Adding upstream version 6.9.7.upstream/6.9.7

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 75 insertions, 145 deletions

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 4ba613ed3a..2f75a7dfc3 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)
@@ -769,10 +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:
@@ -919,16 +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))
@@ -1398,12 +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;
 
@@ -1611,7 +1558,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < sbi->s_ndevs; i++) {
 		if (i > 0)
-			bdev_release(FDEV(i).bdev_handle);
+			bdev_fput(FDEV(i).bdev_file);
 #ifdef CONFIG_BLK_DEV_ZONED
 		kvfree(FDEV(i).blkz_seq);
 #endif
@@ -1724,7 +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]);
@@ -2015,10 +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");
@@ -2084,9 +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",
@@ -2193,12 +2132,9 @@ static void default_options(struct f2fs_sb_info *sbi, bool remount)
 	F2FS_OPTION(sbi).memory_mode = MEMORY_MODE_NORMAL;
 	F2FS_OPTION(sbi).errors = MOUNT_ERRORS_CONTINUE;
 
-	sbi->sb->s_flags &= ~SB_INLINECRYPT;
-
 	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;
@@ -2253,6 +2189,7 @@ 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);
@@ -2338,7 +2275,6 @@ 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);
@@ -2446,12 +2382,6 @@ 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");
@@ -3712,7 +3642,7 @@ 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 ||
@@ -3824,9 +3754,9 @@ 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);
@@ -3835,7 +3765,7 @@ 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;
@@ -4091,7 +4021,9 @@ 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)
@@ -4134,8 +4066,9 @@ 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);
 }
@@ -4196,9 +4129,15 @@ void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason,
 	if (shutdown)
 		set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
 
-	/* continue filesystem operators if errors=continue */
-	if (continue_fs || f2fs_readonly(sb))
+	/*
+	 * Continue filesystem operators if errors=continue. Should not set
+	 * RO by shutdown, since RO bypasses thaw_super which can hang the
+	 * system.
+	 */
+	if (continue_fs || f2fs_readonly(sb) || shutdown) {
+		f2fs_warn(sbi, "Stopped filesystem due to reason: %d", reason);
 		return;
+	}
 
 	f2fs_warn(sbi, "Remounting filesystem read-only");
 	/*
@@ -4248,7 +4187,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < max_devices; i++) {
 		if (i == 0)
-			FDEV(0).bdev_handle = sbi->sb->s_bdev_handle;
+			FDEV(0).bdev_file = sbi->sb->s_bdev_file;
 		else if (!RDEV(i).path[0])
 			break;
 
@@ -4260,22 +4199,22 @@ 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;
-				FDEV(i).bdev_handle = bdev_open_by_path(
+						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);
 			}
 		}
-		if (IS_ERR(FDEV(i).bdev_handle))
-			return PTR_ERR(FDEV(i).bdev_handle);
+		if (IS_ERR(FDEV(i).bdev_file))
+			return PTR_ERR(FDEV(i).bdev_file);
 
-		FDEV(i).bdev = FDEV(i).bdev_handle->bdev;
+		FDEV(i).bdev = file_bdev(FDEV(i).bdev_file);
 		/* to release errored devices */
 		sbi->s_ndevs = i + 1;
 
@@ -4306,8 +4245,6 @@ 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;
 }
 
@@ -4497,7 +4434,7 @@ try_onemore:
 	sb->s_time_gran = 1;
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
 		(test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
-	memcpy(&sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
+	super_set_uuid(sb, (void *) raw_super->uuid, sizeof(raw_super->uuid));
 	sb->s_iflags |= SB_I_CGROUPWB;
 
 	/* init f2fs-specific super block info */
@@ -4520,19 +4457,10 @@ 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;
@@ -4620,10 +4548,6 @@ 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);
 
@@ -4661,6 +4585,7 @@ try_onemore:
 		goto free_node_inode;
 	}
 
+	generic_set_sb_d_ops(sb);
 	sb->s_root = d_make_root(root); /* allocate root dentry */
 	if (!sb->s_root) {
 		err = -ENOMEM;
@@ -4749,13 +4674,20 @@ 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 +4786,6 @@ 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: