Merge tag 'for-f2fs-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "New features:
   - per-file encryption (e.g., ext4)
   - FALLOC_FL_ZERO_RANGE
   - FALLOC_FL_COLLAPSE_RANGE
   - RENAME_WHITEOUT

  Major enhancement/fixes:
   - recovery broken superblocks
   - enhance f2fs_trim_fs with a discard_map
   - fix a race condition on dentry block allocation
   - fix a deadlock during summary operation
   - fix a missing fiemap result

  .. and many minor bug fixes and clean-ups were done"

* tag 'for-f2fs-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (83 commits)
  f2fs: do not trim preallocated blocks when truncating after i_size
  f2fs crypto: add alloc_bounce_page
  f2fs crypto: fix to handle errors likewise ext4
  f2fs: drop the volatile_write flag only
  f2fs: skip committing valid superblock
  f2fs: setting discard option in parse_options()
  f2fs: fix to return exact trimmed size
  f2fs: support FALLOC_FL_INSERT_RANGE
  f2fs: hide common code in f2fs_replace_block
  f2fs: disable the discard option when device doesn't support
  f2fs crypto: remove alloc_page for bounce_page
  f2fs: fix a deadlock for summary page lock vs. sentry_lock
  f2fs crypto: clean up error handling in f2fs_fname_setup_filename
  f2fs crypto: avoid f2fs_inherit_context for symlink
  f2fs crypto: do not set encryption policy for non-directory by ioctl
  f2fs crypto: allow setting encryption policy once
  f2fs crypto: check context consistent for rename2
  f2fs: avoid duplicated code by reusing f2fs_read_end_io
  f2fs crypto: use per-inode tfm structure
  f2fs: recovering broken superblock during mount
  ...

1 files changed, 175 insertions, 75 deletions

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index f939660941bb..1eb343768781 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -75,6 +75,14 @@ static inline unsigned long __reverse_ffs(unsigned long word)
 static unsigned long __find_rev_next_bit(const unsigned long *addr,
 			unsigned long size, unsigned long offset)
 {
+	while (!f2fs_test_bit(offset, (unsigned char *)addr))
+		offset++;
+
+	if (offset > size)
+		offset = size;
+
+	return offset;
+#if 0
 	const unsigned long *p = addr + BIT_WORD(offset);
 	unsigned long result = offset & ~(BITS_PER_LONG - 1);
 	unsigned long tmp;
@@ -121,11 +129,20 @@ found_first:
 		return result + size;   /* Nope. */
 found_middle:
 	return result + __reverse_ffs(tmp);
+#endif
 }
 
 static unsigned long __find_rev_next_zero_bit(const unsigned long *addr,
 			unsigned long size, unsigned long offset)
 {
+	while (f2fs_test_bit(offset, (unsigned char *)addr))
+		offset++;
+
+	if (offset > size)
+		offset = size;
+
+	return offset;
+#if 0
 	const unsigned long *p = addr + BIT_WORD(offset);
 	unsigned long result = offset & ~(BITS_PER_LONG - 1);
 	unsigned long tmp;
@@ -173,6 +190,7 @@ found_first:
 		return result + size;   /* Nope. */
 found_middle:
 	return result + __reverse_ffz(tmp);
+#endif
 }
 
 void register_inmem_page(struct inode *inode, struct page *page)
@@ -216,8 +234,10 @@ void commit_inmem_pages(struct inode *inode, bool abort)
 	struct inmem_pages *cur, *tmp;
 	bool submit_bio = false;
 	struct f2fs_io_info fio = {
+		.sbi = sbi,
 		.type = DATA,
 		.rw = WRITE_SYNC | REQ_PRIO,
+		.encrypted_page = NULL,
 	};
 
 	/*
@@ -241,7 +261,8 @@ void commit_inmem_pages(struct inode *inode, bool abort)
 				if (clear_page_dirty_for_io(cur->page))
 					inode_dec_dirty_pages(inode);
 				trace_f2fs_commit_inmem_page(cur->page, INMEM);
-				do_write_data_page(cur->page, &fio);
+				fio.page = cur->page;
+				do_write_data_page(&fio);
 				submit_bio = true;
 			}
 			f2fs_put_page(cur->page, 1);
@@ -466,22 +487,43 @@ static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
 {
 	sector_t start = SECTOR_FROM_BLOCK(blkstart);
 	sector_t len = SECTOR_FROM_BLOCK(blklen);
+	struct seg_entry *se;
+	unsigned int offset;
+	block_t i;
+
+	for (i = blkstart; i < blkstart + blklen; i++) {
+		se = get_seg_entry(sbi, GET_SEGNO(sbi, i));
+		offset = GET_BLKOFF_FROM_SEG0(sbi, i);
+
+		if (!f2fs_test_and_set_bit(offset, se->discard_map))
+			sbi->discard_blks--;
+	}
 	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
 	return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
 }
 
 void discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
 {
-	if (f2fs_issue_discard(sbi, blkaddr, 1)) {
-		struct page *page = grab_meta_page(sbi, blkaddr);
-		/* zero-filled page */
-		set_page_dirty(page);
-		f2fs_put_page(page, 1);
+	int err = -ENOTSUPP;
+
+	if (test_opt(sbi, DISCARD)) {
+		struct seg_entry *se = get_seg_entry(sbi,
+				GET_SEGNO(sbi, blkaddr));
+		unsigned int offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
+
+		if (f2fs_test_bit(offset, se->discard_map))
+			return;
+
+		err = f2fs_issue_discard(sbi, blkaddr, 1);
 	}
+
+	if (err)
+		update_meta_page(sbi, NULL, blkaddr);
 }
 
 static void __add_discard_entry(struct f2fs_sb_info *sbi,
-		struct cp_control *cpc, unsigned int start, unsigned int end)
+		struct cp_control *cpc, struct seg_entry *se,
+		unsigned int start, unsigned int end)
 {
 	struct list_head *head = &SM_I(sbi)->discard_list;
 	struct discard_entry *new, *last;
@@ -502,7 +544,6 @@ static void __add_discard_entry(struct f2fs_sb_info *sbi,
 	list_add_tail(&new->list, head);
 done:
 	SM_I(sbi)->nr_discards += end - start;
-	cpc->trimmed += end - start;
 }
 
 static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
@@ -512,41 +553,24 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start);
 	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
 	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
+	unsigned long *discard_map = (unsigned long *)se->discard_map;
 	unsigned long *dmap = SIT_I(sbi)->tmp_map;
 	unsigned int start = 0, end = -1;
 	bool force = (cpc->reason == CP_DISCARD);
 	int i;
 
-	if (!force && (!test_opt(sbi, DISCARD) ||
-			SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards))
+	if (se->valid_blocks == max_blocks)
 		return;
 
-	if (force && !se->valid_blocks) {
-		struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
-		/*
-		 * if this segment is registered in the prefree list, then
-		 * we should skip adding a discard candidate, and let the
-		 * checkpoint do that later.
-		 */
-		mutex_lock(&dirty_i->seglist_lock);
-		if (test_bit(cpc->trim_start, dirty_i->dirty_segmap[PRE])) {
-			mutex_unlock(&dirty_i->seglist_lock);
-			cpc->trimmed += sbi->blocks_per_seg;
+	if (!force) {
+		if (!test_opt(sbi, DISCARD) || !se->valid_blocks ||
+		    SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards)
 			return;
-		}
-		mutex_unlock(&dirty_i->seglist_lock);
-
-		__add_discard_entry(sbi, cpc, 0, sbi->blocks_per_seg);
-		return;
 	}
 
-	/* zero block will be discarded through the prefree list */
-	if (!se->valid_blocks || se->valid_blocks == max_blocks)
-		return;
-
 	/* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
 	for (i = 0; i < entries; i++)
-		dmap[i] = force ? ~ckpt_map[i] :
+		dmap[i] = force ? ~ckpt_map[i] & ~discard_map[i] :
 				(cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
 
 	while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
@@ -555,11 +579,7 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			break;
 
 		end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);
-
-		if (force && end - start < cpc->trim_minlen)
-			continue;
-
-		__add_discard_entry(sbi, cpc, start, end);
+		__add_discard_entry(sbi, cpc, se, start, end);
 	}
 }
 
@@ -589,7 +609,7 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
 	mutex_unlock(&dirty_i->seglist_lock);
 }
 
-void clear_prefree_segments(struct f2fs_sb_info *sbi)
+void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct list_head *head = &(SM_I(sbi)->discard_list);
 	struct discard_entry *entry, *this;
@@ -622,7 +642,11 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi)
 
 	/* send small discards */
 	list_for_each_entry_safe(entry, this, head, list) {
+		if (cpc->reason == CP_DISCARD && entry->len < cpc->trim_minlen)
+			goto skip;
 		f2fs_issue_discard(sbi, entry->blkaddr, entry->len);
+		cpc->trimmed += entry->len;
+skip:
 		list_del(&entry->list);
 		SM_I(sbi)->nr_discards -= entry->len;
 		kmem_cache_free(discard_entry_slab, entry);
@@ -673,9 +697,13 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 	if (del > 0) {
 		if (f2fs_test_and_set_bit(offset, se->cur_valid_map))
 			f2fs_bug_on(sbi, 1);
+		if (!f2fs_test_and_set_bit(offset, se->discard_map))
+			sbi->discard_blks--;
 	} else {
 		if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map))
 			f2fs_bug_on(sbi, 1);
+		if (f2fs_test_and_clear_bit(offset, se->discard_map))
+			sbi->discard_blks++;
 	}
 	if (!f2fs_test_bit(offset, se->ckpt_valid_map))
 		se->ckpt_valid_blocks += del;
@@ -769,16 +797,25 @@ struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
 	return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno));
 }
 
-static void write_sum_page(struct f2fs_sb_info *sbi,
-			struct f2fs_summary_block *sum_blk, block_t blk_addr)
+void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr)
 {
 	struct page *page = grab_meta_page(sbi, blk_addr);
-	void *kaddr = page_address(page);
-	memcpy(kaddr, sum_blk, PAGE_CACHE_SIZE);
+	void *dst = page_address(page);
+
+	if (src)
+		memcpy(dst, src, PAGE_CACHE_SIZE);
+	else
+		memset(dst, 0, PAGE_CACHE_SIZE);
 	set_page_dirty(page);
 	f2fs_put_page(page, 1);
 }
 
+static void write_sum_page(struct f2fs_sb_info *sbi,
+			struct f2fs_summary_block *sum_blk, block_t blk_addr)
+{
+	update_meta_page(sbi, (void *)sum_blk, blk_addr);
+}
+
 static int is_next_segment_free(struct f2fs_sb_info *sbi, int type)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -1060,8 +1097,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	unsigned int start_segno, end_segno;
 	struct cp_control cpc;
 
-	if (range->minlen > SEGMENT_SIZE(sbi) || start >= MAX_BLKADDR(sbi) ||
-						range->len < sbi->blocksize)
+	if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
 		return -EINVAL;
 
 	cpc.trimmed = 0;
@@ -1073,12 +1109,19 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
 						GET_SEGNO(sbi, end);
 	cpc.reason = CP_DISCARD;
-	cpc.trim_minlen = F2FS_BYTES_TO_BLK(range->minlen);
+	cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen));
 
 	/* do checkpoint to issue discard commands safely */
 	for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) {
 		cpc.trim_start = start_segno;
-		cpc.trim_end = min_t(unsigned int, rounddown(start_segno +
+
+		if (sbi->discard_blks == 0)
+			break;
+		else if (sbi->discard_blks < BATCHED_TRIM_BLOCKS(sbi))
+			cpc.trim_end = end_segno;
+		else
+			cpc.trim_end = min_t(unsigned int,
+				rounddown(start_segno +
 				BATCHED_TRIM_SEGMENTS(sbi),
 				sbi->segs_per_sec) - 1, end_segno);
 
@@ -1206,84 +1249,95 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	mutex_unlock(&curseg->curseg_mutex);
 }
 
-static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
-			struct f2fs_summary *sum,
-			struct f2fs_io_info *fio)
+static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
-	int type = __get_segment_type(page, fio->type);
+	int type = __get_segment_type(fio->page, fio->type);
 
-	allocate_data_block(sbi, page, fio->blk_addr, &fio->blk_addr, sum, type);
+	allocate_data_block(fio->sbi, fio->page, fio->blk_addr,
+					&fio->blk_addr, sum, type);
 
 	/* writeout dirty page into bdev */
-	f2fs_submit_page_mbio(sbi, page, fio);
+	f2fs_submit_page_mbio(fio);
 }
 
 void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 {
 	struct f2fs_io_info fio = {
+		.sbi = sbi,
 		.type = META,
 		.rw = WRITE_SYNC | REQ_META | REQ_PRIO,
 		.blk_addr = page->index,
+		.page = page,
+		.encrypted_page = NULL,
 	};
 
 	set_page_writeback(page);
-	f2fs_submit_page_mbio(sbi, page, &fio);
+	f2fs_submit_page_mbio(&fio);
 }
 
-void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
-			unsigned int nid, struct f2fs_io_info *fio)
+void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
 {
 	struct f2fs_summary sum;
+
 	set_summary(&sum, nid, 0, 0);
-	do_write_page(sbi, page, &sum, fio);
+	do_write_page(&sum, fio);
 }
 
-void write_data_page(struct page *page, struct dnode_of_data *dn,
-				struct f2fs_io_info *fio)
+void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
 {
-	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+	struct f2fs_sb_info *sbi = fio->sbi;
 	struct f2fs_summary sum;
 	struct node_info ni;
 
 	f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
-	do_write_page(sbi, page, &sum, fio);
+	do_write_page(&sum, fio);
 	dn->data_blkaddr = fio->blk_addr;
 }
 
-void rewrite_data_page(struct page *page, struct f2fs_io_info *fio)
+void rewrite_data_page(struct f2fs_io_info *fio)
 {
-	stat_inc_inplace_blocks(F2FS_P_SB(page));
-	f2fs_submit_page_mbio(F2FS_P_SB(page), page, fio);
+	stat_inc_inplace_blocks(fio->sbi);
+	f2fs_submit_page_mbio(fio);
 }
 
-void recover_data_page(struct f2fs_sb_info *sbi,
-			struct page *page, struct f2fs_summary *sum,
-			block_t old_blkaddr, block_t new_blkaddr)
+static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
+				struct f2fs_summary *sum,
+				block_t old_blkaddr, block_t new_blkaddr,
+				bool recover_curseg)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg;
 	unsigned int segno, old_cursegno;
 	struct seg_entry *se;
 	int type;
+	unsigned short old_blkoff;
 
 	segno = GET_SEGNO(sbi, new_blkaddr);
 	se = get_seg_entry(sbi, segno);
 	type = se->type;
 
-	if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) {
-		if (old_blkaddr == NULL_ADDR)
-			type = CURSEG_COLD_DATA;
-		else
+	if (!recover_curseg) {
+		/* for recovery flow */
+		if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) {
+			if (old_blkaddr == NULL_ADDR)
+				type = CURSEG_COLD_DATA;
+			else
+				type = CURSEG_WARM_DATA;
+		}
+	} else {
+		if (!IS_CURSEG(sbi, segno))
 			type = CURSEG_WARM_DATA;
 	}
+
 	curseg = CURSEG_I(sbi, type);
 
 	mutex_lock(&curseg->curseg_mutex);
 	mutex_lock(&sit_i->sentry_lock);
 
 	old_cursegno = curseg->segno;
+	old_blkoff = curseg->next_blkoff;
 
 	/* change the current segment */
 	if (segno != curseg->segno) {
@@ -1297,30 +1351,67 @@ void recover_data_page(struct f2fs_sb_info *sbi,
 	refresh_sit_entry(sbi, old_blkaddr, new_blkaddr);
 	locate_dirty_segment(sbi, old_cursegno);
 
+	if (recover_curseg) {
+		if (old_cursegno != curseg->segno) {
+			curseg->next_segno = old_cursegno;
+			change_curseg(sbi, type, true);
+		}
+		curseg->next_blkoff = old_blkoff;
+	}
+
 	mutex_unlock(&sit_i->sentry_lock);
 	mutex_unlock(&curseg->curseg_mutex);
 }
 
+void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
+				block_t old_addr, block_t new_addr,
+				unsigned char version, bool recover_curseg)
+{
+	struct f2fs_summary sum;
+
+	set_summary(&sum, dn->nid, dn->ofs_in_node, version);
+
+	__f2fs_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg);
+
+	dn->data_blkaddr = new_addr;
+	set_data_blkaddr(dn);
+	f2fs_update_extent_cache(dn);
+}
+
 static inline bool is_merged_page(struct f2fs_sb_info *sbi,
 					struct page *page, enum page_type type)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
 	struct f2fs_bio_info *io = &sbi->write_io[btype];
 	struct bio_vec *bvec;
+	struct page *target;
 	int i;
 
 	down_read(&io->io_rwsem);
-	if (!io->bio)
-		goto out;
+	if (!io->bio) {
+		up_read(&io->io_rwsem);
+		return false;
+	}
 
 	bio_for_each_segment_all(bvec, io->bio, i) {
-		if (page == bvec->bv_page) {
+
+		if (bvec->bv_page->mapping) {
+			target = bvec->bv_page;
+		} else {
+			struct f2fs_crypto_ctx *ctx;
+
+			/* encrypted page */
+			ctx = (struct f2fs_crypto_ctx *)page_private(
+								bvec->bv_page);
+			target = ctx->w.control_page;
+		}
+
+		if (page == target) {
 			up_read(&io->io_rwsem);
 			return true;
 		}
 	}
 
-out:
 	up_read(&io->io_rwsem);
 	return false;
 }
@@ -1857,8 +1948,11 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
 		sit_i->sentries[start].ckpt_valid_map
 			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
-		if (!sit_i->sentries[start].cur_valid_map
-				|| !sit_i->sentries[start].ckpt_valid_map)
+		sit_i->sentries[start].discard_map
+			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+		if (!sit_i->sentries[start].cur_valid_map ||
+				!sit_i->sentries[start].ckpt_valid_map ||
+				!sit_i->sentries[start].discard_map)
 			return -ENOMEM;
 	}
 
@@ -1996,6 +2090,11 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 got_it:
 			check_block_count(sbi, start, &sit);
 			seg_info_from_raw_sit(se, &sit);
+
+			/* build discard map only one time */
+			memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
+			sbi->discard_blks += sbi->blocks_per_seg - se->valid_blocks;
+
 			if (sbi->segs_per_sec > 1) {
 				struct sec_entry *e = get_sec_entry(sbi, start);
 				e->valid_blocks += se->valid_blocks;
@@ -2245,6 +2344,7 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
 		for (start = 0; start < MAIN_SEGS(sbi); start++) {
 			kfree(sit_i->sentries[start].cur_valid_map);
 			kfree(sit_i->sentries[start].ckpt_valid_map);
+			kfree(sit_i->sentries[start].discard_map);
 		}
 	}
 	kfree(sit_i->tmp_map);