From: dingtianhong@huawei.com (Ding Tianhong)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH net-next v13 0/3] add hisilicon hip04 ethernet driver
Date: Thu, 15 Jan 2015 20:56:21 +0800 [thread overview]
Message-ID: <54B7B8F5.6060808@huawei.com> (raw)
In-Reply-To: <54B7B4E7.8030108@suse.de>
On 2015/1/15 20:39, Alexander Graf wrote:
>
>
> On 15.01.15 10:42, Arnd Bergmann wrote:
>> On Thursday 15 January 2015 16:37:23 Ding Tianhong wrote:
>>> On 2015/1/14 18:19, Alexander Graf wrote:
>>>>
>>>> >From a 10000 feet perspective it looks like two problems to me
>>>>
>>>> 1) Allocation failure doesn't get handled properly somewhere
>>
>> This is the bug that Eric pointed out as well.
>>
>>>> 2) We fail to allocate with order=0 - I don't see why
>>
>> GFP_ATOMIC. When allocating from a the napi poll function in softirq
>> context, you have to use nonblocking allocations, which occasionally
>> fail. This should not cause any harm other than dropped packets.
>>
>>> is it easy to repetition this bug? how big is your memory on your board,
>>> is it happened in your previous hip04 driver?
>>
>> It should be independent of memory size, but may be more likely if you
>> don't have swap space configured.
>
> With the previous driver I was unable to get this far - I ended up in
> random memory corruption and had a ~90% packet loss after about an hour
> of uptime.
>
> I'm not sure whether it's easy to reproduce, I merely started up a few
> VMs, did some disk I/O and started to compile QEMU in the background ;).
>
> I'll happily give your follow up patch that's going to fix the memory
> allocation problems a try though.
>
Thanks for your work, I am sure we could make it much more better:)
Ding
>
> Alex
>
> .
>
WARNING: multiple messages have this Message-ID (diff)
From: Ding Tianhong <dingtianhong-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
To: Alexander Graf <agraf-l3A5Bk7waGM@public.gmane.org>,
Arnd Bergmann <arnd-r2nGTMty4D4@public.gmane.org>
Cc: robh+dt-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org,
davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org,
grant.likely-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org,
sergei.shtylyov-M4DtvfQ/ZS1MRgGoP+s0PdBPR1lH4CV8@public.gmane.org,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org,
eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org,
xuwei5-C8/M+/jPZTeaMJb+Lgu22Q@public.gmane.org,
zhangfei.gao-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org,
netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-lFZ/pmaqli7XmaaqVzeoHQ@public.gmane.org
Subject: Re: [PATCH net-next v13 0/3] add hisilicon hip04 ethernet driver
Date: Thu, 15 Jan 2015 20:56:21 +0800 [thread overview]
Message-ID: <54B7B8F5.6060808@huawei.com> (raw)
In-Reply-To: <54B7B4E7.8030108-l3A5Bk7waGM@public.gmane.org>
On 2015/1/15 20:39, Alexander Graf wrote:
>
>
> On 15.01.15 10:42, Arnd Bergmann wrote:
>> On Thursday 15 January 2015 16:37:23 Ding Tianhong wrote:
>>> On 2015/1/14 18:19, Alexander Graf wrote:
>>>>
>>>> >From a 10000 feet perspective it looks like two problems to me
>>>>
>>>> 1) Allocation failure doesn't get handled properly somewhere
>>
>> This is the bug that Eric pointed out as well.
>>
>>>> 2) We fail to allocate with order=0 - I don't see why
>>
>> GFP_ATOMIC. When allocating from a the napi poll function in softirq
>> context, you have to use nonblocking allocations, which occasionally
>> fail. This should not cause any harm other than dropped packets.
>>
>>> is it easy to repetition this bug? how big is your memory on your board,
>>> is it happened in your previous hip04 driver?
>>
>> It should be independent of memory size, but may be more likely if you
>> don't have swap space configured.
>
> With the previous driver I was unable to get this far - I ended up in
> random memory corruption and had a ~90% packet loss after about an hour
> of uptime.
>
> I'm not sure whether it's easy to reproduce, I merely started up a few
> VMs, did some disk I/O and started to compile QEMU in the background ;).
>
> I'll happily give your follow up patch that's going to fix the memory
> allocation problems a try though.
>
Thanks for your work, I am sure we could make it much more better:)
Ding
>
> Alex
>
> .
>
--
To unsubscribe from this list: send the line "unsubscribe devicetree" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
WARNING: multiple messages have this Message-ID (diff)
From: Ding Tianhong <dingtianhong-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
To: Alexander Graf <agraf-l3A5Bk7waGM@public.gmane.org>,
Arnd Bergmann <arnd-r2nGTMty4D4@public.gmane.org>
Cc: <robh+dt-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
<davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org>,
<grant.likely-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>,
<sergei.shtylyov-M4DtvfQ/ZS1MRgGoP+s0PdBPR1lH4CV8@public.gmane.org>,
<linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org>,
<eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>,
<xuwei5-C8/M+/jPZTeaMJb+Lgu22Q@public.gmane.org>,
<zhangfei.gao-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>,
<netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
<devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
<linux-lFZ/pmaqli7XmaaqVzeoHQ@public.gmane.org>
Subject: Re: [PATCH net-next v13 0/3] add hisilicon hip04 ethernet driver
Date: Thu, 15 Jan 2015 20:56:21 +0800 [thread overview]
Message-ID: <54B7B8F5.6060808@huawei.com> (raw)
In-Reply-To: <54B7B4E7.8030108-l3A5Bk7waGM@public.gmane.org>
On 2015/1/15 20:39, Alexander Graf wrote:
>
>
> On 15.01.15 10:42, Arnd Bergmann wrote:
>> On Thursday 15 January 2015 16:37:23 Ding Tianhong wrote:
>>> On 2015/1/14 18:19, Alexander Graf wrote:
>>>>
>>>> >From a 10000 feet perspective it looks like two problems to me
>>>>
>>>> 1) Allocation failure doesn't get handled properly somewhere
>>
>> This is the bug that Eric pointed out as well.
>>
>>>> 2) We fail to allocate with order=0 - I don't see why
>>
>> GFP_ATOMIC. When allocating from a the napi poll function in softirq
>> context, you have to use nonblocking allocations, which occasionally
>> fail. This should not cause any harm other than dropped packets.
>>
>>> is it easy to repetition this bug? how big is your memory on your board,
>>> is it happened in your previous hip04 driver?
>>
>> It should be independent of memory size, but may be more likely if you
>> don't have swap space configured.
>
> With the previous driver I was unable to get this far - I ended up in
> random memory corruption and had a ~90% packet loss after about an hour
> of uptime.
>
> I'm not sure whether it's easy to reproduce, I merely started up a few
> VMs, did some disk I/O and started to compile QEMU in the background ;).
>
> I'll happily give your follow up patch that's going to fix the memory
> allocation problems a try though.
>
Thanks for your work, I am sure we could make it much more better:)
Ding
>
> Alex
>
> .
>
--
To unsubscribe from this list: send the line "unsubscribe devicetree" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2015-01-15 12:56 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-01-14 6:34 [PATCH net-next v13 0/3] add hisilicon hip04 ethernet driver Ding Tianhong
2015-01-14 6:34 ` Ding Tianhong
2015-01-14 6:34 ` Ding Tianhong
2015-01-14 6:34 ` [PATCH net-next v13 1/3] Documentation: add Device tree bindings for Hisilicon hip04 ethernet Ding Tianhong
2015-01-14 6:34 ` Ding Tianhong
2015-01-14 6:34 ` Ding Tianhong
2015-01-14 6:34 ` [PATCH net-next v13 2/3] net: hisilicon: new hip04 MDIO driver Ding Tianhong
2015-01-14 6:34 ` Ding Tianhong
2015-01-14 6:34 ` Ding Tianhong
2015-01-14 6:34 ` [PATCH net-next v13 3/3] net: hisilicon: new hip04 ethernet driver Ding Tianhong
2015-01-14 6:34 ` Ding Tianhong
2015-01-14 6:34 ` Ding Tianhong
2015-01-14 8:06 ` Joe Perches
2015-01-14 8:06 ` Joe Perches
2015-01-15 2:56 ` Ding Tianhong
2015-01-15 2:56 ` Ding Tianhong
2015-01-15 2:56 ` Ding Tianhong
2015-01-14 8:53 ` Arnd Bergmann
2015-01-14 8:53 ` Arnd Bergmann
2015-01-15 2:54 ` Ding Tianhong
2015-01-15 2:54 ` Ding Tianhong
2015-01-15 2:54 ` Ding Tianhong
2015-01-15 9:05 ` Arnd Bergmann
2015-01-15 9:05 ` Arnd Bergmann
2015-01-14 16:34 ` Eric Dumazet
2015-01-14 16:34 ` Eric Dumazet
2015-01-15 10:29 ` Ding Tianhong
2015-01-15 10:29 ` Ding Tianhong
2015-01-15 10:29 ` Ding Tianhong
2015-01-15 12:30 ` Arnd Bergmann
2015-01-15 12:30 ` Arnd Bergmann
2015-01-15 4:39 ` Joe Perches
2015-01-15 4:39 ` Joe Perches
2015-01-15 10:28 ` Ding Tianhong
2015-01-15 10:28 ` Ding Tianhong
2015-01-15 10:28 ` Ding Tianhong
2015-01-15 9:53 ` Arnd Bergmann
2015-01-15 9:53 ` Arnd Bergmann
2015-01-19 18:11 ` Alexander Graf
2015-01-19 18:11 ` Alexander Graf
2015-01-19 20:34 ` Arnd Bergmann
2015-01-19 20:34 ` Arnd Bergmann
2015-01-20 2:15 ` Ding Tianhong
2015-01-20 2:15 ` Ding Tianhong
2015-01-20 2:15 ` Ding Tianhong
2015-01-20 12:01 ` Arnd Bergmann
2015-01-20 12:01 ` Arnd Bergmann
2015-01-20 18:12 ` Joe Perches
2015-01-20 18:12 ` Joe Perches
2015-01-14 10:19 ` [PATCH net-next v13 0/3] add hisilicon " Alexander Graf
2015-01-14 10:19 ` Alexander Graf
2015-01-15 8:37 ` Ding Tianhong
2015-01-15 8:37 ` Ding Tianhong
2015-01-15 8:37 ` Ding Tianhong
2015-01-15 9:42 ` Arnd Bergmann
2015-01-15 9:42 ` Arnd Bergmann
2015-01-15 12:39 ` Alexander Graf
2015-01-15 12:39 ` Alexander Graf
2015-01-15 12:56 ` Ding Tianhong [this message]
2015-01-15 12:56 ` Ding Tianhong
2015-01-15 12:56 ` Ding Tianhong
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=54B7B8F5.6060808@huawei.com \
--to=dingtianhong@huawei.com \
--cc=linux-arm-kernel@lists.infradead.org \
/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.