Merge branch 'writeback-for-linus' of git://git.kernel.org/pub/scm/li…

…nux/kernel/git/wfg/linux

* 'writeback-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/wfg/linux:
  writeback: move MIN_WRITEBACK_PAGES to fs-writeback.c
  writeback: balanced_rate cannot exceed write bandwidth
  writeback: do strict bdi dirty_exceeded
  writeback: avoid tiny dirty poll intervals
  writeback: max, min and target dirty pause time
  writeback: dirty ratelimit - think time compensation
  btrfs: fix dirtied pages accounting on sub-page writes
  writeback: fix dirtied pages accounting on redirty
  writeback: fix dirtied pages accounting on sub-page writes
  writeback: charge leaked page dirties to active tasks
  writeback: Include all dirty inodes in background writeback

fs/btrfs/file.c

@@ -1136,7 +1136,8 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
 				     GFP_NOFS);
 	}
 	for (i = 0; i < num_pages; i++) {
-		clear_page_dirty_for_io(pages[i]);
+		if (clear_page_dirty_for_io(pages[i]))
+			account_page_redirty(pages[i]);
 		set_page_extent_mapped(pages[i]);
 		WARN_ON(!PageLocked(pages[i]));
 	}

fs/fs-writeback.c

@@ -20,6 +20,7 @@
 #include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/pagemap.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/writeback.h>
@@ -28,6 +29,11 @@
 #include <linux/tracepoint.h>
 #include "internal.h"
 
+/*
+ * 4MB minimal write chunk size
+ */
+#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_CACHE_SHIFT - 10))
+
 /*
  * Passed into wb_writeback(), essentially a subset of writeback_control
  */
@@ -742,11 +748,17 @@ static long wb_writeback(struct bdi_writeback *wb,
 		if (work->for_background && !over_bground_thresh(wb->bdi))
 			break;
 
+		/*
+		 * Kupdate and background works are special and we want to
+		 * include all inodes that need writing. Livelock avoidance is
+		 * handled by these works yielding to any other work so we are
+		 * safe.
+		 */
 		if (work->for_kupdate) {
 			oldest_jif = jiffies -
 				msecs_to_jiffies(dirty_expire_interval * 10);
-			work->older_than_this = &oldest_jif;
-		}
+		} else if (work->for_background)
+			oldest_jif = jiffies;
 
 		trace_writeback_start(wb->bdi, work);
 		if (list_empty(&wb->b_io))

include/linux/sched.h

@@ -1544,6 +1544,7 @@ struct task_struct {
 	 */
 	int nr_dirtied;
 	int nr_dirtied_pause;
+	unsigned long dirty_paused_when; /* start of a write-and-pause period */
 
 #ifdef CONFIG_LATENCYTOP
 	int latency_record_count;

include/linux/writeback.h

@@ -7,6 +7,8 @@
 #include <linux/sched.h>
 #include <linux/fs.h>
 
+DECLARE_PER_CPU(int, dirty_throttle_leaks);
+
 /*
  * The 1/4 region under the global dirty thresh is for smooth dirty throttling:
  *
@@ -23,11 +25,6 @@
 #define DIRTY_SCOPE		8
 #define DIRTY_FULL_SCOPE	(DIRTY_SCOPE / 2)
 
-/*
- * 4MB minimal write chunk size
- */
-#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_CACHE_SHIFT - 10))
-
 struct backing_dev_info;
 
 /*
@@ -194,6 +191,8 @@ void writeback_set_ratelimit(void);
 void tag_pages_for_writeback(struct address_space *mapping,
 			     pgoff_t start, pgoff_t end);
 
+void account_page_redirty(struct page *page);
+
 /* pdflush.c */
 extern int nr_pdflush_threads;	/* Global so it can be exported to sysctl
 				   read-only. */

include/trace/events/writeback.h

@@ -300,12 +300,13 @@ TRACE_EVENT(balance_dirty_pages,
 		 unsigned long dirty_ratelimit,
 		 unsigned long task_ratelimit,
 		 unsigned long dirtied,
+		 unsigned long period,
 		 long pause,
 		 unsigned long start_time),
 
 	TP_ARGS(bdi, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty,
 		dirty_ratelimit, task_ratelimit,
-		dirtied, pause, start_time),
+		dirtied, period, pause, start_time),
 
 	TP_STRUCT__entry(
 		__array(	 char,	bdi, 32)
@@ -320,6 +321,8 @@ TRACE_EVENT(balance_dirty_pages,
 		__field(unsigned int,	dirtied_pause)
 		__field(unsigned long,	paused)
 		__field(	 long,	pause)
+		__field(unsigned long,	period)
+		__field(	 long,	think)
 	),
 
 	TP_fast_assign(
@@ -336,6 +339,9 @@ TRACE_EVENT(balance_dirty_pages,
 		__entry->task_ratelimit	= KBps(task_ratelimit);
 		__entry->dirtied	= dirtied;
 		__entry->dirtied_pause	= current->nr_dirtied_pause;
+		__entry->think		= current->dirty_paused_when == 0 ? 0 :
+			 (long)(jiffies - current->dirty_paused_when) * 1000/HZ;
+		__entry->period		= period * 1000 / HZ;
 		__entry->pause		= pause * 1000 / HZ;
 		__entry->paused		= (jiffies - start_time) * 1000 / HZ;
 	),
@@ -346,7 +352,7 @@ TRACE_EVENT(balance_dirty_pages,
 		  "bdi_setpoint=%lu bdi_dirty=%lu "
 		  "dirty_ratelimit=%lu task_ratelimit=%lu "
 		  "dirtied=%u dirtied_pause=%u "
-		  "paused=%lu pause=%ld",
+		  "paused=%lu pause=%ld period=%lu think=%ld",
 		  __entry->bdi,
 		  __entry->limit,
 		  __entry->setpoint,
@@ -358,7 +364,9 @@ TRACE_EVENT(balance_dirty_pages,
 		  __entry->dirtied,
 		  __entry->dirtied_pause,
 		  __entry->paused,	/* ms */
-		  __entry->pause	/* ms */
+		  __entry->pause,	/* ms */
+		  __entry->period,	/* ms */
+		  __entry->think	/* ms */
 	  )
 );
 

kernel/exit.c

@@ -51,6 +51,7 @@
 #include <trace/events/sched.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/oom.h>
+#include <linux/writeback.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -1035,6 +1036,8 @@ NORET_TYPE void do_exit(long code)
 	validate_creds_for_do_exit(tsk);
 
 	preempt_disable();
+	if (tsk->nr_dirtied)
+		__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
 	exit_rcu();
 	/* causes final put_task_struct in finish_task_switch(). */
 	tsk->state = TASK_DEAD;

kernel/fork.c

@@ -1294,6 +1294,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	p->nr_dirtied = 0;
 	p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
+	p->dirty_paused_when = 0;
 
 	/*
 	 * Ok, make it visible to the rest of the system.