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.
-
-	To find out how many streams are currently available:
+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:
 	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
 
+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).
+
 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
+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
+	# 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
-
-	    # 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
+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
+
+	# 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 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	/* 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 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 	 * 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 @@ __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
 		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 @@ static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
 		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 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
 	 * 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 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	 * 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 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
 		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;

arch/ia64/include/asm/tlb.h

@@ -205,17 +205,18 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
  * must be delayed until after the TLB has been flushed (see comments at the beginning of
  * this file).
  */
-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->need_flush = 1;
 
 	if (!tlb->nr && tlb->pages == tlb->local)
 		__tlb_alloc_page(tlb);
 
 	tlb->pages[tlb->nr++] = page;
-	VM_BUG_ON(tlb->nr > tlb->max);
-
-	return tlb->max - tlb->nr;
+	return false;
 }
 
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
@@ -235,8 +236,28 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 
 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);
 }
 
 /*

arch/ia64/mm/fault.c

@@ -159,7 +159,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	 * 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/m32r/kernel/m32r_ksyms.c

@@ -41,6 +41,9 @@ EXPORT_SYMBOL(cpu_data);
 EXPORT_SYMBOL(smp_flush_tlb_page);
 #endif
 
+extern int __ucmpdi2(unsigned long long a, unsigned long long b);
+EXPORT_SYMBOL(__ucmpdi2);
+
 /* compiler generated symbol */
 extern void __ashldi3(void);
 extern void __ashrdi3(void);

arch/m32r/lib/Makefile

@@ -3,5 +3,5 @@
 #
 
 lib-y  := checksum.o ashxdi3.o memset.o memcpy.o \
-	  delay.o strlen.o usercopy.o csum_partial_copy.o
-
+	  delay.o strlen.o usercopy.o csum_partial_copy.o \
+	  ucmpdi2.o

arch/m32r/lib/libgcc.h

+#ifndef __ASM_LIBGCC_H
+#define __ASM_LIBGCC_H
+
+#include <asm/byteorder.h>
+
+#ifdef __BIG_ENDIAN
+struct DWstruct {
+	int high, low;
+};
+#elif defined(__LITTLE_ENDIAN)
+struct DWstruct {
+	int low, high;
+};
+#else
+#error I feel sick.
+#endif
+
+typedef union {
+	struct DWstruct s;
+	long long ll;
+} DWunion;
+
+#endif /* __ASM_LIBGCC_H */

arch/m32r/lib/ucmpdi2.c

+#include "libgcc.h"
+
+int __ucmpdi2(unsigned long long a, unsigned long long b)
+{
+	const DWunion au = {.ll = a};
+	const DWunion bu = {.ll = b};
+
+	if ((unsigned int)au.s.high < (unsigned int)bu.s.high)
+		return 0;
+	else if ((unsigned int)au.s.high > (unsigned int)bu.s.high)
+		return 2;
+	if ((unsigned int)au.s.low < (unsigned int)bu.s.low)
+		return 0;
+	else if ((unsigned int)au.s.low > (unsigned int)bu.s.low)
+		return 2;
+	return 1;
+}

arch/m32r/mm/fault.c

@@ -196,7 +196,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	 */
 	addr = (address & PAGE_MASK);
 	set_thread_fault_code(error_code);
-	fault = handle_mm_fault(mm, vma, addr, flags);
+	fault = handle_mm_fault(vma, addr, flags);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;

arch/m68k/mm/fault.c

@@ -136,7 +136,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * the fault.
 	 */
 
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags);
 	pr_debug("handle_mm_fault returns %d\n", fault);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))

arch/metag/mm/fault.c

@@ -133,7 +133,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * 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 0;

arch/microblaze/mm/fault.c

@@ -216,7 +216,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * 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/mips/mm/fault.c

@@ -153,7 +153,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 	 * 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/mn10300/mm/fault.c

@@ -254,7 +254,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code,
 	 * 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/nios2/mm/fault.c

@@ -131,7 +131,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
 	 * 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/openrisc/mm/fault.c

@@ -163,7 +163,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * 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/parisc/mm/fault.c

@@ -239,7 +239,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 	 * 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/powerpc/include/asm/pgtable.h

@@ -71,10 +71,8 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
 static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
 					       bool *is_thp, unsigned *shift)
 {
-	if (!arch_irqs_disabled()) {
-		pr_info("%s called with irq enabled\n", __func__);
-		dump_stack();
-	}
+	VM_WARN(!arch_irqs_disabled(),
+		"%s called with irq enabled\n", __func__);
 	return __find_linux_pte_or_hugepte(pgdir, ea, is_thp, shift);
 }
 

arch/powerpc/mm/copro_fault.c

@@ -75,7 +75,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 	}
 
 	ret = 0;
-	*flt = handle_mm_fault(mm, vma, ea, is_write ? FAULT_FLAG_WRITE : 0);
+	*flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(*flt & VM_FAULT_ERROR)) {
 		if (*flt & VM_FAULT_OOM) {
 			ret = -ENOMEM;

arch/powerpc/mm/fault.c

@@ -429,7 +429,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * 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 (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
 		if (fault & VM_FAULT_SIGSEGV)
 			goto bad_area;

arch/s390/include/asm/tlb.h

@@ -87,10 +87,10 @@ static inline void tlb_finish_mmu(struct mmu_gather *tlb,
  * tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page
  * has already been freed, so just do free_page_and_swap_cache.
  */
-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)
 {
 	free_page_and_swap_cache(page);
-	return 1; /* avoid calling tlb_flush_mmu */
+	return false; /* avoid calling tlb_flush_mmu */
 }
 
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
@@ -98,6 +98,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	free_page_and_swap_cache(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);
+}
+
 /*
  * pte_free_tlb frees a pte table and clears the CRSTE for the
  * page table from the tlb.

arch/s390/mm/fault.c

@@ -456,7 +456,7 @@ static inline int do_exception(struct pt_regs *regs, int access)
 	 * 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);
 	/* No reason to continue if interrupted by SIGKILL. */
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
 		fault = VM_FAULT_SIGNAL;

arch/score/mm/fault.c

@@ -111,7 +111,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
 	* 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 (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;

arch/sh/include/asm/tlb.h

@@ -101,7 +101,7 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	free_page_and_swap_cache(page);
-	return 1; /* avoid calling tlb_flush_mmu */
+	return false; /* avoid calling tlb_flush_mmu */
 }
 
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
@@ -109,6 +109,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	__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);
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	pte_free((tlb)->mm, ptep)
 #define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
 #define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)

arch/sh/mm/fault.c

@@ -487,7 +487,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 	 * 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 (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR)))
 		if (mm_fault_error(regs, error_code, address, fault))

arch/sparc/mm/fault_32.c

@@ -241,7 +241,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	 * 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;
@@ -411,7 +411,7 @@ static void force_user_fault(unsigned long address, int write)
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto bad_area;
 	}
-	switch (handle_mm_fault(mm, vma, address, flags)) {
+	switch (handle_mm_fault(vma, address, flags)) {
 	case VM_FAULT_SIGBUS:
 	case VM_FAULT_OOM:
 		goto do_sigbus;

arch/sparc/mm/fault_64.c

@@ -436,7 +436,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 			goto bad_area;
 	}
 
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 		goto exit_exception;

arch/tile/mm/fault.c

@@ -434,7 +434,7 @@ static int handle_page_fault(struct pt_regs *regs,
 	 * 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 0;

arch/um/include/asm/tlb.h

@@ -102,7 +102,7 @@ static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
 	tlb->need_flush = 1;
 	free_page_and_swap_cache(page);
-	return 1; /* avoid calling tlb_flush_mmu */
+	return false; /* avoid calling tlb_flush_mmu */
 }
 
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
@@ -110,6 +110,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	__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);
+}
+
 /**
  * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
  *

arch/um/kernel/trap.c

@@ -73,7 +73,7 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	do {
 		int 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))
 			goto out_nosemaphore;

arch/unicore32/mm/fault.c

@@ -194,7 +194,7 @@ static int __do_pf(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
 	 * 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, addr & PAGE_MASK, flags);
+	fault = handle_mm_fault(vma, addr & PAGE_MASK, flags);
 	return fault;
 
 check_stack:

arch/x86/Makefile

@@ -126,14 +126,6 @@ else
         KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args)
 endif
 
-# Make sure compiler does not have buggy stack-protector support.
-ifdef CONFIG_CC_STACKPROTECTOR
-	cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh
-        ifneq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y)
-                $(warning stack-protector enabled but compiler support broken)
-        endif
-endif
-
 ifdef CONFIG_X86_X32
 	x32_ld_ok := $(call try-run,\
 			/bin/echo -e '1: .quad 1b' | \

arch/x86/include/asm/pgalloc.h

@@ -81,7 +81,11 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
 	struct page *page;
-	page = alloc_pages(GFP_KERNEL |  __GFP_ZERO, 0);
+	gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO;
+
+	if (mm == &init_mm)
+		gfp &= ~__GFP_ACCOUNT;
+	page = alloc_pages(gfp, 0);
 	if (!page)
 		return NULL;
 	if (!pgtable_pmd_page_ctor(page)) {
@@ -125,7 +129,11 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pud_t *)get_zeroed_page(GFP_KERNEL);
+	gfp_t gfp = GFP_KERNEL_ACCOUNT;
+
+	if (mm == &init_mm)
+		gfp &= ~__GFP_ACCOUNT;
+	return (pud_t *)get_zeroed_page(gfp);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)

arch/x86/mm/fault.c

@@ -1353,7 +1353,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	 * the fault.  Since we never set FAULT_FLAG_RETRY_NOWAIT, if
 	 * we get VM_FAULT_RETRY back, the mmap_sem has been unlocked.
 	 */
-	fault = handle_mm_fault(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags);
 	major |= fault & VM_FAULT_MAJOR;
 
 	/*

arch/x86/mm/pgtable.c

@@ -6,7 +6,7 @@
 #include <asm/fixmap.h>
 #include <asm/mtrr.h>
 
-#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO
+#define PGALLOC_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | __GFP_ZERO)
 
 #ifdef CONFIG_HIGHPTE
 #define PGALLOC_USER_GFP __GFP_HIGHMEM
@@ -18,7 +18,7 @@ gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP;
 
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
-	return (pte_t *)__get_free_page(PGALLOC_GFP);
+	return (pte_t *)__get_free_page(PGALLOC_GFP & ~__GFP_ACCOUNT);
 }
 
 pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
@@ -207,9 +207,13 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
 {
 	int i;
 	bool failed = false;
+	gfp_t gfp = PGALLOC_GFP;
+
+	if (mm == &init_mm)
+		gfp &= ~__GFP_ACCOUNT;
 
 	for(i = 0; i < PREALLOCATED_PMDS; i++) {
-		pmd_t *pmd = (pmd_t *)__get_free_page(PGALLOC_GFP);
+		pmd_t *pmd = (pmd_t *)__get_free_page(gfp);
 		if (!pmd)
 			failed = true;
 		if (pmd && !pgtable_pmd_page_ctor(virt_to_page(pmd))) {

arch/xtensa/mm/fault.c

@@ -110,7 +110,7 @@ void do_page_fault(struct pt_regs *regs)
 	 * 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;

drivers/base/memory.c

@@ -391,6 +391,7 @@ static ssize_t show_valid_zones(struct device *dev,
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
 	struct page *first_page;
 	struct zone *zone;
+	int zone_shift = 0;
 
 	start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	end_pfn = start_pfn + nr_pages;
@@ -402,21 +403,26 @@ static ssize_t show_valid_zones(struct device *dev,
 
 	zone = page_zone(first_page);
 
-	if (zone_idx(zone) == ZONE_MOVABLE - 1) {
-		/*The mem block is the last memoryblock of this zone.*/
-		if (end_pfn == zone_end_pfn(zone))
-			return sprintf(buf, "%s %s\n",
-					zone->name, (zone + 1)->name);
+	/* MMOP_ONLINE_KEEP */
+	sprintf(buf, "%s", zone->name);
+
+	/* MMOP_ONLINE_KERNEL */
+	zone_shift = zone_can_shift(start_pfn, nr_pages, ZONE_NORMAL);
+	if (zone_shift) {
+		strcat(buf, " ");
+		strcat(buf, (zone + zone_shift)->name);
 	}
 
-	if (zone_idx(zone) == ZONE_MOVABLE) {
-		/*The mem block is the first memoryblock of ZONE_MOVABLE.*/
-		if (start_pfn == zone->zone_start_pfn)
-			return sprintf(buf, "%s %s\n",
-					zone->name, (zone - 1)->name);
+	/* MMOP_ONLINE_MOVABLE */
+	zone_shift = zone_can_shift(start_pfn, nr_pages, ZONE_MOVABLE);
+	if (zone_shift) {
+		strcat(buf, " ");
+		strcat(buf, (zone + zone_shift)->name);
 	}
 
-	return sprintf(buf, "%s\n", zone->name);
+	strcat(buf, "\n");
+
+	return strlen(buf);
 }
 static DEVICE_ATTR(valid_zones, 0444, show_valid_zones, NULL);
 #endif

drivers/base/node.c

@@ -113,6 +113,8 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       "Node %d SUnreclaim:     %8lu kB\n"
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		       "Node %d AnonHugePages:  %8lu kB\n"
+		       "Node %d ShmemHugePages: %8lu kB\n"
+		       "Node %d ShmemPmdMapped: %8lu kB\n"
 #endif
 			,
 		       nid, K(node_page_state(nid, NR_FILE_DIRTY)),
@@ -131,10 +133,13 @@ static ssize_t node_read_meminfo(struct device *dev,
 				node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
 		       nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE)),
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE))
-			, nid,
-			K(node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
-			HPAGE_PMD_NR));
+		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
+		       nid, K(node_page_state(nid, NR_ANON_THPS) *
+				       HPAGE_PMD_NR),
+		       nid, K(node_page_state(nid, NR_SHMEM_THPS) *
+				       HPAGE_PMD_NR),
+		       nid, K(node_page_state(nid, NR_SHMEM_PMDMAPPED) *
+				       HPAGE_PMD_NR));
 #else
 		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
 #endif

drivers/block/zram/Kconfig

 config ZRAM
 	tristate "Compressed RAM block device support"
-	depends on BLOCK && SYSFS && ZSMALLOC
-	select LZO_COMPRESS
-	select LZO_DECOMPRESS
+	depends on BLOCK && SYSFS && ZSMALLOC && CRYPTO
+	select CRYPTO_LZO
 	default n
 	help
 	  Creates virtual block devices called /dev/zramX (X = 0, 1, ...).
@@ -14,13 +13,3 @@ config ZRAM
 	  disks and maybe many more.
 
 	  See zram.txt for more information.
-
-config ZRAM_LZ4_COMPRESS
-	bool "Enable LZ4 algorithm support"
-	depends on ZRAM
-	select LZ4_COMPRESS
-	select LZ4_DECOMPRESS
-	default n
-	help
-	  This option enables LZ4 compression algorithm support. Compression
-	  algorithm can be changed using `comp_algorithm' device attribute.
\ No newline at end of file

drivers/block/zram/Makefile

-zram-y	:=	zcomp_lzo.o zcomp.o zram_drv.o
-
-zram-$(CONFIG_ZRAM_LZ4_COMPRESS) += zcomp_lz4.o
+zram-y	:=	zcomp.o zram_drv.o
 
 obj-$(CONFIG_ZRAM)	+=	zram.o

drivers/block/zram/zcomp.c

@@ -14,108 +14,150 @@
 #include <linux/wait.h>
 #include <linux/sched.h>
 #include <linux/cpu.h>
+#include <linux/crypto.h>
 
 #include "zcomp.h"
-#include "zcomp_lzo.h"
-#ifdef CONFIG_ZRAM_LZ4_COMPRESS
-#include "zcomp_lz4.h"
-#endif
 
-static struct zcomp_backend *backends[] = {
-	&zcomp_lzo,
-#ifdef CONFIG_ZRAM_LZ4_COMPRESS
-	&zcomp_lz4,
+static const char * const backends[] = {
+	"lzo",
+#if IS_ENABLED(CONFIG_CRYPTO_LZ4)
+	"lz4",
+#endif
+#if IS_ENABLED(CONFIG_CRYPTO_DEFLATE)
+	"deflate",
+#endif
+#if IS_ENABLED(CONFIG_CRYPTO_LZ4HC)
+	"lz4hc",
+#endif
+#if IS_ENABLED(CONFIG_CRYPTO_842)
+	"842",
 #endif
 	NULL
 };
 
-static struct zcomp_backend *find_backend(const char *compress)
-{
-	int i = 0;
-	while (backends[i]) {
-		if (sysfs_streq(compress, backends[i]->name))
-			break;
-		i++;
-	}
-	return backends[i];
-}
-
-static void zcomp_strm_free(struct zcomp *comp, struct zcomp_strm *zstrm)
+static void zcomp_strm_free(struct zcomp_strm *zstrm)
 {
-	if (zstrm->private)
-		comp->backend->destroy(zstrm->private);
+	if (!IS_ERR_OR_NULL(zstrm->tfm))
+		crypto_free_comp(zstrm->tfm);
 	free_pages((unsigned long)zstrm->buffer, 1);
 	kfree(zstrm);
 }
 
 /*
- * allocate new zcomp_strm structure with ->private initialized by
+ * allocate new zcomp_strm structure with ->tfm initialized by
  * backend, return NULL on error
  */
-static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp, gfp_t flags)
+static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp)
 {
-	struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), flags);
+	struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL);
 	if (!zstrm)
 		return NULL;
 
-	zstrm->private = comp->backend->create(flags);
+	zstrm->tfm = crypto_alloc_comp(comp->name, 0, 0);
 	/*
 	 * allocate 2 pages. 1 for compressed data, plus 1 extra for the
 	 * case when compressed size is larger than the original one
 	 */
-	zstrm->buffer = (void *)__get_free_pages(flags | __GFP_ZERO, 1);
-	if (!zstrm->private || !zstrm->buffer) {
-		zcomp_strm_free(comp, zstrm);
+	zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
+	if (IS_ERR_OR_NULL(zstrm->tfm) || !zstrm->buffer) {
+		zcomp_strm_free(zstrm);
 		zstrm = NULL;
 	}
 	return zstrm;
 }
 
+bool zcomp_available_algorithm(const char *comp)
+{
+	int i = 0;
+
+	while (backends[i]) {
+		if (sysfs_streq(comp, backends[i]))
+			return true;
+		i++;
+	}
+
+	/*
+	 * Crypto does not ignore a trailing new line symbol,
+	 * so make sure you don't supply a string containing
+	 * one.
+	 * This also means that we permit zcomp initialisation
+	 * with any compressing algorithm known to crypto api.
+	 */
+	return crypto_has_comp(comp, 0, 0) == 1;
+}
+
 /* show available compressors */
 ssize_t zcomp_available_show(const char *comp, char *buf)
 {
+	bool known_algorithm = false;
 	ssize_t sz = 0;
 	int i = 0;
 
-	while (backends[i]) {
-		if (!strcmp(comp, backends[i]->name))
+	for (; backends[i]; i++) {
+		if (!strcmp(comp, backends[i])) {
+			known_algorithm = true;
 			sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2,
-					"[%s] ", backends[i]->name);
-		else
+					"[%s] ", backends[i]);
+		} else {
 			sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2,
-					"%s ", backends[i]->name);
-		i++;
+					"%s ", backends[i]);
+		}
 	}
+
+	/*
+	 * Out-of-tree module known to crypto api or a missing
+	 * entry in `backends'.
+	 */
+	if (!known_algorithm && crypto_has_comp(comp, 0, 0) == 1)
+		sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2,
+				"[%s] ", comp);
+
 	sz += scnprintf(buf + sz, PAGE_SIZE - sz, "\n");
 	return sz;
 }
 
-bool zcomp_available_algorithm(const char *comp)
-{
-	return find_backend(comp) != NULL;
-}
-
-struct zcomp_strm *zcomp_strm_find(struct zcomp *comp)
+struct zcomp_strm *zcomp_stream_get(struct zcomp *comp)
 {
 	return *get_cpu_ptr(comp->stream);
 }
 
-void zcomp_strm_release(struct zcomp *comp, struct zcomp_strm *zstrm)
+void zcomp_stream_put(struct zcomp *comp)
 {
 	put_cpu_ptr(comp->stream);
 }
 
-int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
-		const unsigned char *src, size_t *dst_len)
+int zcomp_compress(struct zcomp_strm *zstrm,
+		const void *src, unsigned int *dst_len)
 {
-	return comp->backend->compress(src, zstrm->buffer, dst_len,
-			zstrm->private);
+	/*
+	 * Our dst memory (zstrm->buffer) is always `2 * PAGE_SIZE' sized
+	 * because sometimes we can endup having a bigger compressed data
+	 * due to various reasons: for example compression algorithms tend
+	 * to add some padding to the compressed buffer. Speaking of padding,
+	 * comp algorithm `842' pads the compressed length to multiple of 8
+	 * and returns -ENOSP when the dst memory is not big enough, which
+	 * is not something that ZRAM wants to see. We can handle the
+	 * `compressed_size > PAGE_SIZE' case easily in ZRAM, but when we
+	 * receive -ERRNO from the compressing backend we can't help it
+	 * anymore. To make `842' happy we need to tell the exact size of
+	 * the dst buffer, zram_drv will take care of the fact that
+	 * compressed buffer is too big.
+	 */
+	*dst_len = PAGE_SIZE * 2;
+
+	return crypto_comp_compress(zstrm->tfm,
+			src, PAGE_SIZE,
+			zstrm->buffer, dst_len);
 }
 
-int zcomp_decompress(struct zcomp *comp, const unsigned char *src,
-		size_t src_len, unsigned char *dst)
+int zcomp_decompress(struct zcomp_strm *zstrm,
+		const void *src, unsigned int src_len, void *dst)
 {
-	return comp->backend->decompress(src, src_len, dst);
+	unsigned int dst_len = PAGE_SIZE;
+
+	return crypto_comp_decompress(zstrm->tfm,
+			src, src_len,
+			dst, &dst_len);
 }
 
 static int __zcomp_cpu_notifier(struct zcomp *comp,
@@ -127,7 +169,7 @@ static int __zcomp_cpu_notifier(struct zcomp *comp,
 	case CPU_UP_PREPARE:
 		if (WARN_ON(*per_cpu_ptr(comp->stream, cpu)))
 			break;
-		zstrm = zcomp_strm_alloc(comp, GFP_KERNEL);
+		zstrm = zcomp_strm_alloc(comp);
 		if (IS_ERR_OR_NULL(zstrm)) {
 			pr_err("Can't allocate a compression stream\n");
 			return NOTIFY_BAD;
@@ -138,7 +180,7 @@ static int __zcomp_cpu_notifier(struct zcomp *comp,
 	case CPU_UP_CANCELED:
 		zstrm = *per_cpu_ptr(comp->stream, cpu);
 		if (!IS_ERR_OR_NULL(zstrm))
-			zcomp_strm_free(comp, zstrm);
+			zcomp_strm_free(zstrm);
 		*per_cpu_ptr(comp->stream, cpu) = NULL;
 		break;
 	default:
@@ -209,18 +251,16 @@ void zcomp_destroy(struct zcomp *comp)
 struct zcomp *zcomp_create(const char *compress)
 {
 	struct zcomp *comp;
-	struct zcomp_backend *backend;
 	int error;
 
-	backend = find_backend(compress);
-	if (!backend)
+	if (!zcomp_available_algorithm(compress))
 		return ERR_PTR(-EINVAL);
 
 	comp = kzalloc(sizeof(struct zcomp), GFP_KERNEL);
 	if (!comp)
 		return ERR_PTR(-ENOMEM);
 
-	comp->backend = backend;
+	comp->name = compress;
 	error = zcomp_init(comp);
 	if (error) {
 		kfree(comp);

drivers/block/zram/zcomp.h

@@ -13,33 +13,15 @@
 struct zcomp_strm {
 	/* compression/decompression buffer */
 	void *buffer;
-	/*
-	 * The private data of the compression stream, only compression
-	 * stream backend can touch this (e.g. compression algorithm
-	 * working memory)
-	 */
-	void *private;
-};
-
-/* static compression backend */
-struct zcomp_backend {
-	int (*compress)(const unsigned char *src, unsigned char *dst,
-			size_t *dst_len, void *private);
-
-	int (*decompress)(const unsigned char *src, size_t src_len,
-			unsigned char *dst);
-
-	void *(*create)(gfp_t flags);
-	void (*destroy)(void *private);
-
-	const char *name;
+	struct crypto_comp *tfm;
 };
 
 /* dynamic per-device compression frontend */
 struct zcomp {
 	struct zcomp_strm * __percpu *stream;
-	struct zcomp_backend *backend;
 	struct notifier_block notifier;
+
+	const char *name;
 };
 
 ssize_t zcomp_available_show(const char *comp, char *buf);
@@ -48,14 +30,14 @@ bool zcomp_available_algorithm(const char *comp);
 struct zcomp *zcomp_create(const char *comp);
 void zcomp_destroy(struct zcomp *comp);
 
-struct zcomp_strm *zcomp_strm_find(struct zcomp *comp);
-void zcomp_strm_release(struct zcomp *comp, struct zcomp_strm *zstrm);
+struct zcomp_strm *zcomp_stream_get(struct zcomp *comp);
+void zcomp_stream_put(struct zcomp *comp);
 
-int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
-		const unsigned char *src, size_t *dst_len);
+int zcomp_compress(struct zcomp_strm *zstrm,
+		const void *src, unsigned int *dst_len);
 
-int zcomp_decompress(struct zcomp *comp, const unsigned char *src,
-		size_t src_len, unsigned char *dst);
+int zcomp_decompress(struct zcomp_strm *zstrm,
+		const void *src, unsigned int src_len, void *dst);
 
 bool zcomp_set_max_streams(struct zcomp *comp, int num_strm);
 #endif /* _ZCOMP_H_ */

drivers/block/zram/zcomp_lz4.c

-/*
- * Copyright (C) 2014 Sergey Senozhatsky.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/lz4.h>
-#include <linux/vmalloc.h>
-#include <linux/mm.h>
-
-#include "zcomp_lz4.h"
-
-static void *zcomp_lz4_create(gfp_t flags)
-{
-	void *ret;
-
-	ret = kmalloc(LZ4_MEM_COMPRESS, flags);
-	if (!ret)
-		ret = __vmalloc(LZ4_MEM_COMPRESS,
-				flags | __GFP_HIGHMEM,
-				PAGE_KERNEL);
-	return ret;
-}
-
-static void zcomp_lz4_destroy(void *private)
-{
-	kvfree(private);
-}
-
-static int zcomp_lz4_compress(const unsigned char *src, unsigned char *dst,
-		size_t *dst_len, void *private)
-{
-	/* return  : Success if return 0 */
-	return lz4_compress(src, PAGE_SIZE, dst, dst_len, private);
-}
-
-static int zcomp_lz4_decompress(const unsigned char *src, size_t src_len,
-		unsigned char *dst)
-{
-	size_t dst_len = PAGE_SIZE;
-	/* return  : Success if return 0 */
-	return lz4_decompress_unknownoutputsize(src, src_len, dst, &dst_len);
-}
-
-struct zcomp_backend zcomp_lz4 = {
-	.compress = zcomp_lz4_compress,
-	.decompress = zcomp_lz4_decompress,
-	.create = zcomp_lz4_create,
-	.destroy = zcomp_lz4_destroy,
-	.name = "lz4",
-};

drivers/block/zram/zcomp_lz4.h

-/*
- * Copyright (C) 2014 Sergey Senozhatsky.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#ifndef _ZCOMP_LZ4_H_
-#define _ZCOMP_LZ4_H_
-
-#include "zcomp.h"
-
-extern struct zcomp_backend zcomp_lz4;
-
-#endif /* _ZCOMP_LZ4_H_ */

drivers/block/zram/zcomp_lzo.c

-/*
- * Copyright (C) 2014 Sergey Senozhatsky.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/lzo.h>
-#include <linux/vmalloc.h>
-#include <linux/mm.h>
-
-#include "zcomp_lzo.h"
-
-static void *lzo_create(gfp_t flags)
-{
-	void *ret;
-
-	ret = kmalloc(LZO1X_MEM_COMPRESS, flags);
-	if (!ret)
-		ret = __vmalloc(LZO1X_MEM_COMPRESS,
-				flags | __GFP_HIGHMEM,
-				PAGE_KERNEL);
-	return ret;
-}
-
-static void lzo_destroy(void *private)
-{
-	kvfree(private);
-}
-
-static int lzo_compress(const unsigned char *src, unsigned char *dst,
-		size_t *dst_len, void *private)
-{
-	int ret = lzo1x_1_compress(src, PAGE_SIZE, dst, dst_len, private);
-	return ret == LZO_E_OK ? 0 : ret;
-}
-
-static int lzo_decompress(const unsigned char *src, size_t src_len,
-		unsigned char *dst)
-{
-	size_t dst_len = PAGE_SIZE;
-	int ret = lzo1x_decompress_safe(src, src_len, dst, &dst_len);
-	return ret == LZO_E_OK ? 0 : ret;
-}
-
-struct zcomp_backend zcomp_lzo = {
-	.compress = lzo_compress,
-	.decompress = lzo_decompress,
-	.create = lzo_create,
-	.destroy = lzo_destroy,
-	.name = "lzo",
-};

drivers/block/zram/zcomp_lzo.h

-/*
- * Copyright (C) 2014 Sergey Senozhatsky.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#ifndef _ZCOMP_LZO_H_
-#define _ZCOMP_LZO_H_
-
-#include "zcomp.h"
-
-extern struct zcomp_backend zcomp_lzo;
-
-#endif /* _ZCOMP_LZO_H_ */

drivers/block/zram/zram_drv.c

@@ -342,9 +342,16 @@ static ssize_t comp_algorithm_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
 	struct zram *zram = dev_to_zram(dev);
+	char compressor[CRYPTO_MAX_ALG_NAME];
 	size_t sz;
 
-	if (!zcomp_available_algorithm(buf))
+	strlcpy(compressor, buf, sizeof(compressor));
+	/* ignore trailing newline */
+	sz = strlen(compressor);
+	if (sz > 0 && compressor[sz - 1] == '\n')
+		compressor[sz - 1] = 0x00;
+
+	if (!zcomp_available_algorithm(compressor))
 		return -EINVAL;
 
 	down_write(&zram->init_lock);
@@ -353,13 +360,8 @@ static ssize_t comp_algorithm_store(struct device *dev,
 		pr_info("Can't change algorithm for initialized device\n");
 		return -EBUSY;
 	}
-	strlcpy(zram->compressor, buf, sizeof(zram->compressor));
-
-	/* ignore trailing newline */
-	sz = strlen(zram->compressor);
-	if (sz > 0 && zram->compressor[sz - 1] == '\n')
-		zram->compressor[sz - 1] = 0x00;
 
+	strlcpy(zram->compressor, compressor, sizeof(compressor));
 	up_write(&zram->init_lock);
 	return len;
 }
@@ -563,7 +565,7 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 	unsigned char *cmem;
 	struct zram_meta *meta = zram->meta;
 	unsigned long handle;
-	size_t size;
+	unsigned int size;
 
 	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 	handle = meta->table[index].handle;
@@ -576,10 +578,14 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 	}
 
 	cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
-	if (size == PAGE_SIZE)
+	if (size == PAGE_SIZE) {
 		copy_page(mem, cmem);
-	else
-		ret = zcomp_decompress(zram->comp, cmem, size, mem);
+	} else {
+		struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);
+
+		ret = zcomp_decompress(zstrm, cmem, size, mem);
+		zcomp_stream_put(zram->comp);
+	}
 	zs_unmap_object(meta->mem_pool, handle);
 	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 
@@ -646,7 +652,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 			   int offset)
 {
 	int ret = 0;
-	size_t clen;
+	unsigned int clen;
 	unsigned long handle = 0;
 	struct page *page;
 	unsigned char *user_mem, *cmem, *src, *uncmem = NULL;
@@ -695,8 +701,8 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 		goto out;
 	}
 
-	zstrm = zcomp_strm_find(zram->comp);
-	ret = zcomp_compress(zram->comp, zstrm, uncmem, &clen);
+	zstrm = zcomp_stream_get(zram->comp);
+	ret = zcomp_compress(zstrm, uncmem, &clen);
 	if (!is_partial_io(bvec)) {
 		kunmap_atomic(user_mem);
 		user_mem = NULL;
@@ -732,19 +738,21 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 		handle = zs_malloc(meta->mem_pool, clen,
 				__GFP_KSWAPD_RECLAIM |
 				__GFP_NOWARN |
-				__GFP_HIGHMEM);
+				__GFP_HIGHMEM |
+				__GFP_MOVABLE);
 	if (!handle) {
-		zcomp_strm_release(zram->comp, zstrm);
+		zcomp_stream_put(zram->comp);
 		zstrm = NULL;
 
 		atomic64_inc(&zram->stats.writestall);
 
 		handle = zs_malloc(meta->mem_pool, clen,
-				GFP_NOIO | __GFP_HIGHMEM);
+				GFP_NOIO | __GFP_HIGHMEM |
+				__GFP_MOVABLE);
 		if (handle)
 			goto compress_again;
 
-		pr_err("Error allocating memory for compressed page: %u, size=%zu\n",
+		pr_err("Error allocating memory for compressed page: %u, size=%u\n",
 			index, clen);
 		ret = -ENOMEM;
 		goto out;
@@ -769,7 +777,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 		memcpy(cmem, src, clen);
 	}
 
-	zcomp_strm_release(zram->comp, zstrm);
+	zcomp_stream_put(zram->comp);
 	zstrm = NULL;
 	zs_unmap_object(meta->mem_pool, handle);
 
@@ -789,7 +797,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	atomic64_inc(&zram->stats.pages_stored);
 out:
 	if (zstrm)
-		zcomp_strm_release(zram->comp, zstrm);
+		zcomp_stream_put(zram->comp);
 	if (is_partial_io(bvec))
 		kfree(uncmem);
 	return ret;

drivers/block/zram/zram_drv.h

@@ -15,8 +15,9 @@
 #ifndef _ZRAM_DRV_H_
 #define _ZRAM_DRV_H_
 
-#include <linux/spinlock.h>
+#include <linux/rwsem.h>
 #include <linux/zsmalloc.h>
+#include <linux/crypto.h>
 
 #include "zcomp.h"
 
@@ -113,7 +114,7 @@ struct zram {
 	 * we can store in a disk.
 	 */
 	u64 disksize;	/* bytes */
-	char compressor[10];
+	char compressor[CRYPTO_MAX_ALG_NAME];
 	/*
 	 * zram is claimed so open request will be failed
 	 */

drivers/char/mem.c

@@ -22,6 +22,7 @@
 #include <linux/device.h>
 #include <linux/highmem.h>
 #include <linux/backing-dev.h>
+#include <linux/shmem_fs.h>
 #include <linux/splice.h>
 #include <linux/pfn.h>
 #include <linux/export.h>
@@ -657,6 +658,28 @@ static int mmap_zero(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
+static unsigned long get_unmapped_area_zero(struct file *file,
+				unsigned long addr, unsigned long len,
+				unsigned long pgoff, unsigned long flags)
+{
+#ifdef CONFIG_MMU
+	if (flags & MAP_SHARED) {
+		/*
+		 * mmap_zero() will call shmem_zero_setup() to create a file,
+		 * so use shmem's get_unmapped_area in case it can be huge;
+		 * and pass NULL for file as in mmap.c's get_unmapped_area(),
+		 * so as not to confuse shmem with our handle on "/dev/zero".
+		 */
+		return shmem_get_unmapped_area(NULL, addr, len, pgoff, flags);
+	}
+
+	/* Otherwise flags & MAP_PRIVATE: with no shmem object beneath it */
+	return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+#else
+	return -ENOSYS;
+#endif
+}
+
 static ssize_t write_full(struct file *file, const char __user *buf,
 			  size_t count, loff_t *ppos)
 {
@@ -764,6 +787,7 @@ static const struct file_operations zero_fops = {
 	.read_iter	= read_iter_zero,
 	.write_iter	= write_iter_zero,
 	.mmap		= mmap_zero,
+	.get_unmapped_area = get_unmapped_area_zero,
 #ifndef CONFIG_MMU
 	.mmap_capabilities = zero_mmap_capabilities,
 #endif

drivers/iommu/amd_iommu_v2.c

@@ -538,8 +538,7 @@ static void do_fault(struct work_struct *work)
 	if (access_error(vma, fault))
 		goto out;
 
-	ret = handle_mm_fault(mm, vma, address, flags);
-
+	ret = handle_mm_fault(vma, address, flags);
 out:
 	up_read(&mm->mmap_sem);
 

drivers/iommu/intel-svm.c

@@ -583,7 +583,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 		if (access_error(vma, req))
 			goto invalid;
 
-		ret = handle_mm_fault(svm->mm, vma, address,
+		ret = handle_mm_fault(vma, address,
 				      req->wr_req ? FAULT_FLAG_WRITE : 0);
 		if (ret & VM_FAULT_ERROR)
 			goto invalid;

drivers/tty/sysrq.c

@@ -363,6 +363,7 @@ static void moom_callback(struct work_struct *ignored)
 	struct oom_control oc = {
 		.zonelist = node_zonelist(first_memory_node, gfp_mask),
 		.nodemask = NULL,
+		.memcg = NULL,
 		.gfp_mask = gfp_mask,
 		.order = -1,
 	};

drivers/video/fbdev/core/fbmon.c

@@ -1496,7 +1496,6 @@ int fb_parse_edid(unsigned char *edid, struct fb_var_screeninfo *var)
 }
 void fb_edid_to_monspecs(unsigned char *edid, struct fb_monspecs *specs)
 {
-	specs = NULL;
 }
 void fb_edid_add_monspecs(unsigned char *edid, struct fb_monspecs *specs)
 {

drivers/virtio/virtio_balloon.c

@@ -30,6 +30,7 @@
 #include <linux/oom.h>
 #include <linux/wait.h>
 #include <linux/mm.h>
+#include <linux/mount.h>
 
 /*
  * Balloon device works in 4K page units.  So each page is pointed to by
@@ -45,6 +46,10 @@ static int oom_pages = OOM_VBALLOON_DEFAULT_PAGES;
 module_param(oom_pages, int, S_IRUSR | S_IWUSR);
 MODULE_PARM_DESC(oom_pages, "pages to free on OOM");
 
+#ifdef CONFIG_BALLOON_COMPACTION
+static struct vfsmount *balloon_mnt;
+#endif
+
 struct virtio_balloon {
 	struct virtio_device *vdev;
 	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
@@ -490,6 +495,24 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
 
 	return MIGRATEPAGE_SUCCESS;
 }
+
+static struct dentry *balloon_mount(struct file_system_type *fs_type,
+		int flags, const char *dev_name, void *data)
+{
+	static const struct dentry_operations ops = {
+		.d_dname = simple_dname,
+	};
+
+	return mount_pseudo(fs_type, "balloon-kvm:", NULL, &ops,
+				BALLOON_KVM_MAGIC);
+}
+
+static struct file_system_type balloon_fs = {
+	.name           = "balloon-kvm",
+	.mount          = balloon_mount,
+	.kill_sb        = kill_anon_super,
+};
+
 #endif /* CONFIG_BALLOON_COMPACTION */
 
 static int virtballoon_probe(struct virtio_device *vdev)
@@ -519,9 +542,6 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	vb->vdev = vdev;
 
 	balloon_devinfo_init(&vb->vb_dev_info);
-#ifdef CONFIG_BALLOON_COMPACTION
-	vb->vb_dev_info.migratepage = virtballoon_migratepage;
-#endif
 
 	err = init_vqs(vb);
 	if (err)
@@ -531,13 +551,33 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	vb->nb.priority = VIRTBALLOON_OOM_NOTIFY_PRIORITY;
 	err = register_oom_notifier(&vb->nb);
 	if (err < 0)
-		goto out_oom_notify;
+		goto out_del_vqs;
+
+#ifdef CONFIG_BALLOON_COMPACTION
+	balloon_mnt = kern_mount(&balloon_fs);
+	if (IS_ERR(balloon_mnt)) {
+		err = PTR_ERR(balloon_mnt);
+		unregister_oom_notifier(&vb->nb);
+		goto out_del_vqs;
+	}
+
+	vb->vb_dev_info.migratepage = virtballoon_migratepage;
+	vb->vb_dev_info.inode = alloc_anon_inode(balloon_mnt->mnt_sb);
+	if (IS_ERR(vb->vb_dev_info.inode)) {
+		err = PTR_ERR(vb->vb_dev_info.inode);
+		kern_unmount(balloon_mnt);
+		unregister_oom_notifier(&vb->nb);
+		vb->vb_dev_info.inode = NULL;
+		goto out_del_vqs;
+	}
+	vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
+#endif
 
 	virtio_device_ready(vdev);
 
 	return 0;
 
-out_oom_notify:
+out_del_vqs:
 	vdev->config->del_vqs(vdev);
 out_free_vb:
 	kfree(vb);
@@ -571,6 +611,8 @@ static void virtballoon_remove(struct virtio_device *vdev)
 	cancel_work_sync(&vb->update_balloon_stats_work);
 
 	remove_common(vb);
+	if (vb->vb_dev_info.inode)
+		iput(vb->vb_dev_info.inode);
 	kfree(vb);
 }
 

drivers/xen/xen-selfballoon.c

@@ -195,7 +195,7 @@ static void selfballoon_process(struct work_struct *work)
 				MB2PAGES(selfballoon_reserved_mb);
 #ifdef CONFIG_FRONTSWAP
 		/* allow space for frontswap pages to be repatriated */
-		if (frontswap_selfshrinking && frontswap_enabled)
+		if (frontswap_selfshrinking)
 			goal_pages += frontswap_curr_pages();
 #endif
 		if (cur_pages > goal_pages)
@@ -230,7 +230,7 @@ static void selfballoon_process(struct work_struct *work)
 		reset_timer = true;
 	}
 #ifdef CONFIG_FRONTSWAP
-	if (frontswap_selfshrinking && frontswap_enabled) {
+	if (frontswap_selfshrinking) {
 		frontswap_selfshrink();
 		reset_timer = true;
 	}

fs/btrfs/extent_io.c

@@ -4178,7 +4178,8 @@ int extent_readpages(struct extent_io_tree *tree,
 		prefetchw(&page->flags);
 		list_del(&page->lru);
 		if (add_to_page_cache_lru(page, mapping,
-					page->index, GFP_NOFS)) {
+					page->index,
+					readahead_gfp_mask(mapping))) {
 			put_page(page);
 			continue;
 		}

fs/cifs/file.c

@@ -3366,7 +3366,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 	struct page *page, *tpage;
 	unsigned int expected_index;
 	int rc;
-	gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
+	gfp_t gfp = readahead_gfp_mask(mapping);
 
 	INIT_LIST_HEAD(tmplist);
 

fs/dax.c

@@ -819,16 +819,16 @@ static int dax_insert_mapping(struct address_space *mapping,
 }
 
 /**
- * __dax_fault - handle a page fault on a DAX file
+ * dax_fault - handle a page fault on a DAX file
  * @vma: The virtual memory area where the fault occurred
  * @vmf: The description of the fault
  * @get_block: The filesystem method used to translate file offsets to blocks
  *
  * When a page fault occurs, filesystems may call this helper in their
- * fault handler for DAX files. __dax_fault() assumes the caller has done all
+ * fault handler for DAX files. dax_fault() assumes the caller has done all
  * the necessary locking for the page fault to proceed successfully.
  */
-int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			get_block_t get_block)
 {
 	struct file *file = vma->vm_file;
@@ -913,33 +913,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		return VM_FAULT_SIGBUS | major;
 	return VM_FAULT_NOPAGE | major;
 }
-EXPORT_SYMBOL(__dax_fault);
-
-/**
- * dax_fault - handle a page fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @get_block: The filesystem method used to translate file offsets to blocks
- *
- * When a page fault occurs, filesystems may call this helper in their
- * fault handler for DAX files.
- */
-int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
-	      get_block_t get_block)
-{
-	int result;
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
-
-	if (vmf->flags & FAULT_FLAG_WRITE) {
-		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
-	}
-	result = __dax_fault(vma, vmf, get_block);
-	if (vmf->flags & FAULT_FLAG_WRITE)
-		sb_end_pagefault(sb);
-
-	return result;
-}
 EXPORT_SYMBOL_GPL(dax_fault);
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE)
@@ -967,7 +940,16 @@ static void __dax_dbg(struct buffer_head *bh, unsigned long address,
 
 #define dax_pmd_dbg(bh, address, reason)	__dax_dbg(bh, address, reason, "dax_pmd")
 
-int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+/**
+ * dax_pmd_fault - handle a PMD fault on a DAX file
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * When a page fault occurs, filesystems may call this helper in their
+ * pmd_fault handler for DAX files.
+ */
+int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		pmd_t *pmd, unsigned int flags, get_block_t get_block)
 {
 	struct file *file = vma->vm_file;
@@ -1119,7 +1101,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		 *
 		 * The PMD path doesn't have an equivalent to
 		 * dax_pfn_mkwrite(), though, so for a read followed by a
-		 * write we traverse all the way through __dax_pmd_fault()
+		 * write we traverse all the way through dax_pmd_fault()
 		 * twice.  This means we can just skip inserting a radix tree
 		 * entry completely on the initial read and just wait until
 		 * the write to insert a dirty entry.
@@ -1148,33 +1130,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	result = VM_FAULT_FALLBACK;
 	goto out;
 }
-EXPORT_SYMBOL_GPL(__dax_pmd_fault);
-
-/**
- * dax_pmd_fault - handle a PMD fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @get_block: The filesystem method used to translate file offsets to blocks
- *
- * When a page fault occurs, filesystems may call this helper in their
- * pmd_fault handler for DAX files.
- */
-int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
-			pmd_t *pmd, unsigned int flags, get_block_t get_block)
-{
-	int result;
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
-
-	if (flags & FAULT_FLAG_WRITE) {
-		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
-	}
-	result = __dax_pmd_fault(vma, address, pmd, flags, get_block);
-	if (flags & FAULT_FLAG_WRITE)
-		sb_end_pagefault(sb);
-
-	return result;
-}
 EXPORT_SYMBOL_GPL(dax_pmd_fault);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 

fs/ext2/file.c

@@ -51,7 +51,7 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 	down_read(&ei->dax_sem);
 
-	ret = __dax_fault(vma, vmf, ext2_get_block);
+	ret = dax_fault(vma, vmf, ext2_get_block);
 
 	up_read(&ei->dax_sem);
 	if (vmf->flags & FAULT_FLAG_WRITE)
@@ -72,7 +72,7 @@ static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	}
 	down_read(&ei->dax_sem);
 
-	ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block);
+	ret = dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block);
 
 	up_read(&ei->dax_sem);
 	if (flags & FAULT_FLAG_WRITE)

fs/ext4/file.c

@@ -202,7 +202,7 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
 	else
-		result = __dax_fault(vma, vmf, ext4_dax_get_block);
+		result = dax_fault(vma, vmf, ext4_dax_get_block);
 
 	if (write) {
 		if (!IS_ERR(handle))
@@ -237,7 +237,7 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
 	else
-		result = __dax_pmd_fault(vma, addr, pmd, flags,
+		result = dax_pmd_fault(vma, addr, pmd, flags,
 					 ext4_dax_get_block);
 
 	if (write) {

fs/ext4/readpage.c

@@ -130,7 +130,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
 			page = list_entry(pages->prev, struct page, lru);
 			list_del(&page->lru);
 			if (add_to_page_cache_lru(page, mapping, page->index,
-				  mapping_gfp_constraint(mapping, GFP_KERNEL)))
+				  readahead_gfp_mask(mapping)))
 				goto next_page;
 		}
 

fs/f2fs/data.c

@@ -1002,7 +1002,8 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 			page = list_entry(pages->prev, struct page, lru);
 			list_del(&page->lru);
 			if (add_to_page_cache_lru(page, mapping,
-						  page->index, GFP_KERNEL))
+						  page->index,
+						  readahead_gfp_mask(mapping)))
 				goto next_page;
 		}
 

fs/fs-writeback.c

@@ -980,6 +980,42 @@ void inode_io_list_del(struct inode *inode)
 	spin_unlock(&wb->list_lock);
 }
 
+/*
+ * mark an inode as under writeback on the sb
+ */
+void sb_mark_inode_writeback(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	unsigned long flags;
+
+	if (list_empty(&inode->i_wb_list)) {
+		spin_lock_irqsave(&sb->s_inode_wblist_lock, flags);
+		if (list_empty(&inode->i_wb_list)) {
+			list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb);
+			trace_sb_mark_inode_writeback(inode);
+		}
+		spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags);
+	}
+}
+
+/*
+ * clear an inode as under writeback on the sb
+ */
+void sb_clear_inode_writeback(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	unsigned long flags;
+
+	if (!list_empty(&inode->i_wb_list)) {
+		spin_lock_irqsave(&sb->s_inode_wblist_lock, flags);
+		if (!list_empty(&inode->i_wb_list)) {
+			list_del_init(&inode->i_wb_list);
+			trace_sb_clear_inode_writeback(inode);
+		}
+		spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags);
+	}
+}
+
 /*
  * Redirty an inode: set its when-it-was dirtied timestamp and move it to the
  * furthest end of its superblock's dirty-inode list.
@@ -2154,7 +2190,7 @@ EXPORT_SYMBOL(__mark_inode_dirty);
  */
 static void wait_sb_inodes(struct super_block *sb)
 {
-	struct inode *inode, *old_inode = NULL;
+	LIST_HEAD(sync_list);
 
 	/*
 	 * We need to be protected against the filesystem going from
@@ -2163,38 +2199,60 @@ static void wait_sb_inodes(struct super_block *sb)
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
 	mutex_lock(&sb->s_sync_lock);
-	spin_lock(&sb->s_inode_list_lock);
 
 	/*
-	 * Data integrity sync. Must wait for all pages under writeback,
-	 * because there may have been pages dirtied before our sync
-	 * call, but which had writeout started before we write it out.
-	 * In which case, the inode may not be on the dirty list, but
-	 * we still have to wait for that writeout.
+	 * Splice the writeback list onto a temporary list to avoid waiting on
+	 * inodes that have started writeback after this point.
+	 *
+	 * Use rcu_read_lock() to keep the inodes around until we have a
+	 * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as
+	 * the local list because inodes can be dropped from either by writeback
+	 * completion.
+	 */
+	rcu_read_lock();
+	spin_lock_irq(&sb->s_inode_wblist_lock);
+	list_splice_init(&sb->s_inodes_wb, &sync_list);
+
+	/*
+	 * Data integrity sync. Must wait for all pages under writeback, because
+	 * there may have been pages dirtied before our sync call, but which had
+	 * writeout started before we write it out.  In which case, the inode
+	 * may not be on the dirty list, but we still have to wait for that
+	 * writeout.
 	 */
-	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+	while (!list_empty(&sync_list)) {
+		struct inode *inode = list_first_entry(&sync_list, struct inode,
+						       i_wb_list);
 		struct address_space *mapping = inode->i_mapping;
 
+		/*
+		 * Move each inode back to the wb list before we drop the lock
+		 * to preserve consistency between i_wb_list and the mapping
+		 * writeback tag. Writeback completion is responsible to remove
+		 * the inode from either list once the writeback tag is cleared.
+		 */
+		list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb);
+
+		/*
+		 * The mapping can appear untagged while still on-list since we
+		 * do not have the mapping lock. Skip it here, wb completion
+		 * will remove it.
+		 */
+		if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
+			continue;
+
+		spin_unlock_irq(&sb->s_inode_wblist_lock);
+
 		spin_lock(&inode->i_lock);
-		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
-		    (mapping->nrpages == 0)) {
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
 			spin_unlock(&inode->i_lock);
+
+			spin_lock_irq(&sb->s_inode_wblist_lock);
 			continue;
 		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&sb->s_inode_list_lock);
-
-		/*
-		 * We hold a reference to 'inode' so it couldn't have been
-		 * removed from s_inodes list while we dropped the
-		 * s_inode_list_lock.  We cannot iput the inode now as we can
-		 * be holding the last reference and we cannot iput it under
-		 * s_inode_list_lock. So we keep the reference and iput it
-		 * later.
-		 */
-		iput(old_inode);
-		old_inode = inode;
+		rcu_read_unlock();
 
 		/*
 		 * We keep the error status of individual mapping so that
@@ -2205,10 +2263,13 @@ static void wait_sb_inodes(struct super_block *sb)
 
 		cond_resched();
 
-		spin_lock(&sb->s_inode_list_lock);
+		iput(inode);
+
+		rcu_read_lock();
+		spin_lock_irq(&sb->s_inode_wblist_lock);
 	}
-	spin_unlock(&sb->s_inode_list_lock);
-	iput(old_inode);
+	spin_unlock_irq(&sb->s_inode_wblist_lock);
+	rcu_read_unlock();
 	mutex_unlock(&sb->s_sync_lock);
 }
 

fs/inode.c

@@ -365,6 +365,7 @@ void inode_init_once(struct inode *inode)
 	INIT_HLIST_NODE(&inode->i_hash);
 	INIT_LIST_HEAD(&inode->i_devices);
 	INIT_LIST_HEAD(&inode->i_io_list);
+	INIT_LIST_HEAD(&inode->i_wb_list);
 	INIT_LIST_HEAD(&inode->i_lru);
 	address_space_init_once(&inode->i_data);
 	i_size_ordered_init(inode);
@@ -507,6 +508,7 @@ void clear_inode(struct inode *inode)
 	BUG_ON(!list_empty(&inode->i_data.private_list));
 	BUG_ON(!(inode->i_state & I_FREEING));
 	BUG_ON(inode->i_state & I_CLEAR);
+	BUG_ON(!list_empty(&inode->i_wb_list));
 	/* don't need i_lock here, no concurrent mods to i_state */
 	inode->i_state = I_FREEING | I_CLEAR;
 }

fs/mpage.c

@@ -72,6 +72,8 @@ mpage_alloc(struct block_device *bdev,
 {
 	struct bio *bio;
 
+	/* Restrict the given (page cache) mask for slab allocations */
+	gfp_flags &= GFP_KERNEL;
 	bio = bio_alloc(gfp_flags, nr_vecs);
 
 	if (bio == NULL && (current->flags & PF_MEMALLOC)) {
@@ -363,7 +365,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	sector_t last_block_in_bio = 0;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
-	gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
+	gfp_t gfp = readahead_gfp_mask(mapping);
 
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;

fs/ocfs2/cluster/tcp.c

@@ -1618,16 +1618,12 @@ static void o2net_start_connect(struct work_struct *work)
 
 	/* watch for racing with tearing a node down */
 	node = o2nm_get_node_by_num(o2net_num_from_nn(nn));
-	if (node == NULL) {
-		ret = 0;
+	if (node == NULL)
 		goto out;
-	}
 
 	mynode = o2nm_get_node_by_num(o2nm_this_node());
-	if (mynode == NULL) {
-		ret = 0;
+	if (mynode == NULL)
 		goto out;
-	}
 
 	spin_lock(&nn->nn_lock);
 	/*

fs/ocfs2/dlm/dlmdebug.c

@@ -347,26 +347,6 @@ static struct dentry *dlm_debugfs_root;
 #define DLM_DEBUGFS_PURGE_LIST			"purge_list"
 
 /* begin - utils funcs */
-static void dlm_debug_free(struct kref *kref)
-{
-	struct dlm_debug_ctxt *dc;
-
-	dc = container_of(kref, struct dlm_debug_ctxt, debug_refcnt);
-
-	kfree(dc);
-}
-
-static void dlm_debug_put(struct dlm_debug_ctxt *dc)
-{
-	if (dc)
-		kref_put(&dc->debug_refcnt, dlm_debug_free);
-}
-
-static void dlm_debug_get(struct dlm_debug_ctxt *dc)
-{
-	kref_get(&dc->debug_refcnt);
-}
-
 static int debug_release(struct inode *inode, struct file *file)
 {
 	free_page((unsigned long)file->private_data);
@@ -932,11 +912,9 @@ int dlm_debug_init(struct dlm_ctxt *dlm)
 		goto bail;
 	}
 
-	dlm_debug_get(dc);
 	return 0;
 
 bail:
-	dlm_debug_shutdown(dlm);
 	return -ENOMEM;
 }
 
@@ -949,7 +927,8 @@ void dlm_debug_shutdown(struct dlm_ctxt *dlm)
 		debugfs_remove(dc->debug_mle_dentry);
 		debugfs_remove(dc->debug_lockres_dentry);
 		debugfs_remove(dc->debug_state_dentry);
-		dlm_debug_put(dc);
+		kfree(dc);
+		dc = NULL;
 	}
 }
 
@@ -969,7 +948,6 @@ int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
 		mlog_errno(-ENOMEM);
 		goto bail;
 	}
-	kref_init(&dlm->dlm_debug_ctxt->debug_refcnt);
 
 	return 0;
 bail:

fs/ocfs2/dlm/dlmdebug.h

@@ -30,7 +30,6 @@ void dlm_print_one_mle(struct dlm_master_list_entry *mle);
 #ifdef CONFIG_DEBUG_FS
 
 struct dlm_debug_ctxt {
-	struct kref debug_refcnt;
 	struct dentry *debug_state_dentry;
 	struct dentry *debug_lockres_dentry;
 	struct dentry *debug_mle_dentry;

fs/ocfs2/dlmglue.c

@@ -1635,7 +1635,6 @@ int ocfs2_create_new_inode_locks(struct inode *inode)
 	int ret;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	BUG_ON(!inode);
 	BUG_ON(!ocfs2_inode_is_new(inode));
 
 	mlog(0, "Inode %llu\n", (unsigned long long)OCFS2_I(inode)->ip_blkno);
@@ -1665,10 +1664,8 @@ int ocfs2_create_new_inode_locks(struct inode *inode)
 	}
 
 	ret = ocfs2_create_new_lock(osb, &OCFS2_I(inode)->ip_open_lockres, 0, 0);
-	if (ret) {
+	if (ret)
 		mlog_errno(ret);
-		goto bail;
-	}
 
 bail:
 	return ret;
@@ -1680,8 +1677,6 @@ int ocfs2_rw_lock(struct inode *inode, int write)
 	struct ocfs2_lock_res *lockres;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	BUG_ON(!inode);
-
 	mlog(0, "inode %llu take %s RW lock\n",
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
 	     write ? "EXMODE" : "PRMODE");
@@ -1724,8 +1719,6 @@ int ocfs2_open_lock(struct inode *inode)
 	struct ocfs2_lock_res *lockres;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	BUG_ON(!inode);
-
 	mlog(0, "inode %llu take PRMODE open lock\n",
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno);
 
@@ -1749,8 +1742,6 @@ int ocfs2_try_open_lock(struct inode *inode, int write)
 	struct ocfs2_lock_res *lockres;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	BUG_ON(!inode);
-
 	mlog(0, "inode %llu try to take %s open lock\n",
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
 	     write ? "EXMODE" : "PRMODE");
@@ -2328,8 +2319,6 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct buffer_head *local_bh = NULL;
 
-	BUG_ON(!inode);
-
 	mlog(0, "inode %llu, take %s META lock\n",
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
 	     ex ? "EXMODE" : "PRMODE");

fs/ocfs2/inode.h

@@ -145,22 +145,15 @@ int ocfs2_drop_inode(struct inode *inode);
 struct inode *ocfs2_ilookup(struct super_block *sb, u64 feoff);
 struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 feoff, unsigned flags,
 			 int sysfile_type);
-int ocfs2_inode_init_private(struct inode *inode);
 int ocfs2_inode_revalidate(struct dentry *dentry);
 void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
 			  int create_ino);
-void ocfs2_read_inode(struct inode *inode);
-void ocfs2_read_inode2(struct inode *inode, void *opaque);
-ssize_t ocfs2_rw_direct(int rw, struct file *filp, char *buf,
-			size_t size, loff_t *offp);
 void ocfs2_sync_blockdev(struct super_block *sb);
 void ocfs2_refresh_inode(struct inode *inode,
 			 struct ocfs2_dinode *fe);
 int ocfs2_mark_inode_dirty(handle_t *handle,
 			   struct inode *inode,
 			   struct buffer_head *bh);
-struct buffer_head *ocfs2_bread(struct inode *inode,
-				int block, int *err, int reada);
 
 void ocfs2_set_inode_flags(struct inode *inode);
 void ocfs2_get_inode_flags(struct ocfs2_inode_info *oi);

fs/ocfs2/journal.c

@@ -1159,10 +1159,8 @@ static int ocfs2_force_read_journal(struct inode *inode)
 	int status = 0;
 	int i;
 	u64 v_blkno, p_blkno, p_blocks, num_blocks;
-#define CONCURRENT_JOURNAL_FILL 32ULL
-	struct buffer_head *bhs[CONCURRENT_JOURNAL_FILL];
-
-	memset(bhs, 0, sizeof(struct buffer_head *) * CONCURRENT_JOURNAL_FILL);
+	struct buffer_head *bh = NULL;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	num_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
 	v_blkno = 0;
@@ -1174,29 +1172,32 @@ static int ocfs2_force_read_journal(struct inode *inode)
 			goto bail;
 		}
 
-		if (p_blocks > CONCURRENT_JOURNAL_FILL)
-			p_blocks = CONCURRENT_JOURNAL_FILL;
-
-		/* We are reading journal data which should not
-		 * be put in the uptodate cache */
-		status = ocfs2_read_blocks_sync(OCFS2_SB(inode->i_sb),
-						p_blkno, p_blocks, bhs);
-		if (status < 0) {
-			mlog_errno(status);
-			goto bail;
-		}
+		for (i = 0; i < p_blocks; i++, p_blkno++) {
+			bh = __find_get_block(osb->sb->s_bdev, p_blkno,
+					osb->sb->s_blocksize);
+			/* block not cached. */
+			if (!bh)
+				continue;
+
+			brelse(bh);
+			bh = NULL;
+			/* We are reading journal data which should not
+			 * be put in the uptodate cache.
+			 */
+			status = ocfs2_read_blocks_sync(osb, p_blkno, 1, &bh);
+			if (status < 0) {
+				mlog_errno(status);
+				goto bail;
+			}
 
-		for(i = 0; i < p_blocks; i++) {
-			brelse(bhs[i]);
-			bhs[i] = NULL;
+			brelse(bh);
+			bh = NULL;
 		}
 
 		v_blkno += p_blocks;
 	}
 
 bail:
-	for(i = 0; i < CONCURRENT_JOURNAL_FILL; i++)
-		brelse(bhs[i]);
 	return status;
 }
 

fs/ocfs2/stackglue.c

@@ -735,8 +735,6 @@ static void __exit ocfs2_stack_glue_exit(void)
 {
 	memset(&locking_max_version, 0,
 	       sizeof(struct ocfs2_protocol_version));
-	locking_max_version.pv_major = 0;
-	locking_max_version.pv_minor = 0;
 	ocfs2_sysfs_exit();
 	if (ocfs2_table_header)
 		unregister_sysctl_table(ocfs2_table_header);

fs/ocfs2/super.c

@@ -2072,7 +2072,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	osb->osb_dx_seed[3] = le32_to_cpu(di->id2.i_super.s_uuid_hash);
 
 	osb->sb = sb;
-	/* Save off for ocfs2_rw_direct */
 	osb->s_sectsize_bits = blksize_bits(sector_size);
 	BUG_ON(!osb->s_sectsize_bits);
 

fs/orangefs/inode.c

@@ -80,7 +80,7 @@ static int orangefs_readpages(struct file *file,
 		if (!add_to_page_cache(page,
 				       mapping,
 				       page->index,
-				       GFP_KERNEL)) {
+				       readahead_gfp_mask(mapping))) {
 			ret = read_one_page(page);
 			gossip_debug(GOSSIP_INODE_DEBUG,
 				"failure adding page to cache, read_one_page returned: %d\n",

fs/pipe.c

@@ -21,6 +21,7 @@
 #include <linux/audit.h>
 #include <linux/syscalls.h>
 #include <linux/fcntl.h>
+#include <linux/memcontrol.h>
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
@@ -137,6 +138,22 @@ static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
 		put_page(page);
 }
 
+static int anon_pipe_buf_steal(struct pipe_inode_info *pipe,
+			       struct pipe_buffer *buf)
+{
+	struct page *page = buf->page;
+
+	if (page_count(page) == 1) {
+		if (memcg_kmem_enabled()) {
+			memcg_kmem_uncharge(page, 0);
+			__ClearPageKmemcg(page);
+		}
+		__SetPageLocked(page);
+		return 0;
+	}
+	return 1;
+}
+
 /**
  * generic_pipe_buf_steal - attempt to take ownership of a &pipe_buffer
  * @pipe:	the pipe that the buffer belongs to
@@ -219,7 +236,7 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = {
 	.can_merge = 1,
 	.confirm = generic_pipe_buf_confirm,
 	.release = anon_pipe_buf_release,
-	.steal = generic_pipe_buf_steal,
+	.steal = anon_pipe_buf_steal,
 	.get = generic_pipe_buf_get,
 };
 
@@ -227,7 +244,7 @@ static const struct pipe_buf_operations packet_pipe_buf_ops = {
 	.can_merge = 0,
 	.confirm = generic_pipe_buf_confirm,
 	.release = anon_pipe_buf_release,
-	.steal = generic_pipe_buf_steal,
+	.steal = anon_pipe_buf_steal,
 	.get = generic_pipe_buf_get,
 };
 
@@ -405,7 +422,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 			int copied;
 
 			if (!page) {
-				page = alloc_page(GFP_HIGHUSER);
+				page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT);
 				if (unlikely(!page)) {
 					ret = ret ? : -ENOMEM;
 					break;
@@ -611,7 +628,7 @@ struct pipe_inode_info *alloc_pipe_info(void)
 {
 	struct pipe_inode_info *pipe;
 
-	pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
+	pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT);
 	if (pipe) {
 		unsigned long pipe_bufs = PIPE_DEF_BUFFERS;
 		struct user_struct *user = get_current_user();
@@ -619,7 +636,9 @@ struct pipe_inode_info *alloc_pipe_info(void)
 		if (!too_many_pipe_buffers_hard(user)) {
 			if (too_many_pipe_buffers_soft(user))
 				pipe_bufs = 1;
-			pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * pipe_bufs, GFP_KERNEL);
+			pipe->bufs = kcalloc(pipe_bufs,
+					     sizeof(struct pipe_buffer),
+					     GFP_KERNEL_ACCOUNT);
 		}
 
 		if (pipe->bufs) {
@@ -1010,7 +1029,8 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
 	if (nr_pages < pipe->nrbufs)
 		return -EBUSY;
 
-	bufs = kcalloc(nr_pages, sizeof(*bufs), GFP_KERNEL | __GFP_NOWARN);
+	bufs = kcalloc(nr_pages, sizeof(*bufs),
+		       GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
 	if (unlikely(!bufs))
 		return -ENOMEM;
 

fs/proc/meminfo.c

@@ -105,6 +105,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		"AnonHugePages:  %8lu kB\n"
+		"ShmemHugePages: %8lu kB\n"
+		"ShmemPmdMapped: %8lu kB\n"
 #endif
 #ifdef CONFIG_CMA
 		"CmaTotal:       %8lu kB\n"
@@ -162,8 +164,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		, atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		, K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
-		   HPAGE_PMD_NR)
+		, K(global_page_state(NR_ANON_THPS) * HPAGE_PMD_NR)
+		, K(global_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR)
+		, K(global_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR)
 #endif
 #ifdef CONFIG_CMA
 		, K(totalcma_pages)

fs/proc/task_mmu.c

@@ -448,6 +448,7 @@ struct mem_size_stats {
 	unsigned long referenced;
 	unsigned long anonymous;
 	unsigned long anonymous_thp;
+	unsigned long shmem_thp;
 	unsigned long swap;
 	unsigned long shared_hugetlb;
 	unsigned long private_hugetlb;
@@ -576,7 +577,12 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 	page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
 	if (IS_ERR_OR_NULL(page))
 		return;
-	mss->anonymous_thp += HPAGE_PMD_SIZE;
+	if (PageAnon(page))
+		mss->anonymous_thp += HPAGE_PMD_SIZE;
+	else if (PageSwapBacked(page))
+		mss->shmem_thp += HPAGE_PMD_SIZE;
+	else
+		VM_BUG_ON_PAGE(1, page);
 	smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
 }
 #else
@@ -770,6 +776,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   "Referenced:     %8lu kB\n"
 		   "Anonymous:      %8lu kB\n"
 		   "AnonHugePages:  %8lu kB\n"
+		   "ShmemPmdMapped: %8lu kB\n"
 		   "Shared_Hugetlb: %8lu kB\n"
 		   "Private_Hugetlb: %7lu kB\n"
 		   "Swap:           %8lu kB\n"
@@ -787,6 +794,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   mss.referenced >> 10,
 		   mss.anonymous >> 10,
 		   mss.anonymous_thp >> 10,
+		   mss.shmem_thp >> 10,
 		   mss.shared_hugetlb >> 10,
 		   mss.private_hugetlb >> 10,
 		   mss.swap >> 10,

fs/super.c

@@ -206,6 +206,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	mutex_init(&s->s_sync_lock);
 	INIT_LIST_HEAD(&s->s_inodes);
 	spin_lock_init(&s->s_inode_list_lock);
+	INIT_LIST_HEAD(&s->s_inodes_wb);
+	spin_lock_init(&s->s_inode_wblist_lock);
 
 	if (list_lru_init_memcg(&s->s_dentry_lru))
 		goto fail;

fs/userfaultfd.c

@@ -257,10 +257,9 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
  * fatal_signal_pending()s, and the mmap_sem must be released before
  * returning it.
  */
-int handle_userfault(struct vm_area_struct *vma, unsigned long address,
-		     unsigned int flags, unsigned long reason)
+int handle_userfault(struct fault_env *fe, unsigned long reason)
 {
-	struct mm_struct *mm = vma->vm_mm;
+	struct mm_struct *mm = fe->vma->vm_mm;
 	struct userfaultfd_ctx *ctx;
 	struct userfaultfd_wait_queue uwq;
 	int ret;
@@ -269,7 +268,7 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 	BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
 	ret = VM_FAULT_SIGBUS;
-	ctx = vma->vm_userfaultfd_ctx.ctx;
+	ctx = fe->vma->vm_userfaultfd_ctx.ctx;
 	if (!ctx)
 		goto out;
 
@@ -302,17 +301,17 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 	 * without first stopping userland access to the memory. For
 	 * VM_UFFD_MISSING userfaults this is enough for now.
 	 */
-	if (unlikely(!(flags & FAULT_FLAG_ALLOW_RETRY))) {
+	if (unlikely(!(fe->flags & FAULT_FLAG_ALLOW_RETRY))) {
 		/*
 		 * Validate the invariant that nowait must allow retry
 		 * to be sure not to return SIGBUS erroneously on
 		 * nowait invocations.
 		 */
-		BUG_ON(flags & FAULT_FLAG_RETRY_NOWAIT);
+		BUG_ON(fe->flags & FAULT_FLAG_RETRY_NOWAIT);
 #ifdef CONFIG_DEBUG_VM
 		if (printk_ratelimit()) {
 			printk(KERN_WARNING
-			       "FAULT_FLAG_ALLOW_RETRY missing %x\n", flags);
+			       "FAULT_FLAG_ALLOW_RETRY missing %x\n", fe->flags);
 			dump_stack();
 		}
 #endif
@@ -324,7 +323,7 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 	 * and wait.
 	 */
 	ret = VM_FAULT_RETRY;
-	if (flags & FAULT_FLAG_RETRY_NOWAIT)
+	if (fe->flags & FAULT_FLAG_RETRY_NOWAIT)
 		goto out;
 
 	/* take the reference before dropping the mmap_sem */
@@ -332,10 +331,11 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 
 	init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
 	uwq.wq.private = current;
-	uwq.msg = userfault_msg(address, flags, reason);
+	uwq.msg = userfault_msg(fe->address, fe->flags, reason);
 	uwq.ctx = ctx;
 
-	return_to_userland = (flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
+	return_to_userland =
+		(fe->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
 		(FAULT_FLAG_USER|FAULT_FLAG_KILLABLE);
 
 	spin_lock(&ctx->fault_pending_wqh.lock);
@@ -353,7 +353,7 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 			  TASK_KILLABLE);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
-	must_wait = userfaultfd_must_wait(ctx, address, flags, reason);
+	must_wait = userfaultfd_must_wait(ctx, fe->address, fe->flags, reason);
 	up_read(&mm->mmap_sem);
 
 	if (likely(must_wait && !ACCESS_ONCE(ctx->released) &&

fs/xfs/xfs_file.c

@@ -1551,7 +1551,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault);
+		ret = dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault);
 	} else {
 		ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
 		ret = block_page_mkwrite_return(ret);
@@ -1585,7 +1585,7 @@ xfs_filemap_fault(
 		 * changes to xfs_get_blocks_direct() to map unwritten extent
 		 * ioend for conversion on read-only mappings.
 		 */
-		ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault);
+		ret = dax_fault(vma, vmf, xfs_get_blocks_dax_fault);
 	} else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1622,7 +1622,7 @@ xfs_filemap_pmd_fault(
 	}
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault);
+	ret = dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (flags & FAULT_FLAG_WRITE)

include/asm-generic/tlb.h

@@ -107,6 +107,12 @@ struct mmu_gather {
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
 	unsigned int		batch_count;
+	/*
+	 * __tlb_adjust_range  will track the new addr here,
+	 * that that we can adjust the range after the flush
+	 */
+	unsigned long addr;
+	int page_size;
 };
 
 #define HAVE_GENERIC_MMU_GATHER
@@ -115,23 +121,20 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
 void tlb_flush_mmu(struct mmu_gather *tlb);
 void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start,
 							unsigned long end);
-int __tlb_remove_page(struct mmu_gather *tlb, struct page *page);
-
-/* tlb_remove_page
- *	Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
- *	required.
- */
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	if (!__tlb_remove_page(tlb, page))
-		tlb_flush_mmu(tlb);
-}
+extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
+				   int page_size);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
 				      unsigned long address)
 {
 	tlb->start = min(tlb->start, address);
 	tlb->end = max(tlb->end, address + PAGE_SIZE);
+	/*
+	 * Track the last address with which we adjusted the range. This
+	 * will be used later to adjust again after a mmu_flush due to
+	 * failed __tlb_remove_page
+	 */
+	tlb->addr = address;
 }
 
 static inline void __tlb_reset_range(struct mmu_gather *tlb)
@@ -144,6 +147,40 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	}
 }
 
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	if (__tlb_remove_page_size(tlb, page, page_size)) {
+		tlb_flush_mmu(tlb);
+		tlb->page_size = page_size;
+		__tlb_adjust_range(tlb, tlb->addr);
+		__tlb_remove_page_size(tlb, page, page_size);
+	}
+}
+
+static bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	return __tlb_remove_page_size(tlb, page, PAGE_SIZE);
+}
+
+/* tlb_remove_page
+ *	Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
+ *	required.
+ */
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	return tlb_remove_page_size(tlb, page, PAGE_SIZE);
+}
+
+static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page)
+{
+	/* active->nr should be zero when we call this */
+	VM_BUG_ON_PAGE(tlb->active->nr, page);
+	tlb->page_size = PAGE_SIZE;
+	__tlb_adjust_range(tlb, tlb->addr);
+	return __tlb_remove_page(tlb, page);
+}
+
 /*
  * In the case of tlb vma handling, we can optimise these away in the
  * case where we're doing a full MM flush.  When we're doing a munmap,

include/linux/balloon_compaction.h

@@ -48,6 +48,7 @@
 #include <linux/migrate.h>
 #include <linux/gfp.h>
 #include <linux/err.h>
+#include <linux/fs.h>
 
 /*
  * Balloon device information descriptor.
@@ -62,6 +63,7 @@ struct balloon_dev_info {
 	struct list_head pages;		/* Pages enqueued & handled to Host */
 	int (*migratepage)(struct balloon_dev_info *, struct page *newpage,
 			struct page *page, enum migrate_mode mode);
+	struct inode *inode;
 };
 
 extern struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info);
@@ -73,44 +75,18 @@ static inline void balloon_devinfo_init(struct balloon_dev_info *balloon)
 	spin_lock_init(&balloon->pages_lock);
 	INIT_LIST_HEAD(&balloon->pages);
 	balloon->migratepage = NULL;
+	balloon->inode = NULL;
 }
 
 #ifdef CONFIG_BALLOON_COMPACTION
-extern bool balloon_page_isolate(struct page *page);
+extern const struct address_space_operations balloon_aops;
+extern bool balloon_page_isolate(struct page *page,
+				isolate_mode_t mode);
 extern void balloon_page_putback(struct page *page);
-extern int balloon_page_migrate(struct page *newpage,
+extern int balloon_page_migrate(struct address_space *mapping,
+				struct page *newpage,
 				struct page *page, enum migrate_mode mode);
 
-/*
- * __is_movable_balloon_page - helper to perform @page PageBalloon tests
- */
-static inline bool __is_movable_balloon_page(struct page *page)
-{
-	return PageBalloon(page);
-}
-
-/*
- * balloon_page_movable - test PageBalloon to identify balloon pages
- *			  and PagePrivate to check that the page is not
- *			  isolated and can be moved by compaction/migration.
- *
- * As we might return false positives in the case of a balloon page being just
- * released under us, this need to be re-tested later, under the page lock.
- */
-static inline bool balloon_page_movable(struct page *page)
-{
-	return PageBalloon(page) && PagePrivate(page);
-}
-
-/*
- * isolated_balloon_page - identify an isolated balloon page on private
- *			   compaction/migration page lists.
- */
-static inline bool isolated_balloon_page(struct page *page)
-{
-	return PageBalloon(page);
-}
-
 /*
  * balloon_page_insert - insert a page into the balloon's page list and make
  *			 the page->private assignment accordingly.
@@ -124,7 +100,7 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon,
 				       struct page *page)
 {
 	__SetPageBalloon(page);
-	SetPagePrivate(page);
+	__SetPageMovable(page, balloon->inode->i_mapping);
 	set_page_private(page, (unsigned long)balloon);
 	list_add(&page->lru, &balloon->pages);
 }
@@ -140,11 +116,14 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon,
 static inline void balloon_page_delete(struct page *page)
 {
 	__ClearPageBalloon(page);
+	__ClearPageMovable(page);
 	set_page_private(page, 0);
-	if (PagePrivate(page)) {
-		ClearPagePrivate(page);
+	/*
+	 * No touch page.lru field once @page has been isolated
+	 * because VM is using the field.
+	 */
+	if (!PageIsolated(page))
 		list_del(&page->lru);
-	}
 }
 
 /*