Merge branch 'upstream-f2fs-stable-linux-4.19.y' of https://mirrors.bfsu.edu.cn/git/AOSP/kernel/common into ack

Author: Molyuu

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -96,6 +96,12 @@ Description:	Controls the issue rate of discard commands that consist of small
 		checkpoint is triggered, and issued during the checkpoint.
 		By default, it is disabled with 0.
 
+What:		/sys/fs/f2fs/<disk>/max_ordered_discard
+Date:		October 2022
+Contact:	"Yangtao Li" <[email protected]>
+Description:	Controls the maximum ordered discard, the unit size is one block(4KB).
+		Set it to 16 by default.
+
 What:		/sys/fs/f2fs/<disk>/max_discard_request
 Date:		December 2021
 Contact:	"Konstantin Vyshetsky" <[email protected]>
@@ -129,7 +135,8 @@ Contact:	"Chao Yu" <[email protected]>
 Description:	Controls discard granularity of inner discard thread. Inner thread
 		will not issue discards with size that is smaller than granularity.
 		The unit size is one block(4KB), now only support configuring
-		in range of [1, 512]. Default value is 4(=16KB).
+		in range of [1, 512]. Default value is 16.
+		For small devices, default value is 1.
 
 What:		/sys/fs/f2fs/<disk>/umount_discard_timeout
 Date:		January 2019
@@ -232,7 +239,7 @@ Description:	Shows total written kbytes issued to disk.
 What:		/sys/fs/f2fs/<disk>/features
 Date:		July 2017
 Contact:	"Jaegeuk Kim" <[email protected]>
-Description:	<deprecated: should use /sys/fs/f2fs/<disk>/feature_list/
+Description:	<deprecated: should use /sys/fs/f2fs/<disk>/feature_list/>
 		Shows all enabled features in current device.
 		Supported features:
 		encryption, blkzoned, extra_attr, projquota, inode_checksum,
@@ -453,6 +460,30 @@ Description:	Show status of f2fs superblock in real time.
 		0x4000 SBI_IS_FREEZING       freefs is in process
 		====== ===================== =================================
 
+What:		/sys/fs/f2fs/<disk>/stat/cp_status
+Date:		September 2022
+Contact:	"Chao Yu" <[email protected]>
+Description:	Show status of f2fs checkpoint in real time.
+
+		=============================== ==============================
+		cp flag				value
+		CP_UMOUNT_FLAG			0x00000001
+		CP_ORPHAN_PRESENT_FLAG		0x00000002
+		CP_COMPACT_SUM_FLAG		0x00000004
+		CP_ERROR_FLAG			0x00000008
+		CP_FSCK_FLAG			0x00000010
+		CP_FASTBOOT_FLAG		0x00000020
+		CP_CRC_RECOVERY_FLAG		0x00000040
+		CP_NAT_BITS_FLAG		0x00000080
+		CP_TRIMMED_FLAG			0x00000100
+		CP_NOCRC_RECOVERY_FLAG		0x00000200
+		CP_LARGE_NAT_BITMAP_FLAG	0x00000400
+		CP_QUOTA_NEED_FSCK_FLAG		0x00000800
+		CP_DISABLED_FLAG		0x00001000
+		CP_DISABLED_QUICK_FLAG		0x00002000
+		CP_RESIZEFS_FLAG		0x00004000
+		=============================== ==============================
+
 What:		/sys/fs/f2fs/<disk>/ckpt_thread_ioprio
 Date:		January 2021
 Contact:	"Daeho Jeong" <[email protected]>
@@ -549,10 +580,10 @@ Description:	With "mode=fragment:block" mount options, we can scatter block allo
 		in the length of 1..<max_fragment_hole> by turns. This value can be set
 		between 1..512 and the default value is 4.
 
-What:		/sys/fs/f2fs/<disk>/gc_urgent_high_remaining
-Date:		December 2021
-Contact:	"Daeho Jeong" <daehojeong@google.com>
-Description:	You can set the trial count limit for GC urgent high mode with this value.
+What:		/sys/fs/f2fs/<disk>/gc_remaining_trials
+Date:		October 2022
+Contact:	"Yangtao Li" <frank.li@vivo.com>
+Description:	You can set the trial count limit for GC urgent and idle mode with this value.
 		If GC thread gets to the limit, the mode will turn back to GC normal mode.
 		By default, the value is zero, which means there is no limit like before.
 
@@ -561,3 +592,55 @@ Date:		January 2022
 Contact:	"Jaegeuk Kim" <[email protected]>
 Description:	Controls max # of node block writes to be used for roll forward
 		recovery. This can limit the roll forward recovery time.
+
+What:		/sys/fs/f2fs/<disk>/current_atomic_write
+Date:		July 2022
+Contact:	"Daeho Jeong" <[email protected]>
+Description:	Show the total current atomic write block count, which is not committed yet.
+		This is a read-only entry.
+
+What:		/sys/fs/f2fs/<disk>/peak_atomic_write
+Date:		July 2022
+Contact:	"Daeho Jeong" <[email protected]>
+Description:	Show the peak value of total current atomic write block count after boot.
+		If you write "0" here, you can initialize to "0".
+
+What:		/sys/fs/f2fs/<disk>/committed_atomic_block
+Date:		July 2022
+Contact:	"Daeho Jeong" <[email protected]>
+Description:	Show the accumulated total committed atomic write block count after boot.
+		If you write "0" here, you can initialize to "0".
+
+What:		/sys/fs/f2fs/<disk>/revoked_atomic_block
+Date:		July 2022
+Contact:	"Daeho Jeong" <[email protected]>
+Description:	Show the accumulated total revoked atomic write block count after boot.
+		If you write "0" here, you can initialize to "0".
+
+What:		/sys/fs/f2fs/<disk>/gc_mode
+Date:		October 2022
+Contact:	"Yangtao Li" <[email protected]>
+Description:	Show the current gc_mode as a string.
+		This is a read-only entry.
+
+What:		/sys/fs/f2fs/<disk>/discard_urgent_util
+Date:		November 2022
+Contact:	"Yangtao Li" <[email protected]>
+Description:	When space utilization exceeds this, do background DISCARD aggressively.
+		Does DISCARD forcibly in a period of given min_discard_issue_time when the number
+		of discards is not 0 and set discard granularity to 1.
+		Default: 80
+
+What:		/sys/fs/f2fs/<disk>/hot_data_age_threshold
+Date:		November 2022
+Contact:	"Ping Xiong" <[email protected]>
+Description:	When DATA SEPARATION is on, it controls the age threshold to indicate
+		the data blocks as hot. By default it was initialized as 262144 blocks
+		(equals to 1GB).
+
+What:		/sys/fs/f2fs/<disk>/warm_data_age_threshold
+Date:		November 2022
+Contact:	"Ping Xiong" <[email protected]>
+Description:	When DATA SEPARATION is on, it controls the age threshold to indicate
+		the data blocks as warm. By default it was initialized as 2621440 blocks
+		(equals to 10GB).

Documentation/filesystems/f2fs.rst

@@ -25,10 +25,14 @@ a consistency checking tool (fsck.f2fs), and a debugging tool (dump.f2fs).
 
 - git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs-tools.git
 
-For reporting bugs and sending patches, please use the following mailing list:
+For sending patches, please use the following mailing list:
 
 - [email protected]
 
+For reporting bugs, please use the following f2fs bug tracker link:
+
+- https://bugzilla.kernel.org/enter_bug.cgi?product=File%20System&component=f2fs
+
 Background and Design issues
 ============================
 
@@ -154,6 +158,8 @@ nobarrier		 This option can be used if underlying storage guarantees
 			 If this option is set, no cache_flush commands are issued
 			 but f2fs still guarantees the write ordering of all the
 			 data writes.
+barrier		 If this option is set, cache_flush commands are allowed to be
+			 issued.
 fastboot		 This option is used when a system wants to reduce mount
 			 time as much as possible, even though normal performance
 			 can be sacrificed.
@@ -199,6 +205,7 @@ fault_type=%d		 Support configuring fault injection type, should be
 			 FAULT_SLAB_ALLOC	  0x000008000
 			 FAULT_DQUOT_INIT	  0x000010000
 			 FAULT_LOCK_OP		  0x000020000
+			 FAULT_BLKADDR		  0x000040000
 			 ===================	  ===========
 mode=%s			 Control block allocation mode which supports "adaptive"
 			 and "lfs". In "lfs" mode, there should be no random
@@ -341,6 +348,10 @@ memory=%s		 Control memory mode. This supports "normal" and "low" modes.
 			 Because of the nature of low memory devices, in this mode, f2fs
 			 will try to save memory sometimes by sacrificing performance.
 			 "normal" mode is the default mode and same as before.
+age_extent_cache	 Enable an age extent cache based on rb-tree. It records
+			 data block update frequency of the extent per inode, in
+			 order to provide better temperature hints for data block
+			 allocation.
 ======================== ============================================================
 
 Debugfs Entries

MAINTAINERS

@@ -5612,6 +5612,7 @@ M:	Jaegeuk Kim <[email protected]>
 M:	Chao Yu <[email protected]>
 L:	[email protected]
 W:	https://f2fs.wiki.kernel.org/
+B:	https://bugzilla.kernel.org/enter_bug.cgi?product=File%20System&component=f2fs
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git
 S:	Maintained
 F:	Documentation/filesystems/f2fs.txt

fs/f2fs/checkpoint.c

@@ -26,12 +26,16 @@
 static struct kmem_cache *ino_entry_slab;
 struct kmem_cache *f2fs_inode_entry_slab;
 
-void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io,
+						unsigned char reason)
 {
 	f2fs_build_fault_attr(sbi, 0, 0);
 	set_ckpt_flags(sbi, CP_ERROR_FLAG);
-	if (!end_io)
+	if (!end_io) {
 		f2fs_flush_merged_writes(sbi);
+
+		f2fs_handle_stop(sbi, reason);
+	}
 }
 
 /*
@@ -122,7 +126,7 @@ struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index)
 		if (PTR_ERR(page) == -EIO &&
 				++count <= DEFAULT_RETRY_IO_COUNT)
 			goto retry;
-		f2fs_stop_checkpoint(sbi, false);
+		f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_META_PAGE);
 	}
 	return page;
 }
@@ -140,14 +144,21 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
 	unsigned int segno, offset;
 	bool exist;
 
-	if (type != DATA_GENERIC_ENHANCE && type != DATA_GENERIC_ENHANCE_READ)
+	if (type == DATA_GENERIC)
 		return true;
 
 	segno = GET_SEGNO(sbi, blkaddr);
 	offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
 	se = get_seg_entry(sbi, segno);
 
 	exist = f2fs_test_bit(offset, se->cur_valid_map);
+	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) {
 		f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
 			 blkaddr, exist);
@@ -160,6 +171,11 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
 bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 					block_t blkaddr, int type)
 {
+	if (time_to_inject(sbi, FAULT_BLKADDR)) {
+		f2fs_show_injection_info(sbi, FAULT_BLKADDR);
+		return false;
+	}
+
 	switch (type) {
 	case META_NAT:
 		break;
@@ -185,6 +201,7 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 	case DATA_GENERIC:
 	case DATA_GENERIC_ENHANCE:
 	case DATA_GENERIC_ENHANCE_READ:
+	case DATA_GENERIC_ENHANCE_UPDATE:
 		if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
 				blkaddr < MAIN_BLKADDR(sbi))) {
 			f2fs_warn(sbi, "access invalid blkaddr:%u",
@@ -447,8 +464,7 @@ static int f2fs_set_meta_page_dirty(struct page *page)
 
 	if (!PageUptodate(page))
 		SetPageUptodate(page);
-	if (!PageDirty(page)) {
-		__set_page_dirty_nobuffers(page);
+	if (__set_page_dirty_nobuffers(page)) {
 		inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
 		set_page_private_reference(page);
 		return 1;
@@ -1054,7 +1070,8 @@ void f2fs_remove_dirty_inode(struct inode *inode)
 	spin_unlock(&sbi->inode_lock[type]);
 }
 
-int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
+int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type,
+						bool from_cp)
 {
 	struct list_head *head;
 	struct inode *inode;
@@ -1089,11 +1106,15 @@ int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
 	if (inode) {
 		unsigned long cur_ino = inode->i_ino;
 
-		F2FS_I(inode)->cp_task = current;
+		if (from_cp)
+			F2FS_I(inode)->cp_task = current;
+		F2FS_I(inode)->wb_task = current;
 
 		filemap_fdatawrite(inode->i_mapping);
 
-		F2FS_I(inode)->cp_task = NULL;
+		F2FS_I(inode)->wb_task = NULL;
+		if (from_cp)
+			F2FS_I(inode)->cp_task = NULL;
 
 		iput(inode);
 		/* We need to give cpu to another writers. */
@@ -1222,7 +1243,7 @@ static int block_operations(struct f2fs_sb_info *sbi)
 	/* write all the dirty dentry pages */
 	if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
 		f2fs_unlock_all(sbi);
-		err = f2fs_sync_dirty_inodes(sbi, DIR_INODE);
+		err = f2fs_sync_dirty_inodes(sbi, DIR_INODE, true);
 		if (err)
 			return err;
 		cond_resched();
@@ -1889,8 +1910,10 @@ int f2fs_start_ckpt_thread(struct f2fs_sb_info *sbi)
 	cprc->f2fs_issue_ckpt = kthread_run(issue_checkpoint_thread, sbi,
 			"f2fs_ckpt-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(cprc->f2fs_issue_ckpt)) {
+		int err = PTR_ERR(cprc->f2fs_issue_ckpt);
+
 		cprc->f2fs_issue_ckpt = NULL;
-		return -ENOMEM;
+		return err;
 	}
 
 	set_task_ioprio(cprc->f2fs_issue_ckpt, cprc->ckpt_thread_ioprio);
@@ -1901,15 +1924,27 @@ int f2fs_start_ckpt_thread(struct f2fs_sb_info *sbi)
 void f2fs_stop_ckpt_thread(struct f2fs_sb_info *sbi)
 {
 	struct ckpt_req_control *cprc = &sbi->cprc_info;
+	struct task_struct *ckpt_task;
 
-	if (cprc->f2fs_issue_ckpt) {
-		struct task_struct *ckpt_task = cprc->f2fs_issue_ckpt;
+	if (!cprc->f2fs_issue_ckpt)
+		return;
 
-		cprc->f2fs_issue_ckpt = NULL;
-		kthread_stop(ckpt_task);
+	ckpt_task = cprc->f2fs_issue_ckpt;
+	cprc->f2fs_issue_ckpt = NULL;
+	kthread_stop(ckpt_task);
 
-		flush_remained_ckpt_reqs(sbi, NULL);
-	}
+	f2fs_flush_ckpt_thread(sbi);
+}
+
+void f2fs_flush_ckpt_thread(struct f2fs_sb_info *sbi)
+{
+	struct ckpt_req_control *cprc = &sbi->cprc_info;
+
+	flush_remained_ckpt_reqs(sbi, NULL);
+
+	/* Let's wait for the previous dispatched checkpoint. */
+	while (atomic_read(&cprc->queued_ckpt))
+		io_schedule_timeout(DEFAULT_IO_TIMEOUT);
 }
 
 void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi)