Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

1 files changed, 2929 insertions, 0 deletions

diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
new file mode 100644
index 000000000..829573cb6
--- /dev/null
+++ b/fs/nilfs2/segment.c
@@ -0,0 +1,2929 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * NILFS segment constructor.
+ *
+ * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
+ *
+ * Written by Ryusuke Konishi.
+ *
+ */
+
+#include <linux/pagemap.h>
+#include <linux/buffer_head.h>
+#include <linux/writeback.h>
+#include <linux/bitops.h>
+#include <linux/bio.h>
+#include <linux/completion.h>
+#include <linux/blkdev.h>
+#include <linux/backing-dev.h>
+#include <linux/freezer.h>
+#include <linux/kthread.h>
+#include <linux/crc32.h>
+#include <linux/folio_batch.h>
+#include <linux/slab.h>
+#include <linux/sched/signal.h>
+
+#include "nilfs.h"
+#include "btnode.h"
+#include "page.h"
+#include "segment.h"
+#include "sufile.h"
+#include "cpfile.h"
+#include "ifile.h"
+#include "segbuf.h"
+
+
+/*
+ * Segment constructor
+ */
+#define SC_N_INODEVEC	16   /* Size of locally allocated inode vector */
+
+#define SC_MAX_SEGDELTA 64   /*
+			      * Upper limit of the number of segments
+			      * appended in collection retry loop
+			      */
+
+/* Construction mode */
+enum {
+	SC_LSEG_SR = 1,	/* Make a logical segment having a super root */
+	SC_LSEG_DSYNC,	/*
+			 * Flush data blocks of a given file and make
+			 * a logical segment without a super root.
+			 */
+	SC_FLUSH_FILE,	/*
+			 * Flush data files, leads to segment writes without
+			 * creating a checkpoint.
+			 */
+	SC_FLUSH_DAT,	/*
+			 * Flush DAT file.  This also creates segments
+			 * without a checkpoint.
+			 */
+};
+
+/* Stage numbers of dirty block collection */
+enum {
+	NILFS_ST_INIT = 0,
+	NILFS_ST_GC,		/* Collecting dirty blocks for GC */
+	NILFS_ST_FILE,
+	NILFS_ST_IFILE,
+	NILFS_ST_CPFILE,
+	NILFS_ST_SUFILE,
+	NILFS_ST_DAT,
+	NILFS_ST_SR,		/* Super root */
+	NILFS_ST_DSYNC,		/* Data sync blocks */
+	NILFS_ST_DONE,
+};
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/nilfs2.h>
+
+/*
+ * nilfs_sc_cstage_inc(), nilfs_sc_cstage_set(), nilfs_sc_cstage_get() are
+ * wrapper functions of stage count (nilfs_sc_info->sc_stage.scnt). Users of
+ * the variable must use them because transition of stage count must involve
+ * trace events (trace_nilfs2_collection_stage_transition).
+ *
+ * nilfs_sc_cstage_get() isn't required for the above purpose because it doesn't
+ * produce tracepoint events. It is provided just for making the intention
+ * clear.
+ */
+static inline void nilfs_sc_cstage_inc(struct nilfs_sc_info *sci)
+{
+	sci->sc_stage.scnt++;
+	trace_nilfs2_collection_stage_transition(sci);
+}
+
+static inline void nilfs_sc_cstage_set(struct nilfs_sc_info *sci, int next_scnt)
+{
+	sci->sc_stage.scnt = next_scnt;
+	trace_nilfs2_collection_stage_transition(sci);
+}
+
+static inline int nilfs_sc_cstage_get(struct nilfs_sc_info *sci)
+{
+	return sci->sc_stage.scnt;
+}
+
+/* State flags of collection */
+#define NILFS_CF_NODE		0x0001	/* Collecting node blocks */
+#define NILFS_CF_IFILE_STARTED	0x0002	/* IFILE stage has started */
+#define NILFS_CF_SUFREED	0x0004	/* segment usages has been freed */
+#define NILFS_CF_HISTORY_MASK	(NILFS_CF_IFILE_STARTED | NILFS_CF_SUFREED)
+
+/* Operations depending on the construction mode and file type */
+struct nilfs_sc_operations {
+	int (*collect_data)(struct nilfs_sc_info *, struct buffer_head *,
+			    struct inode *);
+	int (*collect_node)(struct nilfs_sc_info *, struct buffer_head *,
+			    struct inode *);
+	int (*collect_bmap)(struct nilfs_sc_info *, struct buffer_head *,
+			    struct inode *);
+	void (*write_data_binfo)(struct nilfs_sc_info *,
+				 struct nilfs_segsum_pointer *,
+				 union nilfs_binfo *);
+	void (*write_node_binfo)(struct nilfs_sc_info *,
+				 struct nilfs_segsum_pointer *,
+				 union nilfs_binfo *);
+};
+
+/*
+ * Other definitions
+ */
+static void nilfs_segctor_start_timer(struct nilfs_sc_info *);
+static void nilfs_segctor_do_flush(struct nilfs_sc_info *, int);
+static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *);
+static void nilfs_dispose_list(struct the_nilfs *, struct list_head *, int);
+
+#define nilfs_cnt32_ge(a, b)   \
+	(typecheck(__u32, a) && typecheck(__u32, b) && \
+	 ((__s32)((a) - (b)) >= 0))
+
+static int nilfs_prepare_segment_lock(struct super_block *sb,
+				      struct nilfs_transaction_info *ti)
+{
+	struct nilfs_transaction_info *cur_ti = current->journal_info;
+	void *save = NULL;
+
+	if (cur_ti) {
+		if (cur_ti->ti_magic == NILFS_TI_MAGIC)
+			return ++cur_ti->ti_count;
+
+		/*
+		 * If journal_info field is occupied by other FS,
+		 * it is saved and will be restored on
+		 * nilfs_transaction_commit().
+		 */
+		nilfs_warn(sb, "journal info from a different FS");
+		save = current->journal_info;
+	}
+	if (!ti) {
+		ti = kmem_cache_alloc(nilfs_transaction_cachep, GFP_NOFS);
+		if (!ti)
+			return -ENOMEM;
+		ti->ti_flags = NILFS_TI_DYNAMIC_ALLOC;
+	} else {
+		ti->ti_flags = 0;
+	}
+	ti->ti_count = 0;
+	ti->ti_save = save;
+	ti->ti_magic = NILFS_TI_MAGIC;
+	current->journal_info = ti;
+	return 0;
+}
+
+/**
+ * nilfs_transaction_begin - start indivisible file operations.
+ * @sb: super block
+ * @ti: nilfs_transaction_info
+ * @vacancy_check: flags for vacancy rate checks
+ *
+ * nilfs_transaction_begin() acquires a reader/writer semaphore, called
+ * the segment semaphore, to make a segment construction and write tasks
+ * exclusive.  The function is used with nilfs_transaction_commit() in pairs.
+ * The region enclosed by these two functions can be nested.  To avoid a
+ * deadlock, the semaphore is only acquired or released in the outermost call.
+ *
+ * This function allocates a nilfs_transaction_info struct to keep context
+ * information on it.  It is initialized and hooked onto the current task in
+ * the outermost call.  If a pre-allocated struct is given to @ti, it is used
+ * instead; otherwise a new struct is assigned from a slab.
+ *
+ * When @vacancy_check flag is set, this function will check the amount of
+ * free space, and will wait for the GC to reclaim disk space if low capacity.
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-ENOMEM	- Insufficient memory available.
+ * * %-ENOSPC	- No space left on device (if checking free space).
+ */
+int nilfs_transaction_begin(struct super_block *sb,
+			    struct nilfs_transaction_info *ti,
+			    int vacancy_check)
+{
+	struct the_nilfs *nilfs;
+	int ret = nilfs_prepare_segment_lock(sb, ti);
+	struct nilfs_transaction_info *trace_ti;
+
+	if (unlikely(ret < 0))
+		return ret;
+	if (ret > 0) {
+		trace_ti = current->journal_info;
+
+		trace_nilfs2_transaction_transition(sb, trace_ti,
+				    trace_ti->ti_count, trace_ti->ti_flags,
+				    TRACE_NILFS2_TRANSACTION_BEGIN);
+		return 0;
+	}
+
+	sb_start_intwrite(sb);
+
+	nilfs = sb->s_fs_info;
+	down_read(&nilfs->ns_segctor_sem);
+	if (vacancy_check && nilfs_near_disk_full(nilfs)) {
+		up_read(&nilfs->ns_segctor_sem);
+		ret = -ENOSPC;
+		goto failed;
+	}
+
+	trace_ti = current->journal_info;
+	trace_nilfs2_transaction_transition(sb, trace_ti, trace_ti->ti_count,
+					    trace_ti->ti_flags,
+					    TRACE_NILFS2_TRANSACTION_BEGIN);
+	return 0;
+
+ failed:
+	ti = current->journal_info;
+	current->journal_info = ti->ti_save;
+	if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
+		kmem_cache_free(nilfs_transaction_cachep, ti);
+	sb_end_intwrite(sb);
+	return ret;
+}
+
+/**
+ * nilfs_transaction_commit - commit indivisible file operations.
+ * @sb: super block
+ *
+ * nilfs_transaction_commit() releases the read semaphore which is
+ * acquired by nilfs_transaction_begin(). This is only performed
+ * in outermost call of this function.  If a commit flag is set,
+ * nilfs_transaction_commit() sets a timer to start the segment
+ * constructor.  If a sync flag is set, it starts construction
+ * directly.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+int nilfs_transaction_commit(struct super_block *sb)
+{
+	struct nilfs_transaction_info *ti = current->journal_info;
+	struct the_nilfs *nilfs = sb->s_fs_info;
+	int err = 0;
+
+	BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
+	ti->ti_flags |= NILFS_TI_COMMIT;
+	if (ti->ti_count > 0) {
+		ti->ti_count--;
+		trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+			    ti->ti_flags, TRACE_NILFS2_TRANSACTION_COMMIT);
+		return 0;
+	}
+	if (nilfs->ns_writer) {
+		struct nilfs_sc_info *sci = nilfs->ns_writer;
+
+		if (ti->ti_flags & NILFS_TI_COMMIT)
+			nilfs_segctor_start_timer(sci);
+		if (atomic_read(&nilfs->ns_ndirtyblks) > sci->sc_watermark)
+			nilfs_segctor_do_flush(sci, 0);
+	}
+	up_read(&nilfs->ns_segctor_sem);
+	trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+			    ti->ti_flags, TRACE_NILFS2_TRANSACTION_COMMIT);
+
+	current->journal_info = ti->ti_save;
+
+	if (ti->ti_flags & NILFS_TI_SYNC)
+		err = nilfs_construct_segment(sb);
+	if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
+		kmem_cache_free(nilfs_transaction_cachep, ti);
+	sb_end_intwrite(sb);
+	return err;
+}
+
+void nilfs_transaction_abort(struct super_block *sb)
+{
+	struct nilfs_transaction_info *ti = current->journal_info;
+	struct the_nilfs *nilfs = sb->s_fs_info;
+
+	BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
+	if (ti->ti_count > 0) {
+		ti->ti_count--;
+		trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+			    ti->ti_flags, TRACE_NILFS2_TRANSACTION_ABORT);
+		return;
+	}
+	up_read(&nilfs->ns_segctor_sem);
+
+	trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+		    ti->ti_flags, TRACE_NILFS2_TRANSACTION_ABORT);
+
+	current->journal_info = ti->ti_save;
+	if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
+		kmem_cache_free(nilfs_transaction_cachep, ti);
+	sb_end_intwrite(sb);
+}
+
+void nilfs_relax_pressure_in_lock(struct super_block *sb)
+{
+	struct the_nilfs *nilfs = sb->s_fs_info;
+	struct nilfs_sc_info *sci = nilfs->ns_writer;
+
+	if (sb_rdonly(sb) || unlikely(!sci) || !sci->sc_flush_request)
+		return;
+
+	set_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags);
+	up_read(&nilfs->ns_segctor_sem);
+
+	down_write(&nilfs->ns_segctor_sem);
+	if (sci->sc_flush_request &&
+	    test_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags)) {
+		struct nilfs_transaction_info *ti = current->journal_info;
+
+		ti->ti_flags |= NILFS_TI_WRITER;
+		nilfs_segctor_do_immediate_flush(sci);
+		ti->ti_flags &= ~NILFS_TI_WRITER;
+	}
+	downgrade_write(&nilfs->ns_segctor_sem);
+}
+
+static void nilfs_transaction_lock(struct super_block *sb,
+				   struct nilfs_transaction_info *ti,
+				   int gcflag)
+{
+	struct nilfs_transaction_info *cur_ti = current->journal_info;
+	struct the_nilfs *nilfs = sb->s_fs_info;
+	struct nilfs_sc_info *sci = nilfs->ns_writer;
+
+	WARN_ON(cur_ti);
+	ti->ti_flags = NILFS_TI_WRITER;
+	ti->ti_count = 0;
+	ti->ti_save = cur_ti;
+	ti->ti_magic = NILFS_TI_MAGIC;
+	current->journal_info = ti;
+
+	for (;;) {
+		trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+			    ti->ti_flags, TRACE_NILFS2_TRANSACTION_TRYLOCK);
+
+		down_write(&nilfs->ns_segctor_sem);
+		if (!test_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags))
+			break;
+
+		nilfs_segctor_do_immediate_flush(sci);
+
+		up_write(&nilfs->ns_segctor_sem);
+		cond_resched();
+	}
+	if (gcflag)
+		ti->ti_flags |= NILFS_TI_GC;
+
+	trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+			    ti->ti_flags, TRACE_NILFS2_TRANSACTION_LOCK);
+}
+
+static void nilfs_transaction_unlock(struct super_block *sb)
+{
+	struct nilfs_transaction_info *ti = current->journal_info;
+	struct the_nilfs *nilfs = sb->s_fs_info;
+
+	BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
+	BUG_ON(ti->ti_count > 0);
+
+	up_write(&nilfs->ns_segctor_sem);
+	current->journal_info = ti->ti_save;
+
+	trace_nilfs2_transaction_transition(sb, ti, ti->ti_count,
+			    ti->ti_flags, TRACE_NILFS2_TRANSACTION_UNLOCK);
+}
+
+static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci,
+					    struct nilfs_segsum_pointer *ssp,
+					    unsigned int bytes)
+{
+	struct nilfs_segment_buffer *segbuf = sci->sc_curseg;
+	unsigned int blocksize = sci->sc_super->s_blocksize;
+	void *p;
+
+	if (unlikely(ssp->offset + bytes > blocksize)) {
+		ssp->offset = 0;
+		BUG_ON(NILFS_SEGBUF_BH_IS_LAST(ssp->bh,
+					       &segbuf->sb_segsum_buffers));
+		ssp->bh = NILFS_SEGBUF_NEXT_BH(ssp->bh);
+	}
+	p = ssp->bh->b_data + ssp->offset;
+	ssp->offset += bytes;
+	return p;
+}
+
+/**
+ * nilfs_segctor_reset_segment_buffer - reset the current segment buffer
+ * @sci: nilfs_sc_info
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci)
+{
+	struct nilfs_segment_buffer *segbuf = sci->sc_curseg;
+	struct buffer_head *sumbh;
+	unsigned int sumbytes;
+	unsigned int flags = 0;
+	int err;
+
+	if (nilfs_doing_gc())
+		flags = NILFS_SS_GC;
+	err = nilfs_segbuf_reset(segbuf, flags, sci->sc_seg_ctime, sci->sc_cno);
+	if (unlikely(err))
+		return err;
+
+	sumbh = NILFS_SEGBUF_FIRST_BH(&segbuf->sb_segsum_buffers);
+	sumbytes = segbuf->sb_sum.sumbytes;
+	sci->sc_finfo_ptr.bh = sumbh;  sci->sc_finfo_ptr.offset = sumbytes;
+	sci->sc_binfo_ptr.bh = sumbh;  sci->sc_binfo_ptr.offset = sumbytes;
+	sci->sc_blk_cnt = sci->sc_datablk_cnt = 0;
+	return 0;
+}
+
+/**
+ * nilfs_segctor_zeropad_segsum - zero pad the rest of the segment summary area
+ * @sci: segment constructor object
+ *
+ * nilfs_segctor_zeropad_segsum() zero-fills unallocated space at the end of
+ * the current segment summary block.
+ */
+static void nilfs_segctor_zeropad_segsum(struct nilfs_sc_info *sci)
+{
+	struct nilfs_segsum_pointer *ssp;
+
+	ssp = sci->sc_blk_cnt > 0 ? &sci->sc_binfo_ptr : &sci->sc_finfo_ptr;
+	if (ssp->offset < ssp->bh->b_size)
+		memset(ssp->bh->b_data + ssp->offset, 0,
+		       ssp->bh->b_size - ssp->offset);
+}
+
+static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci)
+{
+	sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks;
+	if (NILFS_SEGBUF_IS_LAST(sci->sc_curseg, &sci->sc_segbufs))
+		return -E2BIG; /*
+				* The current segment is filled up
+				* (internal code)
+				*/
+	nilfs_segctor_zeropad_segsum(sci);
+	sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg);
+	return nilfs_segctor_reset_segment_buffer(sci);
+}
+
+static int nilfs_segctor_add_super_root(struct nilfs_sc_info *sci)
+{
+	struct nilfs_segment_buffer *segbuf = sci->sc_curseg;
+	int err;
+
+	if (segbuf->sb_sum.nblocks >= segbuf->sb_rest_blocks) {
+		err = nilfs_segctor_feed_segment(sci);
+		if (err)
+			return err;
+		segbuf = sci->sc_curseg;
+	}
+	err = nilfs_segbuf_extend_payload(segbuf, &segbuf->sb_super_root);
+	if (likely(!err))
+		segbuf->sb_sum.flags |= NILFS_SS_SR;
+	return err;
+}
+
+/*
+ * Functions for making segment summary and payloads
+ */
+static int nilfs_segctor_segsum_block_required(
+	struct nilfs_sc_info *sci, const struct nilfs_segsum_pointer *ssp,
+	unsigned int binfo_size)
+{
+	unsigned int blocksize = sci->sc_super->s_blocksize;
+	/* Size of finfo and binfo is enough small against blocksize */
+
+	return ssp->offset + binfo_size +
+		(!sci->sc_blk_cnt ? sizeof(struct nilfs_finfo) : 0) >
+		blocksize;
+}
+
+static void nilfs_segctor_begin_finfo(struct nilfs_sc_info *sci,
+				      struct inode *inode)
+{
+	sci->sc_curseg->sb_sum.nfinfo++;
+	sci->sc_binfo_ptr = sci->sc_finfo_ptr;
+	nilfs_segctor_map_segsum_entry(
+		sci, &sci->sc_binfo_ptr, sizeof(struct nilfs_finfo));
+
+	if (NILFS_I(inode)->i_root &&
+	    !test_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags))
+		set_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags);
+	/* skip finfo */
+}
+
+static void nilfs_segctor_end_finfo(struct nilfs_sc_info *sci,
+				    struct inode *inode)
+{
+	struct nilfs_finfo *finfo;
+	struct nilfs_inode_info *ii;
+	struct nilfs_segment_buffer *segbuf;
+	__u64 cno;
+
+	if (sci->sc_blk_cnt == 0)
+		return;
+
+	ii = NILFS_I(inode);
+
+	if (ii->i_type & NILFS_I_TYPE_GC)
+		cno = ii->i_cno;
+	else if (NILFS_ROOT_METADATA_FILE(inode->i_ino))
+		cno = 0;
+	else
+		cno = sci->sc_cno;
+
+	finfo = nilfs_segctor_map_segsum_entry(sci, &sci->sc_finfo_ptr,
+						 sizeof(*finfo));
+	finfo->fi_ino = cpu_to_le64(inode->i_ino);
+	finfo->fi_nblocks = cpu_to_le32(sci->sc_blk_cnt);
+	finfo->fi_ndatablk = cpu_to_le32(sci->sc_datablk_cnt);
+	finfo->fi_cno = cpu_to_le64(cno);
+
+	segbuf = sci->sc_curseg;
+	segbuf->sb_sum.sumbytes = sci->sc_binfo_ptr.offset +
+		sci->sc_super->s_blocksize * (segbuf->sb_sum.nsumblk - 1);
+	sci->sc_finfo_ptr = sci->sc_binfo_ptr;
+	sci->sc_blk_cnt = sci->sc_datablk_cnt = 0;
+}
+
+static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci,
+					struct buffer_head *bh,
+					struct inode *inode,
+					unsigned int binfo_size)
+{
+	struct nilfs_segment_buffer *segbuf;
+	int required, err = 0;
+
+ retry:
+	segbuf = sci->sc_curseg;
+	required = nilfs_segctor_segsum_block_required(
+		sci, &sci->sc_binfo_ptr, binfo_size);
+	if (segbuf->sb_sum.nblocks + required + 1 > segbuf->sb_rest_blocks) {
+		nilfs_segctor_end_finfo(sci, inode);
+		err = nilfs_segctor_feed_segment(sci);
+		if (err)
+			return err;
+		goto retry;
+	}
+	if (unlikely(required)) {
+		nilfs_segctor_zeropad_segsum(sci);
+		err = nilfs_segbuf_extend_segsum(segbuf);
+		if (unlikely(err))
+			goto failed;
+	}
+	if (sci->sc_blk_cnt == 0)
+		nilfs_segctor_begin_finfo(sci, inode);
+
+	nilfs_segctor_map_segsum_entry(sci, &sci->sc_binfo_ptr, binfo_size);
+	/* Substitution to vblocknr is delayed until update_blocknr() */
+	nilfs_segbuf_add_file_buffer(segbuf, bh);
+	sci->sc_blk_cnt++;
+ failed:
+	return err;
+}
+
+/*
+ * Callback functions that enumerate, mark, and collect dirty blocks
+ */
+static int nilfs_collect_file_data(struct nilfs_sc_info *sci,
+				   struct buffer_head *bh, struct inode *inode)
+{
+	int err;
+
+	err = nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
+	if (err < 0)
+		return err;
+
+	err = nilfs_segctor_add_file_block(sci, bh, inode,
+					   sizeof(struct nilfs_binfo_v));
+	if (!err)
+		sci->sc_datablk_cnt++;
+	return err;
+}
+
+static int nilfs_collect_file_node(struct nilfs_sc_info *sci,
+				   struct buffer_head *bh,
+				   struct inode *inode)
+{
+	return nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
+}
+
+static int nilfs_collect_file_bmap(struct nilfs_sc_info *sci,
+				   struct buffer_head *bh,
+				   struct inode *inode)
+{
+	WARN_ON(!buffer_dirty(bh));
+	return nilfs_segctor_add_file_block(sci, bh, inode, sizeof(__le64));
+}
+
+static void nilfs_write_file_data_binfo(struct nilfs_sc_info *sci,
+					struct nilfs_segsum_pointer *ssp,
+					union nilfs_binfo *binfo)
+{
+	struct nilfs_binfo_v *binfo_v = nilfs_segctor_map_segsum_entry(
+		sci, ssp, sizeof(*binfo_v));
+	*binfo_v = binfo->bi_v;
+}
+
+static void nilfs_write_file_node_binfo(struct nilfs_sc_info *sci,
+					struct nilfs_segsum_pointer *ssp,
+					union nilfs_binfo *binfo)
+{
+	__le64 *vblocknr = nilfs_segctor_map_segsum_entry(
+		sci, ssp, sizeof(*vblocknr));
+	*vblocknr = binfo->bi_v.bi_vblocknr;
+}
+
+static const struct nilfs_sc_operations nilfs_sc_file_ops = {
+	.collect_data = nilfs_collect_file_data,
+	.collect_node = nilfs_collect_file_node,
+	.collect_bmap = nilfs_collect_file_bmap,
+	.write_data_binfo = nilfs_write_file_data_binfo,
+	.write_node_binfo = nilfs_write_file_node_binfo,
+};
+
+static int nilfs_collect_dat_data(struct nilfs_sc_info *sci,
+				  struct buffer_head *bh, struct inode *inode)
+{
+	int err;
+
+	err = nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
+	if (err < 0)
+		return err;
+
+	err = nilfs_segctor_add_file_block(sci, bh, inode, sizeof(__le64));
+	if (!err)
+		sci->sc_datablk_cnt++;
+	return err;
+}
+
+static int nilfs_collect_dat_bmap(struct nilfs_sc_info *sci,
+				  struct buffer_head *bh, struct inode *inode)
+{
+	WARN_ON(!buffer_dirty(bh));
+	return nilfs_segctor_add_file_block(sci, bh, inode,
+					    sizeof(struct nilfs_binfo_dat));
+}
+
+static void nilfs_write_dat_data_binfo(struct nilfs_sc_info *sci,
+				       struct nilfs_segsum_pointer *ssp,
+				       union nilfs_binfo *binfo)
+{
+	__le64 *blkoff = nilfs_segctor_map_segsum_entry(sci, ssp,
+							  sizeof(*blkoff));
+	*blkoff = binfo->bi_dat.bi_blkoff;
+}
+
+static void nilfs_write_dat_node_binfo(struct nilfs_sc_info *sci,
+				       struct nilfs_segsum_pointer *ssp,
+				       union nilfs_binfo *binfo)
+{
+	struct nilfs_binfo_dat *binfo_dat =
+		nilfs_segctor_map_segsum_entry(sci, ssp, sizeof(*binfo_dat));
+	*binfo_dat = binfo->bi_dat;
+}
+
+static const struct nilfs_sc_operations nilfs_sc_dat_ops = {
+	.collect_data = nilfs_collect_dat_data,
+	.collect_node = nilfs_collect_file_node,
+	.collect_bmap = nilfs_collect_dat_bmap,
+	.write_data_binfo = nilfs_write_dat_data_binfo,
+	.write_node_binfo = nilfs_write_dat_node_binfo,
+};
+
+static const struct nilfs_sc_operations nilfs_sc_dsync_ops = {
+	.collect_data = nilfs_collect_file_data,
+	.collect_node = NULL,
+	.collect_bmap = NULL,
+	.write_data_binfo = nilfs_write_file_data_binfo,
+	.write_node_binfo = NULL,
+};
+
+static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
+					      struct list_head *listp,
+					      size_t nlimit,
+					      loff_t start, loff_t end)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct folio_batch fbatch;
+	pgoff_t index = 0, last = ULONG_MAX;
+	size_t ndirties = 0;
+	int i;
+
+	if (unlikely(start != 0 || end != LLONG_MAX)) {
+		/*
+		 * A valid range is given for sync-ing data pages. The
+		 * range is rounded to per-page; extra dirty buffers
+		 * may be included if blocksize < pagesize.
+		 */
+		index = start >> PAGE_SHIFT;
+		last = end >> PAGE_SHIFT;
+	}
+	folio_batch_init(&fbatch);
+ repeat:
+	if (unlikely(index > last) ||
+	      !filemap_get_folios_tag(mapping, &index, last,
+		      PAGECACHE_TAG_DIRTY, &fbatch))
+		return ndirties;
+
+	for (i = 0; i < folio_batch_count(&fbatch); i++) {
+		struct buffer_head *bh, *head;
+		struct folio *folio = fbatch.folios[i];
+
+		folio_lock(folio);
+		if (unlikely(folio->mapping != mapping)) {
+			/* Exclude folios removed from the address space */
+			folio_unlock(folio);
+			continue;
+		}
+		head = folio_buffers(folio);
+		if (!head)
+			head = create_empty_buffers(folio,
+					i_blocksize(inode), 0);
+
+		bh = head;
+		do {
+			if (!buffer_dirty(bh) || buffer_async_write(bh))
+				continue;
+			get_bh(bh);
+			list_add_tail(&bh->b_assoc_buffers, listp);
+			ndirties++;
+			if (unlikely(ndirties >= nlimit)) {
+				folio_unlock(folio);
+				folio_batch_release(&fbatch);
+				cond_resched();
+				return ndirties;
+			}
+		} while (bh = bh->b_this_page, bh != head);
+
+		folio_unlock(folio);
+	}
+	folio_batch_release(&fbatch);
+	cond_resched();
+	goto repeat;
+}
+
+static void nilfs_lookup_dirty_node_buffers(struct inode *inode,
+					    struct list_head *listp)
+{
+	struct nilfs_inode_info *ii = NILFS_I(inode);
+	struct inode *btnc_inode = ii->i_assoc_inode;
+	struct folio_batch fbatch;
+	struct buffer_head *bh, *head;
+	unsigned int i;
+	pgoff_t index = 0;
+
+	if (!btnc_inode)
+		return;
+	folio_batch_init(&fbatch);
+
+	while (filemap_get_folios_tag(btnc_inode->i_mapping, &index,
+				(pgoff_t)-1, PAGECACHE_TAG_DIRTY, &fbatch)) {
+		for (i = 0; i < folio_batch_count(&fbatch); i++) {
+			bh = head = folio_buffers(fbatch.folios[i]);
+			do {
+				if (buffer_dirty(bh) &&
+						!buffer_async_write(bh)) {
+					get_bh(bh);
+					list_add_tail(&bh->b_assoc_buffers,
+						      listp);
+				}
+				bh = bh->b_this_page;
+			} while (bh != head);
+		}
+		folio_batch_release(&fbatch);
+		cond_resched();
+	}
+}
+
+static void nilfs_dispose_list(struct the_nilfs *nilfs,
+			       struct list_head *head, int force)
+{
+	struct nilfs_inode_info *ii, *n;
+	struct nilfs_inode_info *ivec[SC_N_INODEVEC], **pii;
+	unsigned int nv = 0;
+
+	while (!list_empty(head)) {
+		spin_lock(&nilfs->ns_inode_lock);
+		list_for_each_entry_safe(ii, n, head, i_dirty) {
+			list_del_init(&ii->i_dirty);
+			if (force) {
+				if (unlikely(ii->i_bh)) {
+					brelse(ii->i_bh);
+					ii->i_bh = NULL;
+				}
+			} else if (test_bit(NILFS_I_DIRTY, &ii->i_state)) {
+				set_bit(NILFS_I_QUEUED, &ii->i_state);
+				list_add_tail(&ii->i_dirty,
+					      &nilfs->ns_dirty_files);
+				continue;
+			}
+			ivec[nv++] = ii;
+			if (nv == SC_N_INODEVEC)
+				break;
+		}
+		spin_unlock(&nilfs->ns_inode_lock);
+
+		for (pii = ivec; nv > 0; pii++, nv--)
+			iput(&(*pii)->vfs_inode);
+	}
+}
+
+static void nilfs_iput_work_func(struct work_struct *work)
+{
+	struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info,
+						 sc_iput_work);
+	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+
+	nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0);
+}
+
+static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs,
+				     struct nilfs_root *root)
+{
+	int ret = 0;
+
+	if (nilfs_mdt_fetch_dirty(root->ifile))
+		ret++;
+	if (nilfs_mdt_fetch_dirty(nilfs->ns_cpfile))
+		ret++;
+	if (nilfs_mdt_fetch_dirty(nilfs->ns_sufile))
+		ret++;
+	if ((ret || nilfs_doing_gc()) && nilfs_mdt_fetch_dirty(nilfs->ns_dat))
+		ret++;
+	return ret;
+}
+
+static int nilfs_segctor_clean(struct nilfs_sc_info *sci)
+{
+	return list_empty(&sci->sc_dirty_files) &&
+		!test_bit(NILFS_SC_DIRTY, &sci->sc_flags) &&
+		sci->sc_nfreesegs == 0 &&
+		(!nilfs_doing_gc() || list_empty(&sci->sc_gc_inodes));
+}
+
+static int nilfs_segctor_confirm(struct nilfs_sc_info *sci)
+{
+	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+	int ret = 0;
+
+	if (nilfs_test_metadata_dirty(nilfs, sci->sc_root))
+		set_bit(NILFS_SC_DIRTY, &sci->sc_flags);
+
+	spin_lock(&nilfs->ns_inode_lock);
+	if (list_empty(&nilfs->ns_dirty_files) && nilfs_segctor_clean(sci))
+		ret++;
+
+	spin_unlock(&nilfs->ns_inode_lock);
+	return ret;
+}
+
+static void nilfs_segctor_clear_metadata_dirty(struct nilfs_sc_info *sci)
+{
+	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+
+	nilfs_mdt_clear_dirty(sci->sc_root->ifile);
+	nilfs_mdt_clear_dirty(nilfs->ns_cpfile);
+	nilfs_mdt_clear_dirty(nilfs->ns_sufile);
+	nilfs_mdt_clear_dirty(nilfs->ns_dat);
+}
+
+static void nilfs_fill_in_file_bmap(struct inode *ifile,
+				    struct nilfs_inode_info *ii)
+
+{
+	struct buffer_head *ibh;
+	struct nilfs_inode *raw_inode;
+
+	if (test_bit(NILFS_I_BMAP, &ii->i_state)) {
+		ibh = ii->i_bh;
+		BUG_ON(!ibh);
+		raw_inode = nilfs_ifile_map_inode(ifile, ii->vfs_inode.i_ino,
+						  ibh);
+		nilfs_bmap_write(ii->i_bmap, raw_inode);
+		nilfs_ifile_unmap_inode(raw_inode);
+	}
+}
+
+static void nilfs_segctor_fill_in_file_bmap(struct nilfs_sc_info *sci)
+{
+	struct nilfs_inode_info *ii;
+
+	list_for_each_entry(ii, &sci->sc_dirty_files, i_dirty) {
+		nilfs_fill_in_file_bmap(sci->sc_root->ifile, ii);
+		set_bit(NILFS_I_COLLECTED, &ii->i_state);
+	}
+}
+
+/**
+ * nilfs_write_root_mdt_inode - export root metadata inode information to
+ *                              the on-disk inode
+ * @inode:     inode object of the root metadata file
+ * @raw_inode: on-disk inode
+ *
+ * nilfs_write_root_mdt_inode() writes inode information and bmap data of
+ * @inode to the inode area of the metadata file allocated on the super root
+ * block created to finalize the log.  Since super root blocks are configured
+ * each time, this function zero-fills the unused area of @raw_inode.
+ */
+static void nilfs_write_root_mdt_inode(struct inode *inode,
+				       struct nilfs_inode *raw_inode)
+{
+	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
+
+	nilfs_write_inode_common(inode, raw_inode);
+
+	/* zero-fill unused portion of raw_inode */
+	raw_inode->i_xattr = 0;
+	raw_inode->i_pad = 0;
+	memset((void *)raw_inode + sizeof(*raw_inode), 0,
+	       nilfs->ns_inode_size - sizeof(*raw_inode));
+
+	nilfs_bmap_write(NILFS_I(inode)->i_bmap, raw_inode);
+}
+
+static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci,
+					     struct the_nilfs *nilfs)
+{
+	struct buffer_head *bh_sr;
+	struct nilfs_super_root *raw_sr;
+	unsigned int isz, srsz;
+
+	bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root;
+
+	lock_buffer(bh_sr);
+	raw_sr = (struct nilfs_super_root *)bh_sr->b_data;
+	isz = nilfs->ns_inode_size;
+	srsz = NILFS_SR_BYTES(isz);
+
+	raw_sr->sr_sum = 0;  /* Ensure initialization within this update */
+	raw_sr->sr_bytes = cpu_to_le16(srsz);
+	raw_sr->sr_nongc_ctime
+		= cpu_to_le64(nilfs_doing_gc() ?
+			      nilfs->ns_nongc_ctime : sci->sc_seg_ctime);
+	raw_sr->sr_flags = 0;
+
+	nilfs_write_root_mdt_inode(nilfs->ns_dat, (void *)raw_sr +
+				   NILFS_SR_DAT_OFFSET(isz));
+	nilfs_write_root_mdt_inode(nilfs->ns_cpfile, (void *)raw_sr +
+				   NILFS_SR_CPFILE_OFFSET(isz));
+	nilfs_write_root_mdt_inode(nilfs->ns_sufile, (void *)raw_sr +
+				   NILFS_SR_SUFILE_OFFSET(isz));
+
+	memset((void *)raw_sr + srsz, 0, nilfs->ns_blocksize - srsz);
+	set_buffer_uptodate(bh_sr);
+	unlock_buffer(bh_sr);
+}
+
+static void nilfs_redirty_inodes(struct list_head *head)
+{
+	struct nilfs_inode_info *ii;
+
+	list_for_each_entry(ii, head, i_dirty) {
+		if (test_bit(NILFS_I_COLLECTED, &ii->i_state))
+			clear_bit(NILFS_I_COLLECTED, &ii->i_state);
+	}
+}
+
+static void nilfs_drop_collected_inodes(struct list_head *head)
+{
+	struct nilfs_inode_info *ii;
+
+	list_for_each_entry(ii, head, i_dirty) {
+		if (!test_and_clear_bit(NILFS_I_COLLECTED, &ii->i_state))
+			continue;
+
+		clear_bit(NILFS_I_INODE_SYNC, &ii->i_state);
+		set_bit(NILFS_I_UPDATED, &ii->i_state);
+	}
+}
+
+static int nilfs_segctor_apply_buffers(struct nilfs_sc_info *sci,
+				       struct inode *inode,
+				       struct list_head *listp,
+				       int (*collect)(struct nilfs_sc_info *,
+						      struct buffer_head *,
+						      struct inode *))
+{
+	struct buffer_head *bh, *n;
+	int err = 0;
+
+	if (collect) {
+		list_for_each_entry_safe(bh, n, listp, b_assoc_buffers) {
+			list_del_init(&bh->b_assoc_buffers);
+			err = collect(sci, bh, inode);
+			brelse(bh);
+			if (unlikely(err))
+				goto dispose_buffers;
+		}
+		return 0;
+	}
+
+ dispose_buffers:
+	while (!list_empty(listp)) {
+		bh = list_first_entry(listp, struct buffer_head,
+				      b_assoc_buffers);
+		list_del_init(&bh->b_assoc_buffers);
+		brelse(bh);
+	}
+	return err;
+}
+
+static size_t nilfs_segctor_buffer_rest(struct nilfs_sc_info *sci)
+{
+	/* Remaining number of blocks within segment buffer */
+	return sci->sc_segbuf_nblocks -
+		(sci->sc_nblk_this_inc + sci->sc_curseg->sb_sum.nblocks);
+}
+
+static int nilfs_segctor_scan_file(struct nilfs_sc_info *sci,
+				   struct inode *inode,
+				   const struct nilfs_sc_operations *sc_ops)
+{
+	LIST_HEAD(data_buffers);
+	LIST_HEAD(node_buffers);
+	int err;
+
+	if (!(sci->sc_stage.flags & NILFS_CF_NODE)) {
+		size_t n, rest = nilfs_segctor_buffer_rest(sci);
+
+		n = nilfs_lookup_dirty_data_buffers(
+			inode, &data_buffers, rest + 1, 0, LLONG_MAX);
+		if (n > rest) {
+			err = nilfs_segctor_apply_buffers(
+				sci, inode, &data_buffers,
+				sc_ops->collect_data);
+			BUG_ON(!err); /* always receive -E2BIG or true error */
+			goto break_or_fail;
+		}
+	}
+	nilfs_lookup_dirty_node_buffers(inode, &node_buffers);
+
+	if (!(sci->sc_stage.flags & NILFS_CF_NODE)) {
+		err = nilfs_segctor_apply_buffers(
+			sci, inode, &data_buffers, sc_ops->collect_data);
+		if (unlikely(err)) {
+			/* dispose node list */
+			nilfs_segctor_apply_buffers(
+				sci, inode, &node_buffers, NULL);
+			goto break_or_fail;
+		}
+		sci->sc_stage.flags |= NILFS_CF_NODE;
+	}
+	/* Collect node */
+	err = nilfs_segctor_apply_buffers(
+		sci, inode, &node_buffers, sc_ops->collect_node);
+	if (unlikely(err))
+		goto break_or_fail;
+
+	nilfs_bmap_lookup_dirty_buffers(NILFS_I(inode)->i_bmap, &node_buffers);
+	err = nilfs_segctor_apply_buffers(
+		sci, inode, &node_buffers, sc_ops->collect_bmap);
+	if (unlikely(err))
+		goto break_or_fail;
+
+	nilfs_segctor_end_finfo(sci, inode);
+	sci->sc_stage.flags &= ~NILFS_CF_NODE;
+
+ break_or_fail:
+	return err;
+}
+
+static int nilfs_segctor_scan_file_dsync(struct nilfs_sc_info *sci,
+					 struct inode *inode)
+{
+	LIST_HEAD(data_buffers);
+	size_t n, rest = nilfs_segctor_buffer_rest(sci);
+	int err;
+
+	n = nilfs_lookup_dirty_data_buffers(inode, &data_buffers, rest + 1,
+					    sci->sc_dsync_start,
+					    sci->sc_dsync_end);
+
+	err = nilfs_segctor_apply_buffers(sci, inode, &data_buffers,
+					  nilfs_collect_file_data);
+	if (!err) {
+		nilfs_segctor_end_finfo(sci, inode);
+		BUG_ON(n > rest);
+		/* always receive -E2BIG or true error if n > rest */
+	}
+	return err;
+}
+
+/**
+ * nilfs_free_segments - free the segments given by an array of segment numbers
+ * @nilfs:   nilfs object
+ * @segnumv: array of segment numbers to be freed
+ * @nsegs:   number of segments to be freed in @segnumv
+ *
+ * nilfs_free_segments() wraps nilfs_sufile_freev() and
+ * nilfs_sufile_cancel_freev(), and edits the segment usage metadata file
+ * (sufile) to free all segments given by @segnumv and @nsegs at once.  If
+ * it fails midway, it cancels the changes so that none of the segments are
+ * freed.  If @nsegs is 0, this function does nothing.
+ *
+ * The freeing of segments is not finalized until the writing of a log with
+ * a super root block containing this sufile change is complete, and it can
+ * be canceled with nilfs_sufile_cancel_freev() until then.
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EINVAL	- Invalid segment number.
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
+ */
+static int nilfs_free_segments(struct the_nilfs *nilfs, __u64 *segnumv,
+			       size_t nsegs)
+{
+	size_t ndone;
+	int ret;
+
+	if (!nsegs)
+		return 0;
+
+	ret = nilfs_sufile_freev(nilfs->ns_sufile, segnumv, nsegs, &ndone);
+	if (unlikely(ret)) {
+		nilfs_sufile_cancel_freev(nilfs->ns_sufile, segnumv, ndone,
+					  NULL);
+		/*
+		 * If a segment usage of the segments to be freed is in a
+		 * hole block, nilfs_sufile_freev() will return -ENOENT.
+		 * In this case, -EINVAL should be returned to the caller
+		 * since there is something wrong with the given segment
+		 * number array.  This error can only occur during GC, so
+		 * there is no need to worry about it propagating to other
+		 * callers (such as fsync).
+		 */
+		if (ret == -ENOENT) {
+			nilfs_err(nilfs->ns_sb,
+				  "The segment usage entry %llu to be freed is invalid (in a hole)",
+				  (unsigned long long)segnumv[ndone]);
+			ret = -EINVAL;
+		}
+	}
+	return ret;
+}
+
+static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
+{
+	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+	struct list_head *head;
+	struct nilfs_inode_info *ii;
+	int err = 0;
+
+	switch (nilfs_sc_cstage_get(sci)) {
+	case NILFS_ST_INIT:
+		/* Pre-processes */
+		sci->sc_stage.flags = 0;
+
+		if (!test_bit(NILFS_SC_UNCLOSED, &sci->sc_flags)) {
+			sci->sc_nblk_inc = 0;
+			sci->sc_curseg->sb_sum.flags = NILFS_SS_LOGBGN;
+			if (mode == SC_LSEG_DSYNC) {
+				nilfs_sc_cstage_set(sci, NILFS_ST_DSYNC);
+				goto dsync_mode;
+			}
+		}
+
+		sci->sc_stage.dirty_file_ptr = NULL;
+		sci->sc_stage.gc_inode_ptr = NULL;
+		if (mode == SC_FLUSH_DAT) {
+			nilfs_sc_cstage_set(sci, NILFS_ST_DAT);
+			goto dat_stage;
+		}
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
+	case NILFS_ST_GC:
+		if (nilfs_doing_gc()) {
+			head = &sci->sc_gc_inodes;
+			ii = list_prepare_entry(sci->sc_stage.gc_inode_ptr,
+						head, i_dirty);
+			list_for_each_entry_continue(ii, head, i_dirty) {
+				err = nilfs_segctor_scan_file(
+					sci, &ii->vfs_inode,
+					&nilfs_sc_file_ops);
+				if (unlikely(err)) {
+					sci->sc_stage.gc_inode_ptr = list_entry(
+						ii->i_dirty.prev,
+						struct nilfs_inode_info,
+						i_dirty);
+					goto break_or_fail;
+				}
+				set_bit(NILFS_I_COLLECTED, &ii->i_state);
+			}
+			sci->sc_stage.gc_inode_ptr = NULL;
+		}
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
+	case NILFS_ST_FILE:
+		head = &sci->sc_dirty_files;
+		ii = list_prepare_entry(sci->sc_stage.dirty_file_ptr, head,
+					i_dirty);
+		list_for_each_entry_continue(ii, head, i_dirty) {
+			clear_bit(NILFS_I_DIRTY, &ii->i_state);
+
+			err = nilfs_segctor_scan_file(sci, &ii->vfs_inode,
+						      &nilfs_sc_file_ops);
+			if (unlikely(err)) {
+				sci->sc_stage.dirty_file_ptr =
+					list_entry(ii->i_dirty.prev,
+						   struct nilfs_inode_info,
+						   i_dirty);
+				goto break_or_fail;
+			}
+			/* sci->sc_stage.dirty_file_ptr = NILFS_I(inode); */
+			/* XXX: required ? */
+		}
+		sci->sc_stage.dirty_file_ptr = NULL;
+		if (mode == SC_FLUSH_FILE) {
+			nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
+			return 0;
+		}
+		nilfs_sc_cstage_inc(sci);
+		sci->sc_stage.flags |= NILFS_CF_IFILE_STARTED;
+		fallthrough;
+	case NILFS_ST_IFILE:
+		err = nilfs_segctor_scan_file(sci, sci->sc_root->ifile,
+					      &nilfs_sc_file_ops);
+		if (unlikely(err))
+			break;
+		nilfs_sc_cstage_inc(sci);
+		/* Creating a checkpoint */
+		err = nilfs_cpfile_create_checkpoint(nilfs->ns_cpfile,
+						     nilfs->ns_cno);
+		if (unlikely(err))
+			break;
+		fallthrough;
+	case NILFS_ST_CPFILE:
+		err = nilfs_segctor_scan_file(sci, nilfs->ns_cpfile,
+					      &nilfs_sc_file_ops);
+		if (unlikely(err))
+			break;
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
+	case NILFS_ST_SUFILE:
+		err = nilfs_free_segments(nilfs, sci->sc_freesegs,
+					  sci->sc_nfreesegs);
+		if (unlikely(err))
+			break;
+		sci->sc_stage.flags |= NILFS_CF_SUFREED;
+
+		err = nilfs_segctor_scan_file(sci, nilfs->ns_sufile,
+					      &nilfs_sc_file_ops);
+		if (unlikely(err))
+			break;
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
+	case NILFS_ST_DAT:
+ dat_stage:
+		err = nilfs_segctor_scan_file(sci, nilfs->ns_dat,
+					      &nilfs_sc_dat_ops);
+		if (unlikely(err))
+			break;
+		if (mode == SC_FLUSH_DAT) {
+			nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
+			return 0;
+		}
+		nilfs_sc_cstage_inc(sci);
+		fallthrough;
+	case NILFS_ST_SR:
+		if (mode == SC_LSEG_SR) {
+			/* Appending a super root */
+			err = nilfs_segctor_add_super_root(sci);
+			if (unlikely(err))
+				break;
+		}
+		/* End of a logical segment */
+		sci->sc_curseg->sb_sum.flags |= NILFS_SS_LOGEND;
+		nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
+		return 0;
+	case NILFS_ST_DSYNC:
+ dsync_mode:
+		sci->sc_curseg->sb_sum.flags |= NILFS_SS_SYNDT;
+		ii = sci->sc_dsync_inode;
+		if (!test_bit(NILFS_I_BUSY, &ii->i_state))
+			break;
+
+		err = nilfs_segctor_scan_file_dsync(sci, &ii->vfs_inode);
+		if (unlikely(err))
+			break;
+		sci->sc_curseg->sb_sum.flags |= NILFS_SS_LOGEND;
+		nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
+		return 0;
+	case NILFS_ST_DONE:
+		return 0;
+	default:
+		BUG();
+	}
+
+ break_or_fail:
+	return err;
+}
+
+/**
+ * nilfs_segctor_begin_construction - setup segment buffer to make a new log
+ * @sci: nilfs_sc_info
+ * @nilfs: nilfs object
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int nilfs_segctor_begin_construction(struct nilfs_sc_info *sci,
+					    struct the_nilfs *nilfs)
+{
+	struct nilfs_segment_buffer *segbuf, *prev;
+	__u64 nextnum;
+	int err, alloc = 0;
+
+	segbuf = nilfs_segbuf_new(sci->sc_super);
+	if (unlikely(!segbuf))
+		return -ENOMEM;
+
+	if (list_empty(&sci->sc_write_logs)) {
+		nilfs_segbuf_map(segbuf, nilfs->ns_segnum,
+				 nilfs->ns_pseg_offset, nilfs);
+		if (segbuf->sb_rest_blocks < NILFS_PSEG_MIN_BLOCKS) {
+			nilfs_shift_to_next_segment(nilfs);
+			nilfs_segbuf_map(segbuf, nilfs->ns_segnum, 0, nilfs);
+		}
+
+		segbuf->sb_sum.seg_seq = nilfs->ns_seg_seq;
+		nextnum = nilfs->ns_nextnum;
+
+		if (nilfs->ns_segnum == nilfs->ns_nextnum)
+			/* Start from the head of a new full segment */
+			alloc++;
+	} else {
+		/* Continue logs */
+		prev = NILFS_LAST_SEGBUF(&sci->sc_write_logs);
+		nilfs_segbuf_map_cont(segbuf, prev);
+		segbuf->sb_sum.seg_seq = prev->sb_sum.seg_seq;
+		nextnum = prev->sb_nextnum;
+
+		if (segbuf->sb_rest_blocks < NILFS_PSEG_MIN_BLOCKS) {
+			nilfs_segbuf_map(segbuf, prev->sb_nextnum, 0, nilfs);
+			segbuf->sb_sum.seg_seq++;
+			alloc++;
+		}
+	}
+
+	err = nilfs_sufile_mark_dirty(nilfs->ns_sufile, segbuf->sb_segnum);
+	if (err)
+		goto failed;
+
+	if (alloc) {
+		err = nilfs_sufile_alloc(nilfs->ns_sufile, &nextnum);
+		if (err)
+			goto failed;
+	}
+	nilfs_segbuf_set_next_segnum(segbuf, nextnum, nilfs);
+
+	BUG_ON(!list_empty(&sci->sc_segbufs));
+	list_add_tail(&segbuf->sb_list, &sci->sc_segbufs);
+	sci->sc_segbuf_nblocks = segbuf->sb_rest_blocks;
+	return 0;
+
+ failed:
+	nilfs_segbuf_free(segbuf);
+	return err;
+}
+
+static int nilfs_segctor_extend_segments(struct nilfs_sc_info *sci,
+					 struct the_nilfs *nilfs, int nadd)
+{
+	struct nilfs_segment_buffer *segbuf, *prev;
+	struct inode *sufile = nilfs->ns_sufile;
+	__u64 nextnextnum;
+	LIST_HEAD(list);
+	int err, ret, i;
+
+	prev = NILFS_LAST_SEGBUF(&sci->sc_segbufs);
+	/*
+	 * Since the segment specified with nextnum might be allocated during
+	 * the previous construction, the buffer including its segusage may
+	 * not be dirty.  The following call ensures that the buffer is dirty
+	 * and will pin the buffer on memory until the sufile is written.
+	 */
+	err = nilfs_sufile_mark_dirty(sufile, prev->sb_nextnum);
+	if (unlikely(err))
+		return err;
+
+	for (i = 0; i < nadd; i++) {
+		/* extend segment info */
+		err = -ENOMEM;
+		segbuf = nilfs_segbuf_new(sci->sc_super);
+		if (unlikely(!segbuf))
+			goto failed;
+
+		/* map this buffer to region of segment on-disk */
+		nilfs_segbuf_map(segbuf, prev->sb_nextnum, 0, nilfs);
+		sci->sc_segbuf_nblocks += segbuf->sb_rest_blocks;
+
+		/* allocate the next next full segment */
+		err = nilfs_sufile_alloc(sufile, &nextnextnum);
+		if (unlikely(err))
+			goto failed_segbuf;
+
+		segbuf->sb_sum.seg_seq = prev->sb_sum.seg_seq + 1;
+		nilfs_segbuf_set_next_segnum(segbuf, nextnextnum, nilfs);
+
+		list_add_tail(&segbuf->sb_list, &list);
+		prev = segbuf;
+	}
+	list_splice_tail(&list, &sci->sc_segbufs);
+	return 0;
+
+ failed_segbuf:
+	nilfs_segbuf_free(segbuf);
+ failed:
+	list_for_each_entry(segbuf, &list, sb_list) {
+		ret = nilfs_sufile_free(sufile, segbuf->sb_nextnum);
+		nilfs_sufile_warn_on_error(sufile, ret);
+	}
+	nilfs_destroy_logs(&list);
+	return err;
+}
+
+static void nilfs_free_incomplete_logs(struct list_head *logs,
+				       struct the_nilfs *nilfs)
+{
+	struct nilfs_segment_buffer *segbuf, *prev;
+	struct inode *sufile = nilfs->ns_sufile;
+	int ret;
+
+	segbuf = NILFS_FIRST_SEGBUF(logs);
+	if (nilfs->ns_nextnum != segbuf->sb_nextnum) {
+		ret = nilfs_sufile_free(sufile, segbuf->sb_nextnum);
+		nilfs_sufile_warn_on_error(sufile, ret);
+	}
+	if (atomic_read(&segbuf->sb_err)) {
+		/* Case 1: The first segment failed */
+		if (segbuf->sb_pseg_start != segbuf->sb_fseg_start)
+			/*
+			 * Case 1a:  Partial segment appended into an existing
+			 * segment
+			 */
+			nilfs_terminate_segment(nilfs, segbuf->sb_fseg_start,
+						segbuf->sb_fseg_end);
+		else /* Case 1b:  New full segment */
+			set_nilfs_discontinued(nilfs);
+	}
+
+	prev = segbuf;
+	list_for_each_entry_continue(segbuf, logs, sb_list) {
+		if (prev->sb_nextnum != segbuf->sb_nextnum) {
+			ret = nilfs_sufile_free(sufile, segbuf->sb_nextnum);
+			nilfs_sufile_warn_on_error(sufile, ret);
+		}
+		if (atomic_read(&segbuf->sb_err) &&
+		    segbuf->sb_segnum != nilfs->ns_nextnum)
+			/* Case 2: extended segment (!= next) failed */
+			nilfs_sufile_set_error(sufile, segbuf->sb_segnum);
+		prev = segbuf;
+	}
+}
+
+static void nilfs_segctor_update_segusage(struct nilfs_sc_info *sci,
+					  struct inode *sufile)
+{
+	struct nilfs_segment_buffer *segbuf;
+	unsigned long live_blocks;
+	int ret;
+
+	list_for_each_entry(segbuf, &sci->sc_segbufs, sb_list) {
+		live_blocks = segbuf->sb_sum.nblocks +
+			(segbuf->sb_pseg_start - segbuf->sb_fseg_start);
+		ret = nilfs_sufile_set_segment_usage(sufile, segbuf->sb_segnum,
+						     live_blocks,
+						     sci->sc_seg_ctime);
+		nilfs_sufile_warn_on_error(sufile, ret);
+	}
+}
+
+static void nilfs_cancel_segusage(struct list_head *logs, struct inode *sufile)
+{
+	struct nilfs_segment_buffer *segbuf;
+	int ret;
+
+	segbuf = NILFS_FIRST_SEGBUF(logs);
+	ret = nilfs_sufile_set_segment_usage(sufile, segbuf->sb_segnum,
+					     segbuf->sb_pseg_start -
+					     segbuf->sb_fseg_start, 0);
+	nilfs_sufile_warn_on_error(sufile, ret);
+
+	list_for_each_entry_continue(segbuf, logs, sb_list) {
+		ret = nilfs_sufile_set_segment_usage(sufile, segbuf->sb_segnum,
+						     0, 0);
+		nilfs_sufile_warn_on_error(sufile, ret);
+	}
+}
+
+static int nilfs_segctor_truncate_segments(struct nilfs_sc_info *sci,
+					struct nilfs_segment_buffer *last,
+					struct inode *sufile)
+{
+	struct nilfs_segment_buffer *segbuf = last;
+	int ret, err = 0;
+
+	list_for_each_entry_continue(segbuf, &sci->sc_segbufs, sb_list) {
+		sci->sc_segbuf_nblocks -= segbuf->sb_rest_blocks;
+
+		ret = nilfs_sufile_warn_on_error(
+			sufile, nilfs_sufile_free(sufile, segbuf->sb_nextnum));
+		if (unlikely(ret) && err != -EROFS)
+			err = ret;
+	}
+	nilfs_truncate_logs(&sci->sc_segbufs, last);
+	return err;
+}
+
+
+static int nilfs_segctor_collect(struct nilfs_sc_info *sci,
+				 struct the_nilfs *nilfs, int mode)
+{
+	struct nilfs_cstage prev_stage = sci->sc_stage;
+	int err, nadd = 1;
+
+	/* Collection retry loop */
+	for (;;) {
+		sci->sc_nblk_this_inc = 0;
+		sci->sc_curseg = NILFS_FIRST_SEGBUF(&sci->sc_segbufs);
+
+		err = nilfs_segctor_reset_segment_buffer(sci);
+		if (unlikely(err))
+			goto failed;
+
+		err = nilfs_segctor_collect_blocks(sci, mode);
+		sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks;
+		if (!err)
+			break;
+
+		if (unlikely(err != -E2BIG))
+			goto failed;
+
+		/* The current segment is filled up */
+		if (mode != SC_LSEG_SR ||
+		    nilfs_sc_cstage_get(sci) < NILFS_ST_CPFILE)
+			break;
+
+		nilfs_clear_logs(&sci->sc_segbufs);
+
+		if (sci->sc_stage.flags & NILFS_CF_SUFREED) {
+			err = nilfs_sufile_cancel_freev(nilfs->ns_sufile,
+							sci->sc_freesegs,
+							sci->sc_nfreesegs,
+							NULL);
+			nilfs_sufile_warn_on_error(nilfs->ns_sufile, err);
+			sci->sc_stage.flags &= ~NILFS_CF_SUFREED;
+		}
+
+		err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
+		if (unlikely(err))
+			return err;
+
+		nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA);
+		sci->sc_stage = prev_stage;
+	}
+	nilfs_segctor_zeropad_segsum(sci);
+	err = nilfs_segctor_truncate_segments(sci, sci->sc_curseg,
+					nilfs->ns_sufile);
+
+ failed:
+	return err;
+}
+
+static void nilfs_list_replace_buffer(struct buffer_head *old_bh,
+				      struct buffer_head *new_bh)
+{
+	BUG_ON(!list_empty(&new_bh->b_assoc_buffers));
+
+	list_replace_init(&old_bh->b_assoc_buffers, &new_bh->b_assoc_buffers);
+	/* The caller must release old_bh */
+}
+
+static int
+nilfs_segctor_update_payload_blocknr(struct nilfs_sc_info *sci,
+				     struct nilfs_segment_buffer *segbuf,
+				     int mode)
+{
+	struct inode *inode = NULL;
+	sector_t blocknr;
+	unsigned long nfinfo = segbuf->sb_sum.nfinfo;
+	unsigned long nblocks = 0, ndatablk = 0;
+	const struct nilfs_sc_operations *sc_op = NULL;
+	struct nilfs_segsum_pointer ssp;
+	struct nilfs_finfo *finfo = NULL;
+	union nilfs_binfo binfo;
+	struct buffer_head *bh, *bh_org;
+	u64 ino = 0;
+	int err = 0;
+
+	if (!nfinfo)
+		goto out;
+
+	blocknr = segbuf->sb_pseg_start + segbuf->sb_sum.nsumblk;
+	ssp.bh = NILFS_SEGBUF_FIRST_BH(&segbuf->sb_segsum_buffers);
+	ssp.offset = sizeof(struct nilfs_segment_summary);
+
+	list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) {
+		if (bh == segbuf->sb_super_root)
+			break;
+		if (!finfo) {
+			finfo =	nilfs_segctor_map_segsum_entry(
+				sci, &ssp, sizeof(*finfo));
+			ino = le64_to_cpu(finfo->fi_ino);
+			nblocks = le32_to_cpu(finfo->fi_nblocks);
+			ndatablk = le32_to_cpu(finfo->fi_ndatablk);
+
+			inode = bh->b_folio->mapping->host;
+
+			if (mode == SC_LSEG_DSYNC)
+				sc_op = &nilfs_sc_dsync_ops;
+			else if (ino == NILFS_DAT_INO)
+				sc_op = &nilfs_sc_dat_ops;
+			else /* file blocks */
+				sc_op = &nilfs_sc_file_ops;
+		}
+		bh_org = bh;
+		get_bh(bh_org);
+		err = nilfs_bmap_assign(NILFS_I(inode)->i_bmap, &bh, blocknr,
+					&binfo);
+		if (bh != bh_org)
+			nilfs_list_replace_buffer(bh_org, bh);
+		brelse(bh_org);
+		if (unlikely(err))
+			goto failed_bmap;
+
+		if (ndatablk > 0)
+			sc_op->write_data_binfo(sci, &ssp, &binfo);
+		else
+			sc_op->write_node_binfo(sci, &ssp, &binfo);
+
+		blocknr++;
+		if (--nblocks == 0) {
+			finfo = NULL;
+			if (--nfinfo == 0)
+				break;
+		} else if (ndatablk > 0)
+			ndatablk--;
+	}
+ out:
+	return 0;
+
+ failed_bmap:
+	return err;
+}
+
+static int nilfs_segctor_assign(struct nilfs_sc_info *sci, int mode)
+{
+	struct nilfs_segment_buffer *segbuf;
+	int err;
+
+	list_for_each_entry(segbuf, &sci->sc_segbufs, sb_list) {
+		err = nilfs_segctor_update_payload_blocknr(sci, segbuf, mode);
+		if (unlikely(err))
+			return err;
+		nilfs_segbuf_fill_in_segsum(segbuf);
+	}
+	return 0;
+}
+
+static void nilfs_begin_folio_io(struct folio *folio)
+{
+	if (!folio || folio_test_writeback(folio))
+		/*
+		 * For split b-tree node pages, this function may be called
+		 * twice.  We ignore the 2nd or later calls by this check.
+		 */
+		return;
+
+	folio_lock(folio);
+	folio_clear_dirty_for_io(folio);
+	folio_start_writeback(folio);
+	folio_unlock(folio);
+}
+
+/**
+ * nilfs_prepare_write_logs - prepare to write logs
+ * @logs: logs to prepare for writing
+ * @seed: checksum seed value
+ *
+ * nilfs_prepare_write_logs() adds checksums and prepares the block
+ * buffers/folios for writing logs.  In order to stabilize folios of
+ * memory-mapped file blocks by putting them in writeback state before
+ * calculating the checksums, first prepare to write payload blocks other
+ * than segment summary and super root blocks in which the checksums will
+ * be embedded.
+ */
+static void nilfs_prepare_write_logs(struct list_head *logs, u32 seed)
+{
+	struct nilfs_segment_buffer *segbuf;
+	struct folio *bd_folio = NULL, *fs_folio = NULL;
+	struct buffer_head *bh;
+
+	/* Prepare to write payload blocks */
+	list_for_each_entry(segbuf, logs, sb_list) {
+		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
+				    b_assoc_buffers) {
+			if (bh == segbuf->sb_super_root)
+				break;
+			set_buffer_async_write(bh);
+			if (bh->b_folio != fs_folio) {
+				nilfs_begin_folio_io(fs_folio);
+				fs_folio = bh->b_folio;
+			}
+		}
+	}
+	nilfs_begin_folio_io(fs_folio);
+
+	nilfs_add_checksums_on_logs(logs, seed);
+
+	/* Prepare to write segment summary blocks */
+	list_for_each_entry(segbuf, logs, sb_list) {
+		list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
+				    b_assoc_buffers) {
+			mark_buffer_dirty(bh);
+			if (bh->b_folio == bd_folio)
+				continue;
+			if (bd_folio) {
+				folio_lock(bd_folio);
+				folio_wait_writeback(bd_folio);
+				folio_clear_dirty_for_io(bd_folio);
+				folio_start_writeback(bd_folio);
+				folio_unlock(bd_folio);
+			}
+			bd_folio = bh->b_folio;
+		}
+	}
+
+	/* Prepare to write super root block */
+	bh = NILFS_LAST_SEGBUF(logs)->sb_super_root;
+	if (bh) {
+		mark_buffer_dirty(bh);
+		if (bh->b_folio != bd_folio) {
+			folio_lock(bd_folio);
+			folio_wait_writeback(bd_folio);
+			folio_clear_dirty_for_io(bd_folio);
+			folio_start_writeback(bd_folio);
+			folio_unlock(bd_folio);
+			bd_folio = bh->b_folio;
+		}
+	}
+
+	if (bd_folio) {
+		folio_lock(bd_folio);
+		folio_wait_writeback(bd_folio);
+		folio_clear_dirty_for_io(bd_folio);
+		folio_start_writeback(bd_folio);
+		folio_unlock(bd_folio);
+	}
+}
+
+static int nilfs_segctor_write(struct nilfs_sc_info *sci,
+			       struct the_nilfs *nilfs)
+{
+	int ret;
+
+	ret = nilfs_write_logs(&sci->sc_segbufs, nilfs);
+	list_splice_tail_init(&sci->sc_segbufs, &sci->sc_write_logs);
+	return ret;
+}
+
+static void nilfs_end_folio_io(struct folio *folio, int err)
+{
+	if (!folio)
+		return;
+
+	if (buffer_nilfs_node(folio_buffers(folio)) &&
+			!folio_test_writeback(folio)) {
+		/*
+		 * For b-tree node pages, this function may be called twice
+		 * or more because they might be split in a segment.
+		 */
+		if (folio_test_dirty(folio)) {
+			/*
+			 * For pages holding split b-tree node buffers, dirty
+			 * flag on the buffers may be cleared discretely.
+			 * In that case, the page is once redirtied for
+			 * remaining buffers, and it must be cancelled if
+			 * all the buffers get cleaned later.
+			 */
+			folio_lock(folio);
+			if (nilfs_folio_buffers_clean(folio))
+				__nilfs_clear_folio_dirty(folio);
+			folio_unlock(folio);
+		}
+		return;
+	}
+
+	if (err || !nilfs_folio_buffers_clean(folio))
+		filemap_dirty_folio(folio->mapping, folio);
+
+	folio_end_writeback(folio);
+}
+
+static void nilfs_abort_logs(struct list_head *logs, int err)
+{
+	struct nilfs_segment_buffer *segbuf;
+	struct folio *bd_folio = NULL, *fs_folio = NULL;
+	struct buffer_head *bh;
+
+	if (list_empty(logs))
+		return;
+
+	list_for_each_entry(segbuf, logs, sb_list) {
+		list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
+				    b_assoc_buffers) {
+			clear_buffer_uptodate(bh);
+			if (bh->b_folio != bd_folio) {
+				if (bd_folio)
+					folio_end_writeback(bd_folio);
+				bd_folio = bh->b_folio;
+			}
+		}
+
+		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
+				    b_assoc_buffers) {
+			if (bh == segbuf->sb_super_root) {
+				clear_buffer_uptodate(bh);
+				if (bh->b_folio != bd_folio) {
+					folio_end_writeback(bd_folio);
+					bd_folio = bh->b_folio;
+				}
+				break;
+			}
+			clear_buffer_async_write(bh);
+			if (bh->b_folio != fs_folio) {
+				nilfs_end_folio_io(fs_folio, err);
+				fs_folio = bh->b_folio;
+			}
+		}
+	}
+	if (bd_folio)
+		folio_end_writeback(bd_folio);
+
+	nilfs_end_folio_io(fs_folio, err);
+}
+
+static void nilfs_segctor_abort_construction(struct nilfs_sc_info *sci,
+					     struct the_nilfs *nilfs, int err)
+{
+	LIST_HEAD(logs);
+	int ret;
+
+	list_splice_tail_init(&sci->sc_write_logs, &logs);
+	ret = nilfs_wait_on_logs(&logs);
+	nilfs_abort_logs(&logs, ret ? : err);
+
+	list_splice_tail_init(&sci->sc_segbufs, &logs);
+	if (list_empty(&logs))
+		return; /* if the first segment buffer preparation failed */
+
+	nilfs_cancel_segusage(&logs, nilfs->ns_sufile);
+	nilfs_free_incomplete_logs(&logs, nilfs);
+
+	if (sci->sc_stage.flags & NILFS_CF_SUFREED) {
+		ret = nilfs_sufile_cancel_freev(nilfs->ns_sufile,
+						sci->sc_freesegs,
+						sci->sc_nfreesegs,
+						NULL);
+		nilfs_sufile_warn_on_error(nilfs->ns_sufile, ret);
+	}
+
+	nilfs_destroy_logs(&logs);
+}
+
+static void nilfs_set_next_segment(struct the_nilfs *nilfs,
+				   struct nilfs_segment_buffer *segbuf)
+{
+	nilfs->ns_segnum = segbuf->sb_segnum;
+	nilfs->ns_nextnum = segbuf->sb_nextnum;
+	nilfs->ns_pseg_offset = segbuf->sb_pseg_start - segbuf->sb_fseg_start
+		+ segbuf->sb_sum.nblocks;
+	nilfs->ns_seg_seq = segbuf->sb_sum.seg_seq;
+	nilfs->ns_ctime = segbuf->sb_sum.ctime;
+}
+
+static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
+{
+	struct nilfs_segment_buffer *segbuf;
+	struct folio *bd_folio = NULL, *fs_folio = NULL;
+	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+	int update_sr = false;
+
+	list_for_each_entry(segbuf, &sci->sc_write_logs, sb_list) {
+		struct buffer_head *bh;
+
+		list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
+				    b_assoc_buffers) {
+			set_buffer_uptodate(bh);
+			clear_buffer_dirty(bh);
+			if (bh->b_folio != bd_folio) {
+				if (bd_folio)
+					folio_end_writeback(bd_folio);
+				bd_folio = bh->b_folio;
+			}
+		}
+		/*
+		 * We assume that the buffers which belong to the same folio
+		 * continue over the buffer list.
+		 * Under this assumption, the last BHs of folios is
+		 * identifiable by the discontinuity of bh->b_folio
+		 * (folio != fs_folio).
+		 *
+		 * For B-tree node blocks, however, this assumption is not
+		 * guaranteed.  The cleanup code of B-tree node folios needs
+		 * special care.
+		 */
+		list_for_each_entry(bh, &segbuf->sb_payload_buffers,
+				    b_assoc_buffers) {
+			const unsigned long set_bits = BIT(BH_Uptodate);
+			const unsigned long clear_bits =
+				(BIT(BH_Dirty) | BIT(BH_Async_Write) |
+				 BIT(BH_Delay) | BIT(BH_NILFS_Volatile) |
+				 BIT(BH_NILFS_Redirected));
+
+			if (bh == segbuf->sb_super_root) {
+				set_buffer_uptodate(bh);
+				clear_buffer_dirty(bh);
+				if (bh->b_folio != bd_folio) {
+					folio_end_writeback(bd_folio);
+					bd_folio = bh->b_folio;
+				}
+				update_sr = true;
+				break;
+			}
+			set_mask_bits(&bh->b_state, clear_bits, set_bits);
+			if (bh->b_folio != fs_folio) {
+				nilfs_end_folio_io(fs_folio, 0);
+				fs_folio = bh->b_folio;
+			}
+		}
+
+		if (!nilfs_segbuf_simplex(segbuf)) {
+			if (segbuf->sb_sum.flags & NILFS_SS_LOGBGN) {
+				set_bit(NILFS_SC_UNCLOSED, &sci->sc_flags);
+				sci->sc_lseg_stime = jiffies;
+			}
+			if (segbuf->sb_sum.flags & NILFS_SS_LOGEND)
+				clear_bit(NILFS_SC_UNCLOSED, &sci->sc_flags);
+		}
+	}
+	/*
+	 * Since folios may continue over multiple segment buffers,
+	 * end of the last folio must be checked outside of the loop.
+	 */
+	if (bd_folio)
+		folio_end_writeback(bd_folio);
+
+	nilfs_end_folio_io(fs_folio, 0);
+
+	nilfs_drop_collected_inodes(&sci->sc_dirty_files);
+
+	if (nilfs_doing_gc())
+		nilfs_drop_collected_inodes(&sci->sc_gc_inodes);
+	else
+		nilfs->ns_nongc_ctime = sci->sc_seg_ctime;
+
+	sci->sc_nblk_inc += sci->sc_nblk_this_inc;
+
+	segbuf = NILFS_LAST_SEGBUF(&sci->sc_write_logs);
+	nilfs_set_next_segment(nilfs, segbuf);
+
+	if (update_sr) {
+		nilfs->ns_flushed_device = 0;
+		nilfs_set_last_segment(nilfs, segbuf->sb_pseg_start,
+				       segbuf->sb_sum.seg_seq, nilfs->ns_cno++);
+
+		clear_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags);
+		clear_bit(NILFS_SC_DIRTY, &sci->sc_flags);
+		set_bit(NILFS_SC_SUPER_ROOT, &sci->sc_flags);
+		nilfs_segctor_clear_metadata_dirty(sci);
+	} else
+		clear_bit(NILFS_SC_SUPER_ROOT, &sci->sc_flags);
+}
+
+static int nilfs_segctor_wait(struct nilfs_sc_info *sci)
+{
+	int ret;
+
+	ret = nilfs_wait_on_logs(&sci->sc_write_logs);
+	if (!ret) {
+		nilfs_segctor_complete_write(sci);
+		nilfs_destroy_logs(&sci->sc_write_logs);
+	}
+	return ret;
+}
+
+static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci,
+					     struct the_nilfs *nilfs)
+{
+	struct nilfs_inode_info *ii, *n;
+	struct inode *ifile = sci->sc_root->ifile;
+
+	spin_lock(&nilfs->ns_inode_lock);
+ retry:
+	list_for_each_entry_safe(ii, n, &nilfs->ns_dirty_files, i_dirty) {
+		if (!ii->i_bh) {
+			struct buffer_head *ibh;
+			int err;
+
+			spin_unlock(&nilfs->ns_inode_lock);
+			err = nilfs_ifile_get_inode_block(
+				ifile, ii->vfs_inode.i_ino, &ibh);
+			if (unlikely(err)) {
+				nilfs_warn(sci->sc_super,
+					   "log writer: error %d getting inode block (ino=%llu)",
+					   err, ii->vfs_inode.i_ino);
+				return err;
+			}
+			spin_lock(&nilfs->ns_inode_lock);
+			if (likely(!ii->i_bh))
+				ii->i_bh = ibh;
+			else
+				brelse(ibh);
+			goto retry;
+		}
+
+		// Always redirty the buffer to avoid race condition
+		mark_buffer_dirty(ii->i_bh);
+		nilfs_mdt_mark_dirty(ifile);
+
+		clear_bit(NILFS_I_QUEUED, &ii->i_state);
+		set_bit(NILFS_I_BUSY, &ii->i_state);
+		list_move_tail(&ii->i_dirty, &sci->sc_dirty_files);
+	}
+	spin_unlock(&nilfs->ns_inode_lock);
+
+	return 0;
+}
+
+static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
+					     struct the_nilfs *nilfs)
+{
+	struct nilfs_inode_info *ii, *n;
+	int during_mount = !(sci->sc_super->s_flags & SB_ACTIVE);
+	int defer_iput = false;
+
+	spin_lock(&nilfs->ns_inode_lock);
+	list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) {
+		if (!test_and_clear_bit(NILFS_I_UPDATED, &ii->i_state) ||
+		    test_bit(NILFS_I_DIRTY, &ii->i_state))
+			continue;
+
+		clear_bit(NILFS_I_BUSY, &ii->i_state);
+		brelse(ii->i_bh);
+		ii->i_bh = NULL;
+		list_del_init(&ii->i_dirty);
+		if (!ii->vfs_inode.i_nlink || during_mount) {
+			/*
+			 * Defer calling iput() to avoid deadlocks if
+			 * i_nlink == 0 or mount is not yet finished.
+			 */
+			list_add_tail(&ii->i_dirty, &sci->sc_iput_queue);
+			defer_iput = true;
+		} else {
+			spin_unlock(&nilfs->ns_inode_lock);
+			iput(&ii->vfs_inode);
+			spin_lock(&nilfs->ns_inode_lock);
+		}
+	}
+	spin_unlock(&nilfs->ns_inode_lock);
+
+	if (defer_iput)
+		schedule_work(&sci->sc_iput_work);
+}
+
+/*
+ * Main procedure of segment constructor
+ */
+static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
+{
+	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+	int err;
+
+	if (sb_rdonly(sci->sc_super))
+		return -EROFS;
+
+	nilfs_sc_cstage_set(sci, NILFS_ST_INIT);
+	sci->sc_cno = nilfs->ns_cno;
+
+	err = nilfs_segctor_collect_dirty_files(sci, nilfs);
+	if (unlikely(err))
+		goto out;
+
+	if (nilfs_test_metadata_dirty(nilfs, sci->sc_root))
+		set_bit(NILFS_SC_DIRTY, &sci->sc_flags);
+
+	if (nilfs_segctor_clean(sci))
+		goto out;
+
+	do {
+		sci->sc_stage.flags &= ~NILFS_CF_HISTORY_MASK;
+
+		err = nilfs_segctor_begin_construction(sci, nilfs);
+		if (unlikely(err))
+			goto failed;
+
+		/* Update time stamp */
+		sci->sc_seg_ctime = ktime_get_real_seconds();
+
+		err = nilfs_segctor_collect(sci, nilfs, mode);
+		if (unlikely(err))
+			goto failed;
+
+		/* Avoid empty segment */
+		if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE &&
+		    nilfs_segbuf_empty(sci->sc_curseg)) {
+			nilfs_segctor_abort_construction(sci, nilfs, 1);
+			goto out;
+		}
+
+		err = nilfs_segctor_assign(sci, mode);
+		if (unlikely(err))
+			goto failed;
+
+		if (sci->sc_stage.flags & NILFS_CF_IFILE_STARTED)
+			nilfs_segctor_fill_in_file_bmap(sci);
+
+		if (mode == SC_LSEG_SR &&
+		    nilfs_sc_cstage_get(sci) >= NILFS_ST_CPFILE) {
+			err = nilfs_cpfile_finalize_checkpoint(
+				nilfs->ns_cpfile, nilfs->ns_cno, sci->sc_root,
+				sci->sc_nblk_inc + sci->sc_nblk_this_inc,
+				sci->sc_seg_ctime,
+				!test_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags));
+			if (unlikely(err))
+				goto failed_to_write;
+
+			nilfs_segctor_fill_in_super_root(sci, nilfs);
+		}
+		nilfs_segctor_update_segusage(sci, nilfs->ns_sufile);
+
+		/* Write partial segments */
+		nilfs_prepare_write_logs(&sci->sc_segbufs, nilfs->ns_crc_seed);
+
+		err = nilfs_segctor_write(sci, nilfs);
+		if (unlikely(err))
+			goto failed_to_write;
+
+		if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE ||
+		    nilfs->ns_blocksize_bits != PAGE_SHIFT) {
+			/*
+			 * At this point, we avoid double buffering
+			 * for blocksize < pagesize because page dirty
+			 * flag is turned off during write and dirty
+			 * buffers are not properly collected for
+			 * pages crossing over segments.
+			 */
+			err = nilfs_segctor_wait(sci);
+			if (err)
+				goto failed_to_write;
+		}
+	} while (nilfs_sc_cstage_get(sci) != NILFS_ST_DONE);
+
+ out:
+	nilfs_segctor_drop_written_files(sci, nilfs);
+	return err;
+
+ failed_to_write:
+ failed:
+	if (mode == SC_LSEG_SR && nilfs_sc_cstage_get(sci) >= NILFS_ST_IFILE)
+		nilfs_redirty_inodes(&sci->sc_dirty_files);
+	if (nilfs_doing_gc())
+		nilfs_redirty_inodes(&sci->sc_gc_inodes);
+	nilfs_segctor_abort_construction(sci, nilfs, err);
+	goto out;
+}
+
+/**
+ * nilfs_segctor_start_timer - set timer of background write
+ * @sci: nilfs_sc_info
+ *
+ * If the timer has already been set, it ignores the new request.
+ * This function MUST be called within a section locking the segment
+ * semaphore.
+ */
+static void nilfs_segctor_start_timer(struct nilfs_sc_info *sci)
+{
+	spin_lock(&sci->sc_state_lock);
+	if (!(sci->sc_state & NILFS_SEGCTOR_COMMIT)) {
+		if (sci->sc_task) {
+			sci->sc_timer.expires = jiffies + sci->sc_interval;
+			add_timer(&sci->sc_timer);
+		}
+		sci->sc_state |= NILFS_SEGCTOR_COMMIT;
+	}
+	spin_unlock(&sci->sc_state_lock);
+}
+
+static void nilfs_segctor_do_flush(struct nilfs_sc_info *sci, int bn)
+{
+	spin_lock(&sci->sc_state_lock);
+	if (!(sci->sc_flush_request & BIT(bn))) {
+		unsigned long prev_req = sci->sc_flush_request;
+
+		sci->sc_flush_request |= BIT(bn);
+		if (!prev_req)
+			wake_up(&sci->sc_wait_daemon);
+	}
+	spin_unlock(&sci->sc_state_lock);
+}
+
+struct nilfs_segctor_wait_request {
+	wait_queue_entry_t	wq;
+	__u32		seq;
+	int		err;
+	atomic_t	done;
+};
+
+static int nilfs_segctor_sync(struct nilfs_sc_info *sci)
+{
+	struct nilfs_segctor_wait_request wait_req;
+	int err = 0;
+
+	init_wait(&wait_req.wq);
+	wait_req.err = 0;
+	atomic_set(&wait_req.done, 0);
+	init_waitqueue_entry(&wait_req.wq, current);
+
+	/*
+	 * To prevent a race issue where completion notifications from the
+	 * log writer thread are missed, increment the request sequence count
+	 * "sc_seq_request" and insert a wait queue entry using the current
+	 * sequence number into the "sc_wait_request" queue at the same time
+	 * within the lock section of "sc_state_lock".
+	 */
+	spin_lock(&sci->sc_state_lock);
+	wait_req.seq = ++sci->sc_seq_request;
+	add_wait_queue(&sci->sc_wait_request, &wait_req.wq);
+	spin_unlock(&sci->sc_state_lock);
+
+	wake_up(&sci->sc_wait_daemon);
+
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		/*
+		 * Synchronize only while the log writer thread is alive.
+		 * Leave flushing out after the log writer thread exits to
+		 * the cleanup work in nilfs_segctor_destroy().
+		 */
+		if (!sci->sc_task)
+			break;
+
+		if (atomic_read(&wait_req.done)) {
+			err = wait_req.err;
+			break;
+		}
+		if (!signal_pending(current)) {
+			schedule();
+			continue;
+		}
+		err = -ERESTARTSYS;
+		break;
+	}
+	finish_wait(&sci->sc_wait_request, &wait_req.wq);
+	return err;
+}
+
+static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err, bool force)
+{
+	struct nilfs_segctor_wait_request *wrq, *n;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sci->sc_wait_request.lock, flags);
+	list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.head, wq.entry) {
+		if (!atomic_read(&wrq->done) &&
+		    (force || nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq))) {
+			wrq->err = err;
+			atomic_set(&wrq->done, 1);
+		}
+		if (atomic_read(&wrq->done)) {
+			wrq->wq.func(&wrq->wq,
+				     TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE,
+				     0, NULL);
+		}
+	}
+	spin_unlock_irqrestore(&sci->sc_wait_request.lock, flags);
+}
+
+/**
+ * nilfs_construct_segment - construct a logical segment
+ * @sb: super block
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO		- I/O error (including metadata corruption).
+ * * %-ENOMEM		- Insufficient memory available.
+ * * %-ENOSPC		- No space left on device (only in a panic state).
+ * * %-ERESTARTSYS	- Interrupted.
+ * * %-EROFS		- Read only filesystem.
+ */
+int nilfs_construct_segment(struct super_block *sb)
+{
+	struct the_nilfs *nilfs = sb->s_fs_info;
+	struct nilfs_sc_info *sci = nilfs->ns_writer;
+	struct nilfs_transaction_info *ti;
+
+	if (sb_rdonly(sb) || unlikely(!sci))
+		return -EROFS;
+
+	/* A call inside transactions causes a deadlock. */
+	BUG_ON((ti = current->journal_info) && ti->ti_magic == NILFS_TI_MAGIC);
+
+	return nilfs_segctor_sync(sci);
+}
+
+/**
+ * nilfs_construct_dsync_segment - construct a data-only logical segment
+ * @sb: super block
+ * @inode: inode whose data blocks should be written out
+ * @start: start byte offset
+ * @end: end byte offset (inclusive)
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO		- I/O error (including metadata corruption).
+ * * %-ENOMEM		- Insufficient memory available.
+ * * %-ENOSPC		- No space left on device (only in a panic state).
+ * * %-ERESTARTSYS	- Interrupted.
+ * * %-EROFS		- Read only filesystem.
+ */
+int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode,
+				  loff_t start, loff_t end)
+{
+	struct the_nilfs *nilfs = sb->s_fs_info;
+	struct nilfs_sc_info *sci = nilfs->ns_writer;
+	struct nilfs_inode_info *ii;
+	struct nilfs_transaction_info ti;
+	int err = 0;
+
+	if (sb_rdonly(sb) || unlikely(!sci))
+		return -EROFS;
+
+	nilfs_transaction_lock(sb, &ti, 0);
+
+	ii = NILFS_I(inode);
+	if (test_bit(NILFS_I_INODE_SYNC, &ii->i_state) ||
+	    nilfs_test_opt(nilfs, STRICT_ORDER) ||
+	    test_bit(NILFS_SC_UNCLOSED, &sci->sc_flags) ||
+	    nilfs_discontinued(nilfs)) {
+		nilfs_transaction_unlock(sb);
+		err = nilfs_segctor_sync(sci);
+		return err;
+	}
+
+	spin_lock(&nilfs->ns_inode_lock);
+	if (!test_bit(NILFS_I_QUEUED, &ii->i_state) &&
+	    !test_bit(NILFS_I_BUSY, &ii->i_state)) {
+		spin_unlock(&nilfs->ns_inode_lock);
+		nilfs_transaction_unlock(sb);
+		return 0;
+	}
+	spin_unlock(&nilfs->ns_inode_lock);
+	sci->sc_dsync_inode = ii;
+	sci->sc_dsync_start = start;
+	sci->sc_dsync_end = end;
+
+	err = nilfs_segctor_do_construct(sci, SC_LSEG_DSYNC);
+	if (!err)
+		nilfs->ns_flushed_device = 0;
+
+	nilfs_transaction_unlock(sb);
+	return err;
+}
+
+#define FLUSH_FILE_BIT	(0x1) /* data file only */
+#define FLUSH_DAT_BIT	BIT(NILFS_DAT_INO) /* DAT only */
+
+/**
+ * nilfs_segctor_accept - record accepted sequence count of log-write requests
+ * @sci: segment constructor object
+ */
+static void nilfs_segctor_accept(struct nilfs_sc_info *sci)
+{
+	bool thread_is_alive;
+
+	spin_lock(&sci->sc_state_lock);
+	sci->sc_seq_accepted = sci->sc_seq_request;
+	thread_is_alive = (bool)sci->sc_task;
+	spin_unlock(&sci->sc_state_lock);
+
+	/*
+	 * This function does not race with the log writer thread's
+	 * termination.  Therefore, deleting sc_timer, which should not be
+	 * done after the log writer thread exits, can be done safely outside
+	 * the area protected by sc_state_lock.
+	 */
+	if (thread_is_alive)
+		timer_delete_sync(&sci->sc_timer);
+}
+
+/**
+ * nilfs_segctor_notify - notify the result of request to caller threads
+ * @sci: segment constructor object
+ * @mode: mode of log forming
+ * @err: error code to be notified
+ */
+static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err)
+{
+	/* Clear requests (even when the construction failed) */
+	spin_lock(&sci->sc_state_lock);
+
+	if (mode == SC_LSEG_SR) {
+		sci->sc_state &= ~NILFS_SEGCTOR_COMMIT;
+		sci->sc_seq_done = sci->sc_seq_accepted;
+		nilfs_segctor_wakeup(sci, err, false);
+		sci->sc_flush_request = 0;
+	} else {
+		if (mode == SC_FLUSH_FILE)
+			sci->sc_flush_request &= ~FLUSH_FILE_BIT;
+		else if (mode == SC_FLUSH_DAT)
+			sci->sc_flush_request &= ~FLUSH_DAT_BIT;
+
+		/* re-enable timer if checkpoint creation was not done */
+		if ((sci->sc_state & NILFS_SEGCTOR_COMMIT) && sci->sc_task &&
+		    time_before(jiffies, sci->sc_timer.expires))
+			add_timer(&sci->sc_timer);
+	}
+	spin_unlock(&sci->sc_state_lock);
+}
+
+/**
+ * nilfs_segctor_construct - form logs and write them to disk
+ * @sci: segment constructor object
+ * @mode: mode of log forming
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+static int nilfs_segctor_construct(struct nilfs_sc_info *sci, int mode)
+{
+	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+	struct nilfs_super_block **sbp;
+	int err = 0;
+
+	nilfs_segctor_accept(sci);
+
+	if (nilfs_discontinued(nilfs))
+		mode = SC_LSEG_SR;
+	if (!nilfs_segctor_confirm(sci))
+		err = nilfs_segctor_do_construct(sci, mode);
+
+	if (likely(!err)) {
+		if (mode != SC_FLUSH_DAT)
+			atomic_set(&nilfs->ns_ndirtyblks, 0);
+		if (test_bit(NILFS_SC_SUPER_ROOT, &sci->sc_flags) &&
+		    nilfs_discontinued(nilfs)) {
+			down_write(&nilfs->ns_sem);
+			err = -EIO;
+			sbp = nilfs_prepare_super(sci->sc_super,
+						  nilfs_sb_will_flip(nilfs));
+			if (likely(sbp)) {
+				nilfs_set_log_cursor(sbp[0], nilfs);
+				err = nilfs_commit_super(sci->sc_super,
+							 NILFS_SB_COMMIT);
+			}
+			up_write(&nilfs->ns_sem);
+		}
+	}
+
+	nilfs_segctor_notify(sci, mode, err);
+	return err;
+}
+
+static void nilfs_construction_timeout(struct timer_list *t)
+{
+	struct nilfs_sc_info *sci = timer_container_of(sci, t, sc_timer);
+
+	wake_up_process(sci->sc_task);
+}
+
+static void
+nilfs_remove_written_gcinodes(struct the_nilfs *nilfs, struct list_head *head)
+{
+	struct nilfs_inode_info *ii, *n;
+
+	list_for_each_entry_safe(ii, n, head, i_dirty) {
+		if (!test_bit(NILFS_I_UPDATED, &ii->i_state))
+			continue;
+		list_del_init(&ii->i_dirty);
+		truncate_inode_pages(&ii->vfs_inode.i_data, 0);
+		nilfs_btnode_cache_clear(ii->i_assoc_inode->i_mapping);
+		iput(&ii->vfs_inode);
+	}
+}
+
+int nilfs_clean_segments(struct super_block *sb, struct nilfs_argv *argv,
+			 void **kbufs)
+{
+	struct the_nilfs *nilfs = sb->s_fs_info;
+	struct nilfs_sc_info *sci = nilfs->ns_writer;
+	struct nilfs_transaction_info ti;
+	int err;
+	size_t i, nfreesegs = argv[4].v_nmembs;
+	__u64 *segnumv = kbufs[4];
+
+	if (unlikely(!sci))
+		return -EROFS;
+
+	nilfs_transaction_lock(sb, &ti, 1);
+
+	/*
+	 * Validate segment numbers under ns_segctor_sem (held for write
+	 * by nilfs_transaction_lock above) so the check is serialized
+	 * against nilfs_ioctl_resize(), which can modify ns_nsegments.
+	 * Rejecting bad input here, before any segment-cleaning work
+	 * begins, avoids the per-element diagnostic path inside
+	 * nilfs_sufile_updatev() that would otherwise run under this
+	 * same lock and stall concurrent readers.
+	 */
+	for (i = 0; i < nfreesegs; i++) {
+		if (segnumv[i] >= nilfs->ns_nsegments) {
+			nilfs_err(sb,
+				 "Segment number %llu to be freed is out of range",
+				 (unsigned long long)segnumv[i]);
+			err = -EINVAL;
+			goto bail_unlock;
+		}
+	}
+
+	err = nilfs_mdt_save_to_shadow_map(nilfs->ns_dat);
+	if (unlikely(err))
+		goto out_unlock;
+
+	err = nilfs_ioctl_prepare_clean_segments(nilfs, argv, kbufs);
+	if (unlikely(err)) {
+		nilfs_mdt_restore_from_shadow_map(nilfs->ns_dat);
+		goto out_unlock;
+	}
+
+	sci->sc_freesegs = kbufs[4];
+	sci->sc_nfreesegs = argv[4].v_nmembs;
+	list_splice_tail_init(&nilfs->ns_gc_inodes, &sci->sc_gc_inodes);
+
+	for (;;) {
+		err = nilfs_segctor_construct(sci, SC_LSEG_SR);
+		nilfs_remove_written_gcinodes(nilfs, &sci->sc_gc_inodes);
+
+		if (likely(!err))
+			break;
+
+		nilfs_warn(sb, "error %d cleaning segments", err);
+
+		if (unlikely(err == -EROFS))
+			goto out_unlock;
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(sci->sc_interval);
+	}
+	if (nilfs_test_opt(nilfs, DISCARD)) {
+		int ret = nilfs_discard_segments(nilfs, sci->sc_freesegs,
+						 sci->sc_nfreesegs);
+		if (ret) {
+			nilfs_warn(sb,
+				   "error %d on discard request, turning discards off for the device",
+				   ret);
+			nilfs_clear_opt(nilfs, DISCARD);
+		}
+	}
+
+ out_unlock:
+	sci->sc_freesegs = NULL;
+	sci->sc_nfreesegs = 0;
+	nilfs_mdt_clear_shadow_map(nilfs->ns_dat);
+ bail_unlock:
+	nilfs_transaction_unlock(sb);
+	return err;
+}
+
+static void nilfs_segctor_thread_construct(struct nilfs_sc_info *sci, int mode)
+{
+	struct nilfs_transaction_info ti;
+
+	nilfs_transaction_lock(sci->sc_super, &ti, 0);
+	nilfs_segctor_construct(sci, mode);
+
+	/*
+	 * Unclosed segment should be retried.  We do this using sc_timer.
+	 * Timeout of sc_timer will invoke complete construction which leads
+	 * to close the current logical segment.
+	 */
+	if (test_bit(NILFS_SC_UNCLOSED, &sci->sc_flags))
+		nilfs_segctor_start_timer(sci);
+
+	nilfs_transaction_unlock(sci->sc_super);
+}
+
+static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *sci)
+{
+	int mode = 0;
+
+	spin_lock(&sci->sc_state_lock);
+	mode = (sci->sc_flush_request & FLUSH_DAT_BIT) ?
+		SC_FLUSH_DAT : SC_FLUSH_FILE;
+	spin_unlock(&sci->sc_state_lock);
+
+	if (mode) {
+		nilfs_segctor_do_construct(sci, mode);
+
+		spin_lock(&sci->sc_state_lock);
+		sci->sc_flush_request &= (mode == SC_FLUSH_FILE) ?
+			~FLUSH_FILE_BIT : ~FLUSH_DAT_BIT;
+		spin_unlock(&sci->sc_state_lock);
+	}
+	clear_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags);
+}
+
+static int nilfs_segctor_flush_mode(struct nilfs_sc_info *sci)
+{
+	if (!test_bit(NILFS_SC_UNCLOSED, &sci->sc_flags) ||
+	    time_before(jiffies, sci->sc_lseg_stime + sci->sc_mjcp_freq)) {
+		if (!(sci->sc_flush_request & ~FLUSH_FILE_BIT))
+			return SC_FLUSH_FILE;
+		else if (!(sci->sc_flush_request & ~FLUSH_DAT_BIT))
+			return SC_FLUSH_DAT;
+	}
+	return SC_LSEG_SR;
+}
+
+/**
+ * nilfs_log_write_required - determine whether log writing is required
+ * @sci:   nilfs_sc_info struct
+ * @modep: location for storing log writing mode
+ *
+ * Return: true if log writing is required, false otherwise.  If log writing
+ * is required, the mode is stored in the location pointed to by @modep.
+ */
+static bool nilfs_log_write_required(struct nilfs_sc_info *sci, int *modep)
+{
+	bool timedout, ret = true;
+
+	spin_lock(&sci->sc_state_lock);
+	timedout = ((sci->sc_state & NILFS_SEGCTOR_COMMIT) &&
+		   time_after_eq(jiffies, sci->sc_timer.expires));
+	if (timedout || sci->sc_seq_request != sci->sc_seq_done)
+		*modep = SC_LSEG_SR;
+	else if (sci->sc_flush_request)
+		*modep = nilfs_segctor_flush_mode(sci);
+	else
+		ret = false;
+
+	spin_unlock(&sci->sc_state_lock);
+	return ret;
+}
+
+/**
+ * nilfs_segctor_thread - main loop of the log writer thread
+ * @arg: pointer to a struct nilfs_sc_info.
+ *
+ * nilfs_segctor_thread() is the main loop function of the log writer kernel
+ * thread, which determines whether log writing is necessary, and if so,
+ * performs the log write in the background, or waits if not.  It is also
+ * used to decide the background writeback of the superblock.
+ *
+ * Return: Always 0.
+ */
+static int nilfs_segctor_thread(void *arg)
+{
+	struct nilfs_sc_info *sci = (struct nilfs_sc_info *)arg;
+	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+
+	nilfs_info(sci->sc_super,
+		   "segctord starting. Construction interval = %lu seconds, CP frequency < %lu seconds",
+		   sci->sc_interval / HZ, sci->sc_mjcp_freq / HZ);
+
+	set_freezable();
+
+	while (!kthread_should_stop()) {
+		DEFINE_WAIT(wait);
+		bool should_write;
+		int mode;
+
+		if (freezing(current)) {
+			try_to_freeze();
+			continue;
+		}
+
+		prepare_to_wait(&sci->sc_wait_daemon, &wait,
+				TASK_INTERRUPTIBLE);
+		should_write = nilfs_log_write_required(sci, &mode);
+		if (!should_write)
+			schedule();
+		finish_wait(&sci->sc_wait_daemon, &wait);
+
+		if (nilfs_sb_dirty(nilfs) && nilfs_sb_need_update(nilfs))
+			set_nilfs_discontinued(nilfs);
+
+		if (should_write)
+			nilfs_segctor_thread_construct(sci, mode);
+	}
+
+	/* end sync. */
+	spin_lock(&sci->sc_state_lock);
+	sci->sc_task = NULL;
+	timer_shutdown_sync(&sci->sc_timer);
+	spin_unlock(&sci->sc_state_lock);
+	return 0;
+}
+
+/*
+ * Setup & clean-up functions
+ */
+static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb,
+					       struct nilfs_root *root)
+{
+	struct the_nilfs *nilfs = sb->s_fs_info;
+	struct nilfs_sc_info *sci;
+
+	sci = kzalloc_obj(*sci);
+	if (!sci)
+		return NULL;
+
+	sci->sc_super = sb;
+
+	nilfs_get_root(root);
+	sci->sc_root = root;
+
+	init_waitqueue_head(&sci->sc_wait_request);
+	init_waitqueue_head(&sci->sc_wait_daemon);
+	spin_lock_init(&sci->sc_state_lock);
+	INIT_LIST_HEAD(&sci->sc_dirty_files);
+	INIT_LIST_HEAD(&sci->sc_segbufs);
+	INIT_LIST_HEAD(&sci->sc_write_logs);
+	INIT_LIST_HEAD(&sci->sc_gc_inodes);
+	INIT_LIST_HEAD(&sci->sc_iput_queue);
+	INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func);
+
+	sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT;
+	sci->sc_mjcp_freq = HZ * NILFS_SC_DEFAULT_SR_FREQ;
+	sci->sc_watermark = NILFS_SC_DEFAULT_WATERMARK;
+
+	if (nilfs->ns_interval)
+		sci->sc_interval = HZ * nilfs->ns_interval;
+	if (nilfs->ns_watermark)
+		sci->sc_watermark = nilfs->ns_watermark;
+	return sci;
+}
+
+static void nilfs_segctor_write_out(struct nilfs_sc_info *sci)
+{
+	int ret, retrycount = NILFS_SC_CLEANUP_RETRY;
+
+	/*
+	 * The segctord thread was stopped and its timer was removed.
+	 * But some tasks remain.
+	 */
+	do {
+		struct nilfs_transaction_info ti;
+
+		nilfs_transaction_lock(sci->sc_super, &ti, 0);
+		ret = nilfs_segctor_construct(sci, SC_LSEG_SR);
+		nilfs_transaction_unlock(sci->sc_super);
+
+		flush_work(&sci->sc_iput_work);
+
+	} while (ret && ret != -EROFS && retrycount-- > 0);
+}
+
+/**
+ * nilfs_segctor_destroy - destroy the segment constructor.
+ * @sci: nilfs_sc_info
+ *
+ * nilfs_segctor_destroy() kills the segctord thread and frees
+ * the nilfs_sc_info struct.
+ * Caller must hold the segment semaphore.
+ */
+static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
+{
+	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+	int flag;
+
+	up_write(&nilfs->ns_segctor_sem);
+
+	if (sci->sc_task) {
+		wake_up(&sci->sc_wait_daemon);
+		if (kthread_stop(sci->sc_task)) {
+			spin_lock(&sci->sc_state_lock);
+			sci->sc_task = NULL;
+			timer_shutdown_sync(&sci->sc_timer);
+			spin_unlock(&sci->sc_state_lock);
+		}
+	}
+
+	spin_lock(&sci->sc_state_lock);
+	flag = ((sci->sc_state & NILFS_SEGCTOR_COMMIT) || sci->sc_flush_request
+		|| sci->sc_seq_request != sci->sc_seq_done);
+	spin_unlock(&sci->sc_state_lock);
+
+	/*
+	 * Forcibly wake up tasks waiting in nilfs_segctor_sync(), which can
+	 * be called from delayed iput() via nilfs_evict_inode() and can race
+	 * with the above log writer thread termination.
+	 */
+	nilfs_segctor_wakeup(sci, 0, true);
+
+	if (flush_work(&sci->sc_iput_work))
+		flag = true;
+
+	if (flag || !nilfs_segctor_confirm(sci))
+		nilfs_segctor_write_out(sci);
+
+	if (!list_empty(&sci->sc_dirty_files)) {
+		nilfs_warn(sci->sc_super,
+			   "disposed unprocessed dirty file(s) when stopping log writer");
+		nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1);
+	}
+
+	if (!list_empty(&sci->sc_iput_queue)) {
+		nilfs_warn(sci->sc_super,
+			   "disposed unprocessed inode(s) in iput queue when stopping log writer");
+		nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1);
+	}
+
+	WARN_ON(!list_empty(&sci->sc_segbufs));
+	WARN_ON(!list_empty(&sci->sc_write_logs));
+
+	nilfs_put_root(sci->sc_root);
+
+	down_write(&nilfs->ns_segctor_sem);
+
+	kfree(sci);
+}
+
+/**
+ * nilfs_attach_log_writer - attach log writer
+ * @sb: super block instance
+ * @root: root object of the current filesystem tree
+ *
+ * This allocates a log writer object, initializes it, and starts the
+ * log writer.
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EINTR	- Log writer thread creation failed due to interruption.
+ * * %-ENOMEM	- Insufficient memory available.
+ */
+int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root)
+{
+	struct the_nilfs *nilfs = sb->s_fs_info;
+	struct nilfs_sc_info *sci;
+	struct task_struct *t;
+	int err;
+
+	if (nilfs->ns_writer) {
+		/*
+		 * This happens if the filesystem is made read-only by
+		 * __nilfs_error or nilfs_remount and then remounted
+		 * read/write.  In these cases, reuse the existing
+		 * writer.
+		 */
+		return 0;
+	}
+
+	sci = nilfs_segctor_new(sb, root);
+	if (unlikely(!sci))
+		return -ENOMEM;
+
+	nilfs->ns_writer = sci;
+	t = kthread_create(nilfs_segctor_thread, sci, "segctord");
+	if (IS_ERR(t)) {
+		err = PTR_ERR(t);
+		nilfs_err(sb, "error %d creating segctord thread", err);
+		nilfs_detach_log_writer(sb);
+		return err;
+	}
+	sci->sc_task = t;
+	timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0);
+
+	wake_up_process(sci->sc_task);
+	return 0;
+}
+
+/**
+ * nilfs_detach_log_writer - destroy log writer
+ * @sb: super block instance
+ *
+ * This kills log writer daemon, frees the log writer object, and
+ * destroys list of dirty files.
+ */
+void nilfs_detach_log_writer(struct super_block *sb)
+{
+	struct the_nilfs *nilfs = sb->s_fs_info;
+	LIST_HEAD(garbage_list);
+
+	down_write(&nilfs->ns_segctor_sem);
+	if (nilfs->ns_writer) {
+		nilfs_segctor_destroy(nilfs->ns_writer);
+		nilfs->ns_writer = NULL;
+	}
+	set_nilfs_purging(nilfs);
+
+	/* Force to free the list of dirty files */
+	spin_lock(&nilfs->ns_inode_lock);
+	if (!list_empty(&nilfs->ns_dirty_files)) {
+		list_splice_init(&nilfs->ns_dirty_files, &garbage_list);
+		nilfs_warn(sb,
+			   "disposed unprocessed dirty file(s) when detaching log writer");
+	}
+	spin_unlock(&nilfs->ns_inode_lock);
+	up_write(&nilfs->ns_segctor_sem);
+
+	nilfs_dispose_list(nilfs, &garbage_list, 1);
+	clear_nilfs_purging(nilfs);
+}