From: NeilBrown <neilb@suse.de>
Date: Wed, 1 Apr 2020 17:26:03 +1100
Subject: [PATCH] MM: replace PF_LESS_THROTTLE with PF_LOCAL_THROTTLE
Patch-mainline: Submitted, Tue, 07 Apr 2020 09:44:25 +1000 - linux-mm@kvack.org,
References: bsc#1163403

PF_LESS_THROTTLE exists for loop-back nfsd, and a similar need in the
loop block driver, where a daemon needs to write to one bdi in
order to free up writes queued to another bdi.

The daemon sets PF_LESS_THROTTLE and gets a larger allowance of dirty
pages, so that it can still dirty pages after other processses have been
throttled.

This approach was designed when all threads were blocked equally,
independently on which device they were writing to, or how fast it was.
Since that time the writeback algorithm has changed substantially with
different threads getting different allowances based on non-trivial
heuristics.  This means the simple "add 25%" heuristic is no longer
reliable.

This patch changes the heuristic to ignore the global limits and
consider only the limit relevant to the bdi being written to.  This
approach is already available for BDI_CAP_STRICTLIMIT users (fuse) and
should not introduce surprises.  This has the desired result of
protecting the task from the consequences of large amounts of dirty data
queued for other devices.

This approach of "only consider the target bdi" is consistent with the
other use of PF_LESS_THROTTLE in current_may_throttle(), were it causes
attention to be focussed only on the target bdi.

So this patch
 - renames PF_LESS_THROTTLE to PF_LOCAL_THROTTLE,
 - remove the 25% bonus that that flag gives, and
 - imposes 'strictlimit' handling for any process with PF_LOCAL_THROTTLE
   set.

Note that previously realtime threads were treated the same as
PF_LESS_THROTTLE threads.  This patch does *not* change the behvaiour for
real-time threads, so it is now different from the behaviour of nfsd and
loop tasks.  I don't know what is wanted for realtime.

Signed-off-by: NeilBrown <neilb@suse.de>
Acked-by: NeilBrown <neilb@suse.com>

---
 drivers/block/loop.c  |    2 +-
 fs/nfsd/vfs.c         |    9 +++++----
 include/linux/sched.h |    2 +-
 mm/page-writeback.c   |   10 ++++++----
 mm/vmscan.c           |    4 ++--
 5 files changed, 15 insertions(+), 12 deletions(-)

--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -910,7 +910,7 @@ static void loop_unprepare_queue(struct
 
 static int loop_kthread_worker_fn(void *worker_ptr)
 {
-	current->flags |= PF_LESS_THROTTLE | PF_MEMALLOC_NOIO;
+	current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO;
 	return kthread_worker_fn(worker_ptr);
 }
 
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -985,12 +985,13 @@ nfsd_vfs_write(struct svc_rqst *rqstp, s
 
 	if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
 		/*
-		 * We want less throttling in balance_dirty_pages()
-		 * and shrink_inactive_list() so that nfs to
+		 * We want throttling in balance_dirty_pages()
+		 * and shrink_inactive_list() to only consider
+		 * the backingdev we are writing to, so that nfs to
 		 * localhost doesn't cause nfsd to lock up due to all
 		 * the client's dirty pages or its congested queue.
 		 */
-		current->flags |= PF_LESS_THROTTLE;
+		current->flags |= PF_LOCAL_THROTTLE;
 
 	exp = fhp->fh_export;
 	use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
@@ -1021,7 +1022,7 @@ out_nfserr:
 	else
 		err = nfserrno(host_err);
 	if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
-		current_restore_flags(pflags, PF_LESS_THROTTLE);
+		current_restore_flags(pflags, PF_LOCAL_THROTTLE);
 	return err;
 }
 
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1257,7 +1257,7 @@ extern struct pid *cad_pid;
 #define PF_KSWAPD		0x00020000	/* I am kswapd */
 #define PF_MEMALLOC_NOFS	0x00040000	/* All allocation requests will inherit GFP_NOFS */
 #define PF_MEMALLOC_NOIO	0x00080000	/* All allocation requests will inherit GFP_NOIO */
-#define PF_LESS_THROTTLE	0x00100000	/* Throttle me less: I clean memory */
+#define PF_LOCAL_THROTTLE	0x00100000	/* Throttle me less: I clean memory */
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
 #define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -387,8 +387,7 @@ static unsigned long global_dirtyable_me
  * Calculate @dtc->thresh and ->bg_thresh considering
  * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}.  The caller
  * must ensure that @dtc->avail is set before calling this function.  The
- * dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and
- * real-time tasks.
+ * dirty limits will be lifted by 1/4 for real-time tasks.
  */
 static void domain_dirty_limits(struct dirty_throttle_control *dtc)
 {
@@ -436,7 +435,7 @@ static void domain_dirty_limits(struct d
 	if (bg_thresh >= thresh)
 		bg_thresh = thresh / 2;
 	tsk = current;
-	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
+	if (rt_task(tsk)) {
 		bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32;
 		thresh += thresh / 4 + global_wb_domain.dirty_limit / 32;
 	}
@@ -486,7 +485,7 @@ static unsigned long node_dirty_limit(st
 	else
 		dirty = vm_dirty_ratio * node_memory / 100;
 
-	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk))
+	if (rt_task(tsk))
 		dirty += dirty / 4;
 
 	return dirty;
@@ -1581,6 +1580,9 @@ static void balance_dirty_pages(struct b
 	bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT;
 	unsigned long start_time = jiffies;
 
+	if (current->flags & PF_LOCAL_THROTTLE)
+		/* This task must only be throttled by its own writeback */
+		strictlimit = true;
 	for (;;) {
 		unsigned long now = jiffies;
 		unsigned long dirty, thresh, bg_thresh;
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1700,13 +1700,13 @@ putback_inactive_pages(struct lruvec *lr
 
 /*
  * If a kernel thread (such as nfsd for loop-back mounts) services
- * a backing device by writing to the page cache it sets PF_LESS_THROTTLE.
+ * a backing device by writing to the page cache it sets PF_LOCAL_THROTTLE.
  * In that case we should only throttle if the backing device it is
  * writing to is congested.  In other cases it is safe to throttle.
  */
 static int current_may_throttle(void)
 {
-	return !(current->flags & PF_LESS_THROTTLE) ||
+	return !(current->flags & PF_LOCAL_THROTTLE) ||
 		current->backing_dev_info == NULL ||
 		bdi_write_congested(current->backing_dev_info);
 }