mm: only enforce stable page writes if the backing device requires it

Create a helper function to check if a backing device requires stable
page writes and, if so, performs the necessary wait.  Then, make it so
that all points in the memory manager that handle making pages writable
use the helper function.  This should provide stable page write support
to most filesystems, while eliminating unnecessary waiting for devices
that don't require the feature.

Before this patchset, all filesystems would block, regardless of whether
or not it was necessary.  ext3 would wait, but still generate occasional
checksum errors.  The network filesystems were left to do their own
thing, so they'd wait too.

After this patchset, all the disk filesystems except ext3 and btrfs will
wait only if the hardware requires it.  ext3 (if necessary) snapshots
pages instead of blocking, and btrfs provides its own bdi so the mm will
never wait.  Network filesystems haven't been touched, so either they
provide their own stable page guarantees or they don't block at all.
The blocking behavior is back to what it was before 3.0 if you don't
have a disk requiring stable page writes.

Here's the result of using dbench to test latency on ext2:

3.8.0-rc3:
 Operation      Count    AvgLat    MaxLat
 ----------------------------------------
 WriteX        109347     0.028    59.817
 ReadX         347180     0.004     3.391
 Flush          15514    29.828   287.283

Throughput 57.429 MB/sec  4 clients  4 procs  max_latency=287.290 ms

3.8.0-rc3 + patches:
 WriteX        105556     0.029     4.273
 ReadX         335004     0.005     4.112
 Flush          14982    30.540   298.634

Throughput 55.4496 MB/sec  4 clients  4 procs  max_latency=298.650 ms

As you can see, the maximum write latency drops considerably with this
patch enabled.  The other filesystems (ext3/ext4/xfs/btrfs) behave
similarly, but see the cover letter for those results.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Acked-by: Steven Whitehouse <swhiteho@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Artem Bityutskiy <dedekind1@gmail.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Eric Van Hensbergen <ericvh@gmail.com>
Cc: Ron Minnich <rminnich@sandia.gov>
Cc: Latchesar Ionkov <lucho@ionkov.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

7 files changed, 27 insertions, 5 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 7a75c3e..2ea9cd44 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2359,7 +2359,7 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 	if (unlikely(ret < 0))
 		goto out_unlock;
 	set_page_dirty(page);
-	wait_on_page_writeback(page);
+	wait_for_stable_page(page);
 	return 0;
 out_unlock:
 	unlock_page(page);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index cbfe13b..cd818d8b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4968,7 +4968,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 					    0, len, NULL,
 					    ext4_bh_unmapped)) {
 			/* Wait so that we don't change page under IO */
-			wait_on_page_writeback(page);
+			wait_for_stable_page(page);
 			ret = VM_FAULT_LOCKED;
 			goto out;
 		}
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 06b7092..2687f50d 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -483,7 +483,7 @@ out:
 	gfs2_holder_uninit(&gh);
 	if (ret == 0) {
 		set_page_dirty(page);
-		wait_on_page_writeback(page);
+		wait_for_stable_page(page);
 	}
 	sb_end_pagefault(inode->i_sb);
 	return block_page_mkwrite_return(ret);
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 6194688..bec4af6 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -126,7 +126,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	nilfs_transaction_commit(inode->i_sb);
 
  mapped:
-	wait_on_page_writeback(page);
+	wait_for_stable_page(page);
  out:
 	sb_end_pagefault(inode->i_sb);
 	return block_page_mkwrite_return(ret);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 6da609d..0e38e13 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -414,6 +414,7 @@ static inline void wait_on_page_writeback(struct page *page)
 }
 
 extern void end_page_writeback(struct page *page);
+void wait_for_stable_page(struct page *page);
 
 /*
  * Add an arbitrary waiter to a page's wait queue
diff --git a/mm/filemap.c b/mm/filemap.c
index 24a7ea5..c610076 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1728,6 +1728,7 @@ int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	 * see the dirty page and writeprotect it again.
 	 */
 	set_page_dirty(page);
+	wait_for_stable_page(page);
 out:
 	sb_end_pagefault(inode->i_sb);
 	return ret;
@@ -2274,7 +2275,7 @@ repeat:
 		return NULL;
 	}
 found:
-	wait_on_page_writeback(page);
+	wait_for_stable_page(page);
 	return page;
 }
 EXPORT_SYMBOL(grab_cache_page_write_begin);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 66a0024..355d5ee 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2290,3 +2290,23 @@ int mapping_tagged(struct address_space *mapping, int tag)
 	return radix_tree_tagged(&mapping->page_tree, tag);
 }
 EXPORT_SYMBOL(mapping_tagged);
+
+/**
+ * wait_for_stable_page() - wait for writeback to finish, if necessary.
+ * @page:	The page to wait on.
+ *
+ * This function determines if the given page is related to a backing device
+ * that requires page contents to be held stable during writeback.  If so, then
+ * it will wait for any pending writeback to complete.
+ */
+void wait_for_stable_page(struct page *page)
+{
+	struct address_space *mapping = page_mapping(page);
+	struct backing_dev_info *bdi = mapping->backing_dev_info;
+
+	if (!bdi_cap_stable_pages_required(bdi))
+		return;
+
+	wait_on_page_writeback(page);
+}
+EXPORT_SYMBOL_GPL(wait_for_stable_page);