From b34df792b4e9e311db47fad27949095d0629c197 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 19 Nov 2009 18:11:14 +0000
Subject: FS-Cache: Use radix tree preload correctly in tracking of pages to be
 stored

__fscache_write_page() attempts to load the radix tree preallocation pool for
the CPU it is on before calling radix_tree_insert(), as the insertion must be
done inside a pair of spinlocks.

Use of the preallocation pool, however, is contingent on the radix tree being
initialised without __GFP_WAIT specified.  __fscache_acquire_cookie() was
passing GFP_NOFS to INIT_RADIX_TREE() - but that includes __GFP_WAIT.

The solution is to AND out __GFP_WAIT.

Additionally, the banner comment to radix_tree_preload() is altered to make
note of this prerequisite.  Possibly there should be a WARN_ON() too.

Without this fix, I have seen the following recursive deadlock caused by
radix_tree_insert() attempting to allocate memory inside the spinlocked
region, which resulted in FS-Cache being called back into to release memory -
which required the spinlock already held.

=============================================
[ INFO: possible recursive locking detected ]
2.6.32-rc6-cachefs #24
---------------------------------------------
nfsiod/7916 is trying to acquire lock:
 (&cookie->lock){+.+.-.}, at: [<ffffffffa0076872>] __fscache_uncache_page+0xdb/0x160 [fscache]

but task is already holding lock:
 (&cookie->lock){+.+.-.}, at: [<ffffffffa0076acc>] __fscache_write_page+0x15c/0x3f3 [fscache]

other info that might help us debug this:
5 locks held by nfsiod/7916:
 #0:  (nfsiod){+.+.+.}, at: [<ffffffff81048290>] worker_thread+0x19a/0x2e2
 #1:  (&task->u.tk_work#2){+.+.+.}, at: [<ffffffff81048290>] worker_thread+0x19a/0x2e2
 #2:  (&cookie->lock){+.+.-.}, at: [<ffffffffa0076acc>] __fscache_write_page+0x15c/0x3f3 [fscache]
 #3:  (&object->lock#2){+.+.-.}, at: [<ffffffffa0076b07>] __fscache_write_page+0x197/0x3f3 [fscache]
 #4:  (&cookie->stores_lock){+.+...}, at: [<ffffffffa0076b0f>] __fscache_write_page+0x19f/0x3f3 [fscache]

stack backtrace:
Pid: 7916, comm: nfsiod Not tainted 2.6.32-rc6-cachefs #24
Call Trace:
 [<ffffffff8105ac7f>] __lock_acquire+0x1649/0x16e3
 [<ffffffff81059ded>] ? __lock_acquire+0x7b7/0x16e3
 [<ffffffff8100e27d>] ? dump_trace+0x248/0x257
 [<ffffffff8105ad70>] lock_acquire+0x57/0x6d
 [<ffffffffa0076872>] ? __fscache_uncache_page+0xdb/0x160 [fscache]
 [<ffffffff8135467c>] _spin_lock+0x2c/0x3b
 [<ffffffffa0076872>] ? __fscache_uncache_page+0xdb/0x160 [fscache]
 [<ffffffffa0076872>] __fscache_uncache_page+0xdb/0x160 [fscache]
 [<ffffffffa0077eb7>] ? __fscache_check_page_write+0x0/0x71 [fscache]
 [<ffffffffa00b4755>] nfs_fscache_release_page+0x86/0xc4 [nfs]
 [<ffffffffa00907f0>] nfs_release_page+0x3c/0x41 [nfs]
 [<ffffffff81087ffb>] try_to_release_page+0x32/0x3b
 [<ffffffff81092c2b>] shrink_page_list+0x316/0x4ac
 [<ffffffff81058a9b>] ? mark_held_locks+0x52/0x70
 [<ffffffff8135451b>] ? _spin_unlock_irq+0x2b/0x31
 [<ffffffff81093153>] shrink_inactive_list+0x392/0x67c
 [<ffffffff81058a9b>] ? mark_held_locks+0x52/0x70
 [<ffffffff810934ca>] shrink_list+0x8d/0x8f
 [<ffffffff81093744>] shrink_zone+0x278/0x33c
 [<ffffffff81052c70>] ? ktime_get_ts+0xad/0xba
 [<ffffffff8109453b>] try_to_free_pages+0x22e/0x392
 [<ffffffff8109184c>] ? isolate_pages_global+0x0/0x212
 [<ffffffff8108e16b>] __alloc_pages_nodemask+0x3dc/0x5cf
 [<ffffffff810ae24a>] cache_alloc_refill+0x34d/0x6c1
 [<ffffffff811bcf74>] ? radix_tree_node_alloc+0x52/0x5c
 [<ffffffff810ae929>] kmem_cache_alloc+0xb2/0x118
 [<ffffffff811bcf74>] radix_tree_node_alloc+0x52/0x5c
 [<ffffffff811bcfd5>] radix_tree_insert+0x57/0x19c
 [<ffffffffa0076b53>] __fscache_write_page+0x1e3/0x3f3 [fscache]
 [<ffffffffa00b4248>] __nfs_readpage_to_fscache+0x58/0x11e [nfs]
 [<ffffffffa009bb77>] nfs_readpage_release+0x34/0x9b [nfs]
 [<ffffffffa009c0d9>] nfs_readpage_release_full+0x32/0x4b [nfs]
 [<ffffffffa0006cff>] rpc_release_calldata+0x12/0x14 [sunrpc]
 [<ffffffffa0006e2d>] rpc_free_task+0x59/0x61 [sunrpc]
 [<ffffffffa0006f03>] rpc_async_release+0x10/0x12 [sunrpc]
 [<ffffffff810482e5>] worker_thread+0x1ef/0x2e2
 [<ffffffff81048290>] ? worker_thread+0x19a/0x2e2
 [<ffffffff81352433>] ? thread_return+0x3e/0x101
 [<ffffffffa0006ef3>] ? rpc_async_release+0x0/0x12 [sunrpc]
 [<ffffffff8104bff5>] ? autoremove_wake_function+0x0/0x34
 [<ffffffff81058d25>] ? trace_hardirqs_on+0xd/0xf
 [<ffffffff810480f6>] ? worker_thread+0x0/0x2e2
 [<ffffffff8104bd21>] kthread+0x7a/0x82
 [<ffffffff8100beda>] child_rip+0xa/0x20
 [<ffffffff8100b87c>] ? restore_args+0x0/0x30
 [<ffffffff8104c2b9>] ? add_wait_queue+0x15/0x44
 [<ffffffff8104bca7>] ? kthread+0x0/0x82
 [<ffffffff8100bed0>] ? child_rip+0x0/0x20

Signed-off-by: David Howells <dhowells@redhat.com>
---
 lib/radix-tree.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'lib/radix-tree.c')

diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 23abbd93cae..ae610685556 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -200,6 +200,9 @@ radix_tree_node_free(struct radix_tree_node *node)
  * ensure that the addition of a single element in the tree cannot fail.  On
  * success, return zero, with preemption disabled.  On error, return -ENOMEM
  * with preemption not disabled.
+ *
+ * To make use of this facility, the radix tree must be initialised without
+ * __GFP_WAIT being passed to INIT_RADIX_TREE().
  */
 int radix_tree_preload(gfp_t gfp_mask)
 {
-- 
cgit v1.2.3-70-g09d2


From 285e728b0ac55b53a673114096168d6f74930167 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 19 Nov 2009 18:11:29 +0000
Subject: FS-Cache: Don't delete pending pages from the page-store tracking
 tree

Don't delete pending pages from the page-store tracking tree, but rather send
them for another write as they've presumably been updated.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 fs/fscache/page.c | 7 +++++--
 lib/radix-tree.c  | 2 --
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'lib/radix-tree.c')

diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 3ea8897bc21..022a5da8e13 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -57,8 +57,11 @@ static void fscache_end_page_write(struct fscache_object *object,
 		/* delete the page from the tree if it is now no longer
 		 * pending */
 		spin_lock(&cookie->stores_lock);
-		fscache_stat(&fscache_n_store_radix_deletes);
-		xpage = radix_tree_delete(&cookie->stores, page->index);
+		if (!radix_tree_tag_get(&cookie->stores, page->index,
+					FSCACHE_COOKIE_PENDING_TAG)) {
+			fscache_stat(&fscache_n_store_radix_deletes);
+			xpage = radix_tree_delete(&cookie->stores, page->index);
+		}
 		spin_unlock(&cookie->stores_lock);
 		wake_up_bit(&cookie->flags, 0);
 	}
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index ae610685556..92cdd9936e3 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -546,7 +546,6 @@ out:
 }
 EXPORT_SYMBOL(radix_tree_tag_clear);
 
-#ifndef __KERNEL__	/* Only the test harness uses this at present */
 /**
  * radix_tree_tag_get - get a tag on a radix tree node
  * @root:		radix tree root
@@ -609,7 +608,6 @@ int radix_tree_tag_get(struct radix_tree_root *root,
 	}
 }
 EXPORT_SYMBOL(radix_tree_tag_get);
-#endif
 
 /**
  *	radix_tree_next_hole    -    find the next hole (not-present entry)
-- 
cgit v1.2.3-70-g09d2