From: Tejun Heo <tj@kernel.org>
To: axboe@kernel.dk
Cc: linux-kernel@vger.kernel.org, jack@suse.cz, hch@infradead.org,
hannes@cmpxchg.org, linux-fsdevel@vger.kernel.org,
vgoyal@redhat.com, lizefan@huawei.com, cgroups@vger.kernel.org,
linux-mm@kvack.org, mhocko@suse.cz, clm@fb.com,
fengguang.wu@intel.com, david@fromorbit.com, gthelen@google.com,
Tejun Heo <tj@kernel.org>
Subject: [PATCH 41/48] writeback: implement bdi_wait_for_completion()
Date: Mon, 23 Mar 2015 00:54:52 -0400 [thread overview]
Message-ID: <1427086499-15657-42-git-send-email-tj@kernel.org> (raw)
In-Reply-To: <1427086499-15657-1-git-send-email-tj@kernel.org>
If the completion of a wb_writeback_work can be waited upon by setting
its ->done to a struct completion and waiting on it; however, for
cgroup writeback support, it's necessary to issue multiple work items
to multiple bdi_writebacks and wait for the completion of all.
This patch implements wb_completion which can wait for multiple work
items and replaces the struct completion with it. It can be defined
using DEFINE_WB_COMPLETION_ONSTACK(), used for multiple work items and
waited for by wb_wait_for_completion().
Nobody currently issues multiple work items and this patch doesn't
introduce any behavior changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jan Kara <jack@suse.cz>
---
fs/fs-writeback.c | 57 +++++++++++++++++++++++++++++++---------
include/linux/backing-dev-defs.h | 2 ++
mm/backing-dev.c | 1 +
3 files changed, 48 insertions(+), 12 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 25504be..944e53d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -34,6 +34,10 @@
*/
#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_CACHE_SHIFT - 10))
+struct wb_completion {
+ atomic_t cnt;
+};
+
/*
* Passed into wb_writeback(), essentially a subset of writeback_control
*/
@@ -51,9 +55,21 @@ struct wb_writeback_work {
enum wb_reason reason; /* why was writeback initiated? */
struct list_head list; /* pending work list */
- struct completion *done; /* set if the caller waits */
+ struct wb_completion *done; /* set if the caller waits */
};
+/*
+ * If one wants to wait for one or more wb_writeback_works, each work's
+ * ->done should be set to a wb_completion defined using the following
+ * macro. Once all work items are issued with wb_queue_work(), the caller
+ * can wait for the completion of all using wb_wait_for_completion(). Work
+ * items which are waited upon aren't freed automatically on completion.
+ */
+#define DEFINE_WB_COMPLETION_ONSTACK(cmpl) \
+ struct wb_completion cmpl = { \
+ .cnt = ATOMIC_INIT(1), \
+ }
+
static inline struct inode *wb_inode(struct list_head *head)
{
return list_entry(head, struct inode, i_wb_list);
@@ -149,17 +165,34 @@ static void wb_queue_work(struct bdi_writeback *wb,
trace_writeback_queue(wb->bdi, work);
spin_lock_bh(&wb->work_lock);
- if (!test_bit(WB_registered, &wb->state)) {
- if (work->done)
- complete(work->done);
+ if (!test_bit(WB_registered, &wb->state))
goto out_unlock;
- }
+ if (work->done)
+ atomic_inc(&work->done->cnt);
list_add_tail(&work->list, &wb->work_list);
mod_delayed_work(bdi_wq, &wb->dwork, 0);
out_unlock:
spin_unlock_bh(&wb->work_lock);
}
+/**
+ * wb_wait_for_completion - wait for completion of bdi_writeback_works
+ * @bdi: bdi work items were issued to
+ * @done: target wb_completion
+ *
+ * Wait for one or more work items issued to @bdi with their ->done field
+ * set to @done, which should have been defined with
+ * DEFINE_WB_COMPLETION_ONSTACK(). This function returns after all such
+ * work items are completed. Work items which are waited upon aren't freed
+ * automatically on completion.
+ */
+static void wb_wait_for_completion(struct backing_dev_info *bdi,
+ struct wb_completion *done)
+{
+ atomic_dec(&done->cnt); /* put down the initial count */
+ wait_event(bdi->wb_waitq, !atomic_read(&done->cnt));
+}
+
#ifdef CONFIG_CGROUP_WRITEBACK
/**
@@ -1135,7 +1168,7 @@ static long wb_do_writeback(struct bdi_writeback *wb)
set_bit(WB_writeback_running, &wb->state);
while ((work = get_next_work_item(wb)) != NULL) {
- struct completion *done = work->done;
+ struct wb_completion *done = work->done;
trace_writeback_exec(wb->bdi, work);
@@ -1143,8 +1176,8 @@ static long wb_do_writeback(struct bdi_writeback *wb)
if (work->auto_free)
kfree(work);
- if (done)
- complete(done);
+ if (done && atomic_dec_and_test(&done->cnt))
+ wake_up_all(&wb->bdi->wb_waitq);
}
/*
@@ -1448,7 +1481,7 @@ void writeback_inodes_sb_nr(struct super_block *sb,
unsigned long nr,
enum wb_reason reason)
{
- DECLARE_COMPLETION_ONSTACK(done);
+ DEFINE_WB_COMPLETION_ONSTACK(done);
struct wb_writeback_work work = {
.sb = sb,
.sync_mode = WB_SYNC_NONE,
@@ -1463,7 +1496,7 @@ void writeback_inodes_sb_nr(struct super_block *sb,
return;
WARN_ON(!rwsem_is_locked(&sb->s_umount));
wb_queue_work(&bdi->wb, &work);
- wait_for_completion(&done);
+ wb_wait_for_completion(bdi, &done);
}
EXPORT_SYMBOL(writeback_inodes_sb_nr);
@@ -1530,7 +1563,7 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb);
*/
void sync_inodes_sb(struct super_block *sb)
{
- DECLARE_COMPLETION_ONSTACK(done);
+ DEFINE_WB_COMPLETION_ONSTACK(done);
struct wb_writeback_work work = {
.sb = sb,
.sync_mode = WB_SYNC_ALL,
@@ -1548,7 +1581,7 @@ void sync_inodes_sb(struct super_block *sb)
WARN_ON(!rwsem_is_locked(&sb->s_umount));
wb_queue_work(&bdi->wb, &work);
- wait_for_completion(&done);
+ wb_wait_for_completion(bdi, &done);
wait_sb_inodes(sb);
}
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 8c857d7..97a92fa 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -155,6 +155,8 @@ struct backing_dev_info {
struct rb_root cgwb_congested_tree; /* their congested states */
atomic_t usage_cnt; /* counts both cgwbs and cgwb_contested's */
#endif
+ wait_queue_head_t wb_waitq;
+
struct device *dev;
struct timer_list laptop_mode_wb_timer;
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index eab5181..331e4d7 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -769,6 +769,7 @@ int bdi_init(struct backing_dev_info *bdi)
bdi->max_ratio = 100;
bdi->max_prop_frac = FPROP_FRAC_BASE;
INIT_LIST_HEAD(&bdi->bdi_list);
+ init_waitqueue_head(&bdi->wb_waitq);
err = wb_init(&bdi->wb, bdi, GFP_KERNEL);
if (err)
--
2.1.0
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2015-03-23 4:56 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-03-23 4:54 [PATCHSET 1/3 v2 block/for-4.1/core] writeback: cgroup writeback support Tejun Heo
2015-03-23 4:54 ` [PATCH 01/48] memcg: add per cgroup dirty page accounting Tejun Heo
2015-03-23 4:54 ` [PATCH 02/48] blkcg: move block/blk-cgroup.h to include/linux/blk-cgroup.h Tejun Heo
2015-03-23 4:54 ` [PATCH 03/48] update !CONFIG_BLK_CGROUP dummies in include/linux/blk-cgroup.h Tejun Heo
2015-03-23 4:54 ` [PATCH 04/48] memcg: add mem_cgroup_root_css Tejun Heo
2015-03-23 4:54 ` [PATCH 05/48] blkcg: add blkcg_root_css Tejun Heo
2015-03-23 4:54 ` [PATCH 06/48] cgroup, block: implement task_get_css() and use it in bio_associate_current() Tejun Heo
2015-03-23 4:54 ` [PATCH 07/48] blkcg: implement task_get_blkcg_css() Tejun Heo
2015-03-23 4:54 ` [PATCH 08/48] blkcg: implement bio_associate_blkcg() Tejun Heo
2015-03-23 4:54 ` [PATCH 09/48] memcg: implement mem_cgroup_css_from_page() Tejun Heo
2015-03-23 4:54 ` [PATCH 10/48] writeback: move backing_dev_info->state into bdi_writeback Tejun Heo
2015-03-23 4:54 ` [PATCH 11/48] writeback: move backing_dev_info->bdi_stat[] " Tejun Heo
2015-03-23 4:54 ` [PATCH 12/48] writeback: move bandwidth related fields from backing_dev_info " Tejun Heo
2015-03-23 4:54 ` [PATCH 13/48] writeback: s/bdi/wb/ in mm/page-writeback.c Tejun Heo
2015-03-23 4:54 ` [PATCH 14/48] writeback: move backing_dev_info->wb_lock and ->worklist into bdi_writeback Tejun Heo
2015-03-23 4:54 ` [PATCH 15/48] writeback: reorganize mm/backing-dev.c Tejun Heo
2015-03-23 4:54 ` [PATCH 16/48] writeback: separate out include/linux/backing-dev-defs.h Tejun Heo
2015-03-23 4:54 ` [PATCH 17/48] bdi: make inode_to_bdi() inline Tejun Heo
2015-03-23 4:54 ` [PATCH 18/48] writeback: add @gfp to wb_init() Tejun Heo
2015-03-23 4:54 ` [PATCH 19/48] bdi: separate out congested state into a separate struct Tejun Heo
2015-03-23 4:54 ` [PATCH 20/48] writeback: add {CONFIG|BDI_CAP|FS}_CGROUP_WRITEBACK Tejun Heo
2015-03-23 4:54 ` [PATCH 21/48] writeback: make backing_dev_info host cgroup-specific bdi_writebacks Tejun Heo
2015-03-27 21:06 ` Vivek Goyal
2015-03-27 21:41 ` Tejun Heo
2015-03-23 4:54 ` [PATCH 22/48] writeback, blkcg: associate each blkcg_gq with the corresponding bdi_writeback_congested Tejun Heo
2015-03-23 4:54 ` [PATCH 23/48] writeback: attribute stats to the matching per-cgroup bdi_writeback Tejun Heo
2015-03-23 4:54 ` [PATCH 24/48] writeback: let balance_dirty_pages() work on the matching cgroup bdi_writeback Tejun Heo
2015-03-23 4:54 ` [PATCH 25/48] writeback: make congestion functions per bdi_writeback Tejun Heo
2015-03-23 4:54 ` [PATCH 26/48] writeback, blkcg: restructure blk_{set|clear}_queue_congested() Tejun Heo
2015-03-23 4:54 ` [PATCH 27/48] writeback, blkcg: propagate non-root blkcg congestion state Tejun Heo
2015-03-23 4:54 ` [PATCH 28/48] writeback: implement and use mapping_congested() Tejun Heo
2015-03-27 18:06 ` Vivek Goyal
2015-03-27 21:46 ` Tejun Heo
2015-03-23 4:54 ` [PATCH 29/48] writeback: implement WB_has_dirty_io wb_state flag Tejun Heo
2015-03-23 4:54 ` [PATCH 30/48] writeback: implement backing_dev_info->tot_write_bandwidth Tejun Heo
2015-03-23 4:54 ` [PATCH 31/48] writeback: make bdi_has_dirty_io() take multiple bdi_writeback's into account Tejun Heo
2015-03-23 4:54 ` [PATCH 32/48] writeback: don't issue wb_writeback_work if clean Tejun Heo
2015-03-23 4:54 ` [PATCH 33/48] writeback: make bdi->min/max_ratio handling cgroup writeback aware Tejun Heo
2015-03-23 4:54 ` [PATCH 34/48] writeback: implement bdi_for_each_wb() Tejun Heo
2015-03-23 4:54 ` [PATCH 35/48] writeback: remove bdi_start_writeback() Tejun Heo
2015-03-23 4:54 ` [PATCH 36/48] writeback: make laptop_mode_timer_fn() handle multiple bdi_writeback's Tejun Heo
2015-03-23 4:54 ` [PATCH 37/48] writeback: make writeback_in_progress() take bdi_writeback instead of backing_dev_info Tejun Heo
2015-03-23 4:54 ` [PATCH 38/48] writeback: make bdi_start_background_writeback() " Tejun Heo
2015-03-23 4:54 ` [PATCH 39/48] writeback: make wakeup_flusher_threads() handle multiple bdi_writeback's Tejun Heo
2015-03-23 4:54 ` [PATCH 40/48] writeback: add wb_writeback_work->auto_free Tejun Heo
2015-03-23 4:54 ` Tejun Heo [this message]
2015-03-23 4:54 ` [PATCH 42/48] writeback: implement wb_wait_for_single_work() Tejun Heo
2015-03-23 4:54 ` [PATCH 43/48] writeback: restructure try_writeback_inodes_sb[_nr]() Tejun Heo
2015-03-23 4:54 ` [PATCH 44/48] writeback: make writeback initiation functions handle multiple bdi_writeback's Tejun Heo
2015-03-23 4:54 ` [PATCH 45/48] writeback: dirty inodes against their matching cgroup bdi_writeback's Tejun Heo
2015-03-23 4:54 ` [PATCH 46/48] buffer, writeback: make __block_write_full_page() honor cgroup writeback Tejun Heo
2015-03-23 4:54 ` [PATCH 47/48] mpage: make __mpage_writepage() " Tejun Heo
2015-03-23 4:54 ` [PATCH 48/48] ext2: enable cgroup writeback support Tejun Heo
2015-03-25 15:40 ` [PATCHSET 1/3 v2 block/for-4.1/core] writeback: " Vivek Goyal
2015-03-25 16:01 ` Tejun Heo
2015-03-31 15:26 ` Tejun Heo
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=1427086499-15657-42-git-send-email-tj@kernel.org \
--to=tj@kernel.org \
--cc=axboe@kernel.dk \
--cc=cgroups@vger.kernel.org \
--cc=clm@fb.com \
--cc=david@fromorbit.com \
--cc=fengguang.wu@intel.com \
--cc=gthelen@google.com \
--cc=hannes@cmpxchg.org \
--cc=hch@infradead.org \
--cc=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizefan@huawei.com \
--cc=mhocko@suse.cz \
--cc=vgoyal@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).