Merge tag 'f2fs-for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've introduced native swap file support which can
  exploit DIO, enhanced existing checkpoint=disable feature with
  additional mount option to tune the triggering condition, and allowed
  user to preallocate physical blocks in a pinned file which will be
  useful to avoid f2fs fragmentation in append-only workloads. In
  addition, we've fixed subtle quota corruption issue.

  Enhancements:
   - add swap file support which uses DIO
   - allocate blocks for pinned file
   - allow SSR and mount option to enhance checkpoint=disable
   - enhance IPU IOs
   - add more sanity checks such as memory boundary access

  Bug fixes:
   - quota corruption in very corner case of error-injected SPO case
   - fix root_reserved on remount and some wrong counts
   - add missing fsck flag

  Some patches were also introduced to clean up ambiguous i_flags and
  debugging messages codes"

* tag 'f2fs-for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (33 commits)
  f2fs: improve print log in f2fs_sanity_check_ckpt()
  f2fs: avoid out-of-range memory access
  f2fs: fix to avoid long latency during umount
  f2fs: allow all the users to pin a file
  f2fs: support swap file w/ DIO
  f2fs: allocate blocks for pinned file
  f2fs: fix is_idle() check for discard type
  f2fs: add a rw_sem to cover quota flag changes
  f2fs: set SBI_NEED_FSCK for xattr corruption case
  f2fs: use generic EFSBADCRC/EFSCORRUPTED
  f2fs: Use DIV_ROUND_UP() instead of open-coding
  f2fs: print kernel message if filesystem is inconsistent
  f2fs: introduce f2fs_<level> macros to wrap f2fs_printk()
  f2fs: avoid get_valid_blocks() for cleanup
  f2fs: ioctl for removing a range from F2FS
  f2fs: only set project inherit bit for directory
  f2fs: separate f2fs i_flags from fs_flags and ext4 i_flags
  f2fs: replace ktype default_attrs with default_groups
  f2fs: Add option to limit required GC for checkpoint=disable
  f2fs: Fix accounting for unusable blocks
  ...

1 files changed, 224 insertions, 25 deletions

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index a546ac8685ea..0ca530afc684 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -14,6 +14,7 @@
 #include <linux/pagevec.h>
 #include <linux/blkdev.h>
 #include <linux/bio.h>
+#include <linux/swap.h>
 #include <linux/prefetch.h>
 #include <linux/uio.h>
 #include <linux/cleancache.h>
@@ -54,7 +55,7 @@ static bool __is_cp_guaranteed(struct page *page)
 
 static enum count_type __read_io_type(struct page *page)
 {
-	struct address_space *mapping = page->mapping;
+	struct address_space *mapping = page_file_mapping(page);
 
 	if (mapping) {
 		struct inode *inode = mapping->host;
@@ -347,20 +348,20 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 	io->bio = NULL;
 }
 
-static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
+static bool __has_merged_page(struct bio *bio, struct inode *inode,
 						struct page *page, nid_t ino)
 {
 	struct bio_vec *bvec;
 	struct page *target;
 	struct bvec_iter_all iter_all;
 
-	if (!io->bio)
+	if (!bio)
 		return false;
 
 	if (!inode && !page && !ino)
 		return true;
 
-	bio_for_each_segment_all(bvec, io->bio, iter_all) {
+	bio_for_each_segment_all(bvec, bio, iter_all) {
 
 		target = bvec->bv_page;
 		if (fscrypt_is_bounce_page(target))
@@ -410,7 +411,7 @@ static void __submit_merged_write_cond(struct f2fs_sb_info *sbi,
 			struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
 
 			down_read(&io->io_rwsem);
-			ret = __has_merged_page(io, inode, page, ino);
+			ret = __has_merged_page(io->bio, inode, page, ino);
 			up_read(&io->io_rwsem);
 		}
 		if (ret)
@@ -454,7 +455,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
 			fio->is_por ? META_POR : (__is_meta_io(fio) ?
 			META_GENERIC : DATA_GENERIC_ENHANCE)))
-		return -EFAULT;
+		return -EFSCORRUPTED;
 
 	trace_f2fs_submit_page_bio(page, fio);
 	f2fs_trace_ios(fio, 0);
@@ -480,6 +481,61 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	return 0;
 }
 
+int f2fs_merge_page_bio(struct f2fs_io_info *fio)
+{
+	struct bio *bio = *fio->bio;
+	struct page *page = fio->encrypted_page ?
+			fio->encrypted_page : fio->page;
+
+	if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
+			__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
+		return -EFSCORRUPTED;
+
+	trace_f2fs_submit_page_bio(page, fio);
+	f2fs_trace_ios(fio, 0);
+
+	if (bio && (*fio->last_block + 1 != fio->new_blkaddr ||
+			!__same_bdev(fio->sbi, fio->new_blkaddr, bio))) {
+		__submit_bio(fio->sbi, bio, fio->type);
+		bio = NULL;
+	}
+alloc_new:
+	if (!bio) {
+		bio = __bio_alloc(fio->sbi, fio->new_blkaddr, fio->io_wbc,
+				BIO_MAX_PAGES, false, fio->type, fio->temp);
+		bio_set_op_attrs(bio, fio->op, fio->op_flags);
+	}
+
+	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+		__submit_bio(fio->sbi, bio, fio->type);
+		bio = NULL;
+		goto alloc_new;
+	}
+
+	if (fio->io_wbc)
+		wbc_account_io(fio->io_wbc, page, PAGE_SIZE);
+
+	inc_page_count(fio->sbi, WB_DATA_TYPE(page));
+
+	*fio->last_block = fio->new_blkaddr;
+	*fio->bio = bio;
+
+	return 0;
+}
+
+static void f2fs_submit_ipu_bio(struct f2fs_sb_info *sbi, struct bio **bio,
+							struct page *page)
+{
+	if (!bio)
+		return;
+
+	if (!__has_merged_page(*bio, NULL, page, 0))
+		return;
+
+	__submit_bio(sbi, *bio, DATA);
+	*bio = NULL;
+}
+
 void f2fs_submit_page_write(struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = fio->sbi;
@@ -733,7 +789,7 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
 		dn.data_blkaddr = ei.blk + index - ei.fofs;
 		if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), dn.data_blkaddr,
 						DATA_GENERIC_ENHANCE_READ)) {
-			err = -EFAULT;
+			err = -EFSCORRUPTED;
 			goto put_err;
 		}
 		goto got_it;
@@ -753,7 +809,7 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
 			!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
 						dn.data_blkaddr,
 						DATA_GENERIC_ENHANCE)) {
-		err = -EFAULT;
+		err = -EFSCORRUPTED;
 		goto put_err;
 	}
 got_it:
@@ -1099,7 +1155,7 @@ next_block:
 
 	if (__is_valid_data_blkaddr(blkaddr) &&
 		!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
-		err = -EFAULT;
+		err = -EFSCORRUPTED;
 		goto sync_out;
 	}
 
@@ -1529,7 +1585,7 @@ static int f2fs_read_single_page(struct inode *inode, struct page *page,
 	sector_t block_nr;
 	int ret = 0;
 
-	block_in_file = (sector_t)page->index;
+	block_in_file = (sector_t)page_index(page);
 	last_block = block_in_file + nr_pages;
 	last_block_in_file = (i_size_read(inode) + blocksize - 1) >>
 							blkbits;
@@ -1562,14 +1618,15 @@ got_it:
 		block_nr = map->m_pblk + block_in_file - map->m_lblk;
 		SetPageMappedToDisk(page);
 
-		if (!PageUptodate(page) && !cleancache_get_page(page)) {
+		if (!PageUptodate(page) && (!PageSwapCache(page) &&
+					!cleancache_get_page(page))) {
 			SetPageUptodate(page);
 			goto confused;
 		}
 
 		if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
 						DATA_GENERIC_ENHANCE_READ)) {
-			ret = -EFAULT;
+			ret = -EFSCORRUPTED;
 			goto out;
 		}
 	} else {
@@ -1660,7 +1717,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 			prefetchw(&page->flags);
 			list_del(&page->lru);
 			if (add_to_page_cache_lru(page, mapping,
-						  page->index,
+						  page_index(page),
 						  readahead_gfp_mask(mapping)))
 				goto next_page;
 		}
@@ -1684,7 +1741,7 @@ next_page:
 
 static int f2fs_read_data_page(struct file *file, struct page *page)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 	int ret = -EAGAIN;
 
 	trace_f2fs_readpage(page, DATA);
@@ -1693,7 +1750,8 @@ static int f2fs_read_data_page(struct file *file, struct page *page)
 	if (f2fs_has_inline_data(inode))
 		ret = f2fs_read_inline_data(inode, page);
 	if (ret == -EAGAIN)
-		ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1, false);
+		ret = f2fs_mpage_readpages(page_file_mapping(page),
+						NULL, page, 1, false);
 	return ret;
 }
 
@@ -1851,7 +1909,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
 
 		if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
 						DATA_GENERIC_ENHANCE))
-			return -EFAULT;
+			return -EFSCORRUPTED;
 
 		ipu_force = true;
 		fio->need_lock = LOCK_DONE;
@@ -1878,7 +1936,7 @@ got_it:
 	if (__is_valid_data_blkaddr(fio->old_blkaddr) &&
 		!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
 						DATA_GENERIC_ENHANCE)) {
-		err = -EFAULT;
+		err = -EFSCORRUPTED;
 		goto out_writepage;
 	}
 	/*
@@ -1946,6 +2004,8 @@ out:
 }
 
 static int __write_data_page(struct page *page, bool *submitted,
+				struct bio **bio,
+				sector_t *last_block,
 				struct writeback_control *wbc,
 				enum iostat_type io_type)
 {
@@ -1971,6 +2031,8 @@ static int __write_data_page(struct page *page, bool *submitted,
 		.need_lock = LOCK_RETRY,
 		.io_type = io_type,
 		.io_wbc = wbc,
+		.bio = bio,
+		.last_block = last_block,
 	};
 
 	trace_f2fs_writepage(page, DATA);
@@ -2069,10 +2131,13 @@ out:
 
 	unlock_page(page);
 	if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) &&
-					!F2FS_I(inode)->cp_task)
+					!F2FS_I(inode)->cp_task) {
+		f2fs_submit_ipu_bio(sbi, bio, page);
 		f2fs_balance_fs(sbi, need_balance_fs);
+	}
 
 	if (unlikely(f2fs_cp_error(sbi))) {
+		f2fs_submit_ipu_bio(sbi, bio, page);
 		f2fs_submit_merged_write(sbi, DATA);
 		submitted = NULL;
 	}
@@ -2099,7 +2164,7 @@ redirty_out:
 static int f2fs_write_data_page(struct page *page,
 					struct writeback_control *wbc)
 {
-	return __write_data_page(page, NULL, wbc, FS_DATA_IO);
+	return __write_data_page(page, NULL, NULL, NULL, wbc, FS_DATA_IO);
 }
 
 /*
@@ -2115,6 +2180,8 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 	int done = 0;
 	struct pagevec pvec;
 	struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
+	struct bio *bio = NULL;
+	sector_t last_block;
 	int nr_pages;
 	pgoff_t uninitialized_var(writeback_index);
 	pgoff_t index;
@@ -2191,17 +2258,20 @@ continue_unlock:
 			}
 
 			if (PageWriteback(page)) {
-				if (wbc->sync_mode != WB_SYNC_NONE)
+				if (wbc->sync_mode != WB_SYNC_NONE) {
 					f2fs_wait_on_page_writeback(page,
 							DATA, true, true);
-				else
+					f2fs_submit_ipu_bio(sbi, &bio, page);
+				} else {
 					goto continue_unlock;
+				}
 			}
 
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
-			ret = __write_data_page(page, &submitted, wbc, io_type);
+			ret = __write_data_page(page, &submitted, &bio,
+					&last_block, wbc, io_type);
 			if (unlikely(ret)) {
 				/*
 				 * keep nr_to_write, since vfs uses this to
@@ -2250,6 +2320,9 @@ continue_unlock:
 	if (nwritten)
 		f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
 								NULL, 0, DATA);
+	/* submit cached bio of IPU write */
+	if (bio)
+		__submit_bio(sbi, bio, DATA);
 
 	return ret;
 }
@@ -2261,6 +2334,9 @@ static inline bool __should_serialize_io(struct inode *inode,
 		return false;
 	if (IS_NOQUOTA(inode))
 		return false;
+	/* to avoid deadlock in path of data flush */
+	if (F2FS_I(inode)->cp_task)
+		return false;
 	if (wbc->sync_mode != WB_SYNC_ALL)
 		return true;
 	if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks)
@@ -2532,7 +2608,7 @@ repeat:
 	} else {
 		if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
 				DATA_GENERIC_ENHANCE_READ)) {
-			err = -EFAULT;
+			err = -EFSCORRUPTED;
 			goto fail;
 		}
 		err = f2fs_submit_page_read(inode, page, blkaddr);
@@ -2777,13 +2853,14 @@ int f2fs_release_page(struct page *page, gfp_t wait)
 
 static int f2fs_set_data_page_dirty(struct page *page)
 {
-	struct address_space *mapping = page->mapping;
-	struct inode *inode = mapping->host;
+	struct inode *inode = page_file_mapping(page)->host;
 
 	trace_f2fs_set_page_dirty(page, DATA);
 
 	if (!PageUptodate(page))
 		SetPageUptodate(page);
+	if (PageSwapCache(page))
+		return __set_page_dirty_nobuffers(page);
 
 	if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) {
 		if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
@@ -2875,6 +2952,126 @@ int f2fs_migrate_page(struct address_space *mapping,
 }
 #endif
 
+#ifdef CONFIG_SWAP
+/* Copied from generic_swapfile_activate() to check any holes */
+static int check_swap_activate(struct file *swap_file, unsigned int max)
+{
+	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;
+
+	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 < max) {
+		unsigned block_in_page;
+		sector_t first_block;
+
+		cond_resched();
+
+		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;
+		}
+
+		page_no++;
+		probe_block += blocks_per_page;
+reprobe:
+		continue;
+	}
+	return 0;
+
+bad_bmap:
+	pr_err("swapon: swapfile has holes\n");
+	return -EINVAL;
+}
+
+static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
+				sector_t *span)
+{
+	struct inode *inode = file_inode(file);
+	int ret;
+
+	if (!S_ISREG(inode->i_mode))
+		return -EINVAL;
+
+	if (f2fs_readonly(F2FS_I_SB(inode)->sb))
+		return -EROFS;
+
+	ret = f2fs_convert_inline_inode(inode);
+	if (ret)
+		return ret;
+
+	ret = check_swap_activate(file, sis->max);
+	if (ret)
+		return ret;
+
+	set_inode_flag(inode, FI_PIN_FILE);
+	f2fs_precache_extents(inode);
+	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+	return 0;
+}
+
+static void f2fs_swap_deactivate(struct file *file)
+{
+	struct inode *inode = file_inode(file);
+
+	clear_inode_flag(inode, FI_PIN_FILE);
+}
+#else
+static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
+				sector_t *span)
+{
+	return -EOPNOTSUPP;
+}
+
+static void f2fs_swap_deactivate(struct file *file)
+{
+}
+#endif
+
 const struct address_space_operations f2fs_dblock_aops = {
 	.readpage	= f2fs_read_data_page,
 	.readpages	= f2fs_read_data_pages,
@@ -2887,6 +3084,8 @@ const struct address_space_operations f2fs_dblock_aops = {
 	.releasepage	= f2fs_release_page,
 	.direct_IO	= f2fs_direct_IO,
 	.bmap		= f2fs_bmap,
+	.swap_activate  = f2fs_swap_activate,
+	.swap_deactivate = f2fs_swap_deactivate,
 #ifdef CONFIG_MIGRATION
 	.migratepage    = f2fs_migrate_page,
 #endif