| 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: <1427086499-15657-30-git-send-email-tj@kernel.org>
Date: Mon, 23 Mar 2015 00:54:40 -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 29/48] writeback: implement WB_has_dirty_io wb_state flag
Currently, wb_has_dirty_io() determines whether a wb (bdi_writeback)
has any dirty inode by testing all three IO lists on each invocation
without actively keeping track. For cgroup writeback support, a
single bdi will host multiple wb's each of which will host dirty
inodes separately and we'll need to make bdi_has_dirty_io(), which
currently only represents the root wb, aggregate has_dirty_io from all
member wb's, which requires tracking transitions in has_dirty_io state
on each wb.
This patch introduces inode_wb_list_{move|del}_locked() to consolidate
IO list operations leaving queue_io() the only other function which
directly manipulates IO lists (via move_expired_inodes()). All three
functions are updated to call wb_io_lists_[de]populated() which keep
track of whether the wb has dirty inodes or not and record it using
the new WB_has_dirty_io flag. inode_wb_list_moved_locked()'s return
value indicates whether the wb had no dirty inodes before.
mark_inode_dirty() is restructured so that the return value of
inode_wb_list_move_locked() can be used for deciding whether to wake
up the wb.
While at it, change {bdi|wb}_has_dirty_io()'s return values to bool.
These functions were returning 0 and 1 before. Also, add a comment
explaining the synchronization of wb_state flags.
v2: Updated to accommodate b_dirty_time.
Signed-off-by: Tejun Heo <tj@...nel.org>
Cc: Jens Axboe <axboe@...nel.dk>
Cc: Jan Kara <jack@...e.cz>
---
fs/fs-writeback.c | 104 ++++++++++++++++++++++++++++++---------
include/linux/backing-dev-defs.h | 1 +
include/linux/backing-dev.h | 8 ++-
mm/backing-dev.c | 2 +-
4 files changed, 86 insertions(+), 29 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 015f359..dc4e399 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -81,6 +81,66 @@ static inline struct inode *wb_inode(struct list_head *head)
EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);
+static bool wb_io_lists_populated(struct bdi_writeback *wb)
+{
+ if (wb_has_dirty_io(wb)) {
+ return false;
+ } else {
+ set_bit(WB_has_dirty_io, &wb->state);
+ return true;
+ }
+}
+
+static void wb_io_lists_depopulated(struct bdi_writeback *wb)
+{
+ if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) &&
+ list_empty(&wb->b_io) && list_empty(&wb->b_more_io))
+ clear_bit(WB_has_dirty_io, &wb->state);
+}
+
+/**
+ * inode_wb_list_move_locked - move an inode onto a bdi_writeback IO list
+ * @inode: inode to be moved
+ * @wb: target bdi_writeback
+ * @head: one of @wb->b_{dirty|io|more_io}
+ *
+ * Move @inode->i_wb_list to @list of @wb and set %WB_has_dirty_io.
+ * Returns %true if @inode is the first occupant of the !dirty_time IO
+ * lists; otherwise, %false.
+ */
+static bool inode_wb_list_move_locked(struct inode *inode,
+ struct bdi_writeback *wb,
+ struct list_head *head)
+{
+ assert_spin_locked(&wb->list_lock);
+
+ list_move(&inode->i_wb_list, head);
+
+ /* dirty_time doesn't count as dirty_io until expiration */
+ if (head != &wb->b_dirty_time)
+ return wb_io_lists_populated(wb);
+
+ wb_io_lists_depopulated(wb);
+ return false;
+}
+
+/**
+ * inode_wb_list_del_locked - remove an inode from its bdi_writeback IO list
+ * @inode: inode to be removed
+ * @wb: bdi_writeback @inode is being removed from
+ *
+ * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and
+ * clear %WB_has_dirty_io if all are empty afterwards.
+ */
+static void inode_wb_list_del_locked(struct inode *inode,
+ struct bdi_writeback *wb)
+{
+ assert_spin_locked(&wb->list_lock);
+
+ list_del_init(&inode->i_wb_list);
+ wb_io_lists_depopulated(wb);
+}
+
static void wb_wakeup(struct bdi_writeback *wb)
{
spin_lock_bh(&wb->work_lock);
@@ -215,7 +275,7 @@ void inode_wb_list_del(struct inode *inode)
struct bdi_writeback *wb = inode_to_wb(inode);
spin_lock(&wb->list_lock);
- list_del_init(&inode->i_wb_list);
+ inode_wb_list_del_locked(inode, wb);
spin_unlock(&wb->list_lock);
}
@@ -230,7 +290,6 @@ void inode_wb_list_del(struct inode *inode)
*/
static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
{
- assert_spin_locked(&wb->list_lock);
if (!list_empty(&wb->b_dirty)) {
struct inode *tail;
@@ -238,7 +297,7 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
if (time_before(inode->dirtied_when, tail->dirtied_when))
inode->dirtied_when = jiffies;
}
- list_move(&inode->i_wb_list, &wb->b_dirty);
+ inode_wb_list_move_locked(inode, wb, &wb->b_dirty);
}
/*
@@ -246,8 +305,7 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
*/
static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
{
- assert_spin_locked(&wb->list_lock);
- list_move(&inode->i_wb_list, &wb->b_more_io);
+ inode_wb_list_move_locked(inode, wb, &wb->b_more_io);
}
static void inode_sync_complete(struct inode *inode)
@@ -356,6 +414,8 @@ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work);
moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
EXPIRE_DIRTY_ATIME, work);
+ if (moved)
+ wb_io_lists_populated(wb);
trace_writeback_queue_io(wb, work, moved);
}
@@ -480,10 +540,10 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
*/
redirty_tail(inode, wb);
} else if (inode->i_state & I_DIRTY_TIME) {
- list_move(&inode->i_wb_list, &wb->b_dirty_time);
+ inode_wb_list_move_locked(inode, wb, &wb->b_dirty_time);
} else {
/* The inode is clean. Remove from writeback lists. */
- list_del_init(&inode->i_wb_list);
+ inode_wb_list_del_locked(inode, wb);
}
}
@@ -620,7 +680,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
* touch it. See comment above for explanation.
*/
if (!(inode->i_state & I_DIRTY_ALL))
- list_del_init(&inode->i_wb_list);
+ inode_wb_list_del_locked(inode, wb);
spin_unlock(&wb->list_lock);
inode_sync_complete(inode);
out:
@@ -1274,27 +1334,25 @@ void __mark_inode_dirty(struct inode *inode, int flags)
spin_unlock(&inode->i_lock);
spin_lock(&bdi->wb.list_lock);
- if (bdi_cap_writeback_dirty(bdi)) {
- WARN(!test_bit(WB_registered, &bdi->wb.state),
- "bdi-%s not registered\n", bdi->name);
- /*
- * If this is the first dirty inode for this
- * bdi, we have to wake-up the corresponding
- * bdi thread to make sure background
- * write-back happens later.
- */
- if (!wb_has_dirty_io(&bdi->wb))
- wakeup_bdi = true;
- }
+ WARN(bdi_cap_writeback_dirty(bdi) &&
+ !test_bit(WB_registered, &bdi->wb.state),
+ "bdi-%s not registered\n", bdi->name);
inode->dirtied_when = jiffies;
- list_move(&inode->i_wb_list, dirtytime ?
- &bdi->wb.b_dirty_time : &bdi->wb.b_dirty);
+ wakeup_bdi = inode_wb_list_move_locked(inode, &bdi->wb,
+ dirtytime ? &bdi->wb.b_dirty_time :
+ &bdi->wb.b_dirty);
spin_unlock(&bdi->wb.list_lock);
trace_writeback_dirty_inode_enqueue(inode);
- if (wakeup_bdi)
+ /*
+ * If this is the first dirty inode for this bdi,
+ * we have to wake-up the corresponding bdi thread
+ * to make sure background write-back happens
+ * later.
+ */
+ if (bdi_cap_writeback_dirty(bdi) && wakeup_bdi)
wb_wakeup_delayed(&bdi->wb);
return;
}
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index eb38676..7a94b78 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -21,6 +21,7 @@ struct dentry;
enum wb_state {
WB_registered, /* bdi_register() was done */
WB_writeback_running, /* Writeback is in progress */
+ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */
};
enum wb_congested_state {
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index cfa23ab..bab5927 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -29,7 +29,7 @@ void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
enum wb_reason reason);
void bdi_start_background_writeback(struct backing_dev_info *bdi);
void wb_workfn(struct work_struct *work);
-int bdi_has_dirty_io(struct backing_dev_info *bdi);
+bool bdi_has_dirty_io(struct backing_dev_info *bdi);
void wb_wakeup_delayed(struct bdi_writeback *wb);
extern spinlock_t bdi_lock;
@@ -37,11 +37,9 @@ extern struct list_head bdi_list;
extern struct workqueue_struct *bdi_wq;
-static inline int wb_has_dirty_io(struct bdi_writeback *wb)
+static inline bool wb_has_dirty_io(struct bdi_writeback *wb)
{
- return !list_empty(&wb->b_dirty) ||
- !list_empty(&wb->b_io) ||
- !list_empty(&wb->b_more_io);
+ return test_bit(WB_has_dirty_io, &wb->state);
}
static inline void __add_wb_stat(struct bdi_writeback *wb,
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 7721e7a..56d7622 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -256,7 +256,7 @@ static int __init default_bdi_init(void)
}
subsys_initcall(default_bdi_init);
-int bdi_has_dirty_io(struct backing_dev_info *bdi)
+bool bdi_has_dirty_io(struct backing_dev_info *bdi)
{
return wb_has_dirty_io(&bdi->wb);
}
--
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