[PATCH 1/3] f2fs: use kvmalloc, if kmalloc is failed

[PATCH 1/3] f2fs: use kvmalloc, if kmalloc is failed

[Jaegeuk Kim]

One report says memalloc failure during mount.

 (unwind_backtrace) from [<c010cd4c>] (show_stack+0x10/0x14)
 (show_stack) from [<c049c6b8>] (dump_stack+0x8c/0xa0)
 (dump_stack) from [<c024fcf0>] (warn_alloc+0xc4/0x160)
 (warn_alloc) from [<c0250218>] (__alloc_pages_nodemask+0x3f4/0x10d0)
 (__alloc_pages_nodemask) from [<c0270450>] (kmalloc_order_trace+0x2c/0x120)
 (kmalloc_order_trace) from [<c03fa748>] (build_node_manager+0x35c/0x688)
 (build_node_manager) from [<c03de494>] (f2fs_fill_super+0xf0c/0x16cc)
 (f2fs_fill_super) from [<c02a5864>] (mount_bdev+0x15c/0x188)
 (mount_bdev) from [<c03da624>] (f2fs_mount+0x18/0x20)
 (f2fs_mount) from [<c02a68b8>] (mount_fs+0x158/0x19c)
 (mount_fs) from [<c02c3c9c>] (vfs_kern_mount+0x78/0x134)
 (vfs_kern_mount) from [<c02c76ac>] (do_mount+0x474/0xca4)
 (do_mount) from [<c02c8264>] (SyS_mount+0x94/0xbc)
 (SyS_mount) from [<c0108180>] (ret_fast_syscall+0x0/0x48)

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/acl.c        |  6 ++--
 fs/f2fs/checkpoint.c |  2 +-
 fs/f2fs/data.c       |  2 +-
 fs/f2fs/debug.c      |  2 +-
 fs/f2fs/f2fs.h       | 10 +++++--
 fs/f2fs/gc.c         |  4 +--
 fs/f2fs/inline.c     |  4 +--
 fs/f2fs/namei.c      |  2 +-
 fs/f2fs/node.c       | 10 +++----
 fs/f2fs/segment.c    | 36 +++++++++++------------
 fs/f2fs/super.c      | 68 ++++++++++++++++++++++----------------------
 11 files changed, 76 insertions(+), 70 deletions(-)

diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 22f0d17cde43..63e599524085 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -160,7 +160,7 @@ static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi,
 	return (void *)f2fs_acl;
 
 fail:
-	kfree(f2fs_acl);
+	kvfree(f2fs_acl);
 	return ERR_PTR(-EINVAL);
 }
 
@@ -190,7 +190,7 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
 		acl = NULL;
 	else
 		acl = ERR_PTR(retval);
-	kfree(value);
+	kvfree(value);
 
 	return acl;
 }
@@ -240,7 +240,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 
 	error = f2fs_setxattr(inode, name_index, "", value, size, ipage, 0);
 
-	kfree(value);
+	kvfree(value);
 	if (!error)
 		set_cached_acl(inode, type, acl);
 
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 3a25cf22d732..5cba6a8ee55c 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -911,7 +911,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	f2fs_put_page(cp1, 1);
 	f2fs_put_page(cp2, 1);
 fail_no_cp:
-	kfree(sbi->ckpt);
+	kvfree(sbi->ckpt);
 	return -EINVAL;
 }
 
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index fd3a1e5ab6d9..59d86f692c84 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2573,7 +2573,7 @@ static void f2fs_dio_end_io(struct bio *bio)
 	bio->bi_private = dio->orig_private;
 	bio->bi_end_io = dio->orig_end_io;
 
-	kfree(dio);
+	kvfree(dio);
 
 	bio_endio(bio);
 }
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 1f1230f690ec..11d4448e8e09 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -503,7 +503,7 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
 	list_del(&si->stat_list);
 	mutex_unlock(&f2fs_stat_mutex);
 
-	kfree(si);
+	kvfree(si);
 }
 
 int __init f2fs_create_root_stats(void)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 7cec897146a3..81bd9a2bf22b 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1631,7 +1631,7 @@ static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
 	if (lock)
 		spin_lock_irqsave(&sbi->cp_lock, flags);
 	__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
-	kfree(NM_I(sbi)->nat_bits);
+	kvfree(NM_I(sbi)->nat_bits);
 	NM_I(sbi)->nat_bits = NULL;
 	if (lock)
 		spin_unlock_irqrestore(&sbi->cp_lock, flags);
@@ -2705,12 +2705,18 @@ static inline bool f2fs_may_extent_tree(struct inode *inode)
 static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
 					size_t size, gfp_t flags)
 {
+	void *ret;
+
 	if (time_to_inject(sbi, FAULT_KMALLOC)) {
 		f2fs_show_injection_info(FAULT_KMALLOC);
 		return NULL;
 	}
 
-	return kmalloc(size, flags);
+	ret = kmalloc(size, flags);
+	if (ret)
+		return ret;
+
+	return kvmalloc(size, flags);
 }
 
 static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 71462f2e47d4..20ca8141a720 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -142,7 +142,7 @@ int f2fs_start_gc_thread(struct f2fs_sb_info *sbi)
 			"f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(gc_th->f2fs_gc_task)) {
 		err = PTR_ERR(gc_th->f2fs_gc_task);
-		kfree(gc_th);
+		kvfree(gc_th);
 		sbi->gc_thread = NULL;
 	}
 out:
@@ -155,7 +155,7 @@ void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi)
 	if (!gc_th)
 		return;
 	kthread_stop(gc_th->f2fs_gc_task);
-	kfree(gc_th);
+	kvfree(gc_th);
 	sbi->gc_thread = NULL;
 }
 
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 7b0cff7e6051..0113bebe2ea8 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -501,7 +501,7 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
 
 	stat_dec_inline_dir(dir);
 	clear_inode_flag(dir, FI_INLINE_DENTRY);
-	kfree(backup_dentry);
+	kvfree(backup_dentry);
 	return 0;
 recover:
 	lock_page(ipage);
@@ -512,7 +512,7 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
 	set_page_dirty(ipage);
 	f2fs_put_page(ipage, 1);
 
-	kfree(backup_dentry);
+	kvfree(backup_dentry);
 	return err;
 }
 
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 2d5626939893..62d9829f3a6a 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -635,7 +635,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	f2fs_handle_failed_inode(inode);
 out_free_encrypted_link:
 	if (disk_link.name != (unsigned char *)symname)
-		kfree(disk_link.name);
+		kvfree(disk_link.name);
 	return err;
 }
 
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index a2273340991f..a08cb2e46547 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -3115,17 +3115,17 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi)
 
 		for (i = 0; i < nm_i->nat_blocks; i++)
 			kvfree(nm_i->free_nid_bitmap[i]);
-		kfree(nm_i->free_nid_bitmap);
+		kvfree(nm_i->free_nid_bitmap);
 	}
 	kvfree(nm_i->free_nid_count);
 
-	kfree(nm_i->nat_bitmap);
-	kfree(nm_i->nat_bits);
+	kvfree(nm_i->nat_bitmap);
+	kvfree(nm_i->nat_bits);
 #ifdef CONFIG_F2FS_CHECK_FS
-	kfree(nm_i->nat_bitmap_mir);
+	kvfree(nm_i->nat_bitmap_mir);
 #endif
 	sbi->nm_info = NULL;
-	kfree(nm_i);
+	kvfree(nm_i);
 }
 
 int __init f2fs_create_node_manager_caches(void)
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 204d31e58967..98649d304a2f 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -705,7 +705,7 @@ int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi)
 				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(fcc->f2fs_issue_flush)) {
 		err = PTR_ERR(fcc->f2fs_issue_flush);
-		kfree(fcc);
+		kvfree(fcc);
 		SM_I(sbi)->fcc_info = NULL;
 		return err;
 	}
@@ -724,7 +724,7 @@ void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
 		kthread_stop(flush_thread);
 	}
 	if (free) {
-		kfree(fcc);
+		kvfree(fcc);
 		SM_I(sbi)->fcc_info = NULL;
 	}
 }
@@ -2012,7 +2012,7 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
 				"f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(dcc->f2fs_issue_discard)) {
 		err = PTR_ERR(dcc->f2fs_issue_discard);
-		kfree(dcc);
+		kvfree(dcc);
 		SM_I(sbi)->dcc_info = NULL;
 		return err;
 	}
@@ -2029,7 +2029,7 @@ static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi)
 
 	f2fs_stop_discard_thread(sbi);
 
-	kfree(dcc);
+	kvfree(dcc);
 	SM_I(sbi)->dcc_info = NULL;
 }
 
@@ -4316,7 +4316,7 @@ static void destroy_dirty_segmap(struct f2fs_sb_info *sbi)
 
 	destroy_victim_secmap(sbi);
 	SM_I(sbi)->dirty_info = NULL;
-	kfree(dirty_i);
+	kvfree(dirty_i);
 }
 
 static void destroy_curseg(struct f2fs_sb_info *sbi)
@@ -4328,10 +4328,10 @@ static void destroy_curseg(struct f2fs_sb_info *sbi)
 		return;
 	SM_I(sbi)->curseg_array = NULL;
 	for (i = 0; i < NR_CURSEG_TYPE; i++) {
-		kfree(array[i].sum_blk);
-		kfree(array[i].journal);
+		kvfree(array[i].sum_blk);
+		kvfree(array[i].journal);
 	}
-	kfree(array);
+	kvfree(array);
 }
 
 static void destroy_free_segmap(struct f2fs_sb_info *sbi)
@@ -4342,7 +4342,7 @@ static void destroy_free_segmap(struct f2fs_sb_info *sbi)
 	SM_I(sbi)->free_info = NULL;
 	kvfree(free_i->free_segmap);
 	kvfree(free_i->free_secmap);
-	kfree(free_i);
+	kvfree(free_i);
 }
 
 static void destroy_sit_info(struct f2fs_sb_info *sbi)
@@ -4355,26 +4355,26 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
 
 	if (sit_i->sentries) {
 		for (start = 0; start < MAIN_SEGS(sbi); start++) {
-			kfree(sit_i->sentries[start].cur_valid_map);
+			kvfree(sit_i->sentries[start].cur_valid_map);
 #ifdef CONFIG_F2FS_CHECK_FS
-			kfree(sit_i->sentries[start].cur_valid_map_mir);
+			kvfree(sit_i->sentries[start].cur_valid_map_mir);
 #endif
-			kfree(sit_i->sentries[start].ckpt_valid_map);
-			kfree(sit_i->sentries[start].discard_map);
+			kvfree(sit_i->sentries[start].ckpt_valid_map);
+			kvfree(sit_i->sentries[start].discard_map);
 		}
 	}
-	kfree(sit_i->tmp_map);
+	kvfree(sit_i->tmp_map);
 
 	kvfree(sit_i->sentries);
 	kvfree(sit_i->sec_entries);
 	kvfree(sit_i->dirty_sentries_bitmap);
 
 	SM_I(sbi)->sit_info = NULL;
-	kfree(sit_i->sit_bitmap);
+	kvfree(sit_i->sit_bitmap);
 #ifdef CONFIG_F2FS_CHECK_FS
-	kfree(sit_i->sit_bitmap_mir);
+	kvfree(sit_i->sit_bitmap_mir);
 #endif
-	kfree(sit_i);
+	kvfree(sit_i);
 }
 
 void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi)
@@ -4390,7 +4390,7 @@ void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi)
 	destroy_free_segmap(sbi);
 	destroy_sit_info(sbi);
 	sbi->sm_info = NULL;
-	kfree(sm_info);
+	kvfree(sm_info);
 }
 
 int __init f2fs_create_segment_manager_caches(void)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index e184ad4e4e90..b79677639108 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -289,7 +289,7 @@ static int f2fs_set_qf_name(struct super_block *sb, int qtype,
 	set_opt(sbi, QUOTA);
 	return 0;
 errout:
-	kfree(qname);
+	kvfree(qname);
 	return ret;
 }
 
@@ -302,7 +302,7 @@ static int f2fs_clear_qf_name(struct super_block *sb, int qtype)
 			" when quota turned on");
 		return -EINVAL;
 	}
-	kfree(F2FS_OPTION(sbi).s_qf_names[qtype]);
+	kvfree(F2FS_OPTION(sbi).s_qf_names[qtype]);
 	F2FS_OPTION(sbi).s_qf_names[qtype] = NULL;
 	return 0;
 }
@@ -399,10 +399,10 @@ static int parse_options(struct super_block *sb, char *options)
 				set_opt(sbi, BG_GC);
 				set_opt(sbi, FORCE_FG_GC);
 			} else {
-				kfree(name);
+				kvfree(name);
 				return -EINVAL;
 			}
-			kfree(name);
+			kvfree(name);
 			break;
 		case Opt_disable_roll_forward:
 			set_opt(sbi, DISABLE_ROLL_FORWARD);
@@ -570,7 +570,7 @@ static int parse_options(struct super_block *sb, char *options)
 					f2fs_msg(sb, KERN_WARNING,
 						 "adaptive mode is not allowed with "
 						 "zoned block device feature");
-					kfree(name);
+					kvfree(name);
 					return -EINVAL;
 				}
 				set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
@@ -578,10 +578,10 @@ static int parse_options(struct super_block *sb, char *options)
 					!strncmp(name, "lfs", 3)) {
 				set_opt_mode(sbi, F2FS_MOUNT_LFS);
 			} else {
-				kfree(name);
+				kvfree(name);
 				return -EINVAL;
 			}
-			kfree(name);
+			kvfree(name);
 			break;
 		case Opt_io_size_bits:
 			if (args->from && match_int(args, &arg))
@@ -714,10 +714,10 @@ static int parse_options(struct super_block *sb, char *options)
 					!strncmp(name, "fs-based", 8)) {
 				F2FS_OPTION(sbi).whint_mode = WHINT_MODE_FS;
 			} else {
-				kfree(name);
+				kvfree(name);
 				return -EINVAL;
 			}
-			kfree(name);
+			kvfree(name);
 			break;
 		case Opt_alloc:
 			name = match_strdup(&args[0]);
@@ -731,10 +731,10 @@ static int parse_options(struct super_block *sb, char *options)
 					!strncmp(name, "reuse", 5)) {
 				F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_REUSE;
 			} else {
-				kfree(name);
+				kvfree(name);
 				return -EINVAL;
 			}
-			kfree(name);
+			kvfree(name);
 			break;
 		case Opt_fsync:
 			name = match_strdup(&args[0]);
@@ -751,10 +751,10 @@ static int parse_options(struct super_block *sb, char *options)
 				F2FS_OPTION(sbi).fsync_mode =
 							FSYNC_MODE_NOBARRIER;
 			} else {
-				kfree(name);
+				kvfree(name);
 				return -EINVAL;
 			}
-			kfree(name);
+			kvfree(name);
 			break;
 		case Opt_test_dummy_encryption:
 #ifdef CONFIG_F2FS_FS_ENCRYPTION
@@ -783,10 +783,10 @@ static int parse_options(struct super_block *sb, char *options)
 					!strncmp(name, "disable", 7)) {
 				set_opt(sbi, DISABLE_CHECKPOINT);
 			} else {
-				kfree(name);
+				kvfree(name);
 				return -EINVAL;
 			}
-			kfree(name);
+			kvfree(name);
 			break;
 		default:
 			f2fs_msg(sb, KERN_ERR,
@@ -1017,10 +1017,10 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
 	for (i = 0; i < sbi->s_ndevs; i++) {
 		blkdev_put(FDEV(i).bdev, FMODE_EXCL);
 #ifdef CONFIG_BLK_DEV_ZONED
-		kfree(FDEV(i).blkz_type);
+		kvfree(FDEV(i).blkz_type);
 #endif
 	}
-	kfree(sbi->devs);
+	kvfree(sbi->devs);
 }
 
 static void f2fs_put_super(struct super_block *sb)
@@ -1084,25 +1084,25 @@ static void f2fs_put_super(struct super_block *sb)
 	f2fs_destroy_node_manager(sbi);
 	f2fs_destroy_segment_manager(sbi);
 
-	kfree(sbi->ckpt);
+	kvfree(sbi->ckpt);
 
 	f2fs_unregister_sysfs(sbi);
 
 	sb->s_fs_info = NULL;
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
-	kfree(sbi->raw_super);
+	kvfree(sbi->raw_super);
 
 	destroy_device_list(sbi);
 	mempool_destroy(sbi->write_io_dummy);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < MAXQUOTAS; i++)
-		kfree(F2FS_OPTION(sbi).s_qf_names[i]);
+		kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
 #endif
 	destroy_percpu_info(sbi);
 	for (i = 0; i < NR_PAGE_TYPE; i++)
-		kfree(sbi->write_io[i]);
-	kfree(sbi);
+		kvfree(sbi->write_io[i]);
+	kvfree(sbi);
 }
 
 int f2fs_sync_fs(struct super_block *sb, int sync)
@@ -1531,7 +1531,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 				GFP_KERNEL);
 			if (!org_mount_opt.s_qf_names[i]) {
 				for (j = 0; j < i; j++)
-					kfree(org_mount_opt.s_qf_names[j]);
+					kvfree(org_mount_opt.s_qf_names[j]);
 				return -ENOMEM;
 			}
 		} else {
@@ -1651,7 +1651,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 #ifdef CONFIG_QUOTA
 	/* Release old quota file names */
 	for (i = 0; i < MAXQUOTAS; i++)
-		kfree(org_mount_opt.s_qf_names[i]);
+		kvfree(org_mount_opt.s_qf_names[i]);
 #endif
 	/* Update the POSIXACL Flag */
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
@@ -1672,7 +1672,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 #ifdef CONFIG_QUOTA
 	F2FS_OPTION(sbi).s_jquota_fmt = org_mount_opt.s_jquota_fmt;
 	for (i = 0; i < MAXQUOTAS; i++) {
-		kfree(F2FS_OPTION(sbi).s_qf_names[i]);
+		kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
 		F2FS_OPTION(sbi).s_qf_names[i] = org_mount_opt.s_qf_names[i];
 	}
 #endif
@@ -2800,7 +2800,7 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
 		}
 	}
 
-	kfree(zones);
+	kvfree(zones);
 
 	return err;
 }
@@ -2860,7 +2860,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
 
 	/* No valid superblock */
 	if (!*raw_super)
-		kfree(super);
+		kvfree(super);
 	else
 		err = 0;
 
@@ -3369,7 +3369,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		if (err)
 			goto free_meta;
 	}
-	kfree(options);
+	kvfree(options);
 
 	/* recover broken superblock */
 	if (recovery) {
@@ -3418,7 +3418,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	f2fs_destroy_segment_manager(sbi);
 free_devices:
 	destroy_device_list(sbi);
-	kfree(sbi->ckpt);
+	kvfree(sbi->ckpt);
 free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
 	iput(sbi->meta_inode);
@@ -3428,19 +3428,19 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	destroy_percpu_info(sbi);
 free_bio_info:
 	for (i = 0; i < NR_PAGE_TYPE; i++)
-		kfree(sbi->write_io[i]);
+		kvfree(sbi->write_io[i]);
 free_options:
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < MAXQUOTAS; i++)
-		kfree(F2FS_OPTION(sbi).s_qf_names[i]);
+		kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
 #endif
-	kfree(options);
+	kvfree(options);
 free_sb_buf:
-	kfree(raw_super);
+	kvfree(raw_super);
 free_sbi:
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
-	kfree(sbi);
+	kvfree(sbi);
 
 	/* give only one another chance */
 	if (retry) {
-- 
2.19.0.605.g01d371f741-goog

[PATCH 2/3] f2fs: correct wrong spelling, issing_*

[Jaegeuk Kim]

Let's use "queued" instead of "issuing".

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/debug.c   |  4 ++--
 fs/f2fs/f2fs.h    | 10 +++++-----
 fs/f2fs/segment.c | 26 +++++++++++++-------------
 3 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 11d4448e8e09..ebcc121920ba 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -64,7 +64,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 		si->nr_flushed =
 			atomic_read(&SM_I(sbi)->fcc_info->issued_flush);
 		si->nr_flushing =
-			atomic_read(&SM_I(sbi)->fcc_info->issing_flush);
+			atomic_read(&SM_I(sbi)->fcc_info->queued_flush);
 		si->flush_list_empty =
 			llist_empty(&SM_I(sbi)->fcc_info->issue_list);
 	}
@@ -72,7 +72,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 		si->nr_discarded =
 			atomic_read(&SM_I(sbi)->dcc_info->issued_discard);
 		si->nr_discarding =
-			atomic_read(&SM_I(sbi)->dcc_info->issing_discard);
+			atomic_read(&SM_I(sbi)->dcc_info->queued_discard);
 		si->nr_discard_cmd =
 			atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt);
 		si->undiscard_blks = SM_I(sbi)->dcc_info->undiscard_blks;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 81bd9a2bf22b..b634043fe14c 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -285,7 +285,7 @@ struct discard_cmd {
 	struct block_device *bdev;	/* bdev */
 	unsigned short ref;		/* reference count */
 	unsigned char state;		/* state */
-	unsigned char issuing;		/* issuing discard */
+	unsigned char queued;		/* queued discard */
 	int error;			/* bio error */
 	spinlock_t lock;		/* for state/bio_ref updating */
 	unsigned short bio_ref;		/* bio reference count */
@@ -327,7 +327,7 @@ struct discard_cmd_control {
 	unsigned int undiscard_blks;		/* # of undiscard blocks */
 	unsigned int next_pos;			/* next discard position */
 	atomic_t issued_discard;		/* # of issued discard */
-	atomic_t issing_discard;		/* # of issing discard */
+	atomic_t queued_discard;		/* # of queued discard */
 	atomic_t discard_cmd_cnt;		/* # of cached cmd count */
 	struct rb_root_cached root;		/* root of discard rb-tree */
 	bool rbtree_check;			/* config for consistence check */
@@ -892,7 +892,7 @@ struct flush_cmd_control {
 	struct task_struct *f2fs_issue_flush;	/* flush thread */
 	wait_queue_head_t flush_wait_queue;	/* waiting queue for wake-up */
 	atomic_t issued_flush;			/* # of issued flushes */
-	atomic_t issing_flush;			/* # of issing flushes */
+	atomic_t queued_flush;			/* # of queued flushes */
 	struct llist_head issue_list;		/* list for command issue */
 	struct llist_node *dispatch_list;	/* list for command dispatch */
 };
@@ -2167,8 +2167,8 @@ static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
 		get_pages(sbi, F2FS_WB_CP_DATA) ||
 		get_pages(sbi, F2FS_DIO_READ) ||
 		get_pages(sbi, F2FS_DIO_WRITE) ||
-		atomic_read(&SM_I(sbi)->dcc_info->issing_discard) ||
-		atomic_read(&SM_I(sbi)->fcc_info->issing_flush))
+		atomic_read(&SM_I(sbi)->dcc_info->queued_discard) ||
+		atomic_read(&SM_I(sbi)->fcc_info->queued_flush))
 		return false;
 	return f2fs_time_over(sbi, type);
 }
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 98649d304a2f..49ea9009ab5a 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -620,16 +620,16 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino)
 		return 0;
 
 	if (!test_opt(sbi, FLUSH_MERGE)) {
-		atomic_inc(&fcc->issing_flush);
+		atomic_inc(&fcc->queued_flush);
 		ret = submit_flush_wait(sbi, ino);
-		atomic_dec(&fcc->issing_flush);
+		atomic_dec(&fcc->queued_flush);
 		atomic_inc(&fcc->issued_flush);
 		return ret;
 	}
 
-	if (atomic_inc_return(&fcc->issing_flush) == 1 || sbi->s_ndevs > 1) {
+	if (atomic_inc_return(&fcc->queued_flush) == 1 || sbi->s_ndevs > 1) {
 		ret = submit_flush_wait(sbi, ino);
-		atomic_dec(&fcc->issing_flush);
+		atomic_dec(&fcc->queued_flush);
 
 		atomic_inc(&fcc->issued_flush);
 		return ret;
@@ -648,14 +648,14 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino)
 
 	if (fcc->f2fs_issue_flush) {
 		wait_for_completion(&cmd.wait);
-		atomic_dec(&fcc->issing_flush);
+		atomic_dec(&fcc->queued_flush);
 	} else {
 		struct llist_node *list;
 
 		list = llist_del_all(&fcc->issue_list);
 		if (!list) {
 			wait_for_completion(&cmd.wait);
-			atomic_dec(&fcc->issing_flush);
+			atomic_dec(&fcc->queued_flush);
 		} else {
 			struct flush_cmd *tmp, *next;
 
@@ -664,7 +664,7 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino)
 			llist_for_each_entry_safe(tmp, next, list, llnode) {
 				if (tmp == &cmd) {
 					cmd.ret = ret;
-					atomic_dec(&fcc->issing_flush);
+					atomic_dec(&fcc->queued_flush);
 					continue;
 				}
 				tmp->ret = ret;
@@ -693,7 +693,7 @@ int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	if (!fcc)
 		return -ENOMEM;
 	atomic_set(&fcc->issued_flush, 0);
-	atomic_set(&fcc->issing_flush, 0);
+	atomic_set(&fcc->queued_flush, 0);
 	init_waitqueue_head(&fcc->flush_wait_queue);
 	init_llist_head(&fcc->issue_list);
 	SM_I(sbi)->fcc_info = fcc;
@@ -909,7 +909,7 @@ static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi,
 	dc->len = len;
 	dc->ref = 0;
 	dc->state = D_PREP;
-	dc->issuing = 0;
+	dc->queued = 0;
 	dc->error = 0;
 	init_completion(&dc->wait);
 	list_add_tail(&dc->list, pend_list);
@@ -942,7 +942,7 @@ static void __detach_discard_cmd(struct discard_cmd_control *dcc,
 							struct discard_cmd *dc)
 {
 	if (dc->state == D_DONE)
-		atomic_sub(dc->issuing, &dcc->issing_discard);
+		atomic_sub(dc->queued, &dcc->queued_discard);
 
 	list_del(&dc->list);
 	rb_erase_cached(&dc->rb_node, &dcc->root);
@@ -1145,8 +1145,8 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 		dc->bio_ref++;
 		spin_unlock_irqrestore(&dc->lock, flags);
 
-		atomic_inc(&dcc->issing_discard);
-		dc->issuing++;
+		atomic_inc(&dcc->queued_discard);
+		dc->queued++;
 		list_move_tail(&dc->list, wait_list);
 
 		/* sanity check on discard range */
@@ -1996,7 +1996,7 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
 	INIT_LIST_HEAD(&dcc->fstrim_list);
 	mutex_init(&dcc->cmd_lock);
 	atomic_set(&dcc->issued_discard, 0);
-	atomic_set(&dcc->issing_discard, 0);
+	atomic_set(&dcc->queued_discard, 0);
 	atomic_set(&dcc->discard_cmd_cnt, 0);
 	dcc->nr_discards = 0;
 	dcc->max_discards = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg;
-- 
2.19.0.605.g01d371f741-goog

[PATCH 3/3] f2fs: flush stale issued discard candidates

[Jaegeuk Kim]

Sometimes, I could observe # of issuing_discard to be 1 which blocks background
jobs due to is_idle()=false.
The only way to get out of it was to trigger gc_urgent. This patch avoids that
by checking any candidates as done in the list.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/segment.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 49ea9009ab5a..acbbc924e518 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1651,6 +1651,10 @@ static int issue_discard_thread(void *data)
 		if (dcc->discard_wake)
 			dcc->discard_wake = 0;
 
+		/* clean up pending candidates before going to sleep */
+		if (atomic_read(&dcc->queued_discard))
+			__wait_all_discard_cmd(sbi, NULL);
+
 		if (try_to_freeze())
 			continue;
 		if (f2fs_readonly(sbi->sb))
-- 
2.19.0.605.g01d371f741-goog

Re: [f2fs-dev] [PATCH 1/3] f2fs: use kvmalloc, if kmalloc is failed

[Chao Yu]

On 2018/12/14 13:01, Jaegeuk Kim wrote:
> One report says memalloc failure during mount.
> 
>  (unwind_backtrace) from [<c010cd4c>] (show_stack+0x10/0x14)
>  (show_stack) from [<c049c6b8>] (dump_stack+0x8c/0xa0)
>  (dump_stack) from [<c024fcf0>] (warn_alloc+0xc4/0x160)
>  (warn_alloc) from [<c0250218>] (__alloc_pages_nodemask+0x3f4/0x10d0)
>  (__alloc_pages_nodemask) from [<c0270450>] (kmalloc_order_trace+0x2c/0x120)
>  (kmalloc_order_trace) from [<c03fa748>] (build_node_manager+0x35c/0x688)
>  (build_node_manager) from [<c03de494>] (f2fs_fill_super+0xf0c/0x16cc)
>  (f2fs_fill_super) from [<c02a5864>] (mount_bdev+0x15c/0x188)
>  (mount_bdev) from [<c03da624>] (f2fs_mount+0x18/0x20)
>  (f2fs_mount) from [<c02a68b8>] (mount_fs+0x158/0x19c)
>  (mount_fs) from [<c02c3c9c>] (vfs_kern_mount+0x78/0x134)
>  (vfs_kern_mount) from [<c02c76ac>] (do_mount+0x474/0xca4)
>  (do_mount) from [<c02c8264>] (SyS_mount+0x94/0xbc)
>  (SyS_mount) from [<c0108180>] (ret_fast_syscall+0x0/0x48)
> 
> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

Reviewed-by: Chao Yu <yuchao0@huawei.com>

Thanks,

Re: [f2fs-dev] [PATCH 2/3] f2fs: correct wrong spelling, issing_*

[Chao Yu]

On 2018/12/14 13:01, Jaegeuk Kim wrote:
> Let's use "queued" instead of "issuing".
> 
> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

Reviewed-by: Chao Yu <yuchao0@huawei.com>

Thanks,

Re: [f2fs-dev] [PATCH 3/3] f2fs: flush stale issued discard candidates

[Chao Yu]

On 2018/12/14 13:01, Jaegeuk Kim wrote:
> Sometimes, I could observe # of issuing_discard to be 1 which blocks background
> jobs due to is_idle()=false.
> The only way to get out of it was to trigger gc_urgent. This patch avoids that
> by checking any candidates as done in the list.

Well, as below code, once we issued discard commands, we will wait all
queued discard end their IO, so do you know what flow can cause such
condition...?

		issued = __issue_discard_cmd(sbi, &dpolicy);
		if (issued > 0) {
			__wait_all_discard_cmd(sbi, &dpolicy);

Or, I doubt that 'issued' statistical info could be wrong.

Thanks,

> 
> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
> ---
>  fs/f2fs/segment.c | 4 ++++
>  1 file changed, 4 insertions(+)
> 
> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
> index 49ea9009ab5a..acbbc924e518 100644
> --- a/fs/f2fs/segment.c
> +++ b/fs/f2fs/segment.c
> @@ -1651,6 +1651,10 @@ static int issue_discard_thread(void *data)
>  		if (dcc->discard_wake)
>  			dcc->discard_wake = 0;
>  
> +		/* clean up pending candidates before going to sleep */
> +		if (atomic_read(&dcc->queued_discard))
> +			__wait_all_discard_cmd(sbi, NULL);
> +
>  		if (try_to_freeze())
>  			continue;
>  		if (f2fs_readonly(sbi->sb))
> 

Re: [f2fs-dev] [PATCH 3/3] f2fs: flush stale issued discard candidates

[Jaegeuk Kim]

On 12/18, Chao Yu wrote:
> On 2018/12/14 13:01, Jaegeuk Kim wrote:
> > Sometimes, I could observe # of issuing_discard to be 1 which blocks background
> > jobs due to is_idle()=false.
> > The only way to get out of it was to trigger gc_urgent. This patch avoids that
> > by checking any candidates as done in the list.
> 
> Well, as below code, once we issued discard commands, we will wait all
> queued discard end their IO, so do you know what flow can cause such
> condition...?

It's very subtle, and I suspect somehow race condition not from here.

> 
> 		issued = __issue_discard_cmd(sbi, &dpolicy);
> 		if (issued > 0) {
> 			__wait_all_discard_cmd(sbi, &dpolicy);
> 
> Or, I doubt that 'issued' statistical info could be wrong.

No, it simply came back to 0 with this patch. So, something is pending
in the queue even if it is done.

Thanks,

> 
> Thanks,
> 
> > 
> > Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
> > ---
> >  fs/f2fs/segment.c | 4 ++++
> >  1 file changed, 4 insertions(+)
> > 
> > diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
> > index 49ea9009ab5a..acbbc924e518 100644
> > --- a/fs/f2fs/segment.c
> > +++ b/fs/f2fs/segment.c
> > @@ -1651,6 +1651,10 @@ static int issue_discard_thread(void *data)
> >  		if (dcc->discard_wake)
> >  			dcc->discard_wake = 0;
> >  
> > +		/* clean up pending candidates before going to sleep */
> > +		if (atomic_read(&dcc->queued_discard))
> > +			__wait_all_discard_cmd(sbi, NULL);
> > +
> >  		if (try_to_freeze())
> >  			continue;
> >  		if (f2fs_readonly(sbi->sb))
> > 

Re: [f2fs-dev] [PATCH 3/3] f2fs: flush stale issued discard candidates

[Chao Yu]

On 2018/12/19 6:43, Jaegeuk Kim wrote:
> On 12/18, Chao Yu wrote:
>> On 2018/12/14 13:01, Jaegeuk Kim wrote:
>>> Sometimes, I could observe # of issuing_discard to be 1 which blocks background
>>> jobs due to is_idle()=false.
>>> The only way to get out of it was to trigger gc_urgent. This patch avoids that
>>> by checking any candidates as done in the list.
>>
>> Well, as below code, once we issued discard commands, we will wait all
>> queued discard end their IO, so do you know what flow can cause such
>> condition...?
> 
> It's very subtle, and I suspect somehow race condition not from here.
> 
>>
>> 		issued = __issue_discard_cmd(sbi, &dpolicy);
>> 		if (issued > 0) {
>> 			__wait_all_discard_cmd(sbi, &dpolicy);
>>
>> Or, I doubt that 'issued' statistical info could be wrong.
> 
> No, it simply came back to 0 with this patch. So, something is pending
> in the queue even if it is done.

__submit_discard_cmd()
{
....
	dc->len = 0;   <---- reset discard length here

	while (total_len && *issued < dpolicy->max_requests && !err) {
		struct bio *bio = NULL;
		unsigned long flags;
		bool last = true;

		if (len > max_discard_blocks) {
			len = max_discard_blocks;  <---- will truncate len to max_discard_blocks
			last = false;
		}

		(*issued)++;
		if (*issued == dpolicy->max_requests)
			last = true;

		dc->len += len;      <----- will update len into dc->len
...
}

__wait_discard_cmd_range()
{
...
		if (dc->len < dpolicy->granularity)
			continue;
So we can only remove discard entry which size is not smaller than
dpolicy->granularity, if max_discard_blocks is smaller than granularity,
after splitting discard in __submit_discard_cmd(), we may left small-sized
entry there.

...
}

Could you check that whether the left discard was skipped being removed due
to above reason?

Thanks

> 
> Thanks,
> 
>>
>> Thanks,
>>
>>>
>>> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
>>> ---
>>>  fs/f2fs/segment.c | 4 ++++
>>>  1 file changed, 4 insertions(+)
>>>
>>> diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
>>> index 49ea9009ab5a..acbbc924e518 100644
>>> --- a/fs/f2fs/segment.c
>>> +++ b/fs/f2fs/segment.c
>>> @@ -1651,6 +1651,10 @@ static int issue_discard_thread(void *data)
>>>  		if (dcc->discard_wake)
>>>  			dcc->discard_wake = 0;
>>>  
>>> +		/* clean up pending candidates before going to sleep */
>>> +		if (atomic_read(&dcc->queued_discard))
>>> +			__wait_all_discard_cmd(sbi, NULL);
>>> +
>>>  		if (try_to_freeze())
>>>  			continue;
>>>  		if (f2fs_readonly(sbi->sb))
>>>
> 
> .
>