linux-kernel - [PATCH 46/48] buffer, writeback: make __block_write_full

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1427086499-15657-47-git-send-email-tj@kernel.org>
Date:	Mon, 23 Mar 2015 00:54:57 -0400
From:	Tejun Heo <tj@...nel.org>
To:	axboe@...nel.dk
Cc:	linux-kernel@...r.kernel.org, jack@...e.cz, hch@...radead.org,
	hannes@...xchg.org, linux-fsdevel@...r.kernel.org,
	vgoyal@...hat.com, lizefan@...wei.com, cgroups@...r.kernel.org,
	linux-mm@...ck.org, mhocko@...e.cz, clm@...com,
	fengguang.wu@...el.com, david@...morbit.com, gthelen@...gle.com,
	Tejun Heo <tj@...nel.org>,
	Andrew Morton <akpm@...ux-foundation.org>
Subject: [PATCH 46/48] buffer, writeback: make __block_write_full_page() honor cgroup writeback

[__]block_write_full_page() is used to implement ->writepage in
various filesystems.  All writeback logic is now updated to handle
cgroup writeback and the block cgroup to issue IOs for is encoded in
writeback_control and can be retrieved from the inode; however,
[__]block_write_full_page() currently ignores the blkcg indicated by
inode and issues all bio's without explicit blkcg association.

This patch adds submit_bh_blkcg() which associates the bio with the
specified blkio cgroup before issuing and uses it in
__block_write_full_page() so that the issued bio's are associated with
inode_to_writeback_blkcg_css(inode).

v2: Updated for per-inode wb association.

Signed-off-by: Tejun Heo <tj@...nel.org>
Cc: Jens Axboe <axboe@...nel.dk>
Cc: Jan Kara <jack@...e.cz>
Cc: Andrew Morton <akpm@...ux-foundation.org>
---
 fs/buffer.c                 | 26 ++++++++++++++++++++------
 include/linux/backing-dev.h | 12 ++++++++++++
 2 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index 4aa1dc2..f2d594c 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -30,6 +30,7 @@
 #include <linux/quotaops.h>
 #include <linux/highmem.h>
 #include <linux/export.h>
+#include <linux/backing-dev.h>
 #include <linux/writeback.h>
 #include <linux/hash.h>
 #include <linux/suspend.h>
@@ -44,6 +45,9 @@
 #include <trace/events/block.h>
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
+static int submit_bh_blkcg(int rw, struct buffer_head *bh,
+			   unsigned long bio_flags,
+			   struct cgroup_subsys_state *blkcg_css);
 
 #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
 
@@ -1704,8 +1708,8 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 	struct buffer_head *bh, *head;
 	unsigned int blocksize, bbits;
 	int nr_underway = 0;
-	int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
-			WRITE_SYNC : WRITE);
+	int write_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
+	struct cgroup_subsys_state *blkcg_css = inode_to_wb_blkcg_css(inode);
 
 	head = create_page_buffers(page, inode,
 					(1 << BH_Dirty)|(1 << BH_Uptodate));
@@ -1794,7 +1798,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh(write_op, bh);
+			submit_bh_blkcg(write_op, bh, 0, blkcg_css);
 			nr_underway++;
 		}
 		bh = next;
@@ -1848,7 +1852,7 @@ recover:
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
 			clear_buffer_dirty(bh);
-			submit_bh(write_op, bh);
+			submit_bh_blkcg(write_op, bh, 0, blkcg_css);
 			nr_underway++;
 		}
 		bh = next;
@@ -3017,7 +3021,9 @@ void guard_bio_eod(int rw, struct bio *bio)
 	}
 }
 
-int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
+static int submit_bh_blkcg(int rw, struct buffer_head *bh,
+			   unsigned long bio_flags,
+			   struct cgroup_subsys_state *blkcg_css)
 {
 	struct bio *bio;
 	int ret = 0;
@@ -3040,6 +3046,9 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
 	 */
 	bio = bio_alloc(GFP_NOIO, 1);
 
+	if (blkcg_css)
+		bio_associate_blkcg(bio, blkcg_css);
+
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio->bi_bdev = bh->b_bdev;
 	bio->bi_io_vec[0].bv_page = bh->b_page;
@@ -3070,11 +3079,16 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
 	bio_put(bio);
 	return ret;
 }
+
+int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
+{
+	return submit_bh_blkcg(rw, bh, bio_flags, NULL);
+}
 EXPORT_SYMBOL_GPL(_submit_bh);
 
 int submit_bh(int rw, struct buffer_head *bh)
 {
-	return _submit_bh(rw, bh, 0);
+	return submit_bh_blkcg(rw, bh, 0, NULL);
 }
 EXPORT_SYMBOL(submit_bh);
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index fee39cd..a9a843c 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -394,6 +394,12 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
 	return inode->i_wb;
 }
 
+static inline struct cgroup_subsys_state *
+inode_to_wb_blkcg_css(struct inode *inode)
+{
+	return inode_to_wb(inode)->blkcg_css;
+}
+
 struct wb_iter {
 	int			start_blkcg_id;
 	struct radix_tree_iter	tree_iter;
@@ -511,6 +517,12 @@ static inline void wb_blkcg_offline(struct blkcg *blkcg)
 {
 }
 
+static inline struct cgroup_subsys_state *
+inode_to_wb_blkcg_css(struct inode *inode)
+{
+	return blkcg_root_css;
+}
+
 struct wb_iter {
 	int		next_id;
 };
-- 
2.1.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/