linux-kernel - [-mm patch] Correct add_bd

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Date:	Mon, 11 Sep 2006 20:36:47 -0400
From:	"Jun'ichi Nomura" <j-nomura@...jp.nec.com>
To:	linux-kernel@...r.kernel.org, Andrew Morton <akpm@...l.org>
CC:	rdunlap@...otime.net, Alasdair Kergon <agk@...hat.com>
Subject: [-mm patch] Correct add_bd_holder() return value

Hi,

In blockdevc-check-errors.patch, add_bd_holder() is modified to
return error values when some of its operation failed.
Among them, it returns -EEXIST when a given bd_holder object already
exists in the list.
However, in this case, the function completed its work successfully
and need no action by its caller other than freeing unused bd_holder
object.
So I think it's better to return success after freeing by itself.

Otherwise, bd_claim-ing with same claim pointer will fail.
Typically, lvresize will fails with following message:
  device-mapper: reload ioctl failed: Invalid argument
and you'll see messages like below in kernel log:
  device-mapper: table: 254:13: linear: dm-linear: Device lookup failed
  device-mapper: ioctl: error adding target to table

Similarly, it should not add bd_holder to the list if either one
of symlinking fails. I don't have a test case for this to happen
but it should cause dereference of freed pointer.

Thanks,
-- 
Jun'ichi Nomura, NEC Corporation of America

View attachment "correct-add_bd_holder-return-value.patch" of type "text/x-patch" (1981 bytes)