netdev.vger.kernel.org archive mirror
 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>,
	Gal Pressman <gal@nvidia.com>
Subject: [net 09/14] net/mlx5e: Fix missing alignment in size of MTT/KLM entries
Date: Mon, 21 Nov 2022 18:25:54 -0800	[thread overview]
Message-ID: <20221122022559.89459-10-saeed@kernel.org> (raw)
In-Reply-To: <20221122022559.89459-1-saeed@kernel.org>

From: Tariq Toukan <tariqt@nvidia.com>

In the cited patch, an alignment required by the HW spec was mistakenly
dropped. Bring it back to fix error completions like the below:

mlx5_core 0000:00:08.0 eth2: Error cqe on cqn 0x40b, ci 0x0, qn 0x104f, opcode 0xd, syndrome 0x2, vendor syndrome 0x68
00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000030: 00 00 00 00 86 00 68 02 25 00 10 4f 00 00 bb d2
WQE DUMP: WQ size 1024 WQ cur size 0, WQE index 0x0, len: 192
00000000: 00 00 00 25 00 10 4f 0c 00 00 00 00 00 18 2e 00
00000010: 90 00 00 00 00 02 00 00 00 00 00 00 20 00 00 00
00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000030: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000040: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000050: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000060: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000070: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00000080: 08 00 00 00 48 6a 00 02 08 00 00 00 0e 10 00 02
00000090: 08 00 00 00 0c db 00 02 08 00 00 00 0e 82 00 02
000000a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
000000b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00

Fixes: 9f123f740428 ("net/mlx5e: Improve MTT/KSM alignment")
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index e3a4f01bcceb..5e41dfdf79c8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -206,10 +206,11 @@ static void mlx5e_disable_blocking_events(struct mlx5e_priv *priv)
 static u16 mlx5e_mpwrq_umr_octowords(u32 entries, enum mlx5e_mpwrq_umr_mode umr_mode)
 {
 	u8 umr_entry_size = mlx5e_mpwrq_umr_entry_size(umr_mode);
+	u32 sz;
 
-	WARN_ON_ONCE(entries * umr_entry_size % MLX5_OCTWORD);
+	sz = ALIGN(entries * umr_entry_size, MLX5_UMR_MTT_ALIGNMENT);
 
-	return entries * umr_entry_size / MLX5_OCTWORD;
+	return sz / MLX5_OCTWORD;
 }
 
 static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
-- 
2.38.1


  parent reply	other threads:[~2022-11-22  2:29 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-22  2:25 [pull request][net 00/14] mlx5 fixes 2022-11-21 Saeed Mahameed
2022-11-22  2:25 ` [net 01/14] net/mlx5: Do not query pci info while pci disabled Saeed Mahameed
2022-11-23  5:00   ` patchwork-bot+netdevbpf
2022-11-22  2:25 ` [net 02/14] net/mlx5: Fix FW tracer timestamp calculation Saeed Mahameed
2022-11-22  2:25 ` [net 03/14] net/mlx5: SF: Fix probing active SFs during driver probe phase Saeed Mahameed
2022-11-23 14:57   ` Maciej Fijalkowski
2022-11-23 17:11     ` Parav Pandit
2022-11-23 17:44       ` Maciej Fijalkowski
2022-11-23 23:36     ` Saeed Mahameed
2022-11-22  2:25 ` [net 04/14] net/mlx5: cmdif, Print info on any firmware cmd failure to tracepoint Saeed Mahameed
2022-11-23 15:06   ` Maciej Fijalkowski
2022-11-23 23:48     ` Saeed Mahameed
2022-11-24  1:55       ` Jakub Kicinski
2022-11-24  4:37         ` Saeed Mahameed
2022-11-22  2:25 ` [net 05/14] net/mlx5: Fix handling of entry refcount when command is not issued to FW Saeed Mahameed
2022-11-22  2:25 ` [net 06/14] net/mlx5: Lag, avoid lockdep warnings Saeed Mahameed
2022-11-22  2:25 ` [net 07/14] net/mlx5: E-Switch, Set correctly vport destination Saeed Mahameed
2022-11-22  2:25 ` [net 08/14] net/mlx5: Fix sync reset event handler error flow Saeed Mahameed
2022-11-22  2:25 ` Saeed Mahameed [this message]
2022-11-22  2:25 ` [net 10/14] net/mlx5e: Offload rule only when all encaps are valid Saeed Mahameed
2022-11-22  2:25 ` [net 11/14] net/mlx5e: Remove leftovers from old XSK queues enumeration Saeed Mahameed
2022-11-22  2:25 ` [net 12/14] net/mlx5e: Fix MACsec SA initialization routine Saeed Mahameed
2022-11-22  2:25 ` [net 13/14] net/mlx5e: Fix MACsec update SecY Saeed Mahameed
2022-11-23 15:21   ` Maciej Fijalkowski
2022-11-23 23:57     ` Saeed Mahameed
2022-11-22  2:25 ` [net 14/14] net/mlx5e: Fix possible race condition in macsec extended packet number update routine 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=20221122022559.89459-10-saeed@kernel.org \
    --to=saeed@kernel.org \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=gal@nvidia.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 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).