linux-btrfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mark Fasheh <mfasheh@suse.de>
To: linux-btrfs@vger.kernel.org, Josef Bacik <josef@redhat.com>
Cc: Chris Mason <chris.mason@fusionio.com>,
	Gabriel de Perthuis <g2p.code@gmail.com>,
	David Sterba <dsterba@suse.cz>, Zach Brown <zab@redhat.com>,
	Mark Fasheh <mfasheh@suse.de>
Subject: [PATCH 3/4] btrfs: Introduce extent_read_full_page_nolock()
Date: Fri, 26 Jul 2013 09:30:11 -0700	[thread overview]
Message-ID: <1374856212-11228-4-git-send-email-mfasheh@suse.de> (raw)
In-Reply-To: <1374856212-11228-1-git-send-email-mfasheh@suse.de>

We want this for btrfs_extent_same. Basically readpage and friends do their
own extent locking but for the purposes of dedupe, we want to have both
files locked down across a set of readpage operations (so that we can
compare data). Introduce this variant and a flag which can be set for
extent_read_full_page() to indicate that we are already locked.

Partial credit for this patch goes to Gabriel de Perthuis <g2p.code@gmail.com>
as I have included a fix from him to the original patch which avoids a
deadlock on compressed extents.

Signed-off-by: Mark Fasheh <mfasheh@suse.de>
---
 fs/btrfs/compression.c |  6 +++++-
 fs/btrfs/extent_io.c   | 41 +++++++++++++++++++++++++++++++----------
 fs/btrfs/extent_io.h   |  3 +++
 3 files changed, 39 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 15b9408..05819c3 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -636,7 +636,11 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	faili = nr_pages - 1;
 	cb->nr_pages = nr_pages;
 
-	add_ra_bio_pages(inode, em_start + em_len, cb);
+	/* In the parent-locked case, we only locked the range we are
+	 * interested in.  In all other cases, we can opportunistically
+	 * cache decompressed data that goes beyond the requested range. */
+	if (!(bio_flags & EXTENT_BIO_PARENT_LOCKED))
+		add_ra_bio_pages(inode, em_start + em_len, cb);
 
 	/* include any pages we added in add_ra-bio_pages */
 	uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index cdee391..80ce106 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2643,11 +2643,12 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 	struct btrfs_ordered_extent *ordered;
 	int ret;
 	int nr = 0;
+	int parent_locked = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
 	size_t pg_offset = 0;
 	size_t iosize;
 	size_t disk_io_size;
 	size_t blocksize = inode->i_sb->s_blocksize;
-	unsigned long this_bio_flag = 0;
+	unsigned long this_bio_flag = *bio_flags & EXTENT_BIO_PARENT_LOCKED;
 
 	set_page_extent_mapped(page);
 
@@ -2659,7 +2660,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 	}
 
 	end = page_end;
-	while (1) {
+	while (!parent_locked) {
 		lock_extent(tree, start, end);
 		ordered = btrfs_lookup_ordered_extent(inode, start);
 		if (!ordered)
@@ -2695,15 +2696,18 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 			kunmap_atomic(userpage);
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
 					    &cached, GFP_NOFS);
-			unlock_extent_cached(tree, cur, cur + iosize - 1,
-					     &cached, GFP_NOFS);
+			if (!parent_locked)
+				unlock_extent_cached(tree, cur,
+						     cur + iosize - 1,
+						     &cached, GFP_NOFS);
 			break;
 		}
 		em = get_extent(inode, page, pg_offset, cur,
 				end - cur + 1, 0);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
-			unlock_extent(tree, cur, end);
+			if (!parent_locked)
+				unlock_extent(tree, cur, end);
 			break;
 		}
 		extent_offset = cur - em->start;
@@ -2711,7 +2715,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 		BUG_ON(end < cur);
 
 		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
-			this_bio_flag = EXTENT_BIO_COMPRESSED;
+			this_bio_flag |= EXTENT_BIO_COMPRESSED;
 			extent_set_compress_type(&this_bio_flag,
 						 em->compress_type);
 		}
@@ -2755,7 +2759,8 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 		if (test_range_bit(tree, cur, cur_end,
 				   EXTENT_UPTODATE, 1, NULL)) {
 			check_page_uptodate(tree, page);
-			unlock_extent(tree, cur, cur + iosize - 1);
+			if (!parent_locked)
+				unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -2765,7 +2770,8 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 		 */
 		if (block_start == EXTENT_MAP_INLINE) {
 			SetPageError(page);
-			unlock_extent(tree, cur, cur + iosize - 1);
+			if (!parent_locked)
+				unlock_extent(tree, cur, cur + iosize - 1);
 			cur = cur + iosize;
 			pg_offset += iosize;
 			continue;
@@ -2783,7 +2789,8 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 			*bio_flags = this_bio_flag;
 		} else {
 			SetPageError(page);
-			unlock_extent(tree, cur, cur + iosize - 1);
+			if (!parent_locked)
+				unlock_extent(tree, cur, cur + iosize - 1);
 		}
 		cur = cur + iosize;
 		pg_offset += iosize;
@@ -2811,6 +2818,20 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 	return ret;
 }
 
+int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
+				 get_extent_t *get_extent, int mirror_num)
+{
+	struct bio *bio = NULL;
+	unsigned long bio_flags = EXTENT_BIO_PARENT_LOCKED;
+	int ret;
+
+	ret = __extent_read_full_page(tree, page, get_extent, &bio, mirror_num,
+				      &bio_flags);
+	if (bio)
+		ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
+	return ret;
+}
+
 static noinline void update_nr_written(struct page *page,
 				      struct writeback_control *wbc,
 				      unsigned long nr_written)
@@ -3666,7 +3687,7 @@ int extent_readpages(struct extent_io_tree *tree,
 			continue;
 		for (i = 0; i < nr; i++) {
 			__extent_read_full_page(tree, pagepool[i], get_extent,
-					&bio, 0, &bio_flags);
+						&bio, 0, &bio_flags);
 			page_cache_release(pagepool[i]);
 		}
 		nr = 0;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 258c921..e3654bd 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -28,6 +28,7 @@
  */
 #define EXTENT_BIO_COMPRESSED 1
 #define EXTENT_BIO_TREE_LOG 2
+#define EXTENT_BIO_PARENT_LOCKED 4
 #define EXTENT_BIO_FLAG_SHIFT 16
 
 /* these are bit numbers for test/set bit */
@@ -198,6 +199,8 @@ int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end,
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
 int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 			  get_extent_t *get_extent, int mirror_num);
+int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
+				 get_extent_t *get_extent, int mirror_num);
 int __init extent_io_init(void);
 void extent_io_exit(void);
 
-- 
1.8.1.4


  parent reply	other threads:[~2013-07-26 16:30 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-07-26 16:30 [PATCH 0/4] btrfs: offline dedupe v3 Mark Fasheh
2013-07-26 16:30 ` [PATCH 1/4] btrfs: abtract out range locking in clone ioctl() Mark Fasheh
2013-07-26 16:30 ` [PATCH 2/4] btrfs_ioctl_clone: Move clone code into it's own function Mark Fasheh
2013-07-26 16:30 ` Mark Fasheh [this message]
2013-07-26 16:30 ` [PATCH 4/4] btrfs: offline dedupe Mark Fasheh
2013-07-26 22:09   ` Zach Brown
2013-07-26 16:48 ` [PATCH 0/4] btrfs: offline dedupe v3 Ric Wheeler
  -- strict thread matches above, loose matches on Subject: below --
2013-08-06 18:42 [PATCH 0/4] btrfs: out-of-band (aka offline) dedupe v4 Mark Fasheh
2013-08-06 18:42 ` [PATCH 3/4] btrfs: Introduce extent_read_full_page_nolock() Mark Fasheh
2013-06-11 20:31 [PATCH 0/4] btrfs: offline dedupe v2 Mark Fasheh
2013-06-11 20:31 ` [PATCH 3/4] btrfs: Introduce extent_read_full_page_nolock() Mark Fasheh
2013-05-21 18:28 [PATCH 0/4] btrfs: offline dedupe v1 Mark Fasheh
2013-05-21 18:28 ` [PATCH 3/4] btrfs: Introduce extent_read_full_page_nolock() Mark Fasheh
2013-04-16 22:15 [PATCH 0/4] [RFC] btrfs: offline dedupe Mark Fasheh
2013-04-16 22:15 ` [PATCH 3/4] btrfs: Introduce extent_read_full_page_nolock() Mark Fasheh
2013-05-06 12:38   ` David Sterba
2013-05-07  7:33 ` Gabriel de Perthuis
2013-05-09 21:31 ` Gabriel de Perthuis

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1374856212-11228-4-git-send-email-mfasheh@suse.de \
    --to=mfasheh@suse.de \
    --cc=chris.mason@fusionio.com \
    --cc=dsterba@suse.cz \
    --cc=g2p.code@gmail.com \
    --cc=josef@redhat.com \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=zab@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).