Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (159 commits)
  tools/testing/selftests/proc/proc-self-syscall.c: remove duplicate include
  proc: more robust bulk read test
  proc: test /proc/*/maps, smaps, smaps_rollup, statm
  proc: use seq_puts() everywhere
  proc: read kernel cpu stat pointer once
  proc: remove unused argument in proc_pid_lookup()
  fs/proc/thread_self.c: code cleanup for proc_setup_thread_self()
  fs/proc/self.c: code cleanup for proc_setup_self()
  proc: return exit code 4 for skipped tests
  mm,mremap: bail out earlier in mremap_to under map pressure
  mm/sparse: fix a bad comparison
  mm/memory.c: do_fault: avoid usage of stale vm_area_struct
  writeback: fix inode cgroup switching comment
  mm/huge_memory.c: fix "orig_pud" set but not used
  mm/hotplug: fix an imbalance with DEBUG_PAGEALLOC
  mm/memcontrol.c: fix bad line in comment
  mm/cma.c: cma_declare_contiguous: correct err handling
  mm/page_ext.c: fix an imbalance with kmemleak
  mm/compaction: pass pgdat to too_many_isolated() instead of zone
  mm: remove zone_lru_lock() function, access ->lru_lock directly
  ...

1 files changed, 67 insertions, 26 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 9f5e323e883e..a3b4021c448f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -98,8 +98,8 @@
  *    ->swap_lock               (try_to_unmap_one)
  *    ->private_lock            (try_to_unmap_one)
  *    ->i_pages lock            (try_to_unmap_one)
- *    ->zone_lru_lock(zone)     (follow_page->mark_page_accessed)
- *    ->zone_lru_lock(zone)     (check_pte_range->isolate_lru_page)
+ *    ->pgdat->lru_lock         (follow_page->mark_page_accessed)
+ *    ->pgdat->lru_lock         (check_pte_range->isolate_lru_page)
  *    ->private_lock            (page_remove_rmap->set_page_dirty)
  *    ->i_pages lock            (page_remove_rmap->set_page_dirty)
  *    bdi.wb->list_lock         (page_remove_rmap->set_page_dirty)
@@ -392,6 +392,8 @@ static int filemap_check_and_keep_errors(struct address_space *mapping)
  * opposed to a regular memory cleansing writeback.  The difference between
  * these two operations is that if a dirty page/buffer is encountered, it must
  * be waited upon, and not just skipped over.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
                                 loff_t end, int sync_mode)
@@ -438,6 +440,8 @@ EXPORT_SYMBOL(filemap_fdatawrite_range);
  *
  * This is a mostly non-blocking flush.  Not suitable for data-integrity
  * purposes - I/O may not be started against all dirty pages.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int filemap_flush(struct address_space *mapping)
 {
@@ -453,6 +457,9 @@ EXPORT_SYMBOL(filemap_flush);
  *
  * Find at least one page in the range supplied, usually used to check if
  * direct writing in this range will trigger a writeback.
+ *
+ * Return: %true if at least one page exists in the specified range,
+ * %false otherwise.
  */
 bool filemap_range_has_page(struct address_space *mapping,
                            loff_t start_byte, loff_t end_byte)
@@ -529,6 +536,8 @@ static void __filemap_fdatawait_range(struct address_space *mapping,
  * Since the error status of the address space is cleared by this function,
  * callers are responsible for checking the return value and handling and/or
  * reporting the error.
+ *
+ * Return: error status of the address space.
  */
 int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
                             loff_t end_byte)
@@ -551,6 +560,8 @@ EXPORT_SYMBOL(filemap_fdatawait_range);
  * Since the error status of the file is advanced by this function,
  * callers are responsible for checking the return value and handling and/or
  * reporting the error.
+ *
+ * Return: error status of the address space vs. the file->f_wb_err cursor.
  */
 int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte)
 {
@@ -572,6 +583,8 @@ EXPORT_SYMBOL(file_fdatawait_range);
  * Use this function if callers don't handle errors themselves.  Expected
  * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2),
  * fsfreeze(8)
+ *
+ * Return: error status of the address space.
  */
 int filemap_fdatawait_keep_errors(struct address_space *mapping)
 {
@@ -623,6 +636,8 @@ EXPORT_SYMBOL(filemap_write_and_wait);
  *
  * Note that @lend is inclusive (describes the last byte to be written) so
  * that this function can be used to write to the very end-of-file (end = -1).
+ *
+ * Return: error status of the address space.
  */
 int filemap_write_and_wait_range(struct address_space *mapping,
                                  loff_t lstart, loff_t lend)
@@ -678,6 +693,8 @@ EXPORT_SYMBOL(__filemap_set_wb_err);
  * While we handle mapping->wb_err with atomic operations, the f_wb_err
  * value is protected by the f_lock since we must ensure that it reflects
  * the latest value swapped in for this file descriptor.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int file_check_and_advance_wb_err(struct file *file)
 {
@@ -720,6 +737,8 @@ EXPORT_SYMBOL(file_check_and_advance_wb_err);
  *
  * After writing out and waiting on the data, we check and advance the
  * f_wb_err cursor to the latest value, and return any errors detected there.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend)
 {
@@ -753,6 +772,8 @@ EXPORT_SYMBOL(file_write_and_wait_range);
  * caller must do that.
  *
  * The remove + add is atomic.  This function cannot fail.
+ *
+ * Return: %0
  */
 int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 {
@@ -867,6 +888,8 @@ error:
  *
  * This function is used to add a page to the pagecache. It must be locked.
  * This function does not add the page to the LRU.  The caller must do that.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
                 pgoff_t offset, gfp_t gfp_mask)
@@ -1463,7 +1486,7 @@ EXPORT_SYMBOL(page_cache_prev_miss);
  * If the slot holds a shadow entry of a previously evicted page, or a
  * swap entry from shmem/tmpfs, it is returned.
  *
- * Otherwise, %NULL is returned.
+ * Return: the found page or shadow entry, %NULL if nothing is found.
  */
 struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
 {
@@ -1521,9 +1544,9 @@ EXPORT_SYMBOL(find_get_entry);
  * If the slot holds a shadow entry of a previously evicted page, or a
  * swap entry from shmem/tmpfs, it is returned.
  *
- * Otherwise, %NULL is returned.
- *
  * find_lock_entry() may sleep.
+ *
+ * Return: the found page or shadow entry, %NULL if nothing is found.
  */
 struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
 {
@@ -1563,12 +1586,14 @@ EXPORT_SYMBOL(find_lock_entry);
  * - FGP_CREAT: If page is not present then a new page is allocated using
  *   @gfp_mask and added to the page cache and the VM's LRU
  *   list. The page is returned locked and with an increased
- *   refcount. Otherwise, NULL is returned.
+ *   refcount.
  *
  * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
  * if the GFP flags specified for FGP_CREAT are atomic.
  *
  * If there is a page cache page, it is returned with an increased refcount.
+ *
+ * Return: the found page or %NULL otherwise.
  */
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
         int fgp_flags, gfp_t gfp_mask)
@@ -1656,8 +1681,7 @@ EXPORT_SYMBOL(pagecache_get_page);
  * Any shadow entries of evicted pages, or swap entries from
  * shmem/tmpfs, are included in the returned array.
  *
- * find_get_entries() returns the number of pages and shadow entries
- * which were found.
+ * Return: the number of pages and shadow entries which were found.
  */
 unsigned find_get_entries(struct address_space *mapping,
                           pgoff_t start, unsigned int nr_entries,
@@ -1727,8 +1751,8 @@ retry:
  * indexes.  There may be holes in the indices due to not-present pages.
  * We also update @start to index the next page for the traversal.
  *
- * find_get_pages_range() returns the number of pages which were found. If this
- * number is smaller than @nr_pages, the end of specified range has been
+ * Return: the number of pages which were found. If this number is
+ * smaller than @nr_pages, the end of specified range has been
  * reached.
  */
 unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
@@ -1765,7 +1789,7 @@ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
 
                 pages[ret] = page;
                 if (++ret == nr_pages) {
-                        *start = page->index + 1;
+                        *start = xas.xa_index + 1;
                         goto out;
                 }
                 continue;
@@ -1801,7 +1825,7 @@ out:
  * find_get_pages_contig() works exactly like find_get_pages(), except
  * that the returned number of pages are guaranteed to be contiguous.
  *
- * find_get_pages_contig() returns the number of pages which were found.
+ * Return: the number of pages which were found.
  */
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
                                unsigned int nr_pages, struct page **pages)
@@ -1837,16 +1861,6 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
                 if (unlikely(page != xas_reload(&xas)))
                         goto put_page;
 
-                /*
-                 * must check mapping and index after taking the ref.
-                 * otherwise we can get both false positives and false
-                 * negatives, which is just confusing to the caller.
-                 */
-                if (!page->mapping || page_to_pgoff(page) != xas.xa_index) {
-                        put_page(page);
-                        break;
-                }
-
                 pages[ret] = page;
                 if (++ret == nr_pages)
                         break;
@@ -1872,6 +1886,8 @@ EXPORT_SYMBOL(find_get_pages_contig);
  *
  * Like find_get_pages, except we only return pages which are tagged with
  * @tag.   We update @index to index the next page for the traversal.
+ *
+ * Return: the number of pages which were found.
  */
 unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
                         pgoff_t end, xa_mark_t tag, unsigned int nr_pages,
@@ -1911,7 +1927,7 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
 
                 pages[ret] = page;
                 if (++ret == nr_pages) {
-                        *index = page->index + 1;
+                        *index = xas.xa_index + 1;
                         goto out;
                 }
                 continue;
@@ -1949,6 +1965,8 @@ EXPORT_SYMBOL(find_get_pages_range_tag);
  *
  * Like find_get_entries, except we only return entries which are tagged with
  * @tag.
+ *
+ * Return: the number of entries which were found.
  */
 unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
                         xa_mark_t tag, unsigned int nr_entries,
@@ -2034,6 +2052,10 @@ static void shrink_readahead_size_eio(struct file *filp,
  *
  * This is really ugly. But the goto's actually try to clarify some
  * of the logic when it comes to error handling etc.
+ *
+ * Return:
+ * * total number of bytes copied, including those the were already @written
+ * * negative error code if nothing was copied
  */
 static ssize_t generic_file_buffered_read(struct kiocb *iocb,
                 struct iov_iter *iter, ssize_t written)
@@ -2295,6 +2317,9 @@ out:
  *
  * This is the "read_iter()" routine for all filesystems
  * that can use the page cache directly.
+ * Return:
+ * * number of bytes copied, even for partial reads
+ * * negative error code if nothing was read
  */
 ssize_t
 generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
@@ -2362,6 +2387,8 @@ EXPORT_SYMBOL(generic_file_read_iter);
  *
  * This adds the requested page to the page cache if it isn't already there,
  * and schedules an I/O to read in its contents from disk.
+ *
+ * Return: %0 on success, negative error code otherwise.
  */
 static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
 {
@@ -2476,6 +2503,8 @@ static void do_async_mmap_readahead(struct vm_area_struct *vma,
  * has not been released.
  *
  * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set.
+ *
+ * Return: bitwise-OR of %VM_FAULT_ codes.
  */
 vm_fault_t filemap_fault(struct vm_fault *vmf)
 {
@@ -2861,6 +2890,8 @@ out:
  * not set, try to fill the page and wait for it to become unlocked.
  *
  * If the page does not get brought uptodate, return -EIO.
+ *
+ * Return: up to date page on success, ERR_PTR() on failure.
  */
 struct page *read_cache_page(struct address_space *mapping,
                                 pgoff_t index,
@@ -2881,6 +2912,8 @@ EXPORT_SYMBOL(read_cache_page);
  * any new page allocations done using the specified allocation flags.
  *
  * If the page does not get brought uptodate, return -EIO.
+ *
+ * Return: up to date page on success, ERR_PTR() on failure.
  */
 struct page *read_cache_page_gfp(struct address_space *mapping,
                                 pgoff_t index,
@@ -3081,7 +3114,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
         if (iocb->ki_flags & IOCB_NOWAIT) {
                 /* If there are pages to writeback, return */
                 if (filemap_range_has_page(inode->i_mapping, pos,
-                                           pos + write_len))
+                                           pos + write_len - 1))
                         return -EAGAIN;
         } else {
                 written = filemap_write_and_wait_range(mapping, pos,
@@ -3264,6 +3297,10 @@ EXPORT_SYMBOL(generic_perform_write);
  * This function does *not* take care of syncing data in case of O_SYNC write.
  * A caller has to handle it. This is mainly due to the fact that we want to
  * avoid syncing under i_mutex.
+ *
+ * Return:
+ * * number of bytes written, even for truncated writes
+ * * negative error code if no data has been written at all
  */
 ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
@@ -3348,6 +3385,10 @@ EXPORT_SYMBOL(__generic_file_write_iter);
  * This is a wrapper around __generic_file_write_iter() to be used by most
  * filesystems. It takes care of syncing the file in case of O_SYNC file
  * and acquires i_mutex as needed.
+ * Return:
+ * * negative error code if no data has been written at all of
+ *   vfs_fsync_range() failed for a synchronous write
+ * * number of bytes written, even for truncated writes
  */
 ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
@@ -3374,8 +3415,7 @@ EXPORT_SYMBOL(generic_file_write_iter);
  * @gfp_mask: memory allocation flags (and I/O mode)
  *
  * The address_space is to try to release any data against the page
- * (presumably at page->private).  If the release was successful, return '1'.
- * Otherwise return zero.
+ * (presumably at page->private).
  *
  * This may also be called if PG_fscache is set on a page, indicating that the
  * page is known to the local caching routines.
@@ -3383,6 +3423,7 @@ EXPORT_SYMBOL(generic_file_write_iter);
  * The @gfp_mask argument specifies whether I/O may be performed to release
  * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS).
  *
+ * Return: %1 if the release was successful, otherwise return zero.
  */
 int try_to_release_page(struct page *page, gfp_t gfp_mask)
 {