Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "191 patches.

  Subsystems affected by this patch series: kthread, ia64, scripts,
  ntfs, squashfs, ocfs2, kernel/watchdog, and mm (gup, pagealloc, slab,
  slub, kmemleak, dax, debug, pagecache, gup, swap, memcg, pagemap,
  mprotect, bootmem, dma, tracing, vmalloc, kasan, initialization,
  pagealloc, and memory-failure)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (191 commits)
  mm,hwpoison: make get_hwpoison_page() call get_any_page()
  mm,hwpoison: send SIGBUS with error virutal address
  mm/page_alloc: split pcp->high across all online CPUs for cpuless nodes
  mm/page_alloc: allow high-order pages to be stored on the per-cpu lists
  mm: replace CONFIG_FLAT_NODE_MEM_MAP with CONFIG_FLATMEM
  mm: replace CONFIG_NEED_MULTIPLE_NODES with CONFIG_NUMA
  docs: remove description of DISCONTIGMEM
  arch, mm: remove stale mentions of DISCONIGMEM
  mm: remove CONFIG_DISCONTIGMEM
  m68k: remove support for DISCONTIGMEM
  arc: remove support for DISCONTIGMEM
  arc: update comment about HIGHMEM implementation
  alpha: remove DISCONTIGMEM and NUMA
  mm/page_alloc: move free_the_page
  mm/page_alloc: fix counting of managed_pages
  mm/page_alloc: improve memmap_pages dbg msg
  mm: drop SECTION_SHIFT in code comments
  mm/page_alloc: introduce vm.percpu_pagelist_high_fraction
  mm/page_alloc: limit the number of pages on PCP lists when reclaim is active
  mm/page_alloc: scale the number of pages that are batch freed
  ...

1 files changed, 53 insertions, 36 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0062d5c57d41..e5b38ffe9fca 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -32,7 +32,6 @@
 #include <linux/sysctl.h>
 #include <linux/cpu.h>
 #include <linux/syscalls.h>
-#include <linux/buffer_head.h> /* __set_page_dirty_buffers */
 #include <linux/pagevec.h>
 #include <linux/timer.h>
 #include <linux/sched/rt.h>
@@ -845,7 +844,7 @@ static long long pos_ratio_polynom(unsigned long setpoint,
  *     ^ pos_ratio
  *     |
  *     |            |<===== global dirty control scope ======>|
- * 2.0 .............*
+ * 2.0  * * * * * * *
  *     |            .*
  *     |            . *
  *     |            .   *
@@ -1869,10 +1868,9 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
  * which was newly dirtied.  The function will periodically check the system's
  * dirty state and will initiate writeback if needed.
  *
- * On really big machines, get_writeback_state is expensive, so try to avoid
- * calling it too often (ratelimiting).  But once we're over the dirty memory
- * limit we decrease the ratelimiting by a lot, to prevent individual processes
- * from overshooting the limit by (ratelimit_pages) each.
+ * Once we're over the dirty memory limit we decrease the ratelimiting
+ * by a lot, to prevent individual processes from overshooting the limit
+ * by (ratelimit_pages) each.
  */
 void balance_dirty_pages_ratelimited(struct address_space *mapping)
 {
@@ -1945,6 +1943,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 	struct dirty_throttle_control * const gdtc = &gdtc_stor;
 	struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ?
 						     &mdtc_stor : NULL;
+	unsigned long reclaimable;
+	unsigned long thresh;
 
 	/*
 	 * Similar to balance_dirty_pages() but ignores pages being written
@@ -1957,8 +1957,13 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 	if (gdtc->dirty > gdtc->bg_thresh)
 		return true;
 
-	if (wb_stat(wb, WB_RECLAIMABLE) >
-	    wb_calc_thresh(gdtc->wb, gdtc->bg_thresh))
+	thresh = wb_calc_thresh(gdtc->wb, gdtc->bg_thresh);
+	if (thresh < 2 * wb_stat_error())
+		reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE);
+	else
+		reclaimable = wb_stat(wb, WB_RECLAIMABLE);
+
+	if (reclaimable > thresh)
 		return true;
 
 	if (mdtc) {
@@ -1972,8 +1977,13 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 		if (mdtc->dirty > mdtc->bg_thresh)
 			return true;
 
-		if (wb_stat(wb, WB_RECLAIMABLE) >
-		    wb_calc_thresh(mdtc->wb, mdtc->bg_thresh))
+		thresh = wb_calc_thresh(mdtc->wb, mdtc->bg_thresh);
+		if (thresh < 2 * wb_stat_error())
+			reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE);
+		else
+			reclaimable = wb_stat(wb, WB_RECLAIMABLE);
+
+		if (reclaimable > thresh)
 			return true;
 	}
 
@@ -2045,8 +2055,6 @@ void laptop_sync_completion(void)
 /*
  * If ratelimit_pages is too high then we can get into dirty-data overload
  * if a large number of processes all perform writes at the same time.
- * If it is too low then SMP machines will call the (expensive)
- * get_writeback_state too often.
  *
  * Here we set ratelimit_pages to a level which ensures that when all CPUs are
  * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory
@@ -2409,6 +2417,7 @@ int __set_page_dirty_no_writeback(struct page *page)
 		return !TestSetPageDirty(page);
 	return 0;
 }
+EXPORT_SYMBOL(__set_page_dirty_no_writeback);
 
 /*
  * Helper function for set_page_dirty family.
@@ -2417,7 +2426,8 @@ int __set_page_dirty_no_writeback(struct page *page)
  *
  * NOTE: This relies on being atomic wrt interrupts.
  */
-void account_page_dirtied(struct page *page, struct address_space *mapping)
+static void account_page_dirtied(struct page *page,
+		struct address_space *mapping)
 {
 	struct inode *inode = mapping->host;
 
@@ -2436,7 +2446,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 		inc_wb_stat(wb, WB_DIRTIED);
 		task_io_account_write(PAGE_SIZE);
 		current->nr_dirtied++;
-		this_cpu_inc(bdp_ratelimits);
+		__this_cpu_inc(bdp_ratelimits);
 
 		mem_cgroup_track_foreign_dirty(page, wb);
 	}
@@ -2459,6 +2469,30 @@ void account_page_cleaned(struct page *page, struct address_space *mapping,
 }
 
 /*
+ * Mark the page dirty, and set it dirty in the page cache, and mark the inode
+ * dirty.
+ *
+ * If warn is true, then emit a warning if the page is not uptodate and has
+ * not been truncated.
+ *
+ * The caller must hold lock_page_memcg().
+ */
+void __set_page_dirty(struct page *page, struct address_space *mapping,
+			     int warn)
+{
+	unsigned long flags;
+
+	xa_lock_irqsave(&mapping->i_pages, flags);
+	if (page->mapping) {	/* Race with truncate? */
+		WARN_ON_ONCE(warn && !PageUptodate(page));
+		account_page_dirtied(page, mapping);
+		__xa_set_mark(&mapping->i_pages, page_index(page),
+				PAGECACHE_TAG_DIRTY);
+	}
+	xa_unlock_irqrestore(&mapping->i_pages, flags);
+}
+
+/*
  * For address_spaces which do not use buffers.  Just tag the page as dirty in
  * the xarray.
  *
@@ -2475,20 +2509,12 @@ int __set_page_dirty_nobuffers(struct page *page)
 	lock_page_memcg(page);
 	if (!TestSetPageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
-		unsigned long flags;
 
 		if (!mapping) {
 			unlock_page_memcg(page);
 			return 1;
 		}
-
-		xa_lock_irqsave(&mapping->i_pages, flags);
-		BUG_ON(page_mapping(page) != mapping);
-		WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
-		account_page_dirtied(page, mapping);
-		__xa_set_mark(&mapping->i_pages, page_index(page),
-				   PAGECACHE_TAG_DIRTY);
-		xa_unlock_irqrestore(&mapping->i_pages, flags);
+		__set_page_dirty(page, mapping, !PagePrivate(page));
 		unlock_page_memcg(page);
 
 		if (mapping->host) {
@@ -2546,13 +2572,9 @@ EXPORT_SYMBOL(redirty_page_for_writepage);
 /*
  * Dirty a page.
  *
- * For pages with a mapping this should be done under the page lock
- * for the benefit of asynchronous memory errors who prefer a consistent
- * dirty state. This rule can be broken in some special cases,
- * but should be better not to.
- *
- * If the mapping doesn't provide a set_page_dirty a_op, then
- * just fall through and assume that it wants buffer_heads.
+ * For pages with a mapping this should be done under the page lock for the
+ * benefit of asynchronous memory errors who prefer a consistent dirty state.
+ * This rule can be broken in some special cases, but should be better not to.
  */
 int set_page_dirty(struct page *page)
 {
@@ -2560,7 +2582,6 @@ int set_page_dirty(struct page *page)
 
 	page = compound_head(page);
 	if (likely(mapping)) {
-		int (*spd)(struct page *) = mapping->a_ops->set_page_dirty;
 		/*
 		 * readahead/lru_deactivate_page could remain
 		 * PG_readahead/PG_reclaim due to race with end_page_writeback
@@ -2573,11 +2594,7 @@ int set_page_dirty(struct page *page)
 		 */
 		if (PageReclaim(page))
 			ClearPageReclaim(page);
-#ifdef CONFIG_BLOCK
-		if (!spd)
-			spd = __set_page_dirty_buffers;
-#endif
-		return (*spd)(page);
+		return mapping->a_ops->set_page_dirty(page);
 	}
 	if (!PageDirty(page)) {
 		if (!TestSetPageDirty(page))