6 files changed, 84 insertions, 44 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index d9c37ec4c760..1b3c39a7de62 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -15,11 +15,14 @@ prototypes:
         int (*d_compare)(const struct dentry *, const struct dentry *,
                         unsigned int, const char *, const struct qstr *);
         int (*d_delete)(struct dentry *);
+        int (*d_init)(struct dentry *);
         void (*d_release)(struct dentry *);
         void (*d_iput)(struct dentry *, struct inode *);
         char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
         struct vfsmount *(*d_automount)(struct path *path);
         int (*d_manage)(struct dentry *, bool);
+        struct dentry *(*d_real)(struct dentry *, const struct inode *,
+                                 unsigned int);
 
 locking rules:
                 rename_lock     ->d_lock        may block       rcu-walk
@@ -28,12 +31,14 @@ d_weak_revalidate:no		no		yes	 	no
 d_hash          no              no              no              maybe
 d_compare:      yes             no              no              maybe
 d_delete:       no              yes             no              no
+d_init: no              no              yes             no
 d_release:      no              no              yes             no
 d_prune:        no              yes             no              no
 d_iput:         no              no              yes             no
 d_dname:        no              no              no              no
 d_automount:    no              no              yes             no
 d_manage:       no              no              yes (ref-walk)  maybe
+d_real          no              no              yes             no
 
 --------------------------- inode_operations --------------------------- 
 prototypes:
@@ -66,7 +71,6 @@ prototypes:
                                 struct file *, unsigned open_flag,
                                 umode_t create_mode, int *opened);
         int (*tmpfile) (struct inode *, struct dentry *, umode_t);
-        int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 
 locking rules:
         all may block
@@ -95,7 +99,6 @@ fiemap:		no
 update_time:    no
 atomic_open:    yes
 tmpfile:        no
-dentry_open:    no
 
         Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
@@ -179,7 +182,6 @@ unlocks and drops the reference.
 prototypes:
         int (*writepage)(struct page *page, struct writeback_control *wbc);
         int (*readpage)(struct file *, struct page *);
-        int (*sync_page)(struct page *);
         int (*writepages)(struct address_space *, struct writeback_control *);
         int (*set_page_dirty)(struct page *page);
         int (*readpages)(struct file *filp, struct address_space *mapping,
@@ -195,7 +197,9 @@ 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 *);
@@ -208,7 +212,6 @@ locking rules:
                         PageLocked(page)        i_mutex
 writepage:              yes, unlocks (see below)
 readpage:               yes, unlocks
-sync_page:              maybe
 writepages:
 set_page_dirty          no
 readpages:
@@ -219,15 +222,17 @@ 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
 swap_activate:          no
 swap_deactivate:        no
 
-        ->write_begin(), ->write_end(), ->sync_page() and ->readpage()
-may be called from the request handler (/dev/loop).
+        ->write_begin(), ->write_end() and ->readpage() may be called from
+the request handler (/dev/loop).
 
         ->readpage() unlocks the page, either synchronously or via I/O
 completion.
@@ -283,11 +288,6 @@ will leave the page itself marked clean but it will be tagged as dirty in the
 radix tree.  This incoherency can lead to all sorts of hard-to-debug problems
 in the filesystem like having dirty inodes at umount and losing written data.
 
-        ->sync_page() locking rules are not well-defined - usually it is called
-with lock on page, but that is not guaranteed. Considering the currently
-existing instances of this method ->sync_page() itself doesn't look
-well-defined...
-
         ->writepages() is used for periodic writeback and for syscall-initiated
 sync operations.  The address_space should start I/O against at least
 *nr_to_write pages.  *nr_to_write must be decremented for each page which is
@@ -544,13 +544,13 @@ 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
diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt
index ce4587d257d2..0c16a22521a8 100644
--- a/Documentation/filesystems/dax.txt
+++ b/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
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index e1c9f0849da6..ecd808088362 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -109,7 +109,9 @@ background_gc=%s       Turn on/off cleaning operations, namely garbage
 disable_roll_forward   Disable the roll-forward recovery routine
 norecovery             Disable the roll-forward recovery routine, mounted read-
                        only (i.e., -o ro,disable_roll_forward)
-discard                Issue discard/TRIM commands when a segment is cleaned.
+discard/nodiscard      Enable/disable real-time discard in f2fs, if discard is
+                       enabled, f2fs will issue discard/TRIM commands when a
+                       segment is cleaned.
 no_heap                Disable heap-style segment allocation which finds free
                        segments for data from the beginning of main area, while
                        for node from the end of main area.
@@ -151,6 +153,9 @@ noinline_data          Disable the inline data feature, inline data feature is
                        enabled by default.
 data_flush             Enable data flushing before checkpoint in order to
                        persist data of regular and symlink.
+mode=%s                Control block allocation mode which supports "adaptive"
+                       and "lfs". In "lfs" mode, there should be no random
+                       writes towards main area.
 
 ================================================================================
 DEBUGFS ENTRIES
diff --git a/Documentation/filesystems/ocfs2-online-filecheck.txt b/Documentation/filesystems/ocfs2-online-filecheck.txt
index 1ab07860430d..139fab175c8a 100644
--- a/Documentation/filesystems/ocfs2-online-filecheck.txt
+++ b/Documentation/filesystems/ocfs2-online-filecheck.txt
@@ -5,12 +5,12 @@ This document will describe OCFS2 online file check feature.
 
 Introduction
 ============
-OCFS2 is often used in high-availaibility systems. However, OCFS2 usually
+OCFS2 is often used in high-availability systems. However, OCFS2 usually
 converts the filesystem to read-only when encounters an error. This may not be
 necessary, since turning the filesystem read-only would affect other running
 processes as well, decreasing availability.
 Then, a mount option (errors=continue) is introduced, which would return the
--EIO errno to the calling process and terminate furhter processing so that the
+-EIO errno to the calling process and terminate further processing so that the
 filesystem is not corrupted further. The filesystem is not converted to
 read-only, and the problematic file's inode number is reported in the kernel
 log. The user can try to check/fix this file via online filecheck feature.
@@ -44,7 +44,7 @@ There is a sysfs directory for each OCFS2 file system mounting:
 
   /sys/fs/ocfs2/<devname>/filecheck
 
-Here, <devname> indicates the name of OCFS2 volumn device which has been already
+Here, <devname> indicates the name of OCFS2 volume device which has been already
 mounted. The file above would accept inode numbers. This could be used to
 communicate with kernel space, tell which file(inode number) will be checked or
 fixed. Currently, three operations are supported, which includes checking
@@ -76,14 +76,14 @@ The output is like this:
 This time, the <ERROR> column indicates whether this fix is successful or not.
 
 3. The record cache is used to store the history of check/fix results. It's
-defalut size is 10, and can be adjust between the range of 10 ~ 100. You can
+default size is 10, and can be adjust between the range of 10 ~ 100. You can
 adjust the size like this:
 
   # echo "<size>" > /sys/fs/ocfs2/<devname>/filecheck/set
 
 Fixing stuff
 ============
-On receivng the inode, the filesystem would read the inode and the
+On receiving the inode, the filesystem would read the inode and the
 file metadata. In case of errors, the filesystem would fix the errors
 and report the problems it fixed in the kernel log. As a precautionary measure,
 the inode must first be checked for errors before performing a final fix.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index e8d00759bfa5..68080ad6a75e 100644
--- a/Documentation/filesystems/proc.txt
+++ b/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.
@@ -725,7 +728,7 @@ IRQ, you can set it by doing:
   > echo 1 > /proc/irq/10/smp_affinity
 
 This means that only the first CPU will handle the IRQ, but you can also echo
-5 which means that only the first and fourth CPU can handle the IRQ.
+5 which means that only the first and third CPU can handle the IRQ.
 
 The contents of each smp_affinity file is the same by default:
 
@@ -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
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index c61a223ef3ff..8a196851f01d 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -364,7 +364,6 @@ struct inode_operations {
         int (*atomic_open)(struct inode *, struct dentry *, struct file *,
                         unsigned open_flag, umode_t create_mode, int *opened);
         int (*tmpfile) (struct inode *, struct dentry *, umode_t);
-        int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 };
 
 Again, all methods are called without any locks being held, unless
@@ -534,9 +533,7 @@ __sync_single_inode) to check if ->writepages has been successful in
 writing out the whole address_space.
 
 The Writeback tag is used by filemap*wait* and sync_page* functions,
-via filemap_fdatawait_range, to wait for all writeback to
-complete.  While waiting ->sync_page (if defined) will be called on
-each page that is found to require writeback.
+via filemap_fdatawait_range, to wait for all writeback to complete.
 
 An address_space handler may attach extra information to a page,
 typically using the 'private' field in the 'struct page'.  If such
@@ -554,8 +551,8 @@ address_space has finer control of write sizes.
 
 The read process essentially only requires 'readpage'.  The write
 process is more complicated and uses write_begin/write_end or
-set_page_dirty to write data into the address_space, and writepage,
-sync_page, and writepages to writeback data to storage.
+set_page_dirty to write data into the address_space, and writepage
+and writepages to writeback data to storage.
 
 Adding and removing pages to/from an address_space is protected by the
 inode's i_mutex.
@@ -592,9 +589,14 @@ 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 *);
@@ -696,13 +698,6 @@ struct address_space_operations {
         but instead uses bmap to find out where the blocks in the file
         are and uses those addresses directly.
 
-  dentry_open: *WARNING: probably going away soon, do not use!* This is an
-        alternative to f_op->open(), the difference is that this method may open
-        a file not necessarily originating from the same filesystem as the one
-        i_op->open() was called on.  It may be useful for stacking filesystems
-        which want to allow native I/O directly on underlying files.
-
-
   invalidatepage: If a page has PagePrivate set, then invalidatepage
         will be called when part or all of the page is to be removed
         from the address space.  This generally corresponds to either a
@@ -747,6 +742,10 @@ 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 +753,8 @@ 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.
@@ -933,11 +934,14 @@ struct dentry_operations {
         int (*d_compare)(const struct dentry *, const struct dentry *,
                         unsigned int, const char *, const struct qstr *);
         int (*d_delete)(const struct dentry *);
+        int (*d_init)(struct dentry *);
         void (*d_release)(struct dentry *);
         void (*d_iput)(struct dentry *, struct inode *);
         char *(*d_dname)(struct dentry *, char *, int);
         struct vfsmount *(*d_automount)(struct path *);
         int (*d_manage)(struct dentry *, bool);
+        struct dentry *(*d_real)(struct dentry *, const struct inode *,
+                                 unsigned int);
 };
 
   d_revalidate: called when the VFS needs to revalidate a dentry. This
@@ -1003,6 +1007,8 @@ struct dentry_operations {
         always cache a reachable dentry. d_delete must be constant and
         idempotent.
 
+  d_init: called when a dentry is allocated
+
   d_release: called when a dentry is really deallocated
 
   d_iput: called when a dentry loses its inode (just prior to its
@@ -1022,6 +1028,14 @@ struct dentry_operations {
         at the end of the buffer, and returns a pointer to the first char.
         dynamic_dname() helper function is provided to take care of this.
 
+        Example :
+
+        static char *pipefs_dname(struct dentry *dent, char *buffer, int buflen)
+        {
+                return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]",
+                                dentry->d_inode->i_ino);
+        }
+
   d_automount: called when an automount dentry is to be traversed (optional).
         This should create a new VFS mount record and return the record to the
         caller.  The caller is supplied with a path parameter giving the
@@ -1060,13 +1074,23 @@ struct dentry_operations {
         This function is only used if DCACHE_MANAGE_TRANSIT is set on the
         dentry being transited from.
 
-Example :
+  d_real: overlay/union type filesystems implement this method to return one of
+        the underlying dentries hidden by the overlay.  It is used in three
+        different modes:
 
-static char *pipefs_dname(struct dentry *dent, char *buffer, int buflen)
-{
-        return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]",
-                                dentry->d_inode->i_ino);
-}
+        Called from open it may need to copy-up the file depending on the
+        supplied open flags.  This mode is selected with a non-zero flags
+        argument.  In this mode the d_real method can return an error.
+
+        Called from file_dentry() it returns the real dentry matching the inode
+        argument.  The real dentry may be from a lower layer already copied up,
+        but still referenced from the file.  This mode is selected with a
+        non-NULL inode argument.  This will always succeed.
+
+        With NULL inode and zero flags the topmost real underlying dentry is
+        returned.  This will always succeed.
+
+        This method is never called with both non-NULL inode and non-zero flags.
 
 Each dentry has a pointer to its parent dentry, as well as a hash list
 of child dentries. Child dentries are basically like files in a