Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756671Ab0LERae (ORCPT ); Sun, 5 Dec 2010 12:30:34 -0500 Received: from mail-pv0-f174.google.com ([74.125.83.174]:60513 "EHLO mail-pv0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756633Ab0LERa0 (ORCPT ); Sun, 5 Dec 2010 12:30:26 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=from:to:cc:subject:date:message-id:x-mailer:in-reply-to:references; b=urvxUt+xvi1T27DASa1N4C4PCvxFa3JSFK9sXaEufCNdlWq67i557TdYVnTABPm4PQ eSoo+yDqudKtIEj+nRrNzk7Sof2JhPVZ85rf+lcr38QHDavLE/iLafirD+tZfS5DF0us o9uhk/ioZF4s6ZK3jk+D2GUwmp2td4L5c8ODs= From: Minchan Kim To: Andrew Morton Cc: Rik van Riel , KOSAKI Motohiro , linux-mm , LKML , Minchan Kim , Johannes Weiner , Nick Piggin , Mel Gorman , Wu Fengguang , Hugh Dickins Subject: [PATCH v4 7/7] Prevent activation of page in madvise_dontneed Date: Mon, 6 Dec 2010 02:29:15 +0900 Message-Id: X-Mailer: git-send-email 1.7.0.4 In-Reply-To: References: In-Reply-To: References: Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3645 Lines: 113 Now zap_pte_range alwayas activates pages which are pte_young && !VM_SequentialReadHint(vma). But in case of calling MADV_DONTNEED, it's unnecessary since the page wouldn't use any more. Signed-off-by: Minchan Kim Acked-by: Rik van Riel Reviewed-by: KOSAKI Motohiro Cc: KOSAKI Motohiro Cc: Johannes Weiner Cc: Nick Piggin Cc: Mel Gorman Cc: Wu Fengguang Cc: Hugh Dickins Changelog since v3: - Change variable name - suggested by Johannes - Union ignore_references with zap_details - suggested by Hugh Changelog since v2: - remove unnecessary description Changelog since v1: - change word from promote to activate - add activate argument to zap_pte_range and family function --- include/linux/mm.h | 4 +++- mm/madvise.c | 6 +++--- mm/memory.c | 5 ++++- 3 files changed, 10 insertions(+), 5 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 6522ae4..e57190f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -771,12 +771,14 @@ struct zap_details { pgoff_t last_index; /* Highest page->index to unmap */ spinlock_t *i_mmap_lock; /* For unmap_mapping_range: */ unsigned long truncate_count; /* Compare vm_truncate_count */ + bool ignore_references; /* For page activation */ }; #define __ZAP_DETAILS_INITIALIZER(name) \ { .nonlinear_vma = NULL \ , .check_mapping = NULL \ - , .i_mmap_lock = NULL } + , .i_mmap_lock = NULL \ + , .ignore_references = false } #define DEFINE_ZAP_DETAILS(name) \ struct zap_details name = __ZAP_DETAILS_INITIALIZER(name) diff --git a/mm/madvise.c b/mm/madvise.c index bfa17aa..8e7aba3 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -163,6 +163,7 @@ static long madvise_dontneed(struct vm_area_struct * vma, unsigned long start, unsigned long end) { DEFINE_ZAP_DETAILS(details); + details.ignore_references = true; *prev = vma; if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)) @@ -173,10 +174,9 @@ static long madvise_dontneed(struct vm_area_struct * vma, details.last_index = ULONG_MAX; zap_page_range(vma, start, end - start, &details); - } else { - + } else zap_page_range(vma, start, end - start, &details); - } + return 0; } diff --git a/mm/memory.c b/mm/memory.c index c0879bb..44d87e1 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -897,6 +897,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, pte_t *pte; spinlock_t *ptl; int rss[NR_MM_COUNTERS]; + bool ignore_references = details->ignore_references; init_rss_vec(rss); @@ -952,7 +953,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, if (pte_dirty(ptent)) set_page_dirty(page); if (pte_young(ptent) && - likely(!VM_SequentialReadHint(vma))) + likely(!VM_SequentialReadHint(vma)) && + !ignore_references) mark_page_accessed(page); rss[MM_FILEPAGES]--; } @@ -1218,6 +1220,7 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size) { DEFINE_ZAP_DETAILS(details); + details.ignore_references = true; if (address < vma->vm_start || address + size > vma->vm_end || !(vma->vm_flags & VM_PFNMAP)) return -1; -- 1.7.0.4 -- 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/