num Saeed Mahameed
2023-12-14  1:25 ` [net 12/15] net/mlx5e: Fix error code in mlx5e_tc_action_miss_mapping_get() Saeed Mahameed
2023-12-14  1:25 ` [net 13/15] net/mlx5e: Fix error codes in alloc_branch_attr() Saeed Mahameed
2023-12-14  1:25 ` [net 14/15] net/mlx5e: Correct snprintf truncation handling for fw_version buffer Saeed Mahameed
2023-12-14  1:25 ` [net 15/15] net/mlx5e: Correct snprintf truncation handling for fw_version buffer used by representors Saeed Mahameed

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20231214012505.42666-10-saeed@kernel.org \
    --to=saeed@kernel.org \
    --cc=cjubran@nvidia.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=saeedm@nvidia.com \
    --cc=tariqt@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.