| 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
| ||
|
Message-Id: <1427086499-15657-42-git-send-email-tj@kernel.org>
Date: Mon, 23 Mar 2015 00:54:52 -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>
Subject: [PATCH 41/48] writeback: implement bdi_wait_for_completion()
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@...nel.org>
Cc: Jens Axboe <axboe@...nel.dk>
Cc: Jan Kara <jack@...e.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 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/
Powered by blists - more mailing lists