Merge tag 'v3.16' into next

Linux 3.16

1 files changed, 157 insertions, 246 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 088358c8006..900edfaf6df 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -742,7 +742,7 @@ void unlock_page(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	clear_bit_unlock(PG_locked, &page->flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_page(page, PG_locked);
 }
 EXPORT_SYMBOL(unlock_page);
@@ -753,17 +753,51 @@ EXPORT_SYMBOL(unlock_page);
  */
 void end_page_writeback(struct page *page)
 {
-	if (TestClearPageReclaim(page))
+	/*
+	 * TestClearPageReclaim could be used here but it is an atomic
+	 * operation and overkill in this particular case. Failing to
+	 * shuffle a page marked for immediate reclaim is too mild to
+	 * justify taking an atomic operation penalty at the end of
+	 * ever page writeback.
+	 */
+	if (PageReclaim(page)) {
+		ClearPageReclaim(page);
 		rotate_reclaimable_page(page);
+	}
 
 	if (!test_clear_page_writeback(page))
 		BUG();
 
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_page(page, PG_writeback);
 }
 EXPORT_SYMBOL(end_page_writeback);
 
+/*
+ * After completing I/O on a page, call this routine to update the page
+ * flags appropriately
+ */
+void page_endio(struct page *page, int rw, int err)
+{
+	if (rw == READ) {
+		if (!err) {
+			SetPageUptodate(page);
+		} else {
+			ClearPageUptodate(page);
+			SetPageError(page);
+		}
+		unlock_page(page);
+	} else { /* rw == WRITE */
+		if (err) {
+			SetPageError(page);
+			if (page->mapping)
+				mapping_set_error(page->mapping, err);
+		}
+		end_page_writeback(page);
+	}
+}
+EXPORT_SYMBOL_GPL(page_endio);
+
 /**
  * __lock_page - get a lock on the page, assuming we need to sleep to get it
  * @page: the page to lock
@@ -957,26 +991,6 @@ out:
 EXPORT_SYMBOL(find_get_entry);
 
 /**
- * find_get_page - find and get a page reference
- * @mapping: the address_space to search
- * @offset: the page index
- *
- * Looks up the page cache slot at @mapping & @offset.  If there is a
- * page cache page, it is returned with an increased refcount.
- *
- * Otherwise, %NULL is returned.
- */
-struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
-{
-	struct page *page = find_get_entry(mapping, offset);
-
-	if (radix_tree_exceptional_entry(page))
-		page = NULL;
-	return page;
-}
-EXPORT_SYMBOL(find_get_page);
-
-/**
  * find_lock_entry - locate, pin and lock a page cache entry
  * @mapping: the address_space to search
  * @offset: the page cache index
@@ -1013,66 +1027,87 @@ repeat:
 EXPORT_SYMBOL(find_lock_entry);
 
 /**
- * find_lock_page - locate, pin and lock a pagecache page
+ * pagecache_get_page - find and get a page reference
  * @mapping: the address_space to search
  * @offset: the page index
+ * @fgp_flags: PCG flags
+ * @cache_gfp_mask: gfp mask to use for the page cache data page allocation
+ * @radix_gfp_mask: gfp mask to use for radix tree node allocation
  *
- * Looks up the page cache slot at @mapping & @offset.  If there is a
- * page cache page, it is returned locked and with an increased
- * refcount.
- *
- * Otherwise, %NULL is returned.
- *
- * find_lock_page() may sleep.
- */
-struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
-{
-	struct page *page = find_lock_entry(mapping, offset);
-
-	if (radix_tree_exceptional_entry(page))
-		page = NULL;
-	return page;
-}
-EXPORT_SYMBOL(find_lock_page);
-
-/**
- * find_or_create_page - locate or add a pagecache page
- * @mapping: the page's address_space
- * @index: the page's index into the mapping
- * @gfp_mask: page allocation mode
+ * Looks up the page cache slot at @mapping & @offset.
  *
- * Looks up the page cache slot at @mapping & @offset.  If there is a
- * page cache page, it is returned locked and with an increased
- * refcount.
+ * PCG flags modify how the page is returned.
  *
- * If the page is not present, a new page is allocated using @gfp_mask
- * and added to the page cache and the VM's LRU list.  The page is
- * returned locked and with an increased refcount.
+ * FGP_ACCESSED: the page will be marked accessed
+ * FGP_LOCK: Page is return locked
+ * FGP_CREAT: If page is not present then a new page is allocated using
+ *		@cache_gfp_mask and added to the page cache and the VM's LRU
+ *		list. If radix tree nodes are allocated during page cache
+ *		insertion then @radix_gfp_mask is used. The page is returned
+ *		locked and with an increased refcount. Otherwise, %NULL is
+ *		returned.
  *
- * On memory exhaustion, %NULL is returned.
+ * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
+ * if the GFP flags specified for FGP_CREAT are atomic.
  *
- * find_or_create_page() may sleep, even if @gfp_flags specifies an
- * atomic allocation!
+ * If there is a page cache page, it is returned with an increased refcount.
  */
-struct page *find_or_create_page(struct address_space *mapping,
-		pgoff_t index, gfp_t gfp_mask)
+struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
+	int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask)
 {
 	struct page *page;
-	int err;
+
 repeat:
-	page = find_lock_page(mapping, index);
-	if (!page) {
-		page = __page_cache_alloc(gfp_mask);
+	page = find_get_entry(mapping, offset);
+	if (radix_tree_exceptional_entry(page))
+		page = NULL;
+	if (!page)
+		goto no_page;
+
+	if (fgp_flags & FGP_LOCK) {
+		if (fgp_flags & FGP_NOWAIT) {
+			if (!trylock_page(page)) {
+				page_cache_release(page);
+				return NULL;
+			}
+		} else {
+			lock_page(page);
+		}
+
+		/* Has the page been truncated? */
+		if (unlikely(page->mapping != mapping)) {
+			unlock_page(page);
+			page_cache_release(page);
+			goto repeat;
+		}
+		VM_BUG_ON_PAGE(page->index != offset, page);
+	}
+
+	if (page && (fgp_flags & FGP_ACCESSED))
+		mark_page_accessed(page);
+
+no_page:
+	if (!page && (fgp_flags & FGP_CREAT)) {
+		int err;
+		if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping))
+			cache_gfp_mask |= __GFP_WRITE;
+		if (fgp_flags & FGP_NOFS) {
+			cache_gfp_mask &= ~__GFP_FS;
+			radix_gfp_mask &= ~__GFP_FS;
+		}
+
+		page = __page_cache_alloc(cache_gfp_mask);
 		if (!page)
 			return NULL;
-		/*
-		 * We want a regular kernel memory (not highmem or DMA etc)
-		 * allocation for the radix tree nodes, but we need to honour
-		 * the context-specific requirements the caller has asked for.
-		 * GFP_RECLAIM_MASK collects those requirements.
-		 */
-		err = add_to_page_cache_lru(page, mapping, index,
-			(gfp_mask & GFP_RECLAIM_MASK));
+
+		if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK)))
+			fgp_flags |= FGP_LOCK;
+
+		/* Init accessed so avoit atomic mark_page_accessed later */
+		if (fgp_flags & FGP_ACCESSED)
+			init_page_accessed(page);
+
+		err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask);
 		if (unlikely(err)) {
 			page_cache_release(page);
 			page = NULL;
@@ -1080,9 +1115,10 @@ repeat:
 				goto repeat;
 		}
 	}
+
 	return page;
 }
-EXPORT_SYMBOL(find_or_create_page);
+EXPORT_SYMBOL(pagecache_get_page);
 
 /**
  * find_get_entries - gang pagecache lookup
@@ -1379,39 +1415,6 @@ repeat:
 }
 EXPORT_SYMBOL(find_get_pages_tag);
 
-/**
- * grab_cache_page_nowait - returns locked page at given index in given cache
- * @mapping: target address_space
- * @index: the page index
- *
- * Same as grab_cache_page(), but do not wait if the page is unavailable.
- * This is intended for speculative data generators, where the data can
- * be regenerated if the page couldn't be grabbed.  This routine should
- * be safe to call while holding the lock for another page.
- *
- * Clear __GFP_FS when allocating the page to avoid recursion into the fs
- * and deadlock against the caller's locked page.
- */
-struct page *
-grab_cache_page_nowait(struct address_space *mapping, pgoff_t index)
-{
-	struct page *page = find_get_page(mapping, index);
-
-	if (page) {
-		if (trylock_page(page))
-			return page;
-		page_cache_release(page);
-		return NULL;
-	}
-	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS);
-	if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) {
-		page_cache_release(page);
-		page = NULL;
-	}
-	return page;
-}
-EXPORT_SYMBOL(grab_cache_page_nowait);
-
 /*
  * CD/DVDs are error prone. When a medium error occurs, the driver may fail
  * a _large_ part of the i/o request. Imagine the worst scenario:
@@ -1665,96 +1668,42 @@ out:
 	return written ? written : error;
 }
 
-/*
- * Performs necessary checks before doing a write
- * @iov:	io vector request
- * @nr_segs:	number of segments in the iovec
- * @count:	number of bytes to write
- * @access_flags: type of access: %VERIFY_READ or %VERIFY_WRITE
- *
- * Adjust number of segments and amount of bytes to write (nr_segs should be
- * properly initialized first). Returns appropriate error code that caller
- * should return or zero in case that write should be allowed.
- */
-int generic_segment_checks(const struct iovec *iov,
-			unsigned long *nr_segs, size_t *count, int access_flags)
-{
-	unsigned long   seg;
-	size_t cnt = 0;
-	for (seg = 0; seg < *nr_segs; seg++) {
-		const struct iovec *iv = &iov[seg];
-
-		/*
-		 * If any segment has a negative length, or the cumulative
-		 * length ever wraps negative then return -EINVAL.
-		 */
-		cnt += iv->iov_len;
-		if (unlikely((ssize_t)(cnt|iv->iov_len) < 0))
-			return -EINVAL;
-		if (access_ok(access_flags, iv->iov_base, iv->iov_len))
-			continue;
-		if (seg == 0)
-			return -EFAULT;
-		*nr_segs = seg;
-		cnt -= iv->iov_len;	/* This segment is no good */
-		break;
-	}
-	*count = cnt;
-	return 0;
-}
-EXPORT_SYMBOL(generic_segment_checks);
-
 /**
- * generic_file_aio_read - generic filesystem read routine
+ * generic_file_read_iter - generic filesystem read routine
  * @iocb:	kernel I/O control block
- * @iov:	io vector request
- * @nr_segs:	number of segments in the iovec
- * @pos:	current file position
+ * @iter:	destination for the data read
  *
- * This is the "read()" routine for all filesystems
+ * This is the "read_iter()" routine for all filesystems
  * that can use the page cache directly.
  */
 ssize_t
-generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos)
+generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
-	struct file *filp = iocb->ki_filp;
-	ssize_t retval;
-	size_t count;
+	struct file *file = iocb->ki_filp;
+	ssize_t retval = 0;
 	loff_t *ppos = &iocb->ki_pos;
-	struct iov_iter i;
-
-	count = 0;
-	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
-	if (retval)
-		return retval;
-	iov_iter_init(&i, iov, nr_segs, count, 0);
+	loff_t pos = *ppos;
 
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
-	if (filp->f_flags & O_DIRECT) {
+	if (file->f_flags & O_DIRECT) {
+		struct address_space *mapping = file->f_mapping;
+		struct inode *inode = mapping->host;
+		size_t count = iov_iter_count(iter);
 		loff_t size;
-		struct address_space *mapping;
-		struct inode *inode;
 
-		mapping = filp->f_mapping;
-		inode = mapping->host;
 		if (!count)
 			goto out; /* skip atime */
 		size = i_size_read(inode);
 		retval = filemap_write_and_wait_range(mapping, pos,
-					pos + iov_length(iov, nr_segs) - 1);
+					pos + count - 1);
 		if (!retval) {
-			retval = mapping->a_ops->direct_IO(READ, iocb,
-							   iov, pos, nr_segs);
+			struct iov_iter data = *iter;
+			retval = mapping->a_ops->direct_IO(READ, iocb, &data, pos);
 		}
+
 		if (retval > 0) {
 			*ppos = pos + retval;
-			count -= retval;
-			/*
-			 * If we did a short DIO read we need to skip the
-			 * section of the iov that we've already read data into.
-			 */
-			iov_iter_advance(&i, retval);
+			iov_iter_advance(iter, retval);
 		}
 
 		/*
@@ -1765,17 +1714,17 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 		 * and return.  Otherwise fallthrough to buffered io for
 		 * the rest of the read.
 		 */
-		if (retval < 0 || !count || *ppos >= size) {
-			file_accessed(filp);
+		if (retval < 0 || !iov_iter_count(iter) || *ppos >= size) {
+			file_accessed(file);
 			goto out;
 		}
 	}
 
-	retval = do_generic_file_read(filp, ppos, &i, retval);
+	retval = do_generic_file_read(file, ppos, iter, retval);
 out:
 	return retval;
 }
-EXPORT_SYMBOL(generic_file_aio_read);
+EXPORT_SYMBOL(generic_file_read_iter);
 
 #ifdef CONFIG_MMU
 /**
@@ -2381,15 +2330,12 @@ int pagecache_write_end(struct file *file, struct address_space *mapping,
 {
 	const struct address_space_operations *aops = mapping->a_ops;
 
-	mark_page_accessed(page);
 	return aops->write_end(file, mapping, pos, len, copied, page, fsdata);
 }
 EXPORT_SYMBOL(pagecache_write_end);
 
 ssize_t
-generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long *nr_segs, loff_t pos,
-		size_t count, size_t ocount)
+generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
 {
 	struct file	*file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
@@ -2397,11 +2343,9 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	ssize_t		written;
 	size_t		write_len;
 	pgoff_t		end;
+	struct iov_iter data;
 
-	if (count != ocount)
-		*nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count);
-
-	write_len = iov_length(iov, *nr_segs);
+	write_len = iov_iter_count(from);
 	end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT;
 
 	written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1);
@@ -2428,7 +2372,8 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 		}
 	}
 
-	written = mapping->a_ops->direct_IO(WRITE, iocb, iov, pos, *nr_segs);
+	data = *from;
+	written = mapping->a_ops->direct_IO(WRITE, iocb, &data, pos);
 
 	/*
 	 * Finally, try again to invalidate clean pages which might have been
@@ -2445,6 +2390,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 
 	if (written > 0) {
 		pos += written;
+		iov_iter_advance(from, written);
 		if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
 			i_size_write(inode, pos);
 			mark_inode_dirty(inode);
@@ -2463,34 +2409,18 @@ EXPORT_SYMBOL(generic_file_direct_write);
 struct page *grab_cache_page_write_begin(struct address_space *mapping,
 					pgoff_t index, unsigned flags)
 {
-	int status;
-	gfp_t gfp_mask;
 	struct page *page;
-	gfp_t gfp_notmask = 0;
+	int fgp_flags = FGP_LOCK|FGP_ACCESSED|FGP_WRITE|FGP_CREAT;
 
-	gfp_mask = mapping_gfp_mask(mapping);
-	if (mapping_cap_account_dirty(mapping))
-		gfp_mask |= __GFP_WRITE;
 	if (flags & AOP_FLAG_NOFS)
-		gfp_notmask = __GFP_FS;
-repeat:
-	page = find_lock_page(mapping, index);
+		fgp_flags |= FGP_NOFS;
+
+	page = pagecache_get_page(mapping, index, fgp_flags,
+			mapping_gfp_mask(mapping),
+			GFP_KERNEL);
 	if (page)
-		goto found;
+		wait_for_stable_page(page);
 
-	page = __page_cache_alloc(gfp_mask & ~gfp_notmask);
-	if (!page)
-		return NULL;
-	status = add_to_page_cache_lru(page, mapping, index,
-						GFP_KERNEL & ~gfp_notmask);
-	if (unlikely(status)) {
-		page_cache_release(page);
-		if (status == -EEXIST)
-			goto repeat;
-		return NULL;
-	}
-found:
-	wait_for_stable_page(page);
 	return page;
 }
 EXPORT_SYMBOL(grab_cache_page_write_begin);
@@ -2539,7 +2469,7 @@ again:
 
 		status = a_ops->write_begin(file, mapping, pos, bytes, flags,
 						&page, &fsdata);
-		if (unlikely(status))
+		if (unlikely(status < 0))
 			break;
 
 		if (mapping_writably_mapped(mapping))
@@ -2548,7 +2478,6 @@ again:
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
 		flush_dcache_page(page);
 
-		mark_page_accessed(page);
 		status = a_ops->write_end(file, mapping, pos, bytes, copied,
 						page, fsdata);
 		if (unlikely(status < 0))
@@ -2586,10 +2515,9 @@ again:
 EXPORT_SYMBOL(generic_perform_write);
 
 /**
- * __generic_file_aio_write - write data to a file
+ * __generic_file_write_iter - write data to a file
  * @iocb:	IO state structure (file, offset, etc.)
- * @iov:	vector with data to write
- * @nr_segs:	number of segments in the vector
+ * @from:	iov_iter with data to write
  *
  * This function does all the work needed for actually writing data to a
  * file. It does all basic checks, removes SUID from the file, updates
@@ -2603,26 +2531,16 @@ EXPORT_SYMBOL(generic_perform_write);
  * A caller has to handle it. This is mainly due to the fact that we want to
  * avoid syncing under i_mutex.
  */
-ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				 unsigned long nr_segs)
+ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space * mapping = file->f_mapping;
-	size_t ocount;		/* original count */
-	size_t count;		/* after file limit checks */
 	struct inode 	*inode = mapping->host;
 	loff_t		pos = iocb->ki_pos;
 	ssize_t		written = 0;
 	ssize_t		err;
 	ssize_t		status;
-	struct iov_iter from;
-
-	ocount = 0;
-	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
-	if (err)
-		return err;
-
-	count = ocount;
+	size_t		count = iov_iter_count(from);
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
@@ -2633,6 +2551,8 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (count == 0)
 		goto out;
 
+	iov_iter_truncate(from, count);
+
 	err = file_remove_suid(file);
 	if (err)
 		goto out;
@@ -2641,17 +2561,13 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (err)
 		goto out;
 
-	iov_iter_init(&from, iov, nr_segs, count, 0);
-
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (unlikely(file->f_flags & O_DIRECT)) {
 		loff_t endbyte;
 
-		written = generic_file_direct_write(iocb, iov, &from.nr_segs, pos,
-							count, ocount);
+		written = generic_file_direct_write(iocb, from, pos);
 		if (written < 0 || written == count)
 			goto out;
-		iov_iter_advance(&from, written);
 
 		/*
 		 * direct-io write to a hole: fall through to buffered I/O
@@ -2660,7 +2576,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		pos += written;
 		count -= written;
 
-		status = generic_perform_write(file, &from, pos);
+		status = generic_perform_write(file, from, pos);
 		/*
 		 * If generic_perform_write() returned a synchronous error
 		 * then we want to return the number of bytes which were
@@ -2692,7 +2608,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 			 */
 		}
 	} else {
-		written = generic_perform_write(file, &from, pos);
+		written = generic_perform_write(file, from, pos);
 		if (likely(written >= 0))
 			iocb->ki_pos = pos + written;
 	}
@@ -2700,30 +2616,25 @@ out:
 	current->backing_dev_info = NULL;
 	return written ? written : err;
 }
-EXPORT_SYMBOL(__generic_file_aio_write);
+EXPORT_SYMBOL(__generic_file_write_iter);
 
 /**
- * generic_file_aio_write - write data to a file
+ * generic_file_write_iter - write data to a file
  * @iocb:	IO state structure
- * @iov:	vector with data to write
- * @nr_segs:	number of segments in the vector
- * @pos:	position in file where to write
+ * @from:	iov_iter with data to write
  *
- * This is a wrapper around __generic_file_aio_write() to be used by most
+ * 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.
  */
-ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos)
+ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	ssize_t ret;
 
-	BUG_ON(iocb->ki_pos != pos);
-
 	mutex_lock(&inode->i_mutex);
-	ret = __generic_file_aio_write(iocb, iov, nr_segs);
+	ret = __generic_file_write_iter(iocb, from);
 	mutex_unlock(&inode->i_mutex);
 
 	if (ret > 0) {
@@ -2735,7 +2646,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	}
 	return ret;
 }
-EXPORT_SYMBOL(generic_file_aio_write);
+EXPORT_SYMBOL(generic_file_write_iter);
 
 /**
  * try_to_release_page() - release old fs-specific metadata on a page