Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc bits

 - ocfs2

 - most(?) of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (125 commits)
  thp: fix comments of __pmd_trans_huge_lock()
  cgroup: remove unnecessary 0 check from css_from_id()
  cgroup: fix idr leak for the first cgroup root
  mm: memcontrol: fix documentation for compound parameter
  mm: memcontrol: remove BUG_ON in uncharge_list
  mm: fix build warnings in <linux/compaction.h>
  mm, thp: convert from optimistic swapin collapsing to conservative
  mm, thp: fix comment inconsistency for swapin readahead functions
  thp: update Documentation/{vm/transhuge,filesystems/proc}.txt
  shmem: split huge pages beyond i_size under memory pressure
  thp: introduce CONFIG_TRANSPARENT_HUGE_PAGECACHE
  khugepaged: add support of collapse for tmpfs/shmem pages
  shmem: make shmem_inode_info::lock irq-safe
  khugepaged: move up_read(mmap_sem) out of khugepaged_alloc_page()
  thp: extract khugepaged from mm/huge_memory.c
  shmem, thp: respect MADV_{NO,}HUGEPAGE for file mappings
  shmem: add huge pages support
  shmem: get_unmapped_area align huge page
  shmem: prepare huge= mount option and sysfs knob
  mm, rmap: account shmem thp pages
  ...

Documentation/blockdev/zram.txt

@@ -59,23 +59,23 @@ num_devices parameter is optional and tells zram how many devices should be
 pre-created. Default: 1.
 
 2) Set max number of compression streams
-	Regardless the value passed to this attribute, ZRAM will always
-	allocate multiple compression streams - one per online CPUs - thus
-	allowing several concurrent compression operations. The number of
-	allocated compression streams goes down when some of the CPUs
-	become offline. There is no single-compression-stream mode anymore,
-	unless you are running a UP system or has only 1 CPU online.
+Regardless the value passed to this attribute, ZRAM will always
+allocate multiple compression streams - one per online CPUs - thus
+allowing several concurrent compression operations. The number of
+allocated compression streams goes down when some of the CPUs
+become offline. There is no single-compression-stream mode anymore,
+unless you are running a UP system or has only 1 CPU online.
 
-	To find out how many streams are currently available:
+To find out how many streams are currently available:
 	cat /sys/block/zram0/max_comp_streams
 
 3) Select compression algorithm
-	Using comp_algorithm device attribute one can see available and
-	currently selected (shown in square brackets) compression algorithms,
-	change selected compression algorithm (once the device is initialised
-	there is no way to change compression algorithm).
+Using comp_algorithm device attribute one can see available and
+currently selected (shown in square brackets) compression algorithms,
+change selected compression algorithm (once the device is initialised
+there is no way to change compression algorithm).
 
-	Examples:
+Examples:
 	#show supported compression algorithms
 	cat /sys/block/zram0/comp_algorithm
 	lzo [lz4]
@@ -83,17 +83,27 @@ pre-created. Default: 1.
 	#select lzo compression algorithm
 	echo lzo > /sys/block/zram0/comp_algorithm
 
-4) Set Disksize
-        Set disk size by writing the value to sysfs node 'disksize'.
-        The value can be either in bytes or you can use mem suffixes.
-        Examples:
-            # Initialize /dev/zram0 with 50MB disksize
-            echo $((50*1024*1024)) > /sys/block/zram0/disksize
+For the time being, the `comp_algorithm' content does not necessarily
+show every compression algorithm supported by the kernel. We keep this
+list primarily to simplify device configuration and one can configure
+a new device with a compression algorithm that is not listed in
+`comp_algorithm'. The thing is that, internally, ZRAM uses Crypto API
+and, if some of the algorithms were built as modules, it's impossible
+to list all of them using, for instance, /proc/crypto or any other
+method. This, however, has an advantage of permitting the usage of
+custom crypto compression modules (implementing S/W or H/W compression).
 
-            # Using mem suffixes
-            echo 256K > /sys/block/zram0/disksize
-            echo 512M > /sys/block/zram0/disksize
-            echo 1G > /sys/block/zram0/disksize
+4) Set Disksize
+Set disk size by writing the value to sysfs node 'disksize'.
+The value can be either in bytes or you can use mem suffixes.
+Examples:
+	# Initialize /dev/zram0 with 50MB disksize
+	echo $((50*1024*1024)) > /sys/block/zram0/disksize
+
+	# Using mem suffixes
+	echo 256K > /sys/block/zram0/disksize
+	echo 512M > /sys/block/zram0/disksize
+	echo 1G > /sys/block/zram0/disksize
 
 Note:
 There is little point creating a zram of greater than twice the size of memory
@@ -101,20 +111,20 @@ since we expect a 2:1 compression ratio. Note that zram uses about 0.1% of the
 size of the disk when not in use so a huge zram is wasteful.
 
 5) Set memory limit: Optional
-	Set memory limit by writing the value to sysfs node 'mem_limit'.
-	The value can be either in bytes or you can use mem suffixes.
-	In addition, you could change the value in runtime.
-	Examples:
-	    # limit /dev/zram0 with 50MB memory
-	    echo $((50*1024*1024)) > /sys/block/zram0/mem_limit
+Set memory limit by writing the value to sysfs node 'mem_limit'.
+The value can be either in bytes or you can use mem suffixes.
+In addition, you could change the value in runtime.
+Examples:
+	# limit /dev/zram0 with 50MB memory
+	echo $((50*1024*1024)) > /sys/block/zram0/mem_limit
 
-	    # Using mem suffixes
-	    echo 256K > /sys/block/zram0/mem_limit
-	    echo 512M > /sys/block/zram0/mem_limit
-	    echo 1G > /sys/block/zram0/mem_limit
+	# Using mem suffixes
+	echo 256K > /sys/block/zram0/mem_limit
+	echo 512M > /sys/block/zram0/mem_limit
+	echo 1G > /sys/block/zram0/mem_limit
 
-	    # To disable memory limit
-	    echo 0 > /sys/block/zram0/mem_limit
+	# To disable memory limit
+	echo 0 > /sys/block/zram0/mem_limit
 
 6) Activate:
 	mkswap /dev/zram0

Documentation/filesystems/Locking

@@ -195,7 +195,9 @@ prototypes:
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
 	int (*direct_IO)(struct kiocb *, struct iov_iter *iter);
+	bool (*isolate_page) (struct page *, isolate_mode_t);
 	int (*migratepage)(struct address_space *, struct page *, struct page *);
+	void (*putback_page) (struct page *);
 	int (*launder_page)(struct page *);
 	int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long);
 	int (*error_remove_page)(struct address_space *, struct page *);
@@ -219,7 +221,9 @@ invalidatepage:		yes
 releasepage:		yes
 freepage:		yes
 direct_IO:
+isolate_page:		yes
 migratepage:		yes (both)
+putback_page:		yes
 launder_page:		yes
 is_partially_uptodate:	yes
 error_remove_page:	yes
@@ -544,13 +548,13 @@ subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
 locked. The VM will unlock the page.
 
 	->map_pages() is called when VM asks to map easy accessible pages.
-Filesystem should find and map pages associated with offsets from "pgoff"
-till "max_pgoff". ->map_pages() is called with page table locked and must
+Filesystem should find and map pages associated with offsets from "start_pgoff"
+till "end_pgoff". ->map_pages() is called with page table locked and must
 not block.  If it's not possible to reach a page without blocking,
 filesystem should skip it. Filesystem should use do_set_pte() to setup
-page table entry. Pointer to entry associated with offset "pgoff" is
-passed in "pte" field in vm_fault structure. Pointers to entries for other
-offsets should be calculated relative to "pte".
+page table entry. Pointer to entry associated with the page is passed in
+"pte" field in fault_env structure. Pointers to entries for other offsets
+should be calculated relative to "pte".
 
 	->page_mkwrite() is called when a previously read-only pte is
 about to become writeable. The filesystem again must ensure that there are

Documentation/filesystems/dax.txt

@@ -49,6 +49,7 @@ These block devices may be used for inspiration:
 - axonram: Axon DDR2 device driver
 - brd: RAM backed block device driver
 - dcssblk: s390 dcss block device driver
+- pmem: NVDIMM persistent memory driver
 
 
 Implementation Tips for Filesystem Writers
@@ -75,8 +76,9 @@ calls to get_block() (for example by a page-fault racing with a read()
 or a write()) work correctly.
 
 These filesystems may be used for inspiration:
-- ext2: the second extended filesystem, see Documentation/filesystems/ext2.txt
-- ext4: the fourth extended filesystem, see Documentation/filesystems/ext4.txt
+- ext2: see Documentation/filesystems/ext2.txt
+- ext4: see Documentation/filesystems/ext4.txt
+- xfs:  see Documentation/filesystems/xfs.txt
 
 
 Handling Media Errors

Documentation/filesystems/proc.txt

@@ -436,6 +436,7 @@ Private_Dirty:         0 kB
 Referenced:          892 kB
 Anonymous:             0 kB
 AnonHugePages:         0 kB
+ShmemPmdMapped:        0 kB
 Shared_Hugetlb:        0 kB
 Private_Hugetlb:       0 kB
 Swap:                  0 kB
@@ -464,6 +465,8 @@ accessed.
 a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
 and a page is modified, the file page is replaced by a private anonymous copy.
 "AnonHugePages" shows the ammount of memory backed by transparent hugepage.
+"ShmemPmdMapped" shows the ammount of shared (shmem/tmpfs) memory backed by
+huge pages.
 "Shared_Hugetlb" and "Private_Hugetlb" show the ammounts of memory backed by
 hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical
 reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field.
@@ -868,6 +871,9 @@ VmallocTotal:   112216 kB
 VmallocUsed:       428 kB
 VmallocChunk:   111088 kB
 AnonHugePages:   49152 kB
+ShmemHugePages:      0 kB
+ShmemPmdMapped:      0 kB
+
 
     MemTotal: Total usable ram (i.e. physical ram minus a few reserved
               bits and the kernel binary code)
@@ -912,6 +918,9 @@ MemAvailable: An estimate of how much memory is available for starting new
 AnonHugePages: Non-file backed huge pages mapped into userspace page tables
       Mapped: files which have been mmaped, such as libraries
        Shmem: Total memory used by shared memory (shmem) and tmpfs
+ShmemHugePages: Memory used by shared memory (shmem) and tmpfs allocated
+              with huge pages
+ShmemPmdMapped: Shared memory mapped into userspace with huge pages
         Slab: in-kernel data structures cache
 SReclaimable: Part of Slab, that might be reclaimed, such as caches
   SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure

Documentation/filesystems/vfs.txt

@@ -592,9 +592,14 @@ struct address_space_operations {
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
 	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
+	/* isolate a page for migration */
+	bool (*isolate_page) (struct page *, isolate_mode_t);
 	/* migrate the contents of a page to the specified target */
 	int (*migratepage) (struct page *, struct page *);
+	/* put migration-failed page back to right list */
+	void (*putback_page) (struct page *);
 	int (*launder_page) (struct page *);
+
 	int (*is_partially_uptodate) (struct page *, unsigned long,
 					unsigned long);
 	void (*is_dirty_writeback) (struct page *, bool *, bool *);
@@ -747,6 +752,10 @@ struct address_space_operations {
         and transfer data directly between the storage and the
         application's address space.
 
+  isolate_page: Called by the VM when isolating a movable non-lru page.
+	If page is successfully isolated, VM marks the page as PG_isolated
+	via __SetPageIsolated.
+
   migrate_page:  This is used to compact the physical memory usage.
         If the VM wants to relocate a page (maybe off a memory card
         that is signalling imminent failure) it will pass a new page
@@ -754,6 +763,8 @@ struct address_space_operations {
 	transfer any private data across and update any references
         that it has to the page.
 
+  putback_page: Called by the VM when isolated page's migration fails.
+
   launder_page: Called before freeing a page - it writes back the dirty page. To
   	prevent redirtying the page, it is kept locked during the whole
 	operation.

Documentation/vm/page_migration

@@ -142,5 +142,111 @@ Steps:
 20. The new page is moved to the LRU and can be scanned by the swapper
     etc again.
 
-Christoph Lameter, May 8, 2006.
+C. Non-LRU page migration
+-------------------------
 
+Although original migration aimed for reducing the latency of memory access
+for NUMA, compaction who want to create high-order page is also main customer.
+
+Current problem of the implementation is that it is designed to migrate only
+*LRU* pages. However, there are potential non-lru pages which can be migrated
+in drivers, for example, zsmalloc, virtio-balloon pages.
+
+For virtio-balloon pages, some parts of migration code path have been hooked
+up and added virtio-balloon specific functions to intercept migration logics.
+It's too specific to a driver so other drivers who want to make their pages
+movable would have to add own specific hooks in migration path.
+
+To overclome the problem, VM supports non-LRU page migration which provides
+generic functions for non-LRU movable pages without driver specific hooks
+migration path.
+
+If a driver want to make own pages movable, it should define three functions
+which are function pointers of struct address_space_operations.
+
+1. bool (*isolate_page) (struct page *page, isolate_mode_t mode);
+
+What VM expects on isolate_page function of driver is to return *true*
+if driver isolates page successfully. On returing true, VM marks the page
+as PG_isolated so concurrent isolation in several CPUs skip the page
+for isolation. If a driver cannot isolate the page, it should return *false*.
+
+Once page is successfully isolated, VM uses page.lru fields so driver
+shouldn't expect to preserve values in that fields.
+
+2. int (*migratepage) (struct address_space *mapping,
+		struct page *newpage, struct page *oldpage, enum migrate_mode);
+
+After isolation, VM calls migratepage of driver with isolated page.
+The function of migratepage is to move content of the old page to new page
+and set up fields of struct page newpage. Keep in mind that you should
+indicate to the VM the oldpage is no longer movable via __ClearPageMovable()
+under page_lock if you migrated the oldpage successfully and returns
+MIGRATEPAGE_SUCCESS. If driver cannot migrate the page at the moment, driver
+can return -EAGAIN. On -EAGAIN, VM will retry page migration in a short time
+because VM interprets -EAGAIN as "temporal migration failure". On returning
+any error except -EAGAIN, VM will give up the page migration without retrying
+in this time.
+
+Driver shouldn't touch page.lru field VM using in the functions.
+
+3. void (*putback_page)(struct page *);
+
+If migration fails on isolated page, VM should return the isolated page
+to the driver so VM calls driver's putback_page with migration failed page.
+In this function, driver should put the isolated page back to the own data
+structure.
+
+4. non-lru movable page flags
+
+There are two page flags for supporting non-lru movable page.
+
+* PG_movable
+
+Driver should use the below function to make page movable under page_lock.
+
+	void __SetPageMovable(struct page *page, struct address_space *mapping)
+
+It needs argument of address_space for registering migration family functions
+which will be called by VM. Exactly speaking, PG_movable is not a real flag of
+struct page. Rather than, VM reuses page->mapping's lower bits to represent it.
+
+	#define PAGE_MAPPING_MOVABLE 0x2
+	page->mapping = page->mapping | PAGE_MAPPING_MOVABLE;
+
+so driver shouldn't access page->mapping directly. Instead, driver should
+use page_mapping which mask off the low two bits of page->mapping under
+page lock so it can get right struct address_space.
+
+For testing of non-lru movable page, VM supports __PageMovable function.
+However, it doesn't guarantee to identify non-lru movable page because
+page->mapping field is unified with other variables in struct page.
+As well, if driver releases the page after isolation by VM, page->mapping
+doesn't have stable value although it has PAGE_MAPPING_MOVABLE
+(Look at __ClearPageMovable). But __PageMovable is cheap to catch whether
+page is LRU or non-lru movable once the page has been isolated. Because
+LRU pages never can have PAGE_MAPPING_MOVABLE in page->mapping. It is also
+good for just peeking to test non-lru movable pages before more expensive
+checking with lock_page in pfn scanning to select victim.
+
+For guaranteeing non-lru movable page, VM provides PageMovable function.
+Unlike __PageMovable, PageMovable functions validates page->mapping and
+mapping->a_ops->isolate_page under lock_page. The lock_page prevents sudden
+destroying of page->mapping.
+
+Driver using __SetPageMovable should clear the flag via __ClearMovablePage
+under page_lock before the releasing the page.
+
+* PG_isolated
+
+To prevent concurrent isolation among several CPUs, VM marks isolated page
+as PG_isolated under lock_page. So if a CPU encounters PG_isolated non-lru
+movable page, it can skip it. Driver doesn't need to manipulate the flag
+because VM will set/clear it automatically. Keep in mind that if driver
+sees PG_isolated page, it means the page have been isolated by VM so it
+shouldn't touch page.lru field.
+PG_isolated is alias with PG_reclaim flag so driver shouldn't use the flag
+for own purpose.
+
+Christoph Lameter, May 8, 2006.
+Minchan Kim, Mar 28, 2016.

Documentation/vm/transhuge.txt

@@ -9,8 +9,8 @@ using huge pages for the backing of virtual memory with huge pages
 that supports the automatic promotion and demotion of page sizes and
 without the shortcomings of hugetlbfs.
 
-Currently it only works for anonymous memory mappings but in the
-future it can expand over the pagecache layer starting with tmpfs.
+Currently it only works for anonymous memory mappings and tmpfs/shmem.
+But in the future it can expand to other filesystems.
 
 The reason applications are running faster is because of two
 factors. The first factor is almost completely irrelevant and it's not
@@ -57,10 +57,6 @@ miss is going to run faster.
   feature that applies to all dynamic high order allocations in the
   kernel)
 
-- this initial support only offers the feature in the anonymous memory
-  regions but it'd be ideal to move it to tmpfs and the pagecache
-  later
-
 Transparent Hugepage Support maximizes the usefulness of free memory
 if compared to the reservation approach of hugetlbfs by allowing all
 unused memory to be used as cache or other movable (or even unmovable
@@ -94,21 +90,21 @@ madvise(MADV_HUGEPAGE) on their critical mmapped regions.
 
 == sysfs ==
 
-Transparent Hugepage Support can be entirely disabled (mostly for
-debugging purposes) or only enabled inside MADV_HUGEPAGE regions (to
-avoid the risk of consuming more memory resources) or enabled system
-wide. This can be achieved with one of:
+Transparent Hugepage Support for anonymous memory can be entirely disabled
+(mostly for debugging purposes) or only enabled inside MADV_HUGEPAGE
+regions (to avoid the risk of consuming more memory resources) or enabled
+system wide. This can be achieved with one of:
 
 echo always >/sys/kernel/mm/transparent_hugepage/enabled
 echo madvise >/sys/kernel/mm/transparent_hugepage/enabled
 echo never >/sys/kernel/mm/transparent_hugepage/enabled
 
 It's also possible to limit defrag efforts in the VM to generate
-hugepages in case they're not immediately free to madvise regions or
-to never try to defrag memory and simply fallback to regular pages
-unless hugepages are immediately available. Clearly if we spend CPU
-time to defrag memory, we would expect to gain even more by the fact
-we use hugepages later instead of regular pages. This isn't always
+anonymous hugepages in case they're not immediately free to madvise
+regions or to never try to defrag memory and simply fallback to regular
+pages unless hugepages are immediately available. Clearly if we spend CPU
+time to defrag memory, we would expect to gain even more by the fact we
+use hugepages later instead of regular pages. This isn't always
 guaranteed, but it may be more likely in case the allocation is for a
 MADV_HUGEPAGE region.
 
@@ -133,9 +129,9 @@ that are have used madvise(MADV_HUGEPAGE). This is the default behaviour.
 
 "never" should be self-explanatory.
 
-By default kernel tries to use huge zero page on read page fault.
-It's possible to disable huge zero page by writing 0 or enable it
-back by writing 1:
+By default kernel tries to use huge zero page on read page fault to
+anonymous mapping. It's possible to disable huge zero page by writing 0
+or enable it back by writing 1:
 
 echo 0 >/sys/kernel/mm/transparent_hugepage/use_zero_page
 echo 1 >/sys/kernel/mm/transparent_hugepage/use_zero_page
@@ -204,21 +200,67 @@ Support by passing the parameter "transparent_hugepage=always" or
 "transparent_hugepage=madvise" or "transparent_hugepage=never"
 (without "") to the kernel command line.
 
+== Hugepages in tmpfs/shmem ==
+
+You can control hugepage allocation policy in tmpfs with mount option
+"huge=". It can have following values:
+
+  - "always":
+    Attempt to allocate huge pages every time we need a new page;
+
+  - "never":
+    Do not allocate huge pages;
+
+  - "within_size":
+    Only allocate huge page if it will be fully within i_size.
+    Also respect fadvise()/madvise() hints;
+
+  - "advise:
+    Only allocate huge pages if requested with fadvise()/madvise();
+
+The default policy is "never".
+
+"mount -o remount,huge= /mountpoint" works fine after mount: remounting
+huge=never will not attempt to break up huge pages at all, just stop more
+from being allocated.
+
+There's also sysfs knob to control hugepage allocation policy for internal
+shmem mount: /sys/kernel/mm/transparent_hugepage/shmem_enabled. The mount
+is used for SysV SHM, memfds, shared anonymous mmaps (of /dev/zero or
+MAP_ANONYMOUS), GPU drivers' DRM objects, Ashmem.
+
+In addition to policies listed above, shmem_enabled allows two further
+values:
+
+  - "deny":
+    For use in emergencies, to force the huge option off from
+    all mounts;
+  - "force":
+    Force the huge option on for all - very useful for testing;
+
 == Need of application restart ==
 
-The transparent_hugepage/enabled values only affect future
-behavior. So to make them effective you need to restart any
-application that could have been using hugepages. This also applies to
-the regions registered in khugepaged.
+The transparent_hugepage/enabled values and tmpfs mount option only affect
+future behavior. So to make them effective you need to restart any
+application that could have been using hugepages. This also applies to the
+regions registered in khugepaged.
 
 == Monitoring usage ==
 
-The number of transparent huge pages currently used by the system is
-available by reading the AnonHugePages field in /proc/meminfo. To
-identify what applications are using transparent huge pages, it is
-necessary to read /proc/PID/smaps and count the AnonHugePages fields
-for each mapping. Note that reading the smaps file is expensive and
-reading it frequently will incur overhead.
+The number of anonymous transparent huge pages currently used by the
+system is available by reading the AnonHugePages field in /proc/meminfo.
+To identify what applications are using anonymous transparent huge pages,
+it is necessary to read /proc/PID/smaps and count the AnonHugePages fields
+for each mapping.
+
+The number of file transparent huge pages mapped to userspace is available
+by reading ShmemPmdMapped and ShmemHugePages fields in /proc/meminfo.
+To identify what applications are mapping file  transparent huge pages, it
+is necessary to read /proc/PID/smaps and count the FileHugeMapped fields
+for each mapping.
+
+Note that reading the smaps file is expensive and reading it
+frequently will incur overhead.
 
 There are a number of counters in /proc/vmstat that may be used to
 monitor how successfully the system is providing huge pages for use.
@@ -238,6 +280,12 @@ thp_collapse_alloc_failed is incremented if khugepaged found a range
 	of pages that should be collapsed into one huge page but failed
 	the allocation.
 
+thp_file_alloc is incremented every time a file huge page is successfully
+i	allocated.
+
+thp_file_mapped is incremented every time a file huge page is mapped into
+	user address space.
+
 thp_split_page is incremented every time a huge page is split into base
 	pages. This can happen for a variety of reasons but a common
 	reason is that a huge page is old and is being reclaimed.
@@ -403,19 +451,27 @@ pages:
     on relevant sub-page of the compound page.
 
   - map/unmap of the whole compound page accounted in compound_mapcount
-    (stored in first tail page).
+    (stored in first tail page). For file huge pages, we also increment
+    ->_mapcount of all sub-pages in order to have race-free detection of
+    last unmap of subpages.
 
-PageDoubleMap() indicates that ->_mapcount in all subpages is offset up by one.
-This additional reference is required to get race-free detection of unmap of
-subpages when we have them mapped with both PMDs and PTEs.
+PageDoubleMap() indicates that the page is *possibly* mapped with PTEs.
+
+For anonymous pages PageDoubleMap() also indicates ->_mapcount in all
+subpages is offset up by one. This additional reference is required to
+get race-free detection of unmap of subpages when we have them mapped with
+both PMDs and PTEs.
 
 This is optimization required to lower overhead of per-subpage mapcount
 tracking. The alternative is alter ->_mapcount in all subpages on each
 map/unmap of the whole compound page.
 
-We set PG_double_map when a PMD of the page got split for the first time,
-but still have PMD mapping. The additional references go away with last
-compound_mapcount.
+For anonymous pages, we set PG_double_map when a PMD of the page got split
+for the first time, but still have PMD mapping. The additional references
+go away with last compound_mapcount.
+
+File pages get PG_double_map set on first map of the page with PTE and
+goes away when the page gets evicted from page cache.
 
 split_huge_page internally has to distribute the refcounts in the head
 page to the tail pages before clearing all PG_head/tail bits from the page
@@ -427,7 +483,7 @@ sum of mapcount of all sub-pages plus one (split_huge_page caller must
 have reference for head page).
 
 split_huge_page uses migration entries to stabilize page->_refcount and
-page->_mapcount.
+page->_mapcount of anonymous pages. File pages just got unmapped.
 
 We safe against physical memory scanners too: the only legitimate way
 scanner can get reference to a page is get_page_unless_zero().

Documentation/vm/unevictable-lru.txt

@@ -461,6 +461,27 @@ unevictable LRU is enabled, the work of compaction is mostly handled by
 the page migration code and the same work flow as described in MIGRATING
 MLOCKED PAGES will apply.
 
+MLOCKING TRANSPARENT HUGE PAGES
+-------------------------------
+
+A transparent huge page is represented by a single entry on an LRU list.
+Therefore, we can only make unevictable an entire compound page, not
+individual subpages.
+
+If a user tries to mlock() part of a huge page, we want the rest of the
+page to be reclaimable.
+
+We cannot just split the page on partial mlock() as split_huge_page() can
+fail and new intermittent failure mode for the syscall is undesirable.
+
+We handle this by keeping PTE-mapped huge pages on normal LRU lists: the
+PMD on border of VM_LOCKED VMA will be split into PTE table.
+
+This way the huge page is accessible for vmscan. Under memory pressure the
+page will be split, subpages which belong to VM_LOCKED VMAs will be moved
+to unevictable LRU and the rest can be reclaimed.
+
+See also comment in follow_trans_huge_pmd().
 
 mmap(MAP_LOCKED) SYSTEM CALL HANDLING
 -------------------------------------

Makefile

@@ -647,41 +647,28 @@ ifneq ($(CONFIG_FRAME_WARN),0)
 KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN})
 endif
 
-# Handle stack protector mode.
-#
-# Since kbuild can potentially perform two passes (first with the old
-# .config values and then with updated .config values), we cannot error out
-# if a desired compiler option is unsupported. If we were to error, kbuild
-# could never get to the second pass and actually notice that we changed
-# the option to something that was supported.
-#
-# Additionally, we don't want to fallback and/or silently change which compiler
-# flags will be used, since that leads to producing kernels with different
-# security feature characteristics depending on the compiler used. ("But I
-# selected CC_STACKPROTECTOR_STRONG! Why did it build with _REGULAR?!")
-#
-# The middle ground is to warn here so that the failed option is obvious, but
-# to let the build fail with bad compiler flags so that we can't produce a
-# kernel when there is a CONFIG and compiler mismatch.
-#
+# This selects the stack protector compiler flag. Testing it is delayed
+# until after .config has been reprocessed, in the prepare-compiler-check
+# target.
 ifdef CONFIG_CC_STACKPROTECTOR_REGULAR
   stackp-flag := -fstack-protector
-  ifeq ($(call cc-option, $(stackp-flag)),)
-    $(warning Cannot use CONFIG_CC_STACKPROTECTOR_REGULAR: \
-             -fstack-protector not supported by compiler)
-  endif
+  stackp-name := REGULAR
 else
 ifdef CONFIG_CC_STACKPROTECTOR_STRONG
   stackp-flag := -fstack-protector-strong
-  ifeq ($(call cc-option, $(stackp-flag)),)
-    $(warning Cannot use CONFIG_CC_STACKPROTECTOR_STRONG: \
-	      -fstack-protector-strong not supported by compiler)
-  endif
+  stackp-name := STRONG
 else
   # Force off for distro compilers that enable stack protector by default.
   stackp-flag := $(call cc-option, -fno-stack-protector)
 endif
 endif
+# Find arch-specific stack protector compiler sanity-checking script.
+ifdef CONFIG_CC_STACKPROTECTOR
+  stackp-path := $(srctree)/scripts/gcc-$(ARCH)_$(BITS)-has-stack-protector.sh
+  ifneq ($(wildcard $(stackp-path)),)
+    stackp-check := $(stackp-path)
+  endif
+endif
 KBUILD_CFLAGS += $(stackp-flag)
 
 ifdef CONFIG_KCOV
@@ -1017,8 +1004,10 @@ ifneq ($(KBUILD_SRC),)
 	fi;
 endif
 
-# prepare2 creates a makefile if using a separate output directory
-prepare2: prepare3 outputmakefile asm-generic
+# prepare2 creates a makefile if using a separate output directory.
+# From this point forward, .config has been reprocessed, so any rules
+# that need to depend on updated CONFIG_* values can be checked here.
+prepare2: prepare3 prepare-compiler-check outputmakefile asm-generic
 
 prepare1: prepare2 $(version_h) include/generated/utsrelease.h \
                    include/config/auto.conf
@@ -1049,6 +1038,32 @@ endif
 PHONY += prepare-objtool
 prepare-objtool: $(objtool_target)
 
+# Check for CONFIG flags that require compiler support. Abort the build
+# after .config has been processed, but before the kernel build starts.
+#
+# For security-sensitive CONFIG options, we don't want to fallback and/or
+# silently change which compiler flags will be used, since that leads to
+# producing kernels with different security feature characteristics
+# depending on the compiler used. (For example, "But I selected
+# CC_STACKPROTECTOR_STRONG! Why did it build with _REGULAR?!")
+PHONY += prepare-compiler-check
+prepare-compiler-check: FORCE
+# Make sure compiler supports requested stack protector flag.
+ifdef stackp-name
+  ifeq ($(call cc-option, $(stackp-flag)),)
+	@echo Cannot use CONFIG_CC_STACKPROTECTOR_$(stackp-name): \
+		  $(stackp-flag) not supported by compiler >&2 && exit 1
+  endif
+endif
+# Make sure compiler does not have buggy stack-protector support.
+ifdef stackp-check
+  ifneq ($(shell $(CONFIG_SHELL) $(stackp-check) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y)
+	@echo Cannot use CONFIG_CC_STACKPROTECTOR_$(stackp-name): \
+                  $(stackp-flag) available but compiler is broken >&2 && exit 1
+  endif
+endif
+	@:
+
 # Generate some files
 # ---------------------------------------------------------------------------
 

arch/alpha/mm/fault.c

@@ -147,7 +147,7 @@ retry:
 	/* If for any reason at all we couldn't handle the fault,
 	   make sure we exit gracefully rather than endlessly redo
 	   the fault.  */
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 		return;

arch/arc/mm/fault.c

@@ -137,7 +137,7 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags);
 
 	/* If Pagefault was interrupted by SIGKILL, exit page fault "early" */
 	if (unlikely(fatal_signal_pending(current))) {

arch/arm/include/asm/pgalloc.h

@@ -57,7 +57,7 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
-#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 
 static inline void clean_pte_table(pte_t *pte)
 {

arch/arm/include/asm/tlb.h

@@ -209,17 +209,38 @@ tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 		tlb_flush(tlb);
 }
 
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
+	if (tlb->nr == tlb->max)
+		return true;
 	tlb->pages[tlb->nr++] = page;
-	VM_BUG_ON(tlb->nr > tlb->max);
-	return tlb->max - tlb->nr;
+	return false;
 }
 
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
-	if (!__tlb_remove_page(tlb, page))
+	if (__tlb_remove_page(tlb, page)) {
 		tlb_flush_mmu(tlb);
+		__tlb_remove_page(tlb, page);
+	}
+}
+
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
+					 struct page *page)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	return tlb_remove_page(tlb, page);
 }
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,

arch/arm/mm/fault.c

@@ -243,7 +243,7 @@ good_area:
 		goto out;
 	}
 
-	return handle_mm_fault(mm, vma, addr & PAGE_MASK, flags);
+	return handle_mm_fault(vma, addr & PAGE_MASK, flags);
 
 check_stack:
 	/* Don't allow expansion below FIRST_USER_ADDRESS */

arch/arm/mm/pgd.c

@@ -23,7 +23,7 @@
 #define __pgd_alloc()	kmalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL)
 #define __pgd_free(pgd)	kfree(pgd)
 #else
-#define __pgd_alloc()	(pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, 2)
+#define __pgd_alloc()	(pgd_t *)__get_free_pages(GFP_KERNEL, 2)
 #define __pgd_free(pgd)	free_pages((unsigned long)pgd, 2)
 #endif
 

arch/arm64/mm/fault.c

@@ -233,7 +233,7 @@ good_area:
 		goto out;
 	}
 
-	return handle_mm_fault(mm, vma, addr & PAGE_MASK, mm_flags);
+	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags);
 
 check_stack:
 	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))

arch/avr32/mm/fault.c

@@ -134,7 +134,7 @@ good_area:
 	 * sure we exit gracefully rather than endlessly redo the
 	 * fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 		return;

arch/cris/mm/fault.c

@@ -168,7 +168,7 @@ retry:
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 		return;

arch/frv/mm/fault.c

@@ -164,7 +164,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, ear0, flags);
+	fault = handle_mm_fault(vma, ear0, flags);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;

arch/hexagon/mm/vm_fault.c

@@ -101,7 +101,7 @@ good_area:
 		break;
 	}
 
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 		return;