Netdev Archive on 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>
Cc: netdev@vger.kernel.org, Tariq Toukan <tariqt@nvidia.com>,
	Moshe Shemesh <moshe@nvidia.com>,
	Saeed Mahameed <saeedm@nvidia.com>
Subject: [net 05/12] net/mlx5e: RX, Avoid possible data corruption when relaxed ordering and LRO combined
Date: Tue, 27 Jul 2021 16:20:43 -0700	[thread overview]
Message-ID: <20210727232050.606896-6-saeed@kernel.org> (raw)
In-Reply-To: <20210727232050.606896-1-saeed@kernel.org>

From: Tariq Toukan <tariqt@nvidia.com>

When HW aggregates packets for an LRO session, it writes the payload
of two consecutive packets of a flow contiguously, so that they usually
share a cacheline.

The first byte of a packet's payload is written immediately after
the last byte of the preceding packet.
In this flow, there are two consecutive write requests to the shared
cacheline:
1. Regular write for the earlier packet.
2. Read-modify-write for the following packet.

In case of relaxed-ordering on, these two writes might be re-ordered.
Using the end padding optimization (to avoid partial write for the last
cacheline of a packet) becomes problematic if the two writes occur
out-of-order, as the padding would overwrite payload that belongs to
the following packet, causing data corruption.

Avoid this by disabling the end padding optimization when both
LRO and relaxed-ordering are enabled.

Fixes: 17347d5430c4 ("net/mlx5e: Add support for PCI relaxed ordering")
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/params.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 150c8e82c738..2cbf18c967f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -471,6 +471,15 @@ static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev,
 	param->cq_period_mode = params->rx_cq_moderation.cq_period_mode;
 }
 
+static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
+{
+	bool ro = pcie_relaxed_ordering_enabled(mdev->pdev) &&
+		MLX5_CAP_GEN(mdev, relaxed_ordering_write);
+
+	return ro && params->lro_en ?
+		MLX5_WQ_END_PAD_MODE_NONE : MLX5_WQ_END_PAD_MODE_ALIGN;
+}
+
 int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 			 struct mlx5e_params *params,
 			 struct mlx5e_xsk_param *xsk,
@@ -508,7 +517,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
 	}
 
 	MLX5_SET(wq, wq, wq_type,          params->rq_wq_type);
-	MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
+	MLX5_SET(wq, wq, end_padding_mode, rq_end_pad_mode(mdev, params));
 	MLX5_SET(wq, wq, log_wq_stride,
 		 mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs));
 	MLX5_SET(wq, wq, pd,               mdev->mlx5e_res.hw_objs.pdn);
-- 
2.31.1


  parent reply	other threads:[~2021-07-27 23:21 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-27 23:20 [pull request][net 00/12] mlx5 fixes 2021-07-27 Saeed Mahameed
2021-07-27 23:20 ` [net 01/12] net/mlx5: Fix flow table chaining Saeed Mahameed
2021-07-28  8:30   ` patchwork-bot+netdevbpf
2021-07-27 23:20 ` [net 02/12] net/mlx5e: Disable Rx ntuple offload for uplink representor Saeed Mahameed
2021-07-27 23:20 ` [net 03/12] net/mlx5: E-Switch, Set destination vport vhca id only when merged eswitch is supported Saeed Mahameed
2021-07-27 23:20 ` [net 04/12] net/mlx5: E-Switch, handle devcom events only for ports on the same device Saeed Mahameed
2021-07-27 23:20 ` Saeed Mahameed [this message]
2021-07-27 23:20 ` [net 06/12] net/mlx5e: Add NETIF_F_HW_TC to hw_features when HTB offload is available Saeed Mahameed
2021-07-27 23:20 ` [net 07/12] net/mlx5e: Consider PTP-RQ when setting RX VLAN stripping Saeed Mahameed
2021-07-27 23:20 ` [net 08/12] net/mlx5e: Fix page allocation failure for trap-RQ over SF Saeed Mahameed
2021-07-27 23:20 ` [net 09/12] net/mlx5e: Fix page allocation failure for ptp-RQ " Saeed Mahameed
2021-07-27 23:20 ` [net 10/12] net/mlx5: Unload device upon firmware fatal error Saeed Mahameed
2021-07-27 23:20 ` [net 11/12] net/mlx5e: Fix nullptr in mlx5e_hairpin_get_mdev() Saeed Mahameed
2021-07-27 23:20 ` [net 12/12] net/mlx5: Fix mlx5_vport_tbl_attr chain from u16 to u32 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=20210727232050.606896-6-saeed@kernel.org \
    --to=saeed@kernel.org \
    --cc=davem@davemloft.net \
    --cc=kuba@kernel.org \
    --cc=moshe@nvidia.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeedm@nvidia.com \
    --cc=tariqt@nvidia.com \
    --subject='Re: [net 05/12] net/mlx5e: RX, Avoid possible data corruption when relaxed ordering and LRO combined' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).