Merge tag 'f2fs-for-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs update from Jaegeuk Kim:
 "In this round, there are a number of updates on mainly two areas:
  Zoned block device support and Per-file compression. For example,
  we've found several issues to support Zoned block device especially
  having large sections regarding to GC and file pinning used for
  Android devices. In compression side, we've fixed many corner race
  conditions that had broken the design assumption.

  Enhancements:
   - Support file pinning for Zoned block device having large section
   - Enhance the data recovery after sudden power cut on Zoned block
     device
   - Add more error injection cases to easily detect the kernel panics
   - add a proc entry show the entire disk layout
   - Improve various error paths paniced by BUG_ON in block allocation
     and GC
   - support SEEK_DATA and SEEK_HOLE for compression files

  Bug fixes:
   - avoid use-after-free issue in f2fs_filemap_fault
   - fix some race conditions to break the atomic write design
     assumption
   - fix to truncate meta inode pages forcely
   - resolve various per-file compression issues wrt the space
     management and compression policies
   - fix some swap-related bugs

  In addition, we removed deprecated codes such as io_bits and
  heap_allocation, and also fixed minor error handling routines with
  neat debugging messages"

* tag 'f2fs-for-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (60 commits)
  f2fs: fix to avoid use-after-free issue in f2fs_filemap_fault
  f2fs: truncate page cache before clearing flags when aborting atomic write
  f2fs: mark inode dirty for FI_ATOMIC_COMMITTED flag
  f2fs: prevent atomic write on pinned file
  f2fs: fix to handle error paths of {new,change}_curseg()
  f2fs: unify the error handling of f2fs_is_valid_blkaddr
  f2fs: zone: fix to remove pow2 check condition for zoned block device
  f2fs: fix to truncate meta inode pages forcely
  f2fs: compress: fix reserve_cblocks counting error when out of space
  f2fs: compress: relocate some judgments in f2fs_reserve_compress_blocks
  f2fs: add a proc entry show disk layout
  f2fs: introduce SEGS_TO_BLKS/BLKS_TO_SEGS for cleanup
  f2fs: fix to check return value of f2fs_gc_range
  f2fs: fix to check return value __allocate_new_segment
  f2fs: fix to do sanity check in update_sit_entry
  f2fs: fix to reset fields for unloaded curseg
  f2fs: clean up new_curseg()
  f2fs: relocate f2fs_precache_extents() in f2fs_swap_activate()
  f2fs: fix blkofs_end correctly in f2fs_migrate_blocks()
  f2fs: ro: don't start discard thread for readonly image
  ...

1 files changed, 67 insertions, 141 deletions

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index f6ffbfe75653..a6867f26f141 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -44,24 +44,26 @@ static struct kmem_cache *f2fs_inode_cachep;
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 
 const char *f2fs_fault_name[FAULT_MAX] = {
-	[FAULT_KMALLOC]		= "kmalloc",
-	[FAULT_KVMALLOC]	= "kvmalloc",
-	[FAULT_PAGE_ALLOC]	= "page alloc",
-	[FAULT_PAGE_GET]	= "page get",
-	[FAULT_ALLOC_NID]	= "alloc nid",
-	[FAULT_ORPHAN]		= "orphan",
-	[FAULT_BLOCK]		= "no more block",
-	[FAULT_DIR_DEPTH]	= "too big dir depth",
-	[FAULT_EVICT_INODE]	= "evict_inode fail",
-	[FAULT_TRUNCATE]	= "truncate fail",
-	[FAULT_READ_IO]		= "read IO error",
-	[FAULT_CHECKPOINT]	= "checkpoint error",
-	[FAULT_DISCARD]		= "discard error",
-	[FAULT_WRITE_IO]	= "write IO error",
-	[FAULT_SLAB_ALLOC]	= "slab alloc",
-	[FAULT_DQUOT_INIT]	= "dquot initialize",
-	[FAULT_LOCK_OP]		= "lock_op",
-	[FAULT_BLKADDR]		= "invalid blkaddr",
+	[FAULT_KMALLOC]			= "kmalloc",
+	[FAULT_KVMALLOC]		= "kvmalloc",
+	[FAULT_PAGE_ALLOC]		= "page alloc",
+	[FAULT_PAGE_GET]		= "page get",
+	[FAULT_ALLOC_NID]		= "alloc nid",
+	[FAULT_ORPHAN]			= "orphan",
+	[FAULT_BLOCK]			= "no more block",
+	[FAULT_DIR_DEPTH]		= "too big dir depth",
+	[FAULT_EVICT_INODE]		= "evict_inode fail",
+	[FAULT_TRUNCATE]		= "truncate fail",
+	[FAULT_READ_IO]			= "read IO error",
+	[FAULT_CHECKPOINT]		= "checkpoint error",
+	[FAULT_DISCARD]			= "discard error",
+	[FAULT_WRITE_IO]		= "write IO error",
+	[FAULT_SLAB_ALLOC]		= "slab alloc",
+	[FAULT_DQUOT_INIT]		= "dquot initialize",
+	[FAULT_LOCK_OP]			= "lock_op",
+	[FAULT_BLKADDR_VALIDITY]	= "invalid blkaddr",
+	[FAULT_BLKADDR_CONSISTENCE]	= "inconsistent blkaddr",
+	[FAULT_NO_SEGMENT]		= "no free segment",
 };
 
 void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
@@ -137,7 +139,6 @@ enum {
 	Opt_resgid,
 	Opt_resuid,
 	Opt_mode,
-	Opt_io_size_bits,
 	Opt_fault_injection,
 	Opt_fault_type,
 	Opt_lazytime,
@@ -216,7 +217,6 @@ static match_table_t f2fs_tokens = {
 	{Opt_resgid, "resgid=%u"},
 	{Opt_resuid, "resuid=%u"},
 	{Opt_mode, "mode=%s"},
-	{Opt_io_size_bits, "io_bits=%u"},
 	{Opt_fault_injection, "fault_injection=%u"},
 	{Opt_fault_type, "fault_type=%u"},
 	{Opt_lazytime, "lazytime"},
@@ -263,7 +263,8 @@ static match_table_t f2fs_tokens = {
 	{Opt_err, NULL},
 };
 
-void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...)
+void f2fs_printk(struct f2fs_sb_info *sbi, bool limit_rate,
+						const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
@@ -274,8 +275,12 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...)
 	level = printk_get_level(fmt);
 	vaf.fmt = printk_skip_level(fmt);
 	vaf.va = &args;
-	printk("%c%cF2FS-fs (%s): %pV\n",
-	       KERN_SOH_ASCII, level, sbi->sb->s_id, &vaf);
+	if (limit_rate)
+		printk_ratelimited("%c%cF2FS-fs (%s): %pV\n",
+			KERN_SOH_ASCII, level, sbi->sb->s_id, &vaf);
+	else
+		printk("%c%cF2FS-fs (%s): %pV\n",
+			KERN_SOH_ASCII, level, sbi->sb->s_id, &vaf);
 
 	va_end(args);
 }
@@ -343,46 +348,6 @@ static inline void limit_reserve_root(struct f2fs_sb_info *sbi)
 					   F2FS_OPTION(sbi).s_resgid));
 }
 
-static inline int adjust_reserved_segment(struct f2fs_sb_info *sbi)
-{
-	unsigned int sec_blks = sbi->blocks_per_seg * sbi->segs_per_sec;
-	unsigned int avg_vblocks;
-	unsigned int wanted_reserved_segments;
-	block_t avail_user_block_count;
-
-	if (!F2FS_IO_ALIGNED(sbi))
-		return 0;
-
-	/* average valid block count in section in worst case */
-	avg_vblocks = sec_blks / F2FS_IO_SIZE(sbi);
-
-	/*
-	 * we need enough free space when migrating one section in worst case
-	 */
-	wanted_reserved_segments = (F2FS_IO_SIZE(sbi) / avg_vblocks) *
-						reserved_segments(sbi);
-	wanted_reserved_segments -= reserved_segments(sbi);
-
-	avail_user_block_count = sbi->user_block_count -
-				sbi->current_reserved_blocks -
-				F2FS_OPTION(sbi).root_reserved_blocks;
-
-	if (wanted_reserved_segments * sbi->blocks_per_seg >
-					avail_user_block_count) {
-		f2fs_err(sbi, "IO align feature can't grab additional reserved segment: %u, available segments: %u",
-			wanted_reserved_segments,
-			avail_user_block_count >> sbi->log_blocks_per_seg);
-		return -ENOSPC;
-	}
-
-	SM_I(sbi)->additional_reserved_segments = wanted_reserved_segments;
-
-	f2fs_info(sbi, "IO align feature needs additional reserved segment: %u",
-			 wanted_reserved_segments);
-
-	return 0;
-}
-
 static inline void adjust_unusable_cap_perc(struct f2fs_sb_info *sbi)
 {
 	if (!F2FS_OPTION(sbi).unusable_cap_perc)
@@ -663,7 +628,7 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str)
 #ifdef CONFIG_F2FS_FS_ZSTD
 static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str)
 {
-	unsigned int level;
+	int level;
 	int len = 4;
 
 	if (strlen(str) == len) {
@@ -677,9 +642,15 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str)
 		f2fs_info(sbi, "wrong format, e.g. <alg_name>:<compr_level>");
 		return -EINVAL;
 	}
-	if (kstrtouint(str + 1, 10, &level))
+	if (kstrtoint(str + 1, 10, &level))
 		return -EINVAL;
 
+	/* f2fs does not support negative compress level now */
+	if (level < 0) {
+		f2fs_info(sbi, "do not support negative compress level: %d", level);
+		return -ERANGE;
+	}
+
 	if (!f2fs_is_compress_level_valid(COMPRESS_ZSTD, level)) {
 		f2fs_info(sbi, "invalid zstd compress level: %d", level);
 		return -EINVAL;
@@ -763,10 +734,8 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			clear_opt(sbi, DISCARD);
 			break;
 		case Opt_noheap:
-			set_opt(sbi, NOHEAP);
-			break;
 		case Opt_heap:
-			clear_opt(sbi, NOHEAP);
+			f2fs_warn(sbi, "heap/no_heap options were deprecated");
 			break;
 #ifdef CONFIG_F2FS_FS_XATTR
 		case Opt_user_xattr:
@@ -913,16 +882,6 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			}
 			kfree(name);
 			break;
-		case Opt_io_size_bits:
-			if (args->from && match_int(args, &arg))
-				return -EINVAL;
-			if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_VECS)) {
-				f2fs_warn(sbi, "Not support %ld, larger than %d",
-					BIT(arg), BIO_MAX_VECS);
-				return -EINVAL;
-			}
-			F2FS_OPTION(sbi).write_io_size_bits = arg;
-			break;
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 		case Opt_fault_injection:
 			if (args->from && match_int(args, &arg))
@@ -1392,12 +1351,6 @@ default_check:
 	}
 #endif
 
-	if (F2FS_IO_SIZE_BITS(sbi) && !f2fs_lfs_mode(sbi)) {
-		f2fs_err(sbi, "Should set mode=lfs with %luKB-sized IO",
-			 F2FS_IO_SIZE_KB(sbi));
-		return -EINVAL;
-	}
-
 	if (test_opt(sbi, INLINE_XATTR_SIZE)) {
 		int min_size, max_size;
 
@@ -1718,7 +1671,6 @@ static void f2fs_put_super(struct super_block *sb)
 
 	f2fs_destroy_page_array_cache(sbi);
 	f2fs_destroy_xattr_caches(sbi);
-	mempool_destroy(sbi->write_io_dummy);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < MAXQUOTAS; i++)
 		kfree(F2FS_OPTION(sbi).s_qf_names[i]);
@@ -2009,10 +1961,6 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 	} else {
 		seq_puts(seq, ",nodiscard");
 	}
-	if (test_opt(sbi, NOHEAP))
-		seq_puts(seq, ",no_heap");
-	else
-		seq_puts(seq, ",heap");
 #ifdef CONFIG_F2FS_FS_XATTR
 	if (test_opt(sbi, XATTR_USER))
 		seq_puts(seq, ",user_xattr");
@@ -2078,9 +2026,6 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 					F2FS_OPTION(sbi).s_resuid),
 				from_kgid_munged(&init_user_ns,
 					F2FS_OPTION(sbi).s_resgid));
-	if (F2FS_IO_SIZE_BITS(sbi))
-		seq_printf(seq, ",io_bits=%u",
-				F2FS_OPTION(sbi).write_io_size_bits);
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	if (test_opt(sbi, FAULT_INJECTION)) {
 		seq_printf(seq, ",fault_injection=%u",
@@ -2192,7 +2137,6 @@ static void default_options(struct f2fs_sb_info *sbi, bool remount)
 	set_opt(sbi, INLINE_XATTR);
 	set_opt(sbi, INLINE_DATA);
 	set_opt(sbi, INLINE_DENTRY);
-	set_opt(sbi, NOHEAP);
 	set_opt(sbi, MERGE_CHECKPOINT);
 	F2FS_OPTION(sbi).unusable_cap = 0;
 	sbi->sb->s_flags |= SB_LAZYTIME;
@@ -2247,6 +2191,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 			.init_gc_type = FG_GC,
 			.should_migrate_blocks = false,
 			.err_gc_skipped = true,
+			.no_bg_gc = true,
 			.nr_free_secs = 1 };
 
 		f2fs_down_write(&sbi->gc_lock);
@@ -2332,7 +2277,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	bool no_read_extent_cache = !test_opt(sbi, READ_EXTENT_CACHE);
 	bool no_age_extent_cache = !test_opt(sbi, AGE_EXTENT_CACHE);
 	bool enable_checkpoint = !test_opt(sbi, DISABLE_CHECKPOINT);
-	bool no_io_align = !F2FS_IO_ALIGNED(sbi);
 	bool no_atgc = !test_opt(sbi, ATGC);
 	bool no_discard = !test_opt(sbi, DISCARD);
 	bool no_compress_cache = !test_opt(sbi, COMPRESS_CACHE);
@@ -2440,12 +2384,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 		goto restore_opts;
 	}
 
-	if (no_io_align == !!F2FS_IO_ALIGNED(sbi)) {
-		err = -EINVAL;
-		f2fs_warn(sbi, "switch io_bits option is not allowed");
-		goto restore_opts;
-	}
-
 	if (no_compress_cache == !!test_opt(sbi, COMPRESS_CACHE)) {
 		err = -EINVAL;
 		f2fs_warn(sbi, "switch compress_cache option is not allowed");
@@ -3706,7 +3644,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	}
 
 	main_segs = le32_to_cpu(raw_super->segment_count_main);
-	blocks_per_seg = sbi->blocks_per_seg;
+	blocks_per_seg = BLKS_PER_SEG(sbi);
 
 	for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
 		if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs ||
@@ -3818,9 +3756,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	sbi->segs_per_sec = le32_to_cpu(raw_super->segs_per_sec);
 	sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone);
 	sbi->total_sections = le32_to_cpu(raw_super->section_count);
-	sbi->total_node_count =
-		(le32_to_cpu(raw_super->segment_count_nat) / 2)
-			* sbi->blocks_per_seg * NAT_ENTRY_PER_BLOCK;
+	sbi->total_node_count = SEGS_TO_BLKS(sbi,
+			((le32_to_cpu(raw_super->segment_count_nat) / 2) *
+			NAT_ENTRY_PER_BLOCK));
 	F2FS_ROOT_INO(sbi) = le32_to_cpu(raw_super->root_ino);
 	F2FS_NODE_INO(sbi) = le32_to_cpu(raw_super->node_ino);
 	F2FS_META_INO(sbi) = le32_to_cpu(raw_super->meta_ino);
@@ -3829,7 +3767,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	sbi->next_victim_seg[BG_GC] = NULL_SEGNO;
 	sbi->next_victim_seg[FG_GC] = NULL_SEGNO;
 	sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH;
-	sbi->migration_granularity = sbi->segs_per_sec;
+	sbi->migration_granularity = SEGS_PER_SEC(sbi);
 	sbi->seq_file_ra_mul = MIN_RA_MUL;
 	sbi->max_fragment_chunk = DEF_FRAGMENT_SIZE;
 	sbi->max_fragment_hole = DEF_FRAGMENT_SIZE;
@@ -3930,11 +3868,6 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
 		return 0;
 
 	zone_sectors = bdev_zone_sectors(bdev);
-	if (!is_power_of_2(zone_sectors)) {
-		f2fs_err(sbi, "F2FS does not support non power of 2 zone sizes\n");
-		return -EINVAL;
-	}
-
 	if (sbi->blocks_per_blkz && sbi->blocks_per_blkz !=
 				SECTOR_TO_BLOCK(zone_sectors))
 		return -EINVAL;
@@ -4090,7 +4023,9 @@ static void f2fs_record_stop_reason(struct f2fs_sb_info *sbi)
 
 	f2fs_up_write(&sbi->sb_lock);
 	if (err)
-		f2fs_err(sbi, "f2fs_commit_super fails to record err:%d", err);
+		f2fs_err_ratelimited(sbi,
+			"f2fs_commit_super fails to record stop_reason, err:%d",
+			err);
 }
 
 void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag)
@@ -4133,8 +4068,9 @@ static void f2fs_record_errors(struct f2fs_sb_info *sbi, unsigned char error)
 
 	err = f2fs_commit_super(sbi, false);
 	if (err)
-		f2fs_err(sbi, "f2fs_commit_super fails to record errors:%u, err:%d",
-								error, err);
+		f2fs_err_ratelimited(sbi,
+			"f2fs_commit_super fails to record errors:%u, err:%d",
+			error, err);
 out_unlock:
 	f2fs_up_write(&sbi->sb_lock);
 }
@@ -4259,14 +4195,14 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 			if (i == 0) {
 				FDEV(i).start_blk = 0;
 				FDEV(i).end_blk = FDEV(i).start_blk +
-				    (FDEV(i).total_segments <<
-				    sbi->log_blocks_per_seg) - 1 +
-				    le32_to_cpu(raw_super->segment0_blkaddr);
+					SEGS_TO_BLKS(sbi,
+					FDEV(i).total_segments) - 1 +
+					le32_to_cpu(raw_super->segment0_blkaddr);
 			} else {
 				FDEV(i).start_blk = FDEV(i - 1).end_blk + 1;
 				FDEV(i).end_blk = FDEV(i).start_blk +
-					(FDEV(i).total_segments <<
-					sbi->log_blocks_per_seg) - 1;
+						SEGS_TO_BLKS(sbi,
+						FDEV(i).total_segments) - 1;
 				FDEV(i).bdev_file = bdev_file_open_by_path(
 					FDEV(i).path, mode, sbi->sb, NULL);
 			}
@@ -4305,8 +4241,6 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 			  FDEV(i).total_segments,
 			  FDEV(i).start_blk, FDEV(i).end_blk);
 	}
-	f2fs_info(sbi,
-		  "IO Block Size: %8ld KB", F2FS_IO_SIZE_KB(sbi));
 	return 0;
 }
 
@@ -4519,19 +4453,10 @@ try_onemore:
 	if (err)
 		goto free_iostat;
 
-	if (F2FS_IO_ALIGNED(sbi)) {
-		sbi->write_io_dummy =
-			mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 0);
-		if (!sbi->write_io_dummy) {
-			err = -ENOMEM;
-			goto free_percpu;
-		}
-	}
-
 	/* init per sbi slab cache */
 	err = f2fs_init_xattr_caches(sbi);
 	if (err)
-		goto free_io_dummy;
+		goto free_percpu;
 	err = f2fs_init_page_array_cache(sbi);
 	if (err)
 		goto free_xattr_cache;
@@ -4619,10 +4544,6 @@ try_onemore:
 		goto free_nm;
 	}
 
-	err = adjust_reserved_segment(sbi);
-	if (err)
-		goto free_nm;
-
 	/* For write statistics */
 	sbi->sectors_written_start = f2fs_get_sectors_written(sbi);
 
@@ -4749,13 +4670,20 @@ reset_checkpoint:
 	 * If the f2fs is not readonly and fsync data recovery succeeds,
 	 * check zoned block devices' write pointer consistency.
 	 */
-	if (!err && !f2fs_readonly(sb) && f2fs_sb_has_blkzoned(sbi)) {
-		err = f2fs_check_write_pointer(sbi);
-		if (err)
-			goto free_meta;
+	if (f2fs_sb_has_blkzoned(sbi) && !f2fs_readonly(sb)) {
+		int err2;
+
+		f2fs_notice(sbi, "Checking entire write pointers");
+		err2 = f2fs_check_write_pointer(sbi);
+		if (err2)
+			err = err2;
 	}
+	if (err)
+		goto free_meta;
 
-	f2fs_init_inmem_curseg(sbi);
+	err = f2fs_init_inmem_curseg(sbi);
+	if (err)
+		goto sync_free_meta;
 
 	/* f2fs_recover_fsync_data() cleared this already */
 	clear_sbi_flag(sbi, SBI_POR_DOING);
@@ -4854,8 +4782,6 @@ free_page_array_cache:
 	f2fs_destroy_page_array_cache(sbi);
 free_xattr_cache:
 	f2fs_destroy_xattr_caches(sbi);
-free_io_dummy:
-	mempool_destroy(sbi->write_io_dummy);
 free_percpu:
 	destroy_percpu_info(sbi);
 free_iostat: