1 files changed, 353 insertions, 258 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index d5e7c2029d16..c178022d7893 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -102,8 +102,8 @@
  *    ->swap_lock		(try_to_unmap_one)
  *    ->private_lock		(try_to_unmap_one)
  *    ->i_pages lock		(try_to_unmap_one)
- *    ->pgdat->lru_lock		(follow_page->mark_page_accessed)
- *    ->pgdat->lru_lock		(check_pte_range->isolate_lru_page)
+ *    ->lruvec->lru_lock	(follow_page->mark_page_accessed)
+ *    ->lruvec->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)
@@ -204,9 +204,9 @@ static void unaccount_page_cache_page(struct address_space *mapping,
 	if (PageSwapBacked(page)) {
 		__mod_lruvec_page_state(page, NR_SHMEM, -nr);
 		if (PageTransHuge(page))
-			__dec_node_page_state(page, NR_SHMEM_THPS);
+			__dec_lruvec_page_state(page, NR_SHMEM_THPS);
 	} else if (PageTransHuge(page)) {
-		__dec_node_page_state(page, NR_FILE_THPS);
+		__dec_lruvec_page_state(page, NR_FILE_THPS);
 		filemap_nr_thps_dec(mapping);
 	}
 
@@ -1484,11 +1484,19 @@ void end_page_writeback(struct page *page)
 		rotate_reclaimable_page(page);
 	}
 
+	/*
+	 * Writeback does not hold a page reference of its own, relying
+	 * on truncation to wait for the clearing of PG_writeback.
+	 * But here we must make sure that the page is not freed and
+	 * reused before the wake_up_page().
+	 */
+	get_page(page);
 	if (!test_clear_page_writeback(page))
 		BUG();
 
 	smp_mb__after_atomic();
 	wake_up_page(page, PG_writeback);
+	put_page(page);
 }
 EXPORT_SYMBOL(end_page_writeback);
 
@@ -1575,19 +1583,20 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 		else
 			wait_on_page_locked(page);
 		return 0;
-	} else {
-		if (flags & FAULT_FLAG_KILLABLE) {
-			int ret;
+	}
+	if (flags & FAULT_FLAG_KILLABLE) {
+		int ret;
 
-			ret = __lock_page_killable(page);
-			if (ret) {
-				mmap_read_unlock(mm);
-				return 0;
-			}
-		} else
-			__lock_page(page);
-		return 1;
+		ret = __lock_page_killable(page);
+		if (ret) {
+			mmap_read_unlock(mm);
+			return 0;
+		}
+	} else {
+		__lock_page(page);
 	}
+	return 1;
+
 }
 
 /**
@@ -2158,6 +2167,259 @@ static void shrink_readahead_size_eio(struct file_ra_state *ra)
 	ra->ra_pages /= 4;
 }
 
+static int lock_page_for_iocb(struct kiocb *iocb, struct page *page)
+{
+	if (iocb->ki_flags & IOCB_WAITQ)
+		return lock_page_async(page, iocb->ki_waitq);
+	else if (iocb->ki_flags & IOCB_NOWAIT)
+		return trylock_page(page) ? 0 : -EAGAIN;
+	else
+		return lock_page_killable(page);
+}
+
+static struct page *
+generic_file_buffered_read_readpage(struct kiocb *iocb,
+				    struct file *filp,
+				    struct address_space *mapping,
+				    struct page *page)
+{
+	struct file_ra_state *ra = &filp->f_ra;
+	int error;
+
+	if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT)) {
+		unlock_page(page);
+		put_page(page);
+		return ERR_PTR(-EAGAIN);
+	}
+
+	/*
+	 * A previous I/O error may have been due to temporary
+	 * failures, eg. multipath errors.
+	 * PG_error will be set again if readpage fails.
+	 */
+	ClearPageError(page);
+	/* Start the actual read. The read will unlock the page. */
+	error = mapping->a_ops->readpage(filp, page);
+
+	if (unlikely(error)) {
+		put_page(page);
+		return error != AOP_TRUNCATED_PAGE ? ERR_PTR(error) : NULL;
+	}
+
+	if (!PageUptodate(page)) {
+		error = lock_page_for_iocb(iocb, page);
+		if (unlikely(error)) {
+			put_page(page);
+			return ERR_PTR(error);
+		}
+		if (!PageUptodate(page)) {
+			if (page->mapping == NULL) {
+				/*
+				 * invalidate_mapping_pages got it
+				 */
+				unlock_page(page);
+				put_page(page);
+				return NULL;
+			}
+			unlock_page(page);
+			shrink_readahead_size_eio(ra);
+			put_page(page);
+			return ERR_PTR(-EIO);
+		}
+		unlock_page(page);
+	}
+
+	return page;
+}
+
+static struct page *
+generic_file_buffered_read_pagenotuptodate(struct kiocb *iocb,
+					   struct file *filp,
+					   struct iov_iter *iter,
+					   struct page *page,
+					   loff_t pos, loff_t count)
+{
+	struct address_space *mapping = filp->f_mapping;
+	struct inode *inode = mapping->host;
+	int error;
+
+	/*
+	 * See comment in do_read_cache_page on why
+	 * wait_on_page_locked is used to avoid unnecessarily
+	 * serialisations and why it's safe.
+	 */
+	if (iocb->ki_flags & IOCB_WAITQ) {
+		error = wait_on_page_locked_async(page,
+						iocb->ki_waitq);
+	} else {
+		error = wait_on_page_locked_killable(page);
+	}
+	if (unlikely(error)) {
+		put_page(page);
+		return ERR_PTR(error);
+	}
+	if (PageUptodate(page))
+		return page;
+
+	if (inode->i_blkbits == PAGE_SHIFT ||
+			!mapping->a_ops->is_partially_uptodate)
+		goto page_not_up_to_date;
+	/* pipes can't handle partially uptodate pages */
+	if (unlikely(iov_iter_is_pipe(iter)))
+		goto page_not_up_to_date;
+	if (!trylock_page(page))
+		goto page_not_up_to_date;
+	/* Did it get truncated before we got the lock? */
+	if (!page->mapping)
+		goto page_not_up_to_date_locked;
+	if (!mapping->a_ops->is_partially_uptodate(page,
+				pos & ~PAGE_MASK, count))
+		goto page_not_up_to_date_locked;
+	unlock_page(page);
+	return page;
+
+page_not_up_to_date:
+	/* Get exclusive access to the page ... */
+	error = lock_page_for_iocb(iocb, page);
+	if (unlikely(error)) {
+		put_page(page);
+		return ERR_PTR(error);
+	}
+
+page_not_up_to_date_locked:
+	/* Did it get truncated before we got the lock? */
+	if (!page->mapping) {
+		unlock_page(page);
+		put_page(page);
+		return NULL;
+	}
+
+	/* Did somebody else fill it already? */
+	if (PageUptodate(page)) {
+		unlock_page(page);
+		return page;
+	}
+
+	return generic_file_buffered_read_readpage(iocb, filp, mapping, page);
+}
+
+static struct page *
+generic_file_buffered_read_no_cached_page(struct kiocb *iocb,
+					  struct iov_iter *iter)
+{
+	struct file *filp = iocb->ki_filp;
+	struct address_space *mapping = filp->f_mapping;
+	pgoff_t index = iocb->ki_pos >> PAGE_SHIFT;
+	struct page *page;
+	int error;
+
+	if (iocb->ki_flags & IOCB_NOIO)
+		return ERR_PTR(-EAGAIN);
+
+	/*
+	 * Ok, it wasn't cached, so we need to create a new
+	 * page..
+	 */
+	page = page_cache_alloc(mapping);
+	if (!page)
+		return ERR_PTR(-ENOMEM);
+
+	error = add_to_page_cache_lru(page, mapping, index,
+				      mapping_gfp_constraint(mapping, GFP_KERNEL));
+	if (error) {
+		put_page(page);
+		return error != -EEXIST ? ERR_PTR(error) : NULL;
+	}
+
+	return generic_file_buffered_read_readpage(iocb, filp, mapping, page);
+}
+
+static int generic_file_buffered_read_get_pages(struct kiocb *iocb,
+						struct iov_iter *iter,
+						struct page **pages,
+						unsigned int nr)
+{
+	struct file *filp = iocb->ki_filp;
+	struct address_space *mapping = filp->f_mapping;
+	struct file_ra_state *ra = &filp->f_ra;
+	pgoff_t index = iocb->ki_pos >> PAGE_SHIFT;
+	pgoff_t last_index = (iocb->ki_pos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT;
+	int i, j, nr_got, err = 0;
+
+	nr = min_t(unsigned long, last_index - index, nr);
+find_page:
+	if (fatal_signal_pending(current))
+		return -EINTR;
+
+	nr_got = find_get_pages_contig(mapping, index, nr, pages);
+	if (nr_got)
+		goto got_pages;
+
+	if (iocb->ki_flags & IOCB_NOIO)
+		return -EAGAIN;
+
+	page_cache_sync_readahead(mapping, ra, filp, index, last_index - index);
+
+	nr_got = find_get_pages_contig(mapping, index, nr, pages);
+	if (nr_got)
+		goto got_pages;
+
+	pages[0] = generic_file_buffered_read_no_cached_page(iocb, iter);
+	err = PTR_ERR_OR_ZERO(pages[0]);
+	if (!IS_ERR_OR_NULL(pages[0]))
+		nr_got = 1;
+got_pages:
+	for (i = 0; i < nr_got; i++) {
+		struct page *page = pages[i];
+		pgoff_t pg_index = index + i;
+		loff_t pg_pos = max(iocb->ki_pos,
+				    (loff_t) pg_index << PAGE_SHIFT);
+		loff_t pg_count = iocb->ki_pos + iter->count - pg_pos;
+
+		if (PageReadahead(page)) {
+			if (iocb->ki_flags & IOCB_NOIO) {
+				for (j = i; j < nr_got; j++)
+					put_page(pages[j]);
+				nr_got = i;
+				err = -EAGAIN;
+				break;
+			}
+			page_cache_async_readahead(mapping, ra, filp, page,
+					pg_index, last_index - pg_index);
+		}
+
+		if (!PageUptodate(page)) {
+			if ((iocb->ki_flags & IOCB_NOWAIT) ||
+			    ((iocb->ki_flags & IOCB_WAITQ) && i)) {
+				for (j = i; j < nr_got; j++)
+					put_page(pages[j]);
+				nr_got = i;
+				err = -EAGAIN;
+				break;
+			}
+
+			page = generic_file_buffered_read_pagenotuptodate(iocb,
+					filp, iter, page, pg_pos, pg_count);
+			if (IS_ERR_OR_NULL(page)) {
+				for (j = i + 1; j < nr_got; j++)
+					put_page(pages[j]);
+				nr_got = i;
+				err = PTR_ERR_OR_ZERO(page);
+				break;
+			}
+		}
+	}
+
+	if (likely(nr_got))
+		return nr_got;
+	if (err)
+		return err;
+	/*
+	 * No pages and no error means we raced and should retry:
+	 */
+	goto find_page;
+}
+
 /**
  * generic_file_buffered_read - generic file read routine
  * @iocb:	the iocb to read
@@ -2178,284 +2440,117 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 		struct iov_iter *iter, ssize_t written)
 {
 	struct file *filp = iocb->ki_filp;
+	struct file_ra_state *ra = &filp->f_ra;
 	struct address_space *mapping = filp->f_mapping;
 	struct inode *inode = mapping->host;
-	struct file_ra_state *ra = &filp->f_ra;
-	loff_t *ppos = &iocb->ki_pos;
-	pgoff_t index;
-	pgoff_t last_index;
-	pgoff_t prev_index;
-	unsigned long offset;      /* offset into pagecache page */
-	unsigned int prev_offset;
-	int error = 0;
-
-	if (unlikely(*ppos >= inode->i_sb->s_maxbytes))
+	struct page *pages_onstack[PAGEVEC_SIZE], **pages = NULL;
+	unsigned int nr_pages = min_t(unsigned int, 512,
+			((iocb->ki_pos + iter->count + PAGE_SIZE - 1) >> PAGE_SHIFT) -
+			(iocb->ki_pos >> PAGE_SHIFT));
+	int i, pg_nr, error = 0;
+	bool writably_mapped;
+	loff_t isize, end_offset;
+
+	if (unlikely(iocb->ki_pos >= inode->i_sb->s_maxbytes))
 		return 0;
 	iov_iter_truncate(iter, inode->i_sb->s_maxbytes);
 
-	index = *ppos >> PAGE_SHIFT;
-	prev_index = ra->prev_pos >> PAGE_SHIFT;
-	prev_offset = ra->prev_pos & (PAGE_SIZE-1);
-	last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT;
-	offset = *ppos & ~PAGE_MASK;
-
-	/*
-	 * If we've already successfully copied some data, then we
-	 * can no longer safely return -EIOCBQUEUED. Hence mark
-	 * an async read NOWAIT at that point.
-	 */
-	if (written && (iocb->ki_flags & IOCB_WAITQ))
-		iocb->ki_flags |= IOCB_NOWAIT;
+	if (nr_pages > ARRAY_SIZE(pages_onstack))
+		pages = kmalloc_array(nr_pages, sizeof(void *), GFP_KERNEL);
 
-	for (;;) {
-		struct page *page;
-		pgoff_t end_index;
-		loff_t isize;
-		unsigned long nr, ret;
+	if (!pages) {
+		pages = pages_onstack;
+		nr_pages = min_t(unsigned int, nr_pages, ARRAY_SIZE(pages_onstack));
+	}
 
+	do {
 		cond_resched();
-find_page:
-		if (fatal_signal_pending(current)) {
-			error = -EINTR;
-			goto out;
-		}
 
-		page = find_get_page(mapping, index);
-		if (!page) {
-			if (iocb->ki_flags & IOCB_NOIO)
-				goto would_block;
-			page_cache_sync_readahead(mapping,
-					ra, filp,
-					index, last_index - index);
-			page = find_get_page(mapping, index);
-			if (unlikely(page == NULL))
-				goto no_cached_page;
-		}
-		if (PageReadahead(page)) {
-			if (iocb->ki_flags & IOCB_NOIO) {
-				put_page(page);
-				goto out;
-			}
-			page_cache_async_readahead(mapping,
-					ra, filp, page,
-					index, last_index - index);
-		}
-		if (!PageUptodate(page)) {
-			/*
-			 * See comment in do_read_cache_page on why
-			 * wait_on_page_locked is used to avoid unnecessarily
-			 * serialisations and why it's safe.
-			 */
-			if (iocb->ki_flags & IOCB_WAITQ) {
-				if (written) {
-					put_page(page);
-					goto out;
-				}
-				error = wait_on_page_locked_async(page,
-								iocb->ki_waitq);
-			} else {
-				if (iocb->ki_flags & IOCB_NOWAIT) {
-					put_page(page);
-					goto would_block;
-				}
-				error = wait_on_page_locked_killable(page);
-			}
-			if (unlikely(error))
-				goto readpage_error;
-			if (PageUptodate(page))
-				goto page_ok;
-
-			if (inode->i_blkbits == PAGE_SHIFT ||
-					!mapping->a_ops->is_partially_uptodate)
-				goto page_not_up_to_date;
-			/* pipes can't handle partially uptodate pages */
-			if (unlikely(iov_iter_is_pipe(iter)))
-				goto page_not_up_to_date;
-			if (!trylock_page(page))
-				goto page_not_up_to_date;
-			/* Did it get truncated before we got the lock? */
-			if (!page->mapping)
-				goto page_not_up_to_date_locked;
-			if (!mapping->a_ops->is_partially_uptodate(page,
-							offset, iter->count))
-				goto page_not_up_to_date_locked;
-			unlock_page(page);
+		/*
+		 * If we've already successfully copied some data, then we
+		 * can no longer safely return -EIOCBQUEUED. Hence mark
+		 * an async read NOWAIT at that point.
+		 */
+		if ((iocb->ki_flags & IOCB_WAITQ) && written)
+			iocb->ki_flags |= IOCB_NOWAIT;
+
+		i = 0;
+		pg_nr = generic_file_buffered_read_get_pages(iocb, iter,
+							     pages, nr_pages);
+		if (pg_nr < 0) {
+			error = pg_nr;
+			break;
 		}
-page_ok:
+
 		/*
-		 * i_size must be checked after we know the page is Uptodate.
+		 * i_size must be checked after we know the pages are Uptodate.
 		 *
 		 * Checking i_size after the check allows us to calculate
 		 * the correct value for "nr", which means the zero-filled
 		 * part of the page is not copied back to userspace (unless
 		 * another truncate extends the file - this is desired though).
 		 */
-
 		isize = i_size_read(inode);
-		end_index = (isize - 1) >> PAGE_SHIFT;
-		if (unlikely(!isize || index > end_index)) {
-			put_page(page);
-			goto out;
-		}
+		if (unlikely(iocb->ki_pos >= isize))
+			goto put_pages;
 
-		/* nr is the maximum number of bytes to copy from this page */
-		nr = PAGE_SIZE;
-		if (index == end_index) {
-			nr = ((isize - 1) & ~PAGE_MASK) + 1;
-			if (nr <= offset) {
-				put_page(page);
-				goto out;
-			}
-		}
-		nr = nr - offset;
+		end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count);
 
-		/* If users can be writing to this page using arbitrary
-		 * virtual addresses, take care about potential aliasing
-		 * before reading the page on the kernel side.
-		 */
-		if (mapping_writably_mapped(mapping))
-			flush_dcache_page(page);
+		while ((iocb->ki_pos >> PAGE_SHIFT) + pg_nr >
+		       (end_offset + PAGE_SIZE - 1) >> PAGE_SHIFT)
+			put_page(pages[--pg_nr]);
 
 		/*
-		 * When a sequential read accesses a page several times,
-		 * only mark it as accessed the first time.
+		 * Once we start copying data, we don't want to be touching any
+		 * cachelines that might be contended:
 		 */
-		if (prev_index != index || offset != prev_offset)
-			mark_page_accessed(page);
-		prev_index = index;
+		writably_mapped = mapping_writably_mapped(mapping);
 
 		/*
-		 * Ok, we have the page, and it's up-to-date, so
-		 * now we can copy it to user space...
+		 * When a sequential read accesses a page several times, only
+		 * mark it as accessed the first time.
 		 */
+		if (iocb->ki_pos >> PAGE_SHIFT !=
+		    ra->prev_pos >> PAGE_SHIFT)
+			mark_page_accessed(pages[0]);
+		for (i = 1; i < pg_nr; i++)
+			mark_page_accessed(pages[i]);
+
+		for (i = 0; i < pg_nr; i++) {
+			unsigned int offset = iocb->ki_pos & ~PAGE_MASK;
+			unsigned int bytes = min_t(loff_t, end_offset - iocb->ki_pos,
+						   PAGE_SIZE - offset);
+			unsigned int copied;
 
-		ret = copy_page_to_iter(page, offset, nr, iter);
-		offset += ret;
-		index += offset >> PAGE_SHIFT;
-		offset &= ~PAGE_MASK;
-		prev_offset = offset;
-
-		put_page(page);
-		written += ret;
-		if (!iov_iter_count(iter))
-			goto out;
-		if (ret < nr) {
-			error = -EFAULT;
-			goto out;
-		}
-		continue;
-
-page_not_up_to_date:
-		/* Get exclusive access to the page ... */
-		if (iocb->ki_flags & IOCB_WAITQ)
-			error = lock_page_async(page, iocb->ki_waitq);
-		else
-			error = lock_page_killable(page);
-		if (unlikely(error))
-			goto readpage_error;
-
-page_not_up_to_date_locked:
-		/* Did it get truncated before we got the lock? */
-		if (!page->mapping) {
-			unlock_page(page);
-			put_page(page);
-			continue;
-		}
-
-		/* Did somebody else fill it already? */
-		if (PageUptodate(page)) {
-			unlock_page(page);
-			goto page_ok;
-		}
+			/*
+			 * If users can be writing to this page using arbitrary
+			 * virtual addresses, take care about potential aliasing
+			 * before reading the page on the kernel side.
+			 */
+			if (writably_mapped)
+				flush_dcache_page(pages[i]);
 
-readpage:
-		if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT)) {
-			unlock_page(page);
-			put_page(page);
-			goto would_block;
-		}
-		/*
-		 * A previous I/O error may have been due to temporary
-		 * failures, eg. multipath errors.
-		 * PG_error will be set again if readpage fails.
-		 */
-		ClearPageError(page);
-		/* Start the actual read. The read will unlock the page. */
-		error = mapping->a_ops->readpage(filp, page);
+			copied = copy_page_to_iter(pages[i], offset, bytes, iter);
 
-		if (unlikely(error)) {
-			if (error == AOP_TRUNCATED_PAGE) {
-				put_page(page);
-				error = 0;
-				goto find_page;
-			}
-			goto readpage_error;
-		}
+			written += copied;
+			iocb->ki_pos += copied;
+			ra->prev_pos = iocb->ki_pos;
 
-		if (!PageUptodate(page)) {
-			if (iocb->ki_flags & IOCB_WAITQ)
-				error = lock_page_async(page, iocb->ki_waitq);
-			else
-				error = lock_page_killable(page);
-
-			if (unlikely(error))
-				goto readpage_error;
-			if (!PageUptodate(page)) {
-				if (page->mapping == NULL) {
-					/*
-					 * invalidate_mapping_pages got it
-					 */
-					unlock_page(page);
-					put_page(page);
-					goto find_page;
-				}
-				unlock_page(page);
-				shrink_readahead_size_eio(ra);
-				error = -EIO;
-				goto readpage_error;
+			if (copied < bytes) {
+				error = -EFAULT;
+				break;
 			}
-			unlock_page(page);
 		}
+put_pages:
+		for (i = 0; i < pg_nr; i++)
+			put_page(pages[i]);
+	} while (iov_iter_count(iter) && iocb->ki_pos < isize && !error);
 
-		goto page_ok;
-
-readpage_error:
-		/* UHHUH! A synchronous read error occurred. Report it */
-		put_page(page);
-		goto out;
-
-no_cached_page:
-		/*
-		 * Ok, it wasn't cached, so we need to create a new
-		 * page..
-		 */
-		page = page_cache_alloc(mapping);
-		if (!page) {
-			error = -ENOMEM;
-			goto out;
-		}
-		error = add_to_page_cache_lru(page, mapping, index,
-				mapping_gfp_constraint(mapping, GFP_KERNEL));
-		if (error) {
-			put_page(page);
-			if (error == -EEXIST) {
-				error = 0;
-				goto find_page;
-			}
-			goto out;
-		}
-		goto readpage;
-	}
+	file_accessed(filp);
 
-would_block:
-	error = -EAGAIN;
-out:
-	ra->prev_pos = prev_index;
-	ra->prev_pos <<= PAGE_SHIFT;
-	ra->prev_pos |= prev_offset;
+	if (pages != pages_onstack)
+		kfree(pages);
 
-	*ppos = ((loff_t)index << PAGE_SHIFT) + offset;
-	file_accessed(filp);
 	return written ? written : error;
 }
 EXPORT_SYMBOL_GPL(generic_file_buffered_read);