All of lore.kernel.org
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche@acm.org>
To: "Zhijian Li (Fujitsu)" <lizhijian@fujitsu.com>,
	"Daisuke Matsuda (Fujitsu)" <matsuda-daisuke@fujitsu.com>,
	'Zhu Yanjun' <yanjun.zhu@intel.com>,
	"yi.zhang@redhat.com" <yi.zhang@redhat.com>,
	"haris.iqbal@ionos.com" <haris.iqbal@ionos.com>,
	"jinpu.wang@ionos.com" <jinpu.wang@ionos.com>
Cc: Zhu Yanjun <yanjun.zhu@linux.dev>, "jgg@ziepe.ca" <jgg@ziepe.ca>,
	"leon@kernel.org" <leon@kernel.org>,
	"linux-rdma@vger.kernel.org" <linux-rdma@vger.kernel.org>,
	"zyjzyj2000@gmail.com" <zyjzyj2000@gmail.com>
Subject: Re: [PATCH 1/1] RDMA/rxe: Fix blktests srp lead kernel panic with 64k page size
Date: Fri, 20 Oct 2023 09:21:21 -0700	[thread overview]
Message-ID: <e60407d2-13c2-477c-b663-102e6094c551@acm.org> (raw)
In-Reply-To: <e628d470-507d-41a2-92ee-c32b8a8d4791@fujitsu.com>

On 10/19/23 23:54, Zhijian Li (Fujitsu) wrote:
> Add and Hi Bart,
> 
> Yi reported a crash[1] when PAGE_SIZE is 64K
> [1]https://lore.kernel.org/all/CAHj4cs9XRqE25jyVw9rj9YugffLn5+f=1znaBEnu1usLOciD+g@mail.gmail.com/T/
> 
> The root cause is unknown so far, but I notice that SRP over RXE always uses MR with page_size
> 4K = MAX(4K, min(device_support_page_size)) even though the device supports 64K page size.
> * RXE device support 4K ~ 2G page size
> 
> 
> 4024         /*
> 4025          * Use the smallest page size supported by the HCA, down to a
> 4026          * minimum of 4096 bytes. We're unlikely to build large sglists
> 4027          * out of smaller entries.
> 4028          */
> 4029         mr_page_shift           = max(12, ffs(attr->page_size_cap) - 1);
> 4030         srp_dev->mr_page_size   = 1 << mr_page_shift;
> 4031         srp_dev->mr_page_mask   = ~((u64) srp_dev->mr_page_size - 1);
> 4032         max_pages_per_mr        = attr->max_mr_size;
> 
> 
> I doubt if we can use PAGE_SIZE MR if the device supports it.

Hi Zhijian,

Thank you for having Cc-ed me. How about changing "12" in the above code
into PAGE_SHIFT?

Thanks,

Bart.

  reply	other threads:[~2023-10-20 16:21 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-13  1:18 [PATCH 1/1] RDMA/rxe: Fix blktests srp lead kernel panic with 64k page size Zhu Yanjun
2023-10-13 12:01 ` Daisuke Matsuda (Fujitsu)
2023-10-13 12:28   ` Zhu Yanjun
2023-10-13 13:01     ` Daisuke Matsuda (Fujitsu)
2023-10-13 13:44       ` Rain River
2023-10-16  6:07         ` Daisuke Matsuda (Fujitsu)
2023-10-18  8:34           ` Zhu Yanjun
2023-10-20  3:47   ` Zhijian Li (Fujitsu)
2023-10-20  6:54     ` Zhijian Li (Fujitsu)
2023-10-20 16:21       ` Bart Van Assche [this message]
2023-10-23  0:58         ` Zhijian Li (Fujitsu)
2023-10-20 14:01     ` Jason Gunthorpe
2023-10-23  3:52       ` Zhijian Li (Fujitsu)
2023-10-23  6:08         ` Zhu Yanjun
2023-10-23 10:45         ` Yi Zhang
2023-10-24  8:15           ` Zhijian Li (Fujitsu)
2023-10-24  9:13             ` Zhijian Li (Fujitsu)
2023-10-26  9:05               ` Zhijian Li (Fujitsu)
2023-10-26 11:42                 ` Jason Gunthorpe
2023-10-26 12:59                   ` Zhu Yanjun
2023-10-26 23:23                     ` Jason Gunthorpe
2023-10-27  1:36                       ` Zhu Yanjun
2023-10-27  4:01                       ` Zhu Yanjun
2023-10-27 11:51                         ` Jason Gunthorpe
2023-10-26 13:28                 ` Bart Van Assche
2023-10-26 13:43                   ` Jason Gunthorpe
2023-10-26 21:47                     ` Bart Van Assche
2023-10-27  1:26                       ` Daisuke Matsuda (Fujitsu)
2023-10-27  1:39                       ` Zhu Yanjun
2023-10-27  5:43                       ` Zhijian Li (Fujitsu)
2023-10-31  1:36                 ` Zhu Yanjun
     [not found]                   ` <CAEz=LcuLCe7bhUohh6BcHdJ1_ocJdZq=eu07vWb3Md5_ZOGDBg@mail.gmail.com>
     [not found]                     ` <CAEz=LcuQ6fFpHqBPT1oTUgKABAHFJqYDC-AHidE-+n6OtzmCPQ@mail.gmail.com>
2023-10-31  8:14                       ` Greg Sword

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=e60407d2-13c2-477c-b663-102e6094c551@acm.org \
    --to=bvanassche@acm.org \
    --cc=haris.iqbal@ionos.com \
    --cc=jgg@ziepe.ca \
    --cc=jinpu.wang@ionos.com \
    --cc=leon@kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=lizhijian@fujitsu.com \
    --cc=matsuda-daisuke@fujitsu.com \
    --cc=yanjun.zhu@intel.com \
    --cc=yanjun.zhu@linux.dev \
    --cc=yi.zhang@redhat.com \
    --cc=zyjzyj2000@gmail.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.