FS-Cache: Handle pages pending storage that get evicted under OOM conditions

Handle netfs pages that the vmscan algorithm wants to evict from the pagecache
under OOM conditions, but that are waiting for write to the cache.  Under these
conditions, vmscan calls the releasepage() function of the netfs, asking if a
page can be discarded.

The problem is typified by the following trace of a stuck process:

	kslowd005     D 0000000000000000     0  4253      2 0x00000080
	 ffff88001b14f370 0000000000000046 ffff880020d0d000 0000000000000007
	 0000000000000006 0000000000000001 ffff88001b14ffd8 ffff880020d0d2a8
	 000000000000ddf0 00000000000118c0 00000000000118c0 ffff880020d0d2a8
	Call Trace:
	 [<ffffffffa00782d8>] __fscache_wait_on_page_write+0x8b/0xa7 [fscache]
	 [<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34
	 [<ffffffffa0078240>] ? __fscache_check_page_write+0x63/0x70 [fscache]
	 [<ffffffffa00b671d>] nfs_fscache_release_page+0x4e/0xc4 [nfs]
	 [<ffffffffa00927f0>] nfs_release_page+0x3c/0x41 [nfs]
	 [<ffffffff810885d3>] try_to_release_page+0x32/0x3b
	 [<ffffffff81093203>] shrink_page_list+0x316/0x4ac
	 [<ffffffff8109372b>] shrink_inactive_list+0x392/0x67c
	 [<ffffffff813532fa>] ? __mutex_unlock_slowpath+0x100/0x10b
	 [<ffffffff81058df0>] ? trace_hardirqs_on_caller+0x10c/0x130
	 [<ffffffff8135330e>] ? mutex_unlock+0x9/0xb
	 [<ffffffff81093aa2>] shrink_list+0x8d/0x8f
	 [<ffffffff81093d1c>] shrink_zone+0x278/0x33c
	 [<ffffffff81052d6c>] ? ktime_get_ts+0xad/0xba
	 [<ffffffff81094b13>] try_to_free_pages+0x22e/0x392
	 [<ffffffff81091e24>] ? isolate_pages_global+0x0/0x212
	 [<ffffffff8108e743>] __alloc_pages_nodemask+0x3dc/0x5cf
	 [<ffffffff81089529>] grab_cache_page_write_begin+0x65/0xaa
	 [<ffffffff8110f8c0>] ext3_write_begin+0x78/0x1eb
	 [<ffffffff81089ec5>] generic_file_buffered_write+0x109/0x28c
	 [<ffffffff8103cb69>] ? current_fs_time+0x22/0x29
	 [<ffffffff8108a509>] __generic_file_aio_write+0x350/0x385
	 [<ffffffff8108a588>] ? generic_file_aio_write+0x4a/0xae
	 [<ffffffff8108a59e>] generic_file_aio_write+0x60/0xae
	 [<ffffffff810b2e82>] do_sync_write+0xe3/0x120
	 [<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34
	 [<ffffffff810b18e1>] ? __dentry_open+0x1a5/0x2b8
	 [<ffffffff810b1a76>] ? dentry_open+0x82/0x89
	 [<ffffffffa00e693c>] cachefiles_write_page+0x298/0x335 [cachefiles]
	 [<ffffffffa0077147>] fscache_write_op+0x178/0x2c2 [fscache]
	 [<ffffffffa0075656>] fscache_op_execute+0x7a/0xd1 [fscache]
	 [<ffffffff81082093>] slow_work_execute+0x18f/0x2d1
	 [<ffffffff8108239a>] slow_work_thread+0x1c5/0x308
	 [<ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34
	 [<ffffffff810821d5>] ? slow_work_thread+0x0/0x308
	 [<ffffffff8104be91>] kthread+0x7a/0x82
	 [<ffffffff8100beda>] child_rip+0xa/0x20
	 [<ffffffff8100b87c>] ? restore_args+0x0/0x30
	 [<ffffffff8102ef83>] ? tg_shares_up+0x171/0x227
	 [<ffffffff8104be17>] ? kthread+0x0/0x82
	 [<ffffffff8100bed0>] ? child_rip+0x0/0x20

In the above backtrace, the following is happening:

 (1) A page storage operation is being executed by a slow-work thread
     (fscache_write_op()).

 (2) FS-Cache farms the operation out to the cache to perform
     (cachefiles_write_page()).

 (3) CacheFiles is then calling Ext3 to perform the actual write, using Ext3's
     standard write (do_sync_write()) under KERNEL_DS directly from the netfs
     page.

 (4) However, for Ext3 to perform the write, it must allocate some memory, in
     particular, it must allocate at least one page cache page into which it
     can copy the data from the netfs page.

 (5) Under OOM conditions, the memory allocator can't immediately come up with
     a page, so it uses vmscan to find something to discard
     (try_to_free_pages()).

 (6) vmscan finds a clean netfs page it might be able to discard (possibly the
     one it's trying to write out).

 (7) The netfs is called to throw the page away (nfs_release_page()) - but it's
     called with __GFP_WAIT, so the netfs decides to wait for the store to
     complete (__fscache_wait_on_page_write()).

 (8) This blocks a slow-work processing thread - possibly against itself.

The system ends up stuck because it can't write out any netfs pages to the
cache without allocating more memory.

To avoid this, we make FS-Cache cancel some writes that aren't in the middle of
actually being performed.  This means that some data won't make it into the
cache this time.  To support this, a new FS-Cache function is added
fscache_maybe_release_page() that replaces what the netfs releasepage()
functions used to do with respect to the cache.

The decisions fscache_maybe_release_page() makes are counted and displayed
through /proc/fs/fscache/stats on a line labelled "VmScan".  There are four
counters provided: "nos=N" - pages that weren't pending storage; "gon=N" -
pages that were pending storage when we first looked, but weren't by the time
we got the object lock; "bsy=N" - pages that we ignored as they were actively
being written when we looked; and "can=N" - pages that we cancelled the storage
of.

What I'd really like to do is alter the behaviour of the cancellation
heuristics, depending on how necessary it is to expel pages.  If there are
plenty of other pages that aren't waiting to be written to the cache that
could be ejected first, then it would be nice to hold up on immediate
cancellation of cache writes - but I don't see a way of doing that.

Signed-off-by: David Howells <dhowells@redhat.com>

3 files changed, 93 insertions, 2 deletions

diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index a0769872b19c..e5046519b153 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -180,6 +180,11 @@ extern atomic_t fscache_n_store_pages;
 extern atomic_t fscache_n_store_radix_deletes;
 extern atomic_t fscache_n_store_pages_over_limit;
 
+extern atomic_t fscache_n_store_vmscan_not_storing;
+extern atomic_t fscache_n_store_vmscan_gone;
+extern atomic_t fscache_n_store_vmscan_busy;
+extern atomic_t fscache_n_store_vmscan_cancelled;
+
 extern atomic_t fscache_n_marks;
 extern atomic_t fscache_n_uncaches;
 
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 022a5da8e130..fc76798bd968 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -43,6 +43,75 @@ void __fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *pa
 EXPORT_SYMBOL(__fscache_wait_on_page_write);
 
 /*
+ * decide whether a page can be released, possibly by cancelling a store to it
+ * - we're allowed to sleep if __GFP_WAIT is flagged
+ */
+bool __fscache_maybe_release_page(struct fscache_cookie *cookie,
+				  struct page *page,
+				  gfp_t gfp)
+{
+	struct page *xpage;
+	void *val;
+
+	_enter("%p,%p,%x", cookie, page, gfp);
+
+	rcu_read_lock();
+	val = radix_tree_lookup(&cookie->stores, page->index);
+	if (!val) {
+		rcu_read_unlock();
+		fscache_stat(&fscache_n_store_vmscan_not_storing);
+		__fscache_uncache_page(cookie, page);
+		return true;
+	}
+
+	/* see if the page is actually undergoing storage - if so we can't get
+	 * rid of it till the cache has finished with it */
+	if (radix_tree_tag_get(&cookie->stores, page->index,
+			       FSCACHE_COOKIE_STORING_TAG)) {
+		rcu_read_unlock();
+		goto page_busy;
+	}
+
+	/* the page is pending storage, so we attempt to cancel the store and
+	 * discard the store request so that the page can be reclaimed */
+	spin_lock(&cookie->stores_lock);
+	rcu_read_unlock();
+
+	if (radix_tree_tag_get(&cookie->stores, page->index,
+			       FSCACHE_COOKIE_STORING_TAG)) {
+		/* the page started to undergo storage whilst we were looking,
+		 * so now we can only wait or return */
+		spin_unlock(&cookie->stores_lock);
+		goto page_busy;
+	}
+
+	xpage = radix_tree_delete(&cookie->stores, page->index);
+	spin_unlock(&cookie->stores_lock);
+
+	if (xpage) {
+		fscache_stat(&fscache_n_store_vmscan_cancelled);
+		fscache_stat(&fscache_n_store_radix_deletes);
+		ASSERTCMP(xpage, ==, page);
+	} else {
+		fscache_stat(&fscache_n_store_vmscan_gone);
+	}
+
+	wake_up_bit(&cookie->flags, 0);
+	if (xpage)
+		page_cache_release(xpage);
+	__fscache_uncache_page(cookie, page);
+	return true;
+
+page_busy:
+	/* we might want to wait here, but that could deadlock the allocator as
+	 * the slow-work threads writing to the cache may all end up sleeping
+	 * on memory allocation */
+	fscache_stat(&fscache_n_store_vmscan_busy);
+	return false;
+}
+EXPORT_SYMBOL(__fscache_maybe_release_page);
+
+/*
  * note that a page has finished being written to the cache
  */
 static void fscache_end_page_write(struct fscache_object *object,
@@ -57,6 +126,8 @@ 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);
+		radix_tree_tag_clear(&cookie->stores, page->index,
+				     FSCACHE_COOKIE_STORING_TAG);
 		if (!radix_tree_tag_get(&cookie->stores, page->index,
 					FSCACHE_COOKIE_PENDING_TAG)) {
 			fscache_stat(&fscache_n_store_radix_deletes);
@@ -640,8 +711,12 @@ static void fscache_write_op(struct fscache_operation *_op)
 		goto superseded;
 	}
 
-	radix_tree_tag_clear(&cookie->stores, page->index,
-			     FSCACHE_COOKIE_PENDING_TAG);
+	if (page) {
+		radix_tree_tag_set(&cookie->stores, page->index,
+				   FSCACHE_COOKIE_STORING_TAG);
+		radix_tree_tag_clear(&cookie->stores, page->index,
+				     FSCACHE_COOKIE_PENDING_TAG);
+	}
 
 	spin_unlock(&cookie->stores_lock);
 	spin_unlock(&object->lock);
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 045ba396dbf2..cda69994e06d 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -63,6 +63,11 @@ atomic_t fscache_n_store_pages;
 atomic_t fscache_n_store_radix_deletes;
 atomic_t fscache_n_store_pages_over_limit;
 
+atomic_t fscache_n_store_vmscan_not_storing;
+atomic_t fscache_n_store_vmscan_gone;
+atomic_t fscache_n_store_vmscan_busy;
+atomic_t fscache_n_store_vmscan_cancelled;
+
 atomic_t fscache_n_marks;
 atomic_t fscache_n_uncaches;
 
@@ -211,6 +216,12 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_store_radix_deletes),
 		   atomic_read(&fscache_n_store_pages_over_limit));
 
+	seq_printf(m, "VmScan : nos=%u gon=%u bsy=%u can=%u\n",
+		   atomic_read(&fscache_n_store_vmscan_not_storing),
+		   atomic_read(&fscache_n_store_vmscan_gone),
+		   atomic_read(&fscache_n_store_vmscan_busy),
+		   atomic_read(&fscache_n_store_vmscan_cancelled));
+
 	seq_printf(m, "Ops    : pend=%u run=%u enq=%u can=%u rej=%u\n",
 		   atomic_read(&fscache_n_op_pend),
 		   atomic_read(&fscache_n_op_run),