#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>
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 */
{
struct the_nilfs *nilfs;
int ret = nilfs_prepare_segment_lock(ti);
+ struct nilfs_transaction_info *trace_ti;
if (unlikely(ret < 0))
return ret;
- if (ret > 0)
+ 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);
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->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) {
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)
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);
ti->ti_count = 0;
ti->ti_save = cur_ti;
ti->ti_magic = NILFS_TI_MAGIC;
- INIT_LIST_HEAD(&ti->ti_garbage);
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;
}
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)
up_write(&nilfs->ns_segctor_sem);
current->journal_info = ti->ti_save;
- if (!list_empty(&ti->ti_garbage))
- nilfs_dispose_list(nilfs, &ti->ti_garbage, 0);
+
+ 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,
bh = head = page_buffers(page);
do {
- if (!buffer_dirty(bh))
+ if (!buffer_dirty(bh) || buffer_async_write(bh))
continue;
get_bh(bh);
list_add_tail(&bh->b_assoc_buffers, listp);
for (i = 0; i < pagevec_count(&pvec); i++) {
bh = head = page_buffers(pvec.pages[i]);
do {
- if (buffer_dirty(bh)) {
+ if (buffer_dirty(bh) &&
+ !buffer_async_write(bh)) {
get_bh(bh);
list_add_tail(&bh->b_assoc_buffers,
listp);
}
}
+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)
{
raw_cp->cp_snapshot_list.ssl_next = 0;
raw_cp->cp_snapshot_list.ssl_prev = 0;
raw_cp->cp_inodes_count =
- cpu_to_le64(atomic_read(&sci->sc_root->inodes_count));
+ cpu_to_le64(atomic64_read(&sci->sc_root->inodes_count));
raw_cp->cp_blocks_count =
- cpu_to_le64(atomic_read(&sci->sc_root->blocks_count));
+ cpu_to_le64(atomic64_read(&sci->sc_root->blocks_count));
raw_cp->cp_nblk_inc =
cpu_to_le64(sci->sc_nblk_inc + sci->sc_nblk_this_inc);
raw_cp->cp_create = cpu_to_le64(sci->sc_seg_ctime);
if (!test_and_clear_bit(NILFS_I_COLLECTED, &ii->i_state))
continue;
- clear_bit(NILFS_I_INODE_DIRTY, &ii->i_state);
+ clear_bit(NILFS_I_INODE_SYNC, &ii->i_state);
set_bit(NILFS_I_UPDATED, &ii->i_state);
}
}
size_t ndone;
int err = 0;
- switch (sci->sc_stage.scnt) {
+ switch (nilfs_sc_cstage_get(sci)) {
case NILFS_ST_INIT:
/* Pre-processes */
sci->sc_stage.flags = 0;
sci->sc_nblk_inc = 0;
sci->sc_curseg->sb_sum.flags = NILFS_SS_LOGBGN;
if (mode == SC_LSEG_DSYNC) {
- sci->sc_stage.scnt = NILFS_ST_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) {
- sci->sc_stage.scnt = NILFS_ST_DAT;
+ nilfs_sc_cstage_set(sci, NILFS_ST_DAT);
goto dat_stage;
}
- sci->sc_stage.scnt++; /* Fall through */
+ nilfs_sc_cstage_inc(sci); /* Fall through */
case NILFS_ST_GC:
if (nilfs_doing_gc()) {
head = &sci->sc_gc_inodes;
}
sci->sc_stage.gc_inode_ptr = NULL;
}
- sci->sc_stage.scnt++; /* Fall through */
+ nilfs_sc_cstage_inc(sci); /* Fall through */
case NILFS_ST_FILE:
head = &sci->sc_dirty_files;
ii = list_prepare_entry(sci->sc_stage.dirty_file_ptr, head,
}
sci->sc_stage.dirty_file_ptr = NULL;
if (mode == SC_FLUSH_FILE) {
- sci->sc_stage.scnt = NILFS_ST_DONE;
+ nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
return 0;
}
- sci->sc_stage.scnt++;
+ nilfs_sc_cstage_inc(sci);
sci->sc_stage.flags |= NILFS_CF_IFILE_STARTED;
/* Fall through */
case NILFS_ST_IFILE:
&nilfs_sc_file_ops);
if (unlikely(err))
break;
- sci->sc_stage.scnt++;
+ nilfs_sc_cstage_inc(sci);
/* Creating a checkpoint */
err = nilfs_segctor_create_checkpoint(sci);
if (unlikely(err))
&nilfs_sc_file_ops);
if (unlikely(err))
break;
- sci->sc_stage.scnt++; /* Fall through */
+ nilfs_sc_cstage_inc(sci); /* Fall through */
case NILFS_ST_SUFILE:
err = nilfs_sufile_freev(nilfs->ns_sufile, sci->sc_freesegs,
sci->sc_nfreesegs, &ndone);
&nilfs_sc_file_ops);
if (unlikely(err))
break;
- sci->sc_stage.scnt++; /* Fall through */
+ nilfs_sc_cstage_inc(sci); /* Fall through */
case NILFS_ST_DAT:
dat_stage:
err = nilfs_segctor_scan_file(sci, nilfs->ns_dat,
if (unlikely(err))
break;
if (mode == SC_FLUSH_DAT) {
- sci->sc_stage.scnt = NILFS_ST_DONE;
+ nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
return 0;
}
- sci->sc_stage.scnt++; /* Fall through */
+ nilfs_sc_cstage_inc(sci); /* Fall through */
case NILFS_ST_SR:
if (mode == SC_LSEG_SR) {
/* Appending a super root */
}
/* End of a logical segment */
sci->sc_curseg->sb_sum.flags |= NILFS_SS_LOGEND;
- sci->sc_stage.scnt = NILFS_ST_DONE;
+ nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
return 0;
case NILFS_ST_DSYNC:
dsync_mode:
if (unlikely(err))
break;
sci->sc_curseg->sb_sum.flags |= NILFS_SS_LOGEND;
- sci->sc_stage.scnt = NILFS_ST_DONE;
+ nilfs_sc_cstage_set(sci, NILFS_ST_DONE);
return 0;
case NILFS_ST_DONE:
return 0;
goto failed;
/* The current segment is filled up */
- if (mode != SC_LSEG_SR || sci->sc_stage.scnt < NILFS_ST_CPFILE)
+ if (mode != SC_LSEG_SR ||
+ nilfs_sc_cstage_get(sci) < NILFS_ST_CPFILE)
break;
nilfs_clear_logs(&sci->sc_segbufs);
- err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
- if (unlikely(err))
- return err;
-
if (sci->sc_stage.flags & NILFS_CF_SUFREED) {
err = nilfs_sufile_cancel_freev(nilfs->ns_sufile,
sci->sc_freesegs,
sci->sc_nfreesegs,
NULL);
WARN_ON(err); /* do not happen */
+ 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;
}
list_for_each_entry(bh, &segbuf->sb_payload_buffers,
b_assoc_buffers) {
+ set_buffer_async_write(bh);
if (bh == segbuf->sb_super_root) {
if (bh->b_page != bd_page) {
lock_page(bd_page);
list_for_each_entry(bh, &segbuf->sb_payload_buffers,
b_assoc_buffers) {
+ clear_buffer_async_write(bh);
if (bh == segbuf->sb_super_root) {
if (bh->b_page != bd_page) {
end_page_writeback(bd_page);
*/
list_for_each_entry(bh, &segbuf->sb_payload_buffers,
b_assoc_buffers) {
- set_buffer_uptodate(bh);
- clear_buffer_dirty(bh);
- clear_buffer_delay(bh);
- clear_buffer_nilfs_volatile(bh);
- clear_buffer_nilfs_redirected(bh);
+ const unsigned long set_bits = (1 << BH_Uptodate);
+ const unsigned long clear_bits =
+ (1 << BH_Dirty | 1 << BH_Async_Write |
+ 1 << BH_Delay | 1 << BH_NILFS_Volatile |
+ 1 << BH_NILFS_Redirected);
+
+ set_mask_bits(&bh->b_state, clear_bits, set_bits);
if (bh == segbuf->sb_super_root) {
if (bh->b_page != bd_page) {
end_page_writeback(bd_page);
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++);
static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
struct the_nilfs *nilfs)
{
- struct nilfs_transaction_info *ti = current->journal_info;
struct nilfs_inode_info *ii, *n;
+ int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE);
+ int defer_iput = false;
spin_lock(&nilfs->ns_inode_lock);
list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) {
clear_bit(NILFS_I_BUSY, &ii->i_state);
brelse(ii->i_bh);
ii->i_bh = NULL;
- list_move_tail(&ii->i_dirty, &ti->ti_garbage);
+ 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);
}
/*
struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
int err;
- sci->sc_stage.scnt = NILFS_ST_INIT;
+ nilfs_sc_cstage_set(sci, NILFS_ST_INIT);
sci->sc_cno = nilfs->ns_cno;
err = nilfs_segctor_collect_dirty_files(sci, nilfs);
goto failed;
/* Avoid empty segment */
- if (sci->sc_stage.scnt == NILFS_ST_DONE &&
+ if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE &&
nilfs_segbuf_empty(sci->sc_curseg)) {
nilfs_segctor_abort_construction(sci, nilfs, 1);
goto out;
nilfs_segctor_fill_in_file_bmap(sci);
if (mode == SC_LSEG_SR &&
- sci->sc_stage.scnt >= NILFS_ST_CPFILE) {
+ nilfs_sc_cstage_get(sci) >= NILFS_ST_CPFILE) {
err = nilfs_segctor_fill_in_checkpoint(sci);
if (unlikely(err))
goto failed_to_write;
if (unlikely(err))
goto failed_to_write;
- if (sci->sc_stage.scnt == NILFS_ST_DONE ||
+ if (nilfs_sc_cstage_get(sci) == NILFS_ST_DONE ||
nilfs->ns_blocksize_bits != PAGE_CACHE_SHIFT) {
/*
* At this point, we avoid double buffering
if (err)
goto failed_to_write;
}
- } while (sci->sc_stage.scnt != NILFS_ST_DONE);
+ } while (nilfs_sc_cstage_get(sci) != NILFS_ST_DONE);
out:
nilfs_segctor_drop_written_files(sci, nilfs);
nilfs_transaction_lock(sb, &ti, 0);
ii = NILFS_I(inode);
- if (test_bit(NILFS_I_INODE_DIRTY, &ii->i_state) ||
+ 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)) {
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;
static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *sci)
{
int mode = 0;
- int err;
spin_lock(&sci->sc_state_lock);
mode = (sci->sc_flush_request & FLUSH_DAT_BIT) ?
spin_unlock(&sci->sc_state_lock);
if (mode) {
- err = nilfs_segctor_do_construct(sci, mode);
+ nilfs_segctor_do_construct(sci, mode);
spin_lock(&sci->sc_state_lock);
sci->sc_flush_request &= (mode == SC_FLUSH_FILE) ?
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);
init_timer(&sci->sc_timer);
sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT;
ret = nilfs_segctor_construct(sci, SC_LSEG_SR);
nilfs_transaction_unlock(sci->sc_super);
+ flush_work(&sci->sc_iput_work);
+
} while (ret && retrycount-- > 0);
}
|| sci->sc_seq_request != sci->sc_seq_done);
spin_unlock(&sci->sc_state_lock);
+ if (flush_work(&sci->sc_iput_work))
+ flag = true;
+
if (flag || !nilfs_segctor_confirm(sci))
nilfs_segctor_write_out(sci);
nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1);
}
+ if (!list_empty(&sci->sc_iput_queue)) {
+ nilfs_warning(sci->sc_super, __func__,
+ "iput queue is not empty\n");
+ nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1);
+ }
+
WARN_ON(!list_empty(&sci->sc_segbufs));
WARN_ON(!list_empty(&sci->sc_write_logs));
projects / firefly-linux-kernel-4.4.55.git / blobdiff