1 files changed, 290 insertions, 61 deletions

diff --git a/mm/page_io.c b/mm/page_io.c
index 330e00d6db0..955db8b0d49 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -12,70 +12,217 @@
 
 #include <linux/mm.h>
 #include <linux/kernel_stat.h>
+#include <linux/gfp.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
 #include <linux/bio.h>
 #include <linux/swapops.h>
+#include <linux/buffer_head.h>
 #include <linux/writeback.h>
+#include <linux/frontswap.h>
+#include <linux/aio.h>
+#include <linux/blkdev.h>
 #include <asm/pgtable.h>
 
-static struct bio *get_swap_bio(gfp_t gfp_flags, pgoff_t index,
+static struct bio *get_swap_bio(gfp_t gfp_flags,
 				struct page *page, bio_end_io_t end_io)
 {
 	struct bio *bio;
 
 	bio = bio_alloc(gfp_flags, 1);
 	if (bio) {
-		struct swap_info_struct *sis;
-		swp_entry_t entry = { .val = index, };
-
-		sis = get_swap_info_struct(swp_type(entry));
-		bio->bi_sector = map_swap_page(sis, swp_offset(entry)) *
-					(PAGE_SIZE >> 9);
-		bio->bi_bdev = sis->bdev;
+		bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev);
+		bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
 		bio->bi_io_vec[0].bv_page = page;
 		bio->bi_io_vec[0].bv_len = PAGE_SIZE;
 		bio->bi_io_vec[0].bv_offset = 0;
 		bio->bi_vcnt = 1;
-		bio->bi_idx = 0;
-		bio->bi_size = PAGE_SIZE;
+		bio->bi_iter.bi_size = PAGE_SIZE;
 		bio->bi_end_io = end_io;
 	}
 	return bio;
 }
 
-static int end_swap_bio_write(struct bio *bio, unsigned int bytes_done, int err)
+void end_swap_bio_write(struct bio *bio, int err)
 {
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct page *page = bio->bi_io_vec[0].bv_page;
 
-	if (bio->bi_size)
-		return 1;
-
-	if (!uptodate)
+	if (!uptodate) {
 		SetPageError(page);
+		/*
+		 * We failed to write the page out to swap-space.
+		 * Re-dirty the page in order to avoid it being reclaimed.
+		 * Also print a dire warning that things will go BAD (tm)
+		 * very quickly.
+		 *
+		 * Also clear PG_reclaim to avoid rotate_reclaimable_page()
+		 */
+		set_page_dirty(page);
+		printk(KERN_ALERT "Write-error on swap-device (%u:%u:%Lu)\n",
+				imajor(bio->bi_bdev->bd_inode),
+				iminor(bio->bi_bdev->bd_inode),
+				(unsigned long long)bio->bi_iter.bi_sector);
+		ClearPageReclaim(page);
+	}
 	end_page_writeback(page);
 	bio_put(bio);
-	return 0;
 }
 
-static int end_swap_bio_read(struct bio *bio, unsigned int bytes_done, int err)
+void end_swap_bio_read(struct bio *bio, int err)
 {
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct page *page = bio->bi_io_vec[0].bv_page;
 
-	if (bio->bi_size)
-		return 1;
-
 	if (!uptodate) {
 		SetPageError(page);
 		ClearPageUptodate(page);
-	} else {
-		SetPageUptodate(page);
+		printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n",
+				imajor(bio->bi_bdev->bd_inode),
+				iminor(bio->bi_bdev->bd_inode),
+				(unsigned long long)bio->bi_iter.bi_sector);
+		goto out;
 	}
+
+	SetPageUptodate(page);
+
+	/*
+	 * There is no guarantee that the page is in swap cache - the software
+	 * suspend code (at least) uses end_swap_bio_read() against a non-
+	 * swapcache page.  So we must check PG_swapcache before proceeding with
+	 * this optimization.
+	 */
+	if (likely(PageSwapCache(page))) {
+		struct swap_info_struct *sis;
+
+		sis = page_swap_info(page);
+		if (sis->flags & SWP_BLKDEV) {
+			/*
+			 * The swap subsystem performs lazy swap slot freeing,
+			 * expecting that the page will be swapped out again.
+			 * So we can avoid an unnecessary write if the page
+			 * isn't redirtied.
+			 * This is good for real swap storage because we can
+			 * reduce unnecessary I/O and enhance wear-leveling
+			 * if an SSD is used as the as swap device.
+			 * But if in-memory swap device (eg zram) is used,
+			 * this causes a duplicated copy between uncompressed
+			 * data in VM-owned memory and compressed data in
+			 * zram-owned memory.  So let's free zram-owned memory
+			 * and make the VM-owned decompressed page *dirty*,
+			 * so the page should be swapped out somewhere again if
+			 * we again wish to reclaim it.
+			 */
+			struct gendisk *disk = sis->bdev->bd_disk;
+			if (disk->fops->swap_slot_free_notify) {
+				swp_entry_t entry;
+				unsigned long offset;
+
+				entry.val = page_private(page);
+				offset = swp_offset(entry);
+
+				SetPageDirty(page);
+				disk->fops->swap_slot_free_notify(sis->bdev,
+						offset);
+			}
+		}
+	}
+
+out:
 	unlock_page(page);
 	bio_put(bio);
-	return 0;
+}
+
+int generic_swapfile_activate(struct swap_info_struct *sis,
+				struct file *swap_file,
+				sector_t *span)
+{
+	struct address_space *mapping = swap_file->f_mapping;
+	struct inode *inode = mapping->host;
+	unsigned blocks_per_page;
+	unsigned long page_no;
+	unsigned blkbits;
+	sector_t probe_block;
+	sector_t last_block;
+	sector_t lowest_block = -1;
+	sector_t highest_block = 0;
+	int nr_extents = 0;
+	int ret;
+
+	blkbits = inode->i_blkbits;
+	blocks_per_page = PAGE_SIZE >> blkbits;
+
+	/*
+	 * Map all the blocks into the extent list.  This code doesn't try
+	 * to be very smart.
+	 */
+	probe_block = 0;
+	page_no = 0;
+	last_block = i_size_read(inode) >> blkbits;
+	while ((probe_block + blocks_per_page) <= last_block &&
+			page_no < sis->max) {
+		unsigned block_in_page;
+		sector_t first_block;
+
+		first_block = bmap(inode, probe_block);
+		if (first_block == 0)
+			goto bad_bmap;
+
+		/*
+		 * It must be PAGE_SIZE aligned on-disk
+		 */
+		if (first_block & (blocks_per_page - 1)) {
+			probe_block++;
+			goto reprobe;
+		}
+
+		for (block_in_page = 1; block_in_page < blocks_per_page;
+					block_in_page++) {
+			sector_t block;
+
+			block = bmap(inode, probe_block + block_in_page);
+			if (block == 0)
+				goto bad_bmap;
+			if (block != first_block + block_in_page) {
+				/* Discontiguity */
+				probe_block++;
+				goto reprobe;
+			}
+		}
+
+		first_block >>= (PAGE_SHIFT - blkbits);
+		if (page_no) {	/* exclude the header page */
+			if (first_block < lowest_block)
+				lowest_block = first_block;
+			if (first_block > highest_block)
+				highest_block = first_block;
+		}
+
+		/*
+		 * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
+		 */
+		ret = add_swap_extent(sis, page_no, 1, first_block);
+		if (ret < 0)
+			goto out;
+		nr_extents += ret;
+		page_no++;
+		probe_block += blocks_per_page;
+reprobe:
+		continue;
+	}
+	ret = nr_extents;
+	*span = 1 + highest_block - lowest_block;
+	if (page_no == 0)
+		page_no = 1;	/* force Empty message */
+	sis->max = page_no;
+	sis->pages = page_no - 1;
+	sis->highest_bit = page_no - 1;
+out:
+	return ret;
+bad_bmap:
+	printk(KERN_ERR "swapon: swapfile has holes\n");
+	ret = -EINVAL;
+	goto out;
 }
 
 /*
@@ -84,77 +231,159 @@ static int end_swap_bio_read(struct bio *bio, unsigned int bytes_done, int err)
  */
 int swap_writepage(struct page *page, struct writeback_control *wbc)
 {
-	struct bio *bio;
-	int ret = 0, rw = WRITE;
+	int ret = 0;
 
-	if (remove_exclusive_swap_page(page)) {
+	if (try_to_free_swap(page)) {
 		unlock_page(page);
 		goto out;
 	}
-	bio = get_swap_bio(GFP_NOIO, page->private, page, end_swap_bio_write);
-	if (bio == NULL) {
-		set_page_dirty(page);
+	if (frontswap_store(page) == 0) {
+		set_page_writeback(page);
 		unlock_page(page);
-		ret = -ENOMEM;
+		end_page_writeback(page);
 		goto out;
 	}
-	if (wbc->sync_mode == WB_SYNC_ALL)
-		rw |= (1 << BIO_RW_SYNC);
-	inc_page_state(pswpout);
-	set_page_writeback(page);
-	unlock_page(page);
-	submit_bio(rw, bio);
+	ret = __swap_writepage(page, wbc, end_swap_bio_write);
 out:
 	return ret;
 }
 
-int swap_readpage(struct file *file, struct page *page)
+static sector_t swap_page_sector(struct page *page)
+{
+	return (sector_t)__page_file_index(page) << (PAGE_CACHE_SHIFT - 9);
+}
+
+int __swap_writepage(struct page *page, struct writeback_control *wbc,
+	void (*end_write_func)(struct bio *, int))
 {
 	struct bio *bio;
-	int ret = 0;
+	int ret, rw = WRITE;
+	struct swap_info_struct *sis = page_swap_info(page);
+
+	if (sis->flags & SWP_FILE) {
+		struct kiocb kiocb;
+		struct file *swap_file = sis->swap_file;
+		struct address_space *mapping = swap_file->f_mapping;
+		struct bio_vec bv = {
+			.bv_page = page,
+			.bv_len  = PAGE_SIZE,
+			.bv_offset = 0
+		};
+		struct iov_iter from = {
+			.type = ITER_BVEC | WRITE,
+			.count = PAGE_SIZE,
+			.iov_offset = 0,
+			.nr_segs = 1,
+		};
+		from.bvec = &bv;	/* older gcc versions are broken */
+
+		init_sync_kiocb(&kiocb, swap_file);
+		kiocb.ki_pos = page_file_offset(page);
+		kiocb.ki_nbytes = PAGE_SIZE;
+
+		set_page_writeback(page);
+		unlock_page(page);
+		ret = mapping->a_ops->direct_IO(ITER_BVEC | WRITE,
+						&kiocb, &from,
+						kiocb.ki_pos);
+		if (ret == PAGE_SIZE) {
+			count_vm_event(PSWPOUT);
+			ret = 0;
+		} else {
+			/*
+			 * In the case of swap-over-nfs, this can be a
+			 * temporary failure if the system has limited
+			 * memory for allocating transmit buffers.
+			 * Mark the page dirty and avoid
+			 * rotate_reclaimable_page but rate-limit the
+			 * messages but do not flag PageError like
+			 * the normal direct-to-bio case as it could
+			 * be temporary.
+			 */
+			set_page_dirty(page);
+			ClearPageReclaim(page);
+			pr_err_ratelimited("Write error on dio swapfile (%Lu)\n",
+				page_file_offset(page));
+		}
+		end_page_writeback(page);
+		return ret;
+	}
+
+	ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc);
+	if (!ret) {
+		count_vm_event(PSWPOUT);
+		return 0;
+	}
 
-	BUG_ON(!PageLocked(page));
-	ClearPageUptodate(page);
-	bio = get_swap_bio(GFP_KERNEL, page->private, page, end_swap_bio_read);
+	ret = 0;
+	bio = get_swap_bio(GFP_NOIO, page, end_write_func);
 	if (bio == NULL) {
+		set_page_dirty(page);
 		unlock_page(page);
 		ret = -ENOMEM;
 		goto out;
 	}
-	inc_page_state(pswpin);
-	submit_bio(READ, bio);
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		rw |= REQ_SYNC;
+	count_vm_event(PSWPOUT);
+	set_page_writeback(page);
+	unlock_page(page);
+	submit_bio(rw, bio);
 out:
 	return ret;
 }
 
-#ifdef CONFIG_SOFTWARE_SUSPEND
-/*
- * A scruffy utility function to read or write an arbitrary swap page
- * and wait on the I/O.  The caller must have a ref on the page.
- *
- * We use end_swap_bio_read() even for writes, because it happens to do what
- * we want.
- */
-int rw_swap_page_sync(int rw, swp_entry_t entry, struct page *page)
+int swap_readpage(struct page *page)
 {
 	struct bio *bio;
 	int ret = 0;
+	struct swap_info_struct *sis = page_swap_info(page);
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(PageUptodate(page), page);
+	if (frontswap_load(page) == 0) {
+		SetPageUptodate(page);
+		unlock_page(page);
+		goto out;
+	}
+
+	if (sis->flags & SWP_FILE) {
+		struct file *swap_file = sis->swap_file;
+		struct address_space *mapping = swap_file->f_mapping;
+
+		ret = mapping->a_ops->readpage(swap_file, page);
+		if (!ret)
+			count_vm_event(PSWPIN);
+		return ret;
+	}
 
-	lock_page(page);
+	ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
+	if (!ret) {
+		count_vm_event(PSWPIN);
+		return 0;
+	}
 
-	bio = get_swap_bio(GFP_KERNEL, entry.val, page, end_swap_bio_read);
+	ret = 0;
+	bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
 	if (bio == NULL) {
 		unlock_page(page);
 		ret = -ENOMEM;
 		goto out;
 	}
-
-	submit_bio(rw | (1 << BIO_RW_SYNC), bio);
-	wait_on_page_locked(page);
-
-	if (!PageUptodate(page) || PageError(page))
-		ret = -EIO;
+	count_vm_event(PSWPIN);
+	submit_bio(READ, bio);
 out:
 	return ret;
 }
-#endif
+
+int swap_set_page_dirty(struct page *page)
+{
+	struct swap_info_struct *sis = page_swap_info(page);
+
+	if (sis->flags & SWP_FILE) {
+		struct address_space *mapping = sis->swap_file->f_mapping;
+		return mapping->a_ops->set_page_dirty(page);
+	} else {
+		return __set_page_dirty_no_writeback(page);
+	}
+}