summaryrefslogtreecommitdiff
path: root/fs/fscache/page.c
diff options
context:
space:
mode:
authorMilosz Tanski <milosz@adfin.com>2013-08-22 01:30:11 +0400
committerDavid Howells <dhowells@redhat.com>2013-09-06 12:17:30 +0400
commit5a6f282a2052bb13171b53f03b34501cf72c33f1 (patch)
tree2bbad52f3d661f2dda68c476f16bd0bf708ca7c5 /fs/fscache/page.c
parent696f69b6b088f0f5b9470a5d008871c96354f531 (diff)
downloadlinux-5a6f282a2052bb13171b53f03b34501cf72c33f1.tar.xz
fscache: Netfs function for cleanup post readpages
Currently the fscache code expect the netfs to call fscache_readpages_or_alloc inside the aops readpages callback. It marks all the pages in the list provided by readahead with PG_private_2. In the cases that the netfs fails to read all the pages (which is legal) it ends up returning to the readahead and triggering a BUG. This happens because the page list still contains marked pages. This patch implements a simple fscache_readpages_cancel function that the netfs should call before returning from readpages. It will revoke the pages from the underlying cache backend and unmark them. The problem was originally worked out in the Ceph devel tree, but it also occurs in CIFS. It appears that NFS, AFS and 9P are okay as read_cache_pages() will clean up the unprocessed pages in the case of an error. This can be used to address the following oops: [12410647.597278] BUG: Bad page state in process petabucket pfn:3d504e [12410647.597292] page:ffffea000f541380 count:0 mapcount:0 mapping: (null) index:0x0 [12410647.597298] page flags: 0x200000000001000(private_2) ... [12410647.597334] Call Trace: [12410647.597345] [<ffffffff815523f2>] dump_stack+0x19/0x1b [12410647.597356] [<ffffffff8111def7>] bad_page+0xc7/0x120 [12410647.597359] [<ffffffff8111e49e>] free_pages_prepare+0x10e/0x120 [12410647.597361] [<ffffffff8111fc80>] free_hot_cold_page+0x40/0x170 [12410647.597363] [<ffffffff81123507>] __put_single_page+0x27/0x30 [12410647.597365] [<ffffffff81123df5>] put_page+0x25/0x40 [12410647.597376] [<ffffffffa02bdcf9>] ceph_readpages+0x2e9/0x6e0 [ceph] [12410647.597379] [<ffffffff81122a8f>] __do_page_cache_readahead+0x1af/0x260 [12410647.597382] [<ffffffff81122ea1>] ra_submit+0x21/0x30 [12410647.597384] [<ffffffff81118f64>] filemap_fault+0x254/0x490 [12410647.597387] [<ffffffff8113a74f>] __do_fault+0x6f/0x4e0 [12410647.597391] [<ffffffff810125bd>] ? __switch_to+0x16d/0x4a0 [12410647.597395] [<ffffffff810865ba>] ? finish_task_switch+0x5a/0xc0 [12410647.597398] [<ffffffff8113d856>] handle_pte_fault+0xf6/0x930 [12410647.597401] [<ffffffff81008c33>] ? pte_mfn_to_pfn+0x93/0x110 [12410647.597403] [<ffffffff81008cce>] ? xen_pmd_val+0xe/0x10 [12410647.597405] [<ffffffff81005469>] ? __raw_callee_save_xen_pmd_val+0x11/0x1e [12410647.597407] [<ffffffff8113f361>] handle_mm_fault+0x251/0x370 [12410647.597411] [<ffffffff812b0ac4>] ? call_rwsem_down_read_failed+0x14/0x30 [12410647.597414] [<ffffffff8155bffa>] __do_page_fault+0x1aa/0x550 [12410647.597418] [<ffffffff8108011d>] ? up_write+0x1d/0x20 [12410647.597422] [<ffffffff8113141c>] ? vm_mmap_pgoff+0xbc/0xe0 [12410647.597425] [<ffffffff81143bb8>] ? SyS_mmap_pgoff+0xd8/0x240 [12410647.597427] [<ffffffff8155c3ae>] do_page_fault+0xe/0x10 [12410647.597431] [<ffffffff81558818>] page_fault+0x28/0x30 Signed-off-by: Milosz Tanski <milosz@adfin.com> Signed-off-by: David Howells <dhowells@redhat.com>
Diffstat (limited to 'fs/fscache/page.c')
-rw-r--r--fs/fscache/page.c16
1 files changed, 16 insertions, 0 deletions
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 793e3d5ca4b5..8702b732109a 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -701,6 +701,22 @@ nobufs:
EXPORT_SYMBOL(__fscache_alloc_page);
/*
+ * Unmark pages allocate in the readahead code path (via:
+ * fscache_readpages_or_alloc) after delegating to the base filesystem
+ */
+void __fscache_readpages_cancel(struct fscache_cookie *cookie,
+ struct list_head *pages)
+{
+ struct page *page;
+
+ list_for_each_entry(page, pages, lru) {
+ if (PageFsCache(page))
+ __fscache_uncache_page(cookie, page);
+ }
+}
+EXPORT_SYMBOL(__fscache_readpages_cancel);
+
+/*
* release a write op reference
*/
static void fscache_release_write_op(struct fscache_operation *_op)