From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from cantor2.suse.de ([195.135.220.15]:46141 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933543Ab1IILBI (ORCPT ); Fri, 9 Sep 2011 07:01:08 -0400 From: Mel Gorman To: Linux-MM Cc: Linux-Netdev , Linux-NFS , LKML , Andrew Morton , David Miller , Trond Myklebust , Neil Brown , Peter Zijlstra , Mel Gorman Subject: [PATCH 09/10] nfs: Prevent page allocator recursions with swap over NFS. Date: Fri, 9 Sep 2011 12:00:53 +0100 Message-Id: <1315566054-17209-10-git-send-email-mgorman@suse.de> In-Reply-To: <1315566054-17209-1-git-send-email-mgorman@suse.de> References: <1315566054-17209-1-git-send-email-mgorman@suse.de> Sender: linux-nfs-owner@vger.kernel.org List-ID: Content-Type: text/plain MIME-Version: 1.0 GFP_NOFS is _more_ permissive than GFP_NOIO in that it will initiate IO, just not of any filesystem data. The problem is that previously NOFS was correct because that avoids recursion into the NFS code. With swap-over-NFS, it is no longer correct as swap IO can lead to this recursion. Signed-off-by: Peter Zijlstra Signed-off-by: Mel Gorman --- fs/nfs/pagelist.c | 2 +- fs/nfs/write.c | 7 ++++--- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 1fcc294..5eb527d 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -27,7 +27,7 @@ static struct kmem_cache *nfs_page_cachep; static inline struct nfs_page * nfs_page_alloc(void) { - struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL); + struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_NOIO); if (p) INIT_LIST_HEAD(&p->wb_list); return p; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 475e1f2..78e4ce6 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -51,7 +51,7 @@ static mempool_t *nfs_commit_mempool; struct nfs_write_data *nfs_commitdata_alloc(void) { - struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS); + struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOIO); if (p) { memset(p, 0, sizeof(*p)); @@ -71,7 +71,7 @@ EXPORT_SYMBOL_GPL(nfs_commit_free); struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) { - struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS); + struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO); if (p) { memset(p, 0, sizeof(*p)); @@ -80,7 +80,8 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) if (pagecount <= ARRAY_SIZE(p->page_array)) p->pagevec = p->page_array; else { - p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS); + p->pagevec = kcalloc(pagecount, sizeof(struct page *), + GFP_NOIO); if (!p->pagevec) { mempool_free(p, nfs_wdata_mempool); p = NULL; -- 1.7.3.4