linux-kernel - [PATCH 0/10] Hugepage migration (v4)

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 for Android: free password hash cracker in your pocket

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

Message-Id: <1283488658-23137-1-git-send-email-n-horiguchi@ah.jp.nec.com>
Date:	Fri,  3 Sep 2010 13:37:28 +0900
From:	Naoya Horiguchi <n-horiguchi@...jp.nec.com>
To:	Andi Kleen <andi@...stfloor.org>
Cc:	Andrew Morton <akpm@...ux-foundation.org>,
	Christoph Lameter <cl@...ux-foundation.org>,
	Mel Gorman <mel@....ul.ie>,
	Wu Fengguang <fengguang.wu@...el.com>,
	"Jun'ichi Nomura" <j-nomura@...jp.nec.com>,
	linux-mm <linux-mm@...ck.org>,
	LKML <linux-kernel@...r.kernel.org>
Subject: [PATCH 0/10] Hugepage migration (v4)

Hi,

This is the 4th version of "hugepage migration" set.

Major changes: (see individual patches for more details)
- Folded alloc_buddy_huge_page_node() into alloc_buddy_huge_page().
- Fixed race condition between dequeue function and allocate function.
  This is based on the draft patch from Wu Fengguang. Thank you.
- Enabled missing path of recovery from uncorrected error on free hugepage.
- Change semantics of refcount of isolated hugepage from freelist.


Future works:

- Migration can fail for various reasons depending on various factors,
  so it's useful if soft offline can be retried when it noticed migration
  fails. This problem is a more general one because it's applied for
  soft offline of normal-sized pages. So we leave it as a future work.
  
- Corrupted hugepage counter implemeted in the previous version was dropped
  because it's not directly related to migration topic and have no serious
  impact on kernel behavior. We also leave it as the next work.


Summary:

 [PATCH 01/10] hugetlb: fix metadata corruption in hugetlb_fault()
 [PATCH 02/10] hugetlb: add allocate function for hugepage migration
 [PATCH 03/10] hugetlb: redefine hugepage copy functions
 [PATCH 04/10] hugetlb: hugepage migration core
 [PATCH 05/10] HWPOISON, hugetlb: add free check to dequeue_hwpoison_huge_page()
 [PATCH 06/10] hugetlb: move refcounting in hugepage allocation inside hugetlb_lock
 [PATCH 07/10] HWPOSION, hugetlb: recover from free hugepage error when !MF_COUNT_INCREASED
 [PATCH 08/10] HWPOISON, hugetlb: soft offlining for hugepage
 [PATCH 09/10] HWPOISON, hugetlb: fix unpoison for hugepage
 [PATCH 10/10] page-types.c: fix name of unpoison interface

 Documentation/vm/page-types.c |    2 +-
 fs/hugetlbfs/inode.c          |   15 +++
 include/linux/hugetlb.h       |   11 ++-
 include/linux/migrate.h       |   12 ++
 mm/hugetlb.c                  |  225 ++++++++++++++++++++++++++++------------
 mm/memory-failure.c           |   93 +++++++++++++----
 mm/migrate.c                  |  192 +++++++++++++++++++++++++++++++----
 mm/vmscan.c                   |    9 ++-
 8 files changed, 446 insertions(+), 113 deletions(-)


Thanks,
Naoya
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/