linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Yongqiang Liu <liuyongqiang13@huawei.com>
To: <catalin.marinas@arm.com>, <will.deacon@arm.com>
Cc: <linux-arm-kernel@lists.infradead.org>, <linux-mm@kvack.org>,
	<liuyongqiang13@huawei.com>, <wangkefeng.wang@huawei.com>
Subject: [QUESTION] arm64: mmap to the hugetlbfs with hugepagesize=512M got SIGILL
Date: Tue, 1 Jun 2021 17:34:42 +0800	[thread overview]
Message-ID: <e2f5855f-4f05-6341-c0a7-a4ca7069eca7@huawei.com> (raw)

Hi Catalin and Will,

when we mmap the addr NULL with MAP_FIXED flag to the hugetlbfs, system 
will return NULL successfully.

My question is: Why mmap to file with the hugepagesize=512M  we got 
SIGILL but mmap to the file with hugepagesize=2M we got a success ? Here 
is my test steps:

     1. echo 10 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages

         echo 10 > /sys/kernel/mm/hugepages/hugepages-524288kB/nr_hugepages

     2. mount none /mnt -t tmpfs

     3. mkdir /mnt/huge1

         mkdir /mnt/huge2

     4. mount none /mnt/huge1 -t hugetlbfs -o pagesize=512MB

         mount none /mnt/huge2 -t hugetlbfs -o pagesize=2MB

     5. test_case.c

         ... ...

         fd = open("/mnt/huge1/file", O_RDWR | O_CREAT, 0777);

         addr = mmap(NULL, hugepagesize, PROT_READ|PROT_WRITE|PROT_EXEC, 
MAP_PRIVATE | MAP_FIXED, fd, 0);

         ... ...

The result is , mmap to the /mnt/huge1/file will got a success while 
mmap to the /mnt/huge2/file will got SIGILL. Meanwile, we have found 
that the kernel return the address NULL success but set the variable failed.

Here is the pc when SIGILL occured:

         4009bc:   97ffff7d    bl  4007b0 <mmap@plt>

pc->4009c0:   aa0003e1    mov x1, x0



Kind regards,

Yongqiang Liu




             reply	other threads:[~2021-06-01  9:34 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-01  9:34 Yongqiang Liu [this message]
2021-06-01 15:00 ` David Hildenbrand
2021-06-02  1:33   ` Yongqiang Liu

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=e2f5855f-4f05-6341-c0a7-a4ca7069eca7@huawei.com \
    --to=liuyongqiang13@huawei.com \
    --cc=catalin.marinas@arm.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-mm@kvack.org \
    --cc=wangkefeng.wang@huawei.com \
    --cc=will.deacon@arm.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