Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751468AbVK3RMA (ORCPT ); Wed, 30 Nov 2005 12:12:00 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751467AbVK3RMA (ORCPT ); Wed, 30 Nov 2005 12:12:00 -0500 Received: from omx2-ext.sgi.com ([192.48.171.19]:62852 "EHLO omx2.sgi.com") by vger.kernel.org with ESMTP id S1751468AbVK3RL7 (ORCPT ); Wed, 30 Nov 2005 12:11:59 -0500 Date: Wed, 30 Nov 2005 09:11:02 -0800 (PST) From: Christoph Lameter To: akpm@osdl.org Cc: linux-kernel@vger.kernel.org, lhms-devel@lists.sourceforge.net, Cliff Wickman , Christoph Lameter , KAMEZAWA Hiroyuki Message-Id: <20051130171102.19405.62052.sendpatchset@schroedinger.engr.sgi.com> In-Reply-To: <20051130171056.19405.95644.sendpatchset@schroedinger.engr.sgi.com> References: <20051130171056.19405.95644.sendpatchset@schroedinger.engr.sgi.com> Subject: [PATCH 1/5] Direct Migration V6: PageSwapCache checks Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3203 Lines: 90 Check for PageSwapCache after looking up and locking a swap page. The page migration code may change a swap pte to point to a different page under lock_page(). If that happens then the vm must retry the lookup operation in the swap space to find the correct page number. There are a couple of locations in the VM where a lock_page() is done on a swap page. In these locations we need to check afterwards if the page was migrated. If the page was migrated then the old page that was looked up before was freed and no longer has the PageSwapCache bit set. Signed-off-by: Hirokazu Takahashi Signed-off-by: Dave Hansen Signed-off-by: Christoph Lameter Index: linux-2.6.15-rc3-mm1/mm/memory.c =================================================================== --- linux-2.6.15-rc3-mm1.orig/mm/memory.c 2005-11-30 08:46:40.000000000 -0800 +++ linux-2.6.15-rc3-mm1/mm/memory.c 2005-11-30 08:46:44.000000000 -0800 @@ -1882,6 +1882,7 @@ static int do_swap_page(struct mm_struct goto out; entry = pte_to_swp_entry(orig_pte); +again: page = lookup_swap_cache(entry); if (!page) { swapin_readahead(entry, address, vma); @@ -1905,6 +1906,12 @@ static int do_swap_page(struct mm_struct mark_page_accessed(page); lock_page(page); + if (!PageSwapCache(page)) { + /* Page migration has occured */ + unlock_page(page); + page_cache_release(page); + goto again; + } /* * Back out if somebody else already faulted in this pte. Index: linux-2.6.15-rc3-mm1/mm/shmem.c =================================================================== --- linux-2.6.15-rc3-mm1.orig/mm/shmem.c 2005-11-30 08:46:40.000000000 -0800 +++ linux-2.6.15-rc3-mm1/mm/shmem.c 2005-11-30 08:46:44.000000000 -0800 @@ -1028,6 +1028,14 @@ repeat: page_cache_release(swappage); goto repeat; } + if (!PageSwapCache(swappage)) { + /* Page migration has occured */ + shmem_swp_unmap(entry); + spin_unlock(&info->lock); + unlock_page(swappage); + page_cache_release(swappage); + goto repeat; + } if (PageWriteback(swappage)) { shmem_swp_unmap(entry); spin_unlock(&info->lock); Index: linux-2.6.15-rc3-mm1/mm/swapfile.c =================================================================== --- linux-2.6.15-rc3-mm1.orig/mm/swapfile.c 2005-11-28 19:51:27.000000000 -0800 +++ linux-2.6.15-rc3-mm1/mm/swapfile.c 2005-11-30 08:46:44.000000000 -0800 @@ -624,6 +624,7 @@ static int try_to_unuse(unsigned int typ */ swap_map = &si->swap_map[i]; entry = swp_entry(type, i); +again: page = read_swap_cache_async(entry, NULL, 0); if (!page) { /* @@ -658,6 +659,12 @@ static int try_to_unuse(unsigned int typ wait_on_page_locked(page); wait_on_page_writeback(page); lock_page(page); + if (!PageSwapCache(page)) { + /* Page migration has occured */ + unlock_page(page); + page_cache_release(page); + goto again; + } wait_on_page_writeback(page); /* - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/