[PATCH 00/97] Misc series of functional/performance fixes for 3.12-stable

[PATCH 00/97] Misc series of functional/performance fixes for 3.12-stable

[Mel Gorman]

Kernel Summit 2014 had a topic on performance regressions and catching
them.  The situation relatively recently has been good but I believe this
is partially due to major distributions stabilising recently and hardware
vendors working on performance for their latest platforms. On thing I fear is
that we miss performance regressions because releases contains performance
gains and losses, some of which balance out. After a number of mainline
releases, the performance may look ok but in comparison to a distribution
kernel cherry-picking the picture is not as rosy.  The 3.0-longterm
included a number of performance-related patches so it could be used as
a good performance baseline for later releases. It is no longer maintained.

This series contains a large number of patches against 3.12-longterm that
never made it to stable as the bugs were not serious enough or they were
performance patches. 3.10-longterm may need other pre-requisites I did
not research and 3.14-longterm should be able to apply a subset although
I have not tested the result.

The first 12 patches are mostly functional patches. After that is mostly but
not exclusively performance-related patches. Sometimes there are patches
that are clean-ups so that later patches do not have to be extensively
modified for the backport.

I'm aware that this series is outside the standard rules for stable.
Even the stable rules for performance patches is being violated here as
I do not added information to the changelog on user-visible effects or
bugzilla entries beyond what is already available as the information was
not recorded when these patches were identified. By the nature of many of
the patches they do include performance data though. It's up to the -stable
maintainers for each longterm kernel if they want to use the kernel they
maintain as a performance baseline or not.

Al Viro (1):
  callers of iov_copy_from_user_atomic() don't need pagecache_disable()

Bob Liu (2):
  mm: thp: cleanup: mv alloc_hugepage to better place
  mm: thp: khugepaged: add policy for finding target node

Christoph Lameter (1):
  vmscan: reclaim_clean_pages_from_list() must use mod_zone_page_state()

Damien Ramonda (1):
  readahead: fix sequential read cache miss detection

Dan Streetman (4):
  swap: change swap_info singly-linked list to list_head
  lib/plist: add helper functions
  lib/plist: add plist_requeue
  swap: change swap_list_head to plist, add swap_avail_head

Dave Chinner (1):
  fs/superblock: unregister sb shrinker before ->kill_sb()

David Rientjes (10):
  mm, thp: do not allow thp faults to avoid cpuset restrictions
  mm, compaction: avoid isolating pinned pages
  mm, compaction: determine isolation mode only once
  mm, compaction: ignore pageblock skip when manually invoking
    compaction
  mm, migration: add destination page freeing callback
  mm, compaction: return failed migration target pages back to freelist
  mm, compaction: add per-zone migration pfn cache for async compaction
  mm, compaction: embed migration mode in compact_control
  mm, compaction: terminate async compaction when rescheduling
  mm, thp: only collapse hugepages to nodes with affinity for
    zone_reclaim_mode

Davidlohr Bueso (1):
  mm: per-thread vma caching

Fabian Frederick (1):
  mm/readahead.c: inline ra_submit

Han Pingtian (1):
  mm: prevent setting of a value less than 0 to min_free_kbytes

Heesub Shin (1):
  mm/compaction: clean up unused code lines

Hugh Dickins (4):
  mm: fix bad rss-counter if remap_file_pages raced migration
  mm: fix direct reclaim writeback regression
  shmem: fix init_page_accessed use to stop !PageLRU bug
  mm/memory.c: use entry = ACCESS_ONCE(*pte) in handle_pte_fault()

Jens Axboe (1):
  mm/filemap.c: avoid always dirtying mapping->flags on O_DIRECT

Jerome Marchand (2):
  mm: make copy_pte_range static again
  memcg, vmscan: Fix forced scan of anonymous pages

Jianyu Zhan (1):
  mm/swap.c: clean up *lru_cache_add* functions

Johannes Weiner (5):
  lib: radix-tree: add radix_tree_delete_item()
  mm: shmem: save one radix tree lookup when truncating swapped pages
  mm: filemap: move radix tree hole searching here
  mm + fs: prepare for non-page entries in page cache radix trees
  mm: madvise: fix MADV_WILLNEED on shmem swapouts

Joonsoo Kim (7):
  slab: correct pfmemalloc check
  mm/compaction: disallow high-order page for migration target
  mm/compaction: do not call suitable_migration_target() on every page
  mm/compaction: change the timing to check to drop the spinlock
  mm/compaction: check pageblock suitability once per pageblock
  mm/compaction: clean-up code on success of ballon isolation
  vmalloc: use rcu list iterator to reduce vmap_area_lock contention

KOSAKI Motohiro (2):
  mm: get rid of unnecessary overhead of trace_mm_page_alloc_extfrag()
  mm: __rmqueue_fallback() should respect pageblock type

Linus Torvalds (1):
  mm: don't pointlessly use BUG_ON() for sanity check

Mel Gorman (30):
  mm, x86: Account for TLB flushes only when debugging
  x86/mm: Clean up inconsistencies when flushing TLB ranges
  x86/mm: Eliminate redundant page table walk during TLB range flushing
  mm: compaction: trace compaction begin and end
  mm: optimize put_mems_allowed() usage
  mm: vmscan: use proportional scanning during direct reclaim and full
    scan at DEF_PRIORITY
  mm: page_alloc: do not update zlc unless the zlc is active
  mm: page_alloc: do not treat a zone that cannot be used for dirty
    pages as "full"
  include/linux/jump_label.h: expose the reference count
  mm: page_alloc: use jump labels to avoid checking number_of_cpusets
  mm: page_alloc: calculate classzone_idx once from the zonelist ref
  mm: page_alloc: only check the zone id check if pages are buddies
  mm: page_alloc: only check the alloc flags and gfp_mask for dirty once
  mm: page_alloc: take the ALLOC_NO_WATERMARK check out of the fast path
  mm: page_alloc: use unsigned int for order in more places
  mm: page_alloc: reduce number of times page_to_pfn is called
  mm: page_alloc: convert hot/cold parameter and immediate callers to
    bool
  mm: page_alloc: lookup pageblock migratetype with IRQs enabled during
    free
  mm: shmem: avoid atomic operation during shmem_getpage_gfp
  mm: do not use atomic operations when releasing pages
  mm: do not use unnecessary atomic operations when adding pages to the
    LRU
  fs: buffer: do not use unnecessary atomic operations when discarding
    buffers
  mm: non-atomically mark page accessed during page cache allocation
    where possible
  mm: avoid unnecessary atomic operations during end_page_writeback()
  mm: pagemap: avoid unnecessary overhead when tracepoints are
    deactivated
  mm: rearrange zone fields into read-only, page alloc, statistics and
    page reclaim lines
  mm: move zone->pages_scanned into a vmstat counter
  mm: vmscan: only update per-cpu thresholds for online CPU
  mm: page_alloc: abort fair zone allocation policy when remotes nodes
    are encountered
  mm: page_alloc: reduce cost of the fair zone allocation policy

Michal Hocko (1):
  mm: exclude memoryless nodes from zone_reclaim

Nishanth Aravamudan (1):
  hugetlb: ensure hugepage access is denied if hugepages are not
    supported

Raghavendra K T (1):
  mm/readahead.c: fix readahead failure for memoryless NUMA nodes and
    limit readahead pages

Sasha Levin (1):
  mm: remove read_cache_page_async()

Shaohua Li (2):
  swap: add a simple detector for inappropriate swapin readahead
  x86/mm: In the PTE swapout page reclaim case clear the accessed bit
    instead of flushing the TLB

Tim Chen (1):
  fs/superblock: avoid locking counting inodes and dentries before
    reclaiming them

Vladimir Davydov (4):
  mm: vmscan: shrink all slab objects if tight on memory
  mm: vmscan: call NUMA-unaware shrinkers irrespective of nodemask
  mm: vmscan: respect NUMA policy mask when shrinking slab on direct
    reclaim
  mm: vmscan: shrink_slab: rename max_pass -> freeable

Vlastimil Babka (8):
  mm: compaction: encapsulate defer reset logic
  mm: compaction: do not mark unmovable pageblocks as skipped in async
    compaction
  mm: compaction: reset scanner positions immediately when they meet
  mm/compaction: cleanup isolate_freepages()
  mm/compaction: do not count migratepages when unnecessary
  mm/compaction: avoid rescanning pageblocks in isolate_freepages
  mm, compaction: properly signal and act upon lock and need_sched()
    contention
  mm/page_alloc: prevent MIGRATE_RESERVE pages from being misplaced

Yasuaki Ishimatsu (1):
  mm: get rid of unnecessary pageblock scanning in
    setup_zone_migrate_reserve

 arch/tile/mm/homecache.c                 |   2 +-
 arch/unicore32/include/asm/mmu_context.h |   4 +-
 arch/x86/include/asm/tlbflush.h          |   6 +-
 arch/x86/kernel/cpu/mtrr/generic.c       |   4 +-
 arch/x86/mm/pgtable.c                    |  21 +-
 arch/x86/mm/tlb.c                        |  52 +---
 fs/btrfs/compression.c                   |   2 +-
 fs/btrfs/extent_io.c                     |  15 +-
 fs/btrfs/file.c                          |  10 +-
 fs/buffer.c                              |  28 +-
 fs/cramfs/inode.c                        |   3 +-
 fs/exec.c                                |   5 +-
 fs/ext4/mballoc.c                        |  14 +-
 fs/f2fs/checkpoint.c                     |   1 -
 fs/f2fs/node.c                           |   2 -
 fs/fuse/dev.c                            |   2 +-
 fs/fuse/file.c                           |   4 -
 fs/gfs2/aops.c                           |   1 -
 fs/gfs2/meta_io.c                        |   4 +-
 fs/hugetlbfs/inode.c                     |   5 +
 fs/jffs2/fs.c                            |   2 +-
 fs/nfs/blocklayout/blocklayout.c         |   2 +-
 fs/ntfs/attrib.c                         |   1 -
 fs/ntfs/file.c                           |   1 -
 fs/proc/task_mmu.c                       |   3 +-
 fs/super.c                               |  16 +-
 include/linux/compaction.h               |  20 +-
 include/linux/cpuset.h                   |  56 ++--
 include/linux/gfp.h                      |   4 +-
 include/linux/huge_mm.h                  |   4 -
 include/linux/hugetlb.h                  |  10 +
 include/linux/jump_label.h               |  20 +-
 include/linux/migrate.h                  |  11 +-
 include/linux/mm.h                       |  11 +-
 include/linux/mm_types.h                 |   4 +-
 include/linux/mmzone.h                   | 233 ++++++++-------
 include/linux/page-flags.h               |   6 +-
 include/linux/pageblock-flags.h          |  33 +--
 include/linux/pagemap.h                  | 131 +++++++--
 include/linux/pagevec.h                  |   5 +
 include/linux/plist.h                    |  45 +++
 include/linux/radix-tree.h               |   5 +-
 include/linux/sched.h                    |   7 +
 include/linux/shmem_fs.h                 |   1 +
 include/linux/swap.h                     |  30 +-
 include/linux/swapfile.h                 |   2 +-
 include/linux/vm_event_item.h            |   4 +-
 include/linux/vmacache.h                 |  38 +++
 include/linux/vmstat.h                   |   8 +
 include/trace/events/compaction.h        |  67 ++++-
 include/trace/events/kmem.h              |  10 +-
 include/trace/events/pagemap.h           |  16 +-
 kernel/cpuset.c                          |  16 +-
 kernel/debug/debug_core.c                |  14 +-
 kernel/fork.c                            |   7 +-
 lib/plist.c                              |  52 ++++
 lib/radix-tree.c                         | 106 ++-----
 mm/Makefile                              |   2 +-
 mm/compaction.c                          | 347 +++++++++++++----------
 mm/filemap.c                             | 470 +++++++++++++++++++++----------
 mm/fremap.c                              |  28 +-
 mm/frontswap.c                           |  13 +-
 mm/huge_memory.c                         |  93 ++++--
 mm/hugetlb.c                             |  17 +-
 mm/internal.h                            |  22 +-
 mm/madvise.c                             |   2 +-
 mm/memory-failure.c                      |   4 +-
 mm/memory.c                              |   4 +-
 mm/memory_hotplug.c                      |   2 +-
 mm/mempolicy.c                           |  16 +-
 mm/migrate.c                             |  56 ++--
 mm/mincore.c                             |  20 +-
 mm/mmap.c                                |  55 ++--
 mm/nommu.c                               |  24 +-
 mm/page_alloc.c                          | 439 ++++++++++++++++-------------
 mm/readahead.c                           |  37 +--
 mm/shmem.c                               | 133 +++------
 mm/slab.c                                |  12 +-
 mm/slub.c                                |  16 +-
 mm/swap.c                                | 101 ++++++-
 mm/swap_state.c                          |  65 ++++-
 mm/swapfile.c                            | 224 ++++++++-------
 mm/truncate.c                            |  74 ++++-
 mm/vmacache.c                            | 114 ++++++++
 mm/vmalloc.c                             |   6 +-
 mm/vmscan.c                              | 144 ++++++----
 mm/vmstat.c                              |  13 +-
 87 files changed, 2374 insertions(+), 1365 deletions(-)
 create mode 100644 include/linux/vmacache.h
 create mode 100644 mm/vmacache.c

-- 
1.8.4.5

[PATCH 01/97] mm: thp: cleanup: mv alloc_hugepage to better place

[Mel Gorman]

From: Bob Liu <lliubbo@gmail.com>

commit 10dc4155c7714f508fe2e4667164925ea971fb25 upstream.

Move alloc_hugepage() to a better place, no need for a seperate #ifndef
CONFIG_NUMA

Signed-off-by: Bob Liu <bob.liu@oracle.com>
Reviewed-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Andrew Davidoff <davidoff@qedmf.net>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/huge_memory.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 389973f..738a57e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -758,14 +758,6 @@ static inline struct page *alloc_hugepage_vma(int defrag,
 			       HPAGE_PMD_ORDER, vma, haddr, nd);
 }
 
-#ifndef CONFIG_NUMA
-static inline struct page *alloc_hugepage(int defrag)
-{
-	return alloc_pages(alloc_hugepage_gfpmask(defrag, 0),
-			   HPAGE_PMD_ORDER);
-}
-#endif
-
 static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 		struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
 		struct page *zero_page)
@@ -2249,6 +2241,12 @@ static struct page
 	return *hpage;
 }
 #else
+static inline struct page *alloc_hugepage(int defrag)
+{
+	return alloc_pages(alloc_hugepage_gfpmask(defrag, 0),
+			   HPAGE_PMD_ORDER);
+}
+
 static struct page *khugepaged_alloc_hugepage(bool *wait)
 {
 	struct page *hpage;
-- 
1.8.4.5

[PATCH 02/97] mm: thp: khugepaged: add policy for finding target node

[Mel Gorman]

From: Bob Liu <lliubbo@gmail.com>

commit 9f1b868a13ac36bd207a571f5ea1193d823ab18d upstream.

Khugepaged will scan/free HPAGE_PMD_NR normal pages and replace with a
hugepage which is allocated from the node of the first scanned normal
page, but this policy is too rough and may end with unexpected result to
upper users.

The problem is the original page-balancing among all nodes will be
broken after hugepaged started.  Thinking about the case if the first
scanned normal page is allocated from node A, most of other scanned
normal pages are allocated from node B or C..  But hugepaged will always
allocate hugepage from node A which will cause extra memory pressure on
node A which is not the situation before khugepaged started.

This patch try to fix this problem by making khugepaged allocate
hugepage from the node which have max record of scaned normal pages hit,
so that the effect to original page-balancing can be minimized.

The other problem is if normal scanned pages are equally allocated from
Node A,B and C, after khugepaged started Node A will still suffer extra
memory pressure.

Andrew Davidoff reported a related issue several days ago.  He wanted
his application interleaving among all nodes and "numactl
--interleave=all ./test" was used to run the testcase, but the result
wasn't not as expected.

  cat /proc/2814/numa_maps:
  7f50bd440000 interleave:0-3 anon=51403 dirty=51403 N0=435 N1=435 N2=435 N3=50098

The end result showed that most pages are from Node3 instead of
interleave among node0-3 which was unreasonable.

This patch also fix this issue by allocating hugepage round robin from
all nodes have the same record, after this patch the result was as
expected:

  7f78399c0000 interleave:0-3 anon=51403 dirty=51403 N0=12723 N1=12723 N2=13235 N3=12722

The simple testcase is like this:

int main() {
	char *p;
	int i;
	int j;

	for (i=0; i < 200; i++) {
		p = (char *)malloc(1048576);
		printf("malloc done\n");

		if (p == 0) {
			printf("Out of memory\n");
			return 1;
		}
		for (j=0; j < 1048576; j++) {
			p[j] = 'A';
		}
		printf("touched memory\n");

		sleep(1);
	}
	printf("enter sleep\n");
	while(1) {
		sleep(100);
	}
}

[akpm@linux-foundation.org: make last_khugepaged_target_node local to khugepaged_find_target_node()]
Reported-by: Andrew Davidoff <davidoff@qedmf.net>
Tested-by: Andrew Davidoff <davidoff@qedmf.net>
Signed-off-by: Bob Liu <bob.liu@oracle.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/huge_memory.c | 53 ++++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 44 insertions(+), 9 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 738a57e..515e589 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2189,7 +2189,34 @@ static void khugepaged_alloc_sleep(void)
 			msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
 }
 
+static int khugepaged_node_load[MAX_NUMNODES];
+
 #ifdef CONFIG_NUMA
+static int khugepaged_find_target_node(void)
+{
+	static int last_khugepaged_target_node = NUMA_NO_NODE;
+	int nid, target_node = 0, max_value = 0;
+
+	/* find first node with max normal pages hit */
+	for (nid = 0; nid < MAX_NUMNODES; nid++)
+		if (khugepaged_node_load[nid] > max_value) {
+			max_value = khugepaged_node_load[nid];
+			target_node = nid;
+		}
+
+	/* do some balance if several nodes have the same hit record */
+	if (target_node <= last_khugepaged_target_node)
+		for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES;
+				nid++)
+			if (max_value == khugepaged_node_load[nid]) {
+				target_node = nid;
+				break;
+			}
+
+	last_khugepaged_target_node = target_node;
+	return target_node;
+}
+
 static bool khugepaged_prealloc_page(struct page **hpage, bool *wait)
 {
 	if (IS_ERR(*hpage)) {
@@ -2223,9 +2250,8 @@ static struct page
 	 * mmap_sem in read mode is good idea also to allow greater
 	 * scalability.
 	 */
-	*hpage  = alloc_hugepage_vma(khugepaged_defrag(), vma, address,
-				      node, __GFP_OTHER_NODE);
-
+	*hpage = alloc_pages_exact_node(node, alloc_hugepage_gfpmask(
+		khugepaged_defrag(), __GFP_OTHER_NODE), HPAGE_PMD_ORDER);
 	/*
 	 * After allocating the hugepage, release the mmap_sem read lock in
 	 * preparation for taking it in write mode.
@@ -2241,6 +2267,11 @@ static struct page
 	return *hpage;
 }
 #else
+static int khugepaged_find_target_node(void)
+{
+	return 0;
+}
+
 static inline struct page *alloc_hugepage(int defrag)
 {
 	return alloc_pages(alloc_hugepage_gfpmask(defrag, 0),
@@ -2453,6 +2484,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	if (pmd_trans_huge(*pmd))
 		goto out;
 
+	memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 	for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR;
 	     _pte++, _address += PAGE_SIZE) {
@@ -2469,12 +2501,13 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		if (unlikely(!page))
 			goto out_unmap;
 		/*
-		 * Chose the node of the first page. This could
-		 * be more sophisticated and look at more pages,
-		 * but isn't for now.
+		 * Record which node the original page is from and save this
+		 * information to khugepaged_node_load[].
+		 * Khupaged will allocate hugepage from the node has the max
+		 * hit record.
 		 */
-		if (node == NUMA_NO_NODE)
-			node = page_to_nid(page);
+		node = page_to_nid(page);
+		khugepaged_node_load[node]++;
 		VM_BUG_ON(PageCompound(page));
 		if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
 			goto out_unmap;
@@ -2489,9 +2522,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		ret = 1;
 out_unmap:
 	pte_unmap_unlock(pte, ptl);
-	if (ret)
+	if (ret) {
+		node = khugepaged_find_target_node();
 		/* collapse_huge_page will return with the mmap_sem released */
 		collapse_huge_page(mm, address, hpage, vma, node);
+	}
 out:
 	return ret;
 }
-- 
1.8.4.5

[PATCH 03/97] slab: correct pfmemalloc check

[Mel Gorman]

From: Joonsoo Kim <iamjoonsoo.kim@lge.com>

commit 73293c2f900d0adbb6a415b312cd57976d5ae242 upstream.

We checked pfmemalloc by slab unit, not page unit. You can see this
in is_slab_pfmemalloc(). So other pages don't need to be set/cleared
pfmemalloc.

And, therefore we should check pfmemalloc in page flag of first page,
but current implementation don't do that. virt_to_head_page(obj) just
return 'struct page' of that object, not one of first page, since the SLAB
don't use __GFP_COMP when CONFIG_MMU. To get 'struct page' of first page,
we first get a slab and try to get it via virt_to_head_page(slab->s_mem).

Acked-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Pekka Enberg <penberg@iki.fi>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/slab.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/mm/slab.c b/mm/slab.c
index 2580db0..0b4ddaf 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -930,7 +930,8 @@ static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
 {
 	if (unlikely(pfmemalloc_active)) {
 		/* Some pfmemalloc slabs exist, check if this is one */
-		struct page *page = virt_to_head_page(objp);
+		struct slab *slabp = virt_to_slab(objp);
+		struct page *page = virt_to_head_page(slabp->s_mem);
 		if (PageSlabPfmemalloc(page))
 			set_obj_pfmemalloc(&objp);
 	}
@@ -1776,7 +1777,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 		__SetPageSlab(page + i);
 
 		if (page->pfmemalloc)
-			SetPageSlabPfmemalloc(page + i);
+			SetPageSlabPfmemalloc(page);
 	}
 	memcg_bind_pages(cachep, cachep->gfporder);
 
@@ -1809,9 +1810,10 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr)
 	else
 		sub_zone_page_state(page_zone(page),
 				NR_SLAB_UNRECLAIMABLE, nr_freed);
+
+	__ClearPageSlabPfmemalloc(page);
 	while (i--) {
 		BUG_ON(!PageSlab(page));
-		__ClearPageSlabPfmemalloc(page);
 		__ClearPageSlab(page);
 		page++;
 	}
-- 
1.8.4.5

[PATCH 04/97] mm: prevent setting of a value less than 0 to min_free_kbytes

[Mel Gorman]

From: Han Pingtian <hanpt@linux.vnet.ibm.com>

commit da8c757b080ee84f219fa2368cb5dd23ac304fc0 upstream.

If echo -1 > /proc/vm/sys/min_free_kbytes, the system will hang.  Changing
proc_dointvec() to proc_dointvec_minmax() in the
min_free_kbytes_sysctl_handler() can prevent this to happen.

mhocko said:

: You can still do echo $BIG_VALUE > /proc/vm/sys/min_free_kbytes and make
: your machine unusable but I agree that proc_dointvec_minmax is more
: suitable here as we already have:
:
: 	.proc_handler   = min_free_kbytes_sysctl_handler,
: 	.extra1         = &zero,
:
: It used to work properly but then 6fce56ec91b5 ("sysctl: Remove references
: to ctl_name and strategy from the generic sysctl table") has removed
: sysctl_intvec strategy and so extra1 is ignored.

Signed-off-by: Han Pingtian <hanpt@linux.vnet.ibm.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6e0a9cf..bffedeb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5734,7 +5734,12 @@ module_init(init_per_zone_wmark_min)
 int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
-	proc_dointvec(table, write, buffer, length, ppos);
+	int rc;
+
+	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
+	if (rc)
+		return rc;
+
 	if (write) {
 		user_min_free_kbytes = min_free_kbytes;
 		setup_per_zone_wmarks();
-- 
1.8.4.5

[PATCH 05/97] mm: fix bad rss-counter if remap_file_pages raced migration

[Mel Gorman]

From: Hugh Dickins <hughd@google.com>

commit 887843961c4b4681ee993c36d4997bf4b4aa8253 upstream.

Fix some "Bad rss-counter state" reports on exit, arising from the
interaction between page migration and remap_file_pages(): zap_pte()
must count a migration entry when zapping it.

And yes, it is possible (though very unusual) to find an anon page or
swap entry in a VM_SHARED nonlinear mapping: coming from that horrid
get_user_pages(write, force) case which COWs even in a shared mapping.

Signed-off-by: Hugh Dickins <hughd@google.com>
Tested-by: Sasha Levin sasha.levin@oracle.com>
Tested-by: Dave Jones davej@redhat.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/fremap.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/mm/fremap.c b/mm/fremap.c
index bbc4d66..34feba6 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -23,28 +23,44 @@
 
 #include "internal.h"
 
+static int mm_counter(struct page *page)
+{
+	return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES;
+}
+
 static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = *ptep;
+	struct page *page;
+	swp_entry_t entry;
 
 	if (pte_present(pte)) {
-		struct page *page;
-
 		flush_cache_page(vma, addr, pte_pfn(pte));
 		pte = ptep_clear_flush(vma, addr, ptep);
 		page = vm_normal_page(vma, addr, pte);
 		if (page) {
 			if (pte_dirty(pte))
 				set_page_dirty(page);
+			update_hiwater_rss(mm);
+			dec_mm_counter(mm, mm_counter(page));
 			page_remove_rmap(page);
 			page_cache_release(page);
+		}
+	} else {	/* zap_pte() is not called when pte_none() */
+		if (!pte_file(pte)) {
 			update_hiwater_rss(mm);
-			dec_mm_counter(mm, MM_FILEPAGES);
+			entry = pte_to_swp_entry(pte);
+			if (non_swap_entry(entry)) {
+				if (is_migration_entry(entry)) {
+					page = migration_entry_to_page(entry);
+					dec_mm_counter(mm, mm_counter(page));
+				}
+			} else {
+				free_swap_and_cache(entry);
+				dec_mm_counter(mm, MM_SWAPENTS);
+			}
 		}
-	} else {
-		if (!pte_file(pte))
-			free_swap_and_cache(pte_to_swp_entry(pte));
 		pte_clear_not_present_full(mm, addr, ptep, 0);
 	}
 }
-- 
1.8.4.5

[PATCH 06/97] hugetlb: ensure hugepage access is denied if hugepages are not supported

[Mel Gorman]

From: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>

commit 457c1b27ed56ec472d202731b12417bff023594a upstream.

Currently, I am seeing the following when I `mount -t hugetlbfs /none
/dev/hugetlbfs`, and then simply do a `ls /dev/hugetlbfs`.  I think it's
related to the fact that hugetlbfs is properly not correctly setting
itself up in this state?:

  Unable to handle kernel paging request for data at address 0x00000031
  Faulting instruction address: 0xc000000000245710
  Oops: Kernel access of bad area, sig: 11 [#1]
  SMP NR_CPUS=2048 NUMA pSeries
  ....

In KVM guests on Power, in a guest not backed by hugepages, we see the
following:

  AnonHugePages:         0 kB
  HugePages_Total:       0
  HugePages_Free:        0
  HugePages_Rsvd:        0
  HugePages_Surp:        0
  Hugepagesize:         64 kB

HPAGE_SHIFT == 0 in this configuration, which indicates that hugepages
are not supported at boot-time, but this is only checked in
hugetlb_init().  Extract the check to a helper function, and use it in a
few relevant places.

This does make hugetlbfs not supported (not registered at all) in this
environment.  I believe this is fine, as there are no valid hugepages
and that won't change at runtime.

[akpm@linux-foundation.org: use pr_info(), per Mel]
[akpm@linux-foundation.org: fix build when HPAGE_SHIFT is undefined]
Signed-off-by: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 fs/hugetlbfs/inode.c    |  5 +++++
 include/linux/hugetlb.h | 10 ++++++++++
 mm/hugetlb.c            | 13 +++++++++++++
 3 files changed, 28 insertions(+)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d19b30a..a4a8ed5 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1017,6 +1017,11 @@ static int __init init_hugetlbfs_fs(void)
 	int error;
 	int i;
 
+	if (!hugepages_supported()) {
+		pr_info("hugetlbfs: disabling because there are no supported hugepage sizes\n");
+		return -ENOTSUPP;
+	}
+
 	error = bdi_init(&hugetlbfs_backing_dev_info);
 	if (error)
 		return error;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 5214ff6..511b1a0 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -396,6 +396,16 @@ static inline int hugepage_migration_support(struct hstate *h)
 #endif
 }
 
+static inline bool hugepages_supported(void)
+{
+	/*
+	 * Some platform decide whether they support huge pages at boot
+	 * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
+	 * there is no such support
+	 */
+	return HPAGE_SHIFT != 0;
+}
+
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page_node(h, nid) NULL
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 92e103b..2814ca8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2114,6 +2114,9 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	unsigned long tmp;
 	int ret;
 
+	if (!hugepages_supported())
+		return -ENOTSUPP;
+
 	tmp = h->max_huge_pages;
 
 	if (write && h->order >= MAX_ORDER)
@@ -2167,6 +2170,9 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	unsigned long tmp;
 	int ret;
 
+	if (!hugepages_supported())
+		return -ENOTSUPP;
+
 	tmp = h->nr_overcommit_huge_pages;
 
 	if (write && h->order >= MAX_ORDER)
@@ -2192,6 +2198,8 @@ out:
 void hugetlb_report_meminfo(struct seq_file *m)
 {
 	struct hstate *h = &default_hstate;
+	if (!hugepages_supported())
+		return;
 	seq_printf(m,
 			"HugePages_Total:   %5lu\n"
 			"HugePages_Free:    %5lu\n"
@@ -2208,6 +2216,8 @@ void hugetlb_report_meminfo(struct seq_file *m)
 int hugetlb_report_node_meminfo(int nid, char *buf)
 {
 	struct hstate *h = &default_hstate;
+	if (!hugepages_supported())
+		return 0;
 	return sprintf(buf,
 		"Node %d HugePages_Total: %5u\n"
 		"Node %d HugePages_Free:  %5u\n"
@@ -2222,6 +2232,9 @@ void hugetlb_show_meminfo(void)
 	struct hstate *h;
 	int nid;
 
+	if (!hugepages_supported())
+		return;
+
 	for_each_node_state(nid, N_MEMORY)
 		for_each_hstate(h)
 			pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n",
-- 
1.8.4.5

[PATCH 07/97] mm: exclude memoryless nodes from zone_reclaim

[Mel Gorman]

From: Michal Hocko <mhocko@suse.cz>

commit 70ef57e6c22c3323dce179b7d0d433c479266612 upstream.

We had a report about strange OOM killer strikes on a PPC machine
although there was a lot of swap free and a tons of anonymous memory
which could be swapped out.  In the end it turned out that the OOM was a
side effect of zone reclaim which wasn't unmapping and swapping out and
so the system was pushed to the OOM.  Although this sounds like a bug
somewhere in the kswapd vs.  zone reclaim vs.  direct reclaim
interaction numactl on the said hardware suggests that the zone reclaim
should not have been set in the first place:

  node 0 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
  node 0 size: 0 MB
  node 0 free: 0 MB
  node 2 cpus:
  node 2 size: 7168 MB
  node 2 free: 6019 MB
  node distances:
  node   0   2
  0:  10  40
  2:  40  10

So all the CPUs are associated with Node0 which doesn't have any memory
while Node2 contains all the available memory.  Node distances cause an
automatic zone_reclaim_mode enabling.

Zone reclaim is intended to keep the allocations local but this doesn't
make any sense on the memoryless nodes.  So let's exclude such nodes for
init_zone_allows_reclaim which evaluates zone reclaim behavior and
suitable reclaim_nodes.

Signed-off-by: Michal Hocko <mhocko@suse.cz>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Tested-by: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index bffedeb..d37e8cd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1850,7 +1850,7 @@ static void __paginginit init_zone_allows_reclaim(int nid)
 {
 	int i;
 
-	for_each_online_node(i)
+	for_each_node_state(i, N_MEMORY)
 		if (node_distance(nid, i) <= RECLAIM_DISTANCE)
 			node_set(i, NODE_DATA(nid)->reclaim_nodes);
 		else
@@ -4903,7 +4903,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
-	init_zone_allows_reclaim(nid);
+	if (node_state(nid, N_MEMORY))
+		init_zone_allows_reclaim(nid);
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
 #endif
-- 
1.8.4.5

[PATCH 08/97] mm, thp: do not allow thp faults to avoid cpuset restrictions

[Mel Gorman]

From: David Rientjes <rientjes@google.com>

commit b104a35d32025ca740539db2808aa3385d0f30eb upstream.

The page allocator relies on __GFP_WAIT to determine if ALLOC_CPUSET
should be set in allocflags.  ALLOC_CPUSET controls if a page allocation
should be restricted only to the set of allowed cpuset mems.

Transparent hugepages clears __GFP_WAIT when defrag is disabled to prevent
the fault path from using memory compaction or direct reclaim.  Thus, it
is unfairly able to allocate outside of its cpuset mems restriction as a
side-effect.

This patch ensures that ALLOC_CPUSET is only cleared when the gfp mask is
truly GFP_ATOMIC by verifying it is also not a thp allocation.

Signed-off-by: David Rientjes <rientjes@google.com>
Reported-by: Alex Thorlton <athorlton@sgi.com>
Tested-by: Alex Thorlton <athorlton@sgi.com>
Cc: Bob Liu <lliubbo@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Hedi Berriche <hedi@sgi.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d37e8cd..8b010ca 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2425,7 +2425,7 @@ static inline int
 gfp_to_alloc_flags(gfp_t gfp_mask)
 {
 	int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
-	const gfp_t wait = gfp_mask & __GFP_WAIT;
+	const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD));
 
 	/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
 	BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
@@ -2434,20 +2434,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	 * The caller may dip into page reserves a bit more if the caller
 	 * cannot run direct reclaim, or if the caller has realtime scheduling
 	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
-	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
+	 * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
 	 */
 	alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
 
-	if (!wait) {
+	if (atomic) {
 		/*
-		 * Not worth trying to allocate harder for
-		 * __GFP_NOMEMALLOC even if it can't schedule.
+		 * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
+		 * if it can't schedule.
 		 */
-		if  (!(gfp_mask & __GFP_NOMEMALLOC))
+		if (!(gfp_mask & __GFP_NOMEMALLOC))
 			alloc_flags |= ALLOC_HARDER;
 		/*
-		 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
-		 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+		 * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
+		 * comment for __cpuset_node_allowed_softwall().
 		 */
 		alloc_flags &= ~ALLOC_CPUSET;
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
-- 
1.8.4.5

[PATCH 09/97] swap: change swap_info singly-linked list to list_head

[Mel Gorman]

From: Dan Streetman <ddstreet@ieee.org>

commit adfab836f4908deb049a5128082719e689eed964 upstream.

The logic controlling the singly-linked list of swap_info_struct entries
for all active, i.e.  swapon'ed, swap targets is rather complex, because:

 - it stores the entries in priority order
 - there is a pointer to the highest priority entry
 - there is a pointer to the highest priority not-full entry
 - there is a highest_priority_index variable set outside the swap_lock
 - swap entries of equal priority should be used equally

this complexity leads to bugs such as: https://lkml.org/lkml/2014/2/13/181
where different priority swap targets are incorrectly used equally.

That bug probably could be solved with the existing singly-linked lists,
but I think it would only add more complexity to the already difficult to
understand get_swap_page() swap_list iteration logic.

The first patch changes from a singly-linked list to a doubly-linked list
using list_heads; the highest_priority_index and related code are removed
and get_swap_page() starts each iteration at the highest priority
swap_info entry, even if it's full.  While this does introduce unnecessary
list iteration (i.e.  Schlemiel the painter's algorithm) in the case where
one or more of the highest priority entries are full, the iteration and
manipulation code is much simpler and behaves correctly re: the above bug;
and the fourth patch removes the unnecessary iteration.

The second patch adds some minor plist helper functions; nothing new
really, just functions to match existing regular list functions.  These
are used by the next two patches.

The third patch adds plist_requeue(), which is used by get_swap_page() in
the next patch - it performs the requeueing of same-priority entries
(which moves the entry to the end of its priority in the plist), so that
all equal-priority swap_info_structs get used equally.

The fourth patch converts the main list into a plist, and adds a new plist
that contains only swap_info entries that are both active and not full.
As Mel suggested using plists allows removing all the ordering code from
swap - plists handle ordering automatically.  The list naming is also
clarified now that there are two lists, with the original list changed
from swap_list_head to swap_active_head and the new list named
swap_avail_head.  A new spinlock is also added for the new list, so
swap_info entries can be added or removed from the new list immediately as
they become full or not full.

This patch (of 4):

Replace the singly-linked list tracking active, i.e.  swapon'ed,
swap_info_struct entries with a doubly-linked list using struct
list_heads.  Simplify the logic iterating and manipulating the list of
entries, especially get_swap_page(), by using standard list_head
functions, and removing the highest priority iteration logic.

The change fixes the bug:
https://lkml.org/lkml/2014/2/13/181
in which different priority swap entries after the highest priority entry
are incorrectly used equally in pairs.  The swap behavior is now as
advertised, i.e. different priority swap entries are used in order, and
equal priority swap targets are used concurrently.

Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Cc: Weijie Yang <weijieut@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/swap.h     |   7 +-
 include/linux/swapfile.h |   2 +-
 mm/frontswap.c           |  13 ++--
 mm/swapfile.c            | 171 ++++++++++++++++++++---------------------------
 4 files changed, 78 insertions(+), 115 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 46ba0c6..8eaec00 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -214,8 +214,8 @@ struct percpu_cluster {
 struct swap_info_struct {
 	unsigned long	flags;		/* SWP_USED etc: see above */
 	signed short	prio;		/* swap priority of this type */
+	struct list_head list;		/* entry in swap list */
 	signed char	type;		/* strange name for an index */
-	signed char	next;		/* next type on the swap list */
 	unsigned int	max;		/* extent of the swap_map */
 	unsigned char *swap_map;	/* vmalloc'ed array of usage counts */
 	struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
@@ -255,11 +255,6 @@ struct swap_info_struct {
 	struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */
 };
 
-struct swap_list_t {
-	int head;	/* head of priority-ordered swapfile list */
-	int next;	/* swapfile to be used next */
-};
-
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
 extern unsigned long totalreserve_pages;
diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h
index e282624..2eab382 100644
--- a/include/linux/swapfile.h
+++ b/include/linux/swapfile.h
@@ -6,7 +6,7 @@
  * want to expose them to the dozens of source files that include swap.h
  */
 extern spinlock_t swap_lock;
-extern struct swap_list_t swap_list;
+extern struct list_head swap_list_head;
 extern struct swap_info_struct *swap_info[];
 extern int try_to_unuse(unsigned int, bool, unsigned long);
 
diff --git a/mm/frontswap.c b/mm/frontswap.c
index 1b24bdc..fae1160 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -327,15 +327,12 @@ EXPORT_SYMBOL(__frontswap_invalidate_area);
 
 static unsigned long __frontswap_curr_pages(void)
 {
-	int type;
 	unsigned long totalpages = 0;
 	struct swap_info_struct *si = NULL;
 
 	assert_spin_locked(&swap_lock);
-	for (type = swap_list.head; type >= 0; type = si->next) {
-		si = swap_info[type];
+	list_for_each_entry(si, &swap_list_head, list)
 		totalpages += atomic_read(&si->frontswap_pages);
-	}
 	return totalpages;
 }
 
@@ -347,11 +344,9 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused,
 	int si_frontswap_pages;
 	unsigned long total_pages_to_unuse = total;
 	unsigned long pages = 0, pages_to_unuse = 0;
-	int type;
 
 	assert_spin_locked(&swap_lock);
-	for (type = swap_list.head; type >= 0; type = si->next) {
-		si = swap_info[type];
+	list_for_each_entry(si, &swap_list_head, list) {
 		si_frontswap_pages = atomic_read(&si->frontswap_pages);
 		if (total_pages_to_unuse < si_frontswap_pages) {
 			pages = pages_to_unuse = total_pages_to_unuse;
@@ -366,7 +361,7 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused,
 		}
 		vm_unacct_memory(pages);
 		*unused = pages_to_unuse;
-		*swapid = type;
+		*swapid = si->type;
 		ret = 0;
 		break;
 	}
@@ -413,7 +408,7 @@ void frontswap_shrink(unsigned long target_pages)
 	/*
 	 * we don't want to hold swap_lock while doing a very
 	 * lengthy try_to_unuse, but swap_list may change
-	 * so restart scan from swap_list.head each time
+	 * so restart scan from swap_list_head each time
 	 */
 	spin_lock(&swap_lock);
 	ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 0ec2eaf..d40f39e 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -51,14 +51,17 @@ atomic_long_t nr_swap_pages;
 /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */
 long total_swap_pages;
 static int least_priority;
-static atomic_t highest_priority_index = ATOMIC_INIT(-1);
 
 static const char Bad_file[] = "Bad swap file entry ";
 static const char Unused_file[] = "Unused swap file entry ";
 static const char Bad_offset[] = "Bad swap offset entry ";
 static const char Unused_offset[] = "Unused swap offset entry ";
 
-struct swap_list_t swap_list = {-1, -1};
+/*
+ * all active swap_info_structs
+ * protected with swap_lock, and ordered by priority.
+ */
+LIST_HEAD(swap_list_head);
 
 struct swap_info_struct *swap_info[MAX_SWAPFILES];
 
@@ -639,66 +642,54 @@ no_page:
 
 swp_entry_t get_swap_page(void)
 {
-	struct swap_info_struct *si;
+	struct swap_info_struct *si, *next;
 	pgoff_t offset;
-	int type, next;
-	int wrapped = 0;
-	int hp_index;
+	struct list_head *tmp;
 
 	spin_lock(&swap_lock);
 	if (atomic_long_read(&nr_swap_pages) <= 0)
 		goto noswap;
 	atomic_long_dec(&nr_swap_pages);
 
-	for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) {
-		hp_index = atomic_xchg(&highest_priority_index, -1);
-		/*
-		 * highest_priority_index records current highest priority swap
-		 * type which just frees swap entries. If its priority is
-		 * higher than that of swap_list.next swap type, we use it.  It
-		 * isn't protected by swap_lock, so it can be an invalid value
-		 * if the corresponding swap type is swapoff. We double check
-		 * the flags here. It's even possible the swap type is swapoff
-		 * and swapon again and its priority is changed. In such rare
-		 * case, low prority swap type might be used, but eventually
-		 * high priority swap will be used after several rounds of
-		 * swap.
-		 */
-		if (hp_index != -1 && hp_index != type &&
-		    swap_info[type]->prio < swap_info[hp_index]->prio &&
-		    (swap_info[hp_index]->flags & SWP_WRITEOK)) {
-			type = hp_index;
-			swap_list.next = type;
-		}
-
-		si = swap_info[type];
-		next = si->next;
-		if (next < 0 ||
-		    (!wrapped && si->prio != swap_info[next]->prio)) {
-			next = swap_list.head;
-			wrapped++;
-		}
-
+	list_for_each(tmp, &swap_list_head) {
+		si = list_entry(tmp, typeof(*si), list);
 		spin_lock(&si->lock);
-		if (!si->highest_bit) {
-			spin_unlock(&si->lock);
-			continue;
-		}
-		if (!(si->flags & SWP_WRITEOK)) {
+		if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) {
 			spin_unlock(&si->lock);
 			continue;
 		}
 
-		swap_list.next = next;
+		/*
+		 * rotate the current swap_info that we're going to use
+		 * to after any other swap_info that have the same prio,
+		 * so that all equal-priority swap_info get used equally
+		 */
+		next = si;
+		list_for_each_entry_continue(next, &swap_list_head, list) {
+			if (si->prio != next->prio)
+				break;
+			list_rotate_left(&si->list);
+			next = si;
+		}
 
 		spin_unlock(&swap_lock);
 		/* This is called for allocating swap entry for cache */
 		offset = scan_swap_map(si, SWAP_HAS_CACHE);
 		spin_unlock(&si->lock);
 		if (offset)
-			return swp_entry(type, offset);
+			return swp_entry(si->type, offset);
 		spin_lock(&swap_lock);
-		next = swap_list.next;
+		/*
+		 * if we got here, it's likely that si was almost full before,
+		 * and since scan_swap_map() can drop the si->lock, multiple
+		 * callers probably all tried to get a page from the same si
+		 * and it filled up before we could get one.  So we need to
+		 * try again.  Since we dropped the swap_lock, there may now
+		 * be non-full higher priority swap_infos, and this si may have
+		 * even been removed from the list (although very unlikely).
+		 * Let's start over.
+		 */
+		tmp = &swap_list_head;
 	}
 
 	atomic_long_inc(&nr_swap_pages);
@@ -765,27 +756,6 @@ out:
 	return NULL;
 }
 
-/*
- * This swap type frees swap entry, check if it is the highest priority swap
- * type which just frees swap entry. get_swap_page() uses
- * highest_priority_index to search highest priority swap type. The
- * swap_info_struct.lock can't protect us if there are multiple swap types
- * active, so we use atomic_cmpxchg.
- */
-static void set_highest_priority_index(int type)
-{
-	int old_hp_index, new_hp_index;
-
-	do {
-		old_hp_index = atomic_read(&highest_priority_index);
-		if (old_hp_index != -1 &&
-			swap_info[old_hp_index]->prio >= swap_info[type]->prio)
-			break;
-		new_hp_index = type;
-	} while (atomic_cmpxchg(&highest_priority_index,
-		old_hp_index, new_hp_index) != old_hp_index);
-}
-
 static unsigned char swap_entry_free(struct swap_info_struct *p,
 				     swp_entry_t entry, unsigned char usage)
 {
@@ -829,7 +799,6 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
 			p->lowest_bit = offset;
 		if (offset > p->highest_bit)
 			p->highest_bit = offset;
-		set_highest_priority_index(p->type);
 		atomic_long_inc(&nr_swap_pages);
 		p->inuse_pages--;
 		frontswap_invalidate_page(p->type, offset);
@@ -1764,7 +1733,7 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 				unsigned char *swap_map,
 				struct swap_cluster_info *cluster_info)
 {
-	int i, prev;
+	struct swap_info_struct *si;
 
 	if (prio >= 0)
 		p->prio = prio;
@@ -1776,18 +1745,28 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 	atomic_long_add(p->pages, &nr_swap_pages);
 	total_swap_pages += p->pages;
 
-	/* insert swap space into swap_list: */
-	prev = -1;
-	for (i = swap_list.head; i >= 0; i = swap_info[i]->next) {
-		if (p->prio >= swap_info[i]->prio)
-			break;
-		prev = i;
+	assert_spin_locked(&swap_lock);
+	BUG_ON(!list_empty(&p->list));
+	/*
+	 * insert into swap list; the list is in priority order,
+	 * so that get_swap_page() can get a page from the highest
+	 * priority swap_info_struct with available page(s), and
+	 * swapoff can adjust the auto-assigned (i.e. negative) prio
+	 * values for any lower-priority swap_info_structs when
+	 * removing a negative-prio swap_info_struct
+	 */
+	list_for_each_entry(si, &swap_list_head, list) {
+		if (p->prio >= si->prio) {
+			list_add_tail(&p->list, &si->list);
+			return;
+		}
 	}
-	p->next = i;
-	if (prev < 0)
-		swap_list.head = swap_list.next = p->type;
-	else
-		swap_info[prev]->next = p->type;
+	/*
+	 * this covers two cases:
+	 * 1) p->prio is less than all existing prio
+	 * 2) the swap list is empty
+	 */
+	list_add_tail(&p->list, &swap_list_head);
 }
 
 static void enable_swap_info(struct swap_info_struct *p, int prio,
@@ -1822,8 +1801,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	struct address_space *mapping;
 	struct inode *inode;
 	struct filename *pathname;
-	int i, type, prev;
-	int err;
+	int err, found = 0;
 	unsigned int old_block_size;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -1841,17 +1819,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 		goto out;
 
 	mapping = victim->f_mapping;
-	prev = -1;
 	spin_lock(&swap_lock);
-	for (type = swap_list.head; type >= 0; type = swap_info[type]->next) {
-		p = swap_info[type];
+	list_for_each_entry(p, &swap_list_head, list) {
 		if (p->flags & SWP_WRITEOK) {
-			if (p->swap_file->f_mapping == mapping)
+			if (p->swap_file->f_mapping == mapping) {
+				found = 1;
 				break;
+			}
 		}
-		prev = type;
 	}
-	if (type < 0) {
+	if (!found) {
 		err = -EINVAL;
 		spin_unlock(&swap_lock);
 		goto out_dput;
@@ -1863,20 +1840,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 		spin_unlock(&swap_lock);
 		goto out_dput;
 	}
-	if (prev < 0)
-		swap_list.head = p->next;
-	else
-		swap_info[prev]->next = p->next;
-	if (type == swap_list.next) {
-		/* just pick something that's safe... */
-		swap_list.next = swap_list.head;
-	}
 	spin_lock(&p->lock);
 	if (p->prio < 0) {
-		for (i = p->next; i >= 0; i = swap_info[i]->next)
-			swap_info[i]->prio = p->prio--;
+		struct swap_info_struct *si = p;
+
+		list_for_each_entry_continue(si, &swap_list_head, list) {
+			si->prio++;
+		}
 		least_priority++;
 	}
+	list_del_init(&p->list);
 	atomic_long_sub(p->pages, &nr_swap_pages);
 	total_swap_pages -= p->pages;
 	p->flags &= ~SWP_WRITEOK;
@@ -1884,7 +1857,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	spin_unlock(&swap_lock);
 
 	set_current_oom_origin();
-	err = try_to_unuse(type, false, 0); /* force all pages to be unused */
+	err = try_to_unuse(p->type, false, 0); /* force unuse all pages */
 	clear_current_oom_origin();
 
 	if (err) {
@@ -1926,7 +1899,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	frontswap_map_set(p, NULL);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
-	frontswap_invalidate_area(type);
+	frontswap_invalidate_area(p->type);
 	mutex_unlock(&swapon_mutex);
 	free_percpu(p->percpu_cluster);
 	p->percpu_cluster = NULL;
@@ -1934,7 +1907,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	vfree(cluster_info);
 	vfree(frontswap_map);
 	/* Destroy swap account informatin */
-	swap_cgroup_swapoff(type);
+	swap_cgroup_swapoff(p->type);
 
 	inode = mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
@@ -2141,8 +2114,8 @@ static struct swap_info_struct *alloc_swap_info(void)
 		 */
 	}
 	INIT_LIST_HEAD(&p->first_swap_extent.list);
+	INIT_LIST_HEAD(&p->list);
 	p->flags = SWP_USED;
-	p->next = -1;
 	spin_unlock(&swap_lock);
 	spin_lock_init(&p->lock);
 
-- 
1.8.4.5

[PATCH 10/97] lib/plist: add helper functions

[Mel Gorman]

From: Dan Streetman <ddstreet@ieee.org>

commit fd16618e12a05df79a3439d72d5ffdac5d34f3da upstream.

Add PLIST_HEAD() to plist.h, equivalent to LIST_HEAD() from list.h, to
define and initialize a struct plist_head.

Add plist_for_each_continue() and plist_for_each_entry_continue(),
equivalent to list_for_each_continue() and list_for_each_entry_continue(),
to iterate over a plist continuing after the current position.

Add plist_prev() and plist_next(), equivalent to (struct list_head*)->prev
and ->next, implemented by list_prev_entry() and list_next_entry(), to
access the prev/next struct plist_node entry.  These are needed because
unlike struct list_head, direct access of the prev/next struct plist_node
isn't possible; the list must be navigated via the contained struct
list_head.  e.g.  instead of accessing the prev by list_prev_entry(node,
node_list) it can be accessed by plist_prev(node).

Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Cc: Weijie Yang <weijieut@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/plist.h | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/include/linux/plist.h b/include/linux/plist.h
index aa0fb39..c815491 100644
--- a/include/linux/plist.h
+++ b/include/linux/plist.h
@@ -98,6 +98,13 @@ struct plist_node {
 }
 
 /**
+ * PLIST_HEAD - declare and init plist_head
+ * @head:	name for struct plist_head variable
+ */
+#define PLIST_HEAD(head) \
+	struct plist_head head = PLIST_HEAD_INIT(head)
+
+/**
  * PLIST_NODE_INIT - static struct plist_node initializer
  * @node:	struct plist_node variable name
  * @__prio:	initial node priority
@@ -143,6 +150,16 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
 	 list_for_each_entry(pos, &(head)->node_list, node_list)
 
 /**
+ * plist_for_each_continue - continue iteration over the plist
+ * @pos:	the type * to use as a loop cursor
+ * @head:	the head for your list
+ *
+ * Continue to iterate over plist, continuing after the current position.
+ */
+#define plist_for_each_continue(pos, head)	\
+	 list_for_each_entry_continue(pos, &(head)->node_list, node_list)
+
+/**
  * plist_for_each_safe - iterate safely over a plist of given type
  * @pos:	the type * to use as a loop counter
  * @n:	another type * to use as temporary storage
@@ -163,6 +180,18 @@ extern void plist_del(struct plist_node *node, struct plist_head *head);
 	 list_for_each_entry(pos, &(head)->node_list, mem.node_list)
 
 /**
+ * plist_for_each_entry_continue - continue iteration over list of given type
+ * @pos:	the type * to use as a loop cursor
+ * @head:	the head for your list
+ * @m:		the name of the list_struct within the struct
+ *
+ * Continue to iterate over list of given type, continuing after
+ * the current position.
+ */
+#define plist_for_each_entry_continue(pos, head, m)	\
+	list_for_each_entry_continue(pos, &(head)->node_list, m.node_list)
+
+/**
  * plist_for_each_entry_safe - iterate safely over list of given type
  * @pos:	the type * to use as a loop counter
  * @n:		another type * to use as temporary storage
@@ -229,6 +258,20 @@ static inline int plist_node_empty(const struct plist_node *node)
 #endif
 
 /**
+ * plist_next - get the next entry in list
+ * @pos:	the type * to cursor
+ */
+#define plist_next(pos) \
+	list_next_entry(pos, node_list)
+
+/**
+ * plist_prev - get the prev entry in list
+ * @pos:	the type * to cursor
+ */
+#define plist_prev(pos) \
+	list_prev_entry(pos, node_list)
+
+/**
  * plist_first - return the first node (and thus, highest priority)
  * @head:	the &struct plist_head pointer
  *
-- 
1.8.4.5

[PATCH 11/97] lib/plist: add plist_requeue

[Mel Gorman]

From: Dan Streetman <ddstreet@ieee.org>

commit a75f232ce0fe38bd01301899ecd97ffd0254316a upstream.

Add plist_requeue(), which moves the specified plist_node after all other
same-priority plist_nodes in the list.  This is essentially an optimized
plist_del() followed by plist_add().

This is needed by swap, which (with the next patch in this set) uses a
plist of available swap devices.  When a swap device (either a swap
partition or swap file) are added to the system with swapon(), the device
is added to a plist, ordered by the swap device's priority.  When swap
needs to allocate a page from one of the swap devices, it takes the page
from the first swap device on the plist, which is the highest priority
swap device.  The swap device is left in the plist until all its pages are
used, and then removed from the plist when it becomes full.

However, as described in man 2 swapon, swap must allocate pages from swap
devices with the same priority in round-robin order; to do this, on each
swap page allocation, swap uses a page from the first swap device in the
plist, and then calls plist_requeue() to move that swap device entry to
after any other same-priority swap devices.  The next swap page allocation
will again use a page from the first swap device in the plist and requeue
it, and so on, resulting in round-robin usage of equal-priority swap
devices.

Also add plist_test_requeue() test function, for use by plist_test() to
test plist_requeue() function.

Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Cc: Weijie Yang <weijieut@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/plist.h |  2 ++
 lib/plist.c           | 52 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 54 insertions(+)

diff --git a/include/linux/plist.h b/include/linux/plist.h
index c815491..8b6c970 100644
--- a/include/linux/plist.h
+++ b/include/linux/plist.h
@@ -141,6 +141,8 @@ static inline void plist_node_init(struct plist_node *node, int prio)
 extern void plist_add(struct plist_node *node, struct plist_head *head);
 extern void plist_del(struct plist_node *node, struct plist_head *head);
 
+extern void plist_requeue(struct plist_node *node, struct plist_head *head);
+
 /**
  * plist_for_each - iterate over the plist
  * @pos:	the type * to use as a loop counter
diff --git a/lib/plist.c b/lib/plist.c
index 1ebc95f..0f2084d 100644
--- a/lib/plist.c
+++ b/lib/plist.c
@@ -134,6 +134,46 @@ void plist_del(struct plist_node *node, struct plist_head *head)
 	plist_check_head(head);
 }
 
+/**
+ * plist_requeue - Requeue @node at end of same-prio entries.
+ *
+ * This is essentially an optimized plist_del() followed by
+ * plist_add().  It moves an entry already in the plist to
+ * after any other same-priority entries.
+ *
+ * @node:	&struct plist_node pointer - entry to be moved
+ * @head:	&struct plist_head pointer - list head
+ */
+void plist_requeue(struct plist_node *node, struct plist_head *head)
+{
+	struct plist_node *iter;
+	struct list_head *node_next = &head->node_list;
+
+	plist_check_head(head);
+	BUG_ON(plist_head_empty(head));
+	BUG_ON(plist_node_empty(node));
+
+	if (node == plist_last(head))
+		return;
+
+	iter = plist_next(node);
+
+	if (node->prio != iter->prio)
+		return;
+
+	plist_del(node, head);
+
+	plist_for_each_continue(iter, head) {
+		if (node->prio != iter->prio) {
+			node_next = &iter->node_list;
+			break;
+		}
+	}
+	list_add_tail(&node->node_list, node_next);
+
+	plist_check_head(head);
+}
+
 #ifdef CONFIG_DEBUG_PI_LIST
 #include <linux/sched.h>
 #include <linux/module.h>
@@ -170,6 +210,14 @@ static void __init plist_test_check(int nr_expect)
 	BUG_ON(prio_pos->prio_list.next != &first->prio_list);
 }
 
+static void __init plist_test_requeue(struct plist_node *node)
+{
+	plist_requeue(node, &test_head);
+
+	if (node != plist_last(&test_head))
+		BUG_ON(node->prio == plist_next(node)->prio);
+}
+
 static int  __init plist_test(void)
 {
 	int nr_expect = 0, i, loop;
@@ -193,6 +241,10 @@ static int  __init plist_test(void)
 			nr_expect--;
 		}
 		plist_test_check(nr_expect);
+		if (!plist_node_empty(test_node + i)) {
+			plist_test_requeue(test_node + i);
+			plist_test_check(nr_expect);
+		}
 	}
 
 	for (i = 0; i < ARRAY_SIZE(test_node); i++) {
-- 
1.8.4.5

[PATCH 12/97] swap: change swap_list_head to plist, add swap_avail_head

[Mel Gorman]

From: Dan Streetman <ddstreet@ieee.org>

commit 18ab4d4ced0817421e6db6940374cc39d28d65da upstream.

Originally get_swap_page() started iterating through the singly-linked
list of swap_info_structs using swap_list.next or highest_priority_index,
which both were intended to point to the highest priority active swap
target that was not full.  The first patch in this series changed the
singly-linked list to a doubly-linked list, and removed the logic to start
at the highest priority non-full entry; it starts scanning at the highest
priority entry each time, even if the entry is full.

Replace the manually ordered swap_list_head with a plist, swap_active_head.
Add a new plist, swap_avail_head.  The original swap_active_head plist
contains all active swap_info_structs, as before, while the new
swap_avail_head plist contains only swap_info_structs that are active and
available, i.e. not full.  Add a new spinlock, swap_avail_lock, to protect
the swap_avail_head list.

Mel Gorman suggested using plists since they internally handle ordering
the list entries based on priority, which is exactly what swap was doing
manually.  All the ordering code is now removed, and swap_info_struct
entries and simply added to their corresponding plist and automatically
ordered correctly.

Using a new plist for available swap_info_structs simplifies and
optimizes get_swap_page(), which no longer has to iterate over full
swap_info_structs.  Using a new spinlock for swap_avail_head plist
allows each swap_info_struct to add or remove themselves from the
plist when they become full or not-full; previously they could not
do so because the swap_info_struct->lock is held when they change
from full<->not-full, and the swap_lock protecting the main
swap_active_head must be ordered before any swap_info_struct->lock.

Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Shaohua Li <shli@fusionio.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Cc: Weijie Yang <weijieut@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/swap.h     |   3 +-
 include/linux/swapfile.h |   2 +-
 mm/frontswap.c           |   6 +-
 mm/swapfile.c            | 145 +++++++++++++++++++++++++++++------------------
 4 files changed, 97 insertions(+), 59 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 8eaec00..7893249 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -214,7 +214,8 @@ struct percpu_cluster {
 struct swap_info_struct {
 	unsigned long	flags;		/* SWP_USED etc: see above */
 	signed short	prio;		/* swap priority of this type */
-	struct list_head list;		/* entry in swap list */
+	struct plist_node list;		/* entry in swap_active_head */
+	struct plist_node avail_list;	/* entry in swap_avail_head */
 	signed char	type;		/* strange name for an index */
 	unsigned int	max;		/* extent of the swap_map */
 	unsigned char *swap_map;	/* vmalloc'ed array of usage counts */
diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h
index 2eab382..388293a 100644
--- a/include/linux/swapfile.h
+++ b/include/linux/swapfile.h
@@ -6,7 +6,7 @@
  * want to expose them to the dozens of source files that include swap.h
  */
 extern spinlock_t swap_lock;
-extern struct list_head swap_list_head;
+extern struct plist_head swap_active_head;
 extern struct swap_info_struct *swap_info[];
 extern int try_to_unuse(unsigned int, bool, unsigned long);
 
diff --git a/mm/frontswap.c b/mm/frontswap.c
index fae1160..c30eec5 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -331,7 +331,7 @@ static unsigned long __frontswap_curr_pages(void)
 	struct swap_info_struct *si = NULL;
 
 	assert_spin_locked(&swap_lock);
-	list_for_each_entry(si, &swap_list_head, list)
+	plist_for_each_entry(si, &swap_active_head, list)
 		totalpages += atomic_read(&si->frontswap_pages);
 	return totalpages;
 }
@@ -346,7 +346,7 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused,
 	unsigned long pages = 0, pages_to_unuse = 0;
 
 	assert_spin_locked(&swap_lock);
-	list_for_each_entry(si, &swap_list_head, list) {
+	plist_for_each_entry(si, &swap_active_head, list) {
 		si_frontswap_pages = atomic_read(&si->frontswap_pages);
 		if (total_pages_to_unuse < si_frontswap_pages) {
 			pages = pages_to_unuse = total_pages_to_unuse;
@@ -408,7 +408,7 @@ void frontswap_shrink(unsigned long target_pages)
 	/*
 	 * we don't want to hold swap_lock while doing a very
 	 * lengthy try_to_unuse, but swap_list may change
-	 * so restart scan from swap_list_head each time
+	 * so restart scan from swap_active_head each time
 	 */
 	spin_lock(&swap_lock);
 	ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index d40f39e..660b9c0 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -61,7 +61,22 @@ static const char Unused_offset[] = "Unused swap offset entry ";
  * all active swap_info_structs
  * protected with swap_lock, and ordered by priority.
  */
-LIST_HEAD(swap_list_head);
+PLIST_HEAD(swap_active_head);
+
+/*
+ * all available (active, not full) swap_info_structs
+ * protected with swap_avail_lock, ordered by priority.
+ * This is used by get_swap_page() instead of swap_active_head
+ * because swap_active_head includes all swap_info_structs,
+ * but get_swap_page() doesn't need to look at full ones.
+ * This uses its own lock instead of swap_lock because when a
+ * swap_info_struct changes between not-full/full, it needs to
+ * add/remove itself to/from this list, but the swap_info_struct->lock
+ * is held and the locking order requires swap_lock to be taken
+ * before any swap_info_struct->lock.
+ */
+static PLIST_HEAD(swap_avail_head);
+static DEFINE_SPINLOCK(swap_avail_lock);
 
 struct swap_info_struct *swap_info[MAX_SWAPFILES];
 
@@ -594,6 +609,9 @@ checks:
 	if (si->inuse_pages == si->pages) {
 		si->lowest_bit = si->max;
 		si->highest_bit = 0;
+		spin_lock(&swap_avail_lock);
+		plist_del(&si->avail_list, &swap_avail_head);
+		spin_unlock(&swap_avail_lock);
 	}
 	si->swap_map[offset] = usage;
 	inc_cluster_info_page(si, si->cluster_info, offset);
@@ -644,57 +662,63 @@ swp_entry_t get_swap_page(void)
 {
 	struct swap_info_struct *si, *next;
 	pgoff_t offset;
-	struct list_head *tmp;
 
-	spin_lock(&swap_lock);
 	if (atomic_long_read(&nr_swap_pages) <= 0)
 		goto noswap;
 	atomic_long_dec(&nr_swap_pages);
 
-	list_for_each(tmp, &swap_list_head) {
-		si = list_entry(tmp, typeof(*si), list);
+	spin_lock(&swap_avail_lock);
+
+start_over:
+	plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) {
+		/* requeue si to after same-priority siblings */
+		plist_requeue(&si->avail_list, &swap_avail_head);
+		spin_unlock(&swap_avail_lock);
 		spin_lock(&si->lock);
 		if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) {
+			spin_lock(&swap_avail_lock);
+			if (plist_node_empty(&si->avail_list)) {
+				spin_unlock(&si->lock);
+				goto nextsi;
+			}
+			WARN(!si->highest_bit,
+			     "swap_info %d in list but !highest_bit\n",
+			     si->type);
+			WARN(!(si->flags & SWP_WRITEOK),
+			     "swap_info %d in list but !SWP_WRITEOK\n",
+			     si->type);
+			plist_del(&si->avail_list, &swap_avail_head);
 			spin_unlock(&si->lock);
-			continue;
+			goto nextsi;
 		}
 
-		/*
-		 * rotate the current swap_info that we're going to use
-		 * to after any other swap_info that have the same prio,
-		 * so that all equal-priority swap_info get used equally
-		 */
-		next = si;
-		list_for_each_entry_continue(next, &swap_list_head, list) {
-			if (si->prio != next->prio)
-				break;
-			list_rotate_left(&si->list);
-			next = si;
-		}
-
-		spin_unlock(&swap_lock);
 		/* This is called for allocating swap entry for cache */
 		offset = scan_swap_map(si, SWAP_HAS_CACHE);
 		spin_unlock(&si->lock);
 		if (offset)
 			return swp_entry(si->type, offset);
-		spin_lock(&swap_lock);
+		pr_debug("scan_swap_map of si %d failed to find offset\n",
+		       si->type);
+		spin_lock(&swap_avail_lock);
+nextsi:
 		/*
 		 * if we got here, it's likely that si was almost full before,
 		 * and since scan_swap_map() can drop the si->lock, multiple
 		 * callers probably all tried to get a page from the same si
-		 * and it filled up before we could get one.  So we need to
-		 * try again.  Since we dropped the swap_lock, there may now
-		 * be non-full higher priority swap_infos, and this si may have
-		 * even been removed from the list (although very unlikely).
-		 * Let's start over.
+		 * and it filled up before we could get one; or, the si filled
+		 * up between us dropping swap_avail_lock and taking si->lock.
+		 * Since we dropped the swap_avail_lock, the swap_avail_head
+		 * list may have been modified; so if next is still in the
+		 * swap_avail_head list then try it, otherwise start over.
 		 */
-		tmp = &swap_list_head;
+		if (plist_node_empty(&next->avail_list))
+			goto start_over;
 	}
 
+	spin_unlock(&swap_avail_lock);
+
 	atomic_long_inc(&nr_swap_pages);
 noswap:
-	spin_unlock(&swap_lock);
 	return (swp_entry_t) {0};
 }
 
@@ -797,8 +821,18 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
 		dec_cluster_info_page(p, p->cluster_info, offset);
 		if (offset < p->lowest_bit)
 			p->lowest_bit = offset;
-		if (offset > p->highest_bit)
+		if (offset > p->highest_bit) {
+			bool was_full = !p->highest_bit;
 			p->highest_bit = offset;
+			if (was_full && (p->flags & SWP_WRITEOK)) {
+				spin_lock(&swap_avail_lock);
+				WARN_ON(!plist_node_empty(&p->avail_list));
+				if (plist_node_empty(&p->avail_list))
+					plist_add(&p->avail_list,
+						  &swap_avail_head);
+				spin_unlock(&swap_avail_lock);
+			}
+		}
 		atomic_long_inc(&nr_swap_pages);
 		p->inuse_pages--;
 		frontswap_invalidate_page(p->type, offset);
@@ -1733,12 +1767,16 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 				unsigned char *swap_map,
 				struct swap_cluster_info *cluster_info)
 {
-	struct swap_info_struct *si;
-
 	if (prio >= 0)
 		p->prio = prio;
 	else
 		p->prio = --least_priority;
+	/*
+	 * the plist prio is negated because plist ordering is
+	 * low-to-high, while swap ordering is high-to-low
+	 */
+	p->list.prio = -p->prio;
+	p->avail_list.prio = -p->prio;
 	p->swap_map = swap_map;
 	p->cluster_info = cluster_info;
 	p->flags |= SWP_WRITEOK;
@@ -1746,27 +1784,20 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 	total_swap_pages += p->pages;
 
 	assert_spin_locked(&swap_lock);
-	BUG_ON(!list_empty(&p->list));
-	/*
-	 * insert into swap list; the list is in priority order,
-	 * so that get_swap_page() can get a page from the highest
-	 * priority swap_info_struct with available page(s), and
-	 * swapoff can adjust the auto-assigned (i.e. negative) prio
-	 * values for any lower-priority swap_info_structs when
-	 * removing a negative-prio swap_info_struct
-	 */
-	list_for_each_entry(si, &swap_list_head, list) {
-		if (p->prio >= si->prio) {
-			list_add_tail(&p->list, &si->list);
-			return;
-		}
-	}
 	/*
-	 * this covers two cases:
-	 * 1) p->prio is less than all existing prio
-	 * 2) the swap list is empty
+	 * both lists are plists, and thus priority ordered.
+	 * swap_active_head needs to be priority ordered for swapoff(),
+	 * which on removal of any swap_info_struct with an auto-assigned
+	 * (i.e. negative) priority increments the auto-assigned priority
+	 * of any lower-priority swap_info_structs.
+	 * swap_avail_head needs to be priority ordered for get_swap_page(),
+	 * which allocates swap pages from the highest available priority
+	 * swap_info_struct.
 	 */
-	list_add_tail(&p->list, &swap_list_head);
+	plist_add(&p->list, &swap_active_head);
+	spin_lock(&swap_avail_lock);
+	plist_add(&p->avail_list, &swap_avail_head);
+	spin_unlock(&swap_avail_lock);
 }
 
 static void enable_swap_info(struct swap_info_struct *p, int prio,
@@ -1820,7 +1851,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 
 	mapping = victim->f_mapping;
 	spin_lock(&swap_lock);
-	list_for_each_entry(p, &swap_list_head, list) {
+	plist_for_each_entry(p, &swap_active_head, list) {
 		if (p->flags & SWP_WRITEOK) {
 			if (p->swap_file->f_mapping == mapping) {
 				found = 1;
@@ -1840,16 +1871,21 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 		spin_unlock(&swap_lock);
 		goto out_dput;
 	}
+	spin_lock(&swap_avail_lock);
+	plist_del(&p->avail_list, &swap_avail_head);
+	spin_unlock(&swap_avail_lock);
 	spin_lock(&p->lock);
 	if (p->prio < 0) {
 		struct swap_info_struct *si = p;
 
-		list_for_each_entry_continue(si, &swap_list_head, list) {
+		plist_for_each_entry_continue(si, &swap_active_head, list) {
 			si->prio++;
+			si->list.prio--;
+			si->avail_list.prio--;
 		}
 		least_priority++;
 	}
-	list_del_init(&p->list);
+	plist_del(&p->list, &swap_active_head);
 	atomic_long_sub(p->pages, &nr_swap_pages);
 	total_swap_pages -= p->pages;
 	p->flags &= ~SWP_WRITEOK;
@@ -2114,7 +2150,8 @@ static struct swap_info_struct *alloc_swap_info(void)
 		 */
 	}
 	INIT_LIST_HEAD(&p->first_swap_extent.list);
-	INIT_LIST_HEAD(&p->list);
+	plist_node_init(&p->list, 0);
+	plist_node_init(&p->avail_list, 0);
 	p->flags = SWP_USED;
 	spin_unlock(&swap_lock);
 	spin_lock_init(&p->lock);
-- 
1.8.4.5

[PATCH 13/97] readahead: fix sequential read cache miss detection

[Mel Gorman]

From: Damien Ramonda <damien.ramonda@intel.com>

commit af248a0c67457e5c6d2bcf288f07b4b2ed064f1f upstream.

The kernel's readahead algorithm sometimes interprets random read
accesses as sequential and triggers unnecessary data prefecthing from
storage device (impacting random read average latency).

In order to identify sequential cache read misses, the readahead
algorithm intends to check whether offset - previous offset == 1
(trivial sequential reads) or offset - previous offset == 0 (sequential
reads not aligned on page boundary):

  if (offset - (ra->prev_pos >> PAGE_CACHE_SHIFT) <= 1UL)

The current offset is stored in the "offset" variable of type "pgoff_t"
(unsigned long), while previous offset is stored in "ra->prev_pos" of
type "loff_t" (long long).  Therefore, operands of the if statement are
implicitly converted to type long long.  Consequently, when previous
offset > current offset (which happens on random pattern), the if
condition is true and access is wrongly interpeted as sequential.  An
unnecessary data prefetching is triggered, impacting the average random
read latency.

Storing the previous offset value in a "pgoff_t" variable (unsigned
long) fixes the sequential read detection logic.

Signed-off-by: Damien Ramonda <damien.ramonda@intel.com>
Reviewed-by: Fengguang Wu <fengguang.wu@intel.com>
Acked-by: Pierre Tardy <pierre.tardy@intel.com>
Acked-by: David Cohen <david.a.cohen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/readahead.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/mm/readahead.c b/mm/readahead.c
index e4ed041..5b637b5 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -401,6 +401,7 @@ ondemand_readahead(struct address_space *mapping,
 		   unsigned long req_size)
 {
 	unsigned long max = max_sane_readahead(ra->ra_pages);
+	pgoff_t prev_offset;
 
 	/*
 	 * start of file
@@ -452,8 +453,11 @@ ondemand_readahead(struct address_space *mapping,
 
 	/*
 	 * sequential cache miss
+	 * trivial case: (offset - prev_offset) == 1
+	 * unaligned reads: (offset - prev_offset) == 0
 	 */
-	if (offset - (ra->prev_pos >> PAGE_CACHE_SHIFT) <= 1UL)
+	prev_offset = (unsigned long long)ra->prev_pos >> PAGE_CACHE_SHIFT;
+	if (offset - prev_offset <= 1UL)
 		goto initial_readahead;
 
 	/*
-- 
1.8.4.5

[PATCH 14/97] mm: get rid of unnecessary overhead of trace_mm_page_alloc_extfrag()

[Mel Gorman]

From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>

commit 52c8f6a5aeb0bdd396849ecaa72d96f8175528f5 upstream.

In general, every tracepoint should be zero overhead if it is disabled.
However, trace_mm_page_alloc_extfrag() is one of exception.  It evaluate
"new_type == start_migratetype" even if tracepoint is disabled.

However, the code can be moved into tracepoint's TP_fast_assign() and
TP_fast_assign exist exactly such purpose.  This patch does it.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/trace/events/kmem.h | 10 ++++------
 mm/page_alloc.c             |  5 ++---
 2 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index d0c6134..aece134 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -267,14 +267,12 @@ DEFINE_EVENT_PRINT(mm_page, mm_page_pcpu_drain,
 TRACE_EVENT(mm_page_alloc_extfrag,
 
 	TP_PROTO(struct page *page,
-			int alloc_order, int fallback_order,
-			int alloc_migratetype, int fallback_migratetype,
-			int change_ownership),
+		int alloc_order, int fallback_order,
+		int alloc_migratetype, int fallback_migratetype, int new_migratetype),
 
 	TP_ARGS(page,
 		alloc_order, fallback_order,
-		alloc_migratetype, fallback_migratetype,
-		change_ownership),
+		alloc_migratetype, fallback_migratetype, new_migratetype),
 
 	TP_STRUCT__entry(
 		__field(	struct page *,	page			)
@@ -291,7 +289,7 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 		__entry->fallback_order		= fallback_order;
 		__entry->alloc_migratetype	= alloc_migratetype;
 		__entry->fallback_migratetype	= fallback_migratetype;
-		__entry->change_ownership	= change_ownership;
+		__entry->change_ownership	= (new_migratetype == alloc_migratetype);
 	),
 
 	TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d",
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8b010ca..e285eac 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1118,9 +1118,8 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 			       is_migrate_cma(migratetype)
 			     ? migratetype : start_migratetype);
 
-			trace_mm_page_alloc_extfrag(page, order,
-				current_order, start_migratetype, migratetype,
-				new_type == start_migratetype);
+			trace_mm_page_alloc_extfrag(page, order, current_order,
+				start_migratetype, migratetype, new_type);
 
 			return page;
 		}
-- 
1.8.4.5

[PATCH 15/97] mm: __rmqueue_fallback() should respect pageblock type

[Mel Gorman]

From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>

commit 0cbef29a782162a3896487901eca4550bfa397ef upstream.

When __rmqueue_fallback() doesn't find a free block with the required size
it splits a larger page and puts the rest of the page onto the free list.

But it has one serious mistake.  When putting back, __rmqueue_fallback()
always use start_migratetype if type is not CMA.  However,
__rmqueue_fallback() is only called when all of the start_migratetype
queue is empty.  That said, __rmqueue_fallback always puts back memory to
the wrong queue except try_to_steal_freepages() changed pageblock type
(i.e.  requested size is smaller than half of page block).  The end result
is that the antifragmentation framework increases fragmenation instead of
decreasing it.

Mel's original anti fragmentation does the right thing.  But commit
47118af076f6 ("mm: mmzone: MIGRATE_CMA migration type added") broke it.

This patch restores sane and old behavior.  It also removes an incorrect
comment which was introduced by commit fef903efcf0c ("mm/page_alloc.c:
restructure free-page stealing code and fix a bug").

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e285eac..baef87e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1042,6 +1042,10 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page,
 {
 	int current_order = page_order(page);
 
+	/*
+	 * When borrowing from MIGRATE_CMA, we need to release the excess
+	 * buddy pages to CMA itself.
+	 */
 	if (is_migrate_cma(fallback_type))
 		return fallback_type;
 
@@ -1106,17 +1110,8 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 			list_del(&page->lru);
 			rmv_page_order(page);
 
-			/*
-			 * Borrow the excess buddy pages as well, irrespective
-			 * of whether we stole freepages, or took ownership of
-			 * the pageblock or not.
-			 *
-			 * Exception: When borrowing from MIGRATE_CMA, release
-			 * the excess buddy pages to CMA itself.
-			 */
 			expand(zone, page, order, current_order, area,
-			       is_migrate_cma(migratetype)
-			     ? migratetype : start_migratetype);
+			       new_type);
 
 			trace_mm_page_alloc_extfrag(page, order, current_order,
 				start_migratetype, migratetype, new_type);
-- 
1.8.4.5

[PATCH 16/97] mm, x86: Account for TLB flushes only when debugging

[Mel Gorman]

commit ec65993443736a5091b68e80ff1734548944a4b8 upstream.

Bisection between 3.11 and 3.12 fingered commit 9824cf97 ("mm:
vmstats: tlb flush counters") to cause overhead problems.

The counters are undeniably useful but how often do we really
need to debug TLB flush related issues?  It does not justify
taking the penalty everywhere so make it a debugging option.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Tested-by: Davidlohr Bueso <davidlohr@hp.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Alex Shi <alex.shi@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-XzxjntugxuwpxXhcrxqqh53b@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 arch/x86/include/asm/tlbflush.h    |  6 +++---
 arch/x86/kernel/cpu/mtrr/generic.c |  4 ++--
 arch/x86/mm/tlb.c                  | 14 +++++++-------
 include/linux/vm_event_item.h      |  4 +++-
 include/linux/vmstat.h             |  8 ++++++++
 mm/vmstat.c                        |  4 +++-
 6 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index e6d90ba..04905bf 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -62,7 +62,7 @@ static inline void __flush_tlb_all(void)
 
 static inline void __flush_tlb_one(unsigned long addr)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 	__flush_tlb_single(addr);
 }
 
@@ -93,13 +93,13 @@ static inline void __flush_tlb_one(unsigned long addr)
  */
 static inline void __flush_tlb_up(void)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 }
 
 static inline void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb_all();
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index ce2d0a2..0e25a1b 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -683,7 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	}
 
 	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Save MTRR state */
@@ -697,7 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 static void post_set(void) __releases(set_atomicity_lock)
 {
 	/* Flush TLBs (no need to flush caches - they are disabled) */
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	__flush_tlb();
 
 	/* Intel (P6) standard MTRRs */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index ae699b3..05446c1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -103,7 +103,7 @@ static void flush_tlb_func(void *info)
 	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
 		return;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
 		if (f->flush_end == TLB_FLUSH_ALL)
 			local_flush_tlb();
@@ -131,7 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 	info.flush_start = start;
 	info.flush_end = end;
 
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (is_uv_system()) {
 		unsigned int cpu;
 
@@ -151,7 +151,7 @@ void flush_tlb_current_task(void)
 
 	preempt_disable();
 
-	count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 	local_flush_tlb();
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
 		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
@@ -215,7 +215,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 
 	/* tlb_flushall_shift is on balance point, details in commit log */
 	if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
-		count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 		local_flush_tlb();
 	} else {
 		if (has_large_page(mm, start, end)) {
@@ -224,7 +224,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 		}
 		/* flush range by one by one 'invlpg' */
 		for (addr = start; addr < end;	addr += PAGE_SIZE) {
-			count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 			__flush_tlb_single(addr);
 		}
 
@@ -262,7 +262,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
 
 static void do_flush_tlb_all(void *info)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
 	__flush_tlb_all();
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
 		leave_mm(smp_processor_id());
@@ -270,7 +270,7 @@ static void do_flush_tlb_all(void *info)
 
 void flush_tlb_all(void)
 {
-	count_vm_event(NR_TLB_REMOTE_FLUSH);
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
 
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index c557c6d..3a712e2 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -71,12 +71,14 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		THP_ZERO_PAGE_ALLOC,
 		THP_ZERO_PAGE_ALLOC_FAILED,
 #endif
+#ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 		NR_TLB_REMOTE_FLUSH,	/* cpu tried to flush others' tlbs */
 		NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
-#endif
+#endif /* CONFIG_SMP */
 		NR_TLB_LOCAL_FLUSH_ALL,
 		NR_TLB_LOCAL_FLUSH_ONE,
+#endif /* CONFIG_DEBUG_TLBFLUSH */
 		NR_VM_EVENT_ITEMS
 };
 
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index a67b384..67ce70c 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -83,6 +83,14 @@ static inline void vm_events_fold_cpu(int cpu)
 #define count_vm_numa_events(x, y) do { (void)(y); } while (0)
 #endif /* CONFIG_NUMA_BALANCING */
 
+#ifdef CONFIG_DEBUG_TLBFLUSH
+#define count_vm_tlb_event(x)	   count_vm_event(x)
+#define count_vm_tlb_events(x, y)  count_vm_events(x, y)
+#else
+#define count_vm_tlb_event(x)     do {} while (0)
+#define count_vm_tlb_events(x, y) do { (void)(y); } while (0)
+#endif
+
 #define __count_zone_vm_events(item, zone, delta) \
 		__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
 		zone_idx(zone), delta)
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 5a442a7..8e8acfa 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -851,12 +851,14 @@ const char * const vmstat_text[] = {
 	"thp_zero_page_alloc",
 	"thp_zero_page_alloc_failed",
 #endif
+#ifdef CONFIG_DEBUG_TLBFLUSH
 #ifdef CONFIG_SMP
 	"nr_tlb_remote_flush",
 	"nr_tlb_remote_flush_received",
-#endif
+#endif /* CONFIG_SMP */
 	"nr_tlb_local_flush_all",
 	"nr_tlb_local_flush_one",
+#endif /* CONFIG_DEBUG_TLBFLUSH */
 
 #endif /* CONFIG_VM_EVENTS_COUNTERS */
 };
-- 
1.8.4.5

[PATCH 17/97] x86/mm: Clean up inconsistencies when flushing TLB ranges

[Mel Gorman]

commit 15aa368255f249df0b2af630c9487bb5471bd7da upstream.

NR_TLB_LOCAL_FLUSH_ALL is not always accounted for correctly and
the comparison with total_vm is done before taking
tlb_flushall_shift into account.  Clean it up.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Tested-by: Davidlohr Bueso <davidlohr@hp.com>
Reviewed-by: Alex Shi <alex.shi@linaro.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Link: http://lkml.kernel.org/n/tip-Iz5gcahrgskIldvukulzi0hh@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 arch/x86/mm/tlb.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 05446c1..5176526 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -189,6 +189,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 {
 	unsigned long addr;
 	unsigned act_entries, tlb_entries = 0;
+	unsigned long nr_base_pages;
 
 	preempt_disable();
 	if (current->active_mm != mm)
@@ -210,18 +211,17 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 		tlb_entries = tlb_lli_4k[ENTRIES];
 	else
 		tlb_entries = tlb_lld_4k[ENTRIES];
+
 	/* Assume all of TLB entries was occupied by this task */
-	act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
+	act_entries = tlb_entries >> tlb_flushall_shift;
+	act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm;
+	nr_base_pages = (end - start) >> PAGE_SHIFT;
 
 	/* tlb_flushall_shift is on balance point, details in commit log */
-	if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
+	if (nr_base_pages > act_entries || has_large_page(mm, start, end)) {
 		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 		local_flush_tlb();
 	} else {
-		if (has_large_page(mm, start, end)) {
-			local_flush_tlb();
-			goto flush_all;
-		}
 		/* flush range by one by one 'invlpg' */
 		for (addr = start; addr < end;	addr += PAGE_SIZE) {
 			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
-- 
1.8.4.5

[PATCH 18/97] x86/mm: Eliminate redundant page table walk during TLB range flushing

[Mel Gorman]

commit 71b54f8263860a37dd9f50f81880a9d681fd9c10 upstream.

When choosing between doing an address space or ranged flush,
the x86 implementation of flush_tlb_mm_range takes into account
whether there are any large pages in the range.  A per-page
flush typically requires fewer entries than would covered by a
single large page and the check is redundant.

There is one potential exception.  THP migration flushes single
THP entries and it conceivably would benefit from flushing a
single entry instead of the mm.  However, this flush is after a
THP allocation, copy and page table update potentially with any
other threads serialised behind it.  In comparison to that, the
flush is noise.  It makes more sense to optimise balancing to
require fewer flushes than to optimise the flush itself.

This patch deletes the redundant huge page check.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Tested-by: Davidlohr Bueso <davidlohr@hp.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Alex Shi <alex.shi@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-sgei1drpOcburujPsfh6ovmo@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 arch/x86/mm/tlb.c | 28 +---------------------------
 1 file changed, 1 insertion(+), 27 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 5176526..dd8dda1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -158,32 +158,6 @@ void flush_tlb_current_task(void)
 	preempt_enable();
 }
 
-/*
- * It can find out the THP large page, or
- * HUGETLB page in tlb_flush when THP disabled
- */
-static inline unsigned long has_large_page(struct mm_struct *mm,
-				 unsigned long start, unsigned long end)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	unsigned long addr = ALIGN(start, HPAGE_SIZE);
-	for (; addr < end; addr += HPAGE_SIZE) {
-		pgd = pgd_offset(mm, addr);
-		if (likely(!pgd_none(*pgd))) {
-			pud = pud_offset(pgd, addr);
-			if (likely(!pud_none(*pud))) {
-				pmd = pmd_offset(pud, addr);
-				if (likely(!pmd_none(*pmd)))
-					if (pmd_large(*pmd))
-						return addr;
-			}
-		}
-	}
-	return 0;
-}
-
 void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned long vmflag)
 {
@@ -218,7 +192,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	nr_base_pages = (end - start) >> PAGE_SHIFT;
 
 	/* tlb_flushall_shift is on balance point, details in commit log */
-	if (nr_base_pages > act_entries || has_large_page(mm, start, end)) {
+	if (nr_base_pages > act_entries) {
 		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
 		local_flush_tlb();
 	} else {
-- 
1.8.4.5

[PATCH 19/97] mm: compaction: trace compaction begin and end

[Mel Gorman]

commit 0eb927c0ab789d3d7d69f68acb850f69d4e7c36f upstream.

The broad goal of the series is to improve allocation success rates for
huge pages through memory compaction, while trying not to increase the
compaction overhead.  The original objective was to reintroduce
capturing of high-order pages freed by the compaction, before they are
split by concurrent activity.  However, several bugs and opportunities
for simple improvements were found in the current implementation, mostly
through extra tracepoints (which are however too ugly for now to be
considered for sending).

The patches mostly deal with two mechanisms that reduce compaction
overhead, which is caching the progress of migrate and free scanners,
and marking pageblocks where isolation failed to be skipped during
further scans.

Patch 1 (from mgorman) adds tracepoints that allow calculate time spent in
        compaction and potentially debug scanner pfn values.

Patch 2 encapsulates the some functionality for handling deferred compactions
        for better maintainability, without a functional change
        type is not determined without being actually needed.

Patch 3 fixes a bug where cached scanner pfn's are sometimes reset only after
        they have been read to initialize a compaction run.

Patch 4 fixes a bug where scanners meeting is sometimes not properly detected
        and can lead to multiple compaction attempts quitting early without
        doing any work.

Patch 5 improves the chances of sync compaction to process pageblocks that
        async compaction has skipped due to being !MIGRATE_MOVABLE.

Patch 6 improves the chances of sync direct compaction to actually do anything
        when called after async compaction fails during allocation slowpath.

The impact of patches were validated using mmtests's stress-highalloc
benchmark with mmtests's stress-highalloc benchmark on a x86_64 machine
with 4GB memory.

Due to instability of the results (mostly related to the bugs fixed by
patches 2 and 3), 10 iterations were performed, taking min,mean,max
values for success rates and mean values for time and vmstat-based
metrics.

First, the default GFP_HIGHUSER_MOVABLE allocations were tested with the
patches stacked on top of v3.13-rc2.  Patch 2 is OK to serve as baseline
due to no functional changes in 1 and 2.  Comments below.

stress-highalloc
                             3.13-rc2              3.13-rc2              3.13-rc2              3.13-rc2              3.13-rc2
                              2-nothp               3-nothp               4-nothp               5-nothp               6-nothp
Success 1 Min          9.00 (  0.00%)       10.00 (-11.11%)       43.00 (-377.78%)       43.00 (-377.78%)       33.00 (-266.67%)
Success 1 Mean        27.50 (  0.00%)       25.30 (  8.00%)       45.50 (-65.45%)       45.90 (-66.91%)       46.30 (-68.36%)
Success 1 Max         36.00 (  0.00%)       36.00 (  0.00%)       47.00 (-30.56%)       48.00 (-33.33%)       52.00 (-44.44%)
Success 2 Min         10.00 (  0.00%)        8.00 ( 20.00%)       46.00 (-360.00%)       45.00 (-350.00%)       35.00 (-250.00%)
Success 2 Mean        26.40 (  0.00%)       23.50 ( 10.98%)       47.30 (-79.17%)       47.60 (-80.30%)       48.10 (-82.20%)
Success 2 Max         34.00 (  0.00%)       33.00 (  2.94%)       48.00 (-41.18%)       50.00 (-47.06%)       54.00 (-58.82%)
Success 3 Min         65.00 (  0.00%)       63.00 (  3.08%)       85.00 (-30.77%)       84.00 (-29.23%)       85.00 (-30.77%)
Success 3 Mean        76.70 (  0.00%)       70.50 (  8.08%)       86.20 (-12.39%)       85.50 (-11.47%)       86.00 (-12.13%)
Success 3 Max         87.00 (  0.00%)       86.00 (  1.15%)       88.00 ( -1.15%)       87.00 (  0.00%)       87.00 (  0.00%)

            3.13-rc2    3.13-rc2    3.13-rc2    3.13-rc2    3.13-rc2
             2-nothp     3-nothp     4-nothp     5-nothp     6-nothp
User         6437.72     6459.76     5960.32     5974.55     6019.67
System       1049.65     1049.09     1029.32     1031.47     1032.31
Elapsed      1856.77     1874.48     1949.97     1994.22     1983.15

                              3.13-rc2    3.13-rc2    3.13-rc2    3.13-rc2    3.13-rc2
                               2-nothp     3-nothp     4-nothp     5-nothp     6-nothp
Minor Faults                 253952267   254581900   250030122   250507333   250157829
Major Faults                       420         407         506         530         530
Swap Ins                             4           9           9           6           6
Swap Outs                          398         375         345         346         333
Direct pages scanned            197538      189017      298574      287019      299063
Kswapd pages scanned           1809843     1801308     1846674     1873184     1861089
Kswapd pages reclaimed         1806972     1798684     1844219     1870509     1858622
Direct pages reclaimed          197227      188829      298380      286822      298835
Kswapd efficiency                  99%         99%         99%         99%         99%
Kswapd velocity                953.382     970.449     952.243     934.569     922.286
Direct efficiency                  99%         99%         99%         99%         99%
Direct velocity                104.058     101.832     153.961     143.200     148.205
Percentage direct scans             9%          9%         13%         13%         13%
Zone normal velocity           347.289     359.676     348.063     339.933     332.983
Zone dma32 velocity            710.151     712.605     758.140     737.835     737.507
Zone dma velocity                0.000       0.000       0.000       0.000       0.000
Page writes by reclaim         557.600     429.000     353.600     426.400     381.800
Page writes file                   159          53           7          79          48
Page writes anon                   398         375         345         346         333
Page reclaim immediate             825         644         411         575         420
Sector Reads                   2781750     2769780     2878547     2939128     2910483
Sector Writes                 12080843    12083351    12012892    12002132    12010745
Page rescued immediate               0           0           0           0           0
Slabs scanned                  1575654     1545344     1778406     1786700     1794073
Direct inode steals               9657       10037       15795       14104       14645
Kswapd inode steals              46857       46335       50543       50716       51796
Kswapd skipped wait                  0           0           0           0           0
THP fault alloc                     97          91          81          71          77
THP collapse alloc                 456         506         546         544         565
THP splits                           6           5           5           4           4
THP fault fallback                   0           1           0           0           0
THP collapse fail                   14          14          12          13          12
Compaction stalls                 1006         980        1537        1536        1548
Compaction success                 303         284         562         559         578
Compaction failures                702         696         974         976         969
Page migrate success           1177325     1070077     3927538     3781870     3877057
Page migrate failure                 0           0           0           0           0
Compaction pages isolated      2547248     2306457     8301218     8008500     8200674
Compaction migrate scanned    42290478    38832618   153961130   154143900   159141197
Compaction free scanned       89199429    79189151   356529027   351943166   356326727
Compaction cost                   1566        1426        5312        5156        5294
NUMA PTE updates                     0           0           0           0           0
NUMA hint faults                     0           0           0           0           0
NUMA hint local faults               0           0           0           0           0
NUMA hint local percent            100         100         100         100         100
NUMA pages migrated                  0           0           0           0           0
AutoNUMA cost                        0           0           0           0           0

Observations:

- The "Success 3" line is allocation success rate with system idle
  (phases 1 and 2 are with background interference).  I used to get stable
  values around 85% with vanilla 3.11.  The lower min and mean values came
  with 3.12.  This was bisected to commit 81c0a2bb ("mm: page_alloc: fair
  zone allocator policy") As explained in comment for patch 3, I don't
  think the commit is wrong, but that it makes the effect of compaction
  bugs worse.  From patch 3 onwards, the results are OK and match the 3.11
  results.

- Patch 4 also clearly helps phases 1 and 2, and exceeds any results
  I've seen with 3.11 (I didn't measure it that thoroughly then, but it
  was never above 40%).

- Compaction cost and number of scanned pages is higher, especially due
  to patch 4.  However, keep in mind that patches 3 and 4 fix existing
  bugs in the current design of compaction overhead mitigation, they do
  not change it.  If overhead is found unacceptable, then it should be
  decreased differently (and consistently, not due to random conditions)
  than the current implementation does.  In contrast, patches 5 and 6
  (which are not strictly bug fixes) do not increase the overhead (but
  also not success rates).  This might be a limitation of the
  stress-highalloc benchmark as it's quite uniform.

Another set of results is when configuring stress-highalloc t allocate
with similar flags as THP uses:
 (GFP_HIGHUSER_MOVABLE|__GFP_NOMEMALLOC|__GFP_NORETRY|__GFP_NO_KSWAPD)

stress-highalloc
                             3.13-rc2              3.13-rc2              3.13-rc2              3.13-rc2              3.13-rc2
                                2-thp                 3-thp                 4-thp                 5-thp                 6-thp
Success 1 Min          2.00 (  0.00%)        7.00 (-250.00%)       18.00 (-800.00%)       19.00 (-850.00%)       26.00 (-1200.00%)
Success 1 Mean        19.20 (  0.00%)       17.80 (  7.29%)       29.20 (-52.08%)       29.90 (-55.73%)       32.80 (-70.83%)
Success 1 Max         27.00 (  0.00%)       29.00 ( -7.41%)       35.00 (-29.63%)       36.00 (-33.33%)       37.00 (-37.04%)
Success 2 Min          3.00 (  0.00%)        8.00 (-166.67%)       21.00 (-600.00%)       21.00 (-600.00%)       32.00 (-966.67%)
Success 2 Mean        19.30 (  0.00%)       17.90 (  7.25%)       32.20 (-66.84%)       32.60 (-68.91%)       35.70 (-84.97%)
Success 2 Max         27.00 (  0.00%)       30.00 (-11.11%)       36.00 (-33.33%)       37.00 (-37.04%)       39.00 (-44.44%)
Success 3 Min         62.00 (  0.00%)       62.00 (  0.00%)       85.00 (-37.10%)       75.00 (-20.97%)       64.00 ( -3.23%)
Success 3 Mean        66.30 (  0.00%)       65.50 (  1.21%)       85.60 (-29.11%)       83.40 (-25.79%)       83.50 (-25.94%)
Success 3 Max         70.00 (  0.00%)       69.00 (  1.43%)       87.00 (-24.29%)       86.00 (-22.86%)       87.00 (-24.29%)

            3.13-rc2    3.13-rc2    3.13-rc2    3.13-rc2    3.13-rc2
               2-thp       3-thp       4-thp       5-thp       6-thp
User         6547.93     6475.85     6265.54     6289.46     6189.96
System       1053.42     1047.28     1043.23     1042.73     1038.73
Elapsed      1835.43     1821.96     1908.67     1912.74     1956.38

                              3.13-rc2    3.13-rc2    3.13-rc2    3.13-rc2    3.13-rc2
                                 2-thp       3-thp       4-thp       5-thp       6-thp
Minor Faults                 256805673   253106328   253222299   249830289   251184418
Major Faults                       395         375         423         434         448
Swap Ins                            12          10          10          12           9
Swap Outs                          530         537         487         455         415
Direct pages scanned             71859       86046      153244      152764      190713
Kswapd pages scanned           1900994     1870240     1898012     1892864     1880520
Kswapd pages reclaimed         1897814     1867428     1894939     1890125     1877924
Direct pages reclaimed           71766       85908      153167      152643      190600
Kswapd efficiency                  99%         99%         99%         99%         99%
Kswapd velocity               1029.000    1067.782    1000.091     991.049     951.218
Direct efficiency                  99%         99%         99%         99%         99%
Direct velocity                 38.897      49.127      80.747      79.983      96.468
Percentage direct scans             3%          4%          7%          7%          9%
Zone normal velocity           351.377     372.494     348.910     341.689     335.310
Zone dma32 velocity            716.520     744.414     731.928     729.343     712.377
Zone dma velocity                0.000       0.000       0.000       0.000       0.000
Page writes by reclaim         669.300     604.000     545.700     538.900     429.900
Page writes file                   138          66          58          83          14
Page writes anon                   530         537         487         455         415
Page reclaim immediate             806         655         772         548         517
Sector Reads                   2711956     2703239     2811602     2818248     2839459
Sector Writes                 12163238    12018662    12038248    11954736    11994892
Page rescued immediate               0           0           0           0           0
Slabs scanned                  1385088     1388364     1507968     1513292     1558656
Direct inode steals               1739        2564        4622        5496        6007
Kswapd inode steals              47461       46406       47804       48013       48466
Kswapd skipped wait                  0           0           0           0           0
THP fault alloc                    110          82          84          69          70
THP collapse alloc                 445         482         467         462         539
THP splits                           6           5           4           5           3
THP fault fallback                   3           0           0           0           0
THP collapse fail                   15          14          14          14          13
Compaction stalls                  659         685        1033        1073        1111
Compaction success                 222         225         410         427         456
Compaction failures                436         460         622         646         655
Page migrate success            446594      439978     1085640     1095062     1131716
Page migrate failure                 0           0           0           0           0
Compaction pages isolated      1029475     1013490     2453074     2482698     2565400
Compaction migrate scanned     9955461    11344259    24375202    27978356    30494204
Compaction free scanned       27715272    28544654    80150615    82898631    85756132
Compaction cost                    552         555        1344        1379        1436
NUMA PTE updates                     0           0           0           0           0
NUMA hint faults                     0           0           0           0           0
NUMA hint local faults               0           0           0           0           0
NUMA hint local percent            100         100         100         100         100
NUMA pages migrated                  0           0           0           0           0
AutoNUMA cost                        0           0           0           0           0

There are some differences from the previous results for THP-like allocations:

- Here, the bad result for unpatched kernel in phase 3 is much more
  consistent to be between 65-70% and not related to the "regression" in
  3.12.  Still there is the improvement from patch 4 onwards, which brings
  it on par with simple GFP_HIGHUSER_MOVABLE allocations.

- Compaction costs have increased, but nowhere near as much as the
  non-THP case.  Again, the patches should be worth the gained
  determininsm.

- Patches 5 and 6 somewhat increase the number of migrate-scanned pages.
   This is most likely due to __GFP_NO_KSWAPD flag, which means the cached
  pfn's and pageblock skip bits are not reset by kswapd that often (at
  least in phase 3 where no concurrent activity would wake up kswapd) and
  the patches thus help the sync-after-async compaction.  It doesn't
  however show that the sync compaction would help so much with success
  rates, which can be again seen as a limitation of the benchmark
  scenario.

This patch (of 6):

Add two tracepoints for compaction begin and end of a zone.  Using this it
is possible to calculate how much time a workload is spending within
compaction and potentially debug problems related to cached pfns for
scanning.  In combination with the direct reclaim and slab trace points it
should be possible to estimate most allocation-related overhead for a
workload.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/trace/events/compaction.h | 42 +++++++++++++++++++++++++++++++++++++++
 mm/compaction.c                   |  4 ++++
 2 files changed, 46 insertions(+)

diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index fde1b3e..06f544e 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -67,6 +67,48 @@ TRACE_EVENT(mm_compaction_migratepages,
 		__entry->nr_failed)
 );
 
+TRACE_EVENT(mm_compaction_begin,
+	TP_PROTO(unsigned long zone_start, unsigned long migrate_start,
+		unsigned long free_start, unsigned long zone_end),
+
+	TP_ARGS(zone_start, migrate_start, free_start, zone_end),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, zone_start)
+		__field(unsigned long, migrate_start)
+		__field(unsigned long, free_start)
+		__field(unsigned long, zone_end)
+	),
+
+	TP_fast_assign(
+		__entry->zone_start = zone_start;
+		__entry->migrate_start = migrate_start;
+		__entry->free_start = free_start;
+		__entry->zone_end = zone_end;
+	),
+
+	TP_printk("zone_start=%lu migrate_start=%lu free_start=%lu zone_end=%lu",
+		__entry->zone_start,
+		__entry->migrate_start,
+		__entry->free_start,
+		__entry->zone_end)
+);
+
+TRACE_EVENT(mm_compaction_end,
+	TP_PROTO(int status),
+
+	TP_ARGS(status),
+
+	TP_STRUCT__entry(
+		__field(int, status)
+	),
+
+	TP_fast_assign(
+		__entry->status = status;
+	),
+
+	TP_printk("status=%d", __entry->status)
+);
 
 #endif /* _TRACE_COMPACTION_H */
 
diff --git a/mm/compaction.c b/mm/compaction.c
index 6441083e..d656656 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -986,6 +986,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		zone->compact_cached_migrate_pfn = cc->migrate_pfn;
 	}
 
+	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn);
+
 	migrate_prep_local();
 
 	while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
@@ -1035,6 +1037,8 @@ out:
 	cc->nr_freepages -= release_freepages(&cc->freepages);
 	VM_BUG_ON(cc->nr_freepages != 0);
 
+	trace_mm_compaction_end(ret);
+
 	return ret;
 }
 
-- 
1.8.4.5

[PATCH 20/97] mm: compaction: encapsulate defer reset logic

[Mel Gorman]

From: Vlastimil Babka <vbabka@suse.cz>

commit de6c60a6c115acaa721cfd499e028a413d1fcbf3 upstream.

Currently there are several functions to manipulate the deferred
compaction state variables.  The remaining case where the variables are
touched directly is when a successful allocation occurs in direct
compaction, or is expected to be successful in the future by kswapd.
Here, the lowest order that is expected to fail is updated, and in the
case of successful allocation, the deferred status and counter is reset
completely.

Create a new function compaction_defer_reset() to encapsulate this
functionality and make it easier to understand the code.  No functional
change.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/compaction.h | 16 ++++++++++++++++
 mm/compaction.c            |  9 ++++-----
 mm/page_alloc.c            |  5 +----
 3 files changed, 21 insertions(+), 9 deletions(-)

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 091d72e..7e1c76e 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -62,6 +62,22 @@ static inline bool compaction_deferred(struct zone *zone, int order)
 	return zone->compact_considered < defer_limit;
 }
 
+/*
+ * Update defer tracking counters after successful compaction of given order,
+ * which means an allocation either succeeded (alloc_success == true) or is
+ * expected to succeed.
+ */
+static inline void compaction_defer_reset(struct zone *zone, int order,
+		bool alloc_success)
+{
+	if (alloc_success) {
+		zone->compact_considered = 0;
+		zone->compact_defer_shift = 0;
+	}
+	if (order >= zone->compact_order_failed)
+		zone->compact_order_failed = order + 1;
+}
+
 /* Returns true if restarting compaction after many failures */
 static inline bool compaction_restarting(struct zone *zone, int order)
 {
diff --git a/mm/compaction.c b/mm/compaction.c
index d656656..c55bd45 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1144,12 +1144,11 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 			compact_zone(zone, cc);
 
 		if (cc->order > 0) {
-			int ok = zone_watermark_ok(zone, cc->order,
-						low_wmark_pages(zone), 0, 0);
-			if (ok && cc->order >= zone->compact_order_failed)
-				zone->compact_order_failed = cc->order + 1;
+			if (zone_watermark_ok(zone, cc->order,
+						low_wmark_pages(zone), 0, 0))
+				compaction_defer_reset(zone, cc->order, false);
 			/* Currently async compaction is never deferred. */
-			else if (!ok && cc->sync)
+			else if (cc->sync)
 				defer_compaction(zone, cc->order);
 		}
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index baef87e..3078eaf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2251,10 +2251,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 				preferred_zone, migratetype);
 		if (page) {
 			preferred_zone->compact_blockskip_flush = false;
-			preferred_zone->compact_considered = 0;
-			preferred_zone->compact_defer_shift = 0;
-			if (order >= preferred_zone->compact_order_failed)
-				preferred_zone->compact_order_failed = order + 1;
+			compaction_defer_reset(preferred_zone, order, true);
 			count_vm_event(COMPACTSUCCESS);
 			return page;
 		}
-- 
1.8.4.5

[PATCH 21/97] mm: compaction: do not mark unmovable pageblocks as skipped in async compaction

[Mel Gorman]

From: Vlastimil Babka <vbabka@suse.cz>

commit 50b5b094e683f8e51e82c6dfe97b1608cf97e6c0 upstream.

Compaction temporarily marks pageblocks where it fails to isolate pages
as to-be-skipped in further compactions, in order to improve efficiency.
One of the reasons to fail isolating pages is that isolation is not
attempted in pageblocks that are not of MIGRATE_MOVABLE (or CMA) type.

The problem is that blocks skipped due to not being MIGRATE_MOVABLE in
async compaction become skipped due to the temporary mark also in future
sync compaction.  Moreover, this may follow quite soon during
__alloc_page_slowpath, without much time for kswapd to clear the
pageblock skip marks.  This goes against the idea that sync compaction
should try to scan these blocks more thoroughly than the async
compaction.

The fix is to ensure in async compaction that these !MIGRATE_MOVABLE
blocks are not marked to be skipped.  Note this should not affect
performance or locking impact of further async compactions, as skipping
a block due to being !MIGRATE_MOVABLE is done soon after skipping a
block marked to be skipped, both without locking.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index c55bd45..5cf2d60 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -466,6 +466,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	unsigned long flags;
 	bool locked = false;
 	struct page *page = NULL, *valid_page = NULL;
+	bool skipped_async_unsuitable = false;
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
@@ -541,6 +542,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		if (!cc->sync && last_pageblock_nr != pageblock_nr &&
 		    !migrate_async_suitable(get_pageblock_migratetype(page))) {
 			cc->finished_update_migrate = true;
+			skipped_async_unsuitable = true;
 			goto next_pageblock;
 		}
 
@@ -634,8 +636,13 @@ next_pageblock:
 	if (locked)
 		spin_unlock_irqrestore(&zone->lru_lock, flags);
 
-	/* Update the pageblock-skip if the whole pageblock was scanned */
-	if (low_pfn == end_pfn)
+	/*
+	 * Update the pageblock-skip information and cached scanner pfn,
+	 * if the whole pageblock was scanned without isolating any page.
+	 * This is not done when pageblock was skipped due to being unsuitable
+	 * for async compaction, so that eventual sync compaction can try.
+	 */
+	if (low_pfn == end_pfn && !skipped_async_unsuitable)
 		update_pageblock_skip(cc, valid_page, nr_isolated, true);
 
 	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
-- 
1.8.4.5

[PATCH 22/97] mm: compaction: reset scanner positions immediately when they meet

[Mel Gorman]

From: Vlastimil Babka <vbabka@suse.cz>

commit 55b7c4c99f6a448f72179297fe6432544f220063 upstream.

Compaction used to start its migrate and free page scaners at the zone's
lowest and highest pfn, respectively.  Later, caching was introduced to
remember the scanners' progress across compaction attempts so that
pageblocks are not re-scanned uselessly.  Additionally, pageblocks where
isolation failed are marked to be quickly skipped when encountered again
in future compactions.

Currently, both the reset of cached pfn's and clearing of the pageblock
skip information for a zone is done in __reset_isolation_suitable().
This function gets called when:

 - compaction is restarting after being deferred
 - compact_blockskip_flush flag is set in compact_finished() when the scanners
   meet (and not again cleared when direct compaction succeeds in allocation)
   and kswapd acts upon this flag before going to sleep

This behavior is suboptimal for several reasons:

 - when direct sync compaction is called after async compaction fails (in the
   allocation slowpath), it will effectively do nothing, unless kswapd
   happens to process the compact_blockskip_flush flag meanwhile. This is racy
   and goes against the purpose of sync compaction to more thoroughly retry
   the compaction of a zone where async compaction has failed.
   The restart-after-deferring path cannot help here as deferring happens only
   after the sync compaction fails. It is also done only for the preferred
   zone, while the compaction might be done for a fallback zone.

 - the mechanism of marking pageblock to be skipped has little value since the
   cached pfn's are reset only together with the pageblock skip flags. This
   effectively limits pageblock skip usage to parallel compactions.

This patch changes compact_finished() so that cached pfn's are reset
immediately when the scanners meet.  Clearing pageblock skip flags is
unchanged, as well as the other situations where cached pfn's are reset.
This allows the sync-after-async compaction to retry pageblocks not
marked as skipped, such as blocks !MIGRATE_MOVABLE blocks that async
compactions now skips without marking them.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/mm/compaction.c b/mm/compaction.c
index 5cf2d60..ae428e6 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -860,6 +860,10 @@ static int compact_finished(struct zone *zone,
 
 	/* Compaction run completes if the migrate and free scanner meet */
 	if (cc->free_pfn <= cc->migrate_pfn) {
+		/* Let the next compaction start anew. */
+		zone->compact_cached_migrate_pfn = zone->zone_start_pfn;
+		zone->compact_cached_free_pfn = zone_end_pfn(zone);
+
 		/*
 		 * Mark that the PG_migrate_skip information should be cleared
 		 * by kswapd when it goes to sleep. kswapd does not set the
-- 
1.8.4.5

[PATCH 23/97] swap: add a simple detector for inappropriate swapin readahead

[Mel Gorman]

From: Shaohua Li <shli@kernel.org>

commit 579f82901f6f41256642936d7e632f3979ad76d4 upstream.

This is a patch to improve swap readahead algorithm.  It's from Hugh and
I slightly changed it.

Hugh's original changelog:

swapin readahead does a blind readahead, whether or not the swapin is
sequential.  This may be ok on harddisk, because large reads have
relatively small costs, and if the readahead pages are unneeded they can
be reclaimed easily - though, what if their allocation forced reclaim of
useful pages? But on SSD devices large reads are more expensive than
small ones: if the readahead pages are unneeded, reading them in caused
significant overhead.

This patch adds very simplistic random read detection.  Stealing the
PageReadahead technique from Konstantin Khlebnikov's patch, avoiding the
vma/anon_vma sophistications of Shaohua Li's patch, swapin_nr_pages()
simply looks at readahead's current success rate, and narrows or widens
its readahead window accordingly.  There is little science to its
heuristic: it's about as stupid as can be whilst remaining effective.

The table below shows elapsed times (in centiseconds) when running a
single repetitive swapping load across a 1000MB mapping in 900MB ram
with 1GB swap (the harddisk tests had taken painfully too long when I
used mem=500M, but SSD shows similar results for that).

Vanilla is the 3.6-rc7 kernel on which I started; Shaohua denotes his
Sep 3 patch in mmotm and linux-next; HughOld denotes my Oct 1 patch
which Shaohua showed to be defective; HughNew this Nov 14 patch, with
page_cluster as usual at default of 3 (8-page reads); HughPC4 this same
patch with page_cluster 4 (16-page reads); HughPC0 with page_cluster 0
(1-page reads: no readahead).

HDD for swapping to harddisk, SSD for swapping to VertexII SSD.  Seq for
sequential access to the mapping, cycling five times around; Rand for
the same number of random touches.  Anon for a MAP_PRIVATE anon mapping;
Shmem for a MAP_SHARED anon mapping, equivalent to tmpfs.

One weakness of Shaohua's vma/anon_vma approach was that it did not
optimize Shmem: seen below.  Konstantin's approach was perhaps mistuned,
50% slower on Seq: did not compete and is not shown below.

HDD        Vanilla Shaohua HughOld HughNew HughPC4 HughPC0
Seq Anon     73921   76210   75611   76904   78191  121542
Seq Shmem    73601   73176   73855   72947   74543  118322
Rand Anon   895392  831243  871569  845197  846496  841680
Rand Shmem 1058375 1053486  827935  764955  764376  756489

SSD        Vanilla Shaohua HughOld HughNew HughPC4 HughPC0
Seq Anon     24634   24198   24673   25107   21614   70018
Seq Shmem    24959   24932   25052   25703   22030   69678
Rand Anon    43014   26146   28075   25989   26935   25901
Rand Shmem   45349   45215   28249   24268   24138   24332

These tests are, of course, two extremes of a very simple case: under
heavier mixed loads I've not yet observed any consistent improvement or
degradation, and wider testing would be welcome.

Shaohua Li:

Test shows Vanilla is slightly better in sequential workload than Hugh's
patch.  I observed with Hugh's patch sometimes the readahead size is
shrinked too fast (from 8 to 1 immediately) in sequential workload if
there is no hit.  And in such case, continuing doing readahead is good
actually.

I don't prepare a sophisticated algorithm for the sequential workload
because so far we can't guarantee sequential accessed pages are swap out
sequentially.  So I slightly change Hugh's heuristic - don't shrink
readahead size too fast.

Here is my test result (unit second, 3 runs average):
	Vanilla		Hugh		New
Seq	356		370		360
Random	4525		2447		2444

Attached graph is the swapin/swapout throughput I collected with 'vmstat
2'.  The first part is running a random workload (till around 1200 of
the x-axis) and the second part is running a sequential workload.
swapin and swapout throughput are almost identical in steady state in
both workloads.  These are expected behavior.  while in Vanilla, swapin
is much bigger than swapout especially in random workload (because wrong
readahead).

Original patches by: Shaohua Li and Konstantin Khlebnikov.

[fengguang.wu@intel.com: swapin_nr_pages() can be static]
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/page-flags.h |  4 +--
 mm/swap_state.c            | 63 +++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 62 insertions(+), 5 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index dd7d45b..67fc8a2 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -228,9 +228,9 @@ PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1)
 TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback)
 PAGEFLAG(MappedToDisk, mappedtodisk)
 
-/* PG_readahead is only used for file reads; PG_reclaim is only for writes */
+/* PG_readahead is only used for reads; PG_reclaim is only for writes */
 PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim)
-PAGEFLAG(Readahead, reclaim)		/* Reminder to do async read-ahead */
+PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim)
 
 #ifdef CONFIG_HIGHMEM
 /*
diff --git a/mm/swap_state.c b/mm/swap_state.c
index e6f15f8..fdde6f9 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -63,6 +63,8 @@ unsigned long total_swapcache_pages(void)
 	return ret;
 }
 
+static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
+
 void show_swap_cache_info(void)
 {
 	printk("%lu pages in swap cache\n", total_swapcache_pages());
@@ -286,8 +288,11 @@ struct page * lookup_swap_cache(swp_entry_t entry)
 
 	page = find_get_page(swap_address_space(entry), entry.val);
 
-	if (page)
+	if (page) {
 		INC_CACHE_INFO(find_success);
+		if (TestClearPageReadahead(page))
+			atomic_inc(&swapin_readahead_hits);
+	}
 
 	INC_CACHE_INFO(find_total);
 	return page;
@@ -389,6 +394,50 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 	return found_page;
 }
 
+static unsigned long swapin_nr_pages(unsigned long offset)
+{
+	static unsigned long prev_offset;
+	unsigned int pages, max_pages, last_ra;
+	static atomic_t last_readahead_pages;
+
+	max_pages = 1 << ACCESS_ONCE(page_cluster);
+	if (max_pages <= 1)
+		return 1;
+
+	/*
+	 * This heuristic has been found to work well on both sequential and
+	 * random loads, swapping to hard disk or to SSD: please don't ask
+	 * what the "+ 2" means, it just happens to work well, that's all.
+	 */
+	pages = atomic_xchg(&swapin_readahead_hits, 0) + 2;
+	if (pages == 2) {
+		/*
+		 * We can have no readahead hits to judge by: but must not get
+		 * stuck here forever, so check for an adjacent offset instead
+		 * (and don't even bother to check whether swap type is same).
+		 */
+		if (offset != prev_offset + 1 && offset != prev_offset - 1)
+			pages = 1;
+		prev_offset = offset;
+	} else {
+		unsigned int roundup = 4;
+		while (roundup < pages)
+			roundup <<= 1;
+		pages = roundup;
+	}
+
+	if (pages > max_pages)
+		pages = max_pages;
+
+	/* Don't shrink readahead too fast */
+	last_ra = atomic_read(&last_readahead_pages) / 2;
+	if (pages < last_ra)
+		pages = last_ra;
+	atomic_set(&last_readahead_pages, pages);
+
+	return pages;
+}
+
 /**
  * swapin_readahead - swap in pages in hope we need them soon
  * @entry: swap entry of this memory
@@ -412,11 +461,16 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 			struct vm_area_struct *vma, unsigned long addr)
 {
 	struct page *page;
-	unsigned long offset = swp_offset(entry);
+	unsigned long entry_offset = swp_offset(entry);
+	unsigned long offset = entry_offset;
 	unsigned long start_offset, end_offset;
-	unsigned long mask = (1UL << page_cluster) - 1;
+	unsigned long mask;
 	struct blk_plug plug;
 
+	mask = swapin_nr_pages(offset) - 1;
+	if (!mask)
+		goto skip;
+
 	/* Read a page_cluster sized and aligned cluster around offset. */
 	start_offset = offset & ~mask;
 	end_offset = offset | mask;
@@ -430,10 +484,13 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 						gfp_mask, vma, addr);
 		if (!page)
 			continue;
+		if (offset != entry_offset)
+			SetPageReadahead(page);
 		page_cache_release(page);
 	}
 	blk_finish_plug(&plug);
 
 	lru_add_drain();	/* Push any new pages onto the LRU now */
+skip:
 	return read_swap_cache_async(entry, gfp_mask, vma, addr);
 }
-- 
1.8.4.5

[PATCH 24/97] mm: vmscan: shrink all slab objects if tight on memory

[Mel Gorman]

From: Vladimir Davydov <vdavydov@parallels.com>

commit 0b1fb40a3b1291f2f12f13f644ac95cf756a00e6 upstream.

When reclaiming kmem, we currently don't scan slabs that have less than
batch_size objects (see shrink_slab_node()):

        while (total_scan >= batch_size) {
                shrinkctl->nr_to_scan = batch_size;
                shrinker->scan_objects(shrinker, shrinkctl);
                total_scan -= batch_size;
        }

If there are only a few shrinkers available, such a behavior won't cause
any problems, because the batch_size is usually small, but if we have a
lot of slab shrinkers, which is perfectly possible since FS shrinkers
are now per-superblock, we can end up with hundreds of megabytes of
practically unreclaimable kmem objects.  For instance, mounting a
thousand of ext2 FS images with a hundred of files in each and iterating
over all the files using du(1) will result in about 200 Mb of FS caches
that cannot be dropped even with the aid of the vm.drop_caches sysctl!

This problem was initially pointed out by Glauber Costa [*].  Glauber
proposed to fix it by making the shrink_slab() always take at least one
pass, to put it simply, turning the scan loop above to a do{}while()
loop.  However, this proposal was rejected, because it could result in
more aggressive and frequent slab shrinking even under low memory
pressure when total_scan is naturally very small.

This patch is a slightly modified version of Glauber's approach.
Similarly to Glauber's patch, it makes shrink_slab() scan less than
batch_size objects, but only if the total number of objects we want to
scan (total_scan) is greater than the total number of objects available
(max_pass).  Since total_scan is biased as half max_pass if the current
delta change is small:

        if (delta < max_pass / 4)
                total_scan = min(total_scan, max_pass / 2);

this is only possible if we are scanning at high prio.  That said, this
patch shouldn't change the vmscan behaviour if the memory pressure is
low, but if we are tight on memory, we will do our best by trying to
reclaim all available objects, which sounds reasonable.

[*] http://www.spinics.net/lists/cgroups/msg06913.html

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Glauber Costa <glommer@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/vmscan.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5ad29b2..0506995 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -281,17 +281,34 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 				nr_pages_scanned, lru_pages,
 				max_pass, delta, total_scan);
 
-	while (total_scan >= batch_size) {
+	/*
+	 * Normally, we should not scan less than batch_size objects in one
+	 * pass to avoid too frequent shrinker calls, but if the slab has less
+	 * than batch_size objects in total and we are really tight on memory,
+	 * we will try to reclaim all available objects, otherwise we can end
+	 * up failing allocations although there are plenty of reclaimable
+	 * objects spread over several slabs with usage less than the
+	 * batch_size.
+	 *
+	 * We detect the "tight on memory" situations by looking at the total
+	 * number of objects we want to scan (total_scan). If it is greater
+	 * than the total number of objects on slab (max_pass), we must be
+	 * scanning at high prio and therefore should try to reclaim as much as
+	 * possible.
+	 */
+	while (total_scan >= batch_size ||
+	       total_scan >= max_pass) {
 		unsigned long ret;
+		unsigned long nr_to_scan = min(batch_size, total_scan);
 
-		shrinkctl->nr_to_scan = batch_size;
+		shrinkctl->nr_to_scan = nr_to_scan;
 		ret = shrinker->scan_objects(shrinker, shrinkctl);
 		if (ret == SHRINK_STOP)
 			break;
 		freed += ret;
 
-		count_vm_events(SLABS_SCANNED, batch_size);
-		total_scan -= batch_size;
+		count_vm_events(SLABS_SCANNED, nr_to_scan);
+		total_scan -= nr_to_scan;
 
 		cond_resched();
 	}
-- 
1.8.4.5

[PATCH 25/97] mm: vmscan: call NUMA-unaware shrinkers irrespective of nodemask

[Mel Gorman]

From: Vladimir Davydov <vdavydov@parallels.com>

commit ec97097bca147d5718a5d2c024d1ec740b10096d upstream.

If a shrinker is not NUMA-aware, shrink_slab() should call it exactly
once with nid=0, but currently it is not true: if node 0 is not set in
the nodemask or if it is not online, we will not call such shrinkers at
all.  As a result some slabs will be left untouched under some
circumstances.  Let us fix it.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Reported-by: Dave Chinner <dchinner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Glauber Costa <glommer@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/vmscan.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 0506995..e36294b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -369,16 +369,17 @@ unsigned long shrink_slab(struct shrink_control *shrinkctl,
 	}
 
 	list_for_each_entry(shrinker, &shrinker_list, list) {
-		for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
-			if (!node_online(shrinkctl->nid))
-				continue;
-
-			if (!(shrinker->flags & SHRINKER_NUMA_AWARE) &&
-			    (shrinkctl->nid != 0))
-				break;
-
+		if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) {
+			shrinkctl->nid = 0;
 			freed += shrink_slab_node(shrinkctl, shrinker,
-				 nr_pages_scanned, lru_pages);
+					nr_pages_scanned, lru_pages);
+			continue;
+		}
+
+		for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
+			if (node_online(shrinkctl->nid))
+				freed += shrink_slab_node(shrinkctl, shrinker,
+						nr_pages_scanned, lru_pages);
 
 		}
 	}
-- 
1.8.4.5

[PATCH 26/97] mm: get rid of unnecessary pageblock scanning in setup_zone_migrate_reserve

[Mel Gorman]

From: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>

commit 943dca1a1fcbccb58de944669b833fd38a6c809b upstream.

Yasuaki Ishimatsu reported memory hot-add spent more than 5 _hours_ on
9TB memory machine since onlining memory sections is too slow.  And we
found out setup_zone_migrate_reserve spent >90% of the time.

The problem is, setup_zone_migrate_reserve scans all pageblocks
unconditionally, but it is only necessary if the number of reserved
block was reduced (i.e.  memory hot remove).

Moreover, maximum MIGRATE_RESERVE per zone is currently 2.  It means
that the number of reserved pageblocks is almost always unchanged.

This patch adds zone->nr_migrate_reserve_block to maintain the number of
MIGRATE_RESERVE pageblocks and it reduces the overhead of
setup_zone_migrate_reserve dramatically.  The following table shows time
of onlining a memory section.

  Amount of memory     | 128GB | 192GB | 256GB|
  ---------------------------------------------
  linux-3.12           |  23.9 |  31.4 | 44.5 |
  This patch           |   8.3 |   8.3 |  8.6 |
  Mel's proposal patch |  10.9 |  19.2 | 31.3 |
  ---------------------------------------------
                                   (millisecond)

  128GB : 4 nodes and each node has 32GB of memory
  192GB : 6 nodes and each node has 32GB of memory
  256GB : 8 nodes and each node has 32GB of memory

  (*1) Mel proposed his idea by the following threads.
       https://lkml.org/lkml/2013/10/30/272

[akpm@linux-foundation.org: tweak comment]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Reported-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Tested-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mmzone.h |  6 ++++++
 mm/page_alloc.c        | 13 +++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5648290..4719985 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -494,6 +494,12 @@ struct zone {
 	unsigned long		managed_pages;
 
 	/*
+	 * Number of MIGRATE_RESEVE page block. To maintain for just
+	 * optimization. Protected by zone->lock.
+	 */
+	int			nr_migrate_reserve_block;
+
+	/*
 	 * rarely used fields:
 	 */
 	const char		*name;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3078eaf..c34b582 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3934,6 +3934,7 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 	struct page *page;
 	unsigned long block_migratetype;
 	int reserve;
+	int old_reserve;
 
 	/*
 	 * Get the start pfn, end pfn and the number of blocks to reserve
@@ -3955,6 +3956,12 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 	 * future allocation of hugepages at runtime.
 	 */
 	reserve = min(2, reserve);
+	old_reserve = zone->nr_migrate_reserve_block;
+
+	/* When memory hot-add, we almost always need to do nothing */
+	if (reserve == old_reserve)
+		return;
+	zone->nr_migrate_reserve_block = reserve;
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
 		if (!pfn_valid(pfn))
@@ -3992,6 +3999,12 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 				reserve--;
 				continue;
 			}
+		} else if (!old_reserve) {
+			/*
+			 * At boot time we don't need to scan the whole zone
+			 * for turning off MIGRATE_RESERVE.
+			 */
+			break;
 		}
 
 		/*
-- 
1.8.4.5

[PATCH 27/97] mm, compaction: avoid isolating pinned pages

[Mel Gorman]

From: David Rientjes <rientjes@google.com>

commit 119d6d59dcc0980dcd581fdadb6b2033b512a473 upstream.

Page migration will fail for memory that is pinned in memory with, for
example, get_user_pages().  In this case, it is unnecessary to take
zone->lru_lock or isolating the page and passing it to page migration
which will ultimately fail.

This is a racy check, the page can still change from under us, but in
that case we'll just fail later when attempting to move the page.

This avoids very expensive memory compaction when faulting transparent
hugepages after pinning a lot of memory with a Mellanox driver.

On a 128GB machine and pinning ~120GB of memory, before this patch we
see the enormous disparity in the number of page migration failures
because of the pinning (from /proc/vmstat):

	compact_pages_moved 8450
	compact_pagemigrate_failed 15614415

0.05% of pages isolated are successfully migrated and explicitly
triggering memory compaction takes 102 seconds.  After the patch:

	compact_pages_moved 9197
	compact_pagemigrate_failed 7

99.9% of pages isolated are now successfully migrated in this
configuration and memory compaction takes less than one second.

Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/mm/compaction.c b/mm/compaction.c
index ae428e6..4885387 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -582,6 +582,15 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			continue;
 		}
 
+		/*
+		 * Migration will fail if an anonymous page is pinned in memory,
+		 * so avoid taking lru_lock and isolating it unnecessarily in an
+		 * admittedly racy check.
+		 */
+		if (!page_mapping(page) &&
+		    page_count(page) > page_mapcount(page))
+			continue;
+
 		/* Check if it is ok to still hold the lock */
 		locked = compact_checklock_irqsave(&zone->lru_lock, &flags,
 								locked, cc);
-- 
1.8.4.5

[PATCH 28/97] mm/compaction: disallow high-order page for migration target

[Mel Gorman]

From: Joonsoo Kim <iamjoonsoo.kim@lge.com>

commit 7d348b9ea64db0a315d777ce7d4b06697f946503 upstream.

Purpose of compaction is to get a high order page.  Currently, if we
find high-order page while searching migration target page, we break it
to order-0 pages and use them as migration target.  It is contrary to
purpose of compaction, so disallow high-order page to be used for
migration target.

Additionally, clean-up logic in suitable_migration_target() to simplify
the code.  There is no functional changes from this clean-up.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 4885387..5e48834 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -217,21 +217,12 @@ static inline bool compact_trylock_irqsave(spinlock_t *lock,
 /* Returns true if the page is within a block suitable for migration to */
 static bool suitable_migration_target(struct page *page)
 {
-	int migratetype = get_pageblock_migratetype(page);
-
-	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
-	if (migratetype == MIGRATE_RESERVE)
-		return false;
-
-	if (is_migrate_isolate(migratetype))
-		return false;
-
-	/* If the page is a large free page, then allow migration */
+	/* If the page is a large free page, then disallow migration */
 	if (PageBuddy(page) && page_order(page) >= pageblock_order)
-		return true;
+		return false;
 
 	/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
-	if (migrate_async_suitable(migratetype))
+	if (migrate_async_suitable(get_pageblock_migratetype(page)))
 		return true;
 
 	/* Otherwise skip the block */
-- 
1.8.4.5

[PATCH 29/97] mm/compaction: do not call suitable_migration_target() on every page

[Mel Gorman]

From: Joonsoo Kim <iamjoonsoo.kim@lge.com>

commit 01ead5340bcf5f3a1cd2452c75516d0ef4d908d7 upstream.

suitable_migration_target() checks that pageblock is suitable for
migration target.  In isolate_freepages_block(), it is called on every
page and this is inefficient.  So make it called once per pageblock.

suitable_migration_target() also checks if page is highorder or not, but
it's criteria for highorder is pageblock order.  So calling it once
within pageblock range has no problem.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 5e48834..6718a91 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -245,6 +245,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 	struct page *cursor, *valid_page = NULL;
 	unsigned long flags;
 	bool locked = false;
+	bool checked_pageblock = false;
 
 	cursor = pfn_to_page(blockpfn);
 
@@ -276,8 +277,16 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 			break;
 
 		/* Recheck this is a suitable migration target under lock */
-		if (!strict && !suitable_migration_target(page))
-			break;
+		if (!strict && !checked_pageblock) {
+			/*
+			 * We need to check suitability of pageblock only once
+			 * and this isolate_freepages_block() is called with
+			 * pageblock range, so just check once is sufficient.
+			 */
+			checked_pageblock = true;
+			if (!suitable_migration_target(page))
+				break;
+		}
 
 		/* Recheck this is a buddy page under lock */
 		if (!PageBuddy(page))
-- 
1.8.4.5

[PATCH 30/97] mm/compaction: change the timing to check to drop the spinlock

[Mel Gorman]

From: Joonsoo Kim <iamjoonsoo.kim@lge.com>

commit be1aa03b973c7dcdc576f3503f7a60429825c35d upstream.

It is odd to drop the spinlock when we scan (SWAP_CLUSTER_MAX - 1) th
pfn page.  This may results in below situation while isolating
migratepage.

1. try isolate 0x0 ~ 0x200 pfn pages.
2. When low_pfn is 0x1ff, ((low_pfn+1) % SWAP_CLUSTER_MAX) == 0, so drop
   the spinlock.
3. Then, to complete isolating, retry to aquire the lock.

I think that it is better to use SWAP_CLUSTER_MAX th pfn for checking the
criteria about dropping the lock.  This has no harm 0x0 pfn, because, at
this time, locked variable would be false.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 6718a91..4730a2f 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -488,7 +488,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	cond_resched();
 	for (; low_pfn < end_pfn; low_pfn++) {
 		/* give a chance to irqs before checking need_resched() */
-		if (locked && !((low_pfn+1) % SWAP_CLUSTER_MAX)) {
+		if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) {
 			if (should_release_lock(&zone->lru_lock)) {
 				spin_unlock_irqrestore(&zone->lru_lock, flags);
 				locked = false;
-- 
1.8.4.5

[PATCH 31/97] mm/compaction: check pageblock suitability once per pageblock

[Mel Gorman]

From: Joonsoo Kim <iamjoonsoo.kim@lge.com>

commit c122b2087ab94192f2b937e47b563a9c4e688ece upstream.

isolation_suitable() and migrate_async_suitable() is used to be sure
that this pageblock range is fine to be migragted.  It isn't needed to
call it on every page.  Current code do well if not suitable, but, don't
do well when suitable.

1) It re-checks isolation_suitable() on each page of a pageblock that was
   already estabilished as suitable.
2) It re-checks migrate_async_suitable() on each page of a pageblock that
   was not entered through the next_pageblock: label, because
   last_pageblock_nr is not otherwise updated.

This patch fixes situation by 1) calling isolation_suitable() only once
per pageblock and 2) always updating last_pageblock_nr to the pageblock
that was just checked.

Additionally, move PageBuddy() check after pageblock unit check, since
pageblock check is the first thing we should do and makes things more
simple.

[vbabka@suse.cz: rephrase commit description]
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 34 +++++++++++++++++++---------------
 1 file changed, 19 insertions(+), 15 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 4730a2f..229c6f7 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -527,26 +527,31 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 
 		/* If isolation recently failed, do not retry */
 		pageblock_nr = low_pfn >> pageblock_order;
-		if (!isolation_suitable(cc, page))
-			goto next_pageblock;
+		if (last_pageblock_nr != pageblock_nr) {
+			int mt;
+
+			last_pageblock_nr = pageblock_nr;
+			if (!isolation_suitable(cc, page))
+				goto next_pageblock;
+
+			/*
+			 * For async migration, also only scan in MOVABLE
+			 * blocks. Async migration is optimistic to see if
+			 * the minimum amount of work satisfies the allocation
+			 */
+			mt = get_pageblock_migratetype(page);
+			if (!cc->sync && !migrate_async_suitable(mt)) {
+				cc->finished_update_migrate = true;
+				skipped_async_unsuitable = true;
+				goto next_pageblock;
+			}
+		}
 
 		/* Skip if free */
 		if (PageBuddy(page))
 			continue;
 
 		/*
-		 * For async migration, also only scan in MOVABLE blocks. Async
-		 * migration is optimistic to see if the minimum amount of work
-		 * satisfies the allocation
-		 */
-		if (!cc->sync && last_pageblock_nr != pageblock_nr &&
-		    !migrate_async_suitable(get_pageblock_migratetype(page))) {
-			cc->finished_update_migrate = true;
-			skipped_async_unsuitable = true;
-			goto next_pageblock;
-		}
-
-		/*
 		 * Check may be lockless but that's ok as we recheck later.
 		 * It's possible to migrate LRU pages and balloon pages
 		 * Skip any other type of page
@@ -637,7 +642,6 @@ check_compact_cluster:
 
 next_pageblock:
 		low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1;
-		last_pageblock_nr = pageblock_nr;
 	}
 
 	acct_isolated(zone, locked, cc);
-- 
1.8.4.5

[PATCH 32/97] mm/compaction: clean-up code on success of ballon isolation

[Mel Gorman]

From: Joonsoo Kim <iamjoonsoo.kim@lge.com>

commit b6c750163c0d138f5041d95fcdbd1094b6928057 upstream.

It is just for clean-up to reduce code size and improve readability.
There is no functional change.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 229c6f7..10f9f8c 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -560,11 +560,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			if (unlikely(balloon_page_movable(page))) {
 				if (locked && balloon_page_isolate(page)) {
 					/* Successfully isolated */
-					cc->finished_update_migrate = true;
-					list_add(&page->lru, migratelist);
-					cc->nr_migratepages++;
-					nr_isolated++;
-					goto check_compact_cluster;
+					goto isolate_success;
 				}
 			}
 			continue;
@@ -625,13 +621,14 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		VM_BUG_ON(PageTransCompound(page));
 
 		/* Successfully isolated */
-		cc->finished_update_migrate = true;
 		del_page_from_lru_list(page, lruvec, page_lru(page));
+
+isolate_success:
+		cc->finished_update_migrate = true;
 		list_add(&page->lru, migratelist);
 		cc->nr_migratepages++;
 		nr_isolated++;
 
-check_compact_cluster:
 		/* Avoid isolating too much */
 		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
 			++low_pfn;
-- 
1.8.4.5

[PATCH 33/97] mm, compaction: determine isolation mode only once

[Mel Gorman]

From: David Rientjes <rientjes@google.com>

commit da1c67a76f7cf2b3404823d24f9f10fa91aa5dc5 upstream.

The conditions that control the isolation mode in
isolate_migratepages_range() do not change during the iteration, so
extract them out and only define the value once.

This actually does have an effect, gcc doesn't optimize it itself because
of cc->sync.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 10f9f8c..4530818 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -461,12 +461,13 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	unsigned long last_pageblock_nr = 0, pageblock_nr;
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct list_head *migratelist = &cc->migratepages;
-	isolate_mode_t mode = 0;
 	struct lruvec *lruvec;
 	unsigned long flags;
 	bool locked = false;
 	struct page *page = NULL, *valid_page = NULL;
 	bool skipped_async_unsuitable = false;
+	const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) |
+				    (unevictable ? ISOLATE_UNEVICTABLE : 0);
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
@@ -606,12 +607,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			continue;
 		}
 
-		if (!cc->sync)
-			mode |= ISOLATE_ASYNC_MIGRATE;
-
-		if (unevictable)
-			mode |= ISOLATE_UNEVICTABLE;
-
 		lruvec = mem_cgroup_page_lruvec(page, zone);
 
 		/* Try isolate the page */
-- 
1.8.4.5

[PATCH 34/97] mm, compaction: ignore pageblock skip when manually invoking compaction

[Mel Gorman]

From: David Rientjes <rientjes@google.com>

commit 91ca9186484809c57303b33778d841cc28f696ed upstream.

The cached pageblock hint should be ignored when triggering compaction
through /proc/sys/vm/compact_memory so all eligible memory is isolated.
Manually invoking compaction is known to be expensive, there's no need
to skip pageblocks based on heuristics (mainly for debugging).

Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/compaction.c b/mm/compaction.c
index 4530818..5c17302 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1191,6 +1191,7 @@ static void compact_node(int nid)
 	struct compact_control cc = {
 		.order = -1,
 		.sync = true,
+		.ignore_skip_hint = true,
 	};
 
 	__compact_pgdat(NODE_DATA(nid), &cc);
-- 
1.8.4.5

[PATCH 35/97] mm/readahead.c: fix readahead failure for memoryless NUMA nodes and limit readahead pages

[Mel Gorman]

From: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>

commit 6d2be915e589b58cb11418cbe1f22ff90732b6ac upstream.

Currently max_sane_readahead() returns zero on the cpu whose NUMA node
has no local memory which leads to readahead failure.  Fix this
readahead failure by returning minimum of (requested pages, 512).  Users
running applications on a memory-less cpu which needs readahead such as
streaming application see considerable boost in the performance.

Result:

fadvise experiment with FADV_WILLNEED on a PPC machine having memoryless
CPU with 1GB testfile (12 iterations) yielded around 46.66% improvement.

fadvise experiment with FADV_WILLNEED on a x240 machine with 1GB
testfile 32GB* 4G RAM numa machine (12 iterations) showed no impact on
the normal NUMA cases w/ patch.

  Kernel       Avg  Stddev
  base      7.4975   3.92%
  patched   7.4174   3.26%

[Andrew: making return value PAGE_SIZE independent]
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Jan Kara <jack@suse.cz>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/readahead.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/readahead.c b/mm/readahead.c
index 5b637b5..e9c4a6a 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -237,14 +237,14 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
 	return ret;
 }
 
+#define MAX_READAHEAD   ((512*4096)/PAGE_CACHE_SIZE)
 /*
  * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a
  * sensible upper limit.
  */
 unsigned long max_sane_readahead(unsigned long nr)
 {
-	return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE)
-		+ node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2);
+	return min(nr, MAX_READAHEAD);
 }
 
 /*
-- 
1.8.4.5

[PATCH 36/97] mm: optimize put_mems_allowed() usage

[Mel Gorman]

commit d26914d11751b23ca2e8747725f2cae10c2f2c1b upstream.

Since put_mems_allowed() is strictly optional, its a seqcount retry, we
don't need to evaluate the function if the allocation was in fact
successful, saving a smp_rmb some loads and comparisons on some relative
fast-paths.

Since the naming, get/put_mems_allowed() does suggest a mandatory
pairing, rename the interface, as suggested by Mel, to resemble the
seqcount interface.

This gives us: read_mems_allowed_begin() and read_mems_allowed_retry(),
where it is important to note that the return value of the latter call
is inverted from its previous incarnation.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/cpuset.h | 27 ++++++++++++++-------------
 kernel/cpuset.c        |  2 +-
 mm/filemap.c           |  4 ++--
 mm/hugetlb.c           |  4 ++--
 mm/mempolicy.c         | 12 ++++++------
 mm/page_alloc.c        |  8 ++++----
 mm/slab.c              |  4 ++--
 mm/slub.c              | 16 +++++++---------
 8 files changed, 38 insertions(+), 39 deletions(-)

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index cc1b01c..6f30672 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -87,25 +87,26 @@ extern void rebuild_sched_domains(void);
 extern void cpuset_print_task_mems_allowed(struct task_struct *p);
 
 /*
- * get_mems_allowed is required when making decisions involving mems_allowed
- * such as during page allocation. mems_allowed can be updated in parallel
- * and depending on the new value an operation can fail potentially causing
- * process failure. A retry loop with get_mems_allowed and put_mems_allowed
- * prevents these artificial failures.
+ * read_mems_allowed_begin is required when making decisions involving
+ * mems_allowed such as during page allocation. mems_allowed can be updated in
+ * parallel and depending on the new value an operation can fail potentially
+ * causing process failure. A retry loop with read_mems_allowed_begin and
+ * read_mems_allowed_retry prevents these artificial failures.
  */
-static inline unsigned int get_mems_allowed(void)
+static inline unsigned int read_mems_allowed_begin(void)
 {
 	return read_seqcount_begin(&current->mems_allowed_seq);
 }
 
 /*
- * If this returns false, the operation that took place after get_mems_allowed
- * may have failed. It is up to the caller to retry the operation if
+ * If this returns true, the operation that took place after
+ * read_mems_allowed_begin may have failed artificially due to a concurrent
+ * update of mems_allowed. It is up to the caller to retry the operation if
  * appropriate.
  */
-static inline bool put_mems_allowed(unsigned int seq)
+static inline bool read_mems_allowed_retry(unsigned int seq)
 {
-	return !read_seqcount_retry(&current->mems_allowed_seq, seq);
+	return read_seqcount_retry(&current->mems_allowed_seq, seq);
 }
 
 static inline void set_mems_allowed(nodemask_t nodemask)
@@ -221,14 +222,14 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 {
 }
 
-static inline unsigned int get_mems_allowed(void)
+static inline unsigned int read_mems_allowed_begin(void)
 {
 	return 0;
 }
 
-static inline bool put_mems_allowed(unsigned int seq)
+static inline bool read_mems_allowed_retry(unsigned int seq)
 {
-	return true;
+	return false;
 }
 
 #endif /* !CONFIG_CPUSETS */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 0b29c52..15ae2b7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1022,7 +1022,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	task_lock(tsk);
 	/*
 	 * Determine if a loop is necessary if another thread is doing
-	 * get_mems_allowed().  If at least one node remains unchanged and
+	 * read_mems_allowed_begin().  If at least one node remains unchanged and
 	 * tsk does not have a mempolicy, then an empty nodemask will not be
 	 * possible when mems_allowed is larger than a word.
 	 */
diff --git a/mm/filemap.c b/mm/filemap.c
index ae4846f..df13a9b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -520,10 +520,10 @@ struct page *__page_cache_alloc(gfp_t gfp)
 	if (cpuset_do_page_mem_spread()) {
 		unsigned int cpuset_mems_cookie;
 		do {
-			cpuset_mems_cookie = get_mems_allowed();
+			cpuset_mems_cookie = read_mems_allowed_begin();
 			n = cpuset_mem_spread_node();
 			page = alloc_pages_exact_node(n, gfp, 0);
-		} while (!put_mems_allowed(cpuset_mems_cookie) && !page);
+		} while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
 
 		return page;
 	}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2814ca8..11e679b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -574,7 +574,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 		goto err;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 	zonelist = huge_zonelist(vma, address,
 					htlb_alloc_mask(h), &mpol, &nodemask);
 
@@ -596,7 +596,7 @@ retry_cpuset:
 	}
 
 	mpol_cond_put(mpol);
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return page;
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0437f35..0bf6476 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1873,7 +1873,7 @@ int node_random(const nodemask_t *maskp)
  * If the effective policy is 'BIND, returns a pointer to the mempolicy's
  * @nodemask for filtering the zonelist.
  *
- * Must be protected by get_mems_allowed()
+ * Must be protected by read_mems_allowed_begin()
  */
 struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
 				gfp_t gfp_flags, struct mempolicy **mpol,
@@ -2037,7 +2037,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 
 retry_cpuset:
 	pol = get_vma_policy(current, vma, addr);
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
@@ -2045,7 +2045,7 @@ retry_cpuset:
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
 		page = alloc_page_interleave(gfp, order, nid);
-		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 			goto retry_cpuset;
 
 		return page;
@@ -2055,7 +2055,7 @@ retry_cpuset:
 				      policy_nodemask(gfp, pol));
 	if (unlikely(mpol_needs_cond_ref(pol)))
 		__mpol_put(pol);
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return page;
 }
@@ -2089,7 +2089,7 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 		pol = &default_policy;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	/*
 	 * No reference counting needed for current->mempolicy
@@ -2102,7 +2102,7 @@ retry_cpuset:
 				policy_zonelist(gfp, pol, numa_node_id()),
 				policy_nodemask(gfp, pol));
 
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 
 	return page;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c34b582..74bf3e0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2711,7 +2711,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	/* The preferred zone is used for statistics later */
 	first_zones_zonelist(zonelist, high_zoneidx,
@@ -2766,7 +2766,7 @@ out:
 	 * the mask is being updated. If a page allocation is about to fail,
 	 * check if the cpuset changed during allocation and if so, retry.
 	 */
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 
 	memcg_kmem_commit_charge(page, memcg, order);
@@ -3034,9 +3034,9 @@ bool skip_free_areas_node(unsigned int flags, int nid)
 		goto out;
 
 	do {
-		cpuset_mems_cookie = get_mems_allowed();
+		cpuset_mems_cookie = read_mems_allowed_begin();
 		ret = !node_isset(nid, cpuset_current_mems_allowed);
-	} while (!put_mems_allowed(cpuset_mems_cookie));
+	} while (read_mems_allowed_retry(cpuset_mems_cookie));
 out:
 	return ret;
 }
diff --git a/mm/slab.c b/mm/slab.c
index 0b4ddaf..eb4078c 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3222,7 +3222,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 	zonelist = node_zonelist(slab_node(), flags);
 
 retry:
@@ -3278,7 +3278,7 @@ retry:
 		}
 	}
 
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj))
+	if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return obj;
 }
diff --git a/mm/slub.c b/mm/slub.c
index 5c1343a..a88d94c 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1635,7 +1635,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 		return NULL;
 
 	do {
-		cpuset_mems_cookie = get_mems_allowed();
+		cpuset_mems_cookie = read_mems_allowed_begin();
 		zonelist = node_zonelist(slab_node(), flags);
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 			struct kmem_cache_node *n;
@@ -1647,19 +1647,17 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 				object = get_partial_node(s, n, c, flags);
 				if (object) {
 					/*
-					 * Return the object even if
-					 * put_mems_allowed indicated that
-					 * the cpuset mems_allowed was
-					 * updated in parallel. It's a
-					 * harmless race between the alloc
-					 * and the cpuset update.
+					 * Don't check read_mems_allowed_retry()
+					 * here - if mems_allowed was updated in
+					 * parallel, that was a harmless race
+					 * between allocation and the cpuset
+					 * update
 					 */
-					put_mems_allowed(cpuset_mems_cookie);
 					return object;
 				}
 			}
 		}
-	} while (!put_mems_allowed(cpuset_mems_cookie));
+	} while (read_mems_allowed_retry(cpuset_mems_cookie));
 #endif
 	return NULL;
 }
-- 
1.8.4.5

[PATCH 37/97] mm/filemap.c: avoid always dirtying mapping->flags on O_DIRECT

[Mel Gorman]

From: Jens Axboe <axboe@fb.com>

commit 7fcbbaf18392f0b17c95e2f033c8ccf87eecde1d upstream.

In some testing I ran today (some fio jobs that spread over two nodes),
we end up spending 40% of the time in filemap_check_errors().  That
smells fishy.  Looking further, this is basically what happens:

blkdev_aio_read()
    generic_file_aio_read()
        filemap_write_and_wait_range()
            if (!mapping->nr_pages)
                filemap_check_errors()

and filemap_check_errors() always attempts two test_and_clear_bit() on
the mapping flags, thus dirtying it for every single invocation.  The
patch below tests each of these bits before clearing them, avoiding this
issue.  In my test case (4-socket box), performance went from 1.7M IOPS
to 4.0M IOPS.

Signed-off-by: Jens Axboe <axboe@fb.com>
Acked-by: Jeff Moyer <jmoyer@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/filemap.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index df13a9b..ed99e57 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -192,9 +192,11 @@ static int filemap_check_errors(struct address_space *mapping)
 {
 	int ret = 0;
 	/* Check for outstanding write errors */
-	if (test_and_clear_bit(AS_ENOSPC, &mapping->flags))
+	if (test_bit(AS_ENOSPC, &mapping->flags) &&
+	    test_and_clear_bit(AS_ENOSPC, &mapping->flags))
 		ret = -ENOSPC;
-	if (test_and_clear_bit(AS_EIO, &mapping->flags))
+	if (test_bit(AS_EIO, &mapping->flags) &&
+	    test_and_clear_bit(AS_EIO, &mapping->flags))
 		ret = -EIO;
 	return ret;
 }
-- 
1.8.4.5

[PATCH 38/97] mm: vmscan: respect NUMA policy mask when shrinking slab on direct reclaim

[Mel Gorman]

From: Vladimir Davydov <vdavydov@parallels.com>

commit 99120b772b52853f9a2b829a21dd44d9b20558f1 upstream.

When direct reclaim is executed by a process bound to a set of NUMA
nodes, we should scan only those nodes when possible, but currently we
will scan kmem from all online nodes even if the kmem shrinker is NUMA
aware.  That said, binding a process to a particular NUMA node won't
prevent it from shrinking inode/dentry caches from other nodes, which is
not good.  Fix this.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Glauber Costa <glommer@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/vmscan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index e36294b..b59d151 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2424,8 +2424,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			unsigned long lru_pages = 0;
 
 			nodes_clear(shrink->nodes_to_scan);
-			for_each_zone_zonelist(zone, z, zonelist,
-					gfp_zone(sc->gfp_mask)) {
+			for_each_zone_zonelist_nodemask(zone, z, zonelist,
+					gfp_zone(sc->gfp_mask), sc->nodemask) {
 				if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 					continue;
 
-- 
1.8.4.5

[PATCH 39/97] mm: vmscan: shrink_slab: rename max_pass -> freeable

[Mel Gorman]

From: Vladimir Davydov <vdavydov@parallels.com>

commit d5bc5fd3fcb7b8dfb431694a8c8052466504c10c upstream.

The name `max_pass' is misleading, because this variable actually keeps
the estimate number of freeable objects, not the maximal number of
objects we can scan in this pass, which can be twice that.  Rename it to
reflect its actual meaning.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/vmscan.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index b59d151..9de5a52 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -224,15 +224,15 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	unsigned long freed = 0;
 	unsigned long long delta;
 	long total_scan;
-	long max_pass;
+	long freeable;
 	long nr;
 	long new_nr;
 	int nid = shrinkctl->nid;
 	long batch_size = shrinker->batch ? shrinker->batch
 					  : SHRINK_BATCH;
 
-	max_pass = shrinker->count_objects(shrinker, shrinkctl);
-	if (max_pass == 0)
+	freeable = shrinker->count_objects(shrinker, shrinkctl);
+	if (freeable == 0)
 		return 0;
 
 	/*
@@ -244,14 +244,14 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 
 	total_scan = nr;
 	delta = (4 * nr_pages_scanned) / shrinker->seeks;
-	delta *= max_pass;
+	delta *= freeable;
 	do_div(delta, lru_pages + 1);
 	total_scan += delta;
 	if (total_scan < 0) {
 		printk(KERN_ERR
 		"shrink_slab: %pF negative objects to delete nr=%ld\n",
 		       shrinker->scan_objects, total_scan);
-		total_scan = max_pass;
+		total_scan = freeable;
 	}
 
 	/*
@@ -260,26 +260,26 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	 * shrinkers to return -1 all the time. This results in a large
 	 * nr being built up so when a shrink that can do some work
 	 * comes along it empties the entire cache due to nr >>>
-	 * max_pass.  This is bad for sustaining a working set in
+	 * freeable. This is bad for sustaining a working set in
 	 * memory.
 	 *
 	 * Hence only allow the shrinker to scan the entire cache when
 	 * a large delta change is calculated directly.
 	 */
-	if (delta < max_pass / 4)
-		total_scan = min(total_scan, max_pass / 2);
+	if (delta < freeable / 4)
+		total_scan = min(total_scan, freeable / 2);
 
 	/*
 	 * Avoid risking looping forever due to too large nr value:
 	 * never try to free more than twice the estimate number of
 	 * freeable entries.
 	 */
-	if (total_scan > max_pass * 2)
-		total_scan = max_pass * 2;
+	if (total_scan > freeable * 2)
+		total_scan = freeable * 2;
 
 	trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
 				nr_pages_scanned, lru_pages,
-				max_pass, delta, total_scan);
+				freeable, delta, total_scan);
 
 	/*
 	 * Normally, we should not scan less than batch_size objects in one
@@ -292,12 +292,12 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	 *
 	 * We detect the "tight on memory" situations by looking at the total
 	 * number of objects we want to scan (total_scan). If it is greater
-	 * than the total number of objects on slab (max_pass), we must be
+	 * than the total number of objects on slab (freeable), we must be
 	 * scanning at high prio and therefore should try to reclaim as much as
 	 * possible.
 	 */
 	while (total_scan >= batch_size ||
-	       total_scan >= max_pass) {
+	       total_scan >= freeable) {
 		unsigned long ret;
 		unsigned long nr_to_scan = min(batch_size, total_scan);
 
-- 
1.8.4.5

[PATCH 40/97] vmscan: reclaim_clean_pages_from_list() must use mod_zone_page_state()

[Mel Gorman]

From: Christoph Lameter <cl@linux.com>

commit 83da7510058736c09a14b9c17ec7d851940a4332 upstream.

Seems to be called with preemption enabled.  Therefore it must use
mod_zone_page_state instead.

Signed-off-by: Christoph Lameter <cl@linux.com>
Reported-by: Grygorii Strashko <grygorii.strashko@ti.com>
Tested-by: Grygorii Strashko <grygorii.strashko@ti.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Santosh Shilimkar <santosh.shilimkar@ti.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/vmscan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9de5a52..96cd5c4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1144,7 +1144,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 			TTU_UNMAP|TTU_IGNORE_ACCESS,
 			&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
 	list_splice(&clean_pages, page_list);
-	__mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
+	mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
 	return ret;
 }
 
-- 
1.8.4.5

[PATCH 41/97] mm: per-thread vma caching

[Mel Gorman]

From: Davidlohr Bueso <davidlohr@hp.com>

commit 615d6e8756c87149f2d4c1b93d471bca002bd849 upstream.

This patch is a continuation of efforts trying to optimize find_vma(),
avoiding potentially expensive rbtree walks to locate a vma upon faults.
The original approach (https://lkml.org/lkml/2013/11/1/410), where the
largest vma was also cached, ended up being too specific and random,
thus further comparison with other approaches were needed.  There are
two things to consider when dealing with this, the cache hit rate and
the latency of find_vma().  Improving the hit-rate does not necessarily
translate in finding the vma any faster, as the overhead of any fancy
caching schemes can be too high to consider.

We currently cache the last used vma for the whole address space, which
provides a nice optimization, reducing the total cycles in find_vma() by
up to 250%, for workloads with good locality.  On the other hand, this
simple scheme is pretty much useless for workloads with poor locality.
Analyzing ebizzy runs shows that, no matter how many threads are
running, the mmap_cache hit rate is less than 2%, and in many situations
below 1%.

The proposed approach is to replace this scheme with a small per-thread
cache, maximizing hit rates at a very low maintenance cost.
Invalidations are performed by simply bumping up a 32-bit sequence
number.  The only expensive operation is in the rare case of a seq
number overflow, where all caches that share the same address space are
flushed.  Upon a miss, the proposed replacement policy is based on the
page number that contains the virtual address in question.  Concretely,
the following results are seen on an 80 core, 8 socket x86-64 box:

1) System bootup: Most programs are single threaded, so the per-thread
   scheme does improve ~50% hit rate by just adding a few more slots to
   the cache.

+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline       | 50.61%   | 19.90            |
| patched        | 73.45%   | 13.58            |
+----------------+----------+------------------+

2) Kernel build: This one is already pretty good with the current
   approach as we're dealing with good locality.

+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline       | 75.28%   | 11.03            |
| patched        | 88.09%   | 9.31             |
+----------------+----------+------------------+

3) Oracle 11g Data Mining (4k pages): Similar to the kernel build workload.

+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline       | 70.66%   | 17.14            |
| patched        | 91.15%   | 12.57            |
+----------------+----------+------------------+

4) Ebizzy: There's a fair amount of variation from run to run, but this
   approach always shows nearly perfect hit rates, while baseline is just
   about non-existent.  The amounts of cycles can fluctuate between
   anywhere from ~60 to ~116 for the baseline scheme, but this approach
   reduces it considerably.  For instance, with 80 threads:

+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline       | 1.06%    | 91.54            |
| patched        | 99.97%   | 14.18            |
+----------------+----------+------------------+

[akpm@linux-foundation.org: fix nommu build, per Davidlohr]
[akpm@linux-foundation.org: document vmacache_valid() logic]
[akpm@linux-foundation.org: attempt to untangle header files]
[akpm@linux-foundation.org: add vmacache_find() BUG_ON]
[hughd@google.com: add vmacache_valid_mm() (from Oleg)]
[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: adjust and enhance comments]
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Michel Lespinasse <walken@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Tested-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 arch/unicore32/include/asm/mmu_context.h |   4 +-
 fs/exec.c                                |   5 +-
 fs/proc/task_mmu.c                       |   3 +-
 include/linux/mm_types.h                 |   4 +-
 include/linux/sched.h                    |   7 ++
 include/linux/vmacache.h                 |  38 +++++++++++
 kernel/debug/debug_core.c                |  14 +++-
 kernel/fork.c                            |   7 +-
 mm/Makefile                              |   2 +-
 mm/mmap.c                                |  55 ++++++++-------
 mm/nommu.c                               |  24 ++++---
 mm/vmacache.c                            | 112 +++++++++++++++++++++++++++++++
 12 files changed, 231 insertions(+), 44 deletions(-)
 create mode 100644 include/linux/vmacache.h
 create mode 100644 mm/vmacache.c

diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index fb5e4c6..ef470a7 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -14,6 +14,8 @@
 
 #include <linux/compiler.h>
 #include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
@@ -73,7 +75,7 @@ do { \
 		else \
 			mm->mmap = NULL; \
 		rb_erase(&high_vma->vm_rb, &mm->mm_rb); \
-		mm->mmap_cache = NULL; \
+		vmacache_invalidate(mm); \
 		mm->map_count--; \
 		remove_vma(high_vma); \
 	} \
diff --git a/fs/exec.c b/fs/exec.c
index 95eef54..26bb91b 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -26,6 +26,7 @@
 #include <linux/file.h>
 #include <linux/fdtable.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/stat.h>
 #include <linux/fcntl.h>
 #include <linux/swap.h>
@@ -818,7 +819,7 @@ EXPORT_SYMBOL(read_code);
 static int exec_mmap(struct mm_struct *mm)
 {
 	struct task_struct *tsk;
-	struct mm_struct * old_mm, *active_mm;
+	struct mm_struct *old_mm, *active_mm;
 
 	/* Notify parent that we're no longer interested in the old VM */
 	tsk = current;
@@ -844,6 +845,8 @@ static int exec_mmap(struct mm_struct *mm)
 	tsk->mm = mm;
 	tsk->active_mm = mm;
 	activate_mm(active_mm, mm);
+	tsk->mm->vmacache_seqnum = 0;
+	vmacache_flush(tsk);
 	task_unlock(tsk);
 	arch_pick_mmap_layout(mm);
 	if (old_mm) {
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ad4df86..7724fbd 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,4 +1,5 @@
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/hugetlb.h>
 #include <linux/huge_mm.h>
 #include <linux/mount.h>
@@ -159,7 +160,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 
 	/*
 	 * We remember last_addr rather than next_addr to hit with
-	 * mmap_cache most of the time. We have zero last_addr at
+	 * vmacache most of the time. We have zero last_addr at
 	 * the beginning and also after lseek. We will have -1 last_addr
 	 * after the end of the vmas.
 	 */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 8e082f1..b8131e7 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -324,9 +324,9 @@ struct mm_rss_stat {
 
 struct kioctx_table;
 struct mm_struct {
-	struct vm_area_struct * mmap;		/* list of VMAs */
+	struct vm_area_struct *mmap;		/* list of VMAs */
 	struct rb_root mm_rb;
-	struct vm_area_struct * mmap_cache;	/* last find_vma result */
+	u32 vmacache_seqnum;                   /* per-thread vmacache */
 #ifdef CONFIG_MMU
 	unsigned long (*get_unmapped_area) (struct file *filp,
 				unsigned long addr, unsigned long len,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0827bec..cb67b4e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -63,6 +63,10 @@ struct fs_struct;
 struct perf_event_context;
 struct blk_plug;
 
+#define VMACACHE_BITS 2
+#define VMACACHE_SIZE (1U << VMACACHE_BITS)
+#define VMACACHE_MASK (VMACACHE_SIZE - 1)
+
 /*
  * List of flags we want to share for kernel threads,
  * if only because they are not used by them anyway.
@@ -1093,6 +1097,9 @@ struct task_struct {
 #ifdef CONFIG_COMPAT_BRK
 	unsigned brk_randomized:1;
 #endif
+	/* per-thread vma caching */
+	u32 vmacache_seqnum;
+	struct vm_area_struct *vmacache[VMACACHE_SIZE];
 #if defined(SPLIT_RSS_COUNTING)
 	struct task_rss_stat	rss_stat;
 #endif
diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h
new file mode 100644
index 0000000..c3fa0fd4
--- /dev/null
+++ b/include/linux/vmacache.h
@@ -0,0 +1,38 @@
+#ifndef __LINUX_VMACACHE_H
+#define __LINUX_VMACACHE_H
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+
+/*
+ * Hash based on the page number. Provides a good hit rate for
+ * workloads with good locality and those with random accesses as well.
+ */
+#define VMACACHE_HASH(addr) ((addr >> PAGE_SHIFT) & VMACACHE_MASK)
+
+static inline void vmacache_flush(struct task_struct *tsk)
+{
+	memset(tsk->vmacache, 0, sizeof(tsk->vmacache));
+}
+
+extern void vmacache_flush_all(struct mm_struct *mm);
+extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma);
+extern struct vm_area_struct *vmacache_find(struct mm_struct *mm,
+						    unsigned long addr);
+
+#ifndef CONFIG_MMU
+extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
+						  unsigned long start,
+						  unsigned long end);
+#endif
+
+static inline void vmacache_invalidate(struct mm_struct *mm)
+{
+	mm->vmacache_seqnum++;
+
+	/* deal with overflows */
+	if (unlikely(mm->vmacache_seqnum == 0))
+		vmacache_flush_all(mm);
+}
+
+#endif /* __LINUX_VMACACHE_H */
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 0506d44..e911ec6 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -49,6 +49,7 @@
 #include <linux/pid.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/rcupdate.h>
 
 #include <asm/cacheflush.h>
@@ -224,10 +225,17 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
 	if (!CACHE_FLUSH_IS_SAFE)
 		return;
 
-	if (current->mm && current->mm->mmap_cache) {
-		flush_cache_range(current->mm->mmap_cache,
-				  addr, addr + BREAK_INSTR_SIZE);
+	if (current->mm) {
+		int i;
+
+		for (i = 0; i < VMACACHE_SIZE; i++) {
+			if (!current->vmacache[i])
+				continue;
+			flush_cache_range(current->vmacache[i],
+					  addr, addr + BREAK_INSTR_SIZE);
+		}
 	}
+
 	/* Force flush instruction cache if it was outside the mm */
 	flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 1439629..29a1b02 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -28,6 +28,8 @@
 #include <linux/mman.h>
 #include <linux/mmu_notifier.h>
 #include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
 #include <linux/cpu.h>
@@ -363,7 +365,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 
 	mm->locked_vm = 0;
 	mm->mmap = NULL;
-	mm->mmap_cache = NULL;
+	mm->vmacache_seqnum = 0;
 	mm->map_count = 0;
 	cpumask_clear(mm_cpumask(mm));
 	mm->mm_rb = RB_ROOT;
@@ -882,6 +884,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 	if (!oldmm)
 		return 0;
 
+	/* initialize the new vmacache entries */
+	vmacache_flush(tsk);
+
 	if (clone_flags & CLONE_VM) {
 		atomic_inc(&oldmm->mm_users);
 		mm = oldmm;
diff --git a/mm/Makefile b/mm/Makefile
index 305d10a..fb51bc6 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -16,7 +16,7 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
-			   compaction.o balloon_compaction.o \
+			   compaction.o balloon_compaction.o vmacache.o \
 			   interval_tree.o list_lru.o $(mmu-y)
 
 obj-y += init-mm.o
diff --git a/mm/mmap.c b/mm/mmap.c
index af99b9e..c1249cb 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/backing-dev.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/shm.h>
 #include <linux/mman.h>
 #include <linux/pagemap.h>
@@ -682,8 +683,9 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
 	prev->vm_next = next = vma->vm_next;
 	if (next)
 		next->vm_prev = prev;
-	if (mm->mmap_cache == vma)
-		mm->mmap_cache = prev;
+
+	/* Kill the cache */
+	vmacache_invalidate(mm);
 }
 
 /*
@@ -1980,34 +1982,33 @@ EXPORT_SYMBOL(get_unmapped_area);
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
 struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 {
-	struct vm_area_struct *vma = NULL;
+	struct rb_node *rb_node;
+	struct vm_area_struct *vma;
 
 	/* Check the cache first. */
-	/* (Cache hit rate is typically around 35%.) */
-	vma = ACCESS_ONCE(mm->mmap_cache);
-	if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
-		struct rb_node *rb_node;
+	vma = vmacache_find(mm, addr);
+	if (likely(vma))
+		return vma;
 
-		rb_node = mm->mm_rb.rb_node;
-		vma = NULL;
+	rb_node = mm->mm_rb.rb_node;
+	vma = NULL;
 
-		while (rb_node) {
-			struct vm_area_struct *vma_tmp;
-
-			vma_tmp = rb_entry(rb_node,
-					   struct vm_area_struct, vm_rb);
-
-			if (vma_tmp->vm_end > addr) {
-				vma = vma_tmp;
-				if (vma_tmp->vm_start <= addr)
-					break;
-				rb_node = rb_node->rb_left;
-			} else
-				rb_node = rb_node->rb_right;
-		}
-		if (vma)
-			mm->mmap_cache = vma;
+	while (rb_node) {
+		struct vm_area_struct *tmp;
+
+		tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb);
+
+		if (tmp->vm_end > addr) {
+			vma = tmp;
+			if (tmp->vm_start <= addr)
+				break;
+			rb_node = rb_node->rb_left;
+		} else
+			rb_node = rb_node->rb_right;
 	}
+
+	if (vma)
+		vmacache_update(addr, vma);
 	return vma;
 }
 
@@ -2379,7 +2380,9 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 	} else
 		mm->highest_vm_end = prev ? prev->vm_end : 0;
 	tail_vma->vm_next = NULL;
-	mm->mmap_cache = NULL;		/* Kill the cache. */
+
+	/* Kill the cache */
+	vmacache_invalidate(mm);
 }
 
 /*
diff --git a/mm/nommu.c b/mm/nommu.c
index ecd1f15..1221d2b 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -15,6 +15,7 @@
 
 #include <linux/export.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/mman.h>
 #include <linux/swap.h>
 #include <linux/file.h>
@@ -767,16 +768,23 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
  */
 static void delete_vma_from_mm(struct vm_area_struct *vma)
 {
+	int i;
 	struct address_space *mapping;
 	struct mm_struct *mm = vma->vm_mm;
+	struct task_struct *curr = current;
 
 	kenter("%p", vma);
 
 	protect_vma(vma, 0);
 
 	mm->map_count--;
-	if (mm->mmap_cache == vma)
-		mm->mmap_cache = NULL;
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		/* if the vma is cached, invalidate the entire cache */
+		if (curr->vmacache[i] == vma) {
+			vmacache_invalidate(curr->mm);
+			break;
+		}
+	}
 
 	/* remove the VMA from the mapping */
 	if (vma->vm_file) {
@@ -824,8 +832,8 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 	struct vm_area_struct *vma;
 
 	/* check the cache first */
-	vma = ACCESS_ONCE(mm->mmap_cache);
-	if (vma && vma->vm_start <= addr && vma->vm_end > addr)
+	vma = vmacache_find(mm, addr);
+	if (likely(vma))
 		return vma;
 
 	/* trawl the list (there may be multiple mappings in which addr
@@ -834,7 +842,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 		if (vma->vm_start > addr)
 			return NULL;
 		if (vma->vm_end > addr) {
-			mm->mmap_cache = vma;
+			vmacache_update(addr, vma);
 			return vma;
 		}
 	}
@@ -873,8 +881,8 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
 	unsigned long end = addr + len;
 
 	/* check the cache first */
-	vma = mm->mmap_cache;
-	if (vma && vma->vm_start == addr && vma->vm_end == end)
+	vma = vmacache_find_exact(mm, addr, end);
+	if (vma)
 		return vma;
 
 	/* trawl the list (there may be multiple mappings in which addr
@@ -885,7 +893,7 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
 		if (vma->vm_start > addr)
 			return NULL;
 		if (vma->vm_end == end) {
-			mm->mmap_cache = vma;
+			vmacache_update(addr, vma);
 			return vma;
 		}
 	}
diff --git a/mm/vmacache.c b/mm/vmacache.c
new file mode 100644
index 0000000..d4224b3
--- /dev/null
+++ b/mm/vmacache.c
@@ -0,0 +1,112 @@
+/*
+ * Copyright (C) 2014 Davidlohr Bueso.
+ */
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
+
+/*
+ * Flush vma caches for threads that share a given mm.
+ *
+ * The operation is safe because the caller holds the mmap_sem
+ * exclusively and other threads accessing the vma cache will
+ * have mmap_sem held at least for read, so no extra locking
+ * is required to maintain the vma cache.
+ */
+void vmacache_flush_all(struct mm_struct *mm)
+{
+	struct task_struct *g, *p;
+
+	rcu_read_lock();
+	for_each_process_thread(g, p) {
+		/*
+		 * Only flush the vmacache pointers as the
+		 * mm seqnum is already set and curr's will
+		 * be set upon invalidation when the next
+		 * lookup is done.
+		 */
+		if (mm == p->mm)
+			vmacache_flush(p);
+	}
+	rcu_read_unlock();
+}
+
+/*
+ * This task may be accessing a foreign mm via (for example)
+ * get_user_pages()->find_vma().  The vmacache is task-local and this
+ * task's vmacache pertains to a different mm (ie, its own).  There is
+ * nothing we can do here.
+ *
+ * Also handle the case where a kernel thread has adopted this mm via use_mm().
+ * That kernel thread's vmacache is not applicable to this mm.
+ */
+static bool vmacache_valid_mm(struct mm_struct *mm)
+{
+	return current->mm == mm && !(current->flags & PF_KTHREAD);
+}
+
+void vmacache_update(unsigned long addr, struct vm_area_struct *newvma)
+{
+	if (vmacache_valid_mm(newvma->vm_mm))
+		current->vmacache[VMACACHE_HASH(addr)] = newvma;
+}
+
+static bool vmacache_valid(struct mm_struct *mm)
+{
+	struct task_struct *curr;
+
+	if (!vmacache_valid_mm(mm))
+		return false;
+
+	curr = current;
+	if (mm->vmacache_seqnum != curr->vmacache_seqnum) {
+		/*
+		 * First attempt will always be invalid, initialize
+		 * the new cache for this task here.
+		 */
+		curr->vmacache_seqnum = mm->vmacache_seqnum;
+		vmacache_flush(curr);
+		return false;
+	}
+	return true;
+}
+
+struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr)
+{
+	int i;
+
+	if (!vmacache_valid(mm))
+		return NULL;
+
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		struct vm_area_struct *vma = current->vmacache[i];
+
+		if (vma && vma->vm_start <= addr && vma->vm_end > addr) {
+			BUG_ON(vma->vm_mm != mm);
+			return vma;
+		}
+	}
+
+	return NULL;
+}
+
+#ifndef CONFIG_MMU
+struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
+					   unsigned long start,
+					   unsigned long end)
+{
+	int i;
+
+	if (!vmacache_valid(mm))
+		return NULL;
+
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		struct vm_area_struct *vma = current->vmacache[i];
+
+		if (vma && vma->vm_start == start && vma->vm_end == end)
+			return vma;
+	}
+
+	return NULL;
+}
+#endif
-- 
1.8.4.5

[PATCH 42/97] mm: don't pointlessly use BUG_ON() for sanity check

[Mel Gorman]

From: Linus Torvalds <torvalds@linux-foundation.org>

commit 50f5aa8a9b248fa4262cf379863ec9a531b49737 upstream.

BUG_ON() is a big hammer, and should be used _only_ if there is some
major corruption that you cannot possibly recover from, making it
imperative that the current process (and possibly the whole machine) be
terminated with extreme prejudice.

The trivial sanity check in the vmacache code is *not* such a fatal
error.  Recovering from it is absolutely trivial, and using BUG_ON()
just makes it harder to debug for no actual advantage.

To make matters worse, the placement of the BUG_ON() (only if the range
check matched) actually makes it harder to hit the sanity check to begin
with, so _if_ there is a bug (and we just got a report from Srivatsa
Bhat that this can indeed trigger), it is harder to debug not just
because the machine is possibly dead, but because we don't have better
coverage.

BUG_ON() must *die*.  Maybe we should add a checkpatch warning for it,
because it is simply just about the worst thing you can ever do if you
hit some "this cannot happen" situation.

Reported-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/vmacache.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/mm/vmacache.c b/mm/vmacache.c
index d4224b3..1037a3ba 100644
--- a/mm/vmacache.c
+++ b/mm/vmacache.c
@@ -81,10 +81,12 @@ struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr)
 	for (i = 0; i < VMACACHE_SIZE; i++) {
 		struct vm_area_struct *vma = current->vmacache[i];
 
-		if (vma && vma->vm_start <= addr && vma->vm_end > addr) {
-			BUG_ON(vma->vm_mm != mm);
+		if (!vma)
+			continue;
+		if (WARN_ON_ONCE(vma->vm_mm != mm))
+			break;
+		if (vma->vm_start <= addr && vma->vm_end > addr)
 			return vma;
-		}
 	}
 
 	return NULL;
-- 
1.8.4.5

[PATCH 43/97] lib: radix-tree: add radix_tree_delete_item()

[Mel Gorman]

From: Johannes Weiner <hannes@cmpxchg.org>

commit 53c59f262d747ea82e7414774c59a489501186a0 upstream.

Provide a function that does not just delete an entry at a given index,
but also allows passing in an expected item.  Delete only if that item
is still located at the specified index.

This is handy when lockless tree traversals want to delete entries as
well because they don't have to do an second, locked lookup to verify
the slot has not changed under them before deleting the entry.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/radix-tree.h |  1 +
 lib/radix-tree.c           | 31 +++++++++++++++++++++++++++----
 2 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 4039407..1bf0a9c 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -219,6 +219,7 @@ static inline void radix_tree_replace_slot(void **pslot, void *item)
 int radix_tree_insert(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_lookup(struct radix_tree_root *, unsigned long);
 void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long);
+void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_delete(struct radix_tree_root *, unsigned long);
 unsigned int
 radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 7811ed3..f442e32 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1335,15 +1335,18 @@ static inline void radix_tree_shrink(struct radix_tree_root *root)
 }
 
 /**
- *	radix_tree_delete    -    delete an item from a radix tree
+ *	radix_tree_delete_item    -    delete an item from a radix tree
  *	@root:		radix tree root
  *	@index:		index key
+ *	@item:		expected item
  *
- *	Remove the item at @index from the radix tree rooted at @root.
+ *	Remove @item at @index from the radix tree rooted at @root.
  *
- *	Returns the address of the deleted item, or NULL if it was not present.
+ *	Returns the address of the deleted item, or NULL if it was not present
+ *	or the entry at the given @index was not @item.
  */
-void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
+void *radix_tree_delete_item(struct radix_tree_root *root,
+			     unsigned long index, void *item)
 {
 	struct radix_tree_node *node = NULL;
 	struct radix_tree_node *slot = NULL;
@@ -1378,6 +1381,11 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 	if (slot == NULL)
 		goto out;
 
+	if (item && slot != item) {
+		slot = NULL;
+		goto out;
+	}
+
 	/*
 	 * Clear all tags associated with the item to be deleted.
 	 * This way of doing it would be inefficient, but seldom is any set.
@@ -1422,6 +1430,21 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 out:
 	return slot;
 }
+EXPORT_SYMBOL(radix_tree_delete_item);
+
+/**
+ *	radix_tree_delete    -    delete an item from a radix tree
+ *	@root:		radix tree root
+ *	@index:		index key
+ *
+ *	Remove the item at @index from the radix tree rooted at @root.
+ *
+ *	Returns the address of the deleted item, or NULL if it was not present.
+ */
+void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
+{
+	return radix_tree_delete_item(root, index, NULL);
+}
 EXPORT_SYMBOL(radix_tree_delete);
 
 /**
-- 
1.8.4.5

[PATCH 44/97] mm: shmem: save one radix tree lookup when truncating swapped pages

[Mel Gorman]

From: Johannes Weiner <hannes@cmpxchg.org>

commit 6dbaf22ce1f1dfba33313198eb5bd989ae76dd87 upstream.

Page cache radix tree slots are usually stabilized by the page lock, but
shmem's swap cookies have no such thing.  Because the overall truncation
loop is lockless, the swap entry is currently confirmed by a tree lookup
and then deleted by another tree lookup under the same tree lock region.

Use radix_tree_delete_item() instead, which does the verification and
deletion with only one lookup.  This also allows removing the
delete-only special case from shmem_radix_tree_replace().

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/shmem.c | 25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 0da81aa..1460b20 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -243,19 +243,17 @@ static int shmem_radix_tree_replace(struct address_space *mapping,
 			pgoff_t index, void *expected, void *replacement)
 {
 	void **pslot;
-	void *item = NULL;
+	void *item;
 
 	VM_BUG_ON(!expected);
+	VM_BUG_ON(!replacement);
 	pslot = radix_tree_lookup_slot(&mapping->page_tree, index);
-	if (pslot)
-		item = radix_tree_deref_slot_protected(pslot,
-							&mapping->tree_lock);
+	if (!pslot)
+		return -ENOENT;
+	item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock);
 	if (item != expected)
 		return -ENOENT;
-	if (replacement)
-		radix_tree_replace_slot(pslot, replacement);
-	else
-		radix_tree_delete(&mapping->page_tree, index);
+	radix_tree_replace_slot(pslot, replacement);
 	return 0;
 }
 
@@ -387,14 +385,15 @@ export:
 static int shmem_free_swap(struct address_space *mapping,
 			   pgoff_t index, void *radswap)
 {
-	int error;
+	void *old;
 
 	spin_lock_irq(&mapping->tree_lock);
-	error = shmem_radix_tree_replace(mapping, index, radswap, NULL);
+	old = radix_tree_delete_item(&mapping->page_tree, index, radswap);
 	spin_unlock_irq(&mapping->tree_lock);
-	if (!error)
-		free_swap_and_cache(radix_to_swp_entry(radswap));
-	return error;
+	if (old != radswap)
+		return -ENOENT;
+	free_swap_and_cache(radix_to_swp_entry(radswap));
+	return 0;
 }
 
 /*
-- 
1.8.4.5

[PATCH 45/97] mm: filemap: move radix tree hole searching here

[Mel Gorman]

From: Johannes Weiner <hannes@cmpxchg.org>

commit e7b563bb2a6f4d974208da46200784b9c5b5a47e upstream.

The radix tree hole searching code is only used for page cache, for
example the readahead code trying to get a a picture of the area
surrounding a fault.

It sufficed to rely on the radix tree definition of holes, which is
"empty tree slot".  But this is about to change, though, as shadow page
descriptors will be stored in the page cache after the actual pages get
evicted from memory.

Move the functions over to mm/filemap.c and make them native page cache
operations, where they can later be adapted to handle the new definition
of "page cache hole".

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 fs/nfs/blocklayout/blocklayout.c |  2 +-
 include/linux/pagemap.h          |  5 +++
 include/linux/radix-tree.h       |  4 ---
 lib/radix-tree.c                 | 75 ---------------------------------------
 mm/filemap.c                     | 76 ++++++++++++++++++++++++++++++++++++++++
 mm/readahead.c                   |  4 +--
 6 files changed, 84 insertions(+), 82 deletions(-)

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index e242bbf..fdb74cb 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -1220,7 +1220,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
 	end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
 	if (end != NFS_I(inode)->npages) {
 		rcu_read_lock();
-		end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX);
+		end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX);
 		rcu_read_unlock();
 	}
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e3dea75..c73130c 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -243,6 +243,11 @@ static inline struct page *page_cache_alloc_readahead(struct address_space *x)
 
 typedef int filler_t(void *, struct page *);
 
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan);
+pgoff_t page_cache_prev_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan);
+
 extern struct page * find_get_page(struct address_space *mapping,
 				pgoff_t index);
 extern struct page * find_lock_page(struct address_space *mapping,
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 1bf0a9c..e8be53e 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -227,10 +227,6 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root,
 			void ***results, unsigned long *indices,
 			unsigned long first_index, unsigned int max_items);
-unsigned long radix_tree_next_hole(struct radix_tree_root *root,
-				unsigned long index, unsigned long max_scan);
-unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
-				unsigned long index, unsigned long max_scan);
 int radix_tree_preload(gfp_t gfp_mask);
 int radix_tree_maybe_preload(gfp_t gfp_mask);
 void radix_tree_init(void);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index f442e32..e8adb5d 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -946,81 +946,6 @@ next:
 }
 EXPORT_SYMBOL(radix_tree_range_tag_if_tagged);
 
-
-/**
- *	radix_tree_next_hole    -    find the next hole (not-present entry)
- *	@root:		tree root
- *	@index:		index key
- *	@max_scan:	maximum range to search
- *
- *	Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the lowest
- *	indexed hole.
- *
- *	Returns: the index of the hole if found, otherwise returns an index
- *	outside of the set specified (in which case 'return - index >= max_scan'
- *	will be true). In rare cases of index wrap-around, 0 will be returned.
- *
- *	radix_tree_next_hole may be called under rcu_read_lock. However, like
- *	radix_tree_gang_lookup, this will not atomically search a snapshot of
- *	the tree at a single point in time. For example, if a hole is created
- *	at index 5, then subsequently a hole is created at index 10,
- *	radix_tree_next_hole covering both indexes may return 10 if called
- *	under rcu_read_lock.
- */
-unsigned long radix_tree_next_hole(struct radix_tree_root *root,
-				unsigned long index, unsigned long max_scan)
-{
-	unsigned long i;
-
-	for (i = 0; i < max_scan; i++) {
-		if (!radix_tree_lookup(root, index))
-			break;
-		index++;
-		if (index == 0)
-			break;
-	}
-
-	return index;
-}
-EXPORT_SYMBOL(radix_tree_next_hole);
-
-/**
- *	radix_tree_prev_hole    -    find the prev hole (not-present entry)
- *	@root:		tree root
- *	@index:		index key
- *	@max_scan:	maximum range to search
- *
- *	Search backwards in the range [max(index-max_scan+1, 0), index]
- *	for the first hole.
- *
- *	Returns: the index of the hole if found, otherwise returns an index
- *	outside of the set specified (in which case 'index - return >= max_scan'
- *	will be true). In rare cases of wrap-around, ULONG_MAX will be returned.
- *
- *	radix_tree_next_hole may be called under rcu_read_lock. However, like
- *	radix_tree_gang_lookup, this will not atomically search a snapshot of
- *	the tree at a single point in time. For example, if a hole is created
- *	at index 10, then subsequently a hole is created at index 5,
- *	radix_tree_prev_hole covering both indexes may return 5 if called under
- *	rcu_read_lock.
- */
-unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
-				   unsigned long index, unsigned long max_scan)
-{
-	unsigned long i;
-
-	for (i = 0; i < max_scan; i++) {
-		if (!radix_tree_lookup(root, index))
-			break;
-		index--;
-		if (index == ULONG_MAX)
-			break;
-	}
-
-	return index;
-}
-EXPORT_SYMBOL(radix_tree_prev_hole);
-
 /**
  *	radix_tree_gang_lookup - perform multiple lookup on a radix tree
  *	@root:		radix tree root
diff --git a/mm/filemap.c b/mm/filemap.c
index ed99e57..a47d0a7 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -688,6 +688,82 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 }
 
 /**
+ * page_cache_next_hole - find the next hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
+ * lowest indexed hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'return - index >=
+ * max_scan' will be true). In rare cases of index wrap-around, 0 will
+ * be returned.
+ *
+ * page_cache_next_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 5, then subsequently a hole is created at
+ * index 10, page_cache_next_hole covering both indexes may return 10
+ * if called under rcu_read_lock.
+ */
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		if (!radix_tree_lookup(&mapping->page_tree, index))
+			break;
+		index++;
+		if (index == 0)
+			break;
+	}
+
+	return index;
+}
+EXPORT_SYMBOL(page_cache_next_hole);
+
+/**
+ * page_cache_prev_hole - find the prev hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search backwards in the range [max(index-max_scan+1, 0), index] for
+ * the first hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'index - return >=
+ * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX
+ * will be returned.
+ *
+ * page_cache_prev_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 10, then subsequently a hole is created at
+ * index 5, page_cache_prev_hole covering both indexes may return 5 if
+ * called under rcu_read_lock.
+ */
+pgoff_t page_cache_prev_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		if (!radix_tree_lookup(&mapping->page_tree, index))
+			break;
+		index--;
+		if (index == ULONG_MAX)
+			break;
+	}
+
+	return index;
+}
+EXPORT_SYMBOL(page_cache_prev_hole);
+
+/**
  * find_get_page - find and get a page reference
  * @mapping: the address_space to search
  * @offset: the page index
diff --git a/mm/readahead.c b/mm/readahead.c
index e9c4a6a..6db5d56 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -351,7 +351,7 @@ static pgoff_t count_history_pages(struct address_space *mapping,
 	pgoff_t head;
 
 	rcu_read_lock();
-	head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max);
+	head = page_cache_prev_hole(mapping, offset - 1, max);
 	rcu_read_unlock();
 
 	return offset - 1 - head;
@@ -431,7 +431,7 @@ ondemand_readahead(struct address_space *mapping,
 		pgoff_t start;
 
 		rcu_read_lock();
-		start = radix_tree_next_hole(&mapping->page_tree, offset+1,max);
+		start = page_cache_next_hole(mapping, offset + 1, max);
 		rcu_read_unlock();
 
 		if (!start || start - offset > max)
-- 
1.8.4.5

[PATCH 46/97] mm + fs: prepare for non-page entries in page cache radix trees

[Mel Gorman]

From: Johannes Weiner <hannes@cmpxchg.org>

commit 0cd6144aadd2afd19d1aca880153530c52957604 upstream.

shmem mappings already contain exceptional entries where swap slot
information is remembered.

To be able to store eviction information for regular page cache, prepare
every site dealing with the radix trees directly to handle entries other
than pages.

The common lookup functions will filter out non-page entries and return
NULL for page cache holes, just as before.  But provide a raw version of
the API which returns non-page entries as well, and switch shmem over to
use it.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 fs/btrfs/compression.c   |   2 +-
 include/linux/mm.h       |   8 ++
 include/linux/pagemap.h  |  15 ++--
 include/linux/pagevec.h  |   5 ++
 include/linux/shmem_fs.h |   1 +
 mm/filemap.c             | 202 +++++++++++++++++++++++++++++++++++++++++------
 mm/mincore.c             |  20 +++--
 mm/readahead.c           |   2 +-
 mm/shmem.c               |  97 +++++------------------
 mm/swap.c                |  51 ++++++++++++
 mm/truncate.c            |  74 ++++++++++++++---
 11 files changed, 348 insertions(+), 129 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 6e9ff8f..6357298 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -474,7 +474,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->page_tree, pg_index);
 		rcu_read_unlock();
-		if (page) {
+		if (page && !radix_tree_exceptional_entry(page)) {
 			misses++;
 			if (misses > 4)
 				break;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0737343..96fc7dd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -919,6 +919,14 @@ extern void show_free_areas(unsigned int flags);
 extern bool skip_free_areas_node(unsigned int flags, int nid);
 
 int shmem_zero_setup(struct vm_area_struct *);
+#ifdef CONFIG_SHMEM
+bool shmem_mapping(struct address_space *mapping);
+#else
+static inline bool shmem_mapping(struct address_space *mapping)
+{
+	return false;
+}
+#endif
 
 extern int can_do_mlock(void);
 extern int user_shm_lock(size_t, struct user_struct *);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c73130c..76aaeaa 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -248,12 +248,15 @@ pgoff_t page_cache_next_hole(struct address_space *mapping,
 pgoff_t page_cache_prev_hole(struct address_space *mapping,
 			     pgoff_t index, unsigned long max_scan);
 
-extern struct page * find_get_page(struct address_space *mapping,
-				pgoff_t index);
-extern struct page * find_lock_page(struct address_space *mapping,
-				pgoff_t index);
-extern struct page * find_or_create_page(struct address_space *mapping,
-				pgoff_t index, gfp_t gfp_mask);
+struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
+struct page *find_get_page(struct address_space *mapping, pgoff_t offset);
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
+struct page *find_lock_page(struct address_space *mapping, pgoff_t offset);
+struct page *find_or_create_page(struct address_space *mapping, pgoff_t index,
+				 gfp_t gfp_mask);
+unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
+			  unsigned int nr_entries, struct page **entries,
+			  pgoff_t *indices);
 unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
 			unsigned int nr_pages, struct page **pages);
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index e4dbfab3..b45d391 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -22,6 +22,11 @@ struct pagevec {
 
 void __pagevec_release(struct pagevec *pvec);
 void __pagevec_lru_add(struct pagevec *pvec);
+unsigned pagevec_lookup_entries(struct pagevec *pvec,
+				struct address_space *mapping,
+				pgoff_t start, unsigned nr_entries,
+				pgoff_t *indices);
+void pagevec_remove_exceptionals(struct pagevec *pvec);
 unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
 		pgoff_t start, unsigned nr_pages);
 unsigned pagevec_lookup_tag(struct pagevec *pvec,
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 30aa0dc..deb4960 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -49,6 +49,7 @@ extern struct file *shmem_file_setup(const char *name,
 					loff_t size, unsigned long flags);
 extern int shmem_zero_setup(struct vm_area_struct *);
 extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
+extern bool shmem_mapping(struct address_space *mapping);
 extern void shmem_unlock_mapping(struct address_space *mapping);
 extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 					pgoff_t index, gfp_t gfp_mask);
diff --git a/mm/filemap.c b/mm/filemap.c
index a47d0a7..5d57a78 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -448,6 +448,29 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
+static int page_cache_tree_insert(struct address_space *mapping,
+				  struct page *page)
+{
+	void **slot;
+	int error;
+
+	slot = radix_tree_lookup_slot(&mapping->page_tree, page->index);
+	if (slot) {
+		void *p;
+
+		p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+		if (!radix_tree_exceptional_entry(p))
+			return -EEXIST;
+		radix_tree_replace_slot(slot, page);
+		mapping->nrpages++;
+		return 0;
+	}
+	error = radix_tree_insert(&mapping->page_tree, page->index, page);
+	if (!error)
+		mapping->nrpages++;
+	return error;
+}
+
 /**
  * add_to_page_cache_locked - add a locked page to the pagecache
  * @page:	page to add
@@ -482,11 +505,10 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 	page->index = offset;
 
 	spin_lock_irq(&mapping->tree_lock);
-	error = radix_tree_insert(&mapping->page_tree, offset, page);
+	error = page_cache_tree_insert(mapping, page);
 	radix_tree_preload_end();
 	if (unlikely(error))
 		goto err_insert;
-	mapping->nrpages++;
 	__inc_zone_page_state(page, NR_FILE_PAGES);
 	spin_unlock_irq(&mapping->tree_lock);
 	trace_mm_filemap_add_to_page_cache(page);
@@ -714,7 +736,10 @@ pgoff_t page_cache_next_hole(struct address_space *mapping,
 	unsigned long i;
 
 	for (i = 0; i < max_scan; i++) {
-		if (!radix_tree_lookup(&mapping->page_tree, index))
+		struct page *page;
+
+		page = radix_tree_lookup(&mapping->page_tree, index);
+		if (!page || radix_tree_exceptional_entry(page))
 			break;
 		index++;
 		if (index == 0)
@@ -752,7 +777,10 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping,
 	unsigned long i;
 
 	for (i = 0; i < max_scan; i++) {
-		if (!radix_tree_lookup(&mapping->page_tree, index))
+		struct page *page;
+
+		page = radix_tree_lookup(&mapping->page_tree, index);
+		if (!page || radix_tree_exceptional_entry(page))
 			break;
 		index--;
 		if (index == ULONG_MAX)
@@ -764,14 +792,19 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping,
 EXPORT_SYMBOL(page_cache_prev_hole);
 
 /**
- * find_get_page - find and get a page reference
+ * find_get_entry - find and get a page cache entry
  * @mapping: the address_space to search
- * @offset: the page index
+ * @offset: the page cache index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned with an increased refcount.
  *
- * Is there a pagecache struct page at the given (mapping, offset) tuple?
- * If yes, increment its refcount and return it; if no, return NULL.
+ * If the slot holds a shadow entry of a previously evicted page, it
+ * is returned.
+ *
+ * Otherwise, %NULL is returned.
  */
-struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
 {
 	void **pagep;
 	struct page *page;
@@ -812,24 +845,50 @@ out:
 
 	return page;
 }
-EXPORT_SYMBOL(find_get_page);
+EXPORT_SYMBOL(find_get_entry);
 
 /**
- * find_lock_page - locate, pin and lock a pagecache page
+ * find_get_page - find and get a page reference
  * @mapping: the address_space to search
  * @offset: the page index
  *
- * Locates the desired pagecache page, locks it, increments its reference
- * count and returns its address.
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned with an increased refcount.
  *
- * Returns zero if the page was not present. find_lock_page() may sleep.
+ * Otherwise, %NULL is returned.
  */
-struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+{
+	struct page *page = find_get_entry(mapping, offset);
+
+	if (radix_tree_exceptional_entry(page))
+		page = NULL;
+	return page;
+}
+EXPORT_SYMBOL(find_get_page);
+
+/**
+ * find_lock_entry - locate, pin and lock a page cache entry
+ * @mapping: the address_space to search
+ * @offset: the page cache index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the slot holds a shadow entry of a previously evicted page, it
+ * is returned.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_entry() may sleep.
+ */
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
 {
 	struct page *page;
 
 repeat:
-	page = find_get_page(mapping, offset);
+	page = find_get_entry(mapping, offset);
 	if (page && !radix_tree_exception(page)) {
 		lock_page(page);
 		/* Has the page been truncated? */
@@ -842,6 +901,29 @@ repeat:
 	}
 	return page;
 }
+EXPORT_SYMBOL(find_lock_entry);
+
+/**
+ * find_lock_page - locate, pin and lock a pagecache page
+ * @mapping: the address_space to search
+ * @offset: the page index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_page() may sleep.
+ */
+struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
+{
+	struct page *page = find_lock_entry(mapping, offset);
+
+	if (radix_tree_exceptional_entry(page))
+		page = NULL;
+	return page;
+}
 EXPORT_SYMBOL(find_lock_page);
 
 /**
@@ -850,16 +932,18 @@ EXPORT_SYMBOL(find_lock_page);
  * @index: the page's index into the mapping
  * @gfp_mask: page allocation mode
  *
- * Locates a page in the pagecache.  If the page is not present, a new page
- * is allocated using @gfp_mask and is added to the pagecache and to the VM's
- * LRU list.  The returned page is locked and has its reference count
- * incremented.
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the page is not present, a new page is allocated using @gfp_mask
+ * and added to the page cache and the VM's LRU list.  The page is
+ * returned locked and with an increased refcount.
  *
- * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic
- * allocation!
+ * On memory exhaustion, %NULL is returned.
  *
- * find_or_create_page() returns the desired page's address, or zero on
- * memory exhaustion.
+ * find_or_create_page() may sleep, even if @gfp_flags specifies an
+ * atomic allocation!
  */
 struct page *find_or_create_page(struct address_space *mapping,
 		pgoff_t index, gfp_t gfp_mask)
@@ -892,6 +976,76 @@ repeat:
 EXPORT_SYMBOL(find_or_create_page);
 
 /**
+ * find_get_entries - gang pagecache lookup
+ * @mapping:	The address_space to search
+ * @start:	The starting page cache index
+ * @nr_entries:	The maximum number of entries
+ * @entries:	Where the resulting entries are placed
+ * @indices:	The cache indices corresponding to the entries in @entries
+ *
+ * find_get_entries() will search for and return a group of up to
+ * @nr_entries entries in the mapping.  The entries are placed at
+ * @entries.  find_get_entries() takes a reference against any actual
+ * pages it returns.
+ *
+ * The search returns a group of mapping-contiguous page cache entries
+ * with ascending indexes.  There may be holes in the indices due to
+ * not-present pages.
+ *
+ * Any shadow entries of evicted pages are included in the returned
+ * array.
+ *
+ * find_get_entries() returns the number of pages and shadow entries
+ * which were found.
+ */
+unsigned find_get_entries(struct address_space *mapping,
+			  pgoff_t start, unsigned int nr_entries,
+			  struct page **entries, pgoff_t *indices)
+{
+	void **slot;
+	unsigned int ret = 0;
+	struct radix_tree_iter iter;
+
+	if (!nr_entries)
+		return 0;
+
+	rcu_read_lock();
+restart:
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
+		struct page *page;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		if (unlikely(!page))
+			continue;
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page))
+				goto restart;
+			/*
+			 * Otherwise, we must be storing a swap entry
+			 * here as an exceptional entry: so return it
+			 * without attempting to raise page count.
+			 */
+			goto export;
+		}
+		if (!page_cache_get_speculative(page))
+			goto repeat;
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			page_cache_release(page);
+			goto repeat;
+		}
+export:
+		indices[ret] = iter.index;
+		entries[ret] = page;
+		if (++ret == nr_entries)
+			break;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
  * find_get_pages - gang pagecache lookup
  * @mapping:	The address_space to search
  * @start:	The starting page index
diff --git a/mm/mincore.c b/mm/mincore.c
index da2be56..06cb810 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -70,13 +70,21 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 	 * any other file mapping (ie. marked !present and faulted in with
 	 * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
 	 */
-	page = find_get_page(mapping, pgoff);
 #ifdef CONFIG_SWAP
-	/* shmem/tmpfs may return swap: account for swapcache page too. */
-	if (radix_tree_exceptional_entry(page)) {
-		swp_entry_t swap = radix_to_swp_entry(page);
-		page = find_get_page(swap_address_space(swap), swap.val);
-	}
+	if (shmem_mapping(mapping)) {
+		page = find_get_entry(mapping, pgoff);
+		/*
+		 * shmem/tmpfs may return swap: account for swapcache
+		 * page too.
+		 */
+		if (radix_tree_exceptional_entry(page)) {
+			swp_entry_t swp = radix_to_swp_entry(page);
+			page = find_get_page(swap_address_space(swp), swp.val);
+		}
+	} else
+		page = find_get_page(mapping, pgoff);
+#else
+	page = find_get_page(mapping, pgoff);
 #endif
 	if (page) {
 		present = PageUptodate(page);
diff --git a/mm/readahead.c b/mm/readahead.c
index 6db5d56..4ab0c93 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -179,7 +179,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->page_tree, page_offset);
 		rcu_read_unlock();
-		if (page)
+		if (page && !radix_tree_exceptional_entry(page))
 			continue;
 
 		page = page_cache_alloc_readahead(mapping);
diff --git a/mm/shmem.c b/mm/shmem.c
index 1460b20..15e5527 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -330,56 +330,6 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap)
 }
 
 /*
- * Like find_get_pages, but collecting swap entries as well as pages.
- */
-static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping,
-					pgoff_t start, unsigned int nr_pages,
-					struct page **pages, pgoff_t *indices)
-{
-	void **slot;
-	unsigned int ret = 0;
-	struct radix_tree_iter iter;
-
-	if (!nr_pages)
-		return 0;
-
-	rcu_read_lock();
-restart:
-	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
-		struct page *page;
-repeat:
-		page = radix_tree_deref_slot(slot);
-		if (unlikely(!page))
-			continue;
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page))
-				goto restart;
-			/*
-			 * Otherwise, we must be storing a swap entry
-			 * here as an exceptional entry: so return it
-			 * without attempting to raise page count.
-			 */
-			goto export;
-		}
-		if (!page_cache_get_speculative(page))
-			goto repeat;
-
-		/* Has the page moved? */
-		if (unlikely(page != *slot)) {
-			page_cache_release(page);
-			goto repeat;
-		}
-export:
-		indices[ret] = iter.index;
-		pages[ret] = page;
-		if (++ret == nr_pages)
-			break;
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
-/*
  * Remove swap entry from radix tree, free the swap and its page cache.
  */
 static int shmem_free_swap(struct address_space *mapping,
@@ -397,21 +347,6 @@ static int shmem_free_swap(struct address_space *mapping,
 }
 
 /*
- * Pagevec may contain swap entries, so shuffle up pages before releasing.
- */
-static void shmem_deswap_pagevec(struct pagevec *pvec)
-{
-	int i, j;
-
-	for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
-		struct page *page = pvec->pages[i];
-		if (!radix_tree_exceptional_entry(page))
-			pvec->pages[j++] = page;
-	}
-	pvec->nr = j;
-}
-
-/*
  * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
  */
 void shmem_unlock_mapping(struct address_space *mapping)
@@ -429,12 +364,12 @@ void shmem_unlock_mapping(struct address_space *mapping)
 		 * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it
 		 * has finished, if it hits a row of PAGEVEC_SIZE swap entries.
 		 */
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
-					PAGEVEC_SIZE, pvec.pages, indices);
+		pvec.nr = find_get_entries(mapping, index,
+					   PAGEVEC_SIZE, pvec.pages, indices);
 		if (!pvec.nr)
 			break;
 		index = indices[pvec.nr - 1] + 1;
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		check_move_unevictable_pages(pvec.pages, pvec.nr);
 		pagevec_release(&pvec);
 		cond_resched();
@@ -466,9 +401,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 	pagevec_init(&pvec, 0);
 	index = start;
 	while (index < end) {
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
-				min(end - index, (pgoff_t)PAGEVEC_SIZE),
-							pvec.pages, indices);
+		pvec.nr = find_get_entries(mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			pvec.pages, indices);
 		if (!pvec.nr)
 			break;
 		mem_cgroup_uncharge_start();
@@ -497,7 +432,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			}
 			unlock_page(page);
 		}
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -535,9 +470,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 	index = start;
 	while (index < end) {
 		cond_resched();
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+
+		pvec.nr = find_get_entries(mapping, index,
 				min(end - index, (pgoff_t)PAGEVEC_SIZE),
-							pvec.pages, indices);
+				pvec.pages, indices);
 		if (!pvec.nr) {
 			/* If all gone or hole-punch or unfalloc, we're done */
 			if (index == start || end != -1)
@@ -580,7 +516,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			}
 			unlock_page(page);
 		}
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		index++;
@@ -1089,7 +1025,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 		return -EFBIG;
 repeat:
 	swap.val = 0;
-	page = find_lock_page(mapping, index);
+	page = find_lock_entry(mapping, index);
 	if (radix_tree_exceptional_entry(page)) {
 		swap = radix_to_swp_entry(page);
 		page = NULL;
@@ -1484,6 +1420,11 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 	return inode;
 }
 
+bool shmem_mapping(struct address_space *mapping)
+{
+	return mapping->backing_dev_info == &shmem_backing_dev_info;
+}
+
 #ifdef CONFIG_TMPFS
 static const struct inode_operations shmem_symlink_inode_operations;
 static const struct inode_operations shmem_short_symlink_operations;
@@ -1796,7 +1737,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 	pagevec_init(&pvec, 0);
 	pvec.nr = 1;		/* start small: we may be there already */
 	while (!done) {
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+		pvec.nr = find_get_entries(mapping, index,
 					pvec.nr, pvec.pages, indices);
 		if (!pvec.nr) {
 			if (whence == SEEK_DATA)
@@ -1823,7 +1764,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 				break;
 			}
 		}
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		pvec.nr = PAGEVEC_SIZE;
 		cond_resched();
diff --git a/mm/swap.c b/mm/swap.c
index aa4da5d..2d9ee76 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -916,6 +916,57 @@ void __pagevec_lru_add(struct pagevec *pvec)
 EXPORT_SYMBOL(__pagevec_lru_add);
 
 /**
+ * pagevec_lookup_entries - gang pagecache lookup
+ * @pvec:	Where the resulting entries are placed
+ * @mapping:	The address_space to search
+ * @start:	The starting entry index
+ * @nr_entries:	The maximum number of entries
+ * @indices:	The cache indices corresponding to the entries in @pvec
+ *
+ * pagevec_lookup_entries() will search for and return a group of up
+ * to @nr_entries pages and shadow entries in the mapping.  All
+ * entries are placed in @pvec.  pagevec_lookup_entries() takes a
+ * reference against actual pages in @pvec.
+ *
+ * The search returns a group of mapping-contiguous entries with
+ * ascending indexes.  There may be holes in the indices due to
+ * not-present entries.
+ *
+ * pagevec_lookup_entries() returns the number of entries which were
+ * found.
+ */
+unsigned pagevec_lookup_entries(struct pagevec *pvec,
+				struct address_space *mapping,
+				pgoff_t start, unsigned nr_pages,
+				pgoff_t *indices)
+{
+	pvec->nr = find_get_entries(mapping, start, nr_pages,
+				    pvec->pages, indices);
+	return pagevec_count(pvec);
+}
+
+/**
+ * pagevec_remove_exceptionals - pagevec exceptionals pruning
+ * @pvec:	The pagevec to prune
+ *
+ * pagevec_lookup_entries() fills both pages and exceptional radix
+ * tree entries into the pagevec.  This function prunes all
+ * exceptionals from @pvec without leaving holes, so that it can be
+ * passed on to page-only pagevec operations.
+ */
+void pagevec_remove_exceptionals(struct pagevec *pvec)
+{
+	int i, j;
+
+	for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
+		struct page *page = pvec->pages[i];
+		if (!radix_tree_exceptional_entry(page))
+			pvec->pages[j++] = page;
+	}
+	pvec->nr = j;
+}
+
+/**
  * pagevec_lookup - gang pagecache lookup
  * @pvec:	Where the resulting pages are placed
  * @mapping:	The address_space to search
diff --git a/mm/truncate.c b/mm/truncate.c
index 353b683..2e84fe5 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -22,6 +22,22 @@
 #include <linux/cleancache.h>
 #include "internal.h"
 
+static void clear_exceptional_entry(struct address_space *mapping,
+				    pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return;
+
+	spin_lock_irq(&mapping->tree_lock);
+	/*
+	 * Regular page slots are stabilized by the page lock even
+	 * without the tree itself locked.  These unlocked entries
+	 * need verification under the tree lock.
+	 */
+	radix_tree_delete_item(&mapping->page_tree, index, entry);
+	spin_unlock_irq(&mapping->tree_lock);
+}
 
 /**
  * do_invalidatepage - invalidate part or all of a page
@@ -208,6 +224,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	unsigned int	partial_start;	/* inclusive */
 	unsigned int	partial_end;	/* exclusive */
 	struct pagevec	pvec;
+	pgoff_t		indices[PAGEVEC_SIZE];
 	pgoff_t		index;
 	int		i;
 
@@ -238,17 +255,23 @@ void truncate_inode_pages_range(struct address_space *mapping,
 
 	pagevec_init(&pvec, 0);
 	index = start;
-	while (index < end && pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE))) {
+	while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			indices)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index >= end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			if (!trylock_page(page))
 				continue;
 			WARN_ON(page->index != index);
@@ -259,6 +282,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			truncate_inode_page(mapping, page);
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -307,14 +331,16 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	index = start;
 	for ( ; ; ) {
 		cond_resched();
-		if (!pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE))) {
+		if (!pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			indices)) {
 			if (index == start)
 				break;
 			index = start;
 			continue;
 		}
-		if (index == start && pvec.pages[0]->index >= end) {
+		if (index == start && indices[0] >= end) {
+			pagevec_remove_exceptionals(&pvec);
 			pagevec_release(&pvec);
 			break;
 		}
@@ -323,16 +349,22 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index >= end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			lock_page(page);
 			WARN_ON(page->index != index);
 			wait_on_page_writeback(page);
 			truncate_inode_page(mapping, page);
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		index++;
@@ -375,6 +407,7 @@ EXPORT_SYMBOL(truncate_inode_pages);
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t end)
 {
+	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
 	pgoff_t index = start;
 	unsigned long ret;
@@ -390,17 +423,23 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 	 */
 
 	pagevec_init(&pvec, 0);
-	while (index <= end && pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+	while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+			indices)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index > end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			if (!trylock_page(page))
 				continue;
 			WARN_ON(page->index != index);
@@ -414,6 +453,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 				deactivate_page(page);
 			count += ret;
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -481,6 +521,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page)
 int invalidate_inode_pages2_range(struct address_space *mapping,
 				  pgoff_t start, pgoff_t end)
 {
+	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
 	pgoff_t index;
 	int i;
@@ -491,17 +532,23 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 	cleancache_invalidate_inode(mapping);
 	pagevec_init(&pvec, 0);
 	index = start;
-	while (index <= end && pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+	while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+			indices)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index > end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			lock_page(page);
 			WARN_ON(page->index != index);
 			if (page->mapping != mapping) {
@@ -539,6 +586,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 				ret = ret2;
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
-- 
1.8.4.5

[PATCH 47/97] mm: madvise: fix MADV_WILLNEED on shmem swapouts

[Mel Gorman]

From: Johannes Weiner <hannes@cmpxchg.org>

commit 55231e5c898c5c03c14194001e349f40f59bd300 upstream.

MADV_WILLNEED currently does not read swapped out shmem pages back in.

Commit 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page
cache radix trees") made find_get_page() filter exceptional radix tree
entries but failed to convert all find_get_page() callers that WANT
exceptional entries over to find_get_entry().  One of them is shmem swap
readahead in madvise, which now skips over any swap-out records.

Convert it to find_get_entry().

Fixes: 0cd6144aadd2 ("mm + fs: prepare for non-page entries in page cache radix trees")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/madvise.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/madvise.c b/mm/madvise.c
index 539eeb9..a402f8f 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -195,7 +195,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 	for (; start < end; start += PAGE_SIZE) {
 		index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
-		page = find_get_page(mapping, index);
+		page = find_get_entry(mapping, index);
 		if (!radix_tree_exceptional_entry(page)) {
 			if (page)
 				page_cache_release(page);
-- 
1.8.4.5

[PATCH 48/97] mm: remove read_cache_page_async()

[Mel Gorman]

From: Sasha Levin <sasha.levin@oracle.com>

commit 67f9fd91f93c582b7de2ab9325b6e179db77e4d5 upstream.

This patch removes read_cache_page_async() which wasn't really needed
anywhere and simplifies the code around it a bit.

read_cache_page_async() is useful when we want to read a page into the
cache without waiting for it to complete.  This happens when the
appropriate callback 'filler' doesn't complete its read operation and
releases the page lock immediately, and instead queues a different
completion routine to do that.  This never actually happened anywhere in
the code.

read_cache_page_async() had 3 different callers:

- read_cache_page() which is the sync version, it would just wait for
  the requested read to complete using wait_on_page_read().

- JFFS2 would call it from jffs2_gc_fetch_page(), but the filler
  function it supplied doesn't do any async reads, and would complete
  before the filler function returns - making it actually a sync read.

- CRAMFS would call it using the read_mapping_page_async() wrapper, with
  a similar story to JFFS2 - the filler function doesn't do anything that
  reminds async reads and would always complete before the filler function
  returns.

To sum it up, the code in mm/filemap.c never took advantage of having
read_cache_page_async().  While there are filler callbacks that do async
reads (such as the block one), we always called it with the
read_cache_page().

This patch adds a mandatory wait for read to complete when adding a new
page to the cache, and removes read_cache_page_async() and its wrappers.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 fs/cramfs/inode.c       |  3 +--
 fs/jffs2/fs.c           |  2 +-
 include/linux/pagemap.h | 10 --------
 mm/filemap.c            | 64 ++++++++++++++++++-------------------------------
 4 files changed, 25 insertions(+), 54 deletions(-)

diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index e501ac3..2f6cfca 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -179,8 +179,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
 		struct page *page = NULL;
 
 		if (blocknr + i < devsize) {
-			page = read_mapping_page_async(mapping, blocknr + i,
-									NULL);
+			page = read_mapping_page(mapping, blocknr + i, NULL);
 			/* synchronous error? */
 			if (IS_ERR(page))
 				page = NULL;
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index fe3c052..91bf52d 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -682,7 +682,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c,
 	struct inode *inode = OFNI_EDONI_2SFFJ(f);
 	struct page *pg;
 
-	pg = read_cache_page_async(inode->i_mapping, offset >> PAGE_CACHE_SHIFT,
+	pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT,
 			     (void *)jffs2_do_readpage_unlock, inode);
 	if (IS_ERR(pg))
 		return (void *)pg;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 76aaeaa..930b884 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -278,8 +278,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping,
 
 extern struct page * grab_cache_page_nowait(struct address_space *mapping,
 				pgoff_t index);
-extern struct page * read_cache_page_async(struct address_space *mapping,
-				pgoff_t index, filler_t *filler, void *data);
 extern struct page * read_cache_page(struct address_space *mapping,
 				pgoff_t index, filler_t *filler, void *data);
 extern struct page * read_cache_page_gfp(struct address_space *mapping,
@@ -287,14 +285,6 @@ extern struct page * read_cache_page_gfp(struct address_space *mapping,
 extern int read_cache_pages(struct address_space *mapping,
 		struct list_head *pages, filler_t *filler, void *data);
 
-static inline struct page *read_mapping_page_async(
-				struct address_space *mapping,
-				pgoff_t index, void *data)
-{
-	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
-	return read_cache_page_async(mapping, index, filler, data);
-}
-
 static inline struct page *read_mapping_page(struct address_space *mapping,
 				pgoff_t index, void *data)
 {
diff --git a/mm/filemap.c b/mm/filemap.c
index 5d57a78..d0f765f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2029,6 +2029,18 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
 EXPORT_SYMBOL(generic_file_mmap);
 EXPORT_SYMBOL(generic_file_readonly_mmap);
 
+static struct page *wait_on_page_read(struct page *page)
+{
+	if (!IS_ERR(page)) {
+		wait_on_page_locked(page);
+		if (!PageUptodate(page)) {
+			page_cache_release(page);
+			page = ERR_PTR(-EIO);
+		}
+	}
+	return page;
+}
+
 static struct page *__read_cache_page(struct address_space *mapping,
 				pgoff_t index,
 				int (*filler)(void *, struct page *),
@@ -2055,6 +2067,8 @@ repeat:
 		if (err < 0) {
 			page_cache_release(page);
 			page = ERR_PTR(err);
+		} else {
+			page = wait_on_page_read(page);
 		}
 	}
 	return page;
@@ -2091,6 +2105,10 @@ retry:
 	if (err < 0) {
 		page_cache_release(page);
 		return ERR_PTR(err);
+	} else {
+		page = wait_on_page_read(page);
+		if (IS_ERR(page))
+			return page;
 	}
 out:
 	mark_page_accessed(page);
@@ -2098,40 +2116,25 @@ out:
 }
 
 /**
- * read_cache_page_async - read into page cache, fill it if needed
+ * read_cache_page - read into page cache, fill it if needed
  * @mapping:	the page's address_space
  * @index:	the page index
  * @filler:	function to perform the read
  * @data:	first arg to filler(data, page) function, often left as NULL
  *
- * Same as read_cache_page, but don't wait for page to become unlocked
- * after submitting it to the filler.
- *
  * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page but don't wait for it to become unlocked.
+ * not set, try to fill the page and wait for it to become unlocked.
  *
  * If the page does not get brought uptodate, return -EIO.
  */
-struct page *read_cache_page_async(struct address_space *mapping,
+struct page *read_cache_page(struct address_space *mapping,
 				pgoff_t index,
 				int (*filler)(void *, struct page *),
 				void *data)
 {
 	return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
 }
-EXPORT_SYMBOL(read_cache_page_async);
-
-static struct page *wait_on_page_read(struct page *page)
-{
-	if (!IS_ERR(page)) {
-		wait_on_page_locked(page);
-		if (!PageUptodate(page)) {
-			page_cache_release(page);
-			page = ERR_PTR(-EIO);
-		}
-	}
-	return page;
-}
+EXPORT_SYMBOL(read_cache_page);
 
 /**
  * read_cache_page_gfp - read into page cache, using specified page allocation flags.
@@ -2150,31 +2153,10 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 {
 	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
 
-	return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp));
+	return do_read_cache_page(mapping, index, filler, NULL, gfp);
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
-/**
- * read_cache_page - read into page cache, fill it if needed
- * @mapping:	the page's address_space
- * @index:	the page index
- * @filler:	function to perform the read
- * @data:	first arg to filler(data, page) function, often left as NULL
- *
- * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page then wait for it to become unlocked.
- *
- * If the page does not get brought uptodate, return -EIO.
- */
-struct page *read_cache_page(struct address_space *mapping,
-				pgoff_t index,
-				int (*filler)(void *, struct page *),
-				void *data)
-{
-	return wait_on_page_read(read_cache_page_async(mapping, index, filler, data));
-}
-EXPORT_SYMBOL(read_cache_page);
-
 static size_t __iovec_copy_from_user_inatomic(char *vaddr,
 			const struct iovec *iov, size_t base, size_t bytes)
 {
-- 
1.8.4.5

[PATCH 49/97] callers of iov_copy_from_user_atomic() don't need pagecache_disable()

[Mel Gorman]

From: Al Viro <viro@zeniv.linux.org.uk>

commit 9e8c2af96e0d2d5fe298dd796fb6bc16e888a48d upstream.

... it does that itself (via kmap_atomic())

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 fs/btrfs/file.c | 5 -----
 fs/fuse/file.c  | 2 --
 mm/filemap.c    | 3 ---
 3 files changed, 10 deletions(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 72da4df..9952a2a 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -426,13 +426,8 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
 		struct page *page = prepared_pages[pg];
 		/*
 		 * Copy data from userspace to the current page
-		 *
-		 * Disable pagefault to avoid recursive lock since
-		 * the pages are already locked
 		 */
-		pagefault_disable();
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, count);
-		pagefault_enable();
 
 		/* Flush processor's dcache for this page */
 		flush_dcache_page(page);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 4598345..bf9a755 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -985,9 +985,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 		if (mapping_writably_mapped(mapping))
 			flush_dcache_page(page);
 
-		pagefault_disable();
 		tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes);
-		pagefault_enable();
 		flush_dcache_page(page);
 
 		mark_page_accessed(page);
diff --git a/mm/filemap.c b/mm/filemap.c
index d0f765f..8144c27 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2190,7 +2190,6 @@ size_t iov_iter_copy_from_user_atomic(struct page *page,
 	char *kaddr;
 	size_t copied;
 
-	BUG_ON(!in_atomic());
 	kaddr = kmap_atomic(page);
 	if (likely(i->nr_segs == 1)) {
 		int left;
@@ -2564,9 +2563,7 @@ again:
 		if (mapping_writably_mapped(mapping))
 			flush_dcache_page(page);
 
-		pagefault_disable();
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
-		pagefault_enable();
 		flush_dcache_page(page);
 
 		mark_page_accessed(page);
-- 
1.8.4.5

[PATCH 50/97] mm/readahead.c: inline ra_submit

[Mel Gorman]

From: Fabian Frederick <fabf@skynet.be>

commit 29f175d125f0f3a9503af8a5596f93d714cceb08 upstream.

Commit f9acc8c7b35a ("readahead: sanify file_ra_state names") left
ra_submit with a single function call.

Move ra_submit to internal.h and inline it to save some stack.  Thanks
to Andrew Morton for commenting different versions.

Signed-off-by: Fabian Frederick <fabf@skynet.be>
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mm.h |  3 ---
 mm/internal.h      | 15 +++++++++++++++
 mm/readahead.c     | 21 +++------------------
 3 files changed, 18 insertions(+), 21 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 96fc7dd..2b3a533 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1631,9 +1631,6 @@ void page_cache_async_readahead(struct address_space *mapping,
 				unsigned long size);
 
 unsigned long max_sane_readahead(unsigned long nr);
-unsigned long ra_submit(struct file_ra_state *ra,
-			struct address_space *mapping,
-			struct file *filp);
 
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
diff --git a/mm/internal.h b/mm/internal.h
index fdddbc83..c1488a3 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -11,6 +11,7 @@
 #ifndef __MM_INTERNAL_H
 #define __MM_INTERNAL_H
 
+#include <linux/fs.h>
 #include <linux/mm.h>
 
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
@@ -21,6 +22,20 @@ static inline void set_page_count(struct page *page, int v)
 	atomic_set(&page->_count, v);
 }
 
+extern int __do_page_cache_readahead(struct address_space *mapping,
+		struct file *filp, pgoff_t offset, unsigned long nr_to_read,
+		unsigned long lookahead_size);
+
+/*
+ * Submit IO for the read-ahead request in file_ra_state.
+ */
+static inline unsigned long ra_submit(struct file_ra_state *ra,
+		struct address_space *mapping, struct file *filp)
+{
+	return __do_page_cache_readahead(mapping, filp,
+					ra->start, ra->size, ra->async_size);
+}
+
 /*
  * Turn a non-refcounted page (->_count == 0) into refcounted with
  * a count of one.
diff --git a/mm/readahead.c b/mm/readahead.c
index 4ab0c93..0f35e98 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -8,9 +8,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/fs.h>
 #include <linux/gfp.h>
-#include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
@@ -20,6 +18,8 @@
 #include <linux/syscalls.h>
 #include <linux/file.h>
 
+#include "internal.h"
+
 /*
  * Initialise a struct file's readahead state.  Assumes that the caller has
  * memset *ra to zero.
@@ -149,8 +149,7 @@ out:
  *
  * Returns the number of pages requested, or the maximum amount of I/O allowed.
  */
-static int
-__do_page_cache_readahead(struct address_space *mapping, struct file *filp,
+int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 			pgoff_t offset, unsigned long nr_to_read,
 			unsigned long lookahead_size)
 {
@@ -248,20 +247,6 @@ unsigned long max_sane_readahead(unsigned long nr)
 }
 
 /*
- * Submit IO for the read-ahead request in file_ra_state.
- */
-unsigned long ra_submit(struct file_ra_state *ra,
-		       struct address_space *mapping, struct file *filp)
-{
-	int actual;
-
-	actual = __do_page_cache_readahead(mapping, filp,
-					ra->start, ra->size, ra->async_size);
-
-	return actual;
-}
-
-/*
  * Set the initial window size, round to next power of 2 and square
  * for small size, x 4 for medium, and x 2 for large
  * for 128k (32 page) max ra
-- 
1.8.4.5

[PATCH 51/97] mm/compaction: clean up unused code lines

[Mel Gorman]

From: Heesub Shin <heesub.shin@samsung.com>

commit 13fb44e4b0414d7e718433a49e6430d5b76bd46e upstream.

Remove code lines currently not in use or never called.

Signed-off-by: Heesub Shin <heesub.shin@samsung.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Dongjun Shin <d.j.shin@samsung.com>
Cc: Sunghwan Yun <sunghwan.yun@samsung.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Dongjun Shin <d.j.shin@samsung.com>
Cc: Sunghwan Yun <sunghwan.yun@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 5c17302..c5f2f18 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -208,12 +208,6 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
 	return true;
 }
 
-static inline bool compact_trylock_irqsave(spinlock_t *lock,
-			unsigned long *flags, struct compact_control *cc)
-{
-	return compact_checklock_irqsave(lock, flags, false, cc);
-}
-
 /* Returns true if the page is within a block suitable for migration to */
 static bool suitable_migration_target(struct page *page)
 {
@@ -734,7 +728,6 @@ static void isolate_freepages(struct zone *zone,
 			continue;
 
 		/* Found a block suitable for isolating free pages from */
-		isolated = 0;
 
 		/*
 		 * Take care when isolating in last pageblock of a zone which
@@ -1163,9 +1156,6 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 			if (zone_watermark_ok(zone, cc->order,
 						low_wmark_pages(zone), 0, 0))
 				compaction_defer_reset(zone, cc->order, false);
-			/* Currently async compaction is never deferred. */
-			else if (cc->sync)
-				defer_compaction(zone, cc->order);
 		}
 
 		VM_BUG_ON(!list_empty(&cc->freepages));
-- 
1.8.4.5

[PATCH 52/97] mm/compaction: cleanup isolate_freepages()

[Mel Gorman]

From: Vlastimil Babka <vbabka@suse.cz>

commit c96b9e508f3d06ddb601dcc9792d62c044ab359e upstream.

isolate_freepages() is currently somewhat hard to follow thanks to many
looks like it is related to the 'low_pfn' variable, but in fact it is not.

This patch renames the 'high_pfn' variable to a hopefully less confusing name,
and slightly changes its handling without a functional change. A comment made
obsolete by recent changes is also updated.

[akpm@linux-foundation.org: comment fixes, per Minchan]
[iamjoonsoo.kim@lge.com: cleanups]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Dongjun Shin <d.j.shin@samsung.com>
Cc: Sunghwan Yun <sunghwan.yun@samsung.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 56 +++++++++++++++++++++++++++-----------------------------
 1 file changed, 27 insertions(+), 29 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index c5f2f18..43d37cd 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -663,7 +663,10 @@ static void isolate_freepages(struct zone *zone,
 				struct compact_control *cc)
 {
 	struct page *page;
-	unsigned long high_pfn, low_pfn, pfn, z_end_pfn;
+	unsigned long block_start_pfn;	/* start of current pageblock */
+	unsigned long block_end_pfn;	/* end of current pageblock */
+	unsigned long low_pfn;	     /* lowest pfn scanner is able to scan */
+	unsigned long next_free_pfn; /* start pfn for scaning at next round */
 	int nr_freepages = cc->nr_freepages;
 	struct list_head *freelist = &cc->freepages;
 
@@ -671,32 +674,33 @@ static void isolate_freepages(struct zone *zone,
 	 * Initialise the free scanner. The starting point is where we last
 	 * successfully isolated from, zone-cached value, or the end of the
 	 * zone when isolating for the first time. We need this aligned to
-	 * the pageblock boundary, because we do pfn -= pageblock_nr_pages
-	 * in the for loop.
+	 * the pageblock boundary, because we do
+	 * block_start_pfn -= pageblock_nr_pages in the for loop.
+	 * For ending point, take care when isolating in last pageblock of a
+	 * a zone which ends in the middle of a pageblock.
 	 * The low boundary is the end of the pageblock the migration scanner
 	 * is using.
 	 */
-	pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
+	block_start_pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
+	block_end_pfn = min(block_start_pfn + pageblock_nr_pages,
+						zone_end_pfn(zone));
 	low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
 
 	/*
-	 * Take care that if the migration scanner is at the end of the zone
-	 * that the free scanner does not accidentally move to the next zone
-	 * in the next isolation cycle.
+	 * If no pages are isolated, the block_start_pfn < low_pfn check
+	 * will kick in.
 	 */
-	high_pfn = min(low_pfn, pfn);
-
-	z_end_pfn = zone_end_pfn(zone);
+	next_free_pfn = 0;
 
 	/*
 	 * Isolate free pages until enough are available to migrate the
 	 * pages on cc->migratepages. We stop searching if the migrate
 	 * and free page scanners meet or enough free pages are isolated.
 	 */
-	for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
-					pfn -= pageblock_nr_pages) {
+	for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
+				block_end_pfn = block_start_pfn,
+				block_start_pfn -= pageblock_nr_pages) {
 		unsigned long isolated;
-		unsigned long end_pfn;
 
 		/*
 		 * This can iterate a massively long zone without finding any
@@ -705,7 +709,7 @@ static void isolate_freepages(struct zone *zone,
 		 */
 		cond_resched();
 
-		if (!pfn_valid(pfn))
+		if (!pfn_valid(block_start_pfn))
 			continue;
 
 		/*
@@ -715,7 +719,7 @@ static void isolate_freepages(struct zone *zone,
 		 * i.e. it's possible that all pages within a zones range of
 		 * pages do not belong to a single zone.
 		 */
-		page = pfn_to_page(pfn);
+		page = pfn_to_page(block_start_pfn);
 		if (page_zone(page) != zone)
 			continue;
 
@@ -728,14 +732,8 @@ static void isolate_freepages(struct zone *zone,
 			continue;
 
 		/* Found a block suitable for isolating free pages from */
-
-		/*
-		 * Take care when isolating in last pageblock of a zone which
-		 * ends in the middle of a pageblock.
-		 */
-		end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn);
-		isolated = isolate_freepages_block(cc, pfn, end_pfn,
-						   freelist, false);
+		isolated = isolate_freepages_block(cc, block_start_pfn,
+					block_end_pfn, freelist, false);
 		nr_freepages += isolated;
 
 		/*
@@ -743,9 +741,9 @@ static void isolate_freepages(struct zone *zone,
 		 * looking for free pages, the search will restart here as
 		 * page migration may have returned some pages to the allocator
 		 */
-		if (isolated) {
+		if (isolated && next_free_pfn == 0) {
 			cc->finished_update_free = true;
-			high_pfn = max(high_pfn, pfn);
+			next_free_pfn = block_start_pfn;
 		}
 	}
 
@@ -756,10 +754,10 @@ static void isolate_freepages(struct zone *zone,
 	 * If we crossed the migrate scanner, we want to keep it that way
 	 * so that compact_finished() may detect this
 	 */
-	if (pfn < low_pfn)
-		cc->free_pfn = max(pfn, zone->zone_start_pfn);
-	else
-		cc->free_pfn = high_pfn;
+	if (block_start_pfn < low_pfn)
+		next_free_pfn = cc->migrate_pfn;
+
+	cc->free_pfn = next_free_pfn;
 	cc->nr_freepages = nr_freepages;
 }
 
-- 
1.8.4.5

[PATCH 53/97] mm, migration: add destination page freeing callback

[Mel Gorman]

From: David Rientjes <rientjes@google.com>

commit 68711a746345c44ae00c64d8dbac6a9ce13ac54a upstream.

Memory migration uses a callback defined by the caller to determine how to
allocate destination pages.  When migration fails for a source page,
however, it frees the destination page back to the system.

This patch adds a memory migration callback defined by the caller to
determine how to free destination pages.  If a caller, such as memory
compaction, builds its own freelist for migration targets, this can reuse
already freed memory instead of scanning additional memory.

If the caller provides a function to handle freeing of destination pages,
it is called when page migration fails.  If the caller passes NULL then
freeing back to the system will be handled as usual.  This patch
introduces no functional change.

Signed-off-by: David Rientjes <rientjes@google.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/migrate.h | 11 ++++++----
 mm/compaction.c         |  2 +-
 mm/memory-failure.c     |  4 ++--
 mm/memory_hotplug.c     |  2 +-
 mm/mempolicy.c          |  4 ++--
 mm/migrate.c            | 55 +++++++++++++++++++++++++++++++++++--------------
 mm/page_alloc.c         |  2 +-
 7 files changed, 53 insertions(+), 27 deletions(-)

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index ee8b14a..449905e 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -5,7 +5,9 @@
 #include <linux/mempolicy.h>
 #include <linux/migrate_mode.h>
 
-typedef struct page *new_page_t(struct page *, unsigned long private, int **);
+typedef struct page *new_page_t(struct page *page, unsigned long private,
+				int **reason);
+typedef void free_page_t(struct page *page, unsigned long private);
 
 /*
  * Return values from addresss_space_operations.migratepage():
@@ -39,7 +41,7 @@ extern void putback_lru_pages(struct list_head *l);
 extern void putback_movable_pages(struct list_head *l);
 extern int migrate_page(struct address_space *,
 			struct page *, struct page *, enum migrate_mode);
-extern int migrate_pages(struct list_head *l, new_page_t x,
+extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
 		unsigned long private, enum migrate_mode mode, int reason);
 
 extern int fail_migrate_page(struct address_space *,
@@ -61,8 +63,9 @@ extern int migrate_page_move_mapping(struct address_space *mapping,
 
 static inline void putback_lru_pages(struct list_head *l) {}
 static inline void putback_movable_pages(struct list_head *l) {}
-static inline int migrate_pages(struct list_head *l, new_page_t x,
-		unsigned long private, enum migrate_mode mode, int reason)
+static inline int migrate_pages(struct list_head *l, new_page_t new,
+		free_page_t free, unsigned long private, enum migrate_mode mode,
+		int reason)
 	{ return -ENOSYS; }
 
 static inline int migrate_prep(void) { return -ENOSYS; }
diff --git a/mm/compaction.c b/mm/compaction.c
index 43d37cd..fae59ea 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1014,7 +1014,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		}
 
 		nr_migrate = cc->nr_migratepages;
-		err = migrate_pages(&cc->migratepages, compaction_alloc,
+		err = migrate_pages(&cc->migratepages, compaction_alloc, NULL,
 				(unsigned long)cc,
 				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC,
 				MR_COMPACTION);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 6e3f9c3..4ab233d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1554,7 +1554,7 @@ static int soft_offline_huge_page(struct page *page, int flags)
 
 	/* Keep page count to indicate a given hugepage is isolated. */
 	list_move(&hpage->lru, &pagelist);
-	ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
+	ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 				MIGRATE_SYNC, MR_MEMORY_FAILURE);
 	if (ret) {
 		pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
@@ -1635,7 +1635,7 @@ static int __soft_offline_page(struct page *page, int flags)
 		inc_zone_page_state(page, NR_ISOLATED_ANON +
 					page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
-		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
+		ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 					MIGRATE_SYNC, MR_MEMORY_FAILURE);
 		if (ret) {
 			putback_lru_pages(&pagelist);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ed85fe3..d317305 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1321,7 +1321,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		 * alloc_migrate_target should be improooooved!!
 		 * migrate_pages returns # of failed pages.
 		 */
-		ret = migrate_pages(&source, alloc_migrate_target, 0,
+		ret = migrate_pages(&source, alloc_migrate_target, NULL, 0,
 					MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
 		if (ret)
 			putback_movable_pages(&source);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0bf6476..cc61c7a 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1060,7 +1060,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 			flags | MPOL_MF_DISCONTIG_OK, &pagelist);
 
 	if (!list_empty(&pagelist)) {
-		err = migrate_pages(&pagelist, new_node_page, dest,
+		err = migrate_pages(&pagelist, new_node_page, NULL, dest,
 					MIGRATE_SYNC, MR_SYSCALL);
 		if (err)
 			putback_movable_pages(&pagelist);
@@ -1306,7 +1306,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 
 		if (!list_empty(&pagelist)) {
 			WARN_ON_ONCE(flags & MPOL_MF_LAZY);
-			nr_failed = migrate_pages(&pagelist, new_page,
+			nr_failed = migrate_pages(&pagelist, new_page, NULL,
 				start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
 			if (nr_failed)
 				putback_movable_pages(&pagelist);
diff --git a/mm/migrate.c b/mm/migrate.c
index e3cf71d..e397bd2 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -867,8 +867,9 @@ out:
  * Obtain the lock on page, remove all ptes and migrate the page
  * to the newly allocated page in newpage.
  */
-static int unmap_and_move(new_page_t get_new_page, unsigned long private,
-			struct page *page, int force, enum migrate_mode mode)
+static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page,
+			unsigned long private, struct page *page, int force,
+			enum migrate_mode mode)
 {
 	int rc = 0;
 	int *result = NULL;
@@ -912,11 +913,17 @@ out:
 				page_is_file_cache(page));
 		putback_lru_page(page);
 	}
+
 	/*
-	 * Move the new page to the LRU. If migration was not successful
-	 * then this will free the page.
+	 * If migration was not successful and there's a freeing callback, use
+	 * it.  Otherwise, putback_lru_page() will drop the reference grabbed
+	 * during isolation.
 	 */
-	putback_lru_page(newpage);
+	if (rc != MIGRATEPAGE_SUCCESS && put_new_page)
+		put_new_page(newpage, private);
+	else
+		putback_lru_page(newpage);
+
 	if (result) {
 		if (rc)
 			*result = rc;
@@ -945,8 +952,9 @@ out:
  * will wait in the page fault for migration to complete.
  */
 static int unmap_and_move_huge_page(new_page_t get_new_page,
-				unsigned long private, struct page *hpage,
-				int force, enum migrate_mode mode)
+				free_page_t put_new_page, unsigned long private,
+				struct page *hpage, int force,
+				enum migrate_mode mode)
 {
 	int rc = 0;
 	int *result = NULL;
@@ -982,20 +990,30 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	if (!page_mapped(hpage))
 		rc = move_to_new_page(new_hpage, hpage, 1, mode);
 
-	if (rc)
+	if (rc != MIGRATEPAGE_SUCCESS)
 		remove_migration_ptes(hpage, hpage);
 
 	if (anon_vma)
 		put_anon_vma(anon_vma);
 
-	if (!rc)
+	if (rc == MIGRATEPAGE_SUCCESS)
 		hugetlb_cgroup_migrate(hpage, new_hpage);
 
 	unlock_page(hpage);
 out:
 	if (rc != -EAGAIN)
 		putback_active_hugepage(hpage);
-	put_page(new_hpage);
+
+	/*
+	 * If migration was not successful and there's a freeing callback, use
+	 * it.  Otherwise, put_page() will drop the reference grabbed during
+	 * isolation.
+	 */
+	if (rc != MIGRATEPAGE_SUCCESS && put_new_page)
+		put_new_page(new_hpage, private);
+	else
+		put_page(new_hpage);
+
 	if (result) {
 		if (rc)
 			*result = rc;
@@ -1012,6 +1030,8 @@ out:
  * @from:		The list of pages to be migrated.
  * @get_new_page:	The function used to allocate free pages to be used
  *			as the target of the page migration.
+ * @put_new_page:	The function used to free target pages if migration
+ *			fails, or NULL if no special handling is necessary.
  * @private:		Private data to be passed on to get_new_page()
  * @mode:		The migration mode that specifies the constraints for
  *			page migration, if any.
@@ -1025,7 +1045,8 @@ out:
  * Returns the number of pages that were not migrated, or an error code.
  */
 int migrate_pages(struct list_head *from, new_page_t get_new_page,
-		unsigned long private, enum migrate_mode mode, int reason)
+		free_page_t put_new_page, unsigned long private,
+		enum migrate_mode mode, int reason)
 {
 	int retry = 1;
 	int nr_failed = 0;
@@ -1047,10 +1068,11 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 
 			if (PageHuge(page))
 				rc = unmap_and_move_huge_page(get_new_page,
-						private, page, pass > 2, mode);
+						put_new_page, private, page,
+						pass > 2, mode);
 			else
-				rc = unmap_and_move(get_new_page, private,
-						page, pass > 2, mode);
+				rc = unmap_and_move(get_new_page, put_new_page,
+						private, page, pass > 2, mode);
 
 			switch(rc) {
 			case -ENOMEM:
@@ -1194,7 +1216,7 @@ set_status:
 
 	err = 0;
 	if (!list_empty(&pagelist)) {
-		err = migrate_pages(&pagelist, new_page_node,
+		err = migrate_pages(&pagelist, new_page_node, NULL,
 				(unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL);
 		if (err)
 			putback_movable_pages(&pagelist);
@@ -1643,7 +1665,8 @@ int migrate_misplaced_page(struct page *page, int node)
 
 	list_add(&page->lru, &migratepages);
 	nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
-				     node, MIGRATE_ASYNC, MR_NUMA_MISPLACED);
+				     NULL, node, MIGRATE_ASYNC,
+				     MR_NUMA_MISPLACED);
 	if (nr_remaining) {
 		putback_lru_pages(&migratepages);
 		isolated = 0;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 74bf3e0..bfbe0db 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6204,7 +6204,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 		cc->nr_migratepages -= nr_reclaimed;
 
 		ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
-				    0, MIGRATE_SYNC, MR_CMA);
+				    NULL, 0, MIGRATE_SYNC, MR_CMA);
 	}
 	if (ret < 0) {
 		putback_movable_pages(&cc->migratepages);
-- 
1.8.4.5

[PATCH 54/97] mm, compaction: return failed migration target pages back to freelist

[Mel Gorman]

From: David Rientjes <rientjes@google.com>

commit d53aea3d46d64e95da9952887969f7533b9ab25e upstream.

Greg reported that he found isolated free pages were returned back to the
VM rather than the compaction freelist.  This will cause holes behind the
free scanner and cause it to reallocate additional memory if necessary
later.

He detected the problem at runtime seeing that ext4 metadata pages (esp
the ones read by "sbi->s_group_desc[i] = sb_bread(sb, block)") were
constantly visited by compaction calls of migrate_pages().  These pages
had a non-zero b_count which caused fallback_migrate_page() ->
try_to_release_page() -> try_to_free_buffers() to fail.

Memory compaction works by having a "freeing scanner" scan from one end of
a zone which isolates pages as migration targets while another "migrating
scanner" scans from the other end of the same zone which isolates pages
for migration.

When page migration fails for an isolated page, the target page is
returned to the system rather than the freelist built by the freeing
scanner.  This may require the freeing scanner to continue scanning memory
after suitable migration targets have already been returned to the system
needlessly.

This patch returns destination pages to the freeing scanner freelist when
page migration fails.  This prevents unnecessary work done by the freeing
scanner but also encourages memory to be as compacted as possible at the
end of the zone.

Signed-off-by: David Rientjes <rientjes@google.com>
Reported-by: Greg Thelen <gthelen@google.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index fae59ea..e4add42 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -788,23 +788,32 @@ static struct page *compaction_alloc(struct page *migratepage,
 }
 
 /*
- * We cannot control nr_migratepages and nr_freepages fully when migration is
- * running as migrate_pages() has no knowledge of compact_control. When
- * migration is complete, we count the number of pages on the lists by hand.
+ * This is a migrate-callback that "frees" freepages back to the isolated
+ * freelist.  All pages on the freelist are from the same zone, so there is no
+ * special handling needed for NUMA.
+ */
+static void compaction_free(struct page *page, unsigned long data)
+{
+	struct compact_control *cc = (struct compact_control *)data;
+
+	list_add(&page->lru, &cc->freepages);
+	cc->nr_freepages++;
+}
+
+/*
+ * We cannot control nr_migratepages fully when migration is running as
+ * migrate_pages() has no knowledge of of compact_control.  When migration is
+ * complete, we count the number of pages on the list by hand.
  */
 static void update_nr_listpages(struct compact_control *cc)
 {
 	int nr_migratepages = 0;
-	int nr_freepages = 0;
 	struct page *page;
 
 	list_for_each_entry(page, &cc->migratepages, lru)
 		nr_migratepages++;
-	list_for_each_entry(page, &cc->freepages, lru)
-		nr_freepages++;
 
 	cc->nr_migratepages = nr_migratepages;
-	cc->nr_freepages = nr_freepages;
 }
 
 /* possible outcome of isolate_migratepages */
@@ -1014,8 +1023,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		}
 
 		nr_migrate = cc->nr_migratepages;
-		err = migrate_pages(&cc->migratepages, compaction_alloc, NULL,
-				(unsigned long)cc,
+		err = migrate_pages(&cc->migratepages, compaction_alloc,
+				compaction_free, (unsigned long)cc,
 				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC,
 				MR_COMPACTION);
 		update_nr_listpages(cc);
-- 
1.8.4.5

[PATCH 55/97] mm, compaction: add per-zone migration pfn cache for async compaction

[Mel Gorman]

From: David Rientjes <rientjes@google.com>

commit 35979ef3393110ff3c12c6b94552208d3bdf1a36 upstream.

Each zone has a cached migration scanner pfn for memory compaction so that
subsequent calls to memory compaction can start where the previous call
left off.

Currently, the compaction migration scanner only updates the per-zone
cached pfn when pageblocks were not skipped for async compaction.  This
creates a dependency on calling sync compaction to avoid having subsequent
calls to async compaction from scanning an enormous amount of non-MOVABLE
pageblocks each time it is called.  On large machines, this could be
potentially very expensive.

This patch adds a per-zone cached migration scanner pfn only for async
compaction.  It is updated everytime a pageblock has been scanned in its
entirety and when no pages from it were successfully isolated.  The cached
migration scanner pfn for sync compaction is updated only when called for
sync compaction.

Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mmzone.h |  5 ++--
 mm/compaction.c        | 66 ++++++++++++++++++++++++++++++--------------------
 2 files changed, 43 insertions(+), 28 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 4719985..e4d1a88 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -361,9 +361,10 @@ struct zone {
 	/* Set to true when the PG_migrate_skip bits should be cleared */
 	bool			compact_blockskip_flush;
 
-	/* pfns where compaction scanners should start */
+	/* pfn where compaction free scanner should start */
 	unsigned long		compact_cached_free_pfn;
-	unsigned long		compact_cached_migrate_pfn;
+	/* pfn where async and sync compaction migration scanner should start */
+	unsigned long		compact_cached_migrate_pfn[2];
 #endif
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/* see spanned/present_pages for more description */
diff --git a/mm/compaction.c b/mm/compaction.c
index e4add42..618c919 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -89,7 +89,8 @@ static void __reset_isolation_suitable(struct zone *zone)
 	unsigned long end_pfn = zone_end_pfn(zone);
 	unsigned long pfn;
 
-	zone->compact_cached_migrate_pfn = start_pfn;
+	zone->compact_cached_migrate_pfn[0] = start_pfn;
+	zone->compact_cached_migrate_pfn[1] = start_pfn;
 	zone->compact_cached_free_pfn = end_pfn;
 	zone->compact_blockskip_flush = false;
 
@@ -131,9 +132,10 @@ void reset_isolation_suitable(pg_data_t *pgdat)
  */
 static void update_pageblock_skip(struct compact_control *cc,
 			struct page *page, unsigned long nr_isolated,
-			bool migrate_scanner)
+			bool set_unsuitable, bool migrate_scanner)
 {
 	struct zone *zone = cc->zone;
+	unsigned long pfn;
 
 	if (cc->ignore_skip_hint)
 		return;
@@ -141,20 +143,31 @@ static void update_pageblock_skip(struct compact_control *cc,
 	if (!page)
 		return;
 
-	if (!nr_isolated) {
-		unsigned long pfn = page_to_pfn(page);
+	if (nr_isolated)
+		return;
+
+	/*
+	 * Only skip pageblocks when all forms of compaction will be known to
+	 * fail in the near future.
+	 */
+	if (set_unsuitable)
 		set_pageblock_skip(page);
 
-		/* Update where compaction should restart */
-		if (migrate_scanner) {
-			if (!cc->finished_update_migrate &&
-			    pfn > zone->compact_cached_migrate_pfn)
-				zone->compact_cached_migrate_pfn = pfn;
-		} else {
-			if (!cc->finished_update_free &&
-			    pfn < zone->compact_cached_free_pfn)
-				zone->compact_cached_free_pfn = pfn;
-		}
+	pfn = page_to_pfn(page);
+
+	/* Update where async and sync compaction should restart */
+	if (migrate_scanner) {
+		if (cc->finished_update_migrate)
+			return;
+		if (pfn > zone->compact_cached_migrate_pfn[0])
+			zone->compact_cached_migrate_pfn[0] = pfn;
+		if (cc->sync && pfn > zone->compact_cached_migrate_pfn[1])
+			zone->compact_cached_migrate_pfn[1] = pfn;
+	} else {
+		if (cc->finished_update_free)
+			return;
+		if (pfn < zone->compact_cached_free_pfn)
+			zone->compact_cached_free_pfn = pfn;
 	}
 }
 #else
@@ -166,7 +179,7 @@ static inline bool isolation_suitable(struct compact_control *cc,
 
 static void update_pageblock_skip(struct compact_control *cc,
 			struct page *page, unsigned long nr_isolated,
-			bool migrate_scanner)
+			bool set_unsuitable, bool migrate_scanner)
 {
 }
 #endif /* CONFIG_COMPACTION */
@@ -324,7 +337,8 @@ isolate_fail:
 
 	/* Update the pageblock-skip if the whole pageblock was scanned */
 	if (blockpfn == end_pfn)
-		update_pageblock_skip(cc, valid_page, total_isolated, false);
+		update_pageblock_skip(cc, valid_page, total_isolated, true,
+				      false);
 
 	count_compact_events(COMPACTFREE_SCANNED, nr_scanned);
 	if (total_isolated)
@@ -459,7 +473,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	unsigned long flags;
 	bool locked = false;
 	struct page *page = NULL, *valid_page = NULL;
-	bool skipped_async_unsuitable = false;
+	bool set_unsuitable = true;
 	const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) |
 				    (unevictable ? ISOLATE_UNEVICTABLE : 0);
 
@@ -536,8 +550,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			 */
 			mt = get_pageblock_migratetype(page);
 			if (!cc->sync && !migrate_async_suitable(mt)) {
-				cc->finished_update_migrate = true;
-				skipped_async_unsuitable = true;
+				set_unsuitable = false;
 				goto next_pageblock;
 			}
 		}
@@ -638,11 +651,10 @@ next_pageblock:
 	/*
 	 * Update the pageblock-skip information and cached scanner pfn,
 	 * if the whole pageblock was scanned without isolating any page.
-	 * This is not done when pageblock was skipped due to being unsuitable
-	 * for async compaction, so that eventual sync compaction can try.
 	 */
-	if (low_pfn == end_pfn && !skipped_async_unsuitable)
-		update_pageblock_skip(cc, valid_page, nr_isolated, true);
+	if (low_pfn == end_pfn)
+		update_pageblock_skip(cc, valid_page, nr_isolated,
+				      set_unsuitable, true);
 
 	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
 
@@ -866,7 +878,8 @@ static int compact_finished(struct zone *zone,
 	/* Compaction run completes if the migrate and free scanner meet */
 	if (cc->free_pfn <= cc->migrate_pfn) {
 		/* Let the next compaction start anew. */
-		zone->compact_cached_migrate_pfn = zone->zone_start_pfn;
+		zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn;
+		zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn;
 		zone->compact_cached_free_pfn = zone_end_pfn(zone);
 
 		/*
@@ -991,7 +1004,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	 * information on where the scanners should start but check that it
 	 * is initialised by ensuring the values are within zone boundaries.
 	 */
-	cc->migrate_pfn = zone->compact_cached_migrate_pfn;
+	cc->migrate_pfn = zone->compact_cached_migrate_pfn[cc->sync];
 	cc->free_pfn = zone->compact_cached_free_pfn;
 	if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) {
 		cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1);
@@ -999,7 +1012,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	}
 	if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) {
 		cc->migrate_pfn = start_pfn;
-		zone->compact_cached_migrate_pfn = cc->migrate_pfn;
+		zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
+		zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
 	}
 
 	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn);
-- 
1.8.4.5

[PATCH 56/97] mm, compaction: embed migration mode in compact_control

[Mel Gorman]

From: David Rientjes <rientjes@google.com>

commit e0b9daeb453e602a95ea43853dc12d385558ce1f upstream.

We're going to want to manipulate the migration mode for compaction in the
page allocator, and currently compact_control's sync field is only a bool.

Currently, we only do MIGRATE_ASYNC or MIGRATE_SYNC_LIGHT compaction
depending on the value of this bool.  Convert the bool to enum
migrate_mode and pass the migration mode in directly.  Later, we'll want
to avoid MIGRATE_SYNC_LIGHT for thp allocations in the pagefault patch to
avoid unnecessary latency.

This also alters compaction triggered from sysfs, either for the entire
system or for a node, to force MIGRATE_SYNC.

[akpm@linux-foundation.org: fix build]
[iamjoonsoo.kim@lge.com: use MIGRATE_SYNC in alloc_contig_range()]
Signed-off-by: David Rientjes <rientjes@google.com>
Suggested-by: Mel Gorman <mgorman@suse.de>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/compaction.h |  4 ++--
 mm/compaction.c            | 36 +++++++++++++++++++-----------------
 mm/internal.h              |  2 +-
 mm/page_alloc.c            | 39 +++++++++++++++++----------------------
 4 files changed, 39 insertions(+), 42 deletions(-)

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 7e1c76e..01e3132 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -22,7 +22,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
-			bool sync, bool *contended);
+			enum migrate_mode mode, bool *contended);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
@@ -91,7 +91,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync, bool *contended)
+			enum migrate_mode mode, bool *contended)
 {
 	return COMPACT_CONTINUE;
 }
diff --git a/mm/compaction.c b/mm/compaction.c
index 618c919..cebdeca 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -161,7 +161,8 @@ static void update_pageblock_skip(struct compact_control *cc,
 			return;
 		if (pfn > zone->compact_cached_migrate_pfn[0])
 			zone->compact_cached_migrate_pfn[0] = pfn;
-		if (cc->sync && pfn > zone->compact_cached_migrate_pfn[1])
+		if (cc->mode != MIGRATE_ASYNC &&
+		    pfn > zone->compact_cached_migrate_pfn[1])
 			zone->compact_cached_migrate_pfn[1] = pfn;
 	} else {
 		if (cc->finished_update_free)
@@ -208,7 +209,7 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
 		}
 
 		/* async aborts if taking too long or contended */
-		if (!cc->sync) {
+		if (cc->mode == MIGRATE_ASYNC) {
 			cc->contended = true;
 			return false;
 		}
@@ -474,7 +475,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	bool locked = false;
 	struct page *page = NULL, *valid_page = NULL;
 	bool set_unsuitable = true;
-	const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) |
+	const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ?
+					ISOLATE_ASYNC_MIGRATE : 0) |
 				    (unevictable ? ISOLATE_UNEVICTABLE : 0);
 
 	/*
@@ -484,7 +486,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	 */
 	while (unlikely(too_many_isolated(zone))) {
 		/* async migration should just abort */
-		if (!cc->sync)
+		if (cc->mode == MIGRATE_ASYNC)
 			return 0;
 
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -549,7 +551,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			 * the minimum amount of work satisfies the allocation
 			 */
 			mt = get_pageblock_migratetype(page);
-			if (!cc->sync && !migrate_async_suitable(mt)) {
+			if (cc->mode == MIGRATE_ASYNC &&
+			    !migrate_async_suitable(mt)) {
 				set_unsuitable = false;
 				goto next_pageblock;
 			}
@@ -979,6 +982,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	int ret;
 	unsigned long start_pfn = zone->zone_start_pfn;
 	unsigned long end_pfn = zone_end_pfn(zone);
+	const bool sync = cc->mode != MIGRATE_ASYNC;
 
 	ret = compaction_suitable(zone, cc->order);
 	switch (ret) {
@@ -1004,7 +1008,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	 * information on where the scanners should start but check that it
 	 * is initialised by ensuring the values are within zone boundaries.
 	 */
-	cc->migrate_pfn = zone->compact_cached_migrate_pfn[cc->sync];
+	cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync];
 	cc->free_pfn = zone->compact_cached_free_pfn;
 	if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) {
 		cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1);
@@ -1038,8 +1042,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 
 		nr_migrate = cc->nr_migratepages;
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
-				compaction_free, (unsigned long)cc,
-				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC,
+				compaction_free, (unsigned long)cc, cc->mode,
 				MR_COMPACTION);
 		update_nr_listpages(cc);
 		nr_remaining = cc->nr_migratepages;
@@ -1072,9 +1075,8 @@ out:
 	return ret;
 }
 
-static unsigned long compact_zone_order(struct zone *zone,
-				 int order, gfp_t gfp_mask,
-				 bool sync, bool *contended)
+static unsigned long compact_zone_order(struct zone *zone, int order,
+		gfp_t gfp_mask, enum migrate_mode mode, bool *contended)
 {
 	unsigned long ret;
 	struct compact_control cc = {
@@ -1083,7 +1085,7 @@ static unsigned long compact_zone_order(struct zone *zone,
 		.order = order,
 		.migratetype = allocflags_to_migratetype(gfp_mask),
 		.zone = zone,
-		.sync = sync,
+		.mode = mode,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1105,7 +1107,7 @@ int sysctl_extfrag_threshold = 500;
  * @order: The order of the current allocation
  * @gfp_mask: The GFP mask of the current allocation
  * @nodemask: The allowed nodes to allocate from
- * @sync: Whether migration is synchronous or not
+ * @mode: The migration mode for async, sync light, or sync migration
  * @contended: Return value that is true if compaction was aborted due to lock contention
  * @page: Optionally capture a free page of the requested order during compaction
  *
@@ -1113,7 +1115,7 @@ int sysctl_extfrag_threshold = 500;
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync, bool *contended)
+			enum migrate_mode mode, bool *contended)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
@@ -1138,7 +1140,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 								nodemask) {
 		int status;
 
-		status = compact_zone_order(zone, order, gfp_mask, sync,
+		status = compact_zone_order(zone, order, gfp_mask, mode,
 						contended);
 		rc = max(status, rc);
 
@@ -1188,7 +1190,7 @@ void compact_pgdat(pg_data_t *pgdat, int order)
 {
 	struct compact_control cc = {
 		.order = order,
-		.sync = false,
+		.mode = MIGRATE_ASYNC,
 	};
 
 	if (!order)
@@ -1201,7 +1203,7 @@ static void compact_node(int nid)
 {
 	struct compact_control cc = {
 		.order = -1,
-		.sync = true,
+		.mode = MIGRATE_SYNC,
 		.ignore_skip_hint = true,
 	};
 
diff --git a/mm/internal.h b/mm/internal.h
index c1488a3..79ed510 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -135,7 +135,7 @@ struct compact_control {
 	unsigned long nr_migratepages;	/* Number of pages to migrate */
 	unsigned long free_pfn;		/* isolate_freepages search base */
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
-	bool sync;			/* Synchronous migration */
+	enum migrate_mode mode;		/* Async or sync migration mode */
 	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
 	bool finished_update_free;	/* True when the zone cached pfns are
 					 * no longer being updated
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index bfbe0db..08e54b5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2220,7 +2220,7 @@ static struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, bool sync_migration,
+	int migratetype, enum migrate_mode mode,
 	bool *contended_compaction, bool *deferred_compaction,
 	unsigned long *did_some_progress)
 {
@@ -2234,7 +2234,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 
 	current->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
-						nodemask, sync_migration,
+						nodemask, mode,
 						contended_compaction);
 	current->flags &= ~PF_MEMALLOC;
 
@@ -2267,7 +2267,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		 * As async compaction considers a subset of pageblocks, only
 		 * defer if the failure was a sync compaction failure.
 		 */
-		if (sync_migration)
+		if (mode != MIGRATE_ASYNC)
 			defer_compaction(preferred_zone, order);
 
 		cond_resched();
@@ -2280,9 +2280,8 @@ static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, bool sync_migration,
-	bool *contended_compaction, bool *deferred_compaction,
-	unsigned long *did_some_progress)
+	int migratetype, enum migrate_mode mode, bool *contended_compaction,
+	bool *deferred_compaction, unsigned long *did_some_progress)
 {
 	return NULL;
 }
@@ -2477,7 +2476,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	int alloc_flags;
 	unsigned long pages_reclaimed = 0;
 	unsigned long did_some_progress;
-	bool sync_migration = false;
+	enum migrate_mode migration_mode = MIGRATE_ASYNC;
 	bool deferred_compaction = false;
 	bool contended_compaction = false;
 
@@ -2564,17 +2563,15 @@ rebalance:
 	 * Try direct compaction. The first pass is asynchronous. Subsequent
 	 * attempts after direct reclaim are synchronous
 	 */
-	page = __alloc_pages_direct_compact(gfp_mask, order,
-					zonelist, high_zoneidx,
-					nodemask,
-					alloc_flags, preferred_zone,
-					migratetype, sync_migration,
-					&contended_compaction,
+	page = __alloc_pages_direct_compact(gfp_mask, order, zonelist,
+					high_zoneidx, nodemask, alloc_flags,
+					preferred_zone, migratetype,
+					migration_mode, &contended_compaction,
 					&deferred_compaction,
 					&did_some_progress);
 	if (page)
 		goto got_pg;
-	sync_migration = true;
+	migration_mode = MIGRATE_SYNC_LIGHT;
 
 	/*
 	 * If compaction is deferred for high-order allocations, it is because
@@ -2649,12 +2646,10 @@ rebalance:
 		 * direct reclaim and reclaim/compaction depends on compaction
 		 * being called after reclaim so call directly if necessary
 		 */
-		page = __alloc_pages_direct_compact(gfp_mask, order,
-					zonelist, high_zoneidx,
-					nodemask,
-					alloc_flags, preferred_zone,
-					migratetype, sync_migration,
-					&contended_compaction,
+		page = __alloc_pages_direct_compact(gfp_mask, order, zonelist,
+					high_zoneidx, nodemask, alloc_flags,
+					preferred_zone, migratetype,
+					migration_mode, &contended_compaction,
 					&deferred_compaction,
 					&did_some_progress);
 		if (page)
@@ -6204,7 +6199,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 		cc->nr_migratepages -= nr_reclaimed;
 
 		ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
-				    NULL, 0, MIGRATE_SYNC, MR_CMA);
+				    NULL, 0, cc->mode, MR_CMA);
 	}
 	if (ret < 0) {
 		putback_movable_pages(&cc->migratepages);
@@ -6243,7 +6238,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		.nr_migratepages = 0,
 		.order = -1,
 		.zone = page_zone(pfn_to_page(start)),
-		.sync = true,
+		.mode = MIGRATE_SYNC,
 		.ignore_skip_hint = true,
 	};
 	INIT_LIST_HEAD(&cc.migratepages);
-- 
1.8.4.5

[PATCH 57/97] mm, compaction: terminate async compaction when rescheduling

[Mel Gorman]

From: David Rientjes <rientjes@google.com>

commit aeef4b83806f49a0c454b7d4578671b71045bee2 upstream.

Async compaction terminates prematurely when need_resched(), see
compact_checklock_irqsave().  This can never trigger, however, if the
cond_resched() in isolate_migratepages_range() always takes care of the
scheduling.

If the cond_resched() actually triggers, then terminate this pageblock
scan for async compaction as well.

Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index cebdeca..4933fde 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -495,8 +495,13 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			return 0;
 	}
 
+	if (cond_resched()) {
+		/* Async terminates prematurely on need_resched() */
+		if (cc->mode == MIGRATE_ASYNC)
+			return 0;
+	}
+
 	/* Time to isolate some pages for migration */
-	cond_resched();
 	for (; low_pfn < end_pfn; low_pfn++) {
 		/* give a chance to irqs before checking need_resched() */
 		if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) {
-- 
1.8.4.5

[PATCH 58/97] mm/compaction: do not count migratepages when unnecessary

[Mel Gorman]

From: Vlastimil Babka <vbabka@suse.cz>

commit f8c9301fa5a2a8b873c67f2a3d8230d5c13f61b7 upstream.

During compaction, update_nr_listpages() has been used to count remaining
non-migrated and free pages after a call to migrage_pages().  The
freepages counting has become unneccessary, and it turns out that
migratepages counting is also unnecessary in most cases.

The only situation when it's needed to count cc->migratepages is when
migrate_pages() returns with a negative error code.  Otherwise, the
non-negative return value is the number of pages that were not migrated,
which is exactly the count of remaining pages in the cc->migratepages
list.

Furthermore, any non-zero count is only interesting for the tracepoint of
mm_compaction_migratepages events, because after that all remaining
unmigrated pages are put back and their count is set to 0.

This patch therefore removes update_nr_listpages() completely, and changes
the tracepoint definition so that the manual counting is done only when
the tracepoint is enabled, and only when migrate_pages() returns a
negative error code.

Furthermore, migrate_pages() and the tracepoints won't be called when
there's nothing to migrate.  This potentially avoids some wasted cycles
and reduces the volume of uninteresting mm_compaction_migratepages events
where "nr_migrated=0 nr_failed=0".  In the stress-highalloc mmtest, this
was about 75% of the events.  The mm_compaction_isolate_migratepages event
is better for determining that nothing was isolated for migration, and
this one was just duplicating the info.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/trace/events/compaction.h | 25 +++++++++++++++++++++----
 mm/compaction.c                   | 31 +++++++------------------------
 2 files changed, 28 insertions(+), 28 deletions(-)

diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index 06f544e..c6814b9 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -5,6 +5,7 @@
 #define _TRACE_COMPACTION_H
 
 #include <linux/types.h>
+#include <linux/list.h>
 #include <linux/tracepoint.h>
 #include <trace/events/gfpflags.h>
 
@@ -47,10 +48,11 @@ DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages,
 
 TRACE_EVENT(mm_compaction_migratepages,
 
-	TP_PROTO(unsigned long nr_migrated,
-		unsigned long nr_failed),
+	TP_PROTO(unsigned long nr_all,
+		int migrate_rc,
+		struct list_head *migratepages),
 
-	TP_ARGS(nr_migrated, nr_failed),
+	TP_ARGS(nr_all, migrate_rc, migratepages),
 
 	TP_STRUCT__entry(
 		__field(unsigned long, nr_migrated)
@@ -58,7 +60,22 @@ TRACE_EVENT(mm_compaction_migratepages,
 	),
 
 	TP_fast_assign(
-		__entry->nr_migrated = nr_migrated;
+		unsigned long nr_failed = 0;
+		struct list_head *page_lru;
+
+		/*
+		 * migrate_pages() returns either a non-negative number
+		 * with the number of pages that failed migration, or an
+		 * error code, in which case we need to count the remaining
+		 * pages manually
+		 */
+		if (migrate_rc >= 0)
+			nr_failed = migrate_rc;
+		else
+			list_for_each(page_lru, migratepages)
+				nr_failed++;
+
+		__entry->nr_migrated = nr_all - nr_failed;
 		__entry->nr_failed = nr_failed;
 	),
 
diff --git a/mm/compaction.c b/mm/compaction.c
index 4933fde..88b33e6 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -820,22 +820,6 @@ static void compaction_free(struct page *page, unsigned long data)
 	cc->nr_freepages++;
 }
 
-/*
- * We cannot control nr_migratepages fully when migration is running as
- * migrate_pages() has no knowledge of of compact_control.  When migration is
- * complete, we count the number of pages on the list by hand.
- */
-static void update_nr_listpages(struct compact_control *cc)
-{
-	int nr_migratepages = 0;
-	struct page *page;
-
-	list_for_each_entry(page, &cc->migratepages, lru)
-		nr_migratepages++;
-
-	cc->nr_migratepages = nr_migratepages;
-}
-
 /* possible outcome of isolate_migratepages */
 typedef enum {
 	ISOLATE_ABORT,		/* Abort compaction now */
@@ -1030,7 +1014,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	migrate_prep_local();
 
 	while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
-		unsigned long nr_migrate, nr_remaining;
 		int err;
 
 		switch (isolate_migratepages(zone, cc)) {
@@ -1045,20 +1028,20 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 			;
 		}
 
-		nr_migrate = cc->nr_migratepages;
+		if (!cc->nr_migratepages)
+			continue;
+
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
 				compaction_free, (unsigned long)cc, cc->mode,
 				MR_COMPACTION);
-		update_nr_listpages(cc);
-		nr_remaining = cc->nr_migratepages;
 
-		trace_mm_compaction_migratepages(nr_migrate - nr_remaining,
-						nr_remaining);
+		trace_mm_compaction_migratepages(cc->nr_migratepages, err,
+							&cc->migratepages);
 
-		/* Release isolated pages not migrated */
+		/* All pages were either migrated or will be released */
+		cc->nr_migratepages = 0;
 		if (err) {
 			putback_movable_pages(&cc->migratepages);
-			cc->nr_migratepages = 0;
 			/*
 			 * migrate_pages() may return -ENOMEM when scanners meet
 			 * and we want compact_finished() to detect it
-- 
1.8.4.5

[PATCH 59/97] mm/compaction: avoid rescanning pageblocks in isolate_freepages

[Mel Gorman]

From: Vlastimil Babka <vbabka@suse.cz>

commit e9ade569910a82614ff5f2c2cea2b65a8d785da4 upstream.

The compaction free scanner in isolate_freepages() currently remembers PFN
of the highest pageblock where it successfully isolates, to be used as the
starting pageblock for the next invocation.  The rationale behind this is
that page migration might return free pages to the allocator when
migration fails and we don't want to skip them if the compaction
continues.

Since migration now returns free pages back to compaction code where they
can be reused, this is no longer a concern.  This patch changes
isolate_freepages() so that the PFN for restarting is updated with each
pageblock where isolation is attempted.  Using stress-highalloc from
mmtests, this resulted in 10% reduction of the pages scanned by the free
scanner.

Note that the somewhat similar functionality that records highest
successful pageblock in zone->compact_cached_free_pfn, remains unchanged.
This cache is used when the whole compaction is restarted, not for
multiple invocations of the free scanner during single compaction.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 22 +++++++---------------
 1 file changed, 7 insertions(+), 15 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 88b33e6..44aa2d4 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -686,7 +686,6 @@ static void isolate_freepages(struct zone *zone,
 	unsigned long block_start_pfn;	/* start of current pageblock */
 	unsigned long block_end_pfn;	/* end of current pageblock */
 	unsigned long low_pfn;	     /* lowest pfn scanner is able to scan */
-	unsigned long next_free_pfn; /* start pfn for scaning at next round */
 	int nr_freepages = cc->nr_freepages;
 	struct list_head *freelist = &cc->freepages;
 
@@ -707,12 +706,6 @@ static void isolate_freepages(struct zone *zone,
 	low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
 
 	/*
-	 * If no pages are isolated, the block_start_pfn < low_pfn check
-	 * will kick in.
-	 */
-	next_free_pfn = 0;
-
-	/*
 	 * Isolate free pages until enough are available to migrate the
 	 * pages on cc->migratepages. We stop searching if the migrate
 	 * and free page scanners meet or enough free pages are isolated.
@@ -752,19 +745,19 @@ static void isolate_freepages(struct zone *zone,
 			continue;
 
 		/* Found a block suitable for isolating free pages from */
+		cc->free_pfn = block_start_pfn;
 		isolated = isolate_freepages_block(cc, block_start_pfn,
 					block_end_pfn, freelist, false);
 		nr_freepages += isolated;
 
 		/*
-		 * Record the highest PFN we isolated pages from. When next
-		 * looking for free pages, the search will restart here as
-		 * page migration may have returned some pages to the allocator
+		 * Set a flag that we successfully isolated in this pageblock.
+		 * In the next loop iteration, zone->compact_cached_free_pfn
+		 * will not be updated and thus it will effectively contain the
+		 * highest pageblock we isolated pages from.
 		 */
-		if (isolated && next_free_pfn == 0) {
+		if (isolated)
 			cc->finished_update_free = true;
-			next_free_pfn = block_start_pfn;
-		}
 	}
 
 	/* split_free_page does not map the pages */
@@ -775,9 +768,8 @@ static void isolate_freepages(struct zone *zone,
 	 * so that compact_finished() may detect this
 	 */
 	if (block_start_pfn < low_pfn)
-		next_free_pfn = cc->migrate_pfn;
+		cc->free_pfn = cc->migrate_pfn;
 
-	cc->free_pfn = next_free_pfn;
 	cc->nr_freepages = nr_freepages;
 }
 
-- 
1.8.4.5

[PATCH 60/97] mm, compaction: properly signal and act upon lock and need_sched() contention

[Mel Gorman]

From: Vlastimil Babka <vbabka@suse.cz>

commit be9765722e6b7ece8263cbab857490332339bd6f upstream.

Compaction uses compact_checklock_irqsave() function to periodically check
for lock contention and need_resched() to either abort async compaction,
or to free the lock, schedule and retake the lock.  When aborting,
cc->contended is set to signal the contended state to the caller.  Two
problems have been identified in this mechanism.

First, compaction also calls directly cond_resched() in both scanners when
no lock is yet taken.  This call either does not abort async compaction,
or set cc->contended appropriately.  This patch introduces a new
compact_should_abort() function to achieve both.  In isolate_freepages(),
the check frequency is reduced to once by SWAP_CLUSTER_MAX pageblocks to
match what the migration scanner does in the preliminary page checks.  In
case a pageblock is found suitable for calling isolate_freepages_block(),
the checks within there are done on higher frequency.

Second, isolate_freepages() does not check if isolate_freepages_block()
aborted due to contention, and advances to the next pageblock.  This
violates the principle of aborting on contention, and might result in
pageblocks not being scanned completely, since the scanning cursor is
advanced.  This problem has been noticed in the code by Joonsoo Kim when
reviewing related patches.  This patch makes isolate_freepages_block()
check the cc->contended flag and abort.

In case isolate_freepages() has already isolated some pages before
aborting due to contention, page migration will proceed, which is OK since
we do not want to waste the work that has been done, and page migration
has own checks for contention.  However, we do not want another isolation
attempt by either of the scanners, so cc->contended flag check is added
also to compaction_alloc() and compact_finished() to make sure compaction
is aborted right after the migration.

The outcome of the patch should be reduced lock contention by async
compaction and lower latencies for higher-order allocations where direct
compaction is involved.

[akpm@linux-foundation.org: fix typo in comment]
Reported-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Tested-by: Shawn Guo <shawn.guo@linaro.org>
Tested-by: Kevin Hilman <khilman@linaro.org>
Tested-by: Stephen Warren <swarren@nvidia.com>
Tested-by: Fabio Estevam <fabio.estevam@freescale.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/compaction.c | 54 ++++++++++++++++++++++++++++++++++++++++++++----------
 mm/internal.h   |  5 ++++-
 2 files changed, 48 insertions(+), 11 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 44aa2d4..adb6d05 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -222,6 +222,30 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
 	return true;
 }
 
+/*
+ * Aside from avoiding lock contention, compaction also periodically checks
+ * need_resched() and either schedules in sync compaction or aborts async
+ * compaction. This is similar to what compact_checklock_irqsave() does, but
+ * is used where no lock is concerned.
+ *
+ * Returns false when no scheduling was needed, or sync compaction scheduled.
+ * Returns true when async compaction should abort.
+ */
+static inline bool compact_should_abort(struct compact_control *cc)
+{
+	/* async compaction aborts if contended */
+	if (need_resched()) {
+		if (cc->mode == MIGRATE_ASYNC) {
+			cc->contended = true;
+			return true;
+		}
+
+		cond_resched();
+	}
+
+	return false;
+}
+
 /* Returns true if the page is within a block suitable for migration to */
 static bool suitable_migration_target(struct page *page)
 {
@@ -495,11 +519,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			return 0;
 	}
 
-	if (cond_resched()) {
-		/* Async terminates prematurely on need_resched() */
-		if (cc->mode == MIGRATE_ASYNC)
-			return 0;
-	}
+	if (compact_should_abort(cc))
+		return 0;
 
 	/* Time to isolate some pages for migration */
 	for (; low_pfn < end_pfn; low_pfn++) {
@@ -718,9 +739,11 @@ static void isolate_freepages(struct zone *zone,
 		/*
 		 * This can iterate a massively long zone without finding any
 		 * suitable migration targets, so periodically check if we need
-		 * to schedule.
+		 * to schedule, or even abort async compaction.
 		 */
-		cond_resched();
+		if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
+						&& compact_should_abort(cc))
+			break;
 
 		if (!pfn_valid(block_start_pfn))
 			continue;
@@ -758,6 +781,13 @@ static void isolate_freepages(struct zone *zone,
 		 */
 		if (isolated)
 			cc->finished_update_free = true;
+
+		/*
+		 * isolate_freepages_block() might have aborted due to async
+		 * compaction being contended
+		 */
+		if (cc->contended)
+			break;
 	}
 
 	/* split_free_page does not map the pages */
@@ -784,9 +814,13 @@ static struct page *compaction_alloc(struct page *migratepage,
 	struct compact_control *cc = (struct compact_control *)data;
 	struct page *freepage;
 
-	/* Isolate free pages if necessary */
+	/*
+	 * Isolate free pages if necessary, and if we are not aborting due to
+	 * contention.
+	 */
 	if (list_empty(&cc->freepages)) {
-		isolate_freepages(cc->zone, cc);
+		if (!cc->contended)
+			isolate_freepages(cc->zone, cc);
 
 		if (list_empty(&cc->freepages))
 			return NULL;
@@ -856,7 +890,7 @@ static int compact_finished(struct zone *zone,
 	unsigned int order;
 	unsigned long watermark;
 
-	if (fatal_signal_pending(current))
+	if (cc->contended || fatal_signal_pending(current))
 		return COMPACT_PARTIAL;
 
 	/* Compaction run completes if the migrate and free scanner meet */
diff --git a/mm/internal.h b/mm/internal.h
index 79ed510..d610f7c 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -145,7 +145,10 @@ struct compact_control {
 	int order;			/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
-	bool contended;			/* True if a lock was contended */
+	bool contended;			/* True if a lock was contended, or
+					 * need_resched() true during async
+					 * compaction
+					 */
 };
 
 unsigned long
-- 
1.8.4.5

[PATCH 61/97] x86/mm: In the PTE swapout page reclaim case clear the accessed bit instead of flushing the TLB

[Mel Gorman]

From: Shaohua Li <shli@kernel.org>

commit b13b1d2d8692b437203de7a404c6b809d2cc4d99 upstream.

We use the accessed bit to age a page at page reclaim time,
and currently we also flush the TLB when doing so.

But in some workloads TLB flush overhead is very heavy. In my
simple multithreaded app with a lot of swap to several pcie
SSDs, removing the tlb flush gives about 20% ~ 30% swapout
speedup.

Fortunately just removing the TLB flush is a valid optimization:
on x86 CPUs, clearing the accessed bit without a TLB flush
doesn't cause data corruption.

It could cause incorrect page aging and the (mistaken) reclaim of
hot pages, but the chance of that should be relatively low.

So as a performance optimization don't flush the TLB when
clearing the accessed bit, it will eventually be flushed by
a context switch or a VM operation anyway. [ In the rare
event of it not getting flushed for a long time the delay
shouldn't really matter because there's no real memory
pressure for swapout to react to. ]

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Shaohua Li <shli@fusionio.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: linux-mm@kvack.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20140408075809.GA1764@kernel.org
[ Rewrote the changelog and the code comments. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 arch/x86/mm/pgtable.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index dfa537a..5da29d0 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -386,13 +386,20 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 int ptep_clear_flush_young(struct vm_area_struct *vma,
 			   unsigned long address, pte_t *ptep)
 {
-	int young;
-
-	young = ptep_test_and_clear_young(vma, address, ptep);
-	if (young)
-		flush_tlb_page(vma, address);
-
-	return young;
+	/*
+	 * On x86 CPUs, clearing the accessed bit without a TLB flush
+	 * doesn't cause data corruption. [ It could cause incorrect
+	 * page aging and the (mistaken) reclaim of hot pages, but the
+	 * chance of that should be relatively low. ]
+	 *
+	 * So as a performance optimization don't flush the TLB when
+	 * clearing the accessed bit, it will eventually be flushed by
+	 * a context switch or a VM operation anyway. [ In the rare
+	 * event of it not getting flushed for a long time the delay
+	 * shouldn't really matter because there's no real memory
+	 * pressure for swapout to react to. ]
+	 */
+	return ptep_test_and_clear_young(vma, address, ptep);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-- 
1.8.4.5

[PATCH 62/97] mm: fix direct reclaim writeback regression

[Mel Gorman]

From: Hugh Dickins <hughd@google.com>

commit 8bdd638091605dc66d92c57c4b80eb87fffc15f7 upstream.

Shortly before 3.16-rc1, Dave Jones reported:

  WARNING: CPU: 3 PID: 19721 at fs/xfs/xfs_aops.c:971
           xfs_vm_writepage+0x5ce/0x630 [xfs]()
  CPU: 3 PID: 19721 Comm: trinity-c61 Not tainted 3.15.0+ #3
  Call Trace:
    xfs_vm_writepage+0x5ce/0x630 [xfs]
    shrink_page_list+0x8f9/0xb90
    shrink_inactive_list+0x253/0x510
    shrink_lruvec+0x563/0x6c0
    shrink_zone+0x3b/0x100
    shrink_zones+0x1f1/0x3c0
    try_to_free_pages+0x164/0x380
    __alloc_pages_nodemask+0x822/0xc90
    alloc_pages_vma+0xaf/0x1c0
    handle_mm_fault+0xa31/0xc50
  etc.

 970   if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
 971                   PF_MEMALLOC))

I did not respond at the time, because a glance at the PageDirty block
in shrink_page_list() quickly shows that this is impossible: we don't do
writeback on file pages (other than tmpfs) from direct reclaim nowadays.
Dave was hallucinating, but it would have been disrespectful to say so.

However, my own /var/log/messages now shows similar complaints

  WARNING: CPU: 1 PID: 28814 at fs/ext4/inode.c:1881 ext4_writepage+0xa7/0x38b()
  WARNING: CPU: 0 PID: 27347 at fs/ext4/inode.c:1764 ext4_writepage+0xa7/0x38b()

from stressing some mmotm trees during July.

Could a dirty xfs or ext4 file page somehow get marked PageSwapBacked,
so fail shrink_page_list()'s page_is_file_cache() test, and so proceed
to mapping->a_ops->writepage()?

Yes, 3.16-rc1's commit 68711a746345 ("mm, migration: add destination
page freeing callback") has provided such a way to compaction: if
migrating a SwapBacked page fails, its newpage may be put back on the
list for later use with PageSwapBacked still set, and nothing will clear
it.

Whether that can do anything worse than issue WARN_ON_ONCEs, and get
some statistics wrong, is unclear: easier to fix than to think through
the consequences.

Fixing it here, before the put_new_page(), addresses the bug directly,
but is probably the worst place to fix it.  Page migration is doing too
many parts of the job on too many levels: fixing it in
move_to_new_page() to complement its SetPageSwapBacked would be
preferable, except why is it (and newpage->mapping and newpage->index)
done there, rather than down in migrate_page_move_mapping(), once we are
sure of success? Not a cleanup to get into right now, especially not
with memcg cleanups coming in 3.17.

Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/migrate.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index e397bd2..96d4d81 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -919,9 +919,10 @@ out:
 	 * it.  Otherwise, putback_lru_page() will drop the reference grabbed
 	 * during isolation.
 	 */
-	if (rc != MIGRATEPAGE_SUCCESS && put_new_page)
+	if (rc != MIGRATEPAGE_SUCCESS && put_new_page) {
+		ClearPageSwapBacked(newpage);
 		put_new_page(newpage, private);
-	else
+	} else
 		putback_lru_page(newpage);
 
 	if (result) {
-- 
1.8.4.5

[PATCH 63/97] fs/superblock: unregister sb shrinker before ->kill_sb()

[Mel Gorman]

From: Dave Chinner <david@fromorbit.com>

commit 28f2cd4f6da24a1aa06c226618ed5ad69e13df64 upstream.

This series is aimed at regressions noticed during reclaim activity.  The
first two patches are shrinker patches that were posted ages ago but never
merged for reasons that are unclear to me.  I'm posting them again to see
if there was a reason they were dropped or if they just got lost.  Dave?
Time?  The last patch adjusts proportional reclaim.  Yuanhan Liu, can you
retest the vm scalability test cases on a larger machine?  Hugh, does this
work for you on the memcg test cases?

Based on ext4, I get the following results but unfortunately my larger
test machines are all unavailable so this is based on a relatively small
machine.

postmark
                                  3.15.0-rc5            3.15.0-rc5
                                     vanilla       proportion-v1r4
Ops/sec Transactions         21.00 (  0.00%)       25.00 ( 19.05%)
Ops/sec FilesCreate          39.00 (  0.00%)       45.00 ( 15.38%)
Ops/sec CreateTransact       10.00 (  0.00%)       12.00 ( 20.00%)
Ops/sec FilesDeleted       6202.00 (  0.00%)     6202.00 (  0.00%)
Ops/sec DeleteTransact       11.00 (  0.00%)       12.00 (  9.09%)
Ops/sec DataRead/MB          25.97 (  0.00%)       30.02 ( 15.59%)
Ops/sec DataWrite/MB         49.99 (  0.00%)       57.78 ( 15.58%)

ffsb (mail server simulator)
                                 3.15.0-rc5             3.15.0-rc5
                                    vanilla        proportion-v1r4
Ops/sec readall           9402.63 (  0.00%)      9805.74 (  4.29%)
Ops/sec create            4695.45 (  0.00%)      4781.39 (  1.83%)
Ops/sec delete             173.72 (  0.00%)       177.23 (  2.02%)
Ops/sec Transactions     14271.80 (  0.00%)     14764.37 (  3.45%)
Ops/sec Read                37.00 (  0.00%)        38.50 (  4.05%)
Ops/sec Write               18.20 (  0.00%)        18.50 (  1.65%)

dd of a large file
                                3.15.0-rc5            3.15.0-rc5
                                   vanilla       proportion-v1r4
WallTime DownloadTar       75.00 (  0.00%)       61.00 ( 18.67%)
WallTime DD               423.00 (  0.00%)      401.00 (  5.20%)
WallTime Delete             2.00 (  0.00%)        5.00 (-150.00%)

stutter (times mmap latency during large amounts of IO)

                            3.15.0-rc5            3.15.0-rc5
                               vanilla       proportion-v1r4
Unit >5ms Delays  80252.0000 (  0.00%)  81523.0000 ( -1.58%)
Unit Mmap min         8.2118 (  0.00%)      8.3206 ( -1.33%)
Unit Mmap mean       17.4614 (  0.00%)     17.2868 (  1.00%)
Unit Mmap stddev     24.9059 (  0.00%)     34.6771 (-39.23%)
Unit Mmap max      2811.6433 (  0.00%)   2645.1398 (  5.92%)
Unit Mmap 90%        20.5098 (  0.00%)     18.3105 ( 10.72%)
Unit Mmap 93%        22.9180 (  0.00%)     20.1751 ( 11.97%)
Unit Mmap 95%        25.2114 (  0.00%)     22.4988 ( 10.76%)
Unit Mmap 99%        46.1430 (  0.00%)     43.5952 (  5.52%)
Unit Ideal  Tput     85.2623 (  0.00%)     78.8906 (  7.47%)
Unit Tput min        44.0666 (  0.00%)     43.9609 (  0.24%)
Unit Tput mean       45.5646 (  0.00%)     45.2009 (  0.80%)
Unit Tput stddev      0.9318 (  0.00%)      1.1084 (-18.95%)
Unit Tput max        46.7375 (  0.00%)     46.7539 ( -0.04%)

This patch (of 3):

We will like to unregister the sb shrinker before ->kill_sb().  This will
allow cached objects to be counted without call to grab_super_passive() to
update ref count on sb.  We want to avoid locking during memory
reclamation especially when we are skipping the memory reclaim when we are
out of cached objects.

This is safe because grab_super_passive does a try-lock on the
sb->s_umount now, and so if we are in the unmount process, it won't ever
block.  That means what used to be a deadlock and races we were avoiding
by using grab_super_passive() is now:

        shrinker                        umount

        down_read(shrinker_rwsem)
                                        down_write(sb->s_umount)
                                        shrinker_unregister
                                          down_write(shrinker_rwsem)
                                            <blocks>
        grab_super_passive(sb)
          down_read_trylock(sb->s_umount)
            <fails>
        <shrinker aborts>
        ....
        <shrinkers finish running>
        up_read(shrinker_rwsem)
                                          <unblocks>
                                          <removes shrinker>
                                          up_write(shrinker_rwsem)
                                        ->kill_sb()
                                        ....

So it is safe to deregister the shrinker before ->kill_sb().

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Chinner <david@fromorbit.com>
Tested-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Jan Kara <jack@suse.cz>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 fs/super.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/fs/super.c b/fs/super.c
index d127de2..f730016 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -321,10 +321,8 @@ void deactivate_locked_super(struct super_block *s)
 	struct file_system_type *fs = s->s_type;
 	if (atomic_dec_and_test(&s->s_active)) {
 		cleancache_invalidate_fs(s);
-		fs->kill_sb(s);
-
-		/* caches are now gone, we can safely kill the shrinker now */
 		unregister_shrinker(&s->s_shrink);
+		fs->kill_sb(s);
 
 		put_filesystem(fs);
 		put_super(s);
-- 
1.8.4.5

[PATCH 64/97] fs/superblock: avoid locking counting inodes and dentries before reclaiming them

[Mel Gorman]

From: Tim Chen <tim.c.chen@linux.intel.com>

commit d23da150a37c9fe3cc83dbaf71b3e37fd434ed52 upstream.

We remove the call to grab_super_passive in call to super_cache_count.
This becomes a scalability bottleneck as multiple threads are trying to do
memory reclamation, e.g.  when we are doing large amount of file read and
page cache is under pressure.  The cached objects quickly got reclaimed
down to 0 and we are aborting the cache_scan() reclaim.  But counting
creates a log jam acquiring the sb_lock.

We are holding the shrinker_rwsem which ensures the safety of call to
list_lru_count_node() and s_op->nr_cached_objects.  The shrinker is
unregistered now before ->kill_sb() so the operation is safe when we are
doing unmount.

The impact will depend heavily on the machine and the workload but for a
small machine using postmark tuned to use 4xRAM size the results were

                                  3.15.0-rc5            3.15.0-rc5
                                     vanilla         shrinker-v1r1
Ops/sec Transactions         21.00 (  0.00%)       24.00 ( 14.29%)
Ops/sec FilesCreate          39.00 (  0.00%)       44.00 ( 12.82%)
Ops/sec CreateTransact       10.00 (  0.00%)       12.00 ( 20.00%)
Ops/sec FilesDeleted       6202.00 (  0.00%)     6202.00 (  0.00%)
Ops/sec DeleteTransact       11.00 (  0.00%)       12.00 (  9.09%)
Ops/sec DataRead/MB          25.97 (  0.00%)       29.10 ( 12.05%)
Ops/sec DataWrite/MB         49.99 (  0.00%)       56.02 ( 12.06%)

ffsb running in a configuration that is meant to simulate a mail server showed

                                 3.15.0-rc5             3.15.0-rc5
                                    vanilla          shrinker-v1r1
Ops/sec readall           9402.63 (  0.00%)      9567.97 (  1.76%)
Ops/sec create            4695.45 (  0.00%)      4735.00 (  0.84%)
Ops/sec delete             173.72 (  0.00%)       179.83 (  3.52%)
Ops/sec Transactions     14271.80 (  0.00%)     14482.81 (  1.48%)
Ops/sec Read                37.00 (  0.00%)        37.60 (  1.62%)
Ops/sec Write               18.20 (  0.00%)        18.30 (  0.55%)

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Chinner <david@fromorbit.com>
Tested-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Jan Kara <jack@suse.cz>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 fs/super.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/fs/super.c b/fs/super.c
index f730016..fb68a4c 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -112,9 +112,14 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 
 	sb = container_of(shrink, struct super_block, s_shrink);
 
-	if (!grab_super_passive(sb))
-		return 0;
-
+	/*
+	 * Don't call grab_super_passive as it is a potential
+	 * scalability bottleneck. The counts could get updated
+	 * between super_cache_count and super_cache_scan anyway.
+	 * Call to super_cache_count with shrinker_rwsem held
+	 * ensures the safety of call to list_lru_count_node() and
+	 * s_op->nr_cached_objects().
+	 */
 	if (sb->s_op && sb->s_op->nr_cached_objects)
 		total_objects = sb->s_op->nr_cached_objects(sb,
 						 sc->nid);
@@ -125,7 +130,6 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 						 sc->nid);
 
 	total_objects = vfs_pressure_ratio(total_objects);
-	drop_super(sb);
 	return total_objects;
 }
 
-- 
1.8.4.5

[PATCH 65/97] mm: vmscan: use proportional scanning during direct reclaim and full scan at DEF_PRIORITY

[Mel Gorman]

commit 1a501907bbea8e6ebb0b16cf6db9e9cbf1d2c813 upstream.

Commit "mm: vmscan: obey proportional scanning requirements for kswapd"
ensured that file/anon lists were scanned proportionally for reclaim from
kswapd but ignored it for direct reclaim.  The intent was to minimse
direct reclaim latency but Yuanhan Liu pointer out that it substitutes one
long stall for many small stalls and distorts aging for normal workloads
like streaming readers/writers.  Hugh Dickins pointed out that a
side-effect of the same commit was that when one LRU list dropped to zero
that the entirety of the other list was shrunk leading to excessive
reclaim in memcgs.  This patch scans the file/anon lists proportionally
for direct reclaim to similarly age page whether reclaimed by kswapd or
direct reclaim but takes care to abort reclaim if one LRU drops to zero
after reclaiming the requested number of pages.

Based on ext4 and using the Intel VM scalability test

                                              3.15.0-rc5            3.15.0-rc5
                                                shrinker            proportion
Unit  lru-file-readonce    elapsed      5.3500 (  0.00%)      5.4200 ( -1.31%)
Unit  lru-file-readonce time_range      0.2700 (  0.00%)      0.1400 ( 48.15%)
Unit  lru-file-readonce time_stddv      0.1148 (  0.00%)      0.0536 ( 53.33%)
Unit lru-file-readtwice    elapsed      8.1700 (  0.00%)      8.1700 (  0.00%)
Unit lru-file-readtwice time_range      0.4300 (  0.00%)      0.2300 ( 46.51%)
Unit lru-file-readtwice time_stddv      0.1650 (  0.00%)      0.0971 ( 41.16%)

The test cases are running multiple dd instances reading sparse files. The results are within
the noise for the small test machine. The impact of the patch is more noticable from the vmstats

                            3.15.0-rc5  3.15.0-rc5
                              shrinker  proportion
Minor Faults                     35154       36784
Major Faults                       611        1305
Swap Ins                           394        1651
Swap Outs                         4394        5891
Allocation stalls               118616       44781
Direct pages scanned           4935171     4602313
Kswapd pages scanned          15921292    16258483
Kswapd pages reclaimed        15913301    16248305
Direct pages reclaimed         4933368     4601133
Kswapd efficiency                  99%         99%
Kswapd velocity             670088.047  682555.961
Direct efficiency                  99%         99%
Direct velocity             207709.217  193212.133
Percentage direct scans            23%         22%
Page writes by reclaim        4858.000    6232.000
Page writes file                   464         341
Page writes anon                  4394        5891

Note that there are fewer allocation stalls even though the amount
of direct reclaim scanning is very approximately the same.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Tested-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/vmscan.c | 36 +++++++++++++++++++++++++-----------
 1 file changed, 25 insertions(+), 11 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 96cd5c4..e568be9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2018,13 +2018,27 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	unsigned long nr_reclaimed = 0;
 	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
 	struct blk_plug plug;
-	bool scan_adjusted = false;
+	bool scan_adjusted;
 
 	get_scan_count(lruvec, sc, nr);
 
 	/* Record the original scan target for proportional adjustments later */
 	memcpy(targets, nr, sizeof(nr));
 
+	/*
+	 * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal
+	 * event that can occur when there is little memory pressure e.g.
+	 * multiple streaming readers/writers. Hence, we do not abort scanning
+	 * when the requested number of pages are reclaimed when scanning at
+	 * DEF_PRIORITY on the assumption that the fact we are direct
+	 * reclaiming implies that kswapd is not keeping up and it is best to
+	 * do a batch of work at once. For memcg reclaim one check is made to
+	 * abort proportional reclaim if either the file or anon lru has already
+	 * dropped to zero at the first pass.
+	 */
+	scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() &&
+			 sc->priority == DEF_PRIORITY);
+
 	blk_start_plug(&plug);
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
 					nr[LRU_INACTIVE_FILE]) {
@@ -2045,17 +2059,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 			continue;
 
 		/*
-		 * For global direct reclaim, reclaim only the number of pages
-		 * requested. Less care is taken to scan proportionally as it
-		 * is more important to minimise direct reclaim stall latency
-		 * than it is to properly age the LRU lists.
-		 */
-		if (global_reclaim(sc) && !current_is_kswapd())
-			break;
-
-		/*
 		 * For kswapd and memcg, reclaim at least the number of pages
-		 * requested. Ensure that the anon and file LRUs shrink
+		 * requested. Ensure that the anon and file LRUs are scanned
 		 * proportionally what was requested by get_scan_count(). We
 		 * stop reclaiming one LRU and reduce the amount scanning
 		 * proportional to the original scan target.
@@ -2063,6 +2068,15 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
 		nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];
 
+		/*
+		 * It's just vindictive to attack the larger once the smaller
+		 * has gone to zero.  And given the way we stop scanning the
+		 * smaller below, this makes sure that we only make one nudge
+		 * towards proportionality once we've got nr_to_reclaim.
+		 */
+		if (!nr_file || !nr_anon)
+			break;
+
 		if (nr_file > nr_anon) {
 			unsigned long scan_target = targets[LRU_INACTIVE_ANON] +
 						targets[LRU_ACTIVE_ANON] + 1;
-- 
1.8.4.5

[PATCH 66/97] mm/page_alloc: prevent MIGRATE_RESERVE pages from being misplaced

[Mel Gorman]

From: Vlastimil Babka <vbabka@suse.cz>

commit 5bcc9f86ef09a933255ee66bd899d4601785dad5 upstream.

For the MIGRATE_RESERVE pages, it is useful when they do not get
misplaced on free_list of other migratetype, otherwise they might get
allocated prematurely and e.g.  fragment the MIGRATE_RESEVE pageblocks.
While this cannot be avoided completely when allocating new
MIGRATE_RESERVE pageblocks in min_free_kbytes sysctl handler, we should
prevent the misplacement where possible.

Currently, it is possible for the misplacement to happen when a
MIGRATE_RESERVE page is allocated on pcplist through rmqueue_bulk() as a
fallback for other desired migratetype, and then later freed back
through free_pcppages_bulk() without being actually used.  This happens
because free_pcppages_bulk() uses get_freepage_migratetype() to choose
the free_list, and rmqueue_bulk() calls set_freepage_migratetype() with
the *desired* migratetype and not the page's original MIGRATE_RESERVE
migratetype.

This patch fixes the problem by moving the call to
set_freepage_migratetype() from rmqueue_bulk() down to
__rmqueue_smallest() and __rmqueue_fallback() where the actual page's
migratetype (e.g.  from which free_list the page is taken from) is used.
Note that this migratetype might be different from the pageblock's
migratetype due to freepage stealing decisions.  This is OK, as page
stealing never uses MIGRATE_RESERVE as a fallback, and also takes care
to leave all MIGRATE_CMA pages on the correct freelist.

Therefore, as an additional benefit, the call to
get_pageblock_migratetype() from rmqueue_bulk() when CMA is enabled, can
be removed completely.  This relies on the fact that MIGRATE_CMA
pageblocks are created only during system init, and the above.  The
related is_migrate_isolate() check is also unnecessary, as memory
isolation has other ways to move pages between freelists, and drain pcp
lists containing pages that should be isolated.  The buffered_rmqueue()
can also benefit from calling get_freepage_migratetype() instead of
get_pageblock_migratetype().

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Yong-Taek Lee <ytk.lee@samsung.com>
Reported-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Suggested-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Suggested-by: Mel Gorman <mgorman@suse.de>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: "Wang, Yalin" <Yalin.Wang@sonymobile.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 08e54b5..7139ed7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -918,6 +918,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
 		rmv_page_order(page);
 		area->nr_free--;
 		expand(zone, page, order, current_order, area, migratetype);
+		set_freepage_migratetype(page, migratetype);
 		return page;
 	}
 
@@ -1044,7 +1045,9 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page,
 
 	/*
 	 * When borrowing from MIGRATE_CMA, we need to release the excess
-	 * buddy pages to CMA itself.
+	 * buddy pages to CMA itself. We also ensure the freepage_migratetype
+	 * is set to CMA so it is returned to the correct freelist in case
+	 * the page ends up being not actually allocated from the pcp lists.
 	 */
 	if (is_migrate_cma(fallback_type))
 		return fallback_type;
@@ -1112,6 +1115,12 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 
 			expand(zone, page, order, current_order, area,
 			       new_type);
+			/* The freepage_migratetype may differ from pageblock's
+			 * migratetype depending on the decisions in
+			 * try_to_steal_freepages. This is OK as long as it does
+			 * not differ for MIGRATE_CMA type.
+			 */
+			set_freepage_migratetype(page, new_type);
 
 			trace_mm_page_alloc_extfrag(page, order, current_order,
 				start_migratetype, migratetype, new_type);
@@ -1162,7 +1171,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			unsigned long count, struct list_head *list,
 			int migratetype, int cold)
 {
-	int mt = migratetype, i;
+	int i;
 
 	spin_lock(&zone->lock);
 	for (i = 0; i < count; ++i) {
@@ -1183,14 +1192,8 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			list_add(&page->lru, list);
 		else
 			list_add_tail(&page->lru, list);
-		if (IS_ENABLED(CONFIG_CMA)) {
-			mt = get_pageblock_migratetype(page);
-			if (!is_migrate_cma(mt) && !is_migrate_isolate(mt))
-				mt = migratetype;
-		}
-		set_freepage_migratetype(page, mt);
 		list = &page->lru;
-		if (is_migrate_cma(mt))
+		if (is_migrate_cma(get_freepage_migratetype(page)))
 			__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
 					      -(1 << order));
 	}
@@ -1559,7 +1562,7 @@ again:
 		if (!page)
 			goto failed;
 		__mod_zone_freepage_state(zone, -(1 << order),
-					  get_pageblock_migratetype(page));
+					  get_freepage_migratetype(page));
 	}
 
 	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
-- 
1.8.4.5

[PATCH 67/97] mm/swap.c: clean up *lru_cache_add* functions

[Mel Gorman]

From: Jianyu Zhan <nasa4836@gmail.com>

commit 2329d3751b082b4fd354f334a88662d72abac52d upstream.

In mm/swap.c, __lru_cache_add() is exported, but actually there are no
users outside this file.

This patch unexports __lru_cache_add(), and makes it static.  It also
exports lru_cache_add_file(), as it is use by cifs and fuse, which can
loaded as modules.

Signed-off-by: Jianyu Zhan <nasa4836@gmail.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Shaohua Li <shli@kernel.org>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Rafael Aquini <aquini@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/swap.h | 19 ++-----------------
 mm/swap.c            | 31 +++++++++++++++++++++++--------
 2 files changed, 25 insertions(+), 25 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7893249..13eb44c 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -268,8 +268,9 @@ extern unsigned long nr_free_pagecache_pages(void);
 
 
 /* linux/mm/swap.c */
-extern void __lru_cache_add(struct page *);
 extern void lru_cache_add(struct page *);
+extern void lru_cache_add_anon(struct page *page);
+extern void lru_cache_add_file(struct page *page);
 extern void lru_add_page_tail(struct page *page, struct page *page_tail,
 			 struct lruvec *lruvec, struct list_head *head);
 extern void activate_page(struct page *);
@@ -283,22 +284,6 @@ extern void swap_setup(void);
 
 extern void add_page_to_unevictable_list(struct page *page);
 
-/**
- * lru_cache_add: add a page to the page lists
- * @page: the page to add
- */
-static inline void lru_cache_add_anon(struct page *page)
-{
-	ClearPageActive(page);
-	__lru_cache_add(page);
-}
-
-static inline void lru_cache_add_file(struct page *page)
-{
-	ClearPageActive(page);
-	__lru_cache_add(page);
-}
-
 /* linux/mm/vmscan.c */
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);
diff --git a/mm/swap.c b/mm/swap.c
index 2d9ee76..587dfe0 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -548,13 +548,7 @@ void mark_page_accessed(struct page *page)
 }
 EXPORT_SYMBOL(mark_page_accessed);
 
-/*
- * Queue the page for addition to the LRU via pagevec. The decision on whether
- * to add the page to the [in]active [file|anon] list is deferred until the
- * pagevec is drained. This gives a chance for the caller of __lru_cache_add()
- * have the page added to the active list using mark_page_accessed().
- */
-void __lru_cache_add(struct page *page)
+static void __lru_cache_add(struct page *page)
 {
 	struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
 
@@ -564,11 +558,32 @@ void __lru_cache_add(struct page *page)
 	pagevec_add(pvec, page);
 	put_cpu_var(lru_add_pvec);
 }
-EXPORT_SYMBOL(__lru_cache_add);
+
+/**
+ * lru_cache_add: add a page to the page lists
+ * @page: the page to add
+ */
+void lru_cache_add_anon(struct page *page)
+{
+	ClearPageActive(page);
+	__lru_cache_add(page);
+}
+
+void lru_cache_add_file(struct page *page)
+{
+	ClearPageActive(page);
+	__lru_cache_add(page);
+}
+EXPORT_SYMBOL(lru_cache_add_file);
 
 /**
  * lru_cache_add - add a page to a page list
  * @page: the page to be added to the LRU.
+ *
+ * Queue the page for addition to the LRU via pagevec. The decision on whether
+ * to add the page to the [in]active [file|anon] list is deferred until the
+ * pagevec is drained. This gives a chance for the caller of lru_cache_add()
+ * have the page added to the active list using mark_page_accessed().
  */
 void lru_cache_add(struct page *page)
 {
-- 
1.8.4.5

[PATCH 68/97] mm: page_alloc: do not update zlc unless the zlc is active

[Mel Gorman]

commit 65bb371984d6a2c909244eb749e482bb40b72e36 upstream.

The zlc is used on NUMA machines to quickly skip over zones that are full.
 However it is always updated, even for the first zone scanned when the
zlc might not even be active.  As it's a write to a bitmap that
potentially bounces cache line it's deceptively expensive and most
machines will not care.  Only update the zlc if it was active.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7139ed7..2834c31 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2034,7 +2034,7 @@ try_this_zone:
 		if (page)
 			break;
 this_zone_full:
-		if (IS_ENABLED(CONFIG_NUMA))
+		if (IS_ENABLED(CONFIG_NUMA) && zlc_active)
 			zlc_mark_zone_full(zonelist, z);
 	}
 
-- 
1.8.4.5

[PATCH 69/97] mm: page_alloc: do not treat a zone that cannot be used for dirty pages as "full"

[Mel Gorman]

commit 800a1e750c7b04c2aa2459afca77e936e01c0029 upstream.

If a zone cannot be used for a dirty page then it gets marked "full" which
is cached in the zlc and later potentially skipped by allocation requests
that have nothing to do with dirty zones.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2834c31..68e0349 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1966,7 +1966,7 @@ zonelist_scan:
 		 */
 		if ((alloc_flags & ALLOC_WMARK_LOW) &&
 		    (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone))
-			goto this_zone_full;
+			continue;
 
 		mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
 		if (!zone_watermark_ok(zone, order, mark,
-- 
1.8.4.5

[PATCH 70/97] include/linux/jump_label.h: expose the reference count

[Mel Gorman]

commit ea5e9539abf1258f23e725cb9cb25aa74efa29eb upstream.

This patch exposes the jump_label reference count in preparation for the
next patch.  cpusets cares about both the jump_label being enabled and how
many users of the cpusets there currently are.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/jump_label.h | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index a507907..9216e46 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -62,6 +62,10 @@ struct static_key {
 
 # include <asm/jump_label.h>
 # define HAVE_JUMP_LABEL
+#else
+struct static_key {
+	atomic_t enabled;
+};
 #endif	/* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */
 
 enum jump_label_type {
@@ -72,6 +76,12 @@ enum jump_label_type {
 struct module;
 
 #include <linux/atomic.h>
+
+static inline int static_key_count(struct static_key *key)
+{
+	return atomic_read(&key->enabled);
+}
+
 #ifdef HAVE_JUMP_LABEL
 
 #define JUMP_LABEL_TRUE_BRANCH 1UL
@@ -122,24 +132,20 @@ extern void jump_label_apply_nops(struct module *mod);
 
 #else  /* !HAVE_JUMP_LABEL */
 
-struct static_key {
-	atomic_t enabled;
-};
-
 static __always_inline void jump_label_init(void)
 {
 }
 
 static __always_inline bool static_key_false(struct static_key *key)
 {
-	if (unlikely(atomic_read(&key->enabled)) > 0)
+	if (unlikely(static_key_count(key) > 0))
 		return true;
 	return false;
 }
 
 static __always_inline bool static_key_true(struct static_key *key)
 {
-	if (likely(atomic_read(&key->enabled)) > 0)
+	if (likely(static_key_count(key) > 0))
 		return true;
 	return false;
 }
@@ -179,7 +185,7 @@ static inline int jump_label_apply_nops(struct module *mod)
 
 static inline bool static_key_enabled(struct static_key *key)
 {
-	return (atomic_read(&key->enabled) > 0);
+	return static_key_count(key) > 0;
 }
 
 #endif	/* _LINUX_JUMP_LABEL_H */
-- 
1.8.4.5

[PATCH 71/97] mm: page_alloc: use jump labels to avoid checking number_of_cpusets

[Mel Gorman]

commit 664eeddeef6539247691197c1ac124d4aa872ab6 upstream.

If cpusets are not in use then we still check a global variable on every
page allocation.  Use jump labels to avoid the overhead.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/cpuset.h | 29 ++++++++++++++++++++++++++---
 kernel/cpuset.c        | 14 ++++----------
 mm/page_alloc.c        |  3 ++-
 3 files changed, 32 insertions(+), 14 deletions(-)

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 6f30672..a7ebb89 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -12,10 +12,31 @@
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/mm.h>
+#include <linux/jump_label.h>
 
 #ifdef CONFIG_CPUSETS
 
-extern int number_of_cpusets;	/* How many cpusets are defined in system? */
+extern struct static_key cpusets_enabled_key;
+static inline bool cpusets_enabled(void)
+{
+	return static_key_false(&cpusets_enabled_key);
+}
+
+static inline int nr_cpusets(void)
+{
+	/* jump label reference count + the top-level cpuset */
+	return static_key_count(&cpusets_enabled_key) + 1;
+}
+
+static inline void cpuset_inc(void)
+{
+	static_key_slow_inc(&cpusets_enabled_key);
+}
+
+static inline void cpuset_dec(void)
+{
+	static_key_slow_dec(&cpusets_enabled_key);
+}
 
 extern int cpuset_init(void);
 extern void cpuset_init_smp(void);
@@ -32,13 +53,13 @@ extern int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask);
 
 static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
 {
-	return number_of_cpusets <= 1 ||
+	return nr_cpusets() <= 1 ||
 		__cpuset_node_allowed_softwall(node, gfp_mask);
 }
 
 static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
 {
-	return number_of_cpusets <= 1 ||
+	return nr_cpusets() <= 1 ||
 		__cpuset_node_allowed_hardwall(node, gfp_mask);
 }
 
@@ -120,6 +141,8 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 
 #else /* !CONFIG_CPUSETS */
 
+static inline bool cpusets_enabled(void) { return false; }
+
 static inline int cpuset_init(void) { return 0; }
 static inline void cpuset_init_smp(void) {}
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 15ae2b7..c828913 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -61,12 +61,7 @@
 #include <linux/cgroup.h>
 #include <linux/wait.h>
 
-/*
- * Tracks how many cpusets are currently defined in system.
- * When there is only one cpuset (the root cpuset) we can
- * short circuit some hooks.
- */
-int number_of_cpusets __read_mostly;
+struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE;
 
 /* See "Frequency meter" comments, below. */
 
@@ -611,7 +606,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 		goto done;
 	}
 
-	csa = kmalloc(number_of_cpusets * sizeof(cp), GFP_KERNEL);
+	csa = kmalloc(nr_cpusets() * sizeof(cp), GFP_KERNEL);
 	if (!csa)
 		goto done;
 	csn = 0;
@@ -1986,7 +1981,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	if (is_spread_slab(parent))
 		set_bit(CS_SPREAD_SLAB, &cs->flags);
 
-	number_of_cpusets++;
+	cpuset_inc();
 
 	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
 		goto out_unlock;
@@ -2037,7 +2032,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 	if (is_sched_load_balance(cs))
 		update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
 
-	number_of_cpusets--;
+	cpuset_dec();
 	clear_bit(CS_ONLINE, &cs->flags);
 
 	mutex_unlock(&cpuset_mutex);
@@ -2092,7 +2087,6 @@ int __init cpuset_init(void)
 	if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL))
 		BUG();
 
-	number_of_cpusets = 1;
 	return 0;
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 68e0349..5e0f137 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1920,7 +1920,8 @@ zonelist_scan:
 		if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
 			!zlc_zone_worth_trying(zonelist, z, allowednodes))
 				continue;
-		if ((alloc_flags & ALLOC_CPUSET) &&
+		if (cpusets_enabled() &&
+			(alloc_flags & ALLOC_CPUSET) &&
 			!cpuset_zone_allowed_softwall(zone, gfp_mask))
 				continue;
 		BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
-- 
1.8.4.5

[PATCH 72/97] mm: page_alloc: calculate classzone_idx once from the zonelist ref

[Mel Gorman]

commit d8846374a85f4290a473a4e2a64c1ba046c4a0e1 upstream.

There is no need to calculate zone_idx(preferred_zone) multiple times
or use the pgdat to figure it out.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 60 +++++++++++++++++++++++++++++++++------------------------
 1 file changed, 35 insertions(+), 25 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5e0f137..fd2752a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1897,17 +1897,15 @@ static inline void init_zone_allows_reclaim(int nid)
 static struct page *
 get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
 		struct zonelist *zonelist, int high_zoneidx, int alloc_flags,
-		struct zone *preferred_zone, int migratetype)
+		struct zone *preferred_zone, int classzone_idx, int migratetype)
 {
 	struct zoneref *z;
 	struct page *page = NULL;
-	int classzone_idx;
 	struct zone *zone;
 	nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
 	int zlc_active = 0;		/* set if using zonelist_cache */
 	int did_zlc_setup = 0;		/* just call zlc_setup() one time */
 
-	classzone_idx = zone_idx(preferred_zone);
 zonelist_scan:
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
@@ -2171,7 +2169,7 @@ static inline struct page *
 __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, struct zone *preferred_zone,
-	int migratetype)
+	int classzone_idx, int migratetype)
 {
 	struct page *page;
 
@@ -2189,7 +2187,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
 		order, zonelist, high_zoneidx,
 		ALLOC_WMARK_HIGH|ALLOC_CPUSET,
-		preferred_zone, migratetype);
+		preferred_zone, classzone_idx, migratetype);
 	if (page)
 		goto out;
 
@@ -2224,7 +2222,7 @@ static struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, enum migrate_mode mode,
+	int classzone_idx, int migratetype, enum migrate_mode mode,
 	bool *contended_compaction, bool *deferred_compaction,
 	unsigned long *did_some_progress)
 {
@@ -2252,7 +2250,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		page = get_page_from_freelist(gfp_mask, nodemask,
 				order, zonelist, high_zoneidx,
 				alloc_flags & ~ALLOC_NO_WATERMARKS,
-				preferred_zone, migratetype);
+				preferred_zone, classzone_idx, migratetype);
 		if (page) {
 			preferred_zone->compact_blockskip_flush = false;
 			compaction_defer_reset(preferred_zone, order, true);
@@ -2284,7 +2282,8 @@ static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, enum migrate_mode mode, bool *contended_compaction,
+	int classzone_idx, int migratetype,
+	enum migrate_mode mode, bool *contended_compaction,
 	bool *deferred_compaction, unsigned long *did_some_progress)
 {
 	return NULL;
@@ -2324,7 +2323,7 @@ static inline struct page *
 __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress)
+	int classzone_idx, int migratetype, unsigned long *did_some_progress)
 {
 	struct page *page = NULL;
 	bool drained = false;
@@ -2342,7 +2341,8 @@ retry:
 	page = get_page_from_freelist(gfp_mask, nodemask, order,
 					zonelist, high_zoneidx,
 					alloc_flags & ~ALLOC_NO_WATERMARKS,
-					preferred_zone, migratetype);
+					preferred_zone, classzone_idx,
+					migratetype);
 
 	/*
 	 * If an allocation failed after direct reclaim, it could be because
@@ -2365,14 +2365,14 @@ static inline struct page *
 __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, struct zone *preferred_zone,
-	int migratetype)
+	int classzone_idx, int migratetype)
 {
 	struct page *page;
 
 	do {
 		page = get_page_from_freelist(gfp_mask, nodemask, order,
 			zonelist, high_zoneidx, ALLOC_NO_WATERMARKS,
-			preferred_zone, migratetype);
+			preferred_zone, classzone_idx, migratetype);
 
 		if (!page && gfp_mask & __GFP_NOFAIL)
 			wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
@@ -2473,7 +2473,7 @@ static inline struct page *
 __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, struct zone *preferred_zone,
-	int migratetype)
+	int classzone_idx, int migratetype)
 {
 	const gfp_t wait = gfp_mask & __GFP_WAIT;
 	struct page *page = NULL;
@@ -2522,15 +2522,19 @@ restart:
 	 * Find the true preferred zone if the allocation is unconstrained by
 	 * cpusets.
 	 */
-	if (!(alloc_flags & ALLOC_CPUSET) && !nodemask)
-		first_zones_zonelist(zonelist, high_zoneidx, NULL,
-					&preferred_zone);
+	if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) {
+		struct zoneref *preferred_zoneref;
+		preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx,
+				NULL,
+				&preferred_zone);
+		classzone_idx = zonelist_zone_idx(preferred_zoneref);
+	}
 
 rebalance:
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
 			high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
-			preferred_zone, migratetype);
+			preferred_zone, classzone_idx, migratetype);
 	if (page)
 		goto got_pg;
 
@@ -2545,7 +2549,7 @@ rebalance:
 
 		page = __alloc_pages_high_priority(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
-				preferred_zone, migratetype);
+				preferred_zone, classzone_idx, migratetype);
 		if (page) {
 			goto got_pg;
 		}
@@ -2569,7 +2573,8 @@ rebalance:
 	 */
 	page = __alloc_pages_direct_compact(gfp_mask, order, zonelist,
 					high_zoneidx, nodemask, alloc_flags,
-					preferred_zone, migratetype,
+					preferred_zone,
+					classzone_idx, migratetype,
 					migration_mode, &contended_compaction,
 					&deferred_compaction,
 					&did_some_progress);
@@ -2592,7 +2597,8 @@ rebalance:
 					zonelist, high_zoneidx,
 					nodemask,
 					alloc_flags, preferred_zone,
-					migratetype, &did_some_progress);
+					classzone_idx, migratetype,
+					&did_some_progress);
 	if (page)
 		goto got_pg;
 
@@ -2611,7 +2617,7 @@ rebalance:
 			page = __alloc_pages_may_oom(gfp_mask, order,
 					zonelist, high_zoneidx,
 					nodemask, preferred_zone,
-					migratetype);
+					classzone_idx, migratetype);
 			if (page)
 				goto got_pg;
 
@@ -2652,7 +2658,8 @@ rebalance:
 		 */
 		page = __alloc_pages_direct_compact(gfp_mask, order, zonelist,
 					high_zoneidx, nodemask, alloc_flags,
-					preferred_zone, migratetype,
+					preferred_zone,
+					classzone_idx, migratetype,
 					migration_mode, &contended_compaction,
 					&deferred_compaction,
 					&did_some_progress);
@@ -2679,11 +2686,13 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	struct zone *preferred_zone;
+	struct zoneref *preferred_zoneref;
 	struct page *page = NULL;
 	int migratetype = allocflags_to_migratetype(gfp_mask);
 	unsigned int cpuset_mems_cookie;
 	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
 	struct mem_cgroup *memcg = NULL;
+	int classzone_idx;
 
 	gfp_mask &= gfp_allowed_mask;
 
@@ -2713,11 +2722,12 @@ retry_cpuset:
 	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	/* The preferred zone is used for statistics later */
-	first_zones_zonelist(zonelist, high_zoneidx,
+	preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx,
 				nodemask ? : &cpuset_current_mems_allowed,
 				&preferred_zone);
 	if (!preferred_zone)
 		goto out;
+	classzone_idx = zonelist_zone_idx(preferred_zoneref);
 
 #ifdef CONFIG_CMA
 	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
@@ -2727,7 +2737,7 @@ retry:
 	/* First allocation attempt */
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
 			zonelist, high_zoneidx, alloc_flags,
-			preferred_zone, migratetype);
+			preferred_zone, classzone_idx, migratetype);
 	if (unlikely(!page)) {
 		/*
 		 * The first pass makes sure allocations are spread
@@ -2753,7 +2763,7 @@ retry:
 		gfp_mask = memalloc_noio_flags(gfp_mask);
 		page = __alloc_pages_slowpath(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
-				preferred_zone, migratetype);
+				preferred_zone, classzone_idx, migratetype);
 	}
 
 	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
-- 
1.8.4.5

[PATCH 73/97] mm: page_alloc: only check the zone id check if pages are buddies

[Mel Gorman]

commit d34c5fa06fade08a689fc171bf756fba2858ae73 upstream.

A node/zone index is used to check if pages are compatible for merging
but this happens unconditionally even if the buddy page is not free. Defer
the calculation as long as possible. Ideally we would check the zone boundary
but nodes can overlap.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fd2752a..2e7ec3c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -505,16 +505,26 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
 	if (!pfn_valid_within(page_to_pfn(buddy)))
 		return 0;
 
-	if (page_zone_id(page) != page_zone_id(buddy))
-		return 0;
-
 	if (page_is_guard(buddy) && page_order(buddy) == order) {
 		VM_BUG_ON(page_count(buddy) != 0);
+
+		if (page_zone_id(page) != page_zone_id(buddy))
+			return 0;
+
 		return 1;
 	}
 
 	if (PageBuddy(buddy) && page_order(buddy) == order) {
 		VM_BUG_ON(page_count(buddy) != 0);
+
+		/*
+		 * zone check is done late to avoid uselessly
+		 * calculating zone/node ids for pages that could
+		 * never merge.
+		 */
+		if (page_zone_id(page) != page_zone_id(buddy))
+			return 0;
+
 		return 1;
 	}
 	return 0;
-- 
1.8.4.5

[PATCH 74/97] mm: page_alloc: only check the alloc flags and gfp_mask for dirty once

[Mel Gorman]

commit a6e21b14f22041382e832d30deda6f26f37b1097 upstream.

Currently it's calculated once per zone in the zonelist.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2e7ec3c..cb4cadd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1915,6 +1915,8 @@ get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
 	nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
 	int zlc_active = 0;		/* set if using zonelist_cache */
 	int did_zlc_setup = 0;		/* just call zlc_setup() one time */
+	bool consider_zone_dirty = (alloc_flags & ALLOC_WMARK_LOW) &&
+				(gfp_mask & __GFP_WRITE);
 
 zonelist_scan:
 	/*
@@ -1973,8 +1975,7 @@ zonelist_scan:
 		 * will require awareness of zones in the
 		 * dirty-throttling and the flusher threads.
 		 */
-		if ((alloc_flags & ALLOC_WMARK_LOW) &&
-		    (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone))
+		if (consider_zone_dirty && !zone_dirty_ok(zone))
 			continue;
 
 		mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
-- 
1.8.4.5

[PATCH 75/97] mm: page_alloc: take the ALLOC_NO_WATERMARK check out of the fast path

[Mel Gorman]

commit 5dab29113ca56335c78be3f98bf5ddf2ef8eb6a6 upstream.

ALLOC_NO_WATERMARK is set in a few cases.  Always by kswapd, always for
__GFP_MEMALLOC, sometimes for swap-over-nfs, tasks etc.  Each of these
cases are relatively rare events but the ALLOC_NO_WATERMARK check is an
unlikely branch in the fast path.  This patch moves the check out of the
fast path and after it has been determined that the watermarks have not
been met.  This helps the common fast path at the cost of making the slow
path slower and hitting kswapd with a performance cost.  It's a reasonable
tradeoff.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index cb4cadd..332066b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1934,9 +1934,6 @@ zonelist_scan:
 			(alloc_flags & ALLOC_CPUSET) &&
 			!cpuset_zone_allowed_softwall(zone, gfp_mask))
 				continue;
-		BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
-		if (unlikely(alloc_flags & ALLOC_NO_WATERMARKS))
-			goto try_this_zone;
 		/*
 		 * Distribute pages in proportion to the individual
 		 * zone size to ensure fair page aging.  The zone a
@@ -1983,6 +1980,11 @@ zonelist_scan:
 				       classzone_idx, alloc_flags)) {
 			int ret;
 
+			/* Checked here to keep the fast path fast */
+			BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
+			if (alloc_flags & ALLOC_NO_WATERMARKS)
+				goto try_this_zone;
+
 			if (IS_ENABLED(CONFIG_NUMA) &&
 					!did_zlc_setup && nr_online_nodes > 1) {
 				/*
-- 
1.8.4.5

[PATCH 76/97] mm: page_alloc: use unsigned int for order in more places

[Mel Gorman]

commit 7aeb09f9104b760fc53c98cb7d20d06640baf9e6 upstream.

X86 prefers the use of unsigned types for iterators and there is a
tendency to mix whether a signed or unsigned type if used for page order.
This converts a number of sites in mm/page_alloc.c to use unsigned int for
order where possible.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mmzone.h |  8 ++++----
 mm/page_alloc.c        | 43 +++++++++++++++++++++++--------------------
 2 files changed, 27 insertions(+), 24 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index e4d1a88..49aa3e5 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -810,10 +810,10 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat)
 extern struct mutex zonelists_mutex;
 void build_all_zonelists(pg_data_t *pgdat, struct zone *zone);
 void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx);
-bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
-		int classzone_idx, int alloc_flags);
-bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
-		int classzone_idx, int alloc_flags);
+bool zone_watermark_ok(struct zone *z, unsigned int order,
+		unsigned long mark, int classzone_idx, int alloc_flags);
+bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
+		unsigned long mark, int classzone_idx, int alloc_flags);
 enum memmap_context {
 	MEMMAP_EARLY,
 	MEMMAP_HOTPLUG,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 332066b..46b5a56 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -405,7 +405,8 @@ static int destroy_compound_page(struct page *page, unsigned long order)
 	return bad;
 }
 
-static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
+static inline void prep_zero_page(struct page *page, unsigned int order,
+							gfp_t gfp_flags)
 {
 	int i;
 
@@ -449,7 +450,7 @@ static inline void set_page_guard_flag(struct page *page) { }
 static inline void clear_page_guard_flag(struct page *page) { }
 #endif
 
-static inline void set_page_order(struct page *page, int order)
+static inline void set_page_order(struct page *page, unsigned int order)
 {
 	set_page_private(page, order);
 	__SetPageBuddy(page);
@@ -500,7 +501,7 @@ __find_buddy_index(unsigned long page_idx, unsigned int order)
  * For recording page's order, we use page_private(page).
  */
 static inline int page_is_buddy(struct page *page, struct page *buddy,
-								int order)
+							unsigned int order)
 {
 	if (!pfn_valid_within(page_to_pfn(buddy)))
 		return 0;
@@ -708,7 +709,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 	spin_unlock(&zone->lock);
 }
 
-static void free_one_page(struct zone *zone, struct page *page, int order,
+static void free_one_page(struct zone *zone, struct page *page, unsigned int order,
 				int migratetype)
 {
 	spin_lock(&zone->lock);
@@ -879,7 +880,7 @@ static inline int check_new_page(struct page *page)
 	return 0;
 }
 
-static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
+static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags)
 {
 	int i;
 
@@ -1090,16 +1091,17 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page,
 
 /* Remove an element from the buddy allocator from the fallback list */
 static inline struct page *
-__rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
+__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
 {
 	struct free_area *area;
-	int current_order;
+	unsigned int current_order;
 	struct page *page;
 	int migratetype, new_type, i;
 
 	/* Find the largest possible block of pages in the other list */
-	for (current_order = MAX_ORDER-1; current_order >= order;
-						--current_order) {
+	for (current_order = MAX_ORDER-1;
+				current_order >= order && current_order <= MAX_ORDER-1;
+				--current_order) {
 		for (i = 0;; i++) {
 			migratetype = fallbacks[start_migratetype][i];
 
@@ -1327,7 +1329,7 @@ void mark_free_pages(struct zone *zone)
 {
 	unsigned long pfn, max_zone_pfn;
 	unsigned long flags;
-	int order, t;
+	unsigned int order, t;
 	struct list_head *curr;
 
 	if (zone_is_empty(zone))
@@ -1522,8 +1524,8 @@ int split_free_page(struct page *page)
  */
 static inline
 struct page *buffered_rmqueue(struct zone *preferred_zone,
-			struct zone *zone, int order, gfp_t gfp_flags,
-			int migratetype)
+			struct zone *zone, unsigned int order,
+			gfp_t gfp_flags, int migratetype)
 {
 	unsigned long flags;
 	struct page *page;
@@ -1672,8 +1674,9 @@ static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
  * Return true if free pages are above 'mark'. This takes into account the order
  * of the allocation.
  */
-static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
-		      int classzone_idx, int alloc_flags, long free_pages)
+static bool __zone_watermark_ok(struct zone *z, unsigned int order,
+			unsigned long mark, int classzone_idx, int alloc_flags,
+			long free_pages)
 {
 	/* free_pages my go negative - that's OK */
 	long min = mark;
@@ -1707,15 +1710,15 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	return true;
 }
 
-bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 		      int classzone_idx, int alloc_flags)
 {
 	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
 					zone_page_state(z, NR_FREE_PAGES));
 }
 
-bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
-		      int classzone_idx, int alloc_flags)
+bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
+			unsigned long mark, int classzone_idx, int alloc_flags)
 {
 	long free_pages = zone_page_state(z, NR_FREE_PAGES);
 
@@ -4106,7 +4109,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 
 static void __meminit zone_init_free_lists(struct zone *zone)
 {
-	int order, t;
+	unsigned int order, t;
 	for_each_migratetype_order(order, t) {
 		INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
 		zone->free_area[order].nr_free = 0;
@@ -6420,7 +6423,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 {
 	struct page *page;
 	struct zone *zone;
-	int order, i;
+	unsigned int order, i;
 	unsigned long pfn;
 	unsigned long flags;
 	/* find the first valid pfn */
@@ -6472,7 +6475,7 @@ bool is_free_buddy_page(struct page *page)
 	struct zone *zone = page_zone(page);
 	unsigned long pfn = page_to_pfn(page);
 	unsigned long flags;
-	int order;
+	unsigned int order;
 
 	spin_lock_irqsave(&zone->lock, flags);
 	for (order = 0; order < MAX_ORDER; order++) {
-- 
1.8.4.5

[PATCH 77/97] mm: page_alloc: reduce number of times page_to_pfn is called

[Mel Gorman]

commit dc4b0caff24d9b2918e9f27bc65499ee63187eba upstream.

In the free path we calculate page_to_pfn multiple times. Reduce that.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mmzone.h          |  9 +++++++--
 include/linux/pageblock-flags.h | 33 +++++++++++++--------------------
 mm/page_alloc.c                 | 34 +++++++++++++++++++---------------
 3 files changed, 39 insertions(+), 37 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 49aa3e5..b45c3a7 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -78,10 +78,15 @@ extern int page_group_by_mobility_disabled;
 #define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1)
 #define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1)
 
-static inline int get_pageblock_migratetype(struct page *page)
+#define get_pageblock_migratetype(page)					\
+	get_pfnblock_flags_mask(page, page_to_pfn(page),		\
+			PB_migrate_end, MIGRATETYPE_MASK)
+
+static inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn)
 {
 	BUILD_BUG_ON(PB_migrate_end - PB_migrate != 2);
-	return get_pageblock_flags_mask(page, PB_migrate_end, MIGRATETYPE_MASK);
+	return get_pfnblock_flags_mask(page, pfn, PB_migrate_end,
+					MIGRATETYPE_MASK);
 }
 
 struct free_area {
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index c08730c..2baeee1 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -65,33 +65,26 @@ extern int pageblock_order;
 /* Forward declaration */
 struct page;
 
-unsigned long get_pageblock_flags_mask(struct page *page,
+unsigned long get_pfnblock_flags_mask(struct page *page,
+				unsigned long pfn,
 				unsigned long end_bitidx,
 				unsigned long mask);
-void set_pageblock_flags_mask(struct page *page,
+
+void set_pfnblock_flags_mask(struct page *page,
 				unsigned long flags,
+				unsigned long pfn,
 				unsigned long end_bitidx,
 				unsigned long mask);
 
 /* Declarations for getting and setting flags. See mm/page_alloc.c */
-static inline unsigned long get_pageblock_flags_group(struct page *page,
-					int start_bitidx, int end_bitidx)
-{
-	unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1;
-	unsigned long mask = (1 << nr_flag_bits) - 1;
-
-	return get_pageblock_flags_mask(page, end_bitidx, mask);
-}
-
-static inline void set_pageblock_flags_group(struct page *page,
-					unsigned long flags,
-					int start_bitidx, int end_bitidx)
-{
-	unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1;
-	unsigned long mask = (1 << nr_flag_bits) - 1;
-
-	set_pageblock_flags_mask(page, flags, end_bitidx, mask);
-}
+#define get_pageblock_flags_group(page, start_bitidx, end_bitidx) \
+	get_pfnblock_flags_mask(page, page_to_pfn(page),		\
+			end_bitidx,					\
+			(1 << (end_bitidx - start_bitidx + 1)) - 1)
+#define set_pageblock_flags_group(page, flags, start_bitidx, end_bitidx) \
+	set_pfnblock_flags_mask(page, flags, page_to_pfn(page),		\
+			end_bitidx,					\
+			(1 << (end_bitidx - start_bitidx + 1)) - 1)
 
 #ifdef CONFIG_COMPACTION
 #define get_pageblock_skip(page) \
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 46b5a56..031ca22 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -557,6 +557,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
  */
 
 static inline void __free_one_page(struct page *page,
+		unsigned long pfn,
 		struct zone *zone, unsigned int order,
 		int migratetype)
 {
@@ -573,7 +574,7 @@ static inline void __free_one_page(struct page *page,
 
 	VM_BUG_ON(migratetype == -1);
 
-	page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
+	page_idx = pfn & ((1 << MAX_ORDER) - 1);
 
 	VM_BUG_ON(page_idx & ((1 << order) - 1));
 	VM_BUG_ON(bad_range(zone, page));
@@ -697,7 +698,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 			list_del(&page->lru);
 			mt = get_freepage_migratetype(page);
 			/* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
-			__free_one_page(page, zone, 0, mt);
+			__free_one_page(page, page_to_pfn(page), zone, 0, mt);
 			trace_mm_page_pcpu_drain(page, 0, mt);
 			if (likely(!is_migrate_isolate_page(page))) {
 				__mod_zone_page_state(zone, NR_FREE_PAGES, 1);
@@ -709,13 +710,15 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 	spin_unlock(&zone->lock);
 }
 
-static void free_one_page(struct zone *zone, struct page *page, unsigned int order,
+static void free_one_page(struct zone *zone,
+				struct page *page, unsigned long pfn,
+				unsigned int order,
 				int migratetype)
 {
 	spin_lock(&zone->lock);
 	zone->pages_scanned = 0;
 
-	__free_one_page(page, zone, order, migratetype);
+	__free_one_page(page, pfn, zone, order, migratetype);
 	if (unlikely(!is_migrate_isolate(migratetype)))
 		__mod_zone_freepage_state(zone, 1 << order, migratetype);
 	spin_unlock(&zone->lock);
@@ -752,15 +755,16 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 {
 	unsigned long flags;
 	int migratetype;
+	unsigned long pfn = page_to_pfn(page);
 
 	if (!free_pages_prepare(page, order))
 		return;
 
 	local_irq_save(flags);
 	__count_vm_events(PGFREE, 1 << order);
-	migratetype = get_pageblock_migratetype(page);
+	migratetype = get_pfnblock_migratetype(page, pfn);
 	set_freepage_migratetype(page, migratetype);
-	free_one_page(page_zone(page), page, order, migratetype);
+	free_one_page(page_zone(page), page, pfn, order, migratetype);
 	local_irq_restore(flags);
 }
 
@@ -1368,12 +1372,13 @@ void free_hot_cold_page(struct page *page, int cold)
 	struct zone *zone = page_zone(page);
 	struct per_cpu_pages *pcp;
 	unsigned long flags;
+	unsigned long pfn = page_to_pfn(page);
 	int migratetype;
 
 	if (!free_pages_prepare(page, 0))
 		return;
 
-	migratetype = get_pageblock_migratetype(page);
+	migratetype = get_pfnblock_migratetype(page, pfn);
 	set_freepage_migratetype(page, migratetype);
 	local_irq_save(flags);
 	__count_vm_event(PGFREE);
@@ -1387,7 +1392,7 @@ void free_hot_cold_page(struct page *page, int cold)
 	 */
 	if (migratetype >= MIGRATE_PCPTYPES) {
 		if (unlikely(is_migrate_isolate(migratetype))) {
-			free_one_page(zone, page, 0, migratetype);
+			free_one_page(zone, page, pfn, 0, migratetype);
 			goto out;
 		}
 		migratetype = MIGRATE_MOVABLE;
@@ -6011,17 +6016,16 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
  * @end_bitidx: The last bit of interest
  * returns pageblock_bits flags
  */
-unsigned long get_pageblock_flags_mask(struct page *page,
+unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn,
 					unsigned long end_bitidx,
 					unsigned long mask)
 {
 	struct zone *zone;
 	unsigned long *bitmap;
-	unsigned long pfn, bitidx, word_bitidx;
+	unsigned long bitidx, word_bitidx;
 	unsigned long word;
 
 	zone = page_zone(page);
-	pfn = page_to_pfn(page);
 	bitmap = get_pageblock_bitmap(zone, pfn);
 	bitidx = pfn_to_bitidx(zone, pfn);
 	word_bitidx = bitidx / BITS_PER_LONG;
@@ -6033,25 +6037,25 @@ unsigned long get_pageblock_flags_mask(struct page *page,
 }
 
 /**
- * set_pageblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
+ * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
  * @page: The page within the block of interest
  * @start_bitidx: The first bit of interest
  * @end_bitidx: The last bit of interest
  * @flags: The flags to set
  */
-void set_pageblock_flags_mask(struct page *page, unsigned long flags,
+void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
+					unsigned long pfn,
 					unsigned long end_bitidx,
 					unsigned long mask)
 {
 	struct zone *zone;
 	unsigned long *bitmap;
-	unsigned long pfn, bitidx, word_bitidx;
+	unsigned long bitidx, word_bitidx;
 	unsigned long old_word, word;
 
 	BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
 
 	zone = page_zone(page);
-	pfn = page_to_pfn(page);
 	bitmap = get_pageblock_bitmap(zone, pfn);
 	bitidx = pfn_to_bitidx(zone, pfn);
 	word_bitidx = bitidx / BITS_PER_LONG;
-- 
1.8.4.5

[PATCH 78/97] mm: page_alloc: convert hot/cold parameter and immediate callers to bool

[Mel Gorman]

commit b745bc85f21ea707e4ea1a91948055fa3e72c77b upstream.

cold is a bool, make it one.  Make the likely case the "if" part of the
block instead of the else as according to the optimisation manual this is
preferred.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 arch/tile/mm/homecache.c |  2 +-
 fs/fuse/dev.c            |  2 +-
 include/linux/gfp.h      |  4 ++--
 include/linux/pagemap.h  |  2 +-
 include/linux/swap.h     |  2 +-
 mm/page_alloc.c          | 20 ++++++++++----------
 mm/swap.c                |  4 ++--
 mm/swap_state.c          |  2 +-
 mm/vmscan.c              |  6 +++---
 9 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/arch/tile/mm/homecache.c b/arch/tile/mm/homecache.c
index 004ba56..33294fd 100644
--- a/arch/tile/mm/homecache.c
+++ b/arch/tile/mm/homecache.c
@@ -417,7 +417,7 @@ void __homecache_free_pages(struct page *page, unsigned int order)
 	if (put_page_testzero(page)) {
 		homecache_change_page_home(page, order, PAGE_HOME_HASH);
 		if (order == 0) {
-			free_hot_cold_page(page, 0);
+			free_hot_cold_page(page, false);
 		} else {
 			init_page_count(page);
 			__free_pages(page, order);
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index fa8cb4b..fc8e499 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1613,7 +1613,7 @@ out_finish:
 
 static void fuse_retrieve_end(struct fuse_conn *fc, struct fuse_req *req)
 {
-	release_pages(req->pages, req->num_pages, 0);
+	release_pages(req->pages, req->num_pages, false);
 }
 
 static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 9b4dd49..fa7ac98 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -364,8 +364,8 @@ void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
 
 extern void __free_pages(struct page *page, unsigned int order);
 extern void free_pages(unsigned long addr, unsigned int order);
-extern void free_hot_cold_page(struct page *page, int cold);
-extern void free_hot_cold_page_list(struct list_head *list, int cold);
+extern void free_hot_cold_page(struct page *page, bool cold);
+extern void free_hot_cold_page_list(struct list_head *list, bool cold);
 
 extern void __free_memcg_kmem_pages(struct page *page, unsigned int order);
 extern void free_memcg_kmem_pages(unsigned long addr, unsigned int order);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 930b884..57e3693 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -99,7 +99,7 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 
 #define page_cache_get(page)		get_page(page)
 #define page_cache_release(page)	put_page(page)
-void release_pages(struct page **pages, int nr, int cold);
+void release_pages(struct page **pages, int nr, bool cold);
 
 /*
  * speculatively take a reference to a page.
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 13eb44c..c8beed1 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -441,7 +441,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
 #define free_page_and_swap_cache(page) \
 	page_cache_release(page)
 #define free_pages_and_swap_cache(pages, nr) \
-	release_pages((pages), (nr), 0);
+	release_pages((pages), (nr), false);
 
 static inline void show_swap_cache_info(void)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 031ca22..b1b1522 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1185,7 +1185,7 @@ retry_reserve:
  */
 static int rmqueue_bulk(struct zone *zone, unsigned int order,
 			unsigned long count, struct list_head *list,
-			int migratetype, int cold)
+			int migratetype, bool cold)
 {
 	int i;
 
@@ -1204,7 +1204,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 		 * merge IO requests if the physical pages are ordered
 		 * properly.
 		 */
-		if (likely(cold == 0))
+		if (likely(!cold))
 			list_add(&page->lru, list);
 		else
 			list_add_tail(&page->lru, list);
@@ -1365,9 +1365,9 @@ void mark_free_pages(struct zone *zone)
 
 /*
  * Free a 0-order page
- * cold == 1 ? free a cold page : free a hot page
+ * cold == true ? free a cold page : free a hot page
  */
-void free_hot_cold_page(struct page *page, int cold)
+void free_hot_cold_page(struct page *page, bool cold)
 {
 	struct zone *zone = page_zone(page);
 	struct per_cpu_pages *pcp;
@@ -1399,10 +1399,10 @@ void free_hot_cold_page(struct page *page, int cold)
 	}
 
 	pcp = &this_cpu_ptr(zone->pageset)->pcp;
-	if (cold)
-		list_add_tail(&page->lru, &pcp->lists[migratetype]);
-	else
+	if (!cold)
 		list_add(&page->lru, &pcp->lists[migratetype]);
+	else
+		list_add_tail(&page->lru, &pcp->lists[migratetype]);
 	pcp->count++;
 	if (pcp->count >= pcp->high) {
 		unsigned long batch = ACCESS_ONCE(pcp->batch);
@@ -1417,7 +1417,7 @@ out:
 /*
  * Free a list of 0-order pages
  */
-void free_hot_cold_page_list(struct list_head *list, int cold)
+void free_hot_cold_page_list(struct list_head *list, bool cold)
 {
 	struct page *page, *next;
 
@@ -1534,7 +1534,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
 {
 	unsigned long flags;
 	struct page *page;
-	int cold = !!(gfp_flags & __GFP_COLD);
+	bool cold = ((gfp_flags & __GFP_COLD) != 0);
 
 again:
 	if (likely(order == 0)) {
@@ -2835,7 +2835,7 @@ void __free_pages(struct page *page, unsigned int order)
 {
 	if (put_page_testzero(page)) {
 		if (order == 0)
-			free_hot_cold_page(page, 0);
+			free_hot_cold_page(page, false);
 		else
 			__free_pages_ok(page, order);
 	}
diff --git a/mm/swap.c b/mm/swap.c
index 587dfe0..026113d 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -68,7 +68,7 @@ static void __page_cache_release(struct page *page)
 static void __put_single_page(struct page *page)
 {
 	__page_cache_release(page);
-	free_hot_cold_page(page, 0);
+	free_hot_cold_page(page, false);
 }
 
 static void __put_compound_page(struct page *page)
@@ -794,7 +794,7 @@ void lru_add_drain_all(void)
  * grabbed the page via the LRU.  If it did, give up: shrink_inactive_list()
  * will free it.
  */
-void release_pages(struct page **pages, int nr, int cold)
+void release_pages(struct page **pages, int nr, bool cold)
 {
 	int i;
 	LIST_HEAD(pages_to_free);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index fdde6f9..4079edf 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -270,7 +270,7 @@ void free_pages_and_swap_cache(struct page **pages, int nr)
 
 		for (i = 0; i < todo; i++)
 			free_swap_cache(pagep[i]);
-		release_pages(pagep, todo, 0);
+		release_pages(pagep, todo, false);
 		pagep += todo;
 		nr -= todo;
 	}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e568be9..360ef8e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1107,7 +1107,7 @@ keep:
 		VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
 	}
 
-	free_hot_cold_page_list(&free_pages, 1);
+	free_hot_cold_page_list(&free_pages, true);
 
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
@@ -1505,7 +1505,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	spin_unlock_irq(&zone->lru_lock);
 
-	free_hot_cold_page_list(&page_list, 1);
+	free_hot_cold_page_list(&page_list, true);
 
 	/*
 	 * If reclaim is isolating dirty pages under writeback, it implies
@@ -1725,7 +1725,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
 	spin_unlock_irq(&zone->lru_lock);
 
-	free_hot_cold_page_list(&l_hold, 1);
+	free_hot_cold_page_list(&l_hold, true);
 }
 
 #ifdef CONFIG_SWAP
-- 
1.8.4.5

[PATCH 79/97] mm: page_alloc: lookup pageblock migratetype with IRQs enabled during free

[Mel Gorman]

commit cfc47a2803db42140167b92d991ef04018e162c7 upstream.

get_pageblock_migratetype() is called during free with IRQs disabled.
This is unnecessary and disables IRQs for longer than necessary.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b1b1522..478fcfe 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -760,9 +760,9 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	if (!free_pages_prepare(page, order))
 		return;
 
+	migratetype = get_pfnblock_migratetype(page, pfn);
 	local_irq_save(flags);
 	__count_vm_events(PGFREE, 1 << order);
-	migratetype = get_pfnblock_migratetype(page, pfn);
 	set_freepage_migratetype(page, migratetype);
 	free_one_page(page_zone(page), page, pfn, order, migratetype);
 	local_irq_restore(flags);
-- 
1.8.4.5

[PATCH 80/97] mm: shmem: avoid atomic operation during shmem_getpage_gfp

[Mel Gorman]

commit 07a427884348d38a6fd56fa4d78249c407196650 upstream.

shmem_getpage_gfp uses an atomic operation to set the SwapBacked field
before it's even added to the LRU or visible.  This is unnecessary as what
could it possible race against?  Use an unlocked variant.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/page-flags.h | 1 +
 mm/shmem.c                 | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 67fc8a2..0d1b035 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -208,6 +208,7 @@ PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned)	/* Xen */
 PAGEFLAG(SavePinned, savepinned);			/* Xen */
 PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
 PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
+	__SETPAGEFLAG(SwapBacked, swapbacked)
 
 __PAGEFLAG(SlobFree, slob_free)
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 15e5527..8572e8e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1142,7 +1142,7 @@ repeat:
 			goto decused;
 		}
 
-		SetPageSwapBacked(page);
+		__SetPageSwapBacked(page);
 		__set_page_locked(page);
 		error = mem_cgroup_cache_charge(page, current->mm,
 						gfp & GFP_RECLAIM_MASK);
-- 
1.8.4.5

[PATCH 81/97] mm: do not use atomic operations when releasing pages

[Mel Gorman]

commit e3741b506c5088fa8c911bb5884c430f770fb49d upstream.

There should be no references to it any more and a parallel mark should
not be reordered against us.  Use non-locked varient to clear page active.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/swap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/swap.c b/mm/swap.c
index 026113d..afeabe3 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -835,7 +835,7 @@ void release_pages(struct page **pages, int nr, bool cold)
 		}
 
 		/* Clear Active bit in case of parallel mark_page_accessed */
-		ClearPageActive(page);
+		__ClearPageActive(page);
 
 		list_add(&page->lru, &pages_to_free);
 	}
-- 
1.8.4.5

[PATCH 82/97] mm: do not use unnecessary atomic operations when adding pages to the LRU

[Mel Gorman]

commit 6fb81a17d21f2a138b8f424af4cf379f2b694060 upstream.

When adding pages to the LRU we clear the active bit unconditionally.
As the page could be reachable from other paths we cannot use unlocked
operations without risk of corruption such as a parallel
mark_page_accessed.  This patch tests if is necessary to clear the
active flag before using an atomic operation.  This potentially opens a
tiny race when PageActive is checked as mark_page_accessed could be
called after PageActive was checked.  The race already exists but this
patch changes it slightly.  The consequence is that that the page may be
promoted to the active list that might have been left on the inactive
list before the patch.  It's too tiny a race and too marginal a
consequence to always use atomic operations for.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/swap.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index afeabe3..270b520 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -565,13 +565,15 @@ static void __lru_cache_add(struct page *page)
  */
 void lru_cache_add_anon(struct page *page)
 {
-	ClearPageActive(page);
+	if (PageActive(page))
+		ClearPageActive(page);
 	__lru_cache_add(page);
 }
 
 void lru_cache_add_file(struct page *page)
 {
-	ClearPageActive(page);
+	if (PageActive(page))
+		ClearPageActive(page);
 	__lru_cache_add(page);
 }
 EXPORT_SYMBOL(lru_cache_add_file);
-- 
1.8.4.5

[PATCH 83/97] fs: buffer: do not use unnecessary atomic operations when discarding buffers

[Mel Gorman]

commit e7470ee89f003634a88e7b5e5a7b65b3025987de upstream.

Discarding buffers uses a bunch of atomic operations when discarding
buffers because ......  I can't think of a reason.  Use a cmpxchg loop to
clear all the necessary flags.  In most (all?) cases this will be a single
atomic operations.

[akpm@linux-foundation.org: move BUFFER_FLAGS_DISCARD into the .c file]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 fs/buffer.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index aeeea65..6421d61 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1483,16 +1483,27 @@ EXPORT_SYMBOL(set_bh_page);
 /*
  * Called when truncating a buffer on a page completely.
  */
+
+/* Bits that are cleared during an invalidate */
+#define BUFFER_FLAGS_DISCARD \
+	(1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \
+	 1 << BH_Delay | 1 << BH_Unwritten)
+
 static void discard_buffer(struct buffer_head * bh)
 {
+	unsigned long b_state, b_state_old;
+
 	lock_buffer(bh);
 	clear_buffer_dirty(bh);
 	bh->b_bdev = NULL;
-	clear_buffer_mapped(bh);
-	clear_buffer_req(bh);
-	clear_buffer_new(bh);
-	clear_buffer_delay(bh);
-	clear_buffer_unwritten(bh);
+	b_state = bh->b_state;
+	for (;;) {
+		b_state_old = cmpxchg(&bh->b_state, b_state,
+				      (b_state & ~BUFFER_FLAGS_DISCARD));
+		if (b_state_old == b_state)
+			break;
+		b_state = b_state_old;
+	}
 	unlock_buffer(bh);
 }
 
-- 
1.8.4.5

[PATCH 84/97] mm: non-atomically mark page accessed during page cache allocation where possible

[Mel Gorman]

commit 2457aec63745e235bcafb7ef312b182d8682f0fc upstream.

aops->write_begin may allocate a new page and make it visible only to have
mark_page_accessed called almost immediately after.  Once the page is
visible the atomic operations are necessary which is noticable overhead
when writing to an in-memory filesystem like tmpfs but should also be
noticable with fast storage.  The objective of the patch is to initialse
the accessed information with non-atomic operations before the page is
visible.

The bulk of filesystems directly or indirectly use
grab_cache_page_write_begin or find_or_create_page for the initial
allocation of a page cache page.  This patch adds an init_page_accessed()
helper which behaves like the first call to mark_page_accessed() but may
called before the page is visible and can be done non-atomically.

The primary APIs of concern in this care are the following and are used
by most filesystems.

	find_get_page
	find_lock_page
	find_or_create_page
	grab_cache_page_nowait
	grab_cache_page_write_begin

All of them are very similar in detail to the patch creates a core helper
pagecache_get_page() which takes a flags parameter that affects its
behavior such as whether the page should be marked accessed or not.  Then
old API is preserved but is basically a thin wrapper around this core
function.

Each of the filesystems are then updated to avoid calling
mark_page_accessed when it is known that the VM interfaces have already
done the job.  There is a slight snag in that the timing of the
mark_page_accessed() has now changed so in rare cases it's possible a page
gets to the end of the LRU as PageReferenced where as previously it might
have been repromoted.  This is expected to be rare but it's worth the
filesystem people thinking about it in case they see a problem with the
timing change.  It is also the case that some filesystems may be marking
pages accessed that previously did not but it makes sense that filesystems
have consistent behaviour in this regard.

The test case used to evaulate this is a simple dd of a large file done
multiple times with the file deleted on each iterations.  The size of the
file is 1/10th physical memory to avoid dirty page balancing.  In the
async case it will be possible that the workload completes without even
hitting the disk and will have variable results but highlight the impact
of mark_page_accessed for async IO.  The sync results are expected to be
more stable.  The exception is tmpfs where the normal case is for the "IO"
to not hit the disk.

The test machine was single socket and UMA to avoid any scheduling or NUMA
artifacts.  Throughput and wall times are presented for sync IO, only wall
times are shown for async as the granularity reported by dd and the
variability is unsuitable for comparison.  As async results were variable
do to writback timings, I'm only reporting the maximum figures.  The sync
results were stable enough to make the mean and stddev uninteresting.

The performance results are reported based on a run with no profiling.
Profile data is based on a separate run with oprofile running.

async dd
                                    3.15.0-rc3            3.15.0-rc3
                                       vanilla           accessed-v2
ext3    Max      elapsed     13.9900 (  0.00%)     11.5900 ( 17.16%)
tmpfs	Max      elapsed      0.5100 (  0.00%)      0.4900 (  3.92%)
btrfs   Max      elapsed     12.8100 (  0.00%)     12.7800 (  0.23%)
ext4	Max      elapsed     18.6000 (  0.00%)     13.3400 ( 28.28%)
xfs	Max      elapsed     12.5600 (  0.00%)      2.0900 ( 83.36%)

The XFS figure is a bit strange as it managed to avoid a worst case by
sheer luck but the average figures looked reasonable.

        samples percentage
ext3       86107    0.9783  vmlinux-3.15.0-rc4-vanilla        mark_page_accessed
ext3       23833    0.2710  vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed
ext3        5036    0.0573  vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed
ext4       64566    0.8961  vmlinux-3.15.0-rc4-vanilla        mark_page_accessed
ext4        5322    0.0713  vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed
ext4        2869    0.0384  vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed
xfs        62126    1.7675  vmlinux-3.15.0-rc4-vanilla        mark_page_accessed
xfs         1904    0.0554  vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed
xfs          103    0.0030  vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed
btrfs      10655    0.1338  vmlinux-3.15.0-rc4-vanilla        mark_page_accessed
btrfs       2020    0.0273  vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed
btrfs        587    0.0079  vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed
tmpfs      59562    3.2628  vmlinux-3.15.0-rc4-vanilla        mark_page_accessed
tmpfs       1210    0.0696  vmlinux-3.15.0-rc4-accessed-v3r25 init_page_accessed
tmpfs         94    0.0054  vmlinux-3.15.0-rc4-accessed-v3r25 mark_page_accessed

[akpm@linux-foundation.org: don't run init_page_accessed() against an uninitialised pointer]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Tested-by: Prabhakar Lad <prabhakar.csengg@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 fs/btrfs/extent_io.c       |  15 ++--
 fs/btrfs/file.c            |   5 +-
 fs/buffer.c                |   7 +-
 fs/ext4/mballoc.c          |  14 ++--
 fs/f2fs/checkpoint.c       |   1 -
 fs/f2fs/node.c             |   2 -
 fs/fuse/file.c             |   2 -
 fs/gfs2/aops.c             |   1 -
 fs/gfs2/meta_io.c          |   4 +-
 fs/ntfs/attrib.c           |   1 -
 fs/ntfs/file.c             |   1 -
 include/linux/page-flags.h |   1 +
 include/linux/pagemap.h    | 107 ++++++++++++++++++++++--
 include/linux/swap.h       |   1 +
 mm/filemap.c               | 202 +++++++++++++++++----------------------------
 mm/shmem.c                 |   6 +-
 mm/swap.c                  |  11 +++
 17 files changed, 219 insertions(+), 162 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index b395791..adb5052 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4445,7 +4445,8 @@ static void check_buffer_tree_ref(struct extent_buffer *eb)
 	spin_unlock(&eb->refs_lock);
 }
 
-static void mark_extent_buffer_accessed(struct extent_buffer *eb)
+static void mark_extent_buffer_accessed(struct extent_buffer *eb,
+		struct page *accessed)
 {
 	unsigned long num_pages, i;
 
@@ -4454,7 +4455,8 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb)
 	num_pages = num_extent_pages(eb->start, eb->len);
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = extent_buffer_page(eb, i);
-		mark_page_accessed(p);
+		if (p != accessed)
+			mark_page_accessed(p);
 	}
 }
 
@@ -4475,7 +4477,7 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 	eb = radix_tree_lookup(&tree->buffer, start >> PAGE_CACHE_SHIFT);
 	if (eb && atomic_inc_not_zero(&eb->refs)) {
 		rcu_read_unlock();
-		mark_extent_buffer_accessed(eb);
+		mark_extent_buffer_accessed(eb, NULL);
 		return eb;
 	}
 	rcu_read_unlock();
@@ -4503,7 +4505,7 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 				spin_unlock(&mapping->private_lock);
 				unlock_page(p);
 				page_cache_release(p);
-				mark_extent_buffer_accessed(exists);
+				mark_extent_buffer_accessed(exists, p);
 				goto free_eb;
 			}
 
@@ -4518,7 +4520,6 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 		attach_extent_buffer_page(eb, p);
 		spin_unlock(&mapping->private_lock);
 		WARN_ON(PageDirty(p));
-		mark_page_accessed(p);
 		eb->pages[i] = p;
 		if (!PageUptodate(p))
 			uptodate = 0;
@@ -4548,7 +4549,7 @@ again:
 		}
 		spin_unlock(&tree->buffer_lock);
 		radix_tree_preload_end();
-		mark_extent_buffer_accessed(exists);
+		mark_extent_buffer_accessed(exists, NULL);
 		goto free_eb;
 	}
 	/* add one reference for the tree */
@@ -4594,7 +4595,7 @@ struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
 	eb = radix_tree_lookup(&tree->buffer, start >> PAGE_CACHE_SHIFT);
 	if (eb && atomic_inc_not_zero(&eb->refs)) {
 		rcu_read_unlock();
-		mark_extent_buffer_accessed(eb);
+		mark_extent_buffer_accessed(eb, NULL);
 		return eb;
 	}
 	rcu_read_unlock();
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 9952a2a..ad80dfa 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -471,11 +471,12 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages)
 	for (i = 0; i < num_pages; i++) {
 		/* page checked is some magic around finding pages that
 		 * have been modified without going through btrfs_set_page_dirty
-		 * clear it here
+		 * clear it here. There should be no need to mark the pages
+		 * accessed as prepare_pages should have marked them accessed
+		 * in prepare_pages via find_or_create_page()
 		 */
 		ClearPageChecked(pages[i]);
 		unlock_page(pages[i]);
-		mark_page_accessed(pages[i]);
 		page_cache_release(pages[i]);
 	}
 }
diff --git a/fs/buffer.c b/fs/buffer.c
index 6421d61..b788852 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -227,7 +227,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	int all_mapped = 1;
 
 	index = block >> (PAGE_CACHE_SHIFT - bd_inode->i_blkbits);
-	page = find_get_page(bd_mapping, index);
+	page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED);
 	if (!page)
 		goto out;
 
@@ -1366,12 +1366,13 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size)
 	struct buffer_head *bh = lookup_bh_lru(bdev, block, size);
 
 	if (bh == NULL) {
+		/* __find_get_block_slow will mark the page accessed */
 		bh = __find_get_block_slow(bdev, block);
 		if (bh)
 			bh_lru_install(bh);
-	}
-	if (bh)
+	} else
 		touch_buffer(bh);
+
 	return bh;
 }
 EXPORT_SYMBOL(__find_get_block);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 502f0fd..4cb573d 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1044,6 +1044,8 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 	 * allocating. If we are looking at the buddy cache we would
 	 * have taken a reference using ext4_mb_load_buddy and that
 	 * would have pinned buddy page to page cache.
+	 * The call to ext4_mb_get_buddy_page_lock will mark the
+	 * page accessed.
 	 */
 	ret = ext4_mb_get_buddy_page_lock(sb, group, &e4b);
 	if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) {
@@ -1062,7 +1064,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 		ret = -EIO;
 		goto err;
 	}
-	mark_page_accessed(page);
 
 	if (e4b.bd_buddy_page == NULL) {
 		/*
@@ -1082,7 +1083,6 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group)
 		ret = -EIO;
 		goto err;
 	}
-	mark_page_accessed(page);
 err:
 	ext4_mb_put_buddy_page_lock(&e4b);
 	return ret;
@@ -1141,7 +1141,7 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 
 	/* we could use find_or_create_page(), but it locks page
 	 * what we'd like to avoid in fast path ... */
-	page = find_get_page(inode->i_mapping, pnum);
+	page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED);
 	if (page == NULL || !PageUptodate(page)) {
 		if (page)
 			/*
@@ -1172,15 +1172,16 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 		ret = -EIO;
 		goto err;
 	}
+
+	/* Pages marked accessed already */
 	e4b->bd_bitmap_page = page;
 	e4b->bd_bitmap = page_address(page) + (poff * sb->s_blocksize);
-	mark_page_accessed(page);
 
 	block++;
 	pnum = block / blocks_per_page;
 	poff = block % blocks_per_page;
 
-	page = find_get_page(inode->i_mapping, pnum);
+	page = find_get_page_flags(inode->i_mapping, pnum, FGP_ACCESSED);
 	if (page == NULL || !PageUptodate(page)) {
 		if (page)
 			page_cache_release(page);
@@ -1201,9 +1202,10 @@ ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group,
 		ret = -EIO;
 		goto err;
 	}
+
+	/* Pages marked accessed already */
 	e4b->bd_buddy_page = page;
 	e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize);
-	mark_page_accessed(page);
 
 	BUG_ON(e4b->bd_bitmap_page == NULL);
 	BUG_ON(e4b->bd_buddy_page == NULL);
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index bb31220..15a29af 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -70,7 +70,6 @@ repeat:
 		goto repeat;
 	}
 out:
-	mark_page_accessed(page);
 	return page;
 }
 
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 51ef278..d0335bd 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -970,7 +970,6 @@ repeat:
 	}
 got_it:
 	BUG_ON(nid != nid_of_node(page));
-	mark_page_accessed(page);
 	return page;
 }
 
@@ -1026,7 +1025,6 @@ page_hit:
 		f2fs_put_page(page, 1);
 		return ERR_PTR(-EIO);
 	}
-	mark_page_accessed(page);
 	return page;
 }
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index bf9a755..d08c108 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -988,8 +988,6 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 		tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes);
 		flush_dcache_page(page);
 
-		mark_page_accessed(page);
-
 		if (!tmp) {
 			unlock_page(page);
 			page_cache_release(page);
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 1253c20..f3aee0b 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -517,7 +517,6 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos,
 		p = kmap_atomic(page);
 		memcpy(buf + copied, p + offset, amt);
 		kunmap_atomic(p);
-		mark_page_accessed(page);
 		page_cache_release(page);
 		copied += amt;
 		index++;
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 52f177b..89afe3a 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -128,7 +128,8 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
 			yield();
 		}
 	} else {
-		page = find_lock_page(mapping, index);
+		page = find_get_page_flags(mapping, index,
+						FGP_LOCK|FGP_ACCESSED);
 		if (!page)
 			return NULL;
 	}
@@ -145,7 +146,6 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
 		map_bh(bh, sdp->sd_vfs, blkno);
 
 	unlock_page(page);
-	mark_page_accessed(page);
 	page_cache_release(page);
 
 	return bh;
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index a27e3fe..250ed5b 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -1748,7 +1748,6 @@ int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size)
 	if (page) {
 		set_page_dirty(page);
 		unlock_page(page);
-		mark_page_accessed(page);
 		page_cache_release(page);
 	}
 	ntfs_debug("Done.");
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index ea4ba9d..a0b2f34 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -2060,7 +2060,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
 		}
 		do {
 			unlock_page(pages[--do_pages]);
-			mark_page_accessed(pages[do_pages]);
 			page_cache_release(pages[do_pages]);
 		} while (do_pages);
 		if (unlikely(status))
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 0d1b035..2284ea6 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -198,6 +198,7 @@ struct page;	/* forward declaration */
 TESTPAGEFLAG(Locked, locked)
 PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error)
 PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
+	__SETPAGEFLAG(Referenced, referenced)
 PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
 PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru)
 PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 57e3693..d57a02a 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -248,12 +248,109 @@ pgoff_t page_cache_next_hole(struct address_space *mapping,
 pgoff_t page_cache_prev_hole(struct address_space *mapping,
 			     pgoff_t index, unsigned long max_scan);
 
+#define FGP_ACCESSED		0x00000001
+#define FGP_LOCK		0x00000002
+#define FGP_CREAT		0x00000004
+#define FGP_WRITE		0x00000008
+#define FGP_NOFS		0x00000010
+#define FGP_NOWAIT		0x00000020
+
+struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
+		int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask);
+
+/**
+ * find_get_page - find and get a page reference
+ * @mapping: the address_space to search
+ * @offset: the page index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned with an increased refcount.
+ *
+ * Otherwise, %NULL is returned.
+ */
+static inline struct page *find_get_page(struct address_space *mapping,
+					pgoff_t offset)
+{
+	return pagecache_get_page(mapping, offset, 0, 0, 0);
+}
+
+static inline struct page *find_get_page_flags(struct address_space *mapping,
+					pgoff_t offset, int fgp_flags)
+{
+	return pagecache_get_page(mapping, offset, fgp_flags, 0, 0);
+}
+
+/**
+ * find_lock_page - locate, pin and lock a pagecache page
+ * pagecache_get_page - find and get a page reference
+ * @mapping: the address_space to search
+ * @offset: the page index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_page() may sleep.
+ */
+static inline struct page *find_lock_page(struct address_space *mapping,
+					pgoff_t offset)
+{
+	return pagecache_get_page(mapping, offset, FGP_LOCK, 0, 0);
+}
+
+/**
+ * find_or_create_page - locate or add a pagecache page
+ * @mapping: the page's address_space
+ * @index: the page's index into the mapping
+ * @gfp_mask: page allocation mode
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the page is not present, a new page is allocated using @gfp_mask
+ * and added to the page cache and the VM's LRU list.  The page is
+ * returned locked and with an increased refcount.
+ *
+ * On memory exhaustion, %NULL is returned.
+ *
+ * find_or_create_page() may sleep, even if @gfp_flags specifies an
+ * atomic allocation!
+ */
+static inline struct page *find_or_create_page(struct address_space *mapping,
+					pgoff_t offset, gfp_t gfp_mask)
+{
+	return pagecache_get_page(mapping, offset,
+					FGP_LOCK|FGP_ACCESSED|FGP_CREAT,
+					gfp_mask, gfp_mask & GFP_RECLAIM_MASK);
+}
+
+/**
+ * grab_cache_page_nowait - returns locked page at given index in given cache
+ * @mapping: target address_space
+ * @index: the page index
+ *
+ * Same as grab_cache_page(), but do not wait if the page is unavailable.
+ * This is intended for speculative data generators, where the data can
+ * be regenerated if the page couldn't be grabbed.  This routine should
+ * be safe to call while holding the lock for another page.
+ *
+ * Clear __GFP_FS when allocating the page to avoid recursion into the fs
+ * and deadlock against the caller's locked page.
+ */
+static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
+				pgoff_t index)
+{
+	return pagecache_get_page(mapping, index,
+			FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
+			mapping_gfp_mask(mapping),
+			GFP_NOFS);
+}
+
 struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
-struct page *find_get_page(struct address_space *mapping, pgoff_t offset);
 struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
-struct page *find_lock_page(struct address_space *mapping, pgoff_t offset);
-struct page *find_or_create_page(struct address_space *mapping, pgoff_t index,
-				 gfp_t gfp_mask);
 unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
 			  unsigned int nr_entries, struct page **entries,
 			  pgoff_t *indices);
@@ -276,8 +373,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping,
 	return find_or_create_page(mapping, index, mapping_gfp_mask(mapping));
 }
 
-extern struct page * grab_cache_page_nowait(struct address_space *mapping,
-				pgoff_t index);
 extern struct page * read_cache_page(struct address_space *mapping,
 				pgoff_t index, filler_t *filler, void *data);
 extern struct page * read_cache_page_gfp(struct address_space *mapping,
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c8beed1..241bf09 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -275,6 +275,7 @@ extern void lru_add_page_tail(struct page *page, struct page *page_tail,
 			 struct lruvec *lruvec, struct list_head *head);
 extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
+extern void init_page_accessed(struct page *page);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
 extern void lru_add_drain_all(void);
diff --git a/mm/filemap.c b/mm/filemap.c
index 8144c27..115c77d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -848,26 +848,6 @@ out:
 EXPORT_SYMBOL(find_get_entry);
 
 /**
- * find_get_page - find and get a page reference
- * @mapping: the address_space to search
- * @offset: the page index
- *
- * Looks up the page cache slot at @mapping & @offset.  If there is a
- * page cache page, it is returned with an increased refcount.
- *
- * Otherwise, %NULL is returned.
- */
-struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
-{
-	struct page *page = find_get_entry(mapping, offset);
-
-	if (radix_tree_exceptional_entry(page))
-		page = NULL;
-	return page;
-}
-EXPORT_SYMBOL(find_get_page);
-
-/**
  * find_lock_entry - locate, pin and lock a page cache entry
  * @mapping: the address_space to search
  * @offset: the page cache index
@@ -904,66 +884,84 @@ repeat:
 EXPORT_SYMBOL(find_lock_entry);
 
 /**
- * find_lock_page - locate, pin and lock a pagecache page
+ * pagecache_get_page - find and get a page reference
  * @mapping: the address_space to search
  * @offset: the page index
+ * @fgp_flags: PCG flags
+ * @gfp_mask: gfp mask to use if a page is to be allocated
  *
- * Looks up the page cache slot at @mapping & @offset.  If there is a
- * page cache page, it is returned locked and with an increased
- * refcount.
- *
- * Otherwise, %NULL is returned.
- *
- * find_lock_page() may sleep.
- */
-struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
-{
-	struct page *page = find_lock_entry(mapping, offset);
-
-	if (radix_tree_exceptional_entry(page))
-		page = NULL;
-	return page;
-}
-EXPORT_SYMBOL(find_lock_page);
-
-/**
- * find_or_create_page - locate or add a pagecache page
- * @mapping: the page's address_space
- * @index: the page's index into the mapping
- * @gfp_mask: page allocation mode
+ * Looks up the page cache slot at @mapping & @offset.
  *
- * Looks up the page cache slot at @mapping & @offset.  If there is a
- * page cache page, it is returned locked and with an increased
- * refcount.
+ * PCG flags modify how the page is returned
  *
- * If the page is not present, a new page is allocated using @gfp_mask
- * and added to the page cache and the VM's LRU list.  The page is
- * returned locked and with an increased refcount.
+ * FGP_ACCESSED: the page will be marked accessed
+ * FGP_LOCK: Page is return locked
+ * FGP_CREAT: If page is not present then a new page is allocated using
+ *		@gfp_mask and added to the page cache and the VM's LRU
+ *		list. The page is returned locked and with an increased
+ *		refcount. Otherwise, %NULL is returned.
  *
- * On memory exhaustion, %NULL is returned.
+ * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
+ * if the GFP flags specified for FGP_CREAT are atomic.
  *
- * find_or_create_page() may sleep, even if @gfp_flags specifies an
- * atomic allocation!
+ * If there is a page cache page, it is returned with an increased refcount.
  */
-struct page *find_or_create_page(struct address_space *mapping,
-		pgoff_t index, gfp_t gfp_mask)
+struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
+	int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask)
 {
 	struct page *page;
-	int err;
+
 repeat:
-	page = find_lock_page(mapping, index);
-	if (!page) {
-		page = __page_cache_alloc(gfp_mask);
+	page = find_get_entry(mapping, offset);
+	if (radix_tree_exceptional_entry(page))
+		page = NULL;
+	if (!page)
+		goto no_page;
+
+	if (fgp_flags & FGP_LOCK) {
+		if (fgp_flags & FGP_NOWAIT) {
+			if (!trylock_page(page)) {
+				page_cache_release(page);
+				return NULL;
+			}
+		} else {
+			lock_page(page);
+		}
+
+		/* Has the page been truncated? */
+		if (unlikely(page->mapping != mapping)) {
+			unlock_page(page);
+			page_cache_release(page);
+			goto repeat;
+		}
+		VM_BUG_ON(page->index != offset);
+	}
+
+	if (page && (fgp_flags & FGP_ACCESSED))
+		mark_page_accessed(page);
+
+no_page:
+	if (!page && (fgp_flags & FGP_CREAT)) {
+		int err;
+		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
+			cache_gfp_mask |= __GFP_WRITE;
+		if (fgp_flags & FGP_NOFS) {
+			cache_gfp_mask &= ~__GFP_FS;
+			radix_gfp_mask &= ~__GFP_FS;
+		}
+
+		page = __page_cache_alloc(cache_gfp_mask);
 		if (!page)
 			return NULL;
-		/*
-		 * We want a regular kernel memory (not highmem or DMA etc)
-		 * allocation for the radix tree nodes, but we need to honour
-		 * the context-specific requirements the caller has asked for.
-		 * GFP_RECLAIM_MASK collects those requirements.
-		 */
-		err = add_to_page_cache_lru(page, mapping, index,
-			(gfp_mask & GFP_RECLAIM_MASK));
+
+		if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK)))
+			fgp_flags |= FGP_LOCK;
+
+		/* Init accessed so avoit atomic mark_page_accessed later */
+		if (fgp_flags & FGP_ACCESSED)
+			init_page_accessed(page);
+
+		err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask);
 		if (unlikely(err)) {
 			page_cache_release(page);
 			page = NULL;
@@ -971,9 +969,10 @@ repeat:
 				goto repeat;
 		}
 	}
+
 	return page;
 }
-EXPORT_SYMBOL(find_or_create_page);
+EXPORT_SYMBOL(pagecache_get_page);
 
 /**
  * find_get_entries - gang pagecache lookup
@@ -1263,39 +1262,6 @@ repeat:
 }
 EXPORT_SYMBOL(find_get_pages_tag);
 
-/**
- * grab_cache_page_nowait - returns locked page at given index in given cache
- * @mapping: target address_space
- * @index: the page index
- *
- * Same as grab_cache_page(), but do not wait if the page is unavailable.
- * This is intended for speculative data generators, where the data can
- * be regenerated if the page couldn't be grabbed.  This routine should
- * be safe to call while holding the lock for another page.
- *
- * Clear __GFP_FS when allocating the page to avoid recursion into the fs
- * and deadlock against the caller's locked page.
- */
-struct page *
-grab_cache_page_nowait(struct address_space *mapping, pgoff_t index)
-{
-	struct page *page = find_get_page(mapping, index);
-
-	if (page) {
-		if (trylock_page(page))
-			return page;
-		page_cache_release(page);
-		return NULL;
-	}
-	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS);
-	if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) {
-		page_cache_release(page);
-		page = NULL;
-	}
-	return page;
-}
-EXPORT_SYMBOL(grab_cache_page_nowait);
-
 /*
  * CD/DVDs are error prone. When a medium error occurs, the driver may fail
  * a _large_ part of the i/o request. Imagine the worst scenario:
@@ -2399,7 +2365,6 @@ int pagecache_write_end(struct file *file, struct address_space *mapping,
 {
 	const struct address_space_operations *aops = mapping->a_ops;
 
-	mark_page_accessed(page);
 	return aops->write_end(file, mapping, pos, len, copied, page, fsdata);
 }
 EXPORT_SYMBOL(pagecache_write_end);
@@ -2481,34 +2446,18 @@ EXPORT_SYMBOL(generic_file_direct_write);
 struct page *grab_cache_page_write_begin(struct address_space *mapping,
 					pgoff_t index, unsigned flags)
 {
-	int status;
-	gfp_t gfp_mask;
 	struct page *page;
-	gfp_t gfp_notmask = 0;
+	int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT;
 
-	gfp_mask = mapping_gfp_mask(mapping);
-	if (mapping_cap_account_dirty(mapping))
-		gfp_mask |= __GFP_WRITE;
 	if (flags & AOP_FLAG_NOFS)
-		gfp_notmask = __GFP_FS;
-repeat:
-	page = find_lock_page(mapping, index);
+		fgp_flags |= FGP_NOFS;
+
+	page = pagecache_get_page(mapping, index, fgp_flags,
+			mapping_gfp_mask(mapping),
+			GFP_KERNEL);
 	if (page)
-		goto found;
+		wait_for_stable_page(page);
 
-	page = __page_cache_alloc(gfp_mask & ~gfp_notmask);
-	if (!page)
-		return NULL;
-	status = add_to_page_cache_lru(page, mapping, index,
-						GFP_KERNEL & ~gfp_notmask);
-	if (unlikely(status)) {
-		page_cache_release(page);
-		if (status == -EEXIST)
-			goto repeat;
-		return NULL;
-	}
-found:
-	wait_for_stable_page(page);
 	return page;
 }
 EXPORT_SYMBOL(grab_cache_page_write_begin);
@@ -2557,7 +2506,7 @@ again:
 
 		status = a_ops->write_begin(file, mapping, pos, bytes, flags,
 						&page, &fsdata);
-		if (unlikely(status))
+		if (unlikely(status < 0))
 			break;
 
 		if (mapping_writably_mapped(mapping))
@@ -2566,7 +2515,6 @@ again:
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
 		flush_dcache_page(page);
 
-		mark_page_accessed(page);
 		status = a_ops->write_end(file, mapping, pos, bytes, copied,
 						page, fsdata);
 		if (unlikely(status < 0))
diff --git a/mm/shmem.c b/mm/shmem.c
index 8572e8e..d4b7358 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1440,9 +1440,13 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
 {
+	int ret;
 	struct inode *inode = mapping->host;
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
+	ret = shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
+	if (ret == 0 && *pagep)
+		init_page_accessed(*pagep);
+	return ret;
 }
 
 static int
diff --git a/mm/swap.c b/mm/swap.c
index 270b520..845e91f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -548,6 +548,17 @@ void mark_page_accessed(struct page *page)
 }
 EXPORT_SYMBOL(mark_page_accessed);
 
+/*
+ * Used to mark_page_accessed(page) that is not visible yet and when it is
+ * still safe to use non-atomic ops
+ */
+void init_page_accessed(struct page *page)
+{
+	if (!PageReferenced(page))
+		__SetPageReferenced(page);
+}
+EXPORT_SYMBOL(init_page_accessed);
+
 static void __lru_cache_add(struct page *page)
 {
 	struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
-- 
1.8.4.5

[PATCH 85/97] mm: avoid unnecessary atomic operations during end_page_writeback()

[Mel Gorman]

commit 888cf2db475a256fb0cda042140f73d7881f81fe upstream.

If a page is marked for immediate reclaim then it is moved to the tail of
the LRU list.  This occurs when the system is under enough memory pressure
for pages under writeback to reach the end of the LRU but we test for this
using atomic operations on every writeback.  This patch uses an optimistic
non-atomic test first.  It'll miss some pages in rare cases but the
consequences are not severe enough to warrant such a penalty.

While the function does not dominate profiles during a simple dd test the
cost of it is reduced.

73048     0.7428  vmlinux-3.15.0-rc5-mmotm-20140513 end_page_writeback
23740     0.2409  vmlinux-3.15.0-rc5-lessatomic     end_page_writeback

Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/filemap.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 115c77d..b012dae 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -644,8 +644,17 @@ EXPORT_SYMBOL(unlock_page);
  */
 void end_page_writeback(struct page *page)
 {
-	if (TestClearPageReclaim(page))
+	/*
+	 * TestClearPageReclaim could be used here but it is an atomic
+	 * operation and overkill in this particular case. Failing to
+	 * shuffle a page marked for immediate reclaim is too mild to
+	 * justify taking an atomic operation penalty at the end of
+	 * ever page writeback.
+	 */
+	if (PageReclaim(page)) {
+		ClearPageReclaim(page);
 		rotate_reclaimable_page(page);
+	}
 
 	if (!test_clear_page_writeback(page))
 		BUG();
-- 
1.8.4.5

[PATCH 86/97] shmem: fix init_page_accessed use to stop !PageLRU bug

[Mel Gorman]

From: Hugh Dickins <hughd@google.com>

commit 66d2f4d28cd030220e7ea2a628993fcabcb956d1 upstream.

Under shmem swapping load, I sometimes hit the VM_BUG_ON_PAGE(!PageLRU)
in isolate_lru_pages() at mm/vmscan.c:1281!

Commit 2457aec63745 ("mm: non-atomically mark page accessed during page
cache allocation where possible") looks like interrupted work-in-progress.

mm/filemap.c's call to init_page_accessed() is fine, but not mm/shmem.c's
- shmem_write_begin() is clearly wrong to use it after shmem_getpage(),
when the page is always visible in radix_tree, and often already on LRU.

Revert change to shmem_write_begin(), and use init_page_accessed() or
mark_page_accessed() appropriately for SGP_WRITE in shmem_getpage_gfp().

SGP_WRITE also covers shmem_symlink(), which did not mark_page_accessed()
before; but since many other filesystems use [__]page_symlink(), which did
and does mark the page accessed, consider this as rectifying an oversight.

Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Prabhakar Lad <prabhakar.csengg@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/shmem.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index d4b7358..ab05681 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1037,6 +1037,9 @@ repeat:
 		goto failed;
 	}
 
+	if (page && sgp == SGP_WRITE)
+		mark_page_accessed(page);
+
 	/* fallocated page? */
 	if (page && !PageUptodate(page)) {
 		if (sgp != SGP_READ)
@@ -1118,6 +1121,9 @@ repeat:
 		shmem_recalc_inode(inode);
 		spin_unlock(&info->lock);
 
+		if (sgp == SGP_WRITE)
+			mark_page_accessed(page);
+
 		delete_from_swap_cache(page);
 		set_page_dirty(page);
 		swap_free(swap);
@@ -1144,6 +1150,9 @@ repeat:
 
 		__SetPageSwapBacked(page);
 		__set_page_locked(page);
+		if (sgp == SGP_WRITE)
+			init_page_accessed(page);
+
 		error = mem_cgroup_cache_charge(page, current->mm,
 						gfp & GFP_RECLAIM_MASK);
 		if (error)
@@ -1440,13 +1449,9 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
 {
-	int ret;
 	struct inode *inode = mapping->host;
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	ret = shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
-	if (ret == 0 && *pagep)
-		init_page_accessed(*pagep);
-	return ret;
+	return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
 }
 
 static int
-- 
1.8.4.5

[PATCH 87/97] mm/memory.c: use entry = ACCESS_ONCE(*pte) in handle_pte_fault()

[Mel Gorman]

From: Hugh Dickins <hughd@google.com>

commit c0d73261f5c1355a35b8b40e871d31578ce0c044 upstream.

Use ACCESS_ONCE() in handle_pte_fault() when getting the entry or
orig_pte upon which all subsequent decisions and pte_same() tests will
be made.

I have no evidence that its lack is responsible for the mm/filemap.c:202
BUG_ON(page_mapped(page)) in __delete_from_page_cache() found by
trinity, and I am not optimistic that it will fix it.  But I have found
no other explanation, and ACCESS_ONCE() here will surely not hurt.

If gcc does re-access the pte before passing it down, then that would be
disastrous for correct page fault handling, and certainly could explain
the page_mapped() BUGs seen (concurrent fault causing page to be mapped
in a second time on top of itself: mapcount 2 for a single pte).

Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/memory.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/memory.c b/mm/memory.c
index 99fe3aa..b870c9c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3698,7 +3698,7 @@ static int handle_pte_fault(struct mm_struct *mm,
 	pte_t entry;
 	spinlock_t *ptl;
 
-	entry = *pte;
+	entry = ACCESS_ONCE(*pte);
 	if (!pte_present(entry)) {
 		if (pte_none(entry)) {
 			if (vma->vm_ops) {
-- 
1.8.4.5

[PATCH 88/97] mm, thp: only collapse hugepages to nodes with affinity for zone_reclaim_mode

[Mel Gorman]

From: David Rientjes <rientjes@google.com>

commit 14a4e2141e24304fff2c697be6382ffb83888185 upstream.

Commit 9f1b868a13ac ("mm: thp: khugepaged: add policy for finding target
node") improved the previous khugepaged logic which allocated a
transparent hugepages from the node of the first page being collapsed.

However, it is still possible to collapse pages to remote memory which
may suffer from additional access latency.  With the current policy, it
is possible that 255 pages (with PAGE_SHIFT == 12) will be collapsed
remotely if the majority are allocated from that node.

When zone_reclaim_mode is enabled, it means the VM should make every
attempt to allocate locally to prevent NUMA performance degradation.  In
this case, we do not want to collapse hugepages to remote nodes that
would suffer from increased access latency.  Thus, when
zone_reclaim_mode is enabled, only allow collapsing to nodes with
RECLAIM_DISTANCE or less.

There is no functional change for systems that disable
zone_reclaim_mode.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/huge_memory.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 515e589..2ee5374 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2191,6 +2191,30 @@ static void khugepaged_alloc_sleep(void)
 
 static int khugepaged_node_load[MAX_NUMNODES];
 
+static bool khugepaged_scan_abort(int nid)
+{
+	int i;
+
+	/*
+	 * If zone_reclaim_mode is disabled, then no extra effort is made to
+	 * allocate memory locally.
+	 */
+	if (!zone_reclaim_mode)
+		return false;
+
+	/* If there is a count for this node already, it must be acceptable */
+	if (khugepaged_node_load[nid])
+		return false;
+
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		if (!khugepaged_node_load[i])
+			continue;
+		if (node_distance(nid, i) > RECLAIM_DISTANCE)
+			return true;
+	}
+	return false;
+}
+
 #ifdef CONFIG_NUMA
 static int khugepaged_find_target_node(void)
 {
@@ -2507,6 +2531,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		 * hit record.
 		 */
 		node = page_to_nid(page);
+		if (khugepaged_scan_abort(node))
+			goto out_unmap;
 		khugepaged_node_load[node]++;
 		VM_BUG_ON(PageCompound(page));
 		if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
-- 
1.8.4.5

[PATCH 89/97] mm: make copy_pte_range static again

[Mel Gorman]

From: Jerome Marchand <jmarchan@redhat.com>

commit 21bda264f4243f61dfcc485174055f12ad0530b4 upstream.

Commit 71e3aac0724f ("thp: transparent hugepage core") adds
copy_pte_range prototype to huge_mm.h.  I'm not sure why (or if) this
function have been used outside of memory.c, but it currently isn't.
This patch makes copy_pte_range() static again.

Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/huge_mm.h | 4 ----
 mm/memory.c             | 2 +-
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index a291552..aac671b 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -92,10 +92,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
 #endif /* CONFIG_DEBUG_VM */
 
 extern unsigned long transparent_hugepage_flags;
-extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-			  pmd_t *dst_pmd, pmd_t *src_pmd,
-			  struct vm_area_struct *vma,
-			  unsigned long addr, unsigned long end);
 extern int split_huge_page_to_list(struct page *page, struct list_head *list);
 static inline int split_huge_page(struct page *page)
 {
diff --git a/mm/memory.c b/mm/memory.c
index b870c9c..b590106 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -878,7 +878,7 @@ out_set_pte:
 	return 0;
 }
 
-int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		   pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
 		   unsigned long addr, unsigned long end)
 {
-- 
1.8.4.5

[PATCH 90/97] vmalloc: use rcu list iterator to reduce vmap_area_lock contention

[Mel Gorman]

From: Joonsoo Kim <iamjoonsoo.kim@lge.com>

commit 474750aba88817c53f39424e5567b8e4acc4b39b upstream.

Richard Yao reported a month ago that his system have a trouble with
vmap_area_lock contention during performance analysis by /proc/meminfo.
Andrew asked why his analysis checks /proc/meminfo stressfully, but he
didn't answer it.

  https://lkml.org/lkml/2014/4/10/416

Although I'm not sure that this is right usage or not, there is a
solution reducing vmap_area_lock contention with no side-effect.  That
is just to use rcu list iterator in get_vmalloc_info().

rcu can be used in this function because all RCU protocol is already
respected by writers, since Nick Piggin commit db64fe02258f1 ("mm:
rewrite vmap layer") back in linux-2.6.28

Specifically :
   insertions use list_add_rcu(),
   deletions use list_del_rcu() and kfree_rcu().

Note the rb tree is not used from rcu reader (it would not be safe),
only the vmap_area_list has full RCU protection.

Note that __purge_vmap_area_lazy() already uses this rcu protection.

        rcu_read_lock();
        list_for_each_entry_rcu(va, &vmap_area_list, list) {
                if (va->flags & VM_LAZY_FREE) {
                        if (va->va_start < *start)
                                *start = va->va_start;
                        if (va->va_end > *end)
                                *end = va->va_end;
                        nr += (va->va_end - va->va_start) >> PAGE_SHIFT;
                        list_add_tail(&va->purge_list, &valist);
                        va->flags |= VM_LAZY_FREEING;
                        va->flags &= ~VM_LAZY_FREE;
                }
        }
        rcu_read_unlock();

Peter:

: While rcu list traversal over the vmap_area_list is safe, this may
: arrive at different results than the spinlocked version. The rcu list
: traversal version will not be a 'snapshot' of a single, valid instant
: of the entire vmap_area_list, but rather a potential amalgam of
: different list states.

Joonsoo:

: Yes, you are right, but I don't think that we should be strict here.
: Meminfo is already not a 'snapshot' at specific time.  While we try to get
: certain stats, the other stats can change.  And, although we may arrive at
: different results than the spinlocked version, the difference would not be
: large and would not make serious side-effect.

[edumazet@google.com: add more commit description]
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Reported-by: Richard Yao <ryao@gentoo.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Zhang Yanfei <zhangyanfei.yes@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/vmalloc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e2be0f8..060dc36 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2685,14 +2685,14 @@ void get_vmalloc_info(struct vmalloc_info *vmi)
 
 	prev_end = VMALLOC_START;
 
-	spin_lock(&vmap_area_lock);
+	rcu_read_lock();
 
 	if (list_empty(&vmap_area_list)) {
 		vmi->largest_chunk = VMALLOC_TOTAL;
 		goto out;
 	}
 
-	list_for_each_entry(va, &vmap_area_list, list) {
+	list_for_each_entry_rcu(va, &vmap_area_list, list) {
 		unsigned long addr = va->va_start;
 
 		/*
@@ -2719,7 +2719,7 @@ void get_vmalloc_info(struct vmalloc_info *vmi)
 		vmi->largest_chunk = VMALLOC_END - prev_end;
 
 out:
-	spin_unlock(&vmap_area_lock);
+	rcu_read_unlock();
 }
 #endif
 
-- 
1.8.4.5

[PATCH 91/97] memcg, vmscan: Fix forced scan of anonymous pages

[Mel Gorman]

From: Jerome Marchand <jmarchan@redhat.com>

commit 2ab051e11bfa3cbb7b24177f3d6aaed10a0d743e upstream.

When memory cgoups are enabled, the code that decides to force to scan
anonymous pages in get_scan_count() compares global values (free,
high_watermark) to a value that is restricted to a memory cgroup (file).
It make the code over-eager to force anon scan.

For instance, it will force anon scan when scanning a memcg that is
mainly populated by anonymous page, even when there is plenty of file
pages to get rid of in others memcgs, even when swappiness == 0.  It
breaks user's expectation about swappiness and hurts performance.

This patch makes sure that forced anon scan only happens when there not
enough file pages for the all zone, not just in one random memcg.

[hannes@cmpxchg.org: cleanups]
Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/vmscan.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 360ef8e..181f0b8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1847,7 +1847,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	struct zone *zone = lruvec_zone(lruvec);
 	unsigned long anon_prio, file_prio;
 	enum scan_balance scan_balance;
-	unsigned long anon, file, free;
+	unsigned long anon, file;
 	bool force_scan = false;
 	unsigned long ap, fp;
 	enum lru_list lru;
@@ -1895,11 +1895,6 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 		goto out;
 	}
 
-	anon  = get_lru_size(lruvec, LRU_ACTIVE_ANON) +
-		get_lru_size(lruvec, LRU_INACTIVE_ANON);
-	file  = get_lru_size(lruvec, LRU_ACTIVE_FILE) +
-		get_lru_size(lruvec, LRU_INACTIVE_FILE);
-
 	/*
 	 * If it's foreseeable that reclaiming the file cache won't be
 	 * enough to get the zone back into a desirable shape, we have
@@ -1907,8 +1902,14 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	 * thrashing - remaining file pages alone.
 	 */
 	if (global_reclaim(sc)) {
-		free = zone_page_state(zone, NR_FREE_PAGES);
-		if (unlikely(file + free <= high_wmark_pages(zone))) {
+		unsigned long zonefile;
+		unsigned long zonefree;
+
+		zonefree = zone_page_state(zone, NR_FREE_PAGES);
+		zonefile = zone_page_state(zone, NR_ACTIVE_FILE) +
+			   zone_page_state(zone, NR_INACTIVE_FILE);
+
+		if (unlikely(zonefile + zonefree <= high_wmark_pages(zone))) {
 			scan_balance = SCAN_ANON;
 			goto out;
 		}
@@ -1943,6 +1944,12 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	 *
 	 * anon in [0], file in [1]
 	 */
+
+	anon  = get_lru_size(lruvec, LRU_ACTIVE_ANON) +
+		get_lru_size(lruvec, LRU_INACTIVE_ANON);
+	file  = get_lru_size(lruvec, LRU_ACTIVE_FILE) +
+		get_lru_size(lruvec, LRU_INACTIVE_FILE);
+
 	spin_lock_irq(&zone->lru_lock);
 	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
 		reclaim_stat->recent_scanned[0] /= 2;
-- 
1.8.4.5

[PATCH 92/97] mm: pagemap: avoid unnecessary overhead when tracepoints are deactivated

[Mel Gorman]

commit 24b7e5819ad5cbef2b7c7376510862aa8319d240 upstream.

This was formerly the series "Improve sequential read throughput" which
noted some major differences in performance of tiobench since 3.0.
While there are a number of factors, two that dominated were the
introduction of the fair zone allocation policy and changes to CFQ.

The behaviour of fair zone allocation policy makes more sense than
tiobench as a benchmark and CFQ defaults were not changed due to
insufficient benchmarking.

This series is what's left.  It's one functional fix to the fair zone
allocation policy when used on NUMA machines and a reduction of overhead
in general.  tiobench was used for the comparison despite its flaws as
an IO benchmark as in this case we are primarily interested in the
overhead of page allocator and page reclaim activity.

On UMA, it makes little difference to overhead

          3.16.0-rc3   3.16.0-rc3
             vanilla lowercost-v5
User          383.61      386.77
System        403.83      401.74
Elapsed      5411.50     5413.11

On a 4-socket NUMA machine it's a bit more noticable

          3.16.0-rc3   3.16.0-rc3
             vanilla lowercost-v5
User          746.94      802.00
System      65336.22    40852.33
Elapsed     27553.52    27368.46

This patch (of 6):

The LRU insertion and activate tracepoints take PFN as a parameter
forcing the overhead to the caller.  Move the overhead to the tracepoint
fast-assign method to ensure the cost is only incurred when the
tracepoint is active.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/trace/events/pagemap.h | 16 +++++++---------
 mm/swap.c                      |  4 ++--
 2 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h
index 1c9fabd..ce0803b 100644
--- a/include/trace/events/pagemap.h
+++ b/include/trace/events/pagemap.h
@@ -28,12 +28,10 @@ TRACE_EVENT(mm_lru_insertion,
 
 	TP_PROTO(
 		struct page *page,
-		unsigned long pfn,
-		int lru,
-		unsigned long flags
+		int lru
 	),
 
-	TP_ARGS(page, pfn, lru, flags),
+	TP_ARGS(page, lru),
 
 	TP_STRUCT__entry(
 		__field(struct page *,	page	)
@@ -44,9 +42,9 @@ TRACE_EVENT(mm_lru_insertion,
 
 	TP_fast_assign(
 		__entry->page	= page;
-		__entry->pfn	= pfn;
+		__entry->pfn	= page_to_pfn(page);
 		__entry->lru	= lru;
-		__entry->flags	= flags;
+		__entry->flags	= trace_pagemap_flags(page);
 	),
 
 	/* Flag format is based on page-types.c formatting for pagemap */
@@ -64,9 +62,9 @@ TRACE_EVENT(mm_lru_insertion,
 
 TRACE_EVENT(mm_lru_activate,
 
-	TP_PROTO(struct page *page, unsigned long pfn),
+	TP_PROTO(struct page *page),
 
-	TP_ARGS(page, pfn),
+	TP_ARGS(page),
 
 	TP_STRUCT__entry(
 		__field(struct page *,	page	)
@@ -75,7 +73,7 @@ TRACE_EVENT(mm_lru_activate,
 
 	TP_fast_assign(
 		__entry->page	= page;
-		__entry->pfn	= pfn;
+		__entry->pfn	= page_to_pfn(page);
 	),
 
 	/* Flag format is based on page-types.c formatting for pagemap */
diff --git a/mm/swap.c b/mm/swap.c
index 845e91f..16e70ce 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -437,7 +437,7 @@ static void __activate_page(struct page *page, struct lruvec *lruvec,
 		SetPageActive(page);
 		lru += LRU_ACTIVE;
 		add_page_to_lru_list(page, lruvec, lru);
-		trace_mm_lru_activate(page, page_to_pfn(page));
+		trace_mm_lru_activate(page);
 
 		__count_vm_event(PGACTIVATE);
 		update_page_reclaim_stat(lruvec, file, 1);
@@ -930,7 +930,7 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec,
 	SetPageLRU(page);
 	add_page_to_lru_list(page, lruvec, lru);
 	update_page_reclaim_stat(lruvec, file, active);
-	trace_mm_lru_insertion(page, page_to_pfn(page), lru, trace_pagemap_flags(page));
+	trace_mm_lru_insertion(page, lru);
 }
 
 /*
-- 
1.8.4.5

[PATCH 93/97] mm: rearrange zone fields into read-only, page alloc, statistics and page reclaim lines

[Mel Gorman]

commit 3484b2de9499df23c4604a513b36f96326ae81ad upstream.

The arrangement of struct zone has changed over time and now it has
reached the point where there is some inappropriate sharing going on.
On x86-64 for example

o The zone->node field is shared with the zone lock and zone->node is
  accessed frequently from the page allocator due to the fair zone
  allocation policy.

o span_seqlock is almost never used by shares a line with free_area

o Some zone statistics share a cache line with the LRU lock so
  reclaim-intensive and allocator-intensive workloads can bounce the cache
  line on a stat update

This patch rearranges struct zone to put read-only and read-mostly
fields together and then splits the page allocator intensive fields, the
zone statistics and the page reclaim intensive fields into their own
cache lines.  Note that the type of lowmem_reserve changes due to the
watermark calculations being signed and avoiding a signed/unsigned
conversion there.

On the test configuration I used the overall size of struct zone shrunk
by one cache line.  On smaller machines, this is not likely to be
noticable.  However, on a 4-node NUMA machine running tiobench the
system CPU overhead is reduced by this patch.

          3.16.0-rc3  3.16.0-rc3
             vanillarearrange-v5r9
User          746.94      759.78
System      65336.22    58350.98
Elapsed     27553.52    27282.02

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mmzone.h | 205 +++++++++++++++++++++++++------------------------
 mm/page_alloc.c        |   7 +-
 mm/vmstat.c            |   4 +-
 3 files changed, 110 insertions(+), 106 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index b45c3a7..9ff35da 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -321,19 +321,12 @@ enum zone_type {
 #ifndef __GENERATING_BOUNDS_H
 
 struct zone {
-	/* Fields commonly accessed by the page allocator */
+	/* Read-mostly fields */
 
 	/* zone watermarks, access with *_wmark_pages(zone) macros */
 	unsigned long watermark[NR_WMARK];
 
 	/*
-	 * When free pages are below this point, additional steps are taken
-	 * when reading the number of free pages to avoid per-cpu counter
-	 * drift allowing watermarks to be breached
-	 */
-	unsigned long percpu_drift_mark;
-
-	/*
 	 * We don't know if the memory that we're going to allocate will be freeable
 	 * or/and it will be released eventually, so to avoid totally wasting several
 	 * GB of ram we must reserve some of the lower zone memory (otherwise we risk
@@ -341,41 +334,26 @@ struct zone {
 	 * on the higher zones). This array is recalculated at runtime if the
 	 * sysctl_lowmem_reserve_ratio sysctl changes.
 	 */
-	unsigned long		lowmem_reserve[MAX_NR_ZONES];
-
-	/*
-	 * This is a per-zone reserve of pages that should not be
-	 * considered dirtyable memory.
-	 */
-	unsigned long		dirty_balance_reserve;
+	long lowmem_reserve[MAX_NR_ZONES];
 
 #ifdef CONFIG_NUMA
 	int node;
+#endif
+
 	/*
-	 * zone reclaim becomes active if more unmapped pages exist.
+	 * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
+	 * this zone's LRU.  Maintained by the pageout code.
 	 */
-	unsigned long		min_unmapped_pages;
-	unsigned long		min_slab_pages;
-#endif
+	unsigned int inactive_ratio;
+
+	struct pglist_data	*zone_pgdat;
 	struct per_cpu_pageset __percpu *pageset;
+
 	/*
-	 * free areas of different sizes
+	 * This is a per-zone reserve of pages that should not be
+	 * considered dirtyable memory.
 	 */
-	spinlock_t		lock;
-#if defined CONFIG_COMPACTION || defined CONFIG_CMA
-	/* Set to true when the PG_migrate_skip bits should be cleared */
-	bool			compact_blockskip_flush;
-
-	/* pfn where compaction free scanner should start */
-	unsigned long		compact_cached_free_pfn;
-	/* pfn where async and sync compaction migration scanner should start */
-	unsigned long		compact_cached_migrate_pfn[2];
-#endif
-#ifdef CONFIG_MEMORY_HOTPLUG
-	/* see spanned/present_pages for more description */
-	seqlock_t		span_seqlock;
-#endif
-	struct free_area	free_area[MAX_ORDER];
+	unsigned long		dirty_balance_reserve;
 
 #ifndef CONFIG_SPARSEMEM
 	/*
@@ -385,71 +363,14 @@ struct zone {
 	unsigned long		*pageblock_flags;
 #endif /* CONFIG_SPARSEMEM */
 
-#ifdef CONFIG_COMPACTION
-	/*
-	 * On compaction failure, 1<<compact_defer_shift compactions
-	 * are skipped before trying again. The number attempted since
-	 * last failure is tracked with compact_considered.
-	 */
-	unsigned int		compact_considered;
-	unsigned int		compact_defer_shift;
-	int			compact_order_failed;
-#endif
-
-	ZONE_PADDING(_pad1_)
-
-	/* Fields commonly accessed by the page reclaim scanner */
-	spinlock_t		lru_lock;
-	struct lruvec		lruvec;
-
-	unsigned long		pages_scanned;	   /* since last reclaim */
-	unsigned long		flags;		   /* zone flags, see below */
-
-	/* Zone statistics */
-	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
-
-	/*
-	 * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
-	 * this zone's LRU.  Maintained by the pageout code.
-	 */
-	unsigned int inactive_ratio;
-
-
-	ZONE_PADDING(_pad2_)
-	/* Rarely used or read-mostly fields */
-
+#ifdef CONFIG_NUMA
 	/*
-	 * wait_table		-- the array holding the hash table
-	 * wait_table_hash_nr_entries	-- the size of the hash table array
-	 * wait_table_bits	-- wait_table_size == (1 << wait_table_bits)
-	 *
-	 * The purpose of all these is to keep track of the people
-	 * waiting for a page to become available and make them
-	 * runnable again when possible. The trouble is that this
-	 * consumes a lot of space, especially when so few things
-	 * wait on pages at a given time. So instead of using
-	 * per-page waitqueues, we use a waitqueue hash table.
-	 *
-	 * The bucket discipline is to sleep on the same queue when
-	 * colliding and wake all in that wait queue when removing.
-	 * When something wakes, it must check to be sure its page is
-	 * truly available, a la thundering herd. The cost of a
-	 * collision is great, but given the expected load of the
-	 * table, they should be so rare as to be outweighed by the
-	 * benefits from the saved space.
-	 *
-	 * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
-	 * primary users of these fields, and in mm/page_alloc.c
-	 * free_area_init_core() performs the initialization of them.
+	 * zone reclaim becomes active if more unmapped pages exist.
 	 */
-	wait_queue_head_t	* wait_table;
-	unsigned long		wait_table_hash_nr_entries;
-	unsigned long		wait_table_bits;
+	unsigned long		min_unmapped_pages;
+	unsigned long		min_slab_pages;
+#endif /* CONFIG_NUMA */
 
-	/*
-	 * Discontig memory support fields.
-	 */
-	struct pglist_data	*zone_pgdat;
 	/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
 	unsigned long		zone_start_pfn;
 
@@ -495,9 +416,11 @@ struct zone {
 	 * adjust_managed_page_count() should be used instead of directly
 	 * touching zone->managed_pages and totalram_pages.
 	 */
+	unsigned long		managed_pages;
 	unsigned long		spanned_pages;
 	unsigned long		present_pages;
-	unsigned long		managed_pages;
+
+	const char		*name;
 
 	/*
 	 * Number of MIGRATE_RESEVE page block. To maintain for just
@@ -505,10 +428,92 @@ struct zone {
 	 */
 	int			nr_migrate_reserve_block;
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+	/* see spanned/present_pages for more description */
+	seqlock_t		span_seqlock;
+#endif
+
 	/*
-	 * rarely used fields:
+	 * wait_table		-- the array holding the hash table
+	 * wait_table_hash_nr_entries	-- the size of the hash table array
+	 * wait_table_bits	-- wait_table_size == (1 << wait_table_bits)
+	 *
+	 * The purpose of all these is to keep track of the people
+	 * waiting for a page to become available and make them
+	 * runnable again when possible. The trouble is that this
+	 * consumes a lot of space, especially when so few things
+	 * wait on pages at a given time. So instead of using
+	 * per-page waitqueues, we use a waitqueue hash table.
+	 *
+	 * The bucket discipline is to sleep on the same queue when
+	 * colliding and wake all in that wait queue when removing.
+	 * When something wakes, it must check to be sure its page is
+	 * truly available, a la thundering herd. The cost of a
+	 * collision is great, but given the expected load of the
+	 * table, they should be so rare as to be outweighed by the
+	 * benefits from the saved space.
+	 *
+	 * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
+	 * primary users of these fields, and in mm/page_alloc.c
+	 * free_area_init_core() performs the initialization of them.
 	 */
-	const char		*name;
+	wait_queue_head_t	*wait_table;
+	unsigned long		wait_table_hash_nr_entries;
+	unsigned long		wait_table_bits;
+
+	ZONE_PADDING(_pad1_)
+
+	/* Write-intensive fields used from the page allocator */
+	spinlock_t		lock;
+
+	/* free areas of different sizes */
+	struct free_area	free_area[MAX_ORDER];
+
+	/* zone flags, see below */
+	unsigned long		flags;
+
+	ZONE_PADDING(_pad2_)
+
+	/* Write-intensive fields used by page reclaim */
+
+	/* Fields commonly accessed by the page reclaim scanner */
+	spinlock_t		lru_lock;
+	unsigned long		pages_scanned;	   /* since last reclaim */
+	struct lruvec		lruvec;
+
+	/*
+	 * When free pages are below this point, additional steps are taken
+	 * when reading the number of free pages to avoid per-cpu counter
+	 * drift allowing watermarks to be breached
+	 */
+	unsigned long percpu_drift_mark;
+
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+	/* pfn where compaction free scanner should start */
+	unsigned long		compact_cached_free_pfn;
+	/* pfn where async and sync compaction migration scanner should start */
+	unsigned long		compact_cached_migrate_pfn[2];
+#endif
+
+#ifdef CONFIG_COMPACTION
+	/*
+	 * On compaction failure, 1<<compact_defer_shift compactions
+	 * are skipped before trying again. The number attempted since
+	 * last failure is tracked with compact_considered.
+	 */
+	unsigned int		compact_considered;
+	unsigned int		compact_defer_shift;
+	int			compact_order_failed;
+#endif
+
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+	/* Set to true when the PG_migrate_skip bits should be cleared */
+	bool			compact_blockskip_flush;
+#endif
+
+	ZONE_PADDING(_pad3_)
+	/* Zone statistics */
+	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
 } ____cacheline_internodealigned_in_smp;
 
 typedef enum {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 478fcfe..36e6214 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1685,7 +1685,6 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
 {
 	/* free_pages my go negative - that's OK */
 	long min = mark;
-	long lowmem_reserve = z->lowmem_reserve[classzone_idx];
 	int o;
 	long free_cma = 0;
 
@@ -1700,7 +1699,7 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
 		free_cma = zone_page_state(z, NR_FREE_CMA_PAGES);
 #endif
 
-	if (free_pages - free_cma <= min + lowmem_reserve)
+	if (free_pages - free_cma <= min + z->lowmem_reserve[classzone_idx])
 		return false;
 	for (o = 0; o < order; o++) {
 		/* At the next order, this order's pages become unavailable */
@@ -3224,7 +3223,7 @@ void show_free_areas(unsigned int filter)
 			);
 		printk("lowmem_reserve[]:");
 		for (i = 0; i < MAX_NR_ZONES; i++)
-			printk(" %lu", zone->lowmem_reserve[i]);
+			printk(" %ld", zone->lowmem_reserve[i]);
 		printk("\n");
 	}
 
@@ -5527,7 +5526,7 @@ static void calculate_totalreserve_pages(void)
 	for_each_online_pgdat(pgdat) {
 		for (i = 0; i < MAX_NR_ZONES; i++) {
 			struct zone *zone = pgdat->node_zones + i;
-			unsigned long max = 0;
+			long max = 0;
 
 			/* Find valid and maximum lowmem_reserve in the zone */
 			for (j = i; j < MAX_NR_ZONES; j++) {
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 8e8acfa..4a32236 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1065,10 +1065,10 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 				zone_page_state(zone, i));
 
 	seq_printf(m,
-		   "\n        protection: (%lu",
+		   "\n        protection: (%ld",
 		   zone->lowmem_reserve[0]);
 	for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
-		seq_printf(m, ", %lu", zone->lowmem_reserve[i]);
+		seq_printf(m, ", %ld", zone->lowmem_reserve[i]);
 	seq_printf(m,
 		   ")"
 		   "\n  pagesets");
-- 
1.8.4.5

[PATCH 94/97] mm: move zone->pages_scanned into a vmstat counter

[Mel Gorman]

commit 0d5d823ab4e608ec7b52ac4410de4cb74bbe0edd upstream.

zone->pages_scanned is a write-intensive cache line during page reclaim
and it's also updated during page free.  Move the counter into vmstat to
take advantage of the per-cpu updates and do not update it in the free
paths unless necessary.

On a small UMA machine running tiobench the difference is marginal.  On
a 4-node machine the overhead is more noticable.  Note that automatic
NUMA balancing was disabled for this test as otherwise the system CPU
overhead is unpredictable.

          3.16.0-rc3  3.16.0-rc3  3.16.0-rc3
             vanillarearrange-v5   vmstat-v5
User          746.94      759.78      774.56
System      65336.22    58350.98    32847.27
Elapsed     27553.52    27282.02    27415.04

Note that the overhead reduction will vary depending on where exactly
pages are allocated and freed.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mmzone.h |  2 +-
 mm/page_alloc.c        | 12 +++++++++---
 mm/vmscan.c            |  7 ++++---
 mm/vmstat.c            |  3 ++-
 4 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9ff35da..1df12c6 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -143,6 +143,7 @@ enum zone_stat_item {
 	NR_SHMEM,		/* shmem pages (included tmpfs/GEM pages) */
 	NR_DIRTIED,		/* page dirtyings since bootup */
 	NR_WRITTEN,		/* page writings since bootup */
+	NR_PAGES_SCANNED,	/* pages scanned since last reclaim */
 #ifdef CONFIG_NUMA
 	NUMA_HIT,		/* allocated in intended node */
 	NUMA_MISS,		/* allocated in non intended node */
@@ -478,7 +479,6 @@ struct zone {
 
 	/* Fields commonly accessed by the page reclaim scanner */
 	spinlock_t		lru_lock;
-	unsigned long		pages_scanned;	   /* since last reclaim */
 	struct lruvec		lruvec;
 
 	/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 36e6214..ee24ebb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -664,9 +664,12 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 	int migratetype = 0;
 	int batch_free = 0;
 	int to_free = count;
+	unsigned long nr_scanned;
 
 	spin_lock(&zone->lock);
-	zone->pages_scanned = 0;
+	nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
+	if (nr_scanned)
+		__mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
 
 	while (to_free) {
 		struct page *page;
@@ -715,8 +718,11 @@ static void free_one_page(struct zone *zone,
 				unsigned int order,
 				int migratetype)
 {
+	unsigned long nr_scanned;
 	spin_lock(&zone->lock);
-	zone->pages_scanned = 0;
+	nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED);
+	if (nr_scanned)
+		__mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
 
 	__free_one_page(page, pfn, zone, order, migratetype);
 	if (unlikely(!is_migrate_isolate(migratetype)))
@@ -3218,7 +3224,7 @@ void show_free_areas(unsigned int filter)
 			K(zone_page_state(zone, NR_BOUNCE)),
 			K(zone_page_state(zone, NR_FREE_CMA_PAGES)),
 			K(zone_page_state(zone, NR_WRITEBACK_TEMP)),
-			zone->pages_scanned,
+			K(zone_page_state(zone, NR_PAGES_SCANNED)),
 			(!zone_reclaimable(zone) ? "yes" : "no")
 			);
 		printk("lowmem_reserve[]:");
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 181f0b8..5461d02 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -163,7 +163,8 @@ static unsigned long zone_reclaimable_pages(struct zone *zone)
 
 bool zone_reclaimable(struct zone *zone)
 {
-	return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
+	return zone_page_state(zone, NR_PAGES_SCANNED) <
+		zone_reclaimable_pages(zone) * 6;
 }
 
 static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
@@ -1470,7 +1471,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
 
 	if (global_reclaim(sc)) {
-		zone->pages_scanned += nr_scanned;
+		__mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned);
 		if (current_is_kswapd())
 			__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned);
 		else
@@ -1659,7 +1660,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
 				     &nr_scanned, sc, isolate_mode, lru);
 	if (global_reclaim(sc))
-		zone->pages_scanned += nr_scanned;
+		__mod_zone_page_state(zone, NR_PAGES_SCANNED, nr_scanned);
 
 	reclaim_stat->recent_scanned[file] += nr_taken;
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 4a32236..28245d5 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -761,6 +761,7 @@ const char * const vmstat_text[] = {
 	"nr_shmem",
 	"nr_dirtied",
 	"nr_written",
+	"nr_pages_scanned",
 
 #ifdef CONFIG_NUMA
 	"numa_hit",
@@ -1055,7 +1056,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   min_wmark_pages(zone),
 		   low_wmark_pages(zone),
 		   high_wmark_pages(zone),
-		   zone->pages_scanned,
+		   zone_page_state(zone, NR_PAGES_SCANNED),
 		   zone->spanned_pages,
 		   zone->present_pages,
 		   zone->managed_pages);
-- 
1.8.4.5

[PATCH 95/97] mm: vmscan: only update per-cpu thresholds for online CPU

[Mel Gorman]

commit bb0b6dffa2ccfbd9747ad0cc87c7459622896e60 upstream.

When kswapd is awake reclaiming, the per-cpu stat thresholds are lowered
to get more accurate counts to avoid breaching watermarks.  This
threshold update iterates over all possible CPUs which is unnecessary.
Only online CPUs need to be updated.  If a new CPU is onlined,
refresh_zone_stat_thresholds() will set the thresholds correctly.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/vmstat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 28245d5..f7ca044 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -200,7 +200,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat,
 			continue;
 
 		threshold = (*calculate_pressure)(zone);
-		for_each_possible_cpu(cpu)
+		for_each_online_cpu(cpu)
 			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
 							= threshold;
 	}
-- 
1.8.4.5

[PATCH 96/97] mm: page_alloc: abort fair zone allocation policy when remotes nodes are encountered

[Mel Gorman]

commit f7b5d647946aae1647bf5cd26c16b3a793c1ac49 upstream.

The purpose of numa_zonelist_order=zone is to preserve lower zones for
use with 32-bit devices.  If locality is preferred then the
numa_zonelist_order=node policy should be used.

Unfortunately, the fair zone allocation policy overrides this by
skipping zones on remote nodes until the lower one is found.  While this
makes sense from a page aging and performance perspective, it breaks the
expected zonelist policy.  This patch restores the expected behaviour
for zone-list ordering.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ee24ebb..16e6740 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1955,7 +1955,7 @@ zonelist_scan:
 		 */
 		if (alloc_flags & ALLOC_FAIR) {
 			if (!zone_local(preferred_zone, zone))
-				continue;
+				break;
 			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
 				continue;
 		}
-- 
1.8.4.5

[PATCH 97/97] mm: page_alloc: reduce cost of the fair zone allocation policy

[Mel Gorman]

commit 4ffeaf3560a52b4a69cc7909873d08c0ef5909d4 upstream.

The fair zone allocation policy round-robins allocations between zones
within a node to avoid age inversion problems during reclaim.  If the
first allocation fails, the batch counts are reset and a second attempt
made before entering the slow path.

One assumption made with this scheme is that batches expire at roughly
the same time and the resets each time are justified.  This assumption
does not hold when zones reach their low watermark as the batches will
be consumed at uneven rates.  Allocation failure due to watermark
depletion result in additional zonelist scans for the reset and another
watermark check before hitting the slowpath.

On UMA, the benefit is negligible -- around 0.25%.  On 4-socket NUMA
machine it's variable due to the variability of measuring overhead with
the vmstat changes.  The system CPU overhead comparison looks like

          3.16.0-rc3  3.16.0-rc3  3.16.0-rc3
             vanilla   vmstat-v5 lowercost-v5
User          746.94      774.56      802.00
System      65336.22    32847.27    40852.33
Elapsed     27553.52    27415.04    27368.46

However it is worth noting that the overall benchmark still completed
faster and intuitively it makes sense to take as few passes as possible
through the zonelists.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mmzone.h |   6 +++
 mm/page_alloc.c        | 101 ++++++++++++++++++++++++++-----------------------
 2 files changed, 59 insertions(+), 48 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 1df12c6..450f19c 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -529,6 +529,7 @@ typedef enum {
 	ZONE_WRITEBACK,			/* reclaim scanning has recently found
 					 * many pages under writeback
 					 */
+	ZONE_FAIR_DEPLETED,		/* fair zone policy batch depleted */
 } zone_flags_t;
 
 static inline void zone_set_flag(struct zone *zone, zone_flags_t flag)
@@ -566,6 +567,11 @@ static inline int zone_is_reclaim_locked(const struct zone *zone)
 	return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags);
 }
 
+static inline int zone_is_fair_depleted(const struct zone *zone)
+{
+	return test_bit(ZONE_FAIR_DEPLETED, &zone->flags);
+}
+
 static inline int zone_is_oom_locked(const struct zone *zone)
 {
 	return test_bit(ZONE_OOM_LOCKED, &zone->flags);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 16e6740..2f91223 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1589,6 +1589,9 @@ again:
 	}
 
 	__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+	if (zone_page_state(zone, NR_ALLOC_BATCH) == 0 &&
+	    !zone_is_fair_depleted(zone))
+		zone_set_flag(zone, ZONE_FAIR_DEPLETED);
 
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
@@ -1913,6 +1916,18 @@ static inline void init_zone_allows_reclaim(int nid)
 }
 #endif	/* CONFIG_NUMA */
 
+static void reset_alloc_batches(struct zone *preferred_zone)
+{
+	struct zone *zone = preferred_zone->zone_pgdat->node_zones;
+
+	do {
+		mod_zone_page_state(zone, NR_ALLOC_BATCH,
+			high_wmark_pages(zone) - low_wmark_pages(zone) -
+			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
+		zone_clear_flag(zone, ZONE_FAIR_DEPLETED);
+	} while (zone++ != preferred_zone);
+}
+
 /*
  * get_page_from_freelist goes through the zonelist trying to allocate
  * a page.
@@ -1930,8 +1945,12 @@ get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
 	int did_zlc_setup = 0;		/* just call zlc_setup() one time */
 	bool consider_zone_dirty = (alloc_flags & ALLOC_WMARK_LOW) &&
 				(gfp_mask & __GFP_WRITE);
+	int nr_fair_skipped = 0;
+	bool zonelist_rescan;
 
 zonelist_scan:
+	zonelist_rescan = false;
+
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
 	 * See also __cpuset_node_allowed_softwall() comment in kernel/cpuset.c.
@@ -1956,8 +1975,10 @@ zonelist_scan:
 		if (alloc_flags & ALLOC_FAIR) {
 			if (!zone_local(preferred_zone, zone))
 				break;
-			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
+			if (zone_is_fair_depleted(zone)) {
+				nr_fair_skipped++;
 				continue;
+			}
 		}
 		/*
 		 * When allocating a page cache page for writing, we
@@ -2063,13 +2084,7 @@ this_zone_full:
 			zlc_mark_zone_full(zonelist, z);
 	}
 
-	if (unlikely(IS_ENABLED(CONFIG_NUMA) && page == NULL && zlc_active)) {
-		/* Disable zlc cache for second zonelist scan */
-		zlc_active = 0;
-		goto zonelist_scan;
-	}
-
-	if (page)
+	if (page) {
 		/*
 		 * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was
 		 * necessary to allocate the page. The expectation is
@@ -2078,8 +2093,37 @@ this_zone_full:
 		 * for !PFMEMALLOC purposes.
 		 */
 		page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS);
+		return page;
+	}
 
-	return page;
+	/*
+	 * The first pass makes sure allocations are spread fairly within the
+	 * local node.  However, the local node might have free pages left
+	 * after the fairness batches are exhausted, and remote zones haven't
+	 * even been considered yet.  Try once more without fairness, and
+	 * include remote zones now, before entering the slowpath and waking
+	 * kswapd: prefer spilling to a remote zone over swapping locally.
+	 */
+	if (alloc_flags & ALLOC_FAIR) {
+		alloc_flags &= ~ALLOC_FAIR;
+		if (nr_fair_skipped) {
+			zonelist_rescan = true;
+			reset_alloc_batches(preferred_zone);
+		}
+		if (nr_online_nodes > 1)
+			zonelist_rescan = true;
+	}
+
+	if (unlikely(IS_ENABLED(CONFIG_NUMA) && zlc_active)) {
+		/* Disable zlc cache for second zonelist scan */
+		zlc_active = 0;
+		zonelist_rescan = true;
+	}
+
+	if (zonelist_rescan)
+		goto zonelist_scan;
+
+	return NULL;
 }
 
 /*
@@ -2407,28 +2451,6 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
 	return page;
 }
 
-static void reset_alloc_batches(struct zonelist *zonelist,
-				enum zone_type high_zoneidx,
-				struct zone *preferred_zone)
-{
-	struct zoneref *z;
-	struct zone *zone;
-
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
-		/*
-		 * Only reset the batches of zones that were actually
-		 * considered in the fairness pass, we don't want to
-		 * trash fairness information for zones that are not
-		 * actually part of this zonelist's round-robin cycle.
-		 */
-		if (!zone_local(preferred_zone, zone))
-			continue;
-		mod_zone_page_state(zone, NR_ALLOC_BATCH,
-			high_wmark_pages(zone) - low_wmark_pages(zone) -
-			atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
-	}
-}
-
 static void wake_all_kswapds(unsigned int order,
 			     struct zonelist *zonelist,
 			     enum zone_type high_zoneidx,
@@ -2759,29 +2781,12 @@ retry_cpuset:
 	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 #endif
-retry:
 	/* First allocation attempt */
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
 			zonelist, high_zoneidx, alloc_flags,
 			preferred_zone, classzone_idx, migratetype);
 	if (unlikely(!page)) {
 		/*
-		 * The first pass makes sure allocations are spread
-		 * fairly within the local node.  However, the local
-		 * node might have free pages left after the fairness
-		 * batches are exhausted, and remote zones haven't
-		 * even been considered yet.  Try once more without
-		 * fairness, and include remote zones now, before
-		 * entering the slowpath and waking kswapd: prefer
-		 * spilling to a remote zone over swapping locally.
-		 */
-		if (alloc_flags & ALLOC_FAIR) {
-			reset_alloc_batches(zonelist, high_zoneidx,
-					    preferred_zone);
-			alloc_flags &= ~ALLOC_FAIR;
-			goto retry;
-		}
-		/*
 		 * Runtime PM, block IO and its error handling path
 		 * can deadlock because I/O on the device might not
 		 * complete.
-- 
1.8.4.5

Re: [PATCH 08/97] mm, thp: do not allow thp faults to avoid cpuset restrictions

[Jiri Slaby]

On 08/28/2014, 08:34 PM, Mel Gorman wrote:
> From: David Rientjes <rientjes@google.com>
> 
> commit b104a35d32025ca740539db2808aa3385d0f30eb upstream.
> 
> The page allocator relies on __GFP_WAIT to determine if ALLOC_CPUSET
> should be set in allocflags.  ALLOC_CPUSET controls if a page allocation
> should be restricted only to the set of allowed cpuset mems.
> 
> Transparent hugepages clears __GFP_WAIT when defrag is disabled to prevent
> the fault path from using memory compaction or direct reclaim.  Thus, it
> is unfairly able to allocate outside of its cpuset mems restriction as a
> side-effect.
> 
> This patch ensures that ALLOC_CPUSET is only cleared when the gfp mask is
> truly GFP_ATOMIC by verifying it is also not a thp allocation.

Hi, the time has come to apply this series. Thanks a lot for doing that.

It all applies cleanly except this one, as it is already in 2.6.27. So
skipping makes it work nicely.

-- 
js
suse labs

Re: [PATCH 08/97] mm, thp: do not allow thp faults to avoid cpuset restrictions

[Mel Gorman]

On Fri, Sep 26, 2014 at 11:53:14AM +0200, Jiri Slaby wrote:
> On 08/28/2014, 08:34 PM, Mel Gorman wrote:
> > From: David Rientjes <rientjes@google.com>
> > 
> > commit b104a35d32025ca740539db2808aa3385d0f30eb upstream.
> > 
> > The page allocator relies on __GFP_WAIT to determine if ALLOC_CPUSET
> > should be set in allocflags.  ALLOC_CPUSET controls if a page allocation
> > should be restricted only to the set of allowed cpuset mems.
> > 
> > Transparent hugepages clears __GFP_WAIT when defrag is disabled to prevent
> > the fault path from using memory compaction or direct reclaim.  Thus, it
> > is unfairly able to allocate outside of its cpuset mems restriction as a
> > side-effect.
> > 
> > This patch ensures that ALLOC_CPUSET is only cleared when the gfp mask is
> > truly GFP_ATOMIC by verifying it is also not a thp allocation.
> 
> Hi, the time has come to apply this series. Thanks a lot for doing that.
> 

Thanks for picking them up!

-- 
Mel Gorman
SUSE Labs

Re: [PATCH 00/97] Misc series of functional/performance fixes for 3.12-stable

[Greg KH]

On Thu, Aug 28, 2014 at 07:34:08PM +0100, Mel Gorman wrote:
> Kernel Summit 2014 had a topic on performance regressions and catching
> them.  The situation relatively recently has been good but I believe this
> is partially due to major distributions stabilising recently and hardware
> vendors working on performance for their latest platforms. On thing I fear is
> that we miss performance regressions because releases contains performance
> gains and losses, some of which balance out. After a number of mainline
> releases, the performance may look ok but in comparison to a distribution
> kernel cherry-picking the picture is not as rosy.  The 3.0-longterm
> included a number of performance-related patches so it could be used as
> a good performance baseline for later releases. It is no longer maintained.
> 
> This series contains a large number of patches against 3.12-longterm that
> never made it to stable as the bugs were not serious enough or they were
> performance patches. 3.10-longterm may need other pre-requisites I did
> not research and 3.14-longterm should be able to apply a subset although
> I have not tested the result.
> 

I've finally applied the rest of these to the 3.14-stable queue, thanks
again for providing them.

greg k-h