Merge branch 'dev' of https://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git

fs/f2fs/data.c

@@ -1288,10 +1288,11 @@ retry:
 
 	if (folio_test_large(folio)) {
 		pgoff_t folio_index = mapping_align_index(mapping, index);
+		unsigned long nr_pages = folio_nr_pages(folio);
 
 		f2fs_folio_put(folio, true);
 		invalidate_inode_pages2_range(mapping, folio_index,
-				folio_index + folio_nr_pages(folio) - 1);
+				folio_index + nr_pages - 1);
 		f2fs_schedule_timeout(DEFAULT_SCHEDULE_TIMEOUT);
 		goto retry;
 	}
@@ -3900,7 +3901,7 @@ repeat:
 	 * Will wait that below with our IO control.
 	 */
 	folio = f2fs_filemap_get_folio(mapping, index,
-				FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_NOFS,
+				FGP_LOCK | FGP_WRITE | FGP_CREAT,
 				mapping_gfp_mask(mapping));
 	if (IS_ERR(folio)) {
 		err = PTR_ERR(folio);

fs/f2fs/debug.c

@@ -352,10 +352,6 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 get_cache:
 	si->cache_mem = 0;
 
-	/* build gc */
-	if (sbi->gc_thread)
-		si->cache_mem += sizeof(struct f2fs_gc_kthread);
-
 	/* build merge flush thread */
 	if (SM_I(sbi)->fcc_info)
 		si->cache_mem += sizeof(struct flush_cmd_control);

fs/f2fs/dir.c

@@ -320,6 +320,7 @@ start_find_bucket:
 
 		de = find_in_block(dir, dentry_folio, fname, &max_slots, use_hash);
 		if (IS_ERR(de)) {
+			f2fs_folio_put(dentry_folio, false);
 			*res_folio = ERR_CAST(de);
 			de = NULL;
 			break;

fs/f2fs/f2fs.h

@@ -1747,6 +1747,33 @@ struct decompress_io_ctx {
 #define MAX_COMPRESS_LOG_SIZE		8
 #define MAX_COMPRESS_WINDOW_SIZE(log_size)	((PAGE_SIZE) << (log_size))
 
+struct f2fs_gc_kthread {
+	struct task_struct *f2fs_gc_task;
+	wait_queue_head_t gc_wait_queue_head;
+
+	/* for gc sleep time */
+	unsigned int urgent_sleep_time;
+	unsigned int min_sleep_time;
+	unsigned int max_sleep_time;
+	unsigned int no_gc_sleep_time;
+
+	/* for changing gc mode */
+	bool gc_wake;
+
+	/* for GC_MERGE mount option */
+	wait_queue_head_t fggc_wq;		/*
+						 * caller of f2fs_balance_fs()
+						 * will wait on this wait queue.
+						 */
+
+	/* for gc control for zoned devices */
+	unsigned int no_zoned_gc_percent;
+	unsigned int boost_zoned_gc_percent;
+	unsigned int valid_thresh_ratio;
+	unsigned int boost_gc_multiple;
+	unsigned int boost_gc_greedy;
+};
+
 struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
 	struct proc_dir_entry *s_proc;		/* proc entry */
@@ -1882,7 +1909,7 @@ struct f2fs_sb_info {
 						 * semaphore for GC, avoid
 						 * race between GC and GC or CP
 						 */
-	struct f2fs_gc_kthread	*gc_thread;	/* GC thread */
+	struct f2fs_gc_kthread gc_thread;	/* GC thread */
 	struct atgc_management am;		/* atgc management */
 	unsigned int cur_victim_sec;		/* current victim section num */
 	unsigned int gc_mode;			/* current GC state */

fs/f2fs/file.c

@@ -1103,17 +1103,23 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			!IS_ALIGNED(attr->ia_size,
 			F2FS_BLK_TO_BYTES(fi->i_cluster_size)))
 			return -EINVAL;
-		/*
-		 * To prevent scattered pin block generation, we don't allow
-		 * smaller/equal size unaligned truncation for pinned file.
-		 * We only support overwrite IO to pinned file, so don't
-		 * care about larger size truncation.
-		 */
-		if (f2fs_is_pinned_file(inode) &&
-			attr->ia_size <= i_size_read(inode) &&
-			!IS_ALIGNED(attr->ia_size,
-			F2FS_BLK_TO_BYTES(CAP_BLKS_PER_SEC(sbi))))
-			return -EINVAL;
+
+		if (f2fs_is_pinned_file(inode)) {
+			/*
+			 * It may break section-aligned fallocate recovery
+			 * mechanism, so do not allow larger size truncation.
+			 */
+			if (attr->ia_size > i_size_read(inode))
+				return -EINVAL;
+			/*
+			 * To prevent scattered pin block generation, we don't
+			 * allow smaller/equal size unaligned truncation for
+			 * pinned file.
+			 */
+			else if (!IS_ALIGNED(attr->ia_size,
+				F2FS_BLK_TO_BYTES(CAP_BLKS_PER_SEC(sbi))))
+				return -EINVAL;
+		}
 	}
 
 	if (is_quota_modification(idmap, inode, attr)) {

fs/f2fs/gc.c

@@ -31,9 +31,9 @@ static unsigned int count_bits(const unsigned long *addr,
 static int gc_thread_func(void *data)
 {
 	struct f2fs_sb_info *sbi = data;
-	struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
-	wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head;
-	wait_queue_head_t *fggc_wq = &sbi->gc_thread->fggc_wq;
+	struct f2fs_gc_kthread *gc_th = &sbi->gc_thread;
+	wait_queue_head_t *wq = &sbi->gc_thread.gc_wait_queue_head;
+	wait_queue_head_t *fggc_wq = &sbi->gc_thread.fggc_wq;
 	unsigned int wait_ms;
 	struct f2fs_gc_control gc_control = {
 		.victim_segno = NULL_SEGNO,
@@ -193,13 +193,9 @@ next:
 
 int f2fs_start_gc_thread(struct f2fs_sb_info *sbi)
 {
-	struct f2fs_gc_kthread *gc_th;
+	struct f2fs_gc_kthread *gc_th = &sbi->gc_thread;
 	dev_t dev = sbi->sb->s_bdev->bd_dev;
 
-	gc_th = f2fs_kmalloc(sbi, sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
-	if (!gc_th)
-		return -ENOMEM;
-
 	gc_th->urgent_sleep_time = DEF_GC_THREAD_URGENT_SLEEP_TIME;
 	gc_th->valid_thresh_ratio = DEF_GC_THREAD_VALID_THRESH_RATIO;
 	gc_th->boost_gc_multiple = BOOST_GC_MULTIPLE;
@@ -221,16 +217,14 @@ int f2fs_start_gc_thread(struct f2fs_sb_info *sbi)
 
 	gc_th->gc_wake = false;
 
-	sbi->gc_thread = gc_th;
-	init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
-	init_waitqueue_head(&sbi->gc_thread->fggc_wq);
-	sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi,
+	init_waitqueue_head(&gc_th->gc_wait_queue_head);
+	init_waitqueue_head(&gc_th->fggc_wq);
+	gc_th->f2fs_gc_task = kthread_run(gc_thread_func, sbi,
 			"f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(gc_th->f2fs_gc_task)) {
 		int err = PTR_ERR(gc_th->f2fs_gc_task);
 
-		kfree(gc_th);
-		sbi->gc_thread = NULL;
+		gc_th->f2fs_gc_task = NULL;
 		return err;
 	}
 
@@ -241,14 +235,14 @@ int f2fs_start_gc_thread(struct f2fs_sb_info *sbi)
 
 void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi)
 {
-	struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
+	struct f2fs_gc_kthread *gc_th = &sbi->gc_thread;
 
-	if (!gc_th)
+	if (!gc_th->f2fs_gc_task)
 		return;
+
 	kthread_stop(gc_th->f2fs_gc_task);
+	gc_th->f2fs_gc_task = NULL;
 	wake_up_all(&gc_th->fggc_wq);
-	kfree(gc_th);
-	sbi->gc_thread = NULL;
 }
 
 static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type)
@@ -796,7 +790,7 @@ int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result,
 	if (one_time) {
 		p.one_time_gc = one_time;
 		if (has_enough_free_secs(sbi, 0, NR_PERSISTENT_LOG))
-			valid_thresh_ratio = sbi->gc_thread->valid_thresh_ratio;
+			valid_thresh_ratio = sbi->gc_thread.valid_thresh_ratio;
 	}
 
 retry:
@@ -1807,9 +1801,9 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 
 			if (f2fs_sb_has_blkzoned(sbi) &&
 					!has_enough_free_blocks(sbi,
-					sbi->gc_thread->boost_zoned_gc_percent))
+					sbi->gc_thread.boost_zoned_gc_percent))
 				window_granularity *=
-					sbi->gc_thread->boost_gc_multiple;
+					sbi->gc_thread.boost_gc_multiple;
 
 			end_segno = start_segno + window_granularity;
 		}

fs/f2fs/gc.h

@@ -45,32 +45,7 @@
 
 #define NR_GC_CHECKPOINT_SECS (3)	/* data/node/dentry sections */
 
-struct f2fs_gc_kthread {
-	struct task_struct *f2fs_gc_task;
-	wait_queue_head_t gc_wait_queue_head;
 
-	/* for gc sleep time */
-	unsigned int urgent_sleep_time;
-	unsigned int min_sleep_time;
-	unsigned int max_sleep_time;
-	unsigned int no_gc_sleep_time;
-
-	/* for changing gc mode */
-	bool gc_wake;
-
-	/* for GC_MERGE mount option */
-	wait_queue_head_t fggc_wq;		/*
-						 * caller of f2fs_balance_fs()
-						 * will wait on this wait queue.
-						 */
-
-	/* for gc control for zoned devices */
-	unsigned int no_zoned_gc_percent;
-	unsigned int boost_zoned_gc_percent;
-	unsigned int valid_thresh_ratio;
-	unsigned int boost_gc_multiple;
-	unsigned int boost_gc_greedy;
-};
 
 struct gc_inode_list {
 	struct list_head ilist;
@@ -197,6 +172,6 @@ static inline bool need_to_boost_gc(struct f2fs_sb_info *sbi)
 {
 	if (f2fs_sb_has_blkzoned(sbi))
 		return !has_enough_free_blocks(sbi,
-				sbi->gc_thread->boost_zoned_gc_percent);
+				sbi->gc_thread.boost_zoned_gc_percent);
 	return has_enough_invalid_blocks(sbi);
 }

fs/f2fs/segment.c

@@ -452,15 +452,14 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 	f2fs_submit_merged_write(sbi, DATA);
 	f2fs_submit_all_merged_ipu_writes(sbi);
 
-	if (test_opt(sbi, GC_MERGE) && sbi->gc_thread &&
-				sbi->gc_thread->f2fs_gc_task) {
+	if (test_opt(sbi, GC_MERGE) && sbi->gc_thread.f2fs_gc_task) {
 		DEFINE_WAIT(wait);
 
-		prepare_to_wait(&sbi->gc_thread->fggc_wq, &wait,
+		prepare_to_wait(&sbi->gc_thread.fggc_wq, &wait,
 					TASK_UNINTERRUPTIBLE);
-		wake_up(&sbi->gc_thread->gc_wait_queue_head);
+		wake_up(&sbi->gc_thread.gc_wait_queue_head);
 		io_schedule();
-		finish_wait(&sbi->gc_thread->fggc_wq, &wait);
+		finish_wait(&sbi->gc_thread.fggc_wq, &wait);
 	} else {
 		struct f2fs_gc_control gc_control = {
 			.victim_segno = NULL_SEGNO,

fs/f2fs/super.c

@@ -2943,11 +2943,11 @@ static int __f2fs_remount(struct fs_context *fc, struct super_block *sb)
 	if ((flags & SB_RDONLY) ||
 			(F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_OFF &&
 			!test_opt(sbi, GC_MERGE))) {
-		if (sbi->gc_thread) {
+		if (sbi->gc_thread.f2fs_gc_task) {
 			f2fs_stop_gc_thread(sbi);
 			need_restart_gc = true;
 		}
-	} else if (!sbi->gc_thread) {
+	} else if (!sbi->gc_thread.f2fs_gc_task) {
 		err = f2fs_start_gc_thread(sbi);
 		if (err)
 			goto restore_opts;
@@ -3168,7 +3168,7 @@ static ssize_t f2fs_quota_read(struct super_block *sb, int type, char *data,
 
 repeat:
 		folio = mapping_read_folio_gfp(mapping, off >> PAGE_SHIFT,
-				GFP_NOFS);
+				GFP_KERNEL);
 		if (IS_ERR(folio)) {
 			if (PTR_ERR(folio) == -ENOMEM) {
 				memalloc_retry_wait(GFP_NOFS);

fs/f2fs/sysfs.c

@@ -75,7 +75,7 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
 {
 	if (struct_type == GC_THREAD)
-		return (unsigned char *)sbi->gc_thread;
+		return (unsigned char *)&sbi->gc_thread;
 	else if (struct_type == SM_INFO)
 		return (unsigned char *)SM_I(sbi);
 	else if (struct_type == DCC_INFO)
@@ -664,20 +664,20 @@ out:
 			sbi->gc_mode = GC_NORMAL;
 		} else if (t == 1) {
 			sbi->gc_mode = GC_URGENT_HIGH;
-			if (sbi->gc_thread) {
-				sbi->gc_thread->gc_wake = true;
+			if (sbi->gc_thread.f2fs_gc_task) {
+				sbi->gc_thread.gc_wake = true;
 				wake_up_interruptible_all(
-					&sbi->gc_thread->gc_wait_queue_head);
+					&sbi->gc_thread.gc_wait_queue_head);
 				wake_up_discard_thread(sbi, true);
 			}
 		} else if (t == 2) {
 			sbi->gc_mode = GC_URGENT_LOW;
 		} else if (t == 3) {
 			sbi->gc_mode = GC_URGENT_MID;
-			if (sbi->gc_thread) {
-				sbi->gc_thread->gc_wake = true;
+			if (sbi->gc_thread.f2fs_gc_task) {
+				sbi->gc_thread.gc_wake = true;
 				wake_up_interruptible_all(
-					&sbi->gc_thread->gc_wait_queue_head);
+					&sbi->gc_thread.gc_wait_queue_head);
 			}
 		} else {
 			return -EINVAL;
@@ -934,14 +934,14 @@ out:
 	if (!strcmp(a->attr.name, "gc_boost_gc_multiple")) {
 		if (t < 1 || t > SEGS_PER_SEC(sbi))
 			return -EINVAL;
-		sbi->gc_thread->boost_gc_multiple = (unsigned int)t;
+		sbi->gc_thread.boost_gc_multiple = (unsigned int)t;
 		return count;
 	}
 
 	if (!strcmp(a->attr.name, "gc_boost_gc_greedy")) {
 		if (t > GC_GREEDY)
 			return -EINVAL;
-		sbi->gc_thread->boost_gc_greedy = (unsigned int)t;
+		sbi->gc_thread.boost_gc_greedy = (unsigned int)t;
 		return count;
 	}
 
@@ -989,8 +989,8 @@ out:
 		if (sbi->cprc_info.f2fs_issue_ckpt)
 			set_user_nice(sbi->cprc_info.f2fs_issue_ckpt,
 					PRIO_TO_NICE(sbi->critical_task_priority));
-		if (sbi->gc_thread && sbi->gc_thread->f2fs_gc_task)
-			set_user_nice(sbi->gc_thread->f2fs_gc_task,
+		if (sbi->gc_thread.f2fs_gc_task)
+			set_user_nice(sbi->gc_thread.f2fs_gc_task,
 					PRIO_TO_NICE(sbi->critical_task_priority));
 		return count;
 	}