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
  ...

Author: torvalds

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -205,15 +205,15 @@ Description:	Controls the idle timing of system, if there is no FS operation
 What:		/sys/fs/f2fs/<disk>/discard_idle_interval
 Date:		September 2018
 Contact:	"Chao Yu" <[email protected]>
-Contact:	"Sahitya Tummala" <[email protected]>
+Contact:	"Sahitya Tummala" <[email protected]>
 Description:	Controls the idle timing of discard thread given
 		this time interval.
 		Default is 5 secs.
 
 What:		/sys/fs/f2fs/<disk>/gc_idle_interval
 Date:		September 2018
 Contact:	"Chao Yu" <[email protected]>
-Contact:	"Sahitya Tummala" <[email protected]>
+Contact:	"Sahitya Tummala" <[email protected]>
 Description:    Controls the idle timing for gc path. Set to 5 seconds by default.
 
 What:		/sys/fs/f2fs/<disk>/iostat_enable
@@ -701,29 +701,31 @@ Description:	Support configuring fault injection type, should be
 		enabled with fault_injection option, fault type value
 		is shown below, it supports single or combined type.
 
-		===================      ===========
-		Type_Name                Type_Value
-		===================      ===========
-		FAULT_KMALLOC            0x000000001
-		FAULT_KVMALLOC           0x000000002
-		FAULT_PAGE_ALLOC         0x000000004
-		FAULT_PAGE_GET           0x000000008
-		FAULT_ALLOC_BIO          0x000000010 (obsolete)
-		FAULT_ALLOC_NID          0x000000020
-		FAULT_ORPHAN             0x000000040
-		FAULT_BLOCK              0x000000080
-		FAULT_DIR_DEPTH          0x000000100
-		FAULT_EVICT_INODE        0x000000200
-		FAULT_TRUNCATE           0x000000400
-		FAULT_READ_IO            0x000000800
-		FAULT_CHECKPOINT         0x000001000
-		FAULT_DISCARD            0x000002000
-		FAULT_WRITE_IO           0x000004000
-		FAULT_SLAB_ALLOC         0x000008000
-		FAULT_DQUOT_INIT         0x000010000
-		FAULT_LOCK_OP            0x000020000
-		FAULT_BLKADDR            0x000040000
-		===================      ===========
+		===========================      ===========
+		Type_Name                        Type_Value
+		===========================      ===========
+		FAULT_KMALLOC                    0x000000001
+		FAULT_KVMALLOC                   0x000000002
+		FAULT_PAGE_ALLOC                 0x000000004
+		FAULT_PAGE_GET                   0x000000008
+		FAULT_ALLOC_BIO                  0x000000010 (obsolete)
+		FAULT_ALLOC_NID                  0x000000020
+		FAULT_ORPHAN                     0x000000040
+		FAULT_BLOCK                      0x000000080
+		FAULT_DIR_DEPTH                  0x000000100
+		FAULT_EVICT_INODE                0x000000200
+		FAULT_TRUNCATE                   0x000000400
+		FAULT_READ_IO                    0x000000800
+		FAULT_CHECKPOINT                 0x000001000
+		FAULT_DISCARD                    0x000002000
+		FAULT_WRITE_IO                   0x000004000
+		FAULT_SLAB_ALLOC                 0x000008000
+		FAULT_DQUOT_INIT                 0x000010000
+		FAULT_LOCK_OP                    0x000020000
+		FAULT_BLKADDR_VALIDITY           0x000040000
+		FAULT_BLKADDR_CONSISTENCE        0x000080000
+		FAULT_NO_SEGMENT                 0x000100000
+		===========================      ===========
 
 What:		/sys/fs/f2fs/<disk>/discard_io_aware_gran
 Date:		January 2023

Documentation/filesystems/f2fs.rst

@@ -126,9 +126,7 @@ norecovery		 Disable the roll-forward recovery routine, mounted read-
 discard/nodiscard	 Enable/disable real-time discard in f2fs, if discard is
 			 enabled, f2fs will issue discard/TRIM commands when a
 			 segment is cleaned.
-no_heap			 Disable heap-style segment allocation which finds free
-			 segments for data from the beginning of main area, while
-			 for node from the end of main area.
+heap/no_heap		 Deprecated.
 nouser_xattr		 Disable Extended User Attributes. Note: xattr is enabled
 			 by default if CONFIG_F2FS_FS_XATTR is selected.
 noacl			 Disable POSIX Access Control List. Note: acl is enabled
@@ -184,29 +182,31 @@ fault_type=%d		 Support configuring fault injection type, should be
 			 enabled with fault_injection option, fault type value
 			 is shown below, it supports single or combined type.
 
-			 ===================	  ===========
-			 Type_Name		  Type_Value
-			 ===================	  ===========
-			 FAULT_KMALLOC		  0x000000001
-			 FAULT_KVMALLOC		  0x000000002
-			 FAULT_PAGE_ALLOC	  0x000000004
-			 FAULT_PAGE_GET		  0x000000008
-			 FAULT_ALLOC_BIO	  0x000000010 (obsolete)
-			 FAULT_ALLOC_NID	  0x000000020
-			 FAULT_ORPHAN		  0x000000040
-			 FAULT_BLOCK		  0x000000080
-			 FAULT_DIR_DEPTH	  0x000000100
-			 FAULT_EVICT_INODE	  0x000000200
-			 FAULT_TRUNCATE		  0x000000400
-			 FAULT_READ_IO		  0x000000800
-			 FAULT_CHECKPOINT	  0x000001000
-			 FAULT_DISCARD		  0x000002000
-			 FAULT_WRITE_IO		  0x000004000
-			 FAULT_SLAB_ALLOC	  0x000008000
-			 FAULT_DQUOT_INIT	  0x000010000
-			 FAULT_LOCK_OP		  0x000020000
-			 FAULT_BLKADDR		  0x000040000
-			 ===================	  ===========
+			 ===========================      ===========
+			 Type_Name                        Type_Value
+			 ===========================      ===========
+			 FAULT_KMALLOC                    0x000000001
+			 FAULT_KVMALLOC                   0x000000002
+			 FAULT_PAGE_ALLOC                 0x000000004
+			 FAULT_PAGE_GET                   0x000000008
+			 FAULT_ALLOC_BIO                  0x000000010 (obsolete)
+			 FAULT_ALLOC_NID                  0x000000020
+			 FAULT_ORPHAN                     0x000000040
+			 FAULT_BLOCK                      0x000000080
+			 FAULT_DIR_DEPTH                  0x000000100
+			 FAULT_EVICT_INODE                0x000000200
+			 FAULT_TRUNCATE                   0x000000400
+			 FAULT_READ_IO                    0x000000800
+			 FAULT_CHECKPOINT                 0x000001000
+			 FAULT_DISCARD                    0x000002000
+			 FAULT_WRITE_IO                   0x000004000
+			 FAULT_SLAB_ALLOC                 0x000008000
+			 FAULT_DQUOT_INIT                 0x000010000
+			 FAULT_LOCK_OP                    0x000020000
+			 FAULT_BLKADDR_VALIDITY           0x000040000
+			 FAULT_BLKADDR_CONSISTENCE        0x000080000
+			 FAULT_NO_SEGMENT                 0x000100000
+			 ===========================      ===========
 mode=%s			 Control block allocation mode which supports "adaptive"
 			 and "lfs". In "lfs" mode, there should be no random
 			 writes towards main area.
@@ -228,8 +228,6 @@ mode=%s			 Control block allocation mode which supports "adaptive"
 			 option for more randomness.
 			 Please, use these options for your experiments and we strongly
 			 recommend to re-format the filesystem after using these options.
-io_bits=%u		 Set the bit size of write IO requests. It should be set
-			 with "mode=lfs".
 usrquota		 Enable plain user disk quota accounting.
 grpquota		 Enable plain group disk quota accounting.
 prjquota		 Enable plain project quota accounting.

fs/f2fs/checkpoint.c

@@ -154,49 +154,47 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
 	if (unlikely(f2fs_cp_error(sbi)))
 		return exist;
 
-	if (exist && type == DATA_GENERIC_ENHANCE_UPDATE) {
-		f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
-			 blkaddr, exist);
-		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		return exist;
-	}
+	if ((exist && type == DATA_GENERIC_ENHANCE_UPDATE) ||
+		(!exist && type == DATA_GENERIC_ENHANCE))
+		goto out_err;
+	if (!exist && type != DATA_GENERIC_ENHANCE_UPDATE)
+		goto out_handle;
+	return exist;
 
-	if (!exist && type == DATA_GENERIC_ENHANCE) {
-		f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
-			 blkaddr, exist);
-		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		dump_stack();
-	}
+out_err:
+	f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
+		 blkaddr, exist);
+	set_sbi_flag(sbi, SBI_NEED_FSCK);
+	dump_stack();
+out_handle:
+	f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
 	return exist;
 }
 
-bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+static bool __f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 					block_t blkaddr, int type)
 {
-	if (time_to_inject(sbi, FAULT_BLKADDR))
-		return false;
-
 	switch (type) {
 	case META_NAT:
 		break;
 	case META_SIT:
 		if (unlikely(blkaddr >= SIT_BLK_CNT(sbi)))
-			return false;
+			goto err;
 		break;
 	case META_SSA:
 		if (unlikely(blkaddr >= MAIN_BLKADDR(sbi) ||
 			blkaddr < SM_I(sbi)->ssa_blkaddr))
-			return false;
+			goto err;
 		break;
 	case META_CP:
 		if (unlikely(blkaddr >= SIT_I(sbi)->sit_base_addr ||
 			blkaddr < __start_cp_addr(sbi)))
-			return false;
+			goto err;
 		break;
 	case META_POR:
 		if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
 			blkaddr < MAIN_BLKADDR(sbi)))
-			return false;
+			goto err;
 		break;
 	case DATA_GENERIC:
 	case DATA_GENERIC_ENHANCE:
@@ -213,21 +211,38 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 				  blkaddr);
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
 			dump_stack();
-			return false;
+			goto err;
 		} else {
 			return __is_bitmap_valid(sbi, blkaddr, type);
 		}
 		break;
 	case META_GENERIC:
 		if (unlikely(blkaddr < SEG0_BLKADDR(sbi) ||
 			blkaddr >= MAIN_BLKADDR(sbi)))
-			return false;
+			goto err;
 		break;
 	default:
 		BUG();
 	}
 
 	return true;
+err:
+	f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
+	return false;
+}
+
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+					block_t blkaddr, int type)
+{
+	if (time_to_inject(sbi, FAULT_BLKADDR_VALIDITY))
+		return false;
+	return __f2fs_is_valid_blkaddr(sbi, blkaddr, type);
+}
+
+bool f2fs_is_valid_blkaddr_raw(struct f2fs_sb_info *sbi,
+					block_t blkaddr, int type)
+{
+	return __f2fs_is_valid_blkaddr(sbi, blkaddr, type);
 }
 
 /*
@@ -889,7 +904,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 
 	cp_blocks = le32_to_cpu(cp_block->cp_pack_total_block_count);
 
-	if (cp_blocks > sbi->blocks_per_seg || cp_blocks <= F2FS_CP_PACKS) {
+	if (cp_blocks > BLKS_PER_SEG(sbi) || cp_blocks <= F2FS_CP_PACKS) {
 		f2fs_warn(sbi, "invalid cp_pack_total_block_count:%u",
 			  le32_to_cpu(cp_block->cp_pack_total_block_count));
 		goto invalid_cp;
@@ -1324,7 +1339,7 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	if (cpc->reason & CP_UMOUNT) {
 		if (le32_to_cpu(ckpt->cp_pack_total_block_count) +
-			NM_I(sbi)->nat_bits_blocks > sbi->blocks_per_seg) {
+			NM_I(sbi)->nat_bits_blocks > BLKS_PER_SEG(sbi)) {
 			clear_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
 			f2fs_notice(sbi, "Disable nat_bits due to no space");
 		} else if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG) &&
@@ -1527,7 +1542,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		cp_ver |= ((__u64)crc32 << 32);
 		*(__le64 *)nm_i->nat_bits = cpu_to_le64(cp_ver);
 
-		blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks;
+		blk = start_blk + BLKS_PER_SEG(sbi) - nm_i->nat_bits_blocks;
 		for (i = 0; i < nm_i->nat_bits_blocks; i++)
 			f2fs_update_meta_page(sbi, nm_i->nat_bits +
 					(i << F2FS_BLKSIZE_BITS), blk + i);
@@ -1587,8 +1602,9 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	 */
 	if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi) ||
 		f2fs_sb_has_compression(sbi))
-		invalidate_mapping_pages(META_MAPPING(sbi),
-				MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1);
+		f2fs_bug_on(sbi,
+			invalidate_inode_pages2_range(META_MAPPING(sbi),
+				MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1));
 
 	f2fs_release_ino_entry(sbi, false);
 
@@ -1730,9 +1746,9 @@ void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi)
 		im->ino_num = 0;
 	}
 
-	sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS -
+	sbi->max_orphans = (BLKS_PER_SEG(sbi) - F2FS_CP_PACKS -
 			NR_CURSEG_PERSIST_TYPE - __cp_payload(sbi)) *
-				F2FS_ORPHANS_PER_BLOCK;
+			F2FS_ORPHANS_PER_BLOCK;
 }
 
 int __init f2fs_create_checkpoint_caches(void)