Merge tag 'for-f2fs-4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This patch series contains several performance tuning patches
  regarding to the IO submission flow, in addition to supporting new
  features such as a ZBC-base drive and multiple devices.

  It also includes some major bug fixes such as:
   - checkpoint version control
   - fdatasync-related roll-forward recovery routine
   - memory boundary or null-pointer access in corner cases
   - missing error cases

  It has various minor clean-up patches as well"

* tag 'for-f2fs-4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (66 commits)
  f2fs: fix a missing size change in f2fs_setattr
  f2fs: fix to access nullified flush_cmd_control pointer
  f2fs: free meta pages if sanity check for ckpt is failed
  f2fs: detect wrong layout
  f2fs: call sync_fs when f2fs is idle
  Revert "f2fs: use percpu_counter for # of dirty pages in inode"
  f2fs: return AOP_WRITEPAGE_ACTIVATE for writepage
  f2fs: do not activate auto_recovery for fallocated i_size
  f2fs: fix to determine start_cp_addr by sbi->cur_cp_pack
  f2fs: fix 32-bit build
  f2fs: set ->owner for debugfs status file's file_operations
  f2fs: fix incorrect free inode count in ->statfs
  f2fs: drop duplicate header timer.h
  f2fs: fix wrong AUTO_RECOVER condition
  f2fs: do not recover i_size if it's valid
  f2fs: fix fdatasync
  f2fs: fix to account total free nid correctly
  f2fs: fix an infinite loop when flush nodes in cp
  f2fs: don't wait writeback for datas during checkpoint
  f2fs: fix wrong written_valid_blocks counting
  ...

1 files changed, 127 insertions, 65 deletions

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 9e5561fa4cb6..7c344b3ad70f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -29,6 +29,26 @@
 #include "trace.h"
 #include <trace/events/f2fs.h>
 
+static bool __is_cp_guaranteed(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *inode;
+	struct f2fs_sb_info *sbi;
+
+	if (!mapping)
+		return false;
+
+	inode = mapping->host;
+	sbi = F2FS_I_SB(inode);
+
+	if (inode->i_ino == F2FS_META_INO(sbi) ||
+			inode->i_ino ==  F2FS_NODE_INO(sbi) ||
+			S_ISDIR(inode->i_mode) ||
+			is_cold_data(page))
+		return true;
+	return false;
+}
+
 static void f2fs_read_end_io(struct bio *bio)
 {
 	struct bio_vec *bvec;
@@ -71,6 +91,7 @@ static void f2fs_write_end_io(struct bio *bio)
 
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
+		enum count_type type = WB_DATA_TYPE(page);
 
 		fscrypt_pullback_bio_page(&page, true);
 
@@ -78,9 +99,11 @@ static void f2fs_write_end_io(struct bio *bio)
 			mapping_set_error(page->mapping, -EIO);
 			f2fs_stop_checkpoint(sbi, true);
 		}
+		dec_page_count(sbi, type);
+		clear_cold_data(page);
 		end_page_writeback(page);
 	}
-	if (atomic_dec_and_test(&sbi->nr_wb_bios) &&
+	if (!get_pages(sbi, F2FS_WB_CP_DATA) &&
 				wq_has_sleeper(&sbi->cp_wait))
 		wake_up(&sbi->cp_wait);
 
@@ -88,6 +111,46 @@ static void f2fs_write_end_io(struct bio *bio)
 }
 
 /*
+ * Return true, if pre_bio's bdev is same as its target device.
+ */
+struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
+				block_t blk_addr, struct bio *bio)
+{
+	struct block_device *bdev = sbi->sb->s_bdev;
+	int i;
+
+	for (i = 0; i < sbi->s_ndevs; i++) {
+		if (FDEV(i).start_blk <= blk_addr &&
+					FDEV(i).end_blk >= blk_addr) {
+			blk_addr -= FDEV(i).start_blk;
+			bdev = FDEV(i).bdev;
+			break;
+		}
+	}
+	if (bio) {
+		bio->bi_bdev = bdev;
+		bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
+	}
+	return bdev;
+}
+
+int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+	int i;
+
+	for (i = 0; i < sbi->s_ndevs; i++)
+		if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr)
+			return i;
+	return 0;
+}
+
+static bool __same_bdev(struct f2fs_sb_info *sbi,
+				block_t blk_addr, struct bio *bio)
+{
+	return f2fs_target_device(sbi, blk_addr, NULL) == bio->bi_bdev;
+}
+
+/*
  * Low-level block read/write IO operations.
  */
 static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
@@ -97,8 +160,7 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
 
 	bio = f2fs_bio_alloc(npages);
 
-	bio->bi_bdev = sbi->sb->s_bdev;
-	bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
+	f2fs_target_device(sbi, blk_addr, bio);
 	bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
 	bio->bi_private = is_read ? NULL : sbi;
 
@@ -109,8 +171,7 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi,
 				struct bio *bio, enum page_type type)
 {
 	if (!is_read_io(bio_op(bio))) {
-		atomic_inc(&sbi->nr_wb_bios);
-		if (f2fs_sb_mounted_hmsmr(sbi->sb) &&
+		if (f2fs_sb_mounted_blkzoned(sbi->sb) &&
 			current->plug && (type == DATA || type == NODE))
 			blk_finish_plug(current->plug);
 	}
@@ -268,22 +329,24 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 		verify_block_addr(sbi, fio->old_blkaddr);
 	verify_block_addr(sbi, fio->new_blkaddr);
 
+	bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+
+	if (!is_read)
+		inc_page_count(sbi, WB_DATA_TYPE(bio_page));
+
 	down_write(&io->io_rwsem);
 
 	if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
-	    (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags)))
+	    (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags) ||
+			!__same_bdev(sbi, fio->new_blkaddr, io->bio)))
 		__submit_merged_bio(io);
 alloc_new:
 	if (io->bio == NULL) {
-		int bio_blocks = MAX_BIO_BLOCKS(sbi);
-
 		io->bio = __bio_alloc(sbi, fio->new_blkaddr,
-						bio_blocks, is_read);
+						BIO_MAX_PAGES, is_read);
 		io->fio = *fio;
 	}
 
-	bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
-
 	if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) <
 							PAGE_SIZE) {
 		__submit_merged_bio(io);
@@ -588,7 +651,6 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct f2fs_summary sum;
 	struct node_info ni;
-	int seg = CURSEG_WARM_DATA;
 	pgoff_t fofs;
 	blkcnt_t count = 1;
 
@@ -606,11 +668,8 @@ alloc:
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 
-	if (dn->ofs_in_node == 0 && dn->inode_page == dn->node_page)
-		seg = CURSEG_DIRECT_IO;
-
 	allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
-								&sum, seg);
+						&sum, CURSEG_WARM_DATA);
 	set_data_blkaddr(dn);
 
 	/* update i_size */
@@ -622,11 +681,18 @@ alloc:
 	return 0;
 }
 
-ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
+static inline bool __force_buffered_io(struct inode *inode, int rw)
+{
+	return ((f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) ||
+			(rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) ||
+			F2FS_I_SB(inode)->s_ndevs);
+}
+
+int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct f2fs_map_blocks map;
-	ssize_t ret = 0;
+	int err = 0;
 
 	map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
 	map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
@@ -638,19 +704,22 @@ ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 	map.m_next_pgofs = NULL;
 
 	if (iocb->ki_flags & IOCB_DIRECT) {
-		ret = f2fs_convert_inline_inode(inode);
-		if (ret)
-			return ret;
-		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
+		err = f2fs_convert_inline_inode(inode);
+		if (err)
+			return err;
+		return f2fs_map_blocks(inode, &map, 1,
+			__force_buffered_io(inode, WRITE) ?
+				F2FS_GET_BLOCK_PRE_AIO :
+				F2FS_GET_BLOCK_PRE_DIO);
 	}
 	if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA) {
-		ret = f2fs_convert_inline_inode(inode);
-		if (ret)
-			return ret;
+		err = f2fs_convert_inline_inode(inode);
+		if (err)
+			return err;
 	}
 	if (!f2fs_has_inline_data(inode))
 		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
-	return ret;
+	return err;
 }
 
 /*
@@ -674,7 +743,6 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	unsigned int ofs_in_node, last_ofs_in_node;
 	blkcnt_t prealloc;
 	struct extent_info ei;
-	bool allocated = false;
 	block_t blkaddr;
 
 	if (!maxblocks)
@@ -714,7 +782,7 @@ next_dnode:
 	}
 
 	prealloc = 0;
-	ofs_in_node = dn.ofs_in_node;
+	last_ofs_in_node = ofs_in_node = dn.ofs_in_node;
 	end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 
 next_block:
@@ -733,10 +801,8 @@ next_block:
 				}
 			} else {
 				err = __allocate_data_block(&dn);
-				if (!err) {
+				if (!err)
 					set_inode_flag(inode, FI_APPEND_WRITE);
-					allocated = true;
-				}
 			}
 			if (err)
 				goto sync_out;
@@ -791,7 +857,6 @@ skip:
 		err = reserve_new_blocks(&dn, prealloc);
 		if (err)
 			goto sync_out;
-		allocated = dn.node_changed;
 
 		map->m_len += dn.ofs_in_node - ofs_in_node;
 		if (prealloc && dn.ofs_in_node != last_ofs_in_node + 1) {
@@ -810,9 +875,8 @@ skip:
 
 	if (create) {
 		f2fs_unlock_op(sbi);
-		f2fs_balance_fs(sbi, allocated);
+		f2fs_balance_fs(sbi, dn.node_changed);
 	}
-	allocated = false;
 	goto next_dnode;
 
 sync_out:
@@ -820,7 +884,7 @@ sync_out:
 unlock_out:
 	if (create) {
 		f2fs_unlock_op(sbi);
-		f2fs_balance_fs(sbi, allocated);
+		f2fs_balance_fs(sbi, dn.node_changed);
 	}
 out:
 	trace_f2fs_map_blocks(inode, map, err);
@@ -832,19 +896,19 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 			pgoff_t *next_pgofs)
 {
 	struct f2fs_map_blocks map;
-	int ret;
+	int err;
 
 	map.m_lblk = iblock;
 	map.m_len = bh->b_size >> inode->i_blkbits;
 	map.m_next_pgofs = next_pgofs;
 
-	ret = f2fs_map_blocks(inode, &map, create, flag);
-	if (!ret) {
+	err = f2fs_map_blocks(inode, &map, create, flag);
+	if (!err) {
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
 		bh->b_size = map.m_len << inode->i_blkbits;
 	}
-	return ret;
+	return err;
 }
 
 static int get_data_block(struct inode *inode, sector_t iblock,
@@ -889,7 +953,6 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	struct buffer_head map_bh;
 	sector_t start_blk, last_blk;
 	pgoff_t next_pgofs;
-	loff_t isize;
 	u64 logical = 0, phys = 0, size = 0;
 	u32 flags = 0;
 	int ret = 0;
@@ -906,13 +969,6 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 
 	inode_lock(inode);
 
-	isize = i_size_read(inode);
-	if (start >= isize)
-		goto out;
-
-	if (start + len > isize)
-		len = isize - start;
-
 	if (logical_to_blk(inode, len) == 0)
 		len = blk_to_logical(inode, 1);
 
@@ -931,13 +987,11 @@ next:
 	/* HOLE */
 	if (!buffer_mapped(&map_bh)) {
 		start_blk = next_pgofs;
-		/* Go through holes util pass the EOF */
-		if (blk_to_logical(inode, start_blk) < isize)
+
+		if (blk_to_logical(inode, start_blk) < blk_to_logical(inode,
+					F2FS_I_SB(inode)->max_file_blocks))
 			goto prep_next;
-		/* Found a hole beyond isize means no more extents.
-		 * Note that the premise is that filesystems don't
-		 * punch holes beyond isize and keep size unchanged.
-		 */
+
 		flags |= FIEMAP_EXTENT_LAST;
 	}
 
@@ -980,7 +1034,6 @@ static struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct fscrypt_ctx *ctx = NULL;
-	struct block_device *bdev = sbi->sb->s_bdev;
 	struct bio *bio;
 
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
@@ -998,8 +1051,7 @@ static struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
 			fscrypt_release_ctx(ctx);
 		return ERR_PTR(-ENOMEM);
 	}
-	bio->bi_bdev = bdev;
-	bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blkaddr);
+	f2fs_target_device(sbi, blkaddr, bio);
 	bio->bi_end_io = f2fs_read_end_io;
 	bio->bi_private = ctx;
 
@@ -1094,7 +1146,8 @@ got_it:
 		 * This page will go to BIO.  Do we need to send this
 		 * BIO off first?
 		 */
-		if (bio && (last_block_in_bio != block_nr - 1)) {
+		if (bio && (last_block_in_bio != block_nr - 1 ||
+			!__same_bdev(F2FS_I_SB(inode), block_nr, bio))) {
 submit_and_realloc:
 			__submit_bio(F2FS_I_SB(inode), bio, DATA);
 			bio = NULL;
@@ -1309,7 +1362,6 @@ done:
 	if (err && err != -ENOENT)
 		goto redirty_out;
 
-	clear_cold_data(page);
 out:
 	inode_dec_dirty_pages(inode);
 	if (err)
@@ -1330,6 +1382,8 @@ out:
 
 redirty_out:
 	redirty_page_for_writepage(wbc, page);
+	if (!err)
+		return AOP_WRITEPAGE_ACTIVATE;
 	unlock_page(page);
 	return err;
 }
@@ -1425,6 +1479,15 @@ continue_unlock:
 
 			ret = mapping->a_ops->writepage(page, wbc);
 			if (unlikely(ret)) {
+				/*
+				 * keep nr_to_write, since vfs uses this to
+				 * get # of written pages.
+				 */
+				if (ret == AOP_WRITEPAGE_ACTIVATE) {
+					unlock_page(page);
+					ret = 0;
+					continue;
+				}
 				done_index = page->index + 1;
 				done = 1;
 				break;
@@ -1712,7 +1775,6 @@ static int f2fs_write_end(struct file *file,
 		goto unlock_out;
 
 	set_page_dirty(page);
-	clear_cold_data(page);
 
 	if (pos + copied > i_size_read(inode))
 		f2fs_i_size_write(inode, pos + copied);
@@ -1749,9 +1811,7 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	if (err)
 		return err;
 
-	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
-		return 0;
-	if (test_opt(F2FS_I_SB(inode), LFS))
+	if (__force_buffered_io(inode, rw))
 		return 0;
 
 	trace_f2fs_direct_IO_enter(inode, offset, count, rw);
@@ -1783,12 +1843,14 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
 		return;
 
 	if (PageDirty(page)) {
-		if (inode->i_ino == F2FS_META_INO(sbi))
+		if (inode->i_ino == F2FS_META_INO(sbi)) {
 			dec_page_count(sbi, F2FS_DIRTY_META);
-		else if (inode->i_ino == F2FS_NODE_INO(sbi))
+		} else if (inode->i_ino == F2FS_NODE_INO(sbi)) {
 			dec_page_count(sbi, F2FS_DIRTY_NODES);
-		else
+		} else {
 			inode_dec_dirty_pages(inode);
+			remove_dirty_inode(inode);
+		}
 	}
 
 	/* This is atomic written page, keep Private */