Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 335607b..22e9c88 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -42,7 +42,6 @@
struct wb_writeback_work {
long nr_pages;
struct super_block *sb;
- unsigned long *older_than_this;
enum writeback_sync_modes sync_mode;
unsigned int tagged_writepages:1;
unsigned int for_kupdate:1;
@@ -144,7 +143,9 @@
struct bdi_writeback *wb)
{
assert_spin_locked(&wb->list_lock);
+ assert_spin_locked(&inode->i_lock);
+ inode->i_state &= ~I_SYNC_QUEUED;
list_del_init(&inode->i_io_list);
wb_io_lists_depopulated(wb);
}
@@ -504,12 +505,19 @@
if (!isw)
return;
+ atomic_inc(&isw_nr_in_flight);
+
/* find and pin the new wb */
rcu_read_lock();
memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys);
- if (memcg_css)
- isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC);
+ if (memcg_css && !css_tryget(memcg_css))
+ memcg_css = NULL;
rcu_read_unlock();
+ if (!memcg_css)
+ goto out_free;
+
+ isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC);
+ css_put(memcg_css);
if (!isw->new_wb)
goto out_free;
@@ -534,11 +542,10 @@
* Let's continue after I_WB_SWITCH is guaranteed to be visible.
*/
call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn);
-
- atomic_inc(&isw_nr_in_flight);
return;
out_free:
+ atomic_dec(&isw_nr_in_flight);
if (isw->new_wb)
wb_put(isw->new_wb);
kfree(isw);
@@ -1123,7 +1130,9 @@
struct bdi_writeback *wb;
wb = inode_to_wb_and_lock_list(inode);
+ spin_lock(&inode->i_lock);
inode_io_list_del_locked(inode, wb);
+ spin_unlock(&inode->i_lock);
spin_unlock(&wb->list_lock);
}
@@ -1172,8 +1181,10 @@
* the case then the inode must have been redirtied while it was being written
* out and we don't reset its dirtied_when.
*/
-static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
+static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb)
{
+ assert_spin_locked(&inode->i_lock);
+
if (!list_empty(&wb->b_dirty)) {
struct inode *tail;
@@ -1182,6 +1193,14 @@
inode->dirtied_when = jiffies;
}
inode_io_list_move_locked(inode, wb, &wb->b_dirty);
+ inode->i_state &= ~I_SYNC_QUEUED;
+}
+
+static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
+{
+ spin_lock(&inode->i_lock);
+ redirty_tail_locked(inode, wb);
+ spin_unlock(&inode->i_lock);
}
/*
@@ -1220,16 +1239,13 @@
#define EXPIRE_DIRTY_ATIME 0x0001
/*
- * Move expired (dirtied before work->older_than_this) dirty inodes from
+ * Move expired (dirtied before dirtied_before) dirty inodes from
* @delaying_queue to @dispatch_queue.
*/
static int move_expired_inodes(struct list_head *delaying_queue,
struct list_head *dispatch_queue,
- int flags,
- struct wb_writeback_work *work)
+ unsigned long dirtied_before)
{
- unsigned long *older_than_this = NULL;
- unsigned long expire_time;
LIST_HEAD(tmp);
struct list_head *pos, *node;
struct super_block *sb = NULL;
@@ -1237,21 +1253,15 @@
int do_sb_sort = 0;
int moved = 0;
- if ((flags & EXPIRE_DIRTY_ATIME) == 0)
- older_than_this = work->older_than_this;
- else if (!work->for_sync) {
- expire_time = jiffies - (dirtytime_expire_interval * HZ);
- older_than_this = &expire_time;
- }
while (!list_empty(delaying_queue)) {
inode = wb_inode(delaying_queue->prev);
- if (older_than_this &&
- inode_dirtied_after(inode, *older_than_this))
+ if (inode_dirtied_after(inode, dirtied_before))
break;
list_move(&inode->i_io_list, &tmp);
moved++;
- if (flags & EXPIRE_DIRTY_ATIME)
- set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state);
+ spin_lock(&inode->i_lock);
+ inode->i_state |= I_SYNC_QUEUED;
+ spin_unlock(&inode->i_lock);
if (sb_is_blkdev_sb(inode->i_sb))
continue;
if (sb && sb != inode->i_sb)
@@ -1289,18 +1299,22 @@
* |
* +--> dequeue for IO
*/
-static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
+static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work,
+ unsigned long dirtied_before)
{
int moved;
+ unsigned long time_expire_jif = dirtied_before;
assert_spin_locked(&wb->list_lock);
list_splice_init(&wb->b_more_io, &wb->b_io);
- moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work);
+ moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before);
+ if (!work->for_sync)
+ time_expire_jif = jiffies - dirtytime_expire_interval * HZ;
moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
- EXPIRE_DIRTY_ATIME, work);
+ time_expire_jif);
if (moved)
wb_io_lists_populated(wb);
- trace_writeback_queue_io(wb, work, moved);
+ trace_writeback_queue_io(wb, work, dirtied_before, moved);
}
static int write_inode(struct inode *inode, struct writeback_control *wbc)
@@ -1394,7 +1408,7 @@
* writeback is not making progress due to locked
* buffers. Skip this inode for now.
*/
- redirty_tail(inode, wb);
+ redirty_tail_locked(inode, wb);
return;
}
@@ -1414,7 +1428,7 @@
* retrying writeback of the dirty page/inode
* that cannot be performed immediately.
*/
- redirty_tail(inode, wb);
+ redirty_tail_locked(inode, wb);
}
} else if (inode->i_state & I_DIRTY) {
/*
@@ -1422,10 +1436,11 @@
* such as delayed allocation during submission or metadata
* updates after data IO completion.
*/
- redirty_tail(inode, wb);
+ redirty_tail_locked(inode, wb);
} else if (inode->i_state & I_DIRTY_TIME) {
inode->dirtied_when = jiffies;
inode_io_list_move_locked(inode, wb, &wb->b_dirty_time);
+ inode->i_state &= ~I_SYNC_QUEUED;
} else {
/* The inode is clean. Remove from writeback lists. */
inode_io_list_del_locked(inode, wb);
@@ -1465,25 +1480,25 @@
}
/*
+ * If the inode has dirty timestamps and we need to write them, call
+ * mark_inode_dirty_sync() to notify the filesystem about it and to
+ * change I_DIRTY_TIME into I_DIRTY_SYNC.
+ */
+ if ((inode->i_state & I_DIRTY_TIME) &&
+ (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync ||
+ time_after(jiffies, inode->dirtied_time_when +
+ dirtytime_expire_interval * HZ))) {
+ trace_writeback_lazytime(inode);
+ mark_inode_dirty_sync(inode);
+ }
+
+ /*
* Some filesystems may redirty the inode during the writeback
* due to delalloc, clear dirty metadata flags right before
* write_inode()
*/
spin_lock(&inode->i_lock);
-
dirty = inode->i_state & I_DIRTY;
- if (inode->i_state & I_DIRTY_TIME) {
- if ((dirty & I_DIRTY_INODE) ||
- wbc->sync_mode == WB_SYNC_ALL ||
- unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) ||
- unlikely(time_after(jiffies,
- (inode->dirtied_time_when +
- dirtytime_expire_interval * HZ)))) {
- dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
- trace_writeback_lazytime(inode);
- }
- } else
- inode->i_state &= ~I_DIRTY_TIME_EXPIRED;
inode->i_state &= ~dirty;
/*
@@ -1504,8 +1519,6 @@
spin_unlock(&inode->i_lock);
- if (dirty & I_DIRTY_TIME)
- mark_inode_dirty_sync(inode);
/* Don't write the inode if only I_DIRTY_PAGES was set */
if (dirty & ~I_DIRTY_PAGES) {
int err = write_inode(inode, wbc);
@@ -1669,8 +1682,8 @@
*/
spin_lock(&inode->i_lock);
if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
+ redirty_tail_locked(inode, wb);
spin_unlock(&inode->i_lock);
- redirty_tail(inode, wb);
continue;
}
if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) {
@@ -1811,7 +1824,7 @@
blk_start_plug(&plug);
spin_lock(&wb->list_lock);
if (list_empty(&wb->b_io))
- queue_io(wb, &work);
+ queue_io(wb, &work, jiffies);
__writeback_inodes_wb(wb, &work);
spin_unlock(&wb->list_lock);
blk_finish_plug(&plug);
@@ -1831,7 +1844,7 @@
* takes longer than a dirty_writeback_interval interval, then leave a
* one-second gap.
*
- * older_than_this takes precedence over nr_to_write. So we'll only write back
+ * dirtied_before takes precedence over nr_to_write. So we'll only write back
* all dirty pages if they are all attached to "old" mappings.
*/
static long wb_writeback(struct bdi_writeback *wb,
@@ -1839,14 +1852,11 @@
{
unsigned long wb_start = jiffies;
long nr_pages = work->nr_pages;
- unsigned long oldest_jif;
+ unsigned long dirtied_before = jiffies;
struct inode *inode;
long progress;
struct blk_plug plug;
- oldest_jif = jiffies;
- work->older_than_this = &oldest_jif;
-
blk_start_plug(&plug);
spin_lock(&wb->list_lock);
for (;;) {
@@ -1880,14 +1890,14 @@
* safe.
*/
if (work->for_kupdate) {
- oldest_jif = jiffies -
+ dirtied_before = jiffies -
msecs_to_jiffies(dirty_expire_interval * 10);
} else if (work->for_background)
- oldest_jif = jiffies;
+ dirtied_before = jiffies;
trace_writeback_start(wb, work);
if (list_empty(&wb->b_io))
- queue_io(wb, work);
+ queue_io(wb, work, dirtied_before);
if (work->sb)
progress = writeback_sb_inodes(work->sb, wb, work);
else
@@ -2063,7 +2073,7 @@
struct bdi_writeback, dwork);
long pages_written;
- set_worker_desc("flush-%s", dev_name(wb->bdi->dev));
+ set_worker_desc("flush-%s", bdi_dev_name(wb->bdi));
current->flags |= PF_SWAPWRITE;
if (likely(!current_is_workqueue_rescuer() ||
@@ -2192,28 +2202,6 @@
return ret;
}
-static noinline void block_dump___mark_inode_dirty(struct inode *inode)
-{
- if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
- struct dentry *dentry;
- const char *name = "?";
-
- dentry = d_find_alias(inode);
- if (dentry) {
- spin_lock(&dentry->d_lock);
- name = (const char *) dentry->d_name.name;
- }
- printk(KERN_DEBUG
- "%s(%d): dirtied inode %lu (%s) on %s\n",
- current->comm, task_pid_nr(current), inode->i_ino,
- name, inode->i_sb->s_id);
- if (dentry) {
- spin_unlock(&dentry->d_lock);
- dput(dentry);
- }
- }
-}
-
/**
* __mark_inode_dirty - internal function
*
@@ -2273,9 +2261,6 @@
(dirtytime && (inode->i_state & I_DIRTY_INODE)))
return;
- if (unlikely(block_dump))
- block_dump___mark_inode_dirty(inode);
-
spin_lock(&inode->i_lock);
if (dirtytime && (inode->i_state & I_DIRTY_INODE))
goto out_unlock_inode;
@@ -2289,11 +2274,12 @@
inode->i_state |= flags;
/*
- * If the inode is being synced, just update its dirty state.
- * The unlocker will place the inode on the appropriate
- * superblock list, based upon its state.
+ * If the inode is queued for writeback by flush worker, just
+ * update its dirty state. Once the flush worker is done with
+ * the inode it will place it on the appropriate superblock
+ * list, based upon its state.
*/
- if (inode->i_state & I_SYNC)
+ if (inode->i_state & I_SYNC_QUEUED)
goto out_unlock_inode;
/*