Merge tag 'f2fs-for-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this cycle, we've addressed some performance issues such as lock
  contention, misbehaving compress_cache, allowing extent_cache for
  compressed files, and new sysfs to adjust ra_size for fadvise.

  In order to diagnose the performance issues quickly, we also added an
  iostat which shows the IO latencies periodically.

  On the stability side, we've found two memory leakage cases in the
  error path in compression flow. And, we've also fixed various corner
  cases in fiemap, quota, checkpoint=disable, zstd, and so on.

  Enhancements:
   - avoid long checkpoint latency by releasing nat_tree_lock
   - collect and show iostats periodically
   - support extent_cache for compressed files
   - add a sysfs entry to manage ra_size given fadvise(POSIX_FADV_SEQUENTIAL)
   - report f2fs GC status via sysfs
   - add discard_unit=%s in mount option to handle zoned device

  Bug fixes:
   - fix two memory leakages when an error happens in the compressed IO flow
   - fix commpress_cache to get the right LBA
   - fix fiemap to deal with compressed case correctly
   - fix wrong EIO returns due to SBI_NEED_FSCK
   - fix missing writes when enabling checkpoint back
   - fix quota deadlock
   - fix zstd level mount option

  In addition to the above major updates, we've cleaned up several code
  paths such as dio, unnecessary operations, debugfs/f2fs/status, sanity
  check, and typos"

* tag 'f2fs-for-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (46 commits)
  f2fs: should put a page beyond EOF when preparing a write
  f2fs: deallocate compressed pages when error happens
  f2fs: enable realtime discard iff device supports discard
  f2fs: guarantee to write dirty data when enabling checkpoint back
  f2fs: fix to unmap pages from userspace process in punch_hole()
  f2fs: fix unexpected ENOENT comes from f2fs_map_blocks()
  f2fs: fix to account missing .skipped_gc_rwsem
  f2fs: adjust unlock order for cleanup
  f2fs: Don't create discard thread when device doesn't support realtime discard
  f2fs: rebuild nat_bits during umount
  f2fs: introduce periodic iostat io latency traces
  f2fs: separate out iostat feature
  f2fs: compress: do sanity check on cluster
  f2fs: fix description about main_blkaddr node
  f2fs: convert S_IRUGO to 0444
  f2fs: fix to keep compatibility of fault injection interface
  f2fs: support fault injection for f2fs_kmem_cache_alloc()
  f2fs: compress: allow write compress released file after truncate to zero
  f2fs: correct comment in segment.h
  f2fs: improve sbi status info in debugfs/f2fs/status
  ...

1 files changed, 56 insertions, 100 deletions

diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index daad532a4e2b..a32fe31c33b8 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -17,6 +17,7 @@
 #include "f2fs.h"
 #include "segment.h"
 #include "gc.h"
+#include "iostat.h"
 #include <trace/events/f2fs.h>
 
 static struct proc_dir_entry *f2fs_proc_root;
@@ -307,6 +308,14 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 		return sysfs_emit(buf, "%u\n", sbi->compr_new_inode);
 #endif
 
+	if (!strcmp(a->attr.name, "gc_segment_mode"))
+		return sysfs_emit(buf, "%u\n", sbi->gc_segment_mode);
+
+	if (!strcmp(a->attr.name, "gc_reclaimed_segments")) {
+		return sysfs_emit(buf, "%u\n",
+			sbi->gc_reclaimed_segs[sbi->gc_segment_mode]);
+	}
+
 	ui = (unsigned int *)(ptr + a->offset);
 
 	return sprintf(buf, "%u\n", *ui);
@@ -343,7 +352,7 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
 			set = false;
 		}
 
-		if (strlen(name) >= F2FS_EXTENSION_LEN)
+		if (!strlen(name) || strlen(name) >= F2FS_EXTENSION_LEN)
 			return -EINVAL;
 
 		down_write(&sbi->sb_lock);
@@ -420,6 +429,8 @@ out:
 	if (!strcmp(a->attr.name, "discard_granularity")) {
 		if (t == 0 || t > MAX_PLIST_NUM)
 			return -EINVAL;
+		if (!f2fs_block_unit_discard(sbi))
+			return -EINVAL;
 		if (t == *ui)
 			return count;
 		*ui = t;
@@ -467,6 +478,7 @@ out:
 		return count;
 	}
 
+#ifdef CONFIG_F2FS_IOSTAT
 	if (!strcmp(a->attr.name, "iostat_enable")) {
 		sbi->iostat_enable = !!t;
 		if (!sbi->iostat_enable)
@@ -482,6 +494,7 @@ out:
 		spin_unlock(&sbi->iostat_lock);
 		return count;
 	}
+#endif
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	if (!strcmp(a->attr.name, "compr_written_block") ||
@@ -515,6 +528,29 @@ out:
 		return count;
 	}
 
+	if (!strcmp(a->attr.name, "gc_segment_mode")) {
+		if (t < MAX_GC_MODE)
+			sbi->gc_segment_mode = t;
+		else
+			return -EINVAL;
+		return count;
+	}
+
+	if (!strcmp(a->attr.name, "gc_reclaimed_segments")) {
+		if (t != 0)
+			return -EINVAL;
+		sbi->gc_reclaimed_segs[sbi->gc_segment_mode] = 0;
+		return count;
+	}
+
+	if (!strcmp(a->attr.name, "seq_file_ra_mul")) {
+		if (t >= MIN_RA_MUL && t <= MAX_RA_MUL)
+			sbi->seq_file_ra_mul = t;
+		else
+			return -EINVAL;
+		return count;
+	}
+
 	*ui = (unsigned int)t;
 
 	return count;
@@ -667,8 +703,10 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, discard_idle_interval,
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle_interval, interval_time[GC_TIME]);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info,
 		umount_discard_timeout, interval_time[UMOUNT_DISCARD_TIMEOUT]);
+#ifdef CONFIG_F2FS_IOSTAT
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_period_ms, iostat_period_ms);
+#endif
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_io_bytes, max_io_bytes);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold);
@@ -740,6 +778,10 @@ F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_candidate_count, max_candidate_cou
 F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_age_weight, age_weight);
 F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_age_threshold, age_threshold);
 
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, seq_file_ra_mul, seq_file_ra_mul);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_segment_mode, gc_segment_mode);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_reclaimed_segments, gc_reclaimed_segs);
+
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
 static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(gc_urgent_sleep_time),
@@ -770,8 +812,10 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(discard_idle_interval),
 	ATTR_LIST(gc_idle_interval),
 	ATTR_LIST(umount_discard_timeout),
+#ifdef CONFIG_F2FS_IOSTAT
 	ATTR_LIST(iostat_enable),
 	ATTR_LIST(iostat_period_ms),
+#endif
 	ATTR_LIST(readdir_ra),
 	ATTR_LIST(max_io_bytes),
 	ATTR_LIST(gc_pin_file_thresh),
@@ -812,6 +856,9 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(atgc_candidate_count),
 	ATTR_LIST(atgc_age_weight),
 	ATTR_LIST(atgc_age_threshold),
+	ATTR_LIST(seq_file_ra_mul),
+	ATTR_LIST(gc_segment_mode),
+	ATTR_LIST(gc_reclaimed_segments),
 	NULL,
 };
 ATTRIBUTE_GROUPS(f2fs);
@@ -1036,101 +1083,6 @@ static int __maybe_unused segment_bits_seq_show(struct seq_file *seq,
 	return 0;
 }
 
-void f2fs_record_iostat(struct f2fs_sb_info *sbi)
-{
-	unsigned long long iostat_diff[NR_IO_TYPE];
-	int i;
-
-	if (time_is_after_jiffies(sbi->iostat_next_period))
-		return;
-
-	/* Need double check under the lock */
-	spin_lock(&sbi->iostat_lock);
-	if (time_is_after_jiffies(sbi->iostat_next_period)) {
-		spin_unlock(&sbi->iostat_lock);
-		return;
-	}
-	sbi->iostat_next_period = jiffies +
-				msecs_to_jiffies(sbi->iostat_period_ms);
-
-	for (i = 0; i < NR_IO_TYPE; i++) {
-		iostat_diff[i] = sbi->rw_iostat[i] -
-				sbi->prev_rw_iostat[i];
-		sbi->prev_rw_iostat[i] = sbi->rw_iostat[i];
-	}
-	spin_unlock(&sbi->iostat_lock);
-
-	trace_f2fs_iostat(sbi, iostat_diff);
-}
-
-static int __maybe_unused iostat_info_seq_show(struct seq_file *seq,
-					       void *offset)
-{
-	struct super_block *sb = seq->private;
-	struct f2fs_sb_info *sbi = F2FS_SB(sb);
-	time64_t now = ktime_get_real_seconds();
-
-	if (!sbi->iostat_enable)
-		return 0;
-
-	seq_printf(seq, "time:		%-16llu\n", now);
-
-	/* print app write IOs */
-	seq_puts(seq, "[WRITE]\n");
-	seq_printf(seq, "app buffered:	%-16llu\n",
-				sbi->rw_iostat[APP_BUFFERED_IO]);
-	seq_printf(seq, "app direct:	%-16llu\n",
-				sbi->rw_iostat[APP_DIRECT_IO]);
-	seq_printf(seq, "app mapped:	%-16llu\n",
-				sbi->rw_iostat[APP_MAPPED_IO]);
-
-	/* print fs write IOs */
-	seq_printf(seq, "fs data:	%-16llu\n",
-				sbi->rw_iostat[FS_DATA_IO]);
-	seq_printf(seq, "fs node:	%-16llu\n",
-				sbi->rw_iostat[FS_NODE_IO]);
-	seq_printf(seq, "fs meta:	%-16llu\n",
-				sbi->rw_iostat[FS_META_IO]);
-	seq_printf(seq, "fs gc data:	%-16llu\n",
-				sbi->rw_iostat[FS_GC_DATA_IO]);
-	seq_printf(seq, "fs gc node:	%-16llu\n",
-				sbi->rw_iostat[FS_GC_NODE_IO]);
-	seq_printf(seq, "fs cp data:	%-16llu\n",
-				sbi->rw_iostat[FS_CP_DATA_IO]);
-	seq_printf(seq, "fs cp node:	%-16llu\n",
-				sbi->rw_iostat[FS_CP_NODE_IO]);
-	seq_printf(seq, "fs cp meta:	%-16llu\n",
-				sbi->rw_iostat[FS_CP_META_IO]);
-
-	/* print app read IOs */
-	seq_puts(seq, "[READ]\n");
-	seq_printf(seq, "app buffered:	%-16llu\n",
-				sbi->rw_iostat[APP_BUFFERED_READ_IO]);
-	seq_printf(seq, "app direct:	%-16llu\n",
-				sbi->rw_iostat[APP_DIRECT_READ_IO]);
-	seq_printf(seq, "app mapped:	%-16llu\n",
-				sbi->rw_iostat[APP_MAPPED_READ_IO]);
-
-	/* print fs read IOs */
-	seq_printf(seq, "fs data:	%-16llu\n",
-				sbi->rw_iostat[FS_DATA_READ_IO]);
-	seq_printf(seq, "fs gc data:	%-16llu\n",
-				sbi->rw_iostat[FS_GDATA_READ_IO]);
-	seq_printf(seq, "fs compr_data:	%-16llu\n",
-				sbi->rw_iostat[FS_CDATA_READ_IO]);
-	seq_printf(seq, "fs node:	%-16llu\n",
-				sbi->rw_iostat[FS_NODE_READ_IO]);
-	seq_printf(seq, "fs meta:	%-16llu\n",
-				sbi->rw_iostat[FS_META_READ_IO]);
-
-	/* print other IOs */
-	seq_puts(seq, "[OTHER]\n");
-	seq_printf(seq, "fs discard:	%-16llu\n",
-				sbi->rw_iostat[FS_DISCARD]);
-
-	return 0;
-}
-
 static int __maybe_unused victim_bits_seq_show(struct seq_file *seq,
 						void *offset)
 {
@@ -1213,13 +1165,15 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi)
 		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
 
 	if (sbi->s_proc) {
-		proc_create_single_data("segment_info", S_IRUGO, sbi->s_proc,
+		proc_create_single_data("segment_info", 0444, sbi->s_proc,
 				segment_info_seq_show, sb);
-		proc_create_single_data("segment_bits", S_IRUGO, sbi->s_proc,
+		proc_create_single_data("segment_bits", 0444, sbi->s_proc,
 				segment_bits_seq_show, sb);
-		proc_create_single_data("iostat_info", S_IRUGO, sbi->s_proc,
+#ifdef CONFIG_F2FS_IOSTAT
+		proc_create_single_data("iostat_info", 0444, sbi->s_proc,
 				iostat_info_seq_show, sb);
-		proc_create_single_data("victim_bits", S_IRUGO, sbi->s_proc,
+#endif
+		proc_create_single_data("victim_bits", 0444, sbi->s_proc,
 				victim_bits_seq_show, sb);
 	}
 	return 0;
@@ -1238,7 +1192,9 @@ put_sb_kobj:
 void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi)
 {
 	if (sbi->s_proc) {
+#ifdef CONFIG_F2FS_IOSTAT
 		remove_proc_entry("iostat_info", sbi->s_proc);
+#endif
 		remove_proc_entry("segment_info", sbi->s_proc);
 		remove_proc_entry("segment_bits", sbi->s_proc);
 		remove_proc_entry("victim_bits", sbi->s_proc);