[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <03dd8a0d-84b9-c925-9547-99f708e88997@suse.de>
Date: Mon, 3 Jul 2023 14:19:15 +0200
From: Hannes Reinecke <hare@...e.de>
To: Sagi Grimberg <sagi@...mberg.me>, David Howells <dhowells@...hat.com>
Cc: Keith Busch <kbusch@...nel.org>, Christoph Hellwig <hch@....de>,
linux-nvme@...ts.infradead.org, Jakub Kicinski <kuba@...nel.org>,
Eric Dumazet <edumazet@...gle.com>, Paolo Abeni <pabeni@...hat.com>,
netdev@...r.kernel.org
Subject: Re: [PATCHv6 0/5] net/tls: fixes for NVMe-over-TLS
On 7/3/23 14:13, Hannes Reinecke wrote:
> On 7/3/23 12:20, Hannes Reinecke wrote:
>> On 7/3/23 12:08, Sagi Grimberg wrote:
>>>
>>>
>>> On 7/3/23 12:04, Hannes Reinecke wrote:
>>>> Hi all,
>>>>
>>>> here are some small fixes to get NVMe-over-TLS up and running.
>>>> The first three are just minor modifications to have MSG_EOR handled
>>>> for TLS (and adding a test for it), but the last two implement the
>>>> ->read_sock() callback for tls_sw and that, I guess, could do with
>>>> some reviews.
>>>> It does work with my NVMe-TLS test harness, but what do I know :-)
>>>
>>> Hannes, have you tested nvme/tls with the MSG_SPLICE_PAGES series from
>>> david?
>>
>> Yes. This patchset has been tested on top of current linus' HEAD,
>> which includes the MSG_SPLICE_PAGES series (hence the absence of patch
>> hunks for ->sendpage() and friends).
>>
> Well, of course, spoke too soon.
> 'discover' and 'connect' works, but when I'm trying to transfer data
> (eg by doing a 'mkfs.xfs') the whole thing crashes horribly in
> sock_sendmsg() as it's trying to access invalid pages :-(
>
> Debugging to find out if it's my or Davids fault.
>
Hehe.
Wasn't me. Crashes even without TLS.
Sagi, does current linus' HEAD (I've tested with e55e5df193d2) work for
you (traddr tcp 127.0.0.1)?
Cheers,
Hannes
Powered by blists - more mailing lists