From eb65b85e1bce06b665b3568c19a249cd886fa6ff Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 23 Jul 2012 13:58:51 -0400 Subject: nfs: skip commit in releasepage if we're freeing memory for fs-related reasons commit 5cf02d09b50b1ee1c2d536c9cf64af5a7d433f56 upstream. We've had some reports of a deadlock where rpciod ends up with a stack trace like this: PID: 2507 TASK: ffff88103691ab40 CPU: 14 COMMAND: "rpciod/14" #0 [ffff8810343bf2f0] schedule at ffffffff814dabd9 #1 [ffff8810343bf3b8] nfs_wait_bit_killable at ffffffffa038fc04 [nfs] #2 [ffff8810343bf3c8] __wait_on_bit at ffffffff814dbc2f #3 [ffff8810343bf418] out_of_line_wait_on_bit at ffffffff814dbcd8 #4 [ffff8810343bf488] nfs_commit_inode at ffffffffa039e0c1 [nfs] #5 [ffff8810343bf4f8] nfs_release_page at ffffffffa038bef6 [nfs] #6 [ffff8810343bf528] try_to_release_page at ffffffff8110c670 #7 [ffff8810343bf538] shrink_page_list.clone.0 at ffffffff81126271 #8 [ffff8810343bf668] shrink_inactive_list at ffffffff81126638 #9 [ffff8810343bf818] shrink_zone at ffffffff8112788f #10 [ffff8810343bf8c8] do_try_to_free_pages at ffffffff81127b1e #11 [ffff8810343bf958] try_to_free_pages at ffffffff8112812f #12 [ffff8810343bfa08] __alloc_pages_nodemask at ffffffff8111fdad #13 [ffff8810343bfb28] kmem_getpages at ffffffff81159942 #14 [ffff8810343bfb58] fallback_alloc at ffffffff8115a55a #15 [ffff8810343bfbd8] ____cache_alloc_node at ffffffff8115a2d9 #16 [ffff8810343bfc38] kmem_cache_alloc at ffffffff8115b09b #17 [ffff8810343bfc78] sk_prot_alloc at ffffffff81411808 #18 [ffff8810343bfcb8] sk_alloc at ffffffff8141197c #19 [ffff8810343bfce8] inet_create at ffffffff81483ba6 #20 [ffff8810343bfd38] __sock_create at ffffffff8140b4a7 #21 [ffff8810343bfd98] xs_create_sock at ffffffffa01f649b [sunrpc] #22 [ffff8810343bfdd8] xs_tcp_setup_socket at ffffffffa01f6965 [sunrpc] #23 [ffff8810343bfe38] worker_thread at ffffffff810887d0 #24 [ffff8810343bfee8] kthread at ffffffff8108dd96 #25 [ffff8810343bff48] kernel_thread at ffffffff8100c1ca rpciod is trying to allocate memory for a new socket to talk to the server. The VM ends up calling ->releasepage to get more memory, and it tries to do a blocking commit. That commit can't succeed however without a connected socket, so we deadlock. Fix this by setting PF_FSTRANS on the workqueue task prior to doing the socket allocation, and having nfs_release_page check for that flag when deciding whether to do a commit call. Also, set PF_FSTRANS unconditionally in rpc_async_schedule since that function can also do allocations sometimes. Signed-off-by: Jeff Layton Signed-off-by: Trond Myklebust Signed-off-by: Greg Kroah-Hartman --- fs/nfs/file.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/nfs/file.c b/fs/nfs/file.c index dd2f130..6c6e2c4 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -493,8 +493,11 @@ static int nfs_release_page(struct page *page, gfp_t gfp) dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page); - /* Only do I/O if gfp is a superset of GFP_KERNEL */ - if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL) { + /* Only do I/O if gfp is a superset of GFP_KERNEL, and we're not + * doing this memory reclaim for a fs-related allocation. + */ + if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL && + !(current->flags & PF_FSTRANS)) { int how = FLUSH_SYNC; /* Don't let kswapd deadlock waiting for OOM RPC calls */ -- cgit v1.1