Merge android-4.4.159 (624c095) into msm-4.4

* refs/heads/tmp-624c095
  Linux 4.4.159
  iw_cxgb4: only allow 1 flush on user qps
  HID: sony: Support DS4 dongle
  HID: sony: Update device ids
  arm64: Add trace_hardirqs_off annotation in ret_to_user
  ext4: don't mark mmp buffer head dirty
  ext4: fix online resizing for bigalloc file systems with a 1k block size
  ext4: fix online resize's handling of a too-small final block group
  ext4: recalucate superblock checksum after updating free blocks/inodes
  ext4: avoid divide by zero fault when deleting corrupted inline directories
  tty: vt_ioctl: fix potential Spectre v1
  drm/nouveau/drm/nouveau: Use pm_runtime_get_noresume() in connector_detect()
  ocfs2: fix ocfs2 read block panic
  scsi: target: iscsi: Use hex2bin instead of a re-implementation
  neighbour: confirm neigh entries when ARP packet is received
  net: hp100: fix always-true check for link up state
  net/appletalk: fix minor pointer leak to userspace in SIOCFINDIPDDPRT
  ipv6: fix possible use-after-free in ip6_xmit()
  gso_segment: Reset skb->mac_len after modifying network header
  mm: shmem.c: Correctly annotate new inodes for lockdep
  ring-buffer: Allow for rescheduling when removing pages
  xen/x86/vpmu: Zero struct pt_regs before calling into sample handling code
  xen/netfront: don't bug in case of too many frags
  platform/x86: alienware-wmi: Correct a memory leak
  ALSA: emu10k1: fix possible info leak to userspace on SNDRV_EMU10K1_IOCTL_INFO
  ALSA: bebob: use address returned by kmalloc() instead of kernel stack for streaming DMA mapping
  ASoC: cs4265: fix MMTLR Data switch control
  NFC: Fix the number of pipes
  NFC: Fix possible memory corruption when handling SHDLC I-Frame commands
  ANDROID: restrict store of prefer_idle as boolean
  f2fs: readahead encrypted block during GC
  f2fs: avoid fi->i_gc_rwsem[WRITE] lock in f2fs_gc
  f2fs: fix performance issue observed with multi-thread sequential read
  f2fs: fix to skip verifying block address for non-regular inode
  f2fs: rework fault injection handling to avoid a warning
  f2fs: support fault_type mount option
  f2fs: fix to return success when trimming meta area
  f2fs: fix use-after-free of dicard command entry
  f2fs: support discard submission error injection
  f2fs: split discard command in prior to block layer
  f2fs: wake up gc thread immediately when gc_urgent is set
  f2fs: fix incorrect range->len in f2fs_trim_fs()
  f2fs: refresh recent accessed nat entry in lru list
  f2fs: fix avoid race between truncate and background GC
  f2fs: avoid race between zero_range and background GC
  f2fs: fix to do sanity check with block address in main area v2
  f2fs: fix to do sanity check with inline flags
  f2fs: fix to reset i_gc_failures correctly
  f2fs: fix invalid memory access
  f2fs: fix to avoid broken of dnode block list
  f2fs: use true and false for boolean values
  f2fs: fix to do sanity check with cp_pack_start_sum
  f2fs: avoid f2fs_bug_on() in cp_error case
  f2fs: fix to clear PG_checked flag in set_page_dirty()
  f2fs: fix to active page in lru list for read path
  f2fs: don't keep meta pages used for block migration
  f2fs: fix to restrict mount condition when without CONFIG_QUOTA
  f2fs: quota: do not mount as RDWR without QUOTA if quota feature enabled
  f2fs: quota: fix incorrect comments
  f2fs: add proc entry to show victim_secmap bitmap
  f2fs: let checkpoint flush dnode page of regular
  f2fs: issue discard align to section in LFS mode
  f2fs: don't allow any writes on aborted atomic writes
  f2fs: restrict setting up inode.i_advise
  f2fs: fix wrong kernel message when recover fsync data on ro fs
  f2fs: clean up ioctl interface naming
  f2fs: clean up with f2fs_is_{atomic,volatile}_file()
  f2fs: clean up with f2fs_encrypted_inode()
  f2fs: clean up with get_current_nat_page
  f2fs: kill EXT_TREE_VEC_SIZE
  f2fs: avoid duplicated permission check for "trusted." xattrs
  f2fs: fix to propagate error from __get_meta_page()
  f2fs: fix to do sanity check with i_extra_isize
  f2fs: blk_finish_plug of submit_bio in lfs mode
  f2fs: do not set free of current section
  f2fs: Keep alloc_valid_block_count in sync
  f2fs: issue small discard by LBA order
  f2fs: stop issuing discard immediately if there is queued IO
  f2fs: clean up with IS_INODE()
  f2fs: detect bug_on in f2fs_wait_discard_bios
  f2fs: fix defined but not used build warnings
  f2fs: enable real-time discard by default
  f2fs: fix to detect looped node chain correctly
  f2fs: fix to do sanity check with block address in main area
  f2fs: fix to skip GC if type in SSA and SIT is inconsistent
  f2fs: try grabbing node page lock aggressively in sync scenario
  f2fs: show the fsync_mode=nobarrier mount option
  f2fs: check the right return value of memory alloc function
  f2fs: Replace strncpy with memcpy
  f2fs: avoid the global name 'fault_name'
  f2fs: fix to do sanity check with reserved blkaddr of inline inode
  f2fs: fix to do sanity check with node footer and iblocks
  f2fs: Allocate and stat mem used by free nid bitmap more accurately
  f2fs: fix to do sanity check with user_block_count
  f2fs: fix to do sanity check with extra_attr feature
  f2fs: fix to correct return value of f2fs_trim_fs
  f2fs: fix to do sanity check with {sit,nat}_ver_bitmap_bytesize
  f2fs: fix to do sanity check with secs_per_zone
  f2fs: disable f2fs_check_rb_tree_consistence
  f2fs: introduce and spread verify_blkaddr
  f2fs: use timespec64 for inode timestamps
  f2fs: fix to wait on page writeback before updating page
  f2fs: assign REQ_RAHEAD to bio for ->readpages
  f2fs: fix a hungtask problem caused by congestion_wait
  f2fs: Fix uninitialized return in f2fs_ioc_shutdown()
  f2fs: don't issue discard commands in online discard is on
  f2fs: fix to propagate return value of scan_nat_page()
  f2fs: support in-memory inode checksum when checking consistency
  f2fs: fix error path of fill_super
  f2fs: relocate readdir_ra configure initialization
  f2fs: move s_res{u,g}id initialization to default_options()
  f2fs: don't acquire orphan ino during recovery
  f2fs: avoid potential deadlock in f2fs_sbi_store
  f2fs: indicate shutdown f2fs to allow unmount successfully
  f2fs: keep meta pages in cp_error state
  f2fs: do checkpoint in kill_sb
  f2fs: allow wrong configured dio to buffered write
  f2fs: flush journal nat entries for nat_bits during unmount

Conflicts:
	drivers/hid/hid-core.c

Change-Id: Idc486f778059ca65307ab08678f3b1e23c4ec15f
Signed-off-by: Srinivasarao P <spathi@codeaurora.org>

1 files changed, 306 insertions, 89 deletions

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 3d0c42ef0474..fdc17721e41e 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -250,7 +250,13 @@ retry:
 				err = -EAGAIN;
 				goto next;
 			}
-			f2fs_get_node_info(sbi, dn.nid, &ni);
+
+			err = f2fs_get_node_info(sbi, dn.nid, &ni);
+			if (err) {
+				f2fs_put_dnode(&dn);
+				return err;
+			}
+
 			if (cur->old_addr == NEW_ADDR) {
 				f2fs_invalidate_blocks(sbi, dn.data_blkaddr);
 				f2fs_update_data_blkaddr(&dn, NEW_ADDR);
@@ -439,8 +445,10 @@ int f2fs_commit_inmem_pages(struct inode *inode)
 	int err;
 
 	f2fs_balance_fs(sbi, true);
-	f2fs_lock_op(sbi);
 
+	down_write(&fi->i_gc_rwsem[WRITE]);
+
+	f2fs_lock_op(sbi);
 	set_inode_flag(inode, FI_ATOMIC_COMMIT);
 
 	mutex_lock(&fi->inmem_lock);
@@ -455,6 +463,8 @@ int f2fs_commit_inmem_pages(struct inode *inode)
 	clear_inode_flag(inode, FI_ATOMIC_COMMIT);
 
 	f2fs_unlock_op(sbi);
+	up_write(&fi->i_gc_rwsem[WRITE]);
+
 	return err;
 }
 
@@ -464,12 +474,10 @@ int f2fs_commit_inmem_pages(struct inode *inode)
  */
 void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 {
-#ifdef CONFIG_F2FS_FAULT_INJECTION
 	if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
 		f2fs_show_injection_info(FAULT_CHECKPOINT);
 		f2fs_stop_checkpoint(sbi, false);
 	}
-#endif
 
 	/* balance_fs_bg is able to be pending */
 	if (need && excess_cached_nats(sbi))
@@ -503,7 +511,8 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 	else
 		f2fs_build_free_nids(sbi, false, false);
 
-	if (!is_idle(sbi) && !excess_dirty_nats(sbi))
+	if (!is_idle(sbi) &&
+		(!excess_dirty_nats(sbi) && !excess_dirty_nodes(sbi)))
 		return;
 
 	/* checkpoint is the only way to shrink partial cached entries */
@@ -511,6 +520,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 			!f2fs_available_free_memory(sbi, INO_ENTRIES) ||
 			excess_prefree_segs(sbi) ||
 			excess_dirty_nats(sbi) ||
+			excess_dirty_nodes(sbi) ||
 			f2fs_time_over(sbi, CP_TIME)) {
 		if (test_opt(sbi, DATA_FLUSH)) {
 			struct blk_plug plug;
@@ -831,9 +841,12 @@ static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi,
 	dc->len = len;
 	dc->ref = 0;
 	dc->state = D_PREP;
+	dc->issuing = 0;
 	dc->error = 0;
 	init_completion(&dc->wait);
 	list_add_tail(&dc->list, pend_list);
+	spin_lock_init(&dc->lock);
+	dc->bio_ref = 0;
 	atomic_inc(&dcc->discard_cmd_cnt);
 	dcc->undiscard_blks += len;
 
@@ -860,7 +873,7 @@ static void __detach_discard_cmd(struct discard_cmd_control *dcc,
 							struct discard_cmd *dc)
 {
 	if (dc->state == D_DONE)
-		atomic_dec(&dcc->issing_discard);
+		atomic_sub(dc->issuing, &dcc->issing_discard);
 
 	list_del(&dc->list);
 	rb_erase(&dc->rb_node, &dcc->root);
@@ -875,9 +888,17 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
 							struct discard_cmd *dc)
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	unsigned long flags;
 
 	trace_f2fs_remove_discard(dc->bdev, dc->start, dc->len);
 
+	spin_lock_irqsave(&dc->lock, flags);
+	if (dc->bio_ref) {
+		spin_unlock_irqrestore(&dc->lock, flags);
+		return;
+	}
+	spin_unlock_irqrestore(&dc->lock, flags);
+
 	f2fs_bug_on(sbi, dc->ref);
 
 	if (dc->error == -EOPNOTSUPP)
@@ -893,10 +914,17 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
 static void f2fs_submit_discard_endio(struct bio *bio)
 {
 	struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private;
+	unsigned long flags;
 
 	dc->error = bio->bi_error;
-	dc->state = D_DONE;
-	complete_all(&dc->wait);
+
+	spin_lock_irqsave(&dc->lock, flags);
+	dc->bio_ref--;
+	if (!dc->bio_ref && dc->state == D_SUBMIT) {
+		dc->state = D_DONE;
+		complete_all(&dc->wait);
+	}
+	spin_unlock_irqrestore(&dc->lock, flags);
 	bio_put(bio);
 }
 
@@ -1015,6 +1043,7 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi,
 	/* common policy */
 	dpolicy->type = discard_type;
 	dpolicy->sync = true;
+	dpolicy->ordered = false;
 	dpolicy->granularity = granularity;
 
 	dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
@@ -1026,6 +1055,7 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi,
 		dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
 		dpolicy->io_aware = true;
 		dpolicy->sync = false;
+		dpolicy->ordered = true;
 		if (utilization(sbi) > DEF_DISCARD_URGENT_UTIL) {
 			dpolicy->granularity = 1;
 			dpolicy->max_interval = DEF_MIN_DISCARD_ISSUE_TIME;
@@ -1043,47 +1073,114 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi,
 	}
 }
 
-
+static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
+				struct block_device *bdev, block_t lstart,
+				block_t start, block_t len);
 /* this function is copied from blkdev_issue_discard from block/blk-lib.c */
-static void __submit_discard_cmd(struct f2fs_sb_info *sbi,
+static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 						struct discard_policy *dpolicy,
-						struct discard_cmd *dc)
+						struct discard_cmd *dc,
+						unsigned int *issued)
 {
+	struct block_device *bdev = dc->bdev;
+	struct request_queue *q = bdev_get_queue(bdev);
+	unsigned int max_discard_blocks =
+			SECTOR_TO_BLOCK(q->limits.max_discard_sectors);
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 	struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
 					&(dcc->fstrim_list) : &(dcc->wait_list);
-	struct bio *bio = NULL;
 	int flag = dpolicy->sync ? REQ_SYNC : 0;
+	block_t lstart, start, len, total_len;
+	int err = 0;
 
 	if (dc->state != D_PREP)
-		return;
+		return 0;
 
 	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
-		return;
+		return 0;
 
-	trace_f2fs_issue_discard(dc->bdev, dc->start, dc->len);
+	trace_f2fs_issue_discard(bdev, dc->start, dc->len);
 
-	dc->error = __blkdev_issue_discard(dc->bdev,
-				SECTOR_FROM_BLOCK(dc->start),
-				SECTOR_FROM_BLOCK(dc->len),
-				GFP_NOFS, 0, &bio);
-	if (!dc->error) {
-		/* should keep before submission to avoid D_DONE right away */
-		dc->state = D_SUBMIT;
-		atomic_inc(&dcc->issued_discard);
-		atomic_inc(&dcc->issing_discard);
-		if (bio) {
-			bio->bi_private = dc;
-			bio->bi_end_io = f2fs_submit_discard_endio;
-			submit_bio(flag, bio);
-			list_move_tail(&dc->list, wait_list);
-			__check_sit_bitmap(sbi, dc->start, dc->start + dc->len);
+	lstart = dc->lstart;
+	start = dc->start;
+	len = dc->len;
+	total_len = len;
+
+	dc->len = 0;
+
+	while (total_len && *issued < dpolicy->max_requests && !err) {
+		struct bio *bio = NULL;
+		unsigned long flags;
+		bool last = true;
 
-			f2fs_update_iostat(sbi, FS_DISCARD, 1);
+		if (len > max_discard_blocks) {
+			len = max_discard_blocks;
+			last = false;
 		}
-	} else {
-		__remove_discard_cmd(sbi, dc);
+
+		(*issued)++;
+		if (*issued == dpolicy->max_requests)
+			last = true;
+
+		dc->len += len;
+
+		if (time_to_inject(sbi, FAULT_DISCARD)) {
+			f2fs_show_injection_info(FAULT_DISCARD);
+			err = -EIO;
+			goto submit;
+		}
+		err = __blkdev_issue_discard(bdev,
+					SECTOR_FROM_BLOCK(start),
+					SECTOR_FROM_BLOCK(len),
+					GFP_NOFS, 0, &bio);
+submit:
+		if (err) {
+			spin_lock_irqsave(&dc->lock, flags);
+			if (dc->state == D_PARTIAL)
+				dc->state = D_SUBMIT;
+			spin_unlock_irqrestore(&dc->lock, flags);
+
+			break;
+		}
+
+		f2fs_bug_on(sbi, !bio);
+
+		/*
+		 * should keep before submission to avoid D_DONE
+		 * right away
+		 */
+		spin_lock_irqsave(&dc->lock, flags);
+		if (last)
+			dc->state = D_SUBMIT;
+		else
+			dc->state = D_PARTIAL;
+		dc->bio_ref++;
+		spin_unlock_irqrestore(&dc->lock, flags);
+
+		atomic_inc(&dcc->issing_discard);
+		dc->issuing++;
+		list_move_tail(&dc->list, wait_list);
+
+		/* sanity check on discard range */
+		__check_sit_bitmap(sbi, start, start + len);
+
+		bio->bi_private = dc;
+		bio->bi_end_io = f2fs_submit_discard_endio;
+		submit_bio(flag, bio);
+
+		atomic_inc(&dcc->issued_discard);
+
+		f2fs_update_iostat(sbi, FS_DISCARD, 1);
+
+		lstart += len;
+		start += len;
+		total_len -= len;
+		len = total_len;
 	}
+
+	if (!err && len)
+		__update_discard_tree_range(sbi, bdev, lstart, start, len);
+	return err;
 }
 
 static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi,
@@ -1164,10 +1261,11 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
 	struct discard_cmd *dc;
 	struct discard_info di = {0};
 	struct rb_node **insert_p = NULL, *insert_parent = NULL;
+	struct request_queue *q = bdev_get_queue(bdev);
+	unsigned int max_discard_blocks =
+			SECTOR_TO_BLOCK(q->limits.max_discard_sectors);
 	block_t end = lstart + len;
 
-	mutex_lock(&dcc->cmd_lock);
-
 	dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
 					NULL, lstart,
 					(struct rb_entry **)&prev_dc,
@@ -1207,7 +1305,8 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
 
 		if (prev_dc && prev_dc->state == D_PREP &&
 			prev_dc->bdev == bdev &&
-			__is_discard_back_mergeable(&di, &prev_dc->di)) {
+			__is_discard_back_mergeable(&di, &prev_dc->di,
+							max_discard_blocks)) {
 			prev_dc->di.len += di.len;
 			dcc->undiscard_blks += di.len;
 			__relocate_discard_cmd(dcc, prev_dc);
@@ -1218,7 +1317,8 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
 
 		if (next_dc && next_dc->state == D_PREP &&
 			next_dc->bdev == bdev &&
-			__is_discard_front_mergeable(&di, &next_dc->di)) {
+			__is_discard_front_mergeable(&di, &next_dc->di,
+							max_discard_blocks)) {
 			next_dc->di.lstart = di.lstart;
 			next_dc->di.len += di.len;
 			next_dc->di.start = di.start;
@@ -1241,8 +1341,6 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
 		node = rb_next(&prev_dc->rb_node);
 		next_dc = rb_entry_safe(node, struct discard_cmd, rb_node);
 	}
-
-	mutex_unlock(&dcc->cmd_lock);
 }
 
 static int __queue_discard_cmd(struct f2fs_sb_info *sbi,
@@ -1257,10 +1355,72 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi,
 
 		blkstart -= FDEV(devi).start_blk;
 	}
+	mutex_lock(&SM_I(sbi)->dcc_info->cmd_lock);
 	__update_discard_tree_range(sbi, bdev, lblkstart, blkstart, blklen);
+	mutex_unlock(&SM_I(sbi)->dcc_info->cmd_lock);
 	return 0;
 }
 
+static unsigned int __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi,
+					struct discard_policy *dpolicy)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
+	struct rb_node **insert_p = NULL, *insert_parent = NULL;
+	struct discard_cmd *dc;
+	struct blk_plug plug;
+	unsigned int pos = dcc->next_pos;
+	unsigned int issued = 0;
+	bool io_interrupted = false;
+
+	mutex_lock(&dcc->cmd_lock);
+	dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
+					NULL, pos,
+					(struct rb_entry **)&prev_dc,
+					(struct rb_entry **)&next_dc,
+					&insert_p, &insert_parent, true);
+	if (!dc)
+		dc = next_dc;
+
+	blk_start_plug(&plug);
+
+	while (dc) {
+		struct rb_node *node;
+		int err = 0;
+
+		if (dc->state != D_PREP)
+			goto next;
+
+		if (dpolicy->io_aware && !is_idle(sbi)) {
+			io_interrupted = true;
+			break;
+		}
+
+		dcc->next_pos = dc->lstart + dc->len;
+		err = __submit_discard_cmd(sbi, dpolicy, dc, &issued);
+
+		if (issued >= dpolicy->max_requests)
+			break;
+next:
+		node = rb_next(&dc->rb_node);
+		if (err)
+			__remove_discard_cmd(sbi, dc);
+		dc = rb_entry_safe(node, struct discard_cmd, rb_node);
+	}
+
+	blk_finish_plug(&plug);
+
+	if (!dc)
+		dcc->next_pos = 0;
+
+	mutex_unlock(&dcc->cmd_lock);
+
+	if (!issued && io_interrupted)
+		issued = -1;
+
+	return issued;
+}
+
 static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
 					struct discard_policy *dpolicy)
 {
@@ -1268,19 +1428,24 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
 	struct list_head *pend_list;
 	struct discard_cmd *dc, *tmp;
 	struct blk_plug plug;
-	int i, iter = 0, issued = 0;
+	int i, issued = 0;
 	bool io_interrupted = false;
 
 	for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
 		if (i + 1 < dpolicy->granularity)
 			break;
+
+		if (i < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered)
+			return __issue_discard_cmd_orderly(sbi, dpolicy);
+
 		pend_list = &dcc->pend_list[i];
 
 		mutex_lock(&dcc->cmd_lock);
 		if (list_empty(pend_list))
 			goto next;
-		f2fs_bug_on(sbi,
-			!f2fs_check_rb_tree_consistence(sbi, &dcc->root));
+		if (unlikely(dcc->rbtree_check))
+			f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
+								&dcc->root));
 		blk_start_plug(&plug);
 		list_for_each_entry_safe(dc, tmp, pend_list, list) {
 			f2fs_bug_on(sbi, dc->state != D_PREP);
@@ -1288,20 +1453,19 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
 			if (dpolicy->io_aware && i < dpolicy->io_aware_gran &&
 								!is_idle(sbi)) {
 				io_interrupted = true;
-				goto skip;
+				break;
 			}
 
-			__submit_discard_cmd(sbi, dpolicy, dc);
-			issued++;
-skip:
-			if (++iter >= dpolicy->max_requests)
+			__submit_discard_cmd(sbi, dpolicy, dc, &issued);
+
+			if (issued >= dpolicy->max_requests)
 				break;
 		}
 		blk_finish_plug(&plug);
 next:
 		mutex_unlock(&dcc->cmd_lock);
 
-		if (iter >= dpolicy->max_requests)
+		if (issued >= dpolicy->max_requests || io_interrupted)
 			break;
 	}
 
@@ -1399,21 +1563,22 @@ next:
 	return trimmed;
 }
 
-static void __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
+static unsigned int __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
 						struct discard_policy *dpolicy)
 {
 	struct discard_policy dp;
+	unsigned int discard_blks;
 
-	if (dpolicy) {
-		__wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX);
-		return;
-	}
+	if (dpolicy)
+		return __wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX);
 
 	/* wait all */
 	__init_discard_policy(sbi, &dp, DPOLICY_FSTRIM, 1);
-	__wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
+	discard_blks = __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
 	__init_discard_policy(sbi, &dp, DPOLICY_UMOUNT, 1);
-	__wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
+	discard_blks += __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX);
+
+	return discard_blks;
 }
 
 /* This should be covered by global mutex, &sit_i->sentry_lock */
@@ -1466,6 +1631,8 @@ bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi)
 
 	/* just to make sure there is no pending discard commands */
 	__wait_all_discard_cmd(sbi, NULL);
+
+	f2fs_bug_on(sbi, atomic_read(&dcc->discard_cmd_cnt));
 	return dropped;
 }
 
@@ -1723,21 +1890,30 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
 	unsigned int start = 0, end = -1;
 	unsigned int secno, start_segno;
 	bool force = (cpc->reason & CP_DISCARD);
+	bool need_align = test_opt(sbi, LFS) && sbi->segs_per_sec > 1;
 
 	mutex_lock(&dirty_i->seglist_lock);
 
 	while (1) {
 		int i;
+
+		if (need_align && end != -1)
+			end--;
 		start = find_next_bit(prefree_map, MAIN_SEGS(sbi), end + 1);
 		if (start >= MAIN_SEGS(sbi))
 			break;
 		end = find_next_zero_bit(prefree_map, MAIN_SEGS(sbi),
 								start + 1);
 
-		for (i = start; i < end; i++)
-			clear_bit(i, prefree_map);
+		if (need_align) {
+			start = rounddown(start, sbi->segs_per_sec);
+			end = roundup(end, sbi->segs_per_sec);
+		}
 
-		dirty_i->nr_dirty[PRE] -= end - start;
+		for (i = start; i < end; i++) {
+			if (test_and_clear_bit(i, prefree_map))
+				dirty_i->nr_dirty[PRE]--;
+		}
 
 		if (!test_opt(sbi, DISCARD))
 			continue;
@@ -1831,7 +2007,9 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
 	dcc->nr_discards = 0;
 	dcc->max_discards = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg;
 	dcc->undiscard_blks = 0;
+	dcc->next_pos = 0;
 	dcc->root = RB_ROOT;
+	dcc->rbtree_check = false;
 
 	init_waitqueue_head(&dcc->discard_wait_queue);
 	SM_I(sbi)->dcc_info = dcc;
@@ -1981,6 +2159,8 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
 	if (addr == NEW_ADDR)
 		return;
 
+	invalidate_mapping_pages(META_MAPPING(sbi), addr, addr);
+
 	/* add it into sit main buffer */
 	down_write(&sit_i->sentry_lock);
 
@@ -1999,7 +2179,7 @@ bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
 	struct seg_entry *se;
 	bool is_cp = false;
 
-	if (!is_valid_blkaddr(blkaddr))
+	if (!is_valid_data_blkaddr(sbi, blkaddr))
 		return true;
 
 	down_read(&sit_i->sentry_lock);
@@ -2063,7 +2243,7 @@ int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
  */
 struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
 {
-	return f2fs_get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno));
+	return f2fs_get_meta_page_nofail(sbi, GET_SUM_BLOCK(sbi, segno));
 }
 
 void f2fs_update_meta_page(struct f2fs_sb_info *sbi,
@@ -2446,7 +2626,7 @@ bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
 	return has_candidate;
 }
 
-static void __issue_discard_cmd_range(struct f2fs_sb_info *sbi,
+static unsigned int __issue_discard_cmd_range(struct f2fs_sb_info *sbi,
 					struct discard_policy *dpolicy,
 					unsigned int start, unsigned int end)
 {
@@ -2456,12 +2636,15 @@ static void __issue_discard_cmd_range(struct f2fs_sb_info *sbi,
 	struct discard_cmd *dc;
 	struct blk_plug plug;
 	int issued;
+	unsigned int trimmed = 0;
 
 next:
 	issued = 0;
 
 	mutex_lock(&dcc->cmd_lock);
-	f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi, &dcc->root));
+	if (unlikely(dcc->rbtree_check))
+		f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
+								&dcc->root));
 
 	dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
 					NULL, start,
@@ -2475,6 +2658,7 @@ next:
 
 	while (dc && dc->lstart <= end) {
 		struct rb_node *node;
+		int err = 0;
 
 		if (dc->len < dpolicy->granularity)
 			goto skip;
@@ -2484,19 +2668,24 @@ next:
 			goto skip;
 		}
 
-		__submit_discard_cmd(sbi, dpolicy, dc);
+		err = __submit_discard_cmd(sbi, dpolicy, dc, &issued);
 
-		if (++issued >= dpolicy->max_requests) {
+		if (issued >= dpolicy->max_requests) {
 			start = dc->lstart + dc->len;
 
+			if (err)
+				__remove_discard_cmd(sbi, dc);
+
 			blk_finish_plug(&plug);
 			mutex_unlock(&dcc->cmd_lock);
-			__wait_all_discard_cmd(sbi, NULL);
+			trimmed += __wait_all_discard_cmd(sbi, NULL);
 			congestion_wait(BLK_RW_ASYNC, HZ/50);
 			goto next;
 		}
 skip:
 		node = rb_next(&dc->rb_node);
+		if (err)
+			__remove_discard_cmd(sbi, dc);
 		dc = rb_entry_safe(node, struct discard_cmd, rb_node);
 
 		if (fatal_signal_pending(current))
@@ -2505,6 +2694,8 @@ skip:
 
 	blk_finish_plug(&plug);
 	mutex_unlock(&dcc->cmd_lock);
+
+	return trimmed;
 }
 
 int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
@@ -2517,12 +2708,13 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	struct discard_policy dpolicy;
 	unsigned long long trimmed = 0;
 	int err = 0;
+	bool need_align = test_opt(sbi, LFS) && sbi->segs_per_sec > 1;
 
 	if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
 		return -EINVAL;
 
-	if (end <= MAIN_BLKADDR(sbi))
-		return -EINVAL;
+	if (end < MAIN_BLKADDR(sbi))
+		goto out;
 
 	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
 		f2fs_msg(sbi->sb, KERN_WARNING,
@@ -2534,6 +2726,10 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start);
 	end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
 						GET_SEGNO(sbi, end);
+	if (need_align) {
+		start_segno = rounddown(start_segno, sbi->segs_per_sec);
+		end_segno = roundup(end_segno + 1, sbi->segs_per_sec) - 1;
+	}
 
 	cpc.reason = CP_DISCARD;
 	cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen));
@@ -2549,24 +2745,27 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	if (err)
 		goto out;
 
-	start_block = START_BLOCK(sbi, start_segno);
-	end_block = START_BLOCK(sbi, end_segno + 1);
-
-	__init_discard_policy(sbi, &dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen);
-	__issue_discard_cmd_range(sbi, &dpolicy, start_block, end_block);
-
 	/*
 	 * We filed discard candidates, but actually we don't need to wait for
 	 * all of them, since they'll be issued in idle time along with runtime
 	 * discard option. User configuration looks like using runtime discard
 	 * or periodic fstrim instead of it.
 	 */
-	if (!test_opt(sbi, DISCARD)) {
-		trimmed = __wait_discard_cmd_range(sbi, &dpolicy,
+	if (test_opt(sbi, DISCARD))
+		goto out;
+
+	start_block = START_BLOCK(sbi, start_segno);
+	end_block = START_BLOCK(sbi, end_segno + 1);
+
+	__init_discard_policy(sbi, &dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen);
+	trimmed = __issue_discard_cmd_range(sbi, &dpolicy,
+					start_block, end_block);
+
+	trimmed += __wait_discard_cmd_range(sbi, &dpolicy,
 					start_block, end_block);
-		range->len = F2FS_BLK_TO_BYTES(trimmed);
-	}
 out:
+	if (!err)
+		range->len = F2FS_BLK_TO_BYTES(trimmed);
 	return err;
 }
 
@@ -2719,8 +2918,8 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 			return CURSEG_COLD_DATA;
 		if (file_is_hot(inode) ||
 				is_inode_flag_set(inode, FI_HOT_DATA) ||
-				is_inode_flag_set(inode, FI_ATOMIC_FILE) ||
-				is_inode_flag_set(inode, FI_VOLATILE_FILE))
+				f2fs_is_atomic_file(inode) ||
+				f2fs_is_volatile_file(inode))
 			return CURSEG_HOT_DATA;
 		/* f2fs_rw_hint_to_seg_type(inode->i_write_hint); */
 		return CURSEG_WARM_DATA;
@@ -2862,6 +3061,9 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 reallocate:
 	f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
 			&fio->new_blkaddr, sum, type, fio, true);
+	if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO)
+		invalidate_mapping_pages(META_MAPPING(fio->sbi),
+					fio->old_blkaddr, fio->old_blkaddr);
 
 	/* writeout dirty page into bdev */
 	f2fs_submit_page_write(fio);
@@ -2917,11 +3119,9 @@ void f2fs_outplace_write_data(struct dnode_of_data *dn,
 {
 	struct f2fs_sb_info *sbi = fio->sbi;
 	struct f2fs_summary sum;
-	struct node_info ni;
 
 	f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
-	f2fs_get_node_info(sbi, dn->nid, &ni);
-	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
+	set_summary(&sum, dn->nid, dn->ofs_in_node, fio->version);
 	do_write_page(&sum, fio);
 	f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
 
@@ -3018,8 +3218,11 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 
 	if (!recover_curseg || recover_newaddr)
 		update_sit_entry(sbi, new_blkaddr, 1);
-	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
+	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) {
+		invalidate_mapping_pages(META_MAPPING(sbi),
+					old_blkaddr, old_blkaddr);
 		update_sit_entry(sbi, old_blkaddr, -1);
+	}
 
 	locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
 	locate_dirty_segment(sbi, GET_SEGNO(sbi, new_blkaddr));
@@ -3073,7 +3276,7 @@ void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr)
 {
 	struct page *cpage;
 
-	if (!is_valid_blkaddr(blkaddr))
+	if (!is_valid_data_blkaddr(sbi, blkaddr))
 		return;
 
 	cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
@@ -3083,7 +3286,7 @@ void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr)
 	}
 }
 
-static void read_compacted_summaries(struct f2fs_sb_info *sbi)
+static int read_compacted_summaries(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	struct curseg_info *seg_i;
@@ -3095,6 +3298,8 @@ static void read_compacted_summaries(struct f2fs_sb_info *sbi)
 	start = start_sum_block(sbi);
 
 	page = f2fs_get_meta_page(sbi, start++);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
 	kaddr = (unsigned char *)page_address(page);
 
 	/* Step 1: restore nat cache */
@@ -3135,11 +3340,14 @@ static void read_compacted_summaries(struct f2fs_sb_info *sbi)
 			page = NULL;
 
 			page = f2fs_get_meta_page(sbi, start++);
+			if (IS_ERR(page))
+				return PTR_ERR(page);
 			kaddr = (unsigned char *)page_address(page);
 			offset = 0;
 		}
 	}
 	f2fs_put_page(page, 1);
+	return 0;
 }
 
 static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
@@ -3151,6 +3359,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 	unsigned short blk_off;
 	unsigned int segno = 0;
 	block_t blk_addr = 0;
+	int err = 0;
 
 	/* get segment number and block addr */
 	if (IS_DATASEG(type)) {
@@ -3174,6 +3383,8 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 	}
 
 	new = f2fs_get_meta_page(sbi, blk_addr);
+	if (IS_ERR(new))
+		return PTR_ERR(new);
 	sum = (struct f2fs_summary_block *)page_address(new);
 
 	if (IS_NODESEG(type)) {
@@ -3185,7 +3396,9 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 				ns->ofs_in_node = 0;
 			}
 		} else {
-			f2fs_restore_node_summary(sbi, segno, sum);
+			err = f2fs_restore_node_summary(sbi, segno, sum);
+			if (err)
+				goto out;
 		}
 	}
 
@@ -3205,8 +3418,9 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 	curseg->alloc_type = ckpt->alloc_type[type];
 	curseg->next_blkoff = blk_off;
 	mutex_unlock(&curseg->curseg_mutex);
+out:
 	f2fs_put_page(new, 1);
-	return 0;
+	return err;
 }
 
 static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
@@ -3224,7 +3438,9 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 							META_CP, true);
 
 		/* restore for compacted data summary */
-		read_compacted_summaries(sbi);
+		err = read_compacted_summaries(sbi);
+		if (err)
+			return err;
 		type = CURSEG_HOT_NODE;
 	}
 
@@ -3355,7 +3571,7 @@ int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
 static struct page *get_current_sit_page(struct f2fs_sb_info *sbi,
 					unsigned int segno)
 {
-	return f2fs_get_meta_page(sbi, current_sit_addr(sbi, segno));
+	return f2fs_get_meta_page_nofail(sbi, current_sit_addr(sbi, segno));
 }
 
 static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
@@ -4004,6 +4220,7 @@ int f2fs_build_segment_manager(struct f2fs_sb_info *sbi)
 		sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
 	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
 	sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
+	sm_info->min_seq_blocks = sbi->blocks_per_seg * sbi->segs_per_sec;
 	sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
 	sm_info->min_ssr_sections = reserved_sections(sbi);