Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756150Ab1FNK4d (ORCPT ); Tue, 14 Jun 2011 06:56:33 -0400 Received: from smtp-out.google.com ([74.125.121.67]:12980 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756013Ab1FNK4c (ORCPT ); Tue, 14 Jun 2011 06:56:32 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=google.com; s=beta; h=date:from:x-x-sender:to:cc:subject:in-reply-to:message-id :references:user-agent:mime-version:content-type; b=jb8marMNUKDO2wC2KqCM4DzPduSjnDuHWnbMP0ePj9+3/6hrTfy98W+LuE2GR/3tQv dB5RsmUyB2wLojsHuLSA== Date: Tue, 14 Jun 2011 03:56:16 -0700 (PDT) From: Hugh Dickins X-X-Sender: hugh@sister.anvils To: Andrew Morton cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: [PATCH 10/12] tmpfs: convert shmem_writepage and enable swap In-Reply-To: Message-ID: References: User-Agent: Alpine 2.00 (LSU 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-System-Of-Record: true Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6265 Lines: 188 Convert shmem_writepage() to use shmem_delete_from_page_cache() to use shmem_radix_tree_replace() to substitute swap entry for page pointer atomically in the radix tree. As with shmem_add_to_page_cache(), it's not entirely satisfactory to be copying such code from delete_from_swap_cache, but again judged easier to sell than making its other callers go through the extras. Remove the toy implementation's shmem_put_swap() and shmem_get_swap(), now unreferenced, and the hack to disable swap: it's now good to go. The way things have worked out, info->lock no longer helps to guard the shmem_swaplist: we increment swapped under shmem_swaplist_mutex only. That global mutex exclusion between shmem_writepage() and shmem_unuse() is not pretty, and we ought to find another way; but it's been forced on us by recent race discoveries, not a consequence of this patchset. And what has become of the WARN_ON_ONCE(1) free_swap_and_cache() if a swap entry was found already present? That's no longer possible, the (unknown) one inserting this page into filecache would hit the swap entry occupying that slot. Signed-off-by: Hugh Dickins --- mm/shmem.c | 88 +++++++++++++++++++++------------------------------ 1 file changed, 37 insertions(+), 51 deletions(-) --- linux.orig/mm/shmem.c 2011-06-14 00:45:20.685161581 -0700 +++ linux/mm/shmem.c 2011-06-14 00:54:36.499917716 -0700 @@ -6,7 +6,8 @@ * 2000-2001 Christoph Rohland * 2000-2001 SAP AG * 2002 Red Hat Inc. - * Copyright (C) 2002-2005 Hugh Dickins. + * Copyright (C) 2002-2011 Hugh Dickins. + * Copyright (C) 2011 Google Inc. * Copyright (C) 2002-2005 VERITAS Software Corporation. * Copyright (C) 2004 Andi Kleen, SuSE Labs * @@ -219,19 +220,6 @@ static void shmem_recalc_inode(struct in } } -static void shmem_put_swap(struct shmem_inode_info *info, pgoff_t index, - swp_entry_t swap) -{ - if (index < SHMEM_NR_DIRECT) - info->i_direct[index] = swap; -} - -static swp_entry_t shmem_get_swap(struct shmem_inode_info *info, pgoff_t index) -{ - return (index < SHMEM_NR_DIRECT) ? - info->i_direct[index] : (swp_entry_t){0}; -} - /* * Replace item expected in radix tree by a new item, while holding tree lock. */ @@ -300,6 +288,25 @@ static int shmem_add_to_page_cache(struc } /* + * Like delete_from_page_cache, but substitutes swap for page. + */ +static void shmem_delete_from_page_cache(struct page *page, void *radswap) +{ + struct address_space *mapping = page->mapping; + int error; + + spin_lock_irq(&mapping->tree_lock); + error = shmem_radix_tree_replace(mapping, page->index, page, radswap); + page->mapping = NULL; + mapping->nrpages--; + __dec_zone_page_state(page, NR_FILE_PAGES); + __dec_zone_page_state(page, NR_SHMEM); + spin_unlock_irq(&mapping->tree_lock); + page_cache_release(page); + BUG_ON(error); +} + +/* * Like find_get_pages, but collecting swap entries as well as pages. */ static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping, @@ -664,14 +671,10 @@ int shmem_unuse(swp_entry_t swap, struct mutex_lock(&shmem_swaplist_mutex); list_for_each_safe(this, next, &shmem_swaplist) { info = list_entry(this, struct shmem_inode_info, swaplist); - if (!info->swapped) { - spin_lock(&info->lock); - if (!info->swapped) - list_del_init(&info->swaplist); - spin_unlock(&info->lock); - } if (info->swapped) found = shmem_unuse_inode(info, swap, page); + else + list_del_init(&info->swaplist); cond_resched(); if (found) break; @@ -694,10 +697,10 @@ out: static int shmem_writepage(struct page *page, struct writeback_control *wbc) { struct shmem_inode_info *info; - swp_entry_t swap, oswap; struct address_space *mapping; - pgoff_t index; struct inode *inode; + swp_entry_t swap; + pgoff_t index; BUG_ON(!PageLocked(page)); mapping = page->mapping; @@ -720,55 +723,38 @@ static int shmem_writepage(struct page * WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ goto redirty; } - - /* - * Disable even the toy swapping implementation, while we convert - * functions one by one to having swap entries in the radix tree. - */ - if (index < ULONG_MAX) - goto redirty; - swap = get_swap_page(); if (!swap.val) goto redirty; /* * Add inode to shmem_unuse()'s list of swapped-out inodes, - * if it's not already there. Do it now because we cannot take - * mutex while holding spinlock, and must do so before the page - * is moved to swap cache, when its pagelock no longer protects + * if it's not already there. Do it now before the page is + * moved to swap cache, when its pagelock no longer protects * the inode from eviction. But don't unlock the mutex until - * we've taken the spinlock, because shmem_unuse_inode() will - * prune a !swapped inode from the swaplist under both locks. + * we've incremented swapped, because shmem_unuse_inode() will + * prune a !swapped inode from the swaplist under this mutex. */ mutex_lock(&shmem_swaplist_mutex); if (list_empty(&info->swaplist)) list_add_tail(&info->swaplist, &shmem_swaplist); - spin_lock(&info->lock); - mutex_unlock(&shmem_swaplist_mutex); - - oswap = shmem_get_swap(info, index); - if (oswap.val) { - WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ - free_swap_and_cache(oswap); - shmem_put_swap(info, index, (swp_entry_t){0}); - info->swapped--; - } - shmem_recalc_inode(inode); - if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { - delete_from_page_cache(page); - shmem_put_swap(info, index, swap); - info->swapped++; swap_shmem_alloc(swap); + shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); + + spin_lock(&info->lock); + info->swapped++; + shmem_recalc_inode(inode); spin_unlock(&info->lock); + + mutex_unlock(&shmem_swaplist_mutex); BUG_ON(page_mapped(page)); swap_writepage(page, wbc); return 0; } - spin_unlock(&info->lock); + mutex_unlock(&shmem_swaplist_mutex); swapcache_free(swap, NULL); redirty: set_page_dirty(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/