From: Yunqiang Su <ysu@wavecomp.com>
To: huangpei <huangpei@loongson.cn>
Cc: 徐成华 <xuchenghua@loongson.cn>,
"Paul Burton" <pburton@wavecomp.com>,
"Paul Burton" <pburton@wavecomp.com>,
"linux-mips@vger.kernel.org" <linux-mips@vger.kernel.org>,
"chenhc@lemote.com" <chenhc@lemote.com>,
"zhangfx@lemote.com" <zhangfx@lemote.com>,
"wuzhangjin@gmail.com" <wuzhangjin@gmail.com>,
"linux-mips@linux-mips.org" <linux-mips@linux-mips.org>
Subject: Re: [PATCH 1/2] MIPS: Loongson, add sync before target of branch between llsc
Date: Sat, 12 Jan 2019 03:41:56 +0000 [thread overview]
Message-ID: <D6CAABA8-132C-4BDB-AFE0-5E7D782D5142@wavecomp.com> (raw)
In-Reply-To: <20190112112518.4cc0b1d7@ambrosehua-ThinkPad-X201s>
>+#define __LS3A_WAR_LLSC " .set mips64r2\nsynci 0\n.set mips0\n"
>+#define __ls3a_war_llsc() __asm__ __volatile__("synci 0" : : :"memory”)
看起来这个只用于1000,所以我觉得名字应该是 __ls3x1k 或者类似的
俩下划线需要么?
> smp_llsc_mb in cmpxchg.h is enought
enought拼写错了
- __WEAK_LLSC_MB
"3: \n"
+ __WEAK_LLSC_MB
这里可能会影响其他CPU的性能?
#define TX49XX_ICACHE_INDEX_INV_WAR 0
#define ICACHE_REFILLS_WORKAROUND_WAR 0
#define R10000_LLSC_WAR 0
+#define LOONGSON_LLSC_WAR 0
#define MIPS34K_MISSED_ITLB_WAR 0
这个应该要搞个CONFIG_啥啥啥 ?毕竟以后的芯片很可能没这问题了。
> 在 2019年1月12日,上午11:25,huangpei <huangpei@loongson.cn> 写道:
>
> hi, this is the patch for ll/sc bug in Loongson3 based on Linux-4.20
> (8fe28cb58bcb235034b64cbbb7550a8a43fd88be)
>
> +. it cover all loongson3 CPU;
>
> +. to fix the ll/sc bug *sufficiently and exactly*, this patch shows
> how many places need to touch
>
> +. it is built ok for on Loongson3 and Cavium/Octeon, old version is
> tested in high pressure test
>
>
> On Fri, 11 Jan 2019 20:40:49 +0800 (GMT+08:00)
> 徐成华 <xuchenghua@loongson.cn> wrote:
>
>> Hi Paul Burton,
>>
>> For Loongson 3A1000 and 3A3000, when a memory access instruction
>> (load, store, or prefetch)'s executing occurs between the execution
>> of LL and SC, the success or failure of SC is not predictable.
>> Although programmer would not insert memory access instructions
>> between LL and SC, the memory instructions before LL in
>> program-order, may dynamically executed between the execution of
>> LL/SC, so a memory fence(SYNC) is needed before LL/LLD to avoid this
>> situation.
>>
>> Since 3A3000, we improved our hardware design to handle this case.
>> But we later deduce a rarely circumstance that some speculatively
>> executed memory instructions due to branch misprediction between
>> LL/SC still fall into the above case, so a memory fence(SYNC) at
>> branch-target(if its target is not between LL/SC) is needed for
>> 3A1000 and 3A3000.
>>
>> Our processor is continually evolving and we aim to to remove all
>> these workaround-SYNCs around LL/SC for new-come processor.
>>
>> 北京市海淀区中关村环保科技示范园龙芯产业园2号楼 100095电话: +86 (10)
>> 62546668传真: +86 (10)
>> 62600826www.loongson.cn本邮件及其附件含有龙芯中科技术有限公司的商业秘密信息,仅限于发送给上面地址中列出的个人或群组。禁止任何其他人以任何形式使用(包括但不限于全部或部
>> 分地泄露、复制或散发)本邮件及其附件中的信息。如果您错收本邮件,请您立即电话或邮件通知发件人并删除本邮件。
>>
>> This email and its attachments contain confidential information from
>> Loongson Technology Corporation Limited, which is intended only for
>> the person or entity whose address is listed above. Any use of the
>> information contained herein in any way (including, but not limited
>> to, total or partial disclosure, reproduction or dissemination) by
>> persons other than the intended recipient(s) is prohibited. If you
>> receive this email in error, please notify the sender by phone or
>> email immediately and delete it.
> <0001-loongson64-add-helper-for-ll-sc-bugfix-in-loongson3.patch><0002-loongson64-fix-ll-sc-bug-of-loongson3-in-inline-asm.patch><0003-loongson64-fix-ll-sc-bug-of-Loongson-3-in-handle_tlb.patch>
next prev parent reply other threads:[~2019-01-12 3:42 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-11 12:40 [PATCH 1/2] MIPS: Loongson, add sync before target of branch between llsc 徐成华
2019-01-11 12:45 ` huangpei
2019-01-11 19:00 ` Paul Burton
2019-01-12 8:02 ` 徐成华
2019-01-12 8:19 ` huangpei
2019-01-12 3:25 ` huangpei
2019-01-12 3:41 ` Yunqiang Su [this message]
2019-01-12 6:21 ` huangpei
-- strict thread matches above, loose matches on Subject: below --
2019-01-05 15:00 YunQiang Su
2019-01-09 22:08 ` Paul Burton
2019-01-10 1:59 ` Yunqiang Su
2019-01-10 17:35 ` Paul Burton
2019-01-10 18:42 ` YunQiang Su
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=D6CAABA8-132C-4BDB-AFE0-5E7D782D5142@wavecomp.com \
--to=ysu@wavecomp.com \
--cc=chenhc@lemote.com \
--cc=huangpei@loongson.cn \
--cc=linux-mips@linux-mips.org \
--cc=linux-mips@vger.kernel.org \
--cc=pburton@wavecomp.com \
--cc=wuzhangjin@gmail.com \
--cc=xuchenghua@loongson.cn \
--cc=zhangfx@lemote.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).