[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20250225082306.524e8d6a@kernel.org>
Date: Tue, 25 Feb 2025 08:23:06 -0800
From: Jakub Kicinski <kuba@...nel.org>
To: Jijie Shao <shaojijie@...wei.com>
Cc: <davem@...emloft.net>, <edumazet@...gle.com>, <pabeni@...hat.com>,
<andrew+netdev@...n.ch>, <horms@...nel.org>, <shenjian15@...wei.com>,
<wangpeiyang1@...wei.com>, <liuyonglong@...wei.com>,
<chenhao418@...wei.com>, <sudongming1@...wei.com>, <xujunsheng@...wei.com>,
<shiyongbang@...wei.com>, <libaihan@...wei.com>,
<jonathan.cameron@...wei.com>, <shameerali.kolothum.thodi@...wei.com>,
<salil.mehta@...wei.com>, <netdev@...r.kernel.org>,
<linux-kernel@...r.kernel.org>, <kalesh-anakkur.purayil@...adcom.com>
Subject: Re: [PATCH v3 net-next 2/6] net: hibmcge: Add support for rx
checksum offload
On Tue, 25 Feb 2025 17:00:45 +0800 Jijie Shao wrote:
> >> + NETIF_F_RXCSUM)
> > I don't see you setting the checksum to anything other than NONE
>
> When receiving packets, MAC checks the checksum by default. This behavior cannot be disabled.
> If the checksum is incorrect, the MAC notifies the driver through the descriptor.
>
> If checksum offload is enabled, the driver drops the packet.
> Otherwise, the driver set the checksum to NONE and sends the packet to the stack.
Dropping packets with bad csum is not correct.
Packets where device validated L4 csum should have csum set
to UNNECESSARY, most likely. Please read the comment in skbuff.h
Powered by blists - more mailing lists