Resguardo inicial

linux-7.2.3/fs/f2fs/Kconfig

@@ -0,0 +1,152 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config F2FS_FS
+	tristate "F2FS filesystem support"
+	depends on BLOCK
+	select BUFFER_HEAD
+	select NLS
+	select CRC32
+	select F2FS_FS_XATTR if FS_ENCRYPTION
+	select FS_ENCRYPTION_ALGS if FS_ENCRYPTION
+	select FS_IOMAP
+	select LZ4_COMPRESS if F2FS_FS_LZ4
+	select LZ4_DECOMPRESS if F2FS_FS_LZ4
+	select LZ4HC_COMPRESS if F2FS_FS_LZ4HC
+	select LZO_COMPRESS if F2FS_FS_LZO
+	select LZO_DECOMPRESS if F2FS_FS_LZO
+	select ZSTD_COMPRESS if F2FS_FS_ZSTD
+	select ZSTD_DECOMPRESS if F2FS_FS_ZSTD
+	help
+	  F2FS is based on Log-structured File System (LFS), which supports
+	  versatile "flash-friendly" features. The design has been focused on
+	  addressing the fundamental issues in LFS, which are snowball effect
+	  of wandering tree and high cleaning overhead.
+
+	  Since flash-based storages show different characteristics according to
+	  the internal geometry or flash memory management schemes aka FTL, F2FS
+	  and tools support various parameters not only for configuring on-disk
+	  layout, but also for selecting allocation and cleaning algorithms.
+
+	  If unsure, say N.
+
+config F2FS_STAT_FS
+	bool "F2FS Status Information"
+	depends on F2FS_FS
+	default y
+	help
+	  /sys/kernel/debug/f2fs/ contains information about all the partitions
+	  mounted as f2fs. Each file shows the whole f2fs information.
+
+	  /sys/kernel/debug/f2fs/status includes:
+	    - major filesystem information managed by f2fs currently
+	    - average SIT information about whole segments
+	    - current memory footprint consumed by f2fs.
+
+config F2FS_FS_XATTR
+	bool "F2FS extended attributes"
+	depends on F2FS_FS
+	default y
+	help
+	  Extended attributes are name:value pairs associated with inodes by
+	  the kernel or by users (see the attr(5) manual page for details).
+
+	  If unsure, say N.
+
+config F2FS_FS_POSIX_ACL
+	bool "F2FS Access Control Lists"
+	depends on F2FS_FS_XATTR
+	select FS_POSIX_ACL
+	default y
+	help
+	  Posix Access Control Lists (ACLs) support permissions for users and
+	  groups beyond the owner/group/world scheme.
+
+	  If you don't know what Access Control Lists are, say N
+
+config F2FS_FS_SECURITY
+	bool "F2FS Security Labels"
+	depends on F2FS_FS_XATTR
+	help
+	  Security labels provide an access control facility to support Linux
+	  Security Models (LSMs) accepted by AppArmor, SELinux, Smack and TOMOYO
+	  Linux. This option enables an extended attribute handler for file
+	  security labels in the f2fs filesystem, so that it requires enabling
+	  the extended attribute support in advance. In particular you need this
+	  option if you use the setcap command to assign initial process capabi-
+	  lities to executables (the security.* extended attributes).
+
+	  If you are not using a security module, say N.
+
+config F2FS_CHECK_FS
+	bool "F2FS consistency checking feature"
+	depends on F2FS_FS
+	help
+	  Enables BUG_ONs which check the filesystem consistency in runtime.
+
+	  If you want to improve the performance, say N.
+
+config F2FS_FAULT_INJECTION
+	bool "F2FS fault injection facility"
+	depends on F2FS_FS
+	help
+	  Test F2FS to inject faults such as ENOMEM, ENOSPC, and so on.
+
+	  If unsure, say N.
+
+config F2FS_FS_COMPRESSION
+	bool "F2FS compression feature"
+	depends on F2FS_FS
+	help
+	  Enable filesystem-level compression on f2fs regular files,
+	  multiple back-end compression algorithms are supported.
+
+config F2FS_FS_LZO
+	bool "LZO compression support"
+	depends on F2FS_FS_COMPRESSION
+	default y
+	help
+	  Support LZO compress algorithm, if unsure, say Y.
+
+config F2FS_FS_LZORLE
+	bool "LZO-RLE compression support"
+	depends on F2FS_FS_LZO
+	default y
+	help
+	  Support LZO-RLE compress algorithm, if unsure, say Y.
+
+config F2FS_FS_LZ4
+	bool "LZ4 compression support"
+	depends on F2FS_FS_COMPRESSION
+	default y
+	help
+	  Support LZ4 compress algorithm, if unsure, say Y.
+
+config F2FS_FS_LZ4HC
+	bool "LZ4HC compression support"
+	depends on F2FS_FS_LZ4
+	default y
+	help
+	  Support LZ4HC compress algorithm, LZ4HC has compatible on-disk
+	  layout with LZ4, if unsure, say Y.
+
+config F2FS_FS_ZSTD
+	bool "ZSTD compression support"
+	depends on F2FS_FS_COMPRESSION
+	default y
+	help
+	  Support ZSTD compress algorithm, if unsure, say Y.
+
+config F2FS_IOSTAT
+	bool "F2FS IO statistics information"
+	depends on F2FS_FS
+	default y
+	help
+	  Support getting IO statistics through sysfs and printing out periodic
+	  IO statistics tracepoint events. You have to turn on "iostat_enable"
+	  sysfs node to enable this feature.
+
+config F2FS_UNFAIR_RWSEM
+	bool "F2FS unfair rw_semaphore"
+	depends on F2FS_FS && BLK_CGROUP
+	help
+	  Use unfair rw_semaphore, if system configured IO priority by block
+	  cgroup.

linux-7.2.3/fs/f2fs/Makefile

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_F2FS_FS) += f2fs.o
+
+f2fs-y		:= dir.o file.o inode.o namei.o hash.o super.o inline.o
+f2fs-y		+= checkpoint.o gc.o data.o node.o segment.o recovery.o
+f2fs-y		+= shrinker.o extent_cache.o sysfs.o
+f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
+f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
+f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
+f2fs-$(CONFIG_FS_VERITY) += verity.o
+f2fs-$(CONFIG_F2FS_FS_COMPRESSION) += compress.o
+f2fs-$(CONFIG_F2FS_IOSTAT) += iostat.o

linux-7.2.3/fs/f2fs/acl.c

@@ -0,0 +1,455 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fs/f2fs/acl.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * Portions of this code from linux/fs/ext2/acl.c
+ *
+ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
+ */
+#include <linux/fs_struct.h>
+#include <linux/f2fs_fs.h>
+#include "f2fs.h"
+#include "xattr.h"
+#include "acl.h"
+
+static inline size_t f2fs_acl_size(int count)
+{
+	if (count <= 4) {
+		return sizeof(struct f2fs_acl_header) +
+			count * sizeof(struct f2fs_acl_entry_short);
+	} else {
+		return sizeof(struct f2fs_acl_header) +
+			4 * sizeof(struct f2fs_acl_entry_short) +
+			(count - 4) * sizeof(struct f2fs_acl_entry);
+	}
+}
+
+static inline int f2fs_acl_count(size_t size)
+{
+	ssize_t s;
+
+	size -= sizeof(struct f2fs_acl_header);
+	s = size - 4 * sizeof(struct f2fs_acl_entry_short);
+	if (s < 0) {
+		if (size % sizeof(struct f2fs_acl_entry_short))
+			return -1;
+		return size / sizeof(struct f2fs_acl_entry_short);
+	} else {
+		if (s % sizeof(struct f2fs_acl_entry))
+			return -1;
+		return s / sizeof(struct f2fs_acl_entry) + 4;
+	}
+}
+
+static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
+{
+	int i, count;
+	int err = -EINVAL;
+	struct posix_acl *acl;
+	struct f2fs_acl_header *hdr = (struct f2fs_acl_header *)value;
+	struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1);
+	const char *end = value + size;
+
+	if (size < sizeof(struct f2fs_acl_header))
+		return ERR_PTR(-EINVAL);
+
+	if (hdr->a_version != cpu_to_le32(F2FS_ACL_VERSION))
+		return ERR_PTR(-EINVAL);
+
+	count = f2fs_acl_count(size);
+	if (count < 0)
+		return ERR_PTR(-EINVAL);
+	if (count == 0)
+		return NULL;
+
+	acl = posix_acl_alloc(count, GFP_NOFS);
+	if (!acl)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < count; i++) {
+
+		if (unlikely((char *)entry +
+				sizeof(struct f2fs_acl_entry_short) > end)) {
+			err = -EFSCORRUPTED;
+			goto fail;
+		}
+
+		acl->a_entries[i].e_tag  = le16_to_cpu(entry->e_tag);
+		acl->a_entries[i].e_perm = le16_to_cpu(entry->e_perm);
+
+		switch (acl->a_entries[i].e_tag) {
+		case ACL_USER_OBJ:
+		case ACL_GROUP_OBJ:
+		case ACL_MASK:
+		case ACL_OTHER:
+			entry = (struct f2fs_acl_entry *)((char *)entry +
+					sizeof(struct f2fs_acl_entry_short));
+			break;
+
+		case ACL_USER:
+			if (unlikely((char *)entry +
+					sizeof(struct f2fs_acl_entry) > end)) {
+				err = -EFSCORRUPTED;
+				goto fail;
+			}
+			acl->a_entries[i].e_uid =
+				make_kuid(&init_user_ns,
+						le32_to_cpu(entry->e_id));
+			entry = (struct f2fs_acl_entry *)((char *)entry +
+					sizeof(struct f2fs_acl_entry));
+			break;
+		case ACL_GROUP:
+			if (unlikely((char *)entry +
+					sizeof(struct f2fs_acl_entry) > end)) {
+				err = -EFSCORRUPTED;
+				goto fail;
+			}
+			acl->a_entries[i].e_gid =
+				make_kgid(&init_user_ns,
+						le32_to_cpu(entry->e_id));
+			entry = (struct f2fs_acl_entry *)((char *)entry +
+					sizeof(struct f2fs_acl_entry));
+			break;
+		default:
+			goto fail;
+		}
+	}
+	if ((char *)entry != end)
+		goto fail;
+	return acl;
+fail:
+	posix_acl_release(acl);
+	return ERR_PTR(err);
+}
+
+static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi,
+				const struct posix_acl *acl, size_t *size)
+{
+	struct f2fs_acl_header *f2fs_acl;
+	struct f2fs_acl_entry *entry;
+	int i;
+
+	f2fs_acl = f2fs_kmalloc(sbi, sizeof(struct f2fs_acl_header) +
+			acl->a_count * sizeof(struct f2fs_acl_entry),
+			GFP_NOFS);
+	if (!f2fs_acl)
+		return ERR_PTR(-ENOMEM);
+
+	f2fs_acl->a_version = cpu_to_le32(F2FS_ACL_VERSION);
+	entry = (struct f2fs_acl_entry *)(f2fs_acl + 1);
+
+	for (i = 0; i < acl->a_count; i++) {
+
+		entry->e_tag  = cpu_to_le16(acl->a_entries[i].e_tag);
+		entry->e_perm = cpu_to_le16(acl->a_entries[i].e_perm);
+
+		switch (acl->a_entries[i].e_tag) {
+		case ACL_USER:
+			entry->e_id = cpu_to_le32(
+					from_kuid(&init_user_ns,
+						acl->a_entries[i].e_uid));
+			entry = (struct f2fs_acl_entry *)((char *)entry +
+					sizeof(struct f2fs_acl_entry));
+			break;
+		case ACL_GROUP:
+			entry->e_id = cpu_to_le32(
+					from_kgid(&init_user_ns,
+						acl->a_entries[i].e_gid));
+			entry = (struct f2fs_acl_entry *)((char *)entry +
+					sizeof(struct f2fs_acl_entry));
+			break;
+		case ACL_USER_OBJ:
+		case ACL_GROUP_OBJ:
+		case ACL_MASK:
+		case ACL_OTHER:
+			entry = (struct f2fs_acl_entry *)((char *)entry +
+					sizeof(struct f2fs_acl_entry_short));
+			break;
+		default:
+			goto fail;
+		}
+	}
+	*size = f2fs_acl_size(acl->a_count);
+	return (void *)f2fs_acl;
+
+fail:
+	kfree(f2fs_acl);
+	return ERR_PTR(-EINVAL);
+}
+
+static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
+						struct folio *dfolio)
+{
+	int name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT;
+	void *value = NULL;
+	struct posix_acl *acl;
+	int retval;
+
+	if (type == ACL_TYPE_ACCESS)
+		name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
+
+	retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dfolio);
+	if (retval > 0) {
+		value = f2fs_kmalloc(F2FS_I_SB(inode), retval, GFP_F2FS_ZERO);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		retval = f2fs_getxattr(inode, name_index, "", value,
+							retval, dfolio);
+	}
+
+	if (retval > 0)
+		acl = f2fs_acl_from_disk(value, retval);
+	else if (retval == -ENODATA)
+		acl = NULL;
+	else
+		acl = ERR_PTR(retval);
+	kfree(value);
+
+	return acl;
+}
+
+struct posix_acl *f2fs_get_acl(struct inode *inode, int type, bool rcu)
+{
+	if (rcu)
+		return ERR_PTR(-ECHILD);
+
+	return __f2fs_get_acl(inode, type, NULL);
+}
+
+static int f2fs_acl_update_mode(struct mnt_idmap *idmap,
+				struct inode *inode, umode_t *mode_p,
+				struct posix_acl **acl)
+{
+	umode_t mode = inode->i_mode;
+	int error;
+
+	if (is_inode_flag_set(inode, FI_ACL_MODE))
+		mode = F2FS_I(inode)->i_acl_mode;
+
+	error = posix_acl_equiv_mode(*acl, &mode);
+	if (error < 0)
+		return error;
+	if (error == 0)
+		*acl = NULL;
+	if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode)))
+		mode &= ~S_ISGID;
+	*mode_p = mode;
+	return 0;
+}
+
+static int __f2fs_set_acl(struct mnt_idmap *idmap,
+			struct inode *inode, int type,
+			struct posix_acl *acl, struct folio *ifolio)
+{
+	int name_index;
+	void *value = NULL;
+	size_t size = 0;
+	int error;
+	umode_t mode = inode->i_mode;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
+		if (acl && !ifolio) {
+			error = f2fs_acl_update_mode(idmap, inode, &mode, &acl);
+			if (error)
+				return error;
+			set_acl_inode(inode, mode);
+		}
+		break;
+
+	case ACL_TYPE_DEFAULT:
+		name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT;
+		if (!S_ISDIR(inode->i_mode))
+			return acl ? -EACCES : 0;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (acl) {
+		value = f2fs_acl_to_disk(F2FS_I_SB(inode), acl, &size);
+		if (IS_ERR(value)) {
+			clear_inode_flag(inode, FI_ACL_MODE);
+			return PTR_ERR(value);
+		}
+	}
+
+	error = f2fs_setxattr(inode, name_index, "", value, size, ifolio, 0);
+
+	kfree(value);
+	if (!error)
+		set_cached_acl(inode, type, acl);
+
+	clear_inode_flag(inode, FI_ACL_MODE);
+	return error;
+}
+
+int f2fs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+		 struct posix_acl *acl, int type)
+{
+	struct inode *inode = d_inode(dentry);
+
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+		return -EIO;
+
+	return __f2fs_set_acl(idmap, inode, type, acl, NULL);
+}
+
+/*
+ * Most part of f2fs_acl_clone, f2fs_acl_create_masq, f2fs_acl_create
+ * are copied from posix_acl.c
+ */
+static struct posix_acl *f2fs_acl_clone(const struct posix_acl *acl,
+							gfp_t flags)
+{
+	struct posix_acl *clone = NULL;
+
+	if (acl) {
+		clone = kmemdup(acl, struct_size(acl, a_entries, acl->a_count),
+				flags);
+		if (clone)
+			refcount_set(&clone->a_refcount, 1);
+	}
+	return clone;
+}
+
+static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p)
+{
+	struct posix_acl_entry *pa, *pe;
+	struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL;
+	umode_t mode = *mode_p;
+	int not_equiv = 0;
+
+	/* assert(atomic_read(acl->a_refcount) == 1); */
+
+	FOREACH_ACL_ENTRY(pa, acl, pe) {
+		switch (pa->e_tag) {
+		case ACL_USER_OBJ:
+			pa->e_perm &= (mode >> 6) | ~S_IRWXO;
+			mode &= (pa->e_perm << 6) | ~S_IRWXU;
+			break;
+
+		case ACL_USER:
+		case ACL_GROUP:
+			not_equiv = 1;
+			break;
+
+		case ACL_GROUP_OBJ:
+			group_obj = pa;
+			break;
+
+		case ACL_OTHER:
+			pa->e_perm &= mode | ~S_IRWXO;
+			mode &= pa->e_perm | ~S_IRWXO;
+			break;
+
+		case ACL_MASK:
+			mask_obj = pa;
+			not_equiv = 1;
+			break;
+
+		default:
+			return -EIO;
+		}
+	}
+
+	if (mask_obj) {
+		mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
+		mode &= (mask_obj->e_perm << 3) | ~S_IRWXG;
+	} else {
+		if (!group_obj)
+			return -EIO;
+		group_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
+		mode &= (group_obj->e_perm << 3) | ~S_IRWXG;
+	}
+
+	*mode_p = (*mode_p & ~S_IRWXUGO) | mode;
+	return not_equiv;
+}
+
+static int f2fs_acl_create(struct inode *dir, umode_t *mode,
+		struct posix_acl **default_acl, struct posix_acl **acl,
+		struct folio *dfolio)
+{
+	struct posix_acl *p;
+	struct posix_acl *clone;
+	int ret;
+
+	*acl = NULL;
+	*default_acl = NULL;
+
+	if (S_ISLNK(*mode) || !IS_POSIXACL(dir))
+		return 0;
+
+	p = __f2fs_get_acl(dir, ACL_TYPE_DEFAULT, dfolio);
+	if (!p || p == ERR_PTR(-EOPNOTSUPP)) {
+		*mode &= ~current_umask();
+		return 0;
+	}
+	if (IS_ERR(p))
+		return PTR_ERR(p);
+
+	clone = f2fs_acl_clone(p, GFP_NOFS);
+	if (!clone) {
+		ret = -ENOMEM;
+		goto release_acl;
+	}
+
+	ret = f2fs_acl_create_masq(clone, mode);
+	if (ret < 0)
+		goto release_clone;
+
+	if (ret == 0)
+		posix_acl_release(clone);
+	else
+		*acl = clone;
+
+	if (!S_ISDIR(*mode))
+		posix_acl_release(p);
+	else
+		*default_acl = p;
+
+	return 0;
+
+release_clone:
+	posix_acl_release(clone);
+release_acl:
+	posix_acl_release(p);
+	return ret;
+}
+
+int f2fs_init_acl(struct inode *inode, struct inode *dir, struct folio *ifolio,
+							struct folio *dfolio)
+{
+	struct posix_acl *default_acl = NULL, *acl = NULL;
+	int error;
+
+	error = f2fs_acl_create(dir, &inode->i_mode, &default_acl, &acl, dfolio);
+	if (error)
+		return error;
+
+	f2fs_mark_inode_dirty_sync(inode, true);
+
+	if (default_acl) {
+		error = __f2fs_set_acl(NULL, inode, ACL_TYPE_DEFAULT,
+				default_acl, ifolio);
+		posix_acl_release(default_acl);
+	} else {
+		inode->i_default_acl = NULL;
+	}
+	if (acl) {
+		if (!error)
+			error = __f2fs_set_acl(NULL, inode, ACL_TYPE_ACCESS,
+					acl, ifolio);
+		posix_acl_release(acl);
+	} else {
+		inode->i_acl = NULL;
+	}
+
+	return error;
+}

linux-7.2.3/fs/f2fs/acl.h

@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * fs/f2fs/acl.h
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * Portions of this code from linux/fs/ext2/acl.h
+ *
+ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
+ */
+#ifndef __F2FS_ACL_H__
+#define __F2FS_ACL_H__
+
+#include <linux/posix_acl_xattr.h>
+
+#define F2FS_ACL_VERSION	0x0001
+
+struct f2fs_acl_entry {
+	__le16 e_tag;
+	__le16 e_perm;
+	__le32 e_id;
+};
+
+struct f2fs_acl_entry_short {
+	__le16 e_tag;
+	__le16 e_perm;
+};
+
+struct f2fs_acl_header {
+	__le32 a_version;
+};
+
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+
+struct posix_acl *f2fs_get_acl(struct inode *, int, bool);
+int f2fs_set_acl(struct mnt_idmap *, struct dentry *,
+			struct posix_acl *, int);
+int f2fs_init_acl(struct inode *, struct inode *, struct folio *ifolio,
+		struct folio *dfolio);
+#else
+#define f2fs_get_acl	NULL
+#define f2fs_set_acl	NULL
+
+static inline int f2fs_init_acl(struct inode *inode, struct inode *dir,
+				struct folio *ifolio, struct folio *dfolio)
+{
+	return 0;
+}
+#endif
+#endif /* __F2FS_ACL_H__ */

linux-7.2.3/fs/f2fs/debug.c

@@ -0,0 +1,864 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * f2fs debugging statistics
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ * Copyright (c) 2012 Linux Foundation
+ * Copyright (c) 2012 Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+ */
+
+#include <linux/fs.h>
+#include <linux/backing-dev.h>
+#include <linux/f2fs_fs.h>
+#include <linux/blkdev.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include "segment.h"
+#include "gc.h"
+
+static LIST_HEAD(f2fs_stat_list);
+static DEFINE_SPINLOCK(f2fs_stat_lock);
+#ifdef CONFIG_DEBUG_FS
+static struct dentry *f2fs_debugfs_root;
+#endif
+
+/*
+ * This function calculates BDF of every segments
+ */
+void f2fs_update_sit_info(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
+	unsigned long long blks_per_sec, hblks_per_sec, total_vblocks;
+	unsigned long long bimodal, dist;
+	unsigned int segno, vblocks;
+	int ndirty = 0;
+
+	bimodal = 0;
+	total_vblocks = 0;
+	blks_per_sec = CAP_BLKS_PER_SEC(sbi);
+	hblks_per_sec = blks_per_sec / 2;
+	for (segno = 0; segno < MAIN_SEGS(sbi); segno += SEGS_PER_SEC(sbi)) {
+		vblocks = get_valid_blocks(sbi, segno, true);
+		dist = abs(vblocks - hblks_per_sec);
+		bimodal += dist * dist;
+
+		if (vblocks > 0 && vblocks < blks_per_sec) {
+			total_vblocks += vblocks;
+			ndirty++;
+		}
+	}
+	dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100);
+	si->bimodal = div64_u64(bimodal, dist);
+	if (si->dirty_count)
+		si->avg_vblocks = div_u64(total_vblocks, ndirty);
+	else
+		si->avg_vblocks = 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static void update_multidevice_stats(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
+	struct f2fs_dev_stats *dev_stats = si->dev_stats;
+	int i, j;
+
+	if (!f2fs_is_multi_device(sbi))
+		return;
+
+	memset(dev_stats, 0, sizeof(struct f2fs_dev_stats) * sbi->s_ndevs);
+	for (i = 0; i < sbi->s_ndevs; i++) {
+		unsigned int start_segno, end_segno;
+		block_t start_blk, end_blk;
+
+		if (i == 0) {
+			start_blk = MAIN_BLKADDR(sbi);
+			end_blk = FDEV(i).end_blk + 1 - SEG0_BLKADDR(sbi);
+		} else {
+			start_blk = FDEV(i).start_blk;
+			end_blk = FDEV(i).end_blk + 1;
+		}
+
+		start_segno = GET_SEGNO(sbi, start_blk);
+		end_segno = GET_SEGNO(sbi, end_blk);
+
+		for (j = start_segno; j < end_segno; j++) {
+			unsigned int seg_blks, sec_blks;
+
+			seg_blks = get_seg_entry(sbi, j)->valid_blocks;
+
+			/* update segment stats */
+			if (is_curseg(sbi, j))
+				dev_stats[i].devstats[0][DEVSTAT_INUSE]++;
+			else if (seg_blks == BLKS_PER_SEG(sbi))
+				dev_stats[i].devstats[0][DEVSTAT_FULL]++;
+			else if (seg_blks != 0)
+				dev_stats[i].devstats[0][DEVSTAT_DIRTY]++;
+			else if (!test_bit(j, FREE_I(sbi)->free_segmap))
+				dev_stats[i].devstats[0][DEVSTAT_FREE]++;
+			else
+				dev_stats[i].devstats[0][DEVSTAT_PREFREE]++;
+
+			if (!__is_large_section(sbi) ||
+				(j % SEGS_PER_SEC(sbi)) != 0)
+				continue;
+
+			sec_blks = get_sec_entry(sbi, j)->valid_blocks;
+
+			/* update section stats */
+			if (is_cursec(sbi, GET_SEC_FROM_SEG(sbi, j)))
+				dev_stats[i].devstats[1][DEVSTAT_INUSE]++;
+			else if (sec_blks == BLKS_PER_SEC(sbi))
+				dev_stats[i].devstats[1][DEVSTAT_FULL]++;
+			else if (sec_blks != 0)
+				dev_stats[i].devstats[1][DEVSTAT_DIRTY]++;
+			else if (!test_bit(GET_SEC_FROM_SEG(sbi, j),
+					FREE_I(sbi)->free_secmap))
+				dev_stats[i].devstats[1][DEVSTAT_FREE]++;
+			else
+				dev_stats[i].devstats[1][DEVSTAT_PREFREE]++;
+		}
+	}
+}
+
+static void update_general_status(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
+	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	int i;
+
+	/* these will be changed if online resize is done */
+	si->main_area_segs = le32_to_cpu(raw_super->segment_count_main);
+	si->main_area_sections = le32_to_cpu(raw_super->section_count);
+	si->main_area_zones = si->main_area_sections /
+				le32_to_cpu(raw_super->secs_per_zone);
+
+	/* general extent cache stats */
+	for (i = 0; i < NR_EXTENT_CACHES; i++) {
+		struct extent_tree_info *eti = &sbi->extent_tree[i];
+
+		si->hit_cached[i] = atomic64_read(&sbi->read_hit_cached[i]);
+		si->hit_rbtree[i] = atomic64_read(&sbi->read_hit_rbtree[i]);
+		si->total_ext[i] = atomic64_read(&sbi->total_hit_ext[i]);
+		si->hit_total[i] = si->hit_cached[i] + si->hit_rbtree[i];
+		si->ext_tree[i] = atomic_read(&eti->total_ext_tree);
+		si->zombie_tree[i] = atomic_read(&eti->total_zombie_tree);
+		si->ext_node[i] = atomic_read(&eti->total_ext_node);
+	}
+	/* read extent_cache only */
+	si->hit_largest = atomic64_read(&sbi->read_hit_largest);
+	si->hit_total[EX_READ] += si->hit_largest;
+
+	/* block age extent_cache only */
+	si->allocated_data_blocks = atomic64_read(&sbi->allocated_data_blocks);
+
+	/* validation check of the segment numbers */
+	si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES);
+	si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS);
+	si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META);
+	si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA);
+	si->ndirty_qdata = get_pages(sbi, F2FS_DIRTY_QDATA);
+	si->ndirty_imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
+	si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
+	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
+	si->ndonate_files = sbi->donate_files;
+	si->nquota_files = sbi->nquota_files;
+	si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
+	si->aw_cnt = atomic_read(&sbi->atomic_files);
+	si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt);
+	si->nr_dio_read = get_pages(sbi, F2FS_DIO_READ);
+	si->nr_dio_write = get_pages(sbi, F2FS_DIO_WRITE);
+	si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA);
+	si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA);
+	si->nr_rd_data = get_pages(sbi, F2FS_RD_DATA);
+	si->nr_rd_node = get_pages(sbi, F2FS_RD_NODE);
+	si->nr_rd_meta = get_pages(sbi, F2FS_RD_META);
+	if (SM_I(sbi)->fcc_info) {
+		si->nr_flushed =
+			atomic_read(&SM_I(sbi)->fcc_info->issued_flush);
+		si->nr_flushing =
+			atomic_read(&SM_I(sbi)->fcc_info->queued_flush);
+		si->flush_list_empty =
+			llist_empty(&SM_I(sbi)->fcc_info->issue_list);
+	}
+	if (SM_I(sbi)->dcc_info) {
+		si->nr_discarded =
+			atomic_read(&SM_I(sbi)->dcc_info->issued_discard);
+		si->nr_discarding =
+			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;
+	}
+	si->nr_issued_ckpt = atomic_read(&sbi->cprc_info.issued_ckpt);
+	si->nr_total_ckpt = atomic_read(&sbi->cprc_info.total_ckpt);
+	si->nr_queued_ckpt = atomic_read(&sbi->cprc_info.queued_ckpt);
+	spin_lock(&sbi->cprc_info.stat_lock);
+	si->cur_ckpt_time = sbi->cprc_info.cur_time;
+	si->peak_ckpt_time = sbi->cprc_info.peak_time;
+	spin_unlock(&sbi->cprc_info.stat_lock);
+	si->total_count = BLKS_TO_SEGS(sbi, (int)sbi->user_block_count);
+	si->rsvd_segs = reserved_segments(sbi);
+	si->overp_segs = overprovision_segments(sbi);
+	si->valid_count = valid_user_blocks(sbi);
+	si->discard_blks = discard_blocks(sbi);
+	si->valid_node_count = valid_node_count(sbi);
+	si->valid_inode_count = valid_inode_count(sbi);
+	si->inline_xattr = atomic_read(&sbi->inline_xattr);
+	si->inline_inode = atomic_read(&sbi->inline_inode);
+	si->inline_dir = atomic_read(&sbi->inline_dir);
+	si->compr_inode = atomic_read(&sbi->compr_inode);
+	si->swapfile_inode = atomic_read(&sbi->swapfile_inode);
+	si->compr_blocks = atomic64_read(&sbi->compr_blocks);
+	si->append = sbi->im[APPEND_INO].ino_num;
+	si->update = sbi->im[UPDATE_INO].ino_num;
+	si->orphans = sbi->im[ORPHAN_INO].ino_num;
+	si->utilization = utilization(sbi);
+
+	si->free_segs = free_segments(sbi);
+	si->free_secs = free_sections(sbi);
+	si->prefree_count = prefree_segments(sbi);
+	si->dirty_count = dirty_segments(sbi);
+	if (sbi->node_inode)
+		si->node_pages = NODE_MAPPING(sbi)->nrpages;
+	if (sbi->meta_inode)
+		si->meta_pages = META_MAPPING(sbi)->nrpages;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (sbi->compress_inode) {
+		si->compress_pages = COMPRESS_MAPPING(sbi)->nrpages;
+		si->compress_page_hit = atomic_read(&sbi->compress_page_hit);
+	}
+#endif
+	si->nats = NM_I(sbi)->nat_cnt[TOTAL_NAT];
+	si->dirty_nats = NM_I(sbi)->nat_cnt[DIRTY_NAT];
+	si->sits = MAIN_SEGS(sbi);
+	si->dirty_sits = SIT_I(sbi)->dirty_sentries;
+	si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID];
+	si->avail_nids = NM_I(sbi)->available_nids;
+	si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID];
+	si->io_skip_bggc = sbi->io_skip_bggc;
+	si->other_skip_bggc = sbi->other_skip_bggc;
+	si->util_free = (int)(BLKS_TO_SEGS(sbi, free_user_blocks(sbi)))
+		* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
+		/ 2;
+	si->util_valid = (int)(BLKS_TO_SEGS(sbi, written_block_count(sbi)))
+		* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
+		/ 2;
+	si->util_invalid = 50 - si->util_free - si->util_valid;
+	for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) {
+		struct curseg_info *curseg = CURSEG_I(sbi, i);
+
+		si->blkoff[i] = curseg->next_blkoff;
+		si->curseg[i] = curseg->segno;
+		si->cursec[i] = GET_SEC_FROM_SEG(sbi, curseg->segno);
+		si->curzone[i] = GET_ZONE_FROM_SEC(sbi, si->cursec[i]);
+	}
+
+	for (i = META_CP; i < META_MAX; i++)
+		si->meta_count[i] = atomic_read(&sbi->meta_count[i]);
+
+	for (i = 0; i < NO_CHECK_TYPE; i++) {
+		si->dirty_seg[i] = 0;
+		si->full_seg[i] = 0;
+		si->valid_blks[i] = 0;
+	}
+
+	for (i = 0; i < MAIN_SEGS(sbi); i++) {
+		int blks = get_seg_entry(sbi, i)->valid_blocks;
+		int type = get_seg_entry(sbi, i)->type;
+
+		if (!blks)
+			continue;
+
+		if (blks == BLKS_PER_SEG(sbi))
+			si->full_seg[type]++;
+		else
+			si->dirty_seg[type]++;
+		si->valid_blks[type] += blks;
+	}
+
+	update_multidevice_stats(sbi);
+
+	for (i = 0; i < MAX_CALL_TYPE; i++)
+		si->cp_call_count[i] = atomic_read(&sbi->cp_call_count[i]);
+
+	for (i = 0; i < 2; i++) {
+		si->segment_count[i] = sbi->segment_count[i];
+		si->block_count[i] = sbi->block_count[i];
+	}
+
+	si->inplace_count = atomic_read(&sbi->inplace_count);
+}
+
+/*
+ * This function calculates memory footprint.
+ */
+static void update_mem_info(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
+	int i;
+
+	if (si->base_mem)
+		goto get_cache;
+
+	/* build stat */
+	si->base_mem = sizeof(struct f2fs_stat_info);
+
+	/* build superblock */
+	si->base_mem += sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize;
+	si->base_mem += 2 * sizeof(struct f2fs_inode_info);
+	si->base_mem += sizeof(*sbi->ckpt);
+
+	/* build sm */
+	si->base_mem += sizeof(struct f2fs_sm_info);
+
+	/* build sit */
+	si->base_mem += sizeof(struct sit_info);
+	si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry);
+	si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
+	si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
+	si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
+	si->base_mem += SIT_VBLOCK_MAP_SIZE;
+	if (__is_large_section(sbi))
+		si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
+	si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
+
+	/* build free segmap */
+	si->base_mem += sizeof(struct free_segmap_info);
+	si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
+	si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi));
+
+	/* build curseg */
+	si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE;
+	si->base_mem += PAGE_SIZE * NR_CURSEG_TYPE;
+
+	/* build dirty segmap */
+	si->base_mem += sizeof(struct dirty_seglist_info);
+	si->base_mem += NR_DIRTY_TYPE * f2fs_bitmap_size(MAIN_SEGS(sbi));
+	si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi));
+
+	/* build nm */
+	si->base_mem += sizeof(struct f2fs_nm_info);
+	si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
+	si->base_mem += F2FS_BLK_TO_BYTES(NM_I(sbi)->nat_bits_blocks);
+	si->base_mem += NM_I(sbi)->nat_blocks *
+				f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK);
+	si->base_mem += NM_I(sbi)->nat_blocks / 8;
+	si->base_mem += NM_I(sbi)->nat_blocks * sizeof(unsigned short);
+
+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);
+	if (SM_I(sbi)->dcc_info) {
+		si->cache_mem += sizeof(struct discard_cmd_control);
+		si->cache_mem += sizeof(struct discard_cmd) *
+			atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt);
+	}
+
+	/* free nids */
+	si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID] +
+				NM_I(sbi)->nid_cnt[PREALLOC_NID]) *
+				sizeof(struct free_nid);
+	si->cache_mem += NM_I(sbi)->nat_cnt[TOTAL_NAT] *
+				sizeof(struct nat_entry);
+	si->cache_mem += NM_I(sbi)->nat_cnt[DIRTY_NAT] *
+				sizeof(struct nat_entry_set);
+	for (i = 0; i < MAX_INO_ENTRY; i++)
+		si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
+
+	for (i = 0; i < NR_EXTENT_CACHES; i++) {
+		struct extent_tree_info *eti = &sbi->extent_tree[i];
+
+		si->ext_mem[i] = atomic_read(&eti->total_ext_tree) *
+						sizeof(struct extent_tree);
+		si->ext_mem[i] += atomic_read(&eti->total_ext_node) *
+						sizeof(struct extent_node);
+		si->cache_mem += si->ext_mem[i];
+	}
+
+	si->page_mem = 0;
+	if (sbi->node_inode) {
+		unsigned long npages = NODE_MAPPING(sbi)->nrpages;
+
+		si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
+	}
+	if (sbi->meta_inode) {
+		unsigned long npages = META_MAPPING(sbi)->nrpages;
+
+		si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
+	}
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (sbi->compress_inode) {
+		unsigned long npages = COMPRESS_MAPPING(sbi)->nrpages;
+
+		si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
+	}
+#endif
+}
+
+static const char *s_flag[MAX_SBI_FLAG] = {
+	[SBI_IS_DIRTY]		= "fs_dirty",
+	[SBI_IS_CLOSE]		= "closing",
+	[SBI_NEED_FSCK]		= "need_fsck",
+	[SBI_POR_DOING]		= "recovering",
+	[SBI_NEED_SB_WRITE]	= "sb_dirty",
+	[SBI_NEED_CP]		= "need_cp",
+	[SBI_IS_SHUTDOWN]	= "shutdown",
+	[SBI_IS_RECOVERED]	= "recovered",
+	[SBI_CP_DISABLED]	= "cp_disabled",
+	[SBI_CP_DISABLED_QUICK]	= "cp_disabled_quick",
+	[SBI_QUOTA_NEED_FLUSH]	= "quota_need_flush",
+	[SBI_QUOTA_SKIP_FLUSH]	= "quota_skip_flush",
+	[SBI_QUOTA_NEED_REPAIR]	= "quota_need_repair",
+	[SBI_IS_RESIZEFS]	= "resizefs",
+	[SBI_IS_FREEZING]	= "freezefs",
+	[SBI_IS_WRITABLE]	= "writable",
+	[SBI_ENABLE_CHECKPOINT]	= "enable_checkpoint",
+};
+
+static const char *ipu_mode_names[F2FS_IPU_MAX] = {
+	[F2FS_IPU_FORCE]	= "FORCE",
+	[F2FS_IPU_SSR]		= "SSR",
+	[F2FS_IPU_UTIL]		= "UTIL",
+	[F2FS_IPU_SSR_UTIL]	= "SSR_UTIL",
+	[F2FS_IPU_FSYNC]	= "FSYNC",
+	[F2FS_IPU_ASYNC]	= "ASYNC",
+	[F2FS_IPU_NOCACHE]	= "NOCACHE",
+	[F2FS_IPU_HONOR_OPU_WRITE]	= "HONOR_OPU_WRITE",
+};
+
+static int stat_show(struct seq_file *s, void *v)
+{
+	struct f2fs_stat_info *si;
+	int i = 0, j = 0;
+
+	spin_lock(&f2fs_stat_lock);
+	list_for_each_entry(si, &f2fs_stat_list, stat_list) {
+		struct f2fs_sb_info *sbi = si->sbi;
+
+		update_general_status(sbi);
+
+		seq_printf(s, "\n=====[ partition info(%pg). #%d, %s, CP: %s]=====\n",
+			sbi->sb->s_bdev, i++,
+			f2fs_readonly(sbi->sb) ? "RO" : "RW",
+			is_set_ckpt_flags(sbi, CP_DISABLED_FLAG) ?
+			"Disabled" : (f2fs_cp_error(sbi) ? "Error" : "Good"));
+		if (sbi->s_flag) {
+			seq_puts(s, "[SBI:");
+			for_each_set_bit(j, &sbi->s_flag, MAX_SBI_FLAG)
+				seq_printf(s, " %s", s_flag[j]);
+			seq_puts(s, "]\n");
+		}
+		seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
+			   si->sit_area_segs, si->nat_area_segs);
+		seq_printf(s, "[SSA: %d] [MAIN: %d",
+			   si->ssa_area_segs, si->main_area_segs);
+		seq_printf(s, "(OverProv:%d Resv:%d)]\n\n",
+			   si->overp_segs, si->rsvd_segs);
+		seq_printf(s, "Current Time Sec: %llu / Mounted Time Sec: %llu\n\n",
+					ktime_get_boottime_seconds(),
+					SIT_I(sbi)->mounted_time);
+
+		seq_puts(s, "Policy:\n");
+		seq_puts(s, "  - IPU: [");
+		if (IS_F2FS_IPU_DISABLE(sbi)) {
+			seq_puts(s, " DISABLE");
+		} else {
+			unsigned long policy = SM_I(sbi)->ipu_policy;
+
+			for_each_set_bit(j, &policy, F2FS_IPU_MAX)
+				seq_printf(s, " %s", ipu_mode_names[j]);
+		}
+		seq_puts(s, " ]\n\n");
+
+		if (test_opt(sbi, DISCARD))
+			seq_printf(s, "Utilization: %u%% (%u valid blocks, %u discard blocks)\n",
+				si->utilization, si->valid_count, si->discard_blks);
+		else
+			seq_printf(s, "Utilization: %u%% (%u valid blocks)\n",
+				si->utilization, si->valid_count);
+
+		seq_printf(s, "  - Node: %u (Inode: %u, ",
+			   si->valid_node_count, si->valid_inode_count);
+		seq_printf(s, "Other: %u)\n  - Data: %u\n",
+			   si->valid_node_count - si->valid_inode_count,
+			   si->valid_count - si->valid_node_count);
+		seq_printf(s, "  - Inline_xattr Inode: %u\n",
+			   si->inline_xattr);
+		seq_printf(s, "  - Inline_data Inode: %u\n",
+			   si->inline_inode);
+		seq_printf(s, "  - Inline_dentry Inode: %u\n",
+			   si->inline_dir);
+		seq_printf(s, "  - Compressed Inode: %u, Blocks: %llu\n",
+			   si->compr_inode, si->compr_blocks);
+		seq_printf(s, "  - Swapfile Inode: %u\n",
+			   si->swapfile_inode);
+		seq_printf(s, "  - Donate Inode: %u\n",
+			   si->ndonate_files);
+		seq_printf(s, "  - Orphan/Append/Update Inode: %u, %u, %u\n",
+			   si->orphans, si->append, si->update);
+		seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
+			   si->main_area_segs, si->main_area_sections,
+			   si->main_area_zones);
+		seq_printf(s, "    TYPE         %8s %8s %8s %8s %10s %10s %10s\n",
+			   "blkoff", "segno", "secno", "zoneno", "dirty_seg", "full_seg", "valid_blk");
+		seq_printf(s, "  - COLD   data: %8d %8d %8d %8d %10u %10u %10u\n",
+			   si->blkoff[CURSEG_COLD_DATA],
+			   si->curseg[CURSEG_COLD_DATA],
+			   si->cursec[CURSEG_COLD_DATA],
+			   si->curzone[CURSEG_COLD_DATA],
+			   si->dirty_seg[CURSEG_COLD_DATA],
+			   si->full_seg[CURSEG_COLD_DATA],
+			   si->valid_blks[CURSEG_COLD_DATA]);
+		seq_printf(s, "  - WARM   data: %8d %8d %8d %8d %10u %10u %10u\n",
+			   si->blkoff[CURSEG_WARM_DATA],
+			   si->curseg[CURSEG_WARM_DATA],
+			   si->cursec[CURSEG_WARM_DATA],
+			   si->curzone[CURSEG_WARM_DATA],
+			   si->dirty_seg[CURSEG_WARM_DATA],
+			   si->full_seg[CURSEG_WARM_DATA],
+			   si->valid_blks[CURSEG_WARM_DATA]);
+		seq_printf(s, "  - HOT    data: %8d %8d %8d %8d %10u %10u %10u\n",
+			   si->blkoff[CURSEG_HOT_DATA],
+			   si->curseg[CURSEG_HOT_DATA],
+			   si->cursec[CURSEG_HOT_DATA],
+			   si->curzone[CURSEG_HOT_DATA],
+			   si->dirty_seg[CURSEG_HOT_DATA],
+			   si->full_seg[CURSEG_HOT_DATA],
+			   si->valid_blks[CURSEG_HOT_DATA]);
+		seq_printf(s, "  - Dir   dnode: %8d %8d %8d %8d %10u %10u %10u\n",
+			   si->blkoff[CURSEG_HOT_NODE],
+			   si->curseg[CURSEG_HOT_NODE],
+			   si->cursec[CURSEG_HOT_NODE],
+			   si->curzone[CURSEG_HOT_NODE],
+			   si->dirty_seg[CURSEG_HOT_NODE],
+			   si->full_seg[CURSEG_HOT_NODE],
+			   si->valid_blks[CURSEG_HOT_NODE]);
+		seq_printf(s, "  - File  dnode: %8d %8d %8d %8d %10u %10u %10u\n",
+			   si->blkoff[CURSEG_WARM_NODE],
+			   si->curseg[CURSEG_WARM_NODE],
+			   si->cursec[CURSEG_WARM_NODE],
+			   si->curzone[CURSEG_WARM_NODE],
+			   si->dirty_seg[CURSEG_WARM_NODE],
+			   si->full_seg[CURSEG_WARM_NODE],
+			   si->valid_blks[CURSEG_WARM_NODE]);
+		seq_printf(s, "  - Indir nodes: %8d %8d %8d %8d %10u %10u %10u\n",
+			   si->blkoff[CURSEG_COLD_NODE],
+			   si->curseg[CURSEG_COLD_NODE],
+			   si->cursec[CURSEG_COLD_NODE],
+			   si->curzone[CURSEG_COLD_NODE],
+			   si->dirty_seg[CURSEG_COLD_NODE],
+			   si->full_seg[CURSEG_COLD_NODE],
+			   si->valid_blks[CURSEG_COLD_NODE]);
+		seq_printf(s, "  - Pinned file: %8d %8d %8d %8d\n",
+			   si->blkoff[CURSEG_COLD_DATA_PINNED],
+			   si->curseg[CURSEG_COLD_DATA_PINNED],
+			   si->cursec[CURSEG_COLD_DATA_PINNED],
+			   si->curzone[CURSEG_COLD_DATA_PINNED]);
+		seq_printf(s, "  - ATGC   data: %8d %8d %8d %8d\n",
+			   si->blkoff[CURSEG_ALL_DATA_ATGC],
+			   si->curseg[CURSEG_ALL_DATA_ATGC],
+			   si->cursec[CURSEG_ALL_DATA_ATGC],
+			   si->curzone[CURSEG_ALL_DATA_ATGC]);
+		seq_printf(s, "\n  - Valid: %d\n  - Dirty: %d\n",
+			   si->main_area_segs - si->dirty_count -
+			   si->prefree_count - si->free_segs,
+			   si->dirty_count);
+		seq_printf(s, "  - Prefree: %d\n  - Free: %d (%d)\n\n",
+			   si->prefree_count, si->free_segs, si->free_secs);
+		if (f2fs_is_multi_device(sbi)) {
+			seq_puts(s, "Multidevice stats:\n");
+			seq_printf(s, "  [seg:   %8s %8s %8s %8s %8s]",
+					"inuse", "dirty", "full", "free", "prefree");
+			if (__is_large_section(sbi))
+				seq_printf(s, " [sec:   %8s %8s %8s %8s %8s]\n",
+					"inuse", "dirty", "full", "free", "prefree");
+			else
+				seq_puts(s, "\n");
+
+			for (i = 0; i < sbi->s_ndevs; i++) {
+				seq_printf(s, "  #%-2d     %8u %8u %8u %8u %8u", i,
+					si->dev_stats[i].devstats[0][DEVSTAT_INUSE],
+					si->dev_stats[i].devstats[0][DEVSTAT_DIRTY],
+					si->dev_stats[i].devstats[0][DEVSTAT_FULL],
+					si->dev_stats[i].devstats[0][DEVSTAT_FREE],
+					si->dev_stats[i].devstats[0][DEVSTAT_PREFREE]);
+				if (!__is_large_section(sbi)) {
+					seq_puts(s, "\n");
+					continue;
+				}
+				seq_printf(s, "          %8u %8u %8u %8u %8u\n",
+					si->dev_stats[i].devstats[1][DEVSTAT_INUSE],
+					si->dev_stats[i].devstats[1][DEVSTAT_DIRTY],
+					si->dev_stats[i].devstats[1][DEVSTAT_FULL],
+					si->dev_stats[i].devstats[1][DEVSTAT_FREE],
+					si->dev_stats[i].devstats[1][DEVSTAT_PREFREE]);
+			}
+			seq_puts(s, "\n");
+		}
+		seq_printf(s, "CP calls: %d (BG: %d)\n",
+			   si->cp_call_count[TOTAL_CALL],
+			   si->cp_call_count[BACKGROUND]);
+		seq_printf(s, "CP count: %d\n", si->cp_count);
+		seq_printf(s, "  - cp blocks : %u\n", si->meta_count[META_CP]);
+		seq_printf(s, "  - sit blocks : %u\n",
+				si->meta_count[META_SIT]);
+		seq_printf(s, "  - nat blocks : %u\n",
+				si->meta_count[META_NAT]);
+		seq_printf(s, "  - ssa blocks : %u\n",
+				si->meta_count[META_SSA]);
+		seq_puts(s, "CP merge:\n");
+		seq_printf(s, "  - Queued : %4d\n", si->nr_queued_ckpt);
+		seq_printf(s, "  - Issued : %4d\n", si->nr_issued_ckpt);
+		seq_printf(s, "  - Total : %4d\n", si->nr_total_ckpt);
+		seq_printf(s, "  - Cur time : %4d(ms)\n", si->cur_ckpt_time);
+		seq_printf(s, "  - Peak time : %4d(ms)\n", si->peak_ckpt_time);
+		seq_printf(s, "GC calls: %d (gc_thread: %d)\n",
+			   si->gc_call_count[BACKGROUND] +
+			   si->gc_call_count[FOREGROUND],
+			   si->gc_call_count[BACKGROUND]);
+		if (__is_large_section(sbi)) {
+			seq_printf(s, "  - data sections : %d (BG: %d)\n",
+					si->gc_secs[DATA][BG_GC] + si->gc_secs[DATA][FG_GC],
+					si->gc_secs[DATA][BG_GC]);
+			seq_printf(s, "  - node sections : %d (BG: %d)\n",
+					si->gc_secs[NODE][BG_GC] + si->gc_secs[NODE][FG_GC],
+					si->gc_secs[NODE][BG_GC]);
+		}
+		seq_printf(s, "  - data segments : %d (BG: %d)\n",
+				si->gc_segs[DATA][BG_GC] + si->gc_segs[DATA][FG_GC],
+				si->gc_segs[DATA][BG_GC]);
+		seq_printf(s, "  - node segments : %d (BG: %d)\n",
+				si->gc_segs[NODE][BG_GC] + si->gc_segs[NODE][FG_GC],
+				si->gc_segs[NODE][BG_GC]);
+		seq_puts(s, "  - Reclaimed segs :\n");
+		seq_printf(s, "    - Normal : %d\n", sbi->gc_reclaimed_segs[GC_NORMAL]);
+		seq_printf(s, "    - Idle CB : %d\n", sbi->gc_reclaimed_segs[GC_IDLE_CB]);
+		seq_printf(s, "    - Idle Greedy : %d\n",
+				sbi->gc_reclaimed_segs[GC_IDLE_GREEDY]);
+		seq_printf(s, "    - Idle AT : %d\n", sbi->gc_reclaimed_segs[GC_IDLE_AT]);
+		seq_printf(s, "    - Urgent High : %d\n",
+				sbi->gc_reclaimed_segs[GC_URGENT_HIGH]);
+		seq_printf(s, "    - Urgent Mid : %d\n", sbi->gc_reclaimed_segs[GC_URGENT_MID]);
+		seq_printf(s, "    - Urgent Low : %d\n", sbi->gc_reclaimed_segs[GC_URGENT_LOW]);
+		seq_printf(s, "Try to move %d blocks (BG: %d)\n", si->tot_blks,
+				si->bg_data_blks + si->bg_node_blks);
+		seq_printf(s, "  - data blocks : %d (%d)\n", si->data_blks,
+				si->bg_data_blks);
+		seq_printf(s, "  - node blocks : %d (%d)\n", si->node_blks,
+				si->bg_node_blks);
+		seq_printf(s, "BG skip : IO: %u, Other: %u\n",
+				si->io_skip_bggc, si->other_skip_bggc);
+		seq_printf(s, "defrag blocks : %u\n", si->defrag_blks);
+		seq_puts(s, "\nExtent Cache (Read):\n");
+		seq_printf(s, "  - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n",
+				si->hit_largest, si->hit_cached[EX_READ],
+				si->hit_rbtree[EX_READ]);
+		seq_printf(s, "  - Hit Ratio: %llu%% (%llu / %llu)\n",
+				!si->total_ext[EX_READ] ? 0 :
+				div64_u64(si->hit_total[EX_READ] * 100,
+				si->total_ext[EX_READ]),
+				si->hit_total[EX_READ], si->total_ext[EX_READ]);
+		seq_printf(s, "  - Inner Struct Count: tree: %d(%d), node: %d\n",
+				si->ext_tree[EX_READ], si->zombie_tree[EX_READ],
+				si->ext_node[EX_READ]);
+		seq_puts(s, "\nExtent Cache (Block Age):\n");
+		seq_printf(s, "  - Allocated Data Blocks: %llu\n",
+				si->allocated_data_blocks);
+		seq_printf(s, "  - Hit Count: L1:%llu L2:%llu\n",
+				si->hit_cached[EX_BLOCK_AGE],
+				si->hit_rbtree[EX_BLOCK_AGE]);
+		seq_printf(s, "  - Hit Ratio: %llu%% (%llu / %llu)\n",
+				!si->total_ext[EX_BLOCK_AGE] ? 0 :
+				div64_u64(si->hit_total[EX_BLOCK_AGE] * 100,
+				si->total_ext[EX_BLOCK_AGE]),
+				si->hit_total[EX_BLOCK_AGE],
+				si->total_ext[EX_BLOCK_AGE]);
+		seq_printf(s, "  - Inner Struct Count: tree: %d(%d), node: %d\n",
+				si->ext_tree[EX_BLOCK_AGE],
+				si->zombie_tree[EX_BLOCK_AGE],
+				si->ext_node[EX_BLOCK_AGE]);
+		seq_puts(s, "\nBalancing F2FS Async:\n");
+		seq_printf(s, "  - DIO (R: %4d, W: %4d)\n",
+			   si->nr_dio_read, si->nr_dio_write);
+		seq_printf(s, "  - IO_R (Data: %4d, Node: %4d, Meta: %4d\n",
+			   si->nr_rd_data, si->nr_rd_node, si->nr_rd_meta);
+		seq_printf(s, "  - IO_W (CP: %4d, Data: %4d, Flush: (%4d %4d %4d), ",
+			   si->nr_wb_cp_data, si->nr_wb_data,
+			   si->nr_flushing, si->nr_flushed,
+			   si->flush_list_empty);
+		seq_printf(s, "Discard: (%4d %4d)) cmd: %4d undiscard:%4u\n",
+			   si->nr_discarding, si->nr_discarded,
+			   si->nr_discard_cmd, si->undiscard_blks);
+		seq_printf(s, "  - atomic IO: %4d (Max. %4d)\n",
+			   si->aw_cnt, si->max_aw_cnt);
+		seq_printf(s, "  - compress: %4d, hit:%8d\n", si->compress_pages, si->compress_page_hit);
+		seq_printf(s, "  - nodes: %4d in %4d\n",
+			   si->ndirty_node, si->node_pages);
+		seq_printf(s, "  - dents: %4d in dirs:%4d (%4d)\n",
+			   si->ndirty_dent, si->ndirty_dirs, si->ndirty_all);
+		seq_printf(s, "  - data: %4d in files:%4d\n",
+			   si->ndirty_data, si->ndirty_files);
+		seq_printf(s, "  - quota data: %4d in quota files:%4d\n",
+			   si->ndirty_qdata, si->nquota_files);
+		seq_printf(s, "  - meta: %4d in %4d\n",
+			   si->ndirty_meta, si->meta_pages);
+		seq_printf(s, "  - imeta: %4d\n",
+			   si->ndirty_imeta);
+		seq_printf(s, "  - fsync mark: %4lld\n",
+			   percpu_counter_sum_positive(
+					&sbi->rf_node_block_count));
+		seq_printf(s, "  - NATs: %9d/%9d\n  - SITs: %9d/%9d\n",
+			   si->dirty_nats, si->nats, si->dirty_sits, si->sits);
+		seq_printf(s, "  - free_nids: %9d/%9d\n  - alloc_nids: %9d\n",
+			   si->free_nids, si->avail_nids, si->alloc_nids);
+		seq_puts(s, "\nDistribution of User Blocks:");
+		seq_puts(s, " [ valid | invalid | free ]\n");
+		seq_puts(s, "  [");
+
+		for (j = 0; j < si->util_valid; j++)
+			seq_putc(s, '-');
+		seq_putc(s, '|');
+
+		for (j = 0; j < si->util_invalid; j++)
+			seq_putc(s, '-');
+		seq_putc(s, '|');
+
+		for (j = 0; j < si->util_free; j++)
+			seq_putc(s, '-');
+		seq_puts(s, "]\n\n");
+		seq_printf(s, "IPU: %u blocks\n", si->inplace_count);
+		seq_printf(s, "SSR: %u blocks in %u segments\n",
+			   si->block_count[SSR], si->segment_count[SSR]);
+		seq_printf(s, "LFS: %u blocks in %u segments\n",
+			   si->block_count[LFS], si->segment_count[LFS]);
+
+		/* segment usage info */
+		f2fs_update_sit_info(sbi);
+		seq_printf(s, "\nBDF: %u, avg. vblocks: %u\n",
+			   si->bimodal, si->avg_vblocks);
+
+		/* memory footprint */
+		update_mem_info(sbi);
+		seq_printf(s, "\nMemory: %llu KB\n",
+			(si->base_mem + si->cache_mem + si->page_mem) >> 10);
+		seq_printf(s, "  - static: %llu KB\n",
+				si->base_mem >> 10);
+		seq_printf(s, "  - cached all: %llu KB\n",
+				si->cache_mem >> 10);
+		seq_printf(s, "  - read extent cache: %llu KB\n",
+				si->ext_mem[EX_READ] >> 10);
+		seq_printf(s, "  - block age extent cache: %llu KB\n",
+				si->ext_mem[EX_BLOCK_AGE] >> 10);
+		seq_printf(s, "  - paged : %llu KB\n",
+				si->page_mem >> 10);
+	}
+	spin_unlock(&f2fs_stat_lock);
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(stat);
+#endif
+
+int f2fs_build_stats(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	struct f2fs_stat_info *si;
+	struct f2fs_dev_stats *dev_stats;
+	int i;
+
+	si = f2fs_kzalloc(sbi, sizeof(struct f2fs_stat_info), GFP_KERNEL);
+	if (!si)
+		return -ENOMEM;
+
+	dev_stats = f2fs_kzalloc(sbi, sizeof(struct f2fs_dev_stats) *
+						sbi->s_ndevs, GFP_KERNEL);
+	if (!dev_stats) {
+		kfree(si);
+		return -ENOMEM;
+	}
+
+	si->dev_stats = dev_stats;
+
+	si->all_area_segs = le32_to_cpu(raw_super->segment_count);
+	si->sit_area_segs = le32_to_cpu(raw_super->segment_count_sit);
+	si->nat_area_segs = le32_to_cpu(raw_super->segment_count_nat);
+	si->ssa_area_segs = le32_to_cpu(raw_super->segment_count_ssa);
+	si->main_area_segs = le32_to_cpu(raw_super->segment_count_main);
+	si->main_area_sections = le32_to_cpu(raw_super->section_count);
+	si->main_area_zones = si->main_area_sections /
+				le32_to_cpu(raw_super->secs_per_zone);
+	si->sbi = sbi;
+	sbi->stat_info = si;
+
+	/* general extent cache stats */
+	for (i = 0; i < NR_EXTENT_CACHES; i++) {
+		atomic64_set(&sbi->total_hit_ext[i], 0);
+		atomic64_set(&sbi->read_hit_rbtree[i], 0);
+		atomic64_set(&sbi->read_hit_cached[i], 0);
+	}
+
+	/* read extent_cache only */
+	atomic64_set(&sbi->read_hit_largest, 0);
+
+	atomic_set(&sbi->inline_xattr, 0);
+	atomic_set(&sbi->inline_inode, 0);
+	atomic_set(&sbi->inline_dir, 0);
+	atomic_set(&sbi->compr_inode, 0);
+	atomic64_set(&sbi->compr_blocks, 0);
+	atomic_set(&sbi->swapfile_inode, 0);
+	atomic_set(&sbi->atomic_files, 0);
+	atomic_set(&sbi->inplace_count, 0);
+	for (i = META_CP; i < META_MAX; i++)
+		atomic_set(&sbi->meta_count[i], 0);
+	for (i = 0; i < MAX_CALL_TYPE; i++)
+		atomic_set(&sbi->cp_call_count[i], 0);
+
+	atomic_set(&sbi->max_aw_cnt, 0);
+
+	spin_lock(&f2fs_stat_lock);
+	list_add_tail(&si->stat_list, &f2fs_stat_list);
+	spin_unlock(&f2fs_stat_lock);
+
+	return 0;
+}
+
+void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
+
+	spin_lock(&f2fs_stat_lock);
+	list_del(&si->stat_list);
+	spin_unlock(&f2fs_stat_lock);
+
+	kfree(si->dev_stats);
+	kfree(si);
+}
+
+void __init f2fs_create_root_stats(void)
+{
+#ifdef CONFIG_DEBUG_FS
+	f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL);
+
+	debugfs_create_file("status", 0444, f2fs_debugfs_root, NULL,
+			    &stat_fops);
+#endif
+}
+
+void f2fs_destroy_root_stats(void)
+{
+#ifdef CONFIG_DEBUG_FS
+	debugfs_remove_recursive(f2fs_debugfs_root);
+	f2fs_debugfs_root = NULL;
+#endif
+}

linux-7.2.3/fs/f2fs/gc.h

@@ -0,0 +1,202 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * fs/f2fs/gc.h
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ */
+#define GC_THREAD_MIN_WB_PAGES		1	/*
+						 * a threshold to determine
+						 * whether IO subsystem is idle
+						 * or not
+						 */
+#define DEF_GC_THREAD_URGENT_SLEEP_TIME	500	/* 500 ms */
+#define DEF_GC_THREAD_MIN_SLEEP_TIME	30000	/* milliseconds */
+#define DEF_GC_THREAD_MAX_SLEEP_TIME	60000
+#define DEF_GC_THREAD_NOGC_SLEEP_TIME	300000	/* wait 5 min */
+
+/* GC sleep parameters for zoned deivces */
+#define DEF_GC_THREAD_MIN_SLEEP_TIME_ZONED	10
+#define DEF_GC_THREAD_MAX_SLEEP_TIME_ZONED	20
+#define DEF_GC_THREAD_NOGC_SLEEP_TIME_ZONED	60000
+
+/* choose candidates from sections which has age of more than 7 days */
+#define DEF_GC_THREAD_AGE_THRESHOLD		(60 * 60 * 24 * 7)
+#define DEF_GC_THREAD_CANDIDATE_RATIO		20	/* select 20% oldest sections as candidates */
+#define DEF_GC_THREAD_MAX_CANDIDATE_COUNT	10	/* select at most 10 sections as candidates */
+#define DEF_GC_THREAD_AGE_WEIGHT		60	/* age weight */
+#define DEF_GC_THREAD_VALID_THRESH_RATIO	80	/* do not GC over 80% valid block ratio for one time GC */
+#define DEFAULT_ACCURACY_CLASS			10000	/* accuracy class */
+
+#define LIMIT_INVALID_BLOCK	40 /* percentage over total user space */
+#define LIMIT_FREE_BLOCK	40 /* percentage over invalid + free space */
+
+#define LIMIT_NO_ZONED_GC	60 /* percentage over total user space of no gc for zoned devices */
+#define LIMIT_BOOST_ZONED_GC	25 /* percentage over total user space of boosted gc for zoned devices */
+#define DEF_MIGRATION_WINDOW_GRANULARITY_ZONED	3
+#define BOOST_GC_MULTIPLE	5
+#define ZONED_PIN_SEC_REQUIRED_COUNT	1
+
+#define DEF_GC_FAILED_PINNED_FILES	2048
+#define MAX_GC_FAILED_PINNED_FILES	USHRT_MAX
+
+/* Search max. number of dirty segments to select a victim segment */
+#define DEF_MAX_VICTIM_SEARCH 4096 /* covers 8GB */
+
+#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;
+	struct radix_tree_root iroot;
+};
+
+struct victim_entry {
+	struct rb_node rb_node;		/* rb node located in rb-tree */
+	unsigned long long mtime;	/* mtime of section */
+	unsigned int segno;		/* segment No. */
+	struct list_head list;
+};
+
+/*
+ * inline functions
+ */
+
+/*
+ * On a Zoned device zone-capacity can be less than zone-size and if
+ * zone-capacity is not aligned to f2fs segment size(2MB), then the segment
+ * starting just before zone-capacity has some blocks spanning across the
+ * zone-capacity, these blocks are not usable.
+ * Such spanning segments can be in free list so calculate the sum of usable
+ * blocks in currently free segments including normal and spanning segments.
+ */
+static inline block_t free_segs_blk_count_zoned(struct f2fs_sb_info *sbi)
+{
+	block_t free_seg_blks = 0;
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	int j;
+
+	spin_lock(&free_i->segmap_lock);
+	for (j = 0; j < MAIN_SEGS(sbi); j++)
+		if (!test_bit(j, free_i->free_segmap))
+			free_seg_blks += f2fs_usable_blks_in_seg(sbi, j);
+	spin_unlock(&free_i->segmap_lock);
+
+	return free_seg_blks;
+}
+
+static inline block_t free_segs_blk_count(struct f2fs_sb_info *sbi)
+{
+	if (f2fs_sb_has_blkzoned(sbi))
+		return free_segs_blk_count_zoned(sbi);
+
+	return SEGS_TO_BLKS(sbi, free_segments(sbi));
+}
+
+static inline block_t free_user_blocks(struct f2fs_sb_info *sbi)
+{
+	block_t free_blks, ovp_blks;
+
+	free_blks = free_segs_blk_count(sbi);
+	ovp_blks = SEGS_TO_BLKS(sbi, overprovision_segments(sbi));
+
+	if (free_blks < ovp_blks)
+		return 0;
+
+	return free_blks - ovp_blks;
+}
+
+static inline block_t limit_invalid_user_blocks(block_t user_block_count)
+{
+	return (long)(user_block_count * LIMIT_INVALID_BLOCK) / 100;
+}
+
+static inline block_t limit_free_user_blocks(block_t reclaimable_user_blocks)
+{
+	return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100;
+}
+
+static inline void increase_sleep_time(struct f2fs_gc_kthread *gc_th,
+							unsigned int *wait)
+{
+	unsigned int min_time = gc_th->min_sleep_time;
+	unsigned int max_time = gc_th->max_sleep_time;
+
+	if (*wait == gc_th->no_gc_sleep_time)
+		return;
+
+	if ((long long)*wait + (long long)min_time > (long long)max_time)
+		*wait = max_time;
+	else
+		*wait += min_time;
+}
+
+static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th,
+							unsigned int *wait)
+{
+	unsigned int min_time = gc_th->min_sleep_time;
+
+	if (*wait == gc_th->no_gc_sleep_time)
+		*wait = gc_th->max_sleep_time;
+
+	if ((long long)*wait - (long long)min_time < (long long)min_time)
+		*wait = min_time;
+	else
+		*wait -= min_time;
+}
+
+static inline bool has_enough_free_blocks(struct f2fs_sb_info *sbi,
+						unsigned int limit_perc)
+{
+	return free_sections(sbi) > ((sbi->total_sections * limit_perc) / 100);
+}
+
+static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
+{
+	block_t user_block_count = sbi->user_block_count;
+	block_t invalid_user_blocks = user_block_count -
+		written_block_count(sbi);
+	/*
+	 * Background GC is triggered with the following conditions.
+	 * 1. There are a number of invalid blocks.
+	 * 2. There is not enough free space.
+	 */
+	return (invalid_user_blocks >
+			limit_invalid_user_blocks(user_block_count) &&
+		free_user_blocks(sbi) <
+			limit_free_user_blocks(invalid_user_blocks));
+}
+
+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);
+	return has_enough_invalid_blocks(sbi);
+}

linux-7.2.3/fs/f2fs/hash.c

@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fs/f2fs/hash.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * Portions of this code from linux/fs/ext3/hash.c
+ *
+ * Copyright (C) 2002 by Theodore Ts'o
+ */
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/pagemap.h>
+#include <linux/unicode.h>
+
+#include "f2fs.h"
+
+/*
+ * Hashing code copied from ext3
+ */
+#define DELTA 0x9E3779B9
+
+static void TEA_transform(unsigned int buf[4], unsigned int const in[])
+{
+	__u32 sum = 0;
+	__u32 b0 = buf[0], b1 = buf[1];
+	__u32 a = in[0], b = in[1], c = in[2], d = in[3];
+	int n = 16;
+
+	do {
+		sum += DELTA;
+		b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
+		b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
+	} while (--n);
+
+	buf[0] += b0;
+	buf[1] += b1;
+}
+
+static void str2hashbuf(const unsigned char *msg, size_t len,
+				unsigned int *buf, int num)
+{
+	unsigned pad, val;
+	int i;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	val = pad;
+	if (len > num * 4)
+		len = num * 4;
+	for (i = 0; i < len; i++) {
+		if ((i % 4) == 0)
+			val = pad;
+		val = msg[i] + (val << 8);
+		if ((i % 4) == 3) {
+			*buf++ = val;
+			val = pad;
+			num--;
+		}
+	}
+	if (--num >= 0)
+		*buf++ = val;
+	while (--num >= 0)
+		*buf++ = pad;
+}
+
+static u32 TEA_hash_name(const u8 *p, size_t len)
+{
+	__u32 in[8], buf[4];
+
+	/* Initialize the default seed for the hash checksum functions */
+	buf[0] = 0x67452301;
+	buf[1] = 0xefcdab89;
+	buf[2] = 0x98badcfe;
+	buf[3] = 0x10325476;
+
+	while (1) {
+		str2hashbuf(p, len, in, 4);
+		TEA_transform(buf, in);
+		p += 16;
+		if (len <= 16)
+			break;
+		len -= 16;
+	}
+	return buf[0] & ~F2FS_HASH_COL_BIT;
+}
+
+/*
+ * Compute @fname->hash.  For all directories, @fname->disk_name must be set.
+ * For casefolded directories, @fname->usr_fname must be set, and also
+ * @fname->cf_name if the filename is valid Unicode and is not "." or "..".
+ */
+void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname)
+{
+	const u8 *name = fname->disk_name.name;
+	size_t len = fname->disk_name.len;
+
+	WARN_ON_ONCE(!name);
+
+	if (name_is_dot_dotdot(name, len)) {
+		fname->hash = 0;
+		return;
+	}
+
+#if IS_ENABLED(CONFIG_UNICODE)
+	if (IS_CASEFOLDED(dir)) {
+		/*
+		 * If the casefolded name is provided, hash it instead of the
+		 * on-disk name.  If the casefolded name is *not* provided, that
+		 * should only be because the name wasn't valid Unicode or was
+		 * "." or "..", so fall back to treating the name as an opaque
+		 * byte sequence.  Note that to handle encrypted directories,
+		 * the fallback must use usr_fname (plaintext) rather than
+		 * disk_name (ciphertext).
+		 */
+		WARN_ON_ONCE(!fname->usr_fname->name);
+		if (fname->cf_name.name) {
+			name = fname->cf_name.name;
+			len = fname->cf_name.len;
+		} else {
+			name = fname->usr_fname->name;
+			len = fname->usr_fname->len;
+		}
+		if (IS_ENCRYPTED(dir)) {
+			struct qstr tmp = QSTR_INIT(name, len);
+
+			fname->hash =
+				cpu_to_le32(fscrypt_fname_siphash(dir, &tmp));
+			return;
+		}
+	}
+#endif
+	fname->hash = cpu_to_le32(TEA_hash_name(name, len));
+}

linux-7.2.3/fs/f2fs/inline.c

@@ -0,0 +1,860 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fs/f2fs/inline.c
+ * Copyright (c) 2013, Intel Corporation
+ * Authors: Huajun Li <huajun.li@intel.com>
+ *          Haicheng Li <haicheng.li@intel.com>
+ */
+
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/fiemap.h>
+#include <linux/fserror.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include <trace/events/f2fs.h>
+
+static bool support_inline_data(struct inode *inode)
+{
+	if (f2fs_used_in_atomic_write(inode))
+		return false;
+	if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))
+		return false;
+	if (i_size_read(inode) > MAX_INLINE_DATA(inode))
+		return false;
+	return true;
+}
+
+bool f2fs_may_inline_data(struct inode *inode)
+{
+	if (!support_inline_data(inode))
+		return false;
+
+	return !f2fs_post_read_required(inode);
+}
+
+static bool inode_has_blocks(struct inode *inode, struct folio *ifolio)
+{
+	struct f2fs_inode *ri = F2FS_INODE(ifolio);
+	int i;
+
+	if (F2FS_HAS_BLOCKS(inode))
+		return true;
+
+	for (i = 0; i < DEF_NIDS_PER_INODE; i++) {
+		if (ri->i_nid[i])
+			return true;
+	}
+	return false;
+}
+
+bool f2fs_sanity_check_inline_data(struct inode *inode, struct folio *ifolio)
+{
+	if (!f2fs_has_inline_data(inode))
+		return false;
+
+	if (inode_has_blocks(inode, ifolio))
+		return false;
+
+	if (!support_inline_data(inode))
+		return true;
+
+	/*
+	 * used by sanity_check_inode(), when disk layout fields has not
+	 * been synchronized to inmem fields.
+	 */
+	return (S_ISREG(inode->i_mode) &&
+		(file_is_encrypt(inode) || file_is_verity(inode) ||
+		(F2FS_I(inode)->i_flags & F2FS_COMPR_FL)));
+}
+
+bool f2fs_may_inline_dentry(struct inode *inode)
+{
+	if (!test_opt(F2FS_I_SB(inode), INLINE_DENTRY))
+		return false;
+
+	if (!S_ISDIR(inode->i_mode))
+		return false;
+
+	return true;
+}
+
+void f2fs_do_read_inline_data(struct folio *folio, struct folio *ifolio)
+{
+	struct inode *inode = folio->mapping->host;
+
+	if (folio_test_uptodate(folio))
+		return;
+
+	f2fs_bug_on(F2FS_I_SB(inode), folio->index);
+
+	folio_zero_segment(folio, MAX_INLINE_DATA(inode), folio_size(folio));
+
+	/* Copy the whole inline data block */
+	memcpy_to_folio(folio, 0, inline_data_addr(inode, ifolio),
+		       MAX_INLINE_DATA(inode));
+	if (!folio_test_uptodate(folio))
+		folio_mark_uptodate(folio);
+}
+
+void f2fs_truncate_inline_inode(struct inode *inode, struct folio *ifolio,
+		u64 from)
+{
+	void *addr;
+
+	if (from >= MAX_INLINE_DATA(inode))
+		return;
+
+	addr = inline_data_addr(inode, ifolio);
+
+	f2fs_folio_wait_writeback(ifolio, NODE, true, true);
+	memset(addr + from, 0, MAX_INLINE_DATA(inode) - from);
+	folio_mark_dirty(ifolio);
+
+	if (from == 0)
+		clear_inode_flag(inode, FI_DATA_EXIST);
+}
+
+int f2fs_read_inline_data(struct inode *inode, struct folio *folio)
+{
+	struct folio *ifolio;
+
+	ifolio = f2fs_get_inode_folio(F2FS_I_SB(inode), inode->i_ino);
+	if (IS_ERR(ifolio)) {
+		folio_unlock(folio);
+		return PTR_ERR(ifolio);
+	}
+
+	if (!f2fs_has_inline_data(inode)) {
+		f2fs_folio_put(ifolio, true);
+		return -EAGAIN;
+	}
+
+	if (folio->index)
+		folio_zero_segment(folio, 0, folio_size(folio));
+	else
+		f2fs_do_read_inline_data(folio, ifolio);
+
+	if (!folio_test_uptodate(folio))
+		folio_mark_uptodate(folio);
+	f2fs_folio_put(ifolio, true);
+	folio_unlock(folio);
+	return 0;
+}
+
+int f2fs_convert_inline_folio(struct dnode_of_data *dn, struct folio *folio)
+{
+	struct f2fs_io_info fio = {
+		.sbi = F2FS_I_SB(dn->inode),
+		.ino = dn->inode->i_ino,
+		.type = DATA,
+		.op = REQ_OP_WRITE,
+		.op_flags = REQ_SYNC | REQ_PRIO,
+		.folio = folio,
+		.encrypted_page = NULL,
+		.io_type = FS_DATA_IO,
+	};
+	struct node_info ni;
+	int dirty, err;
+
+	if (!f2fs_exist_data(dn->inode))
+		goto clear_out;
+
+	err = f2fs_reserve_block(dn, 0);
+	if (err)
+		return err;
+
+	err = f2fs_get_node_info(fio.sbi, dn->nid, &ni, false);
+	if (err) {
+		f2fs_truncate_data_blocks_range(dn, 1);
+		f2fs_put_dnode(dn);
+		return err;
+	}
+
+	fio.version = ni.version;
+
+	if (unlikely(dn->data_blkaddr != NEW_ADDR)) {
+		f2fs_put_dnode(dn);
+		set_sbi_flag(fio.sbi, SBI_NEED_FSCK);
+		f2fs_warn(fio.sbi, "%s: corrupted inline inode ino=%llu, i_addr[0]:0x%x, run fsck to fix.",
+			  __func__, dn->inode->i_ino, dn->data_blkaddr);
+		f2fs_handle_error(fio.sbi, ERROR_INVALID_BLKADDR);
+		fserror_report_file_metadata(dn->inode, -EFSCORRUPTED, GFP_NOFS);
+		return -EFSCORRUPTED;
+	}
+
+	f2fs_bug_on(F2FS_F_SB(folio), folio_test_writeback(folio));
+
+	f2fs_do_read_inline_data(folio, dn->inode_folio);
+	folio_mark_dirty(folio);
+
+	/* clear dirty state */
+	dirty = folio_clear_dirty_for_io(folio);
+
+	/* write data page to try to make data consistent */
+	folio_start_writeback(folio);
+	fio.old_blkaddr = dn->data_blkaddr;
+	set_inode_flag(dn->inode, FI_HOT_DATA);
+	f2fs_outplace_write_data(dn, &fio);
+	f2fs_folio_wait_writeback(folio, DATA, true, true);
+	if (dirty) {
+		inode_dec_dirty_pages(dn->inode);
+		f2fs_remove_dirty_inode(dn->inode);
+	}
+
+	/* this converted inline_data should be recovered. */
+	set_inode_flag(dn->inode, FI_APPEND_WRITE);
+
+	/* clear inline data and flag after data writeback */
+	f2fs_truncate_inline_inode(dn->inode, dn->inode_folio, 0);
+	folio_clear_f2fs_inline(dn->inode_folio);
+clear_out:
+	stat_dec_inline_inode(dn->inode);
+	clear_inode_flag(dn->inode, FI_INLINE_DATA);
+	f2fs_put_dnode(dn);
+	return 0;
+}
+
+int f2fs_convert_inline_inode(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct dnode_of_data dn;
+	struct f2fs_lock_context lc;
+	struct folio *ifolio, *folio;
+	int err = 0;
+
+	if (f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb))
+		return -EROFS;
+
+	if (!f2fs_has_inline_data(inode))
+		return 0;
+
+	err = f2fs_dquot_initialize(inode);
+	if (err)
+		return err;
+
+	folio = f2fs_grab_cache_folio(inode->i_mapping, 0, false);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
+
+	f2fs_lock_op(sbi, &lc);
+
+	ifolio = f2fs_get_inode_folio(sbi, inode->i_ino);
+	if (IS_ERR(ifolio)) {
+		err = PTR_ERR(ifolio);
+		goto out;
+	}
+
+	set_new_dnode(&dn, inode, ifolio, ifolio, 0);
+
+	if (f2fs_has_inline_data(inode))
+		err = f2fs_convert_inline_folio(&dn, folio);
+
+	f2fs_put_dnode(&dn);
+out:
+	f2fs_unlock_op(sbi, &lc);
+
+	f2fs_folio_put(folio, true);
+
+	if (!err)
+		f2fs_balance_fs(sbi, dn.node_changed);
+
+	return err;
+}
+
+int f2fs_write_inline_data(struct inode *inode, struct folio *folio)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct folio *ifolio;
+
+	ifolio = f2fs_get_inode_folio(sbi, inode->i_ino);
+	if (IS_ERR(ifolio))
+		return PTR_ERR(ifolio);
+
+	if (!f2fs_has_inline_data(inode)) {
+		f2fs_folio_put(ifolio, true);
+		return -EAGAIN;
+	}
+
+	f2fs_bug_on(F2FS_I_SB(inode), folio->index);
+
+	f2fs_folio_wait_writeback(ifolio, NODE, true, true);
+	memcpy_from_folio(inline_data_addr(inode, ifolio),
+			 folio, 0, MAX_INLINE_DATA(inode));
+	folio_mark_dirty(ifolio);
+
+	f2fs_clear_page_cache_dirty_tag(folio);
+
+	set_inode_flag(inode, FI_APPEND_WRITE);
+	set_inode_flag(inode, FI_DATA_EXIST);
+
+	folio_clear_f2fs_inline(ifolio);
+	f2fs_folio_put(ifolio, true);
+	return 0;
+}
+
+int f2fs_recover_inline_data(struct inode *inode, struct folio *nfolio)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_inode *ri = NULL;
+	void *src_addr, *dst_addr;
+
+	/*
+	 * The inline_data recovery policy is as follows.
+	 * [prev.] [next] of inline_data flag
+	 *    o       o  -> recover inline_data
+	 *    o       x  -> remove inline_data, and then recover data blocks
+	 *    x       o  -> remove data blocks, and then recover inline_data
+	 *    x       x  -> recover data blocks
+	 */
+	if (IS_INODE(nfolio))
+		ri = F2FS_INODE(nfolio);
+
+	if (f2fs_has_inline_data(inode) &&
+			ri && (ri->i_inline & F2FS_INLINE_DATA)) {
+		struct folio *ifolio;
+process_inline:
+		ifolio = f2fs_get_inode_folio(sbi, inode->i_ino);
+		if (IS_ERR(ifolio))
+			return PTR_ERR(ifolio);
+
+		f2fs_folio_wait_writeback(ifolio, NODE, true, true);
+
+		src_addr = inline_data_addr(inode, nfolio);
+		dst_addr = inline_data_addr(inode, ifolio);
+		memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode));
+
+		set_inode_flag(inode, FI_INLINE_DATA);
+		set_inode_flag(inode, FI_DATA_EXIST);
+
+		folio_mark_dirty(ifolio);
+		f2fs_folio_put(ifolio, true);
+		return 1;
+	}
+
+	if (f2fs_has_inline_data(inode)) {
+		struct folio *ifolio = f2fs_get_inode_folio(sbi, inode->i_ino);
+		if (IS_ERR(ifolio))
+			return PTR_ERR(ifolio);
+		f2fs_truncate_inline_inode(inode, ifolio, 0);
+		stat_dec_inline_inode(inode);
+		clear_inode_flag(inode, FI_INLINE_DATA);
+		f2fs_folio_put(ifolio, true);
+	} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
+		int ret;
+
+		ret = f2fs_truncate_blocks(inode, 0, false);
+		if (ret)
+			return ret;
+		stat_inc_inline_inode(inode);
+		goto process_inline;
+	}
+	return 0;
+}
+
+struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
+					const struct f2fs_filename *fname,
+					struct folio **res_folio,
+					bool use_hash)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+	struct f2fs_dir_entry *de;
+	struct f2fs_dentry_ptr d;
+	struct folio *ifolio;
+	void *inline_dentry;
+
+	ifolio = f2fs_get_inode_folio(sbi, dir->i_ino);
+	if (IS_ERR(ifolio)) {
+		*res_folio = ifolio;
+		return NULL;
+	}
+
+	inline_dentry = inline_data_addr(dir, ifolio);
+
+	make_dentry_ptr_inline(dir, &d, inline_dentry);
+	de = f2fs_find_target_dentry(&d, fname, NULL, use_hash);
+	folio_unlock(ifolio);
+	if (IS_ERR(de)) {
+		*res_folio = ERR_CAST(de);
+		de = NULL;
+	}
+	if (de)
+		*res_folio = ifolio;
+	else
+		f2fs_folio_put(ifolio, false);
+
+	return de;
+}
+
+int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
+							struct folio *ifolio)
+{
+	struct f2fs_dentry_ptr d;
+	void *inline_dentry;
+
+	inline_dentry = inline_data_addr(inode, ifolio);
+
+	make_dentry_ptr_inline(inode, &d, inline_dentry);
+	f2fs_do_make_empty_dir(inode, parent, &d);
+
+	folio_mark_dirty(ifolio);
+
+	/* update i_size to MAX_INLINE_DATA */
+	if (i_size_read(inode) < MAX_INLINE_DATA(inode))
+		f2fs_i_size_write(inode, MAX_INLINE_DATA(inode));
+	return 0;
+}
+
+/*
+ * NOTE: ipage is grabbed by caller, but if any error occurs, we should
+ * release ipage in this function.
+ */
+static int f2fs_move_inline_dirents(struct inode *dir, struct folio *ifolio,
+							void *inline_dentry)
+{
+	struct folio *folio;
+	struct dnode_of_data dn;
+	struct f2fs_dentry_block *dentry_blk;
+	struct f2fs_dentry_ptr src, dst;
+	int err;
+
+	folio = f2fs_grab_cache_folio(dir->i_mapping, 0, true);
+	if (IS_ERR(folio)) {
+		f2fs_folio_put(ifolio, true);
+		return PTR_ERR(folio);
+	}
+
+	set_new_dnode(&dn, dir, ifolio, NULL, 0);
+	err = f2fs_reserve_block(&dn, 0);
+	if (err)
+		goto out;
+
+	if (unlikely(dn.data_blkaddr != NEW_ADDR)) {
+		f2fs_put_dnode(&dn);
+		set_sbi_flag(F2FS_F_SB(folio), SBI_NEED_FSCK);
+		f2fs_warn(F2FS_F_SB(folio), "%s: corrupted inline inode ino=%llu, i_addr[0]:0x%x, run fsck to fix.",
+			  __func__, dir->i_ino, dn.data_blkaddr);
+		f2fs_handle_error(F2FS_F_SB(folio), ERROR_INVALID_BLKADDR);
+		err = -EFSCORRUPTED;
+		fserror_report_file_metadata(dn.inode, err, GFP_NOFS);
+		goto out;
+	}
+
+	f2fs_folio_wait_writeback(folio, DATA, true, true);
+
+	dentry_blk = folio_address(folio);
+
+	/*
+	 * Start by zeroing the full block, to ensure that all unused space is
+	 * zeroed and no uninitialized memory is leaked to disk.
+	 */
+	memset(dentry_blk, 0, F2FS_BLKSIZE);
+
+	make_dentry_ptr_inline(dir, &src, inline_dentry);
+	make_dentry_ptr_block(dir, &dst, dentry_blk);
+
+	/* copy data from inline dentry block to new dentry block */
+	memcpy(dst.bitmap, src.bitmap, src.nr_bitmap);
+	memcpy(dst.dentry, src.dentry, SIZE_OF_DIR_ENTRY * src.max);
+	memcpy(dst.filename, src.filename, src.max * F2FS_SLOT_LEN);
+
+	if (!folio_test_uptodate(folio))
+		folio_mark_uptodate(folio);
+	folio_mark_dirty(folio);
+
+	/* clear inline dir and flag after data writeback */
+	f2fs_truncate_inline_inode(dir, ifolio, 0);
+
+	stat_dec_inline_dir(dir);
+	clear_inode_flag(dir, FI_INLINE_DENTRY);
+
+	/*
+	 * should retrieve reserved space which was used to keep
+	 * inline_dentry's structure for backward compatibility.
+	 */
+	if (!f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(dir)) &&
+			!f2fs_has_inline_xattr(dir))
+		F2FS_I(dir)->i_inline_xattr_size = 0;
+
+	f2fs_i_depth_write(dir, 1);
+	if (i_size_read(dir) < PAGE_SIZE)
+		f2fs_i_size_write(dir, PAGE_SIZE);
+out:
+	f2fs_folio_put(folio, true);
+	return err;
+}
+
+static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry)
+{
+	struct f2fs_dentry_ptr d;
+	unsigned long bit_pos = 0;
+	int err = 0;
+
+	make_dentry_ptr_inline(dir, &d, inline_dentry);
+
+	while (bit_pos < d.max) {
+		struct f2fs_dir_entry *de;
+		struct f2fs_filename fname;
+		nid_t ino;
+		umode_t fake_mode;
+
+		if (!test_bit_le(bit_pos, d.bitmap)) {
+			bit_pos++;
+			continue;
+		}
+
+		de = &d.dentry[bit_pos];
+
+		if (unlikely(!de->name_len)) {
+			bit_pos++;
+			continue;
+		}
+		if (unlikely(le16_to_cpu(de->name_len) > F2FS_NAME_LEN ||
+			     bit_pos + GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)) >
+			     d.max)) {
+			err = -EFSCORRUPTED;
+			goto punch_dentry_pages;
+		}
+
+		/*
+		 * We only need the disk_name and hash to move the dentry.
+		 * We don't need the original or casefolded filenames.
+		 */
+		memset(&fname, 0, sizeof(fname));
+		fname.disk_name.name = d.filename[bit_pos];
+		fname.disk_name.len = le16_to_cpu(de->name_len);
+		fname.hash = de->hash_code;
+
+		ino = le32_to_cpu(de->ino);
+		fake_mode = fs_ftype_to_dtype(de->file_type) << S_DT_SHIFT;
+
+		err = f2fs_add_regular_entry(dir, &fname, NULL, ino, fake_mode);
+		if (err)
+			goto punch_dentry_pages;
+
+		bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+	}
+	return 0;
+
+punch_dentry_pages:
+	truncate_inode_pages(&dir->i_data, 0);
+	f2fs_truncate_blocks(dir, 0, false);
+	f2fs_remove_dirty_inode(dir);
+	return err;
+}
+
+static int f2fs_move_rehashed_dirents(struct inode *dir, struct folio *ifolio,
+							void *inline_dentry)
+{
+	void *backup_dentry;
+	int err;
+
+	backup_dentry = f2fs_kmalloc(F2FS_I_SB(dir),
+				MAX_INLINE_DATA(dir), GFP_F2FS_ZERO);
+	if (!backup_dentry) {
+		f2fs_folio_put(ifolio, true);
+		return -ENOMEM;
+	}
+
+	memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA(dir));
+	f2fs_truncate_inline_inode(dir, ifolio, 0);
+
+	folio_unlock(ifolio);
+
+	err = f2fs_add_inline_entries(dir, backup_dentry);
+	if (err)
+		goto recover;
+
+	folio_lock(ifolio);
+
+	stat_dec_inline_dir(dir);
+	clear_inode_flag(dir, FI_INLINE_DENTRY);
+
+	/*
+	 * should retrieve reserved space which was used to keep
+	 * inline_dentry's structure for backward compatibility.
+	 */
+	if (!f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(dir)) &&
+			!f2fs_has_inline_xattr(dir))
+		F2FS_I(dir)->i_inline_xattr_size = 0;
+
+	kfree(backup_dentry);
+	return 0;
+recover:
+	folio_lock(ifolio);
+	f2fs_folio_wait_writeback(ifolio, NODE, true, true);
+	memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA(dir));
+	f2fs_i_depth_write(dir, 0);
+	f2fs_i_size_write(dir, MAX_INLINE_DATA(dir));
+	folio_mark_dirty(ifolio);
+	f2fs_folio_put(ifolio, true);
+
+	kfree(backup_dentry);
+	return err;
+}
+
+static int do_convert_inline_dir(struct inode *dir, struct folio *ifolio,
+							void *inline_dentry)
+{
+	if (!F2FS_I(dir)->i_dir_level)
+		return f2fs_move_inline_dirents(dir, ifolio, inline_dentry);
+	else
+		return f2fs_move_rehashed_dirents(dir, ifolio, inline_dentry);
+}
+
+int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+	struct folio *ifolio;
+	struct f2fs_filename fname;
+	struct f2fs_lock_context lc;
+	void *inline_dentry = NULL;
+	int err = 0;
+
+	if (!f2fs_has_inline_dentry(dir))
+		return 0;
+
+	f2fs_lock_op(sbi, &lc);
+
+	err = f2fs_setup_filename(dir, &dentry->d_name, 0, &fname);
+	if (err)
+		goto out;
+
+	ifolio = f2fs_get_inode_folio(sbi, dir->i_ino);
+	if (IS_ERR(ifolio)) {
+		err = PTR_ERR(ifolio);
+		goto out_fname;
+	}
+
+	if (f2fs_has_enough_room(dir, ifolio, &fname)) {
+		f2fs_folio_put(ifolio, true);
+		goto out_fname;
+	}
+
+	inline_dentry = inline_data_addr(dir, ifolio);
+
+	err = do_convert_inline_dir(dir, ifolio, inline_dentry);
+	if (!err)
+		f2fs_folio_put(ifolio, true);
+out_fname:
+	f2fs_free_filename(&fname);
+out:
+	f2fs_unlock_op(sbi, &lc);
+	return err;
+}
+
+int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname,
+			  struct inode *inode, nid_t ino, umode_t mode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+	struct folio *ifolio;
+	unsigned int bit_pos;
+	void *inline_dentry = NULL;
+	struct f2fs_dentry_ptr d;
+	int slots = GET_DENTRY_SLOTS(fname->disk_name.len);
+	struct folio *folio = NULL;
+	int err = 0;
+
+	ifolio = f2fs_get_inode_folio(sbi, dir->i_ino);
+	if (IS_ERR(ifolio))
+		return PTR_ERR(ifolio);
+
+	inline_dentry = inline_data_addr(dir, ifolio);
+	make_dentry_ptr_inline(dir, &d, inline_dentry);
+
+	bit_pos = f2fs_room_for_filename(d.bitmap, slots, d.max);
+	if (bit_pos >= d.max) {
+		err = do_convert_inline_dir(dir, ifolio, inline_dentry);
+		if (err)
+			return err;
+		err = -EAGAIN;
+		goto out;
+	}
+
+	if (inode) {
+		f2fs_down_write_nested(&F2FS_I(inode)->i_sem,
+						SINGLE_DEPTH_NESTING);
+		folio = f2fs_init_inode_metadata(inode, dir, fname, ifolio);
+		if (IS_ERR(folio)) {
+			err = PTR_ERR(folio);
+			goto fail;
+		}
+	}
+
+	f2fs_folio_wait_writeback(ifolio, NODE, true, true);
+
+	f2fs_update_dentry(ino, mode, &d, &fname->disk_name, fname->hash,
+			   bit_pos);
+
+	folio_mark_dirty(ifolio);
+
+	/* we don't need to mark_inode_dirty now */
+	if (inode) {
+		f2fs_i_pino_write(inode, dir->i_ino);
+
+		/* synchronize inode page's data from inode cache */
+		if (is_inode_flag_set(inode, FI_NEW_INODE))
+			f2fs_update_inode(inode, folio);
+
+		f2fs_folio_put(folio, true);
+	}
+
+	f2fs_update_parent_metadata(dir, inode, 0);
+fail:
+	if (inode)
+		f2fs_up_write(&F2FS_I(inode)->i_sem);
+out:
+	f2fs_folio_put(ifolio, true);
+	return err;
+}
+
+void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry,
+		struct folio *folio, struct inode *dir, struct inode *inode)
+{
+	struct f2fs_dentry_ptr d;
+	void *inline_dentry;
+	int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
+	unsigned int bit_pos;
+	int i;
+
+	folio_lock(folio);
+	f2fs_folio_wait_writeback(folio, NODE, true, true);
+
+	inline_dentry = inline_data_addr(dir, folio);
+	make_dentry_ptr_inline(dir, &d, inline_dentry);
+
+	bit_pos = dentry - d.dentry;
+	for (i = 0; i < slots; i++)
+		__clear_bit_le(bit_pos + i, d.bitmap);
+
+	folio_mark_dirty(folio);
+	f2fs_folio_put(folio, true);
+
+	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
+	f2fs_mark_inode_dirty_sync(dir, false);
+
+	if (inode)
+		f2fs_drop_nlink(dir, inode);
+}
+
+bool f2fs_empty_inline_dir(struct inode *dir)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+	struct folio *ifolio;
+	unsigned int bit_pos = 2;
+	void *inline_dentry;
+	struct f2fs_dentry_ptr d;
+
+	ifolio = f2fs_get_inode_folio(sbi, dir->i_ino);
+	if (IS_ERR(ifolio))
+		return false;
+
+	inline_dentry = inline_data_addr(dir, ifolio);
+	make_dentry_ptr_inline(dir, &d, inline_dentry);
+
+	bit_pos = find_next_bit_le(d.bitmap, d.max, bit_pos);
+
+	f2fs_folio_put(ifolio, true);
+
+	if (bit_pos < d.max)
+		return false;
+
+	return true;
+}
+
+int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
+				struct fscrypt_str *fstr)
+{
+	struct inode *inode = file_inode(file);
+	struct folio *ifolio = NULL;
+	struct f2fs_dentry_ptr d;
+	void *inline_dentry = NULL;
+	int err;
+
+	make_dentry_ptr_inline(inode, &d, inline_dentry);
+
+	if (ctx->pos == d.max)
+		return 0;
+
+	ifolio = f2fs_get_inode_folio(F2FS_I_SB(inode), inode->i_ino);
+	if (IS_ERR(ifolio))
+		return PTR_ERR(ifolio);
+
+	/*
+	 * f2fs_readdir was protected by inode.i_rwsem, it is safe to access
+	 * ipage without page's lock held.
+	 */
+	folio_unlock(ifolio);
+
+	inline_dentry = inline_data_addr(inode, ifolio);
+
+	make_dentry_ptr_inline(inode, &d, inline_dentry);
+
+	err = f2fs_fill_dentries(ctx, &d, 0, fstr);
+	if (!err)
+		ctx->pos = d.max;
+
+	f2fs_folio_put(ifolio, false);
+	return err < 0 ? err : 0;
+}
+
+int f2fs_inline_data_fiemap(struct inode *inode,
+		struct fiemap_extent_info *fieinfo, __u64 start, __u64 len)
+{
+	__u64 byteaddr = 0, ilen;
+	__u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED |
+		FIEMAP_EXTENT_LAST;
+	struct node_info ni;
+	struct folio *ifolio;
+	int err = 0;
+
+	ifolio = f2fs_get_inode_folio(F2FS_I_SB(inode), inode->i_ino);
+	if (IS_ERR(ifolio))
+		return PTR_ERR(ifolio);
+
+	if ((S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
+				!f2fs_has_inline_data(inode)) {
+		err = -EAGAIN;
+		goto out;
+	}
+
+	if (S_ISDIR(inode->i_mode) && !f2fs_has_inline_dentry(inode)) {
+		err = -EAGAIN;
+		goto out;
+	}
+
+	if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) {
+		err = f2fs_write_single_node_folio(ifolio, true, false, FS_NODE_IO);
+		if (err)
+			return err;
+		ifolio = f2fs_get_inode_folio(F2FS_I_SB(inode), inode->i_ino);
+		if (IS_ERR(ifolio))
+			return PTR_ERR(ifolio);
+		f2fs_folio_wait_writeback(ifolio, NODE, true, true);
+	}
+	ilen = min_t(size_t, MAX_INLINE_DATA(inode), i_size_read(inode));
+	if (start >= ilen)
+		goto out;
+	if (start + len < ilen)
+		ilen = start + len;
+	ilen -= start;
+
+	err = f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni, false);
+	if (err)
+		goto out;
+
+	if (__is_valid_data_blkaddr(ni.blk_addr)) {
+		byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits;
+		byteaddr += (char *)inline_data_addr(inode, ifolio) -
+						(char *)F2FS_INODE(ifolio);
+	} else {
+		f2fs_bug_on(F2FS_I_SB(inode), ni.blk_addr != NEW_ADDR);
+		flags |= FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN;
+	}
+	err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags);
+	trace_f2fs_fiemap(inode, start, byteaddr, ilen, flags, err);
+out:
+	f2fs_folio_put(ifolio, true);
+	return err;
+}

linux-7.2.3/fs/f2fs/iostat.c

@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * f2fs iostat support
+ *
+ * Copyright 2021 Google LLC
+ * Author: Daeho Jeong <daehojeong@google.com>
+ */
+
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/seq_file.h>
+
+#include "f2fs.h"
+#include "iostat.h"
+#include <trace/events/f2fs.h>
+
+static struct kmem_cache *bio_iostat_ctx_cache;
+static mempool_t *bio_iostat_ctx_pool;
+
+static inline unsigned long long iostat_get_avg_bytes(struct f2fs_sb_info *sbi,
+	enum iostat_type type)
+{
+	return sbi->iostat_count[type] ? div64_u64(sbi->iostat_bytes[type],
+		sbi->iostat_count[type]) : 0;
+}
+
+#define IOSTAT_INFO_SHOW(name, type)					\
+	seq_printf(seq, "%-23s %-16llu %-16llu %-16llu\n",		\
+			name":", sbi->iostat_bytes[type],		\
+			sbi->iostat_count[type],			\
+			iostat_get_avg_bytes(sbi, type))
+
+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);
+	int i;
+
+	if (!sbi->iostat_enable)
+		return 0;
+
+	seq_printf(seq, "time:		%-16llu\n", ktime_get_real_seconds());
+	seq_printf(seq, "\t\t\t%-16s %-16s %-16s\n",
+				"io_bytes", "count", "avg_bytes");
+
+	/* print app write IOs */
+	seq_puts(seq, "[WRITE]\n");
+	IOSTAT_INFO_SHOW("app buffered data", APP_BUFFERED_IO);
+	IOSTAT_INFO_SHOW("app direct data", APP_DIRECT_IO);
+	IOSTAT_INFO_SHOW("app mapped data", APP_MAPPED_IO);
+	IOSTAT_INFO_SHOW("app buffered cdata", APP_BUFFERED_CDATA_IO);
+	IOSTAT_INFO_SHOW("app mapped cdata", APP_MAPPED_CDATA_IO);
+
+	/* print fs write IOs */
+	IOSTAT_INFO_SHOW("fs data", FS_DATA_IO);
+	IOSTAT_INFO_SHOW("fs cdata", FS_CDATA_IO);
+	IOSTAT_INFO_SHOW("fs node", FS_NODE_IO);
+	IOSTAT_INFO_SHOW("fs meta", FS_META_IO);
+	IOSTAT_INFO_SHOW("fs gc data", FS_GC_DATA_IO);
+	IOSTAT_INFO_SHOW("fs gc node", FS_GC_NODE_IO);
+	IOSTAT_INFO_SHOW("fs cp data", FS_CP_DATA_IO);
+	IOSTAT_INFO_SHOW("fs cp node", FS_CP_NODE_IO);
+	IOSTAT_INFO_SHOW("fs cp meta", FS_CP_META_IO);
+
+	/* print app read IOs */
+	seq_puts(seq, "[READ]\n");
+	IOSTAT_INFO_SHOW("app buffered data", APP_BUFFERED_READ_IO);
+	IOSTAT_INFO_SHOW("app direct data", APP_DIRECT_READ_IO);
+	IOSTAT_INFO_SHOW("app mapped data", APP_MAPPED_READ_IO);
+	IOSTAT_INFO_SHOW("app buffered cdata", APP_BUFFERED_CDATA_READ_IO);
+	IOSTAT_INFO_SHOW("app mapped cdata", APP_MAPPED_CDATA_READ_IO);
+
+	/* print fs read IOs */
+	IOSTAT_INFO_SHOW("fs data", FS_DATA_READ_IO);
+	IOSTAT_INFO_SHOW("fs gc data", FS_GDATA_READ_IO);
+	IOSTAT_INFO_SHOW("fs cdata", FS_CDATA_READ_IO);
+	IOSTAT_INFO_SHOW("fs node", FS_NODE_READ_IO);
+	IOSTAT_INFO_SHOW("fs meta", FS_META_READ_IO);
+
+	/* print read folio order stats */
+	seq_printf(seq, "%-23s", "fs read folio order:");
+	for (i = 0; i < NR_PAGE_ORDERS; i++)
+		seq_printf(seq, " %llu", sbi->iostat_read_folio_count[i]);
+	seq_putc(seq, '\n');
+
+	/* print other IOs */
+	seq_puts(seq, "[OTHER]\n");
+	IOSTAT_INFO_SHOW("fs discard", FS_DISCARD_IO);
+	IOSTAT_INFO_SHOW("fs flush", FS_FLUSH_IO);
+	IOSTAT_INFO_SHOW("fs zone reset", FS_ZONE_RESET_IO);
+
+	return 0;
+}
+
+static inline void __record_iostat_latency(struct f2fs_sb_info *sbi)
+{
+	int io, idx;
+	struct f2fs_iostat_latency iostat_lat[MAX_IO_TYPE][NR_PAGE_TYPE];
+	struct iostat_lat_info *io_lat = sbi->iostat_io_lat;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->iostat_lat_lock, flags);
+	for (idx = 0; idx < MAX_IO_TYPE; idx++) {
+		for (io = 0; io < NR_PAGE_TYPE; io++) {
+			iostat_lat[idx][io].peak_lat =
+			   jiffies_to_msecs(io_lat->peak_lat[idx][io]);
+			iostat_lat[idx][io].cnt = io_lat->bio_cnt[idx][io];
+			iostat_lat[idx][io].avg_lat = iostat_lat[idx][io].cnt ?
+			   jiffies_to_msecs(io_lat->sum_lat[idx][io]) / iostat_lat[idx][io].cnt : 0;
+			io_lat->sum_lat[idx][io] = 0;
+			io_lat->peak_lat[idx][io] = 0;
+			io_lat->bio_cnt[idx][io] = 0;
+		}
+	}
+	spin_unlock_irqrestore(&sbi->iostat_lat_lock, flags);
+
+	trace_f2fs_iostat_latency(sbi, iostat_lat);
+}
+
+static inline void f2fs_record_iostat(struct f2fs_sb_info *sbi)
+{
+	unsigned long long iostat_diff[NR_IO_TYPE];
+	unsigned long long read_folio_count_diff[NR_PAGE_ORDERS];
+	int i;
+	unsigned long flags;
+
+	if (time_is_after_jiffies(sbi->iostat_next_period))
+		return;
+
+	/* Need double check under the lock */
+	spin_lock_irqsave(&sbi->iostat_lock, flags);
+	if (time_is_after_jiffies(sbi->iostat_next_period)) {
+		spin_unlock_irqrestore(&sbi->iostat_lock, flags);
+		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->iostat_bytes[i] -
+				sbi->prev_iostat_bytes[i];
+		sbi->prev_iostat_bytes[i] = sbi->iostat_bytes[i];
+	}
+
+	for (i = 0; i < NR_PAGE_ORDERS; i++) {
+		read_folio_count_diff[i] = sbi->iostat_read_folio_count[i] -
+					sbi->prev_iostat_read_folio_count[i];
+		sbi->prev_iostat_read_folio_count[i] = sbi->iostat_read_folio_count[i];
+	}
+	spin_unlock_irqrestore(&sbi->iostat_lock, flags);
+
+	trace_f2fs_iostat(sbi, iostat_diff, read_folio_count_diff);
+
+	__record_iostat_latency(sbi);
+}
+
+void f2fs_reset_iostat(struct f2fs_sb_info *sbi)
+{
+	struct iostat_lat_info *io_lat = sbi->iostat_io_lat;
+	int i;
+
+	spin_lock_irq(&sbi->iostat_lock);
+	for (i = 0; i < NR_IO_TYPE; i++) {
+		sbi->iostat_count[i] = 0;
+		sbi->iostat_bytes[i] = 0;
+		sbi->prev_iostat_bytes[i] = 0;
+	}
+	for (i = 0; i < NR_PAGE_ORDERS; i++) {
+		sbi->iostat_read_folio_count[i] = 0;
+		sbi->prev_iostat_read_folio_count[i] = 0;
+	}
+	spin_unlock_irq(&sbi->iostat_lock);
+
+	spin_lock_irq(&sbi->iostat_lat_lock);
+	memset(io_lat, 0, sizeof(struct iostat_lat_info));
+	spin_unlock_irq(&sbi->iostat_lat_lock);
+}
+
+static inline void __f2fs_update_iostat(struct f2fs_sb_info *sbi,
+			enum iostat_type type, unsigned long long io_bytes)
+{
+	sbi->iostat_bytes[type] += io_bytes;
+	sbi->iostat_count[type]++;
+}
+
+void f2fs_update_read_folio_count(struct f2fs_sb_info *sbi, struct folio *folio)
+{
+	unsigned int order = folio_order(folio);
+	unsigned long flags;
+
+	if (!sbi->iostat_enable)
+		return;
+
+	if (order >= NR_PAGE_ORDERS)
+		order = NR_PAGE_ORDERS - 1;
+
+	spin_lock_irqsave(&sbi->iostat_lock, flags);
+	sbi->iostat_read_folio_count[order]++;
+	spin_unlock_irqrestore(&sbi->iostat_lock, flags);
+
+	f2fs_record_iostat(sbi);
+}
+
+void f2fs_update_iostat(struct f2fs_sb_info *sbi, struct inode *inode,
+			enum iostat_type type, unsigned long long io_bytes)
+{
+	unsigned long flags;
+
+	if (!sbi->iostat_enable)
+		return;
+
+	spin_lock_irqsave(&sbi->iostat_lock, flags);
+	__f2fs_update_iostat(sbi, type, io_bytes);
+
+	if (type == APP_BUFFERED_IO || type == APP_DIRECT_IO)
+		__f2fs_update_iostat(sbi, APP_WRITE_IO, io_bytes);
+
+	if (type == APP_BUFFERED_READ_IO || type == APP_DIRECT_READ_IO)
+		__f2fs_update_iostat(sbi, APP_READ_IO, io_bytes);
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (inode && f2fs_compressed_file(inode)) {
+		if (type == APP_BUFFERED_IO)
+			__f2fs_update_iostat(sbi, APP_BUFFERED_CDATA_IO, io_bytes);
+
+		if (type == APP_BUFFERED_READ_IO)
+			__f2fs_update_iostat(sbi, APP_BUFFERED_CDATA_READ_IO, io_bytes);
+
+		if (type == APP_MAPPED_READ_IO)
+			__f2fs_update_iostat(sbi, APP_MAPPED_CDATA_READ_IO, io_bytes);
+
+		if (type == APP_MAPPED_IO)
+			__f2fs_update_iostat(sbi, APP_MAPPED_CDATA_IO, io_bytes);
+
+		if (type == FS_DATA_READ_IO)
+			__f2fs_update_iostat(sbi, FS_CDATA_READ_IO, io_bytes);
+
+		if (type == FS_DATA_IO)
+			__f2fs_update_iostat(sbi, FS_CDATA_IO, io_bytes);
+	}
+#endif
+
+	spin_unlock_irqrestore(&sbi->iostat_lock, flags);
+
+	f2fs_record_iostat(sbi);
+}
+
+static inline void __update_iostat_latency(struct bio_iostat_ctx *iostat_ctx,
+				enum iostat_lat_type lat_type)
+{
+	unsigned long ts_diff;
+	unsigned int page_type = iostat_ctx->type;
+	struct f2fs_sb_info *sbi = iostat_ctx->sbi;
+	struct iostat_lat_info *io_lat = sbi->iostat_io_lat;
+	unsigned long flags;
+
+	if (!sbi->iostat_enable)
+		return;
+
+	ts_diff = jiffies - iostat_ctx->submit_ts;
+	if (page_type == META_FLUSH) {
+		page_type = META;
+	} else if (page_type >= NR_PAGE_TYPE) {
+		f2fs_warn(sbi, "%s: %d over NR_PAGE_TYPE", __func__, page_type);
+		return;
+	}
+
+	spin_lock_irqsave(&sbi->iostat_lat_lock, flags);
+	io_lat->sum_lat[lat_type][page_type] += ts_diff;
+	io_lat->bio_cnt[lat_type][page_type]++;
+	if (ts_diff > io_lat->peak_lat[lat_type][page_type])
+		io_lat->peak_lat[lat_type][page_type] = ts_diff;
+	spin_unlock_irqrestore(&sbi->iostat_lat_lock, flags);
+}
+
+void iostat_update_and_unbind_ctx(struct bio *bio)
+{
+	struct bio_iostat_ctx *iostat_ctx = bio->bi_private;
+	enum iostat_lat_type lat_type;
+
+	if (op_is_write(bio_op(bio))) {
+		lat_type = bio->bi_opf & REQ_SYNC ?
+				WRITE_SYNC_IO : WRITE_ASYNC_IO;
+		bio->bi_private = iostat_ctx->sbi;
+	} else {
+		lat_type = READ_IO;
+		bio->bi_private = iostat_ctx->post_read_ctx;
+	}
+
+	__update_iostat_latency(iostat_ctx, lat_type);
+	mempool_free(iostat_ctx, bio_iostat_ctx_pool);
+}
+
+void iostat_alloc_and_bind_ctx(struct f2fs_sb_info *sbi,
+		struct bio *bio, struct bio_post_read_ctx *ctx)
+{
+	struct bio_iostat_ctx *iostat_ctx;
+	/* Due to the mempool, this never fails. */
+	iostat_ctx = mempool_alloc(bio_iostat_ctx_pool, GFP_NOFS);
+	iostat_ctx->sbi = sbi;
+	iostat_ctx->submit_ts = 0;
+	iostat_ctx->type = 0;
+	iostat_ctx->post_read_ctx = ctx;
+	bio->bi_private = iostat_ctx;
+}
+
+int __init f2fs_init_iostat_processing(void)
+{
+	bio_iostat_ctx_cache =
+		kmem_cache_create("f2fs_bio_iostat_ctx",
+				  sizeof(struct bio_iostat_ctx), 0, 0, NULL);
+	if (!bio_iostat_ctx_cache)
+		goto fail;
+	bio_iostat_ctx_pool =
+		mempool_create_slab_pool(NUM_PREALLOC_IOSTAT_CTXS,
+					 bio_iostat_ctx_cache);
+	if (!bio_iostat_ctx_pool)
+		goto fail_free_cache;
+	return 0;
+
+fail_free_cache:
+	kmem_cache_destroy(bio_iostat_ctx_cache);
+fail:
+	return -ENOMEM;
+}
+
+void f2fs_destroy_iostat_processing(void)
+{
+	mempool_destroy(bio_iostat_ctx_pool);
+	kmem_cache_destroy(bio_iostat_ctx_cache);
+}
+
+int f2fs_init_iostat(struct f2fs_sb_info *sbi)
+{
+	/* init iostat info */
+	spin_lock_init(&sbi->iostat_lock);
+	spin_lock_init(&sbi->iostat_lat_lock);
+	sbi->iostat_enable = false;
+	sbi->iostat_period_ms = DEFAULT_IOSTAT_PERIOD_MS;
+	sbi->iostat_io_lat = f2fs_kzalloc(sbi, sizeof(struct iostat_lat_info),
+					GFP_KERNEL);
+	if (!sbi->iostat_io_lat)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void f2fs_destroy_iostat(struct f2fs_sb_info *sbi)
+{
+	kfree(sbi->iostat_io_lat);
+}

linux-7.2.3/fs/f2fs/iostat.h

@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2021 Google LLC
+ * Author: Daeho Jeong <daehojeong@google.com>
+ */
+#ifndef __F2FS_IOSTAT_H__
+#define __F2FS_IOSTAT_H__
+
+struct bio_post_read_ctx;
+
+enum iostat_lat_type {
+	READ_IO = 0,
+	WRITE_SYNC_IO,
+	WRITE_ASYNC_IO,
+	MAX_IO_TYPE,
+};
+
+#ifdef CONFIG_F2FS_IOSTAT
+
+#define NUM_PREALLOC_IOSTAT_CTXS	128
+#define DEFAULT_IOSTAT_PERIOD_MS	3000
+#define MIN_IOSTAT_PERIOD_MS		100
+/* maximum period of iostat tracing is 1 day */
+#define MAX_IOSTAT_PERIOD_MS		8640000
+
+struct iostat_lat_info {
+	unsigned long sum_lat[MAX_IO_TYPE][NR_PAGE_TYPE];	/* sum of io latencies */
+	unsigned long peak_lat[MAX_IO_TYPE][NR_PAGE_TYPE];	/* peak io latency */
+	unsigned int bio_cnt[MAX_IO_TYPE][NR_PAGE_TYPE];	/* bio count */
+};
+
+extern int __maybe_unused iostat_info_seq_show(struct seq_file *seq,
+			void *offset);
+extern void f2fs_reset_iostat(struct f2fs_sb_info *sbi);
+extern void f2fs_update_iostat(struct f2fs_sb_info *sbi, struct inode *inode,
+			enum iostat_type type, unsigned long long io_bytes);
+extern void f2fs_update_read_folio_count(struct f2fs_sb_info *sbi,
+			struct folio *folio);
+
+struct bio_iostat_ctx {
+	struct f2fs_sb_info *sbi;
+	unsigned long submit_ts;
+	enum page_type type;
+	struct bio_post_read_ctx *post_read_ctx;
+};
+
+static inline void iostat_update_submit_ctx(struct bio *bio,
+			enum page_type type)
+{
+	struct bio_iostat_ctx *iostat_ctx = bio->bi_private;
+
+	iostat_ctx->submit_ts = jiffies;
+	iostat_ctx->type = type;
+}
+
+static inline struct bio_post_read_ctx *get_post_read_ctx(struct bio *bio)
+{
+	struct bio_iostat_ctx *iostat_ctx = bio->bi_private;
+
+	return iostat_ctx->post_read_ctx;
+}
+
+extern void iostat_update_and_unbind_ctx(struct bio *bio);
+extern void iostat_alloc_and_bind_ctx(struct f2fs_sb_info *sbi,
+		struct bio *bio, struct bio_post_read_ctx *ctx);
+extern int f2fs_init_iostat_processing(void);
+extern void f2fs_destroy_iostat_processing(void);
+extern int f2fs_init_iostat(struct f2fs_sb_info *sbi);
+extern void f2fs_destroy_iostat(struct f2fs_sb_info *sbi);
+#else
+static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi, struct inode *inode,
+		enum iostat_type type, unsigned long long io_bytes) {}
+static inline void f2fs_update_read_folio_count(struct f2fs_sb_info *sbi,
+		struct folio *folio) {}
+static inline void iostat_update_and_unbind_ctx(struct bio *bio) {}
+static inline void iostat_alloc_and_bind_ctx(struct f2fs_sb_info *sbi,
+		struct bio *bio, struct bio_post_read_ctx *ctx) {}
+static inline void iostat_update_submit_ctx(struct bio *bio,
+		enum page_type type) {}
+static inline struct bio_post_read_ctx *get_post_read_ctx(struct bio *bio)
+{
+	return bio->bi_private;
+}
+static inline int f2fs_init_iostat_processing(void) { return 0; }
+static inline void f2fs_destroy_iostat_processing(void) {}
+static inline int f2fs_init_iostat(struct f2fs_sb_info *sbi) { return 0; }
+static inline void f2fs_destroy_iostat(struct f2fs_sb_info *sbi) {}
+#endif
+#endif /* __F2FS_IOSTAT_H__ */

linux-7.2.3/fs/f2fs/node.h

@@ -0,0 +1,433 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * fs/f2fs/node.h
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ */
+/* start node id of a node block dedicated to the given node id */
+#define	START_NID(nid) (((nid) / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK)
+
+/* node block offset on the NAT area dedicated to the given start node id */
+#define	NAT_BLOCK_OFFSET(start_nid) ((start_nid) / NAT_ENTRY_PER_BLOCK)
+
+/* # of pages to perform synchronous readahead before building free nids */
+#define FREE_NID_PAGES	8
+#define MAX_FREE_NIDS	(NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES)
+
+/* size of free nid batch when shrinking */
+#define SHRINK_NID_BATCH_SIZE	8
+
+#define DEF_RA_NID_PAGES	0	/* # of nid pages to be readaheaded */
+
+/* maximum readahead size for node during getting data blocks */
+#define MAX_RA_NODE		128
+
+/* control the memory footprint threshold (10MB per 1GB ram) */
+#define DEF_RAM_THRESHOLD	1
+
+/* control dirty nats ratio threshold (default: 10% over max nid count) */
+#define DEF_DIRTY_NAT_RATIO_THRESHOLD		10
+/* control total # of nats */
+#define DEF_NAT_CACHE_THRESHOLD			100000
+
+/* control total # of node writes used for roll-forward recovery */
+#define DEF_RF_NODE_BLOCKS			0
+
+/* vector size for gang look-up from nat cache that consists of radix tree */
+#define NAT_VEC_SIZE	32
+
+/* return value for read_node_page */
+#define LOCKED_PAGE	1
+
+/* check pinned file's alignment status of physical blocks */
+#define FILE_NOT_ALIGNED	1
+
+/* For flag in struct node_info */
+enum {
+	IS_CHECKPOINTED,	/* is it checkpointed before? */
+	HAS_FSYNCED_INODE,	/* is the inode fsynced before? */
+	HAS_LAST_FSYNC,		/* has the latest node fsync mark? */
+	IS_DIRTY,		/* this nat entry is dirty? */
+	IS_PREALLOC,		/* nat entry is preallocated */
+};
+
+/*
+ * For node information
+ */
+struct node_info {
+	nid_t nid;		/* node id */
+	nid_t ino;		/* inode number of the node's owner */
+	block_t	blk_addr;	/* block address of the node */
+	unsigned char version;	/* version of the node */
+	unsigned char flag;	/* for node information bits */
+};
+
+struct nat_entry {
+	struct list_head list;	/* for clean or dirty nat list */
+	struct node_info ni;	/* in-memory node information */
+};
+
+#define nat_get_nid(nat)		((nat)->ni.nid)
+#define nat_set_nid(nat, n)		((nat)->ni.nid = (n))
+#define nat_get_blkaddr(nat)		((nat)->ni.blk_addr)
+#define nat_set_blkaddr(nat, b)		((nat)->ni.blk_addr = (b))
+#define nat_get_ino(nat)		((nat)->ni.ino)
+#define nat_set_ino(nat, i)		((nat)->ni.ino = (i))
+#define nat_get_version(nat)		((nat)->ni.version)
+#define nat_set_version(nat, v)		((nat)->ni.version = (v))
+
+#define inc_node_version(version)	(++(version))
+
+static inline void copy_node_info(struct node_info *dst,
+						struct node_info *src)
+{
+	dst->nid = src->nid;
+	dst->ino = src->ino;
+	dst->blk_addr = src->blk_addr;
+	dst->version = src->version;
+	/* should not copy flag here */
+}
+
+static inline void set_nat_flag(struct nat_entry *ne,
+				unsigned int type, bool set)
+{
+	if (set)
+		ne->ni.flag |= BIT(type);
+	else
+		ne->ni.flag &= ~BIT(type);
+}
+
+static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type)
+{
+	return ne->ni.flag & BIT(type);
+}
+
+static inline void nat_reset_flag(struct nat_entry *ne)
+{
+	/* these states can be set only after checkpoint was done */
+	set_nat_flag(ne, IS_CHECKPOINTED, true);
+	set_nat_flag(ne, HAS_FSYNCED_INODE, false);
+	set_nat_flag(ne, HAS_LAST_FSYNC, true);
+}
+
+static inline void node_info_from_raw_nat(struct node_info *ni,
+						struct f2fs_nat_entry *raw_ne)
+{
+	ni->ino = le32_to_cpu(raw_ne->ino);
+	ni->blk_addr = le32_to_cpu(raw_ne->block_addr);
+	ni->version = raw_ne->version;
+}
+
+static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,
+						struct node_info *ni)
+{
+	raw_ne->ino = cpu_to_le32(ni->ino);
+	raw_ne->block_addr = cpu_to_le32(ni->blk_addr);
+	raw_ne->version = ni->version;
+}
+
+static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi)
+{
+	/* nat_cnt[] is heuristic accounting sampled locklessly here. */
+	return data_race(READ_ONCE(NM_I(sbi)->nat_cnt[DIRTY_NAT])) >=
+					NM_I(sbi)->max_nid *
+					NM_I(sbi)->dirty_nats_ratio / 100;
+}
+
+static inline bool excess_cached_nats(struct f2fs_sb_info *sbi)
+{
+	/* nat_cnt[] is heuristic accounting sampled locklessly here. */
+	return data_race(READ_ONCE(NM_I(sbi)->nat_cnt[TOTAL_NAT])) >=
+					DEF_NAT_CACHE_THRESHOLD;
+}
+
+enum mem_type {
+	FREE_NIDS,	/* indicates the free nid list */
+	NAT_ENTRIES,	/* indicates the cached nat entry */
+	DIRTY_DENTS,	/* indicates dirty dentry pages */
+	INO_ENTRIES,	/* indicates inode entries */
+	READ_EXTENT_CACHE,	/* indicates read extent cache */
+	AGE_EXTENT_CACHE,	/* indicates age extent cache */
+	DISCARD_CACHE,	/* indicates memory of cached discard cmds */
+	COMPRESS_PAGE,	/* indicates memory of cached compressed pages */
+	BASE_CHECK,	/* check kernel status */
+};
+
+struct nat_entry_set {
+	struct list_head set_list;	/* link with other nat sets */
+	struct list_head entry_list;	/* link with dirty nat entries */
+	nid_t set;			/* set number*/
+	unsigned int entry_cnt;		/* the # of nat entries in set */
+};
+
+struct free_nid {
+	struct list_head list;	/* for free node id list */
+	nid_t nid;		/* node id */
+	int state;		/* in use or not: FREE_NID or PREALLOC_NID */
+};
+
+static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	struct free_nid *fnid;
+
+	spin_lock(&nm_i->nid_list_lock);
+	if (nm_i->nid_cnt[FREE_NID] <= 0) {
+		spin_unlock(&nm_i->nid_list_lock);
+		return;
+	}
+	fnid = list_first_entry(&nm_i->free_nid_list, struct free_nid, list);
+	*nid = fnid->nid;
+	spin_unlock(&nm_i->nid_list_lock);
+}
+
+/*
+ * inline functions
+ */
+static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+	if (memcmp(nm_i->nat_bitmap, nm_i->nat_bitmap_mir,
+						nm_i->bitmap_size))
+		f2fs_bug_on(sbi, 1);
+#endif
+	memcpy(addr, nm_i->nat_bitmap, nm_i->bitmap_size);
+}
+
+static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	pgoff_t block_off;
+	pgoff_t block_addr;
+
+	/*
+	 * block_off = segment_off * 512 + off_in_segment
+	 * OLD = (segment_off * 512) * 2 + off_in_segment
+	 * NEW = 2 * (segment_off * 512 + off_in_segment) - off_in_segment
+	 */
+	block_off = NAT_BLOCK_OFFSET(start);
+
+	block_addr = (pgoff_t)(nm_i->nat_blkaddr +
+		(block_off << 1) -
+		(block_off & (BLKS_PER_SEG(sbi) - 1)));
+
+	if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
+		block_addr += BLKS_PER_SEG(sbi);
+
+	return block_addr;
+}
+
+static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi,
+						pgoff_t block_addr)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+	block_addr -= nm_i->nat_blkaddr;
+	block_addr ^= BIT(sbi->log_blocks_per_seg);
+	return block_addr + nm_i->nat_blkaddr;
+}
+
+static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
+{
+	unsigned int block_off = NAT_BLOCK_OFFSET(start_nid);
+
+	f2fs_change_bit(block_off, nm_i->nat_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+	f2fs_change_bit(block_off, nm_i->nat_bitmap_mir);
+#endif
+}
+
+static inline nid_t ino_of_node(const struct folio *node_folio)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_folio);
+	return le32_to_cpu(rn->footer.ino);
+}
+
+static inline nid_t nid_of_node(const struct folio *node_folio)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_folio);
+	return le32_to_cpu(rn->footer.nid);
+}
+
+static inline unsigned int ofs_of_node(const struct folio *node_folio)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_folio);
+	unsigned flag = le32_to_cpu(rn->footer.flag);
+	return flag >> OFFSET_BIT_SHIFT;
+}
+
+static inline __u64 cpver_of_node(const struct folio *node_folio)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_folio);
+	return le64_to_cpu(rn->footer.cp_ver);
+}
+
+static inline block_t next_blkaddr_of_node(const struct folio *node_folio)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_folio);
+	return le32_to_cpu(rn->footer.next_blkaddr);
+}
+
+static inline void fill_node_footer(const struct folio *folio, nid_t nid,
+				nid_t ino, unsigned int ofs, bool reset)
+{
+	struct f2fs_node *rn = F2FS_NODE(folio);
+	unsigned int old_flag = 0;
+
+	if (reset)
+		memset(rn, 0, sizeof(*rn));
+	else
+		old_flag = le32_to_cpu(rn->footer.flag);
+
+	rn->footer.nid = cpu_to_le32(nid);
+	rn->footer.ino = cpu_to_le32(ino);
+
+	/* should remain old flag bits such as COLD_BIT_SHIFT */
+	rn->footer.flag = cpu_to_le32((ofs << OFFSET_BIT_SHIFT) |
+					(old_flag & OFFSET_BIT_MASK));
+}
+
+static inline void copy_node_footer(const struct folio *dst,
+		const struct folio *src)
+{
+	struct f2fs_node *src_rn = F2FS_NODE(src);
+	struct f2fs_node *dst_rn = F2FS_NODE(dst);
+	memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer));
+}
+
+static inline void fill_node_footer_blkaddr(struct folio *folio, block_t blkaddr)
+{
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_F_SB(folio));
+	struct f2fs_node *rn = F2FS_NODE(folio);
+	__u64 cp_ver = cur_cp_version(ckpt);
+
+	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
+		cp_ver |= (cur_cp_crc(ckpt) << 32);
+
+	rn->footer.cp_ver = cpu_to_le64(cp_ver);
+	rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
+}
+
+static inline bool is_recoverable_dnode(const struct folio *folio)
+{
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_F_SB(folio));
+	__u64 cp_ver = cur_cp_version(ckpt);
+
+	/* Don't care crc part, if fsck.f2fs sets it. */
+	if (__is_set_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG))
+		return (cp_ver << 32) == (cpver_of_node(folio) << 32);
+
+	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
+		cp_ver |= (cur_cp_crc(ckpt) << 32);
+
+	return cp_ver == cpver_of_node(folio);
+}
+
+/*
+ * f2fs assigns the following node offsets described as (num).
+ * N = NIDS_PER_BLOCK
+ *
+ *  Inode block (0)
+ *    |- direct node (1)
+ *    |- direct node (2)
+ *    |- indirect node (3)
+ *    |            `- direct node (4 => 4 + N - 1)
+ *    |- indirect node (4 + N)
+ *    |            `- direct node (5 + N => 5 + 2N - 1)
+ *    `- double indirect node (5 + 2N)
+ *                 `- indirect node (6 + 2N)
+ *                       `- direct node
+ *                 ......
+ *                 `- indirect node ((6 + 2N) + x(N + 1))
+ *                       `- direct node
+ *                 ......
+ *                 `- indirect node ((6 + 2N) + (N - 1)(N + 1))
+ *                       `- direct node
+ */
+static inline bool IS_DNODE(const struct folio *node_folio)
+{
+	unsigned int ofs = ofs_of_node(node_folio);
+
+	if (f2fs_has_xattr_block(ofs))
+		return true;
+
+	if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK ||
+			ofs == 5 + 2 * NIDS_PER_BLOCK)
+		return false;
+	if (ofs >= 6 + 2 * NIDS_PER_BLOCK) {
+		ofs -= 6 + 2 * NIDS_PER_BLOCK;
+		if (!((long int)ofs % (NIDS_PER_BLOCK + 1)))
+			return false;
+	}
+	return true;
+}
+
+static inline int set_nid(struct folio *folio, int off, nid_t nid, bool i)
+{
+	struct f2fs_node *rn = F2FS_NODE(folio);
+
+	f2fs_folio_wait_writeback(folio, NODE, true, true);
+
+	if (i)
+		rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
+	else
+		rn->in.nid[off] = cpu_to_le32(nid);
+	return folio_mark_dirty(folio);
+}
+
+static inline nid_t get_nid(const struct folio *folio, int off, bool i)
+{
+	struct f2fs_node *rn = F2FS_NODE(folio);
+
+	if (i)
+		return le32_to_cpu(rn->i.i_nid[off - NODE_DIR1_BLOCK]);
+	return le32_to_cpu(rn->in.nid[off]);
+}
+
+/*
+ * Coldness identification:
+ *  - Mark cold files in f2fs_inode_info
+ *  - Mark cold node blocks in their node footer
+ *  - Mark cold data pages in page cache
+ */
+
+static inline int is_node(const struct folio *folio, int type)
+{
+	struct f2fs_node *rn = F2FS_NODE(folio);
+	return le32_to_cpu(rn->footer.flag) & BIT(type);
+}
+
+#define is_cold_node(folio)	is_node(folio, COLD_BIT_SHIFT)
+#define is_fsync_dnode(folio)	is_node(folio, FSYNC_BIT_SHIFT)
+#define is_dent_dnode(folio)	is_node(folio, DENT_BIT_SHIFT)
+
+static inline void __set_mark(const struct folio *folio, bool mark, int type)
+{
+	struct f2fs_node *rn = F2FS_NODE(folio);
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+
+	if (mark)
+		flag |= BIT(type);
+	else
+		flag &= ~BIT(type);
+	rn->footer.flag = cpu_to_le32(flag);
+}
+
+static inline void set_cold_node(const struct folio *folio, bool is_dir)
+{
+	__set_mark(folio, !is_dir, COLD_BIT_SHIFT);
+}
+
+static inline void set_mark(struct folio *folio, bool mark, int type)
+{
+	__set_mark(folio, mark, type);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+	f2fs_inode_chksum_set(F2FS_F_SB(folio), folio);
+#endif
+}
+#define set_dentry_mark(folio, mark)	set_mark(folio, mark, DENT_BIT_SHIFT)
+#define set_fsync_mark(folio, mark)	set_mark(folio, mark, FSYNC_BIT_SHIFT)

linux-7.2.3/fs/f2fs/recovery.c

@@ -0,0 +1,970 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fs/f2fs/recovery.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ */
+#include <linux/unaligned.h>
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/sched/mm.h>
+#include <linux/fserror.h>
+#include "f2fs.h"
+#include "node.h"
+#include "segment.h"
+
+/*
+ * Roll forward recovery scenarios.
+ *
+ * [Term] F: fsync_mark, D: dentry_mark
+ *
+ * 1. inode(x) | CP | inode(x) | dnode(F)
+ * -> Update the latest inode(x).
+ *
+ * 2. inode(x) | CP | inode(F) | dnode(F)
+ * -> No problem.
+ *
+ * 3. inode(x) | CP | dnode(F) | inode(x)
+ * -> Recover to the latest dnode(F), and drop the last inode(x)
+ *
+ * 4. inode(x) | CP | dnode(F) | inode(F)
+ * -> No problem.
+ *
+ * 5. CP | inode(x) | dnode(F)
+ * -> The inode(DF) was missing. Should drop this dnode(F).
+ *
+ * 6. CP | inode(DF) | dnode(F)
+ * -> No problem.
+ *
+ * 7. CP | dnode(F) | inode(DF)
+ * -> If f2fs_iget fails, then goto next to find inode(DF).
+ *
+ * 8. CP | dnode(F) | inode(x)
+ * -> If f2fs_iget fails, then goto next to find inode(DF).
+ *    But it will fail due to no inode(DF).
+ */
+
+static struct kmem_cache *fsync_entry_slab;
+
+bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi)
+{
+	s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count);
+
+	if (sbi->last_valid_block_count + nalloc > sbi->user_block_count)
+		return false;
+	if (NM_I(sbi)->max_rf_node_blocks &&
+		percpu_counter_sum_positive(&sbi->rf_node_block_count) >=
+						NM_I(sbi)->max_rf_node_blocks)
+		return false;
+	return true;
+}
+
+static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
+								nid_t ino)
+{
+	struct fsync_inode_entry *entry;
+
+	list_for_each_entry(entry, head, list)
+		if (entry->inode->i_ino == ino)
+			return entry;
+
+	return NULL;
+}
+
+static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi,
+			struct list_head *head, nid_t ino, bool quota_inode)
+{
+	struct inode *inode;
+	struct fsync_inode_entry *entry;
+	int err;
+
+	inode = f2fs_iget_retry(sbi->sb, ino);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+	err = f2fs_dquot_initialize(inode);
+	if (err)
+		goto err_out;
+
+	if (quota_inode) {
+		err = dquot_alloc_inode(inode);
+		if (err)
+			goto err_out;
+	}
+
+	entry = f2fs_kmem_cache_alloc(fsync_entry_slab,
+					GFP_F2FS_ZERO, true, NULL);
+	entry->inode = inode;
+	list_add_tail(&entry->list, head);
+
+	return entry;
+err_out:
+	iput(inode);
+	return ERR_PTR(err);
+}
+
+static void del_fsync_inode(struct fsync_inode_entry *entry, int drop)
+{
+	if (drop) {
+		/* inode should not be recovered, drop it */
+		f2fs_inode_synced(entry->inode);
+	}
+	iput(entry->inode);
+	list_del(&entry->list);
+	kmem_cache_free(fsync_entry_slab, entry);
+}
+
+static int init_recovered_filename(const struct inode *dir,
+				   struct f2fs_inode *raw_inode,
+				   struct f2fs_filename *fname,
+				   struct qstr *usr_fname)
+{
+	int err;
+
+	memset(fname, 0, sizeof(*fname));
+	fname->disk_name.len = le32_to_cpu(raw_inode->i_namelen);
+	fname->disk_name.name = raw_inode->i_name;
+
+	if (WARN_ON(fname->disk_name.len > F2FS_NAME_LEN))
+		return -ENAMETOOLONG;
+
+	if (!IS_ENCRYPTED(dir)) {
+		usr_fname->name = fname->disk_name.name;
+		usr_fname->len = fname->disk_name.len;
+		fname->usr_fname = usr_fname;
+	}
+
+	/* Compute the hash of the filename */
+	if (IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir)) {
+		/*
+		 * In this case the hash isn't computable without the key, so it
+		 * was saved on-disk.
+		 */
+		if (fname->disk_name.len + sizeof(f2fs_hash_t) > F2FS_NAME_LEN)
+			return -EINVAL;
+		fname->hash = get_unaligned((f2fs_hash_t *)
+				&raw_inode->i_name[fname->disk_name.len]);
+	} else if (IS_CASEFOLDED(dir)) {
+		err = f2fs_init_casefolded_name(dir, fname);
+		if (err)
+			return err;
+		f2fs_hash_filename(dir, fname);
+		/* Case-sensitive match is fine for recovery */
+		f2fs_free_casefolded_name(fname);
+	} else {
+		f2fs_hash_filename(dir, fname);
+	}
+	return 0;
+}
+
+static int recover_dentry(struct inode *inode, struct folio *ifolio,
+						struct list_head *dir_list)
+{
+	struct f2fs_inode *raw_inode = F2FS_INODE(ifolio);
+	nid_t pino = le32_to_cpu(raw_inode->i_pino);
+	struct f2fs_dir_entry *de;
+	struct f2fs_filename fname;
+	struct qstr usr_fname;
+	struct folio *folio;
+	struct inode *dir, *einode;
+	struct fsync_inode_entry *entry;
+	int err = 0;
+	char *name;
+
+	entry = get_fsync_inode(dir_list, pino);
+	if (!entry) {
+		entry = add_fsync_inode(F2FS_I_SB(inode), dir_list,
+							pino, false);
+		if (IS_ERR(entry)) {
+			dir = ERR_CAST(entry);
+			err = PTR_ERR(entry);
+			goto out;
+		}
+	}
+
+	dir = entry->inode;
+	err = init_recovered_filename(dir, raw_inode, &fname, &usr_fname);
+	if (err)
+		goto out;
+retry:
+	de = __f2fs_find_entry(dir, &fname, &folio);
+	if (de && inode->i_ino == le32_to_cpu(de->ino))
+		goto out_put;
+
+	if (de) {
+		einode = f2fs_iget_retry(inode->i_sb, le32_to_cpu(de->ino));
+		if (IS_ERR(einode)) {
+			WARN_ON(1);
+			err = PTR_ERR(einode);
+			if (err == -ENOENT)
+				err = -EEXIST;
+			goto out_put;
+		}
+
+		err = f2fs_dquot_initialize(einode);
+		if (err) {
+			iput(einode);
+			goto out_put;
+		}
+
+		err = f2fs_acquire_orphan_inode(F2FS_I_SB(inode));
+		if (err) {
+			iput(einode);
+			goto out_put;
+		}
+		f2fs_delete_entry(de, folio, dir, einode);
+		iput(einode);
+		goto retry;
+	} else if (IS_ERR(folio)) {
+		err = PTR_ERR(folio);
+	} else {
+		err = f2fs_add_dentry(dir, &fname, inode,
+					inode->i_ino, inode->i_mode);
+	}
+	if (err == -ENOMEM)
+		goto retry;
+	goto out;
+
+out_put:
+	f2fs_folio_put(folio, false);
+out:
+	if (file_enc_name(inode))
+		name = "<encrypted>";
+	else
+		name = raw_inode->i_name;
+	f2fs_notice(F2FS_I_SB(inode), "%s: ino = %x, name = %s, dir = %llu, err = %d",
+		    __func__, ino_of_node(ifolio), name,
+		    IS_ERR(dir) ? 0 : dir->i_ino, err);
+	return err;
+}
+
+static int recover_quota_data(struct inode *inode, struct folio *folio)
+{
+	struct f2fs_inode *raw = F2FS_INODE(folio);
+	struct iattr attr;
+	uid_t i_uid = le32_to_cpu(raw->i_uid);
+	gid_t i_gid = le32_to_cpu(raw->i_gid);
+	int err;
+
+	memset(&attr, 0, sizeof(attr));
+
+	attr.ia_vfsuid = VFSUIDT_INIT(make_kuid(inode->i_sb->s_user_ns, i_uid));
+	attr.ia_vfsgid = VFSGIDT_INIT(make_kgid(inode->i_sb->s_user_ns, i_gid));
+
+	if (!vfsuid_eq(attr.ia_vfsuid, i_uid_into_vfsuid(&nop_mnt_idmap, inode)))
+		attr.ia_valid |= ATTR_UID;
+	if (!vfsgid_eq(attr.ia_vfsgid, i_gid_into_vfsgid(&nop_mnt_idmap, inode)))
+		attr.ia_valid |= ATTR_GID;
+
+	if (!attr.ia_valid)
+		return 0;
+
+	err = dquot_transfer(&nop_mnt_idmap, inode, &attr);
+	if (err)
+		set_sbi_flag(F2FS_I_SB(inode), SBI_QUOTA_NEED_REPAIR);
+	return err;
+}
+
+static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri)
+{
+	if (ri->i_inline & F2FS_PIN_FILE)
+		set_inode_flag(inode, FI_PIN_FILE);
+	else
+		clear_inode_flag(inode, FI_PIN_FILE);
+	if (ri->i_inline & F2FS_DATA_EXIST)
+		set_inode_flag(inode, FI_DATA_EXIST);
+	else
+		clear_inode_flag(inode, FI_DATA_EXIST);
+}
+
+static int recover_inode(struct inode *inode, struct folio *folio)
+{
+	struct f2fs_inode *raw = F2FS_INODE(folio);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	char *name;
+	int err;
+
+	inode->i_mode = le16_to_cpu(raw->i_mode);
+
+	err = recover_quota_data(inode, folio);
+	if (err)
+		return err;
+
+	i_uid_write(inode, le32_to_cpu(raw->i_uid));
+	i_gid_write(inode, le32_to_cpu(raw->i_gid));
+
+	if (raw->i_inline & F2FS_EXTRA_ATTR) {
+		if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)) &&
+			F2FS_FITS_IN_INODE(raw, le16_to_cpu(raw->i_extra_isize),
+								i_projid)) {
+			projid_t i_projid;
+			kprojid_t kprojid;
+
+			i_projid = (projid_t)le32_to_cpu(raw->i_projid);
+			kprojid = make_kprojid(&init_user_ns, i_projid);
+
+			if (!projid_eq(kprojid, fi->i_projid)) {
+				err = f2fs_transfer_project_quota(inode,
+								kprojid);
+				if (err)
+					return err;
+				fi->i_projid = kprojid;
+			}
+		}
+	}
+
+	f2fs_i_size_write(inode, le64_to_cpu(raw->i_size));
+	inode_set_atime(inode, le64_to_cpu(raw->i_atime),
+			le32_to_cpu(raw->i_atime_nsec));
+	inode_set_ctime(inode, le64_to_cpu(raw->i_ctime),
+			le32_to_cpu(raw->i_ctime_nsec));
+	inode_set_mtime(inode, le64_to_cpu(raw->i_mtime),
+			le32_to_cpu(raw->i_mtime_nsec));
+
+	fi->i_advise = raw->i_advise;
+	fi->i_flags = le32_to_cpu(raw->i_flags);
+	f2fs_set_inode_flags(inode);
+	fi->i_gc_failures = le16_to_cpu(raw->i_gc_failures);
+
+	recover_inline_flags(inode, raw);
+
+	f2fs_mark_inode_dirty_sync(inode, true);
+
+	if (file_enc_name(inode))
+		name = "<encrypted>";
+	else
+		name = F2FS_INODE(folio)->i_name;
+
+	f2fs_notice(F2FS_I_SB(inode), "recover_inode: ino = %x, name = %s, inline = %x",
+		    ino_of_node(folio), name, raw->i_inline);
+	return 0;
+}
+
+static unsigned int adjust_por_ra_blocks(struct f2fs_sb_info *sbi,
+				unsigned int ra_blocks, unsigned int blkaddr,
+				unsigned int next_blkaddr)
+{
+	if (blkaddr + 1 == next_blkaddr)
+		ra_blocks = min_t(unsigned int, RECOVERY_MAX_RA_BLOCKS,
+							ra_blocks * 2);
+	else if (next_blkaddr % BLKS_PER_SEG(sbi))
+		ra_blocks = max_t(unsigned int, RECOVERY_MIN_RA_BLOCKS,
+							ra_blocks / 2);
+	return ra_blocks;
+}
+
+/* Detect looped node chain with Floyd's cycle detection algorithm. */
+static int sanity_check_node_chain(struct f2fs_sb_info *sbi, block_t blkaddr,
+		block_t *blkaddr_fast, bool *is_detecting)
+{
+	unsigned int ra_blocks = RECOVERY_MAX_RA_BLOCKS;
+	int i;
+
+	if (!*is_detecting)
+		return 0;
+
+	for (i = 0; i < 2; i++) {
+		struct folio *folio;
+
+		if (!f2fs_is_valid_blkaddr(sbi, *blkaddr_fast, META_POR)) {
+			*is_detecting = false;
+			return 0;
+		}
+
+		folio = f2fs_get_tmp_folio(sbi, *blkaddr_fast);
+		if (IS_ERR(folio))
+			return PTR_ERR(folio);
+
+		if (!is_recoverable_dnode(folio)) {
+			f2fs_folio_put(folio, true);
+			*is_detecting = false;
+			return 0;
+		}
+
+		ra_blocks = adjust_por_ra_blocks(sbi, ra_blocks, *blkaddr_fast,
+					next_blkaddr_of_node(folio));
+
+		*blkaddr_fast = next_blkaddr_of_node(folio);
+		f2fs_folio_put(folio, true);
+
+		f2fs_ra_meta_pages_cond(sbi, *blkaddr_fast, ra_blocks);
+	}
+
+	if (*blkaddr_fast == blkaddr) {
+		f2fs_notice(sbi, "%s: Detect looped node chain on blkaddr:%u."
+				" Run fsck to fix it.", __func__, blkaddr);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
+				bool check_only, bool *new_inode)
+{
+	struct curseg_info *curseg;
+	block_t blkaddr, blkaddr_fast;
+	bool is_detecting = true;
+	int err = 0;
+
+	/* get node pages in the current segment */
+	curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
+	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
+	blkaddr_fast = blkaddr;
+
+	while (1) {
+		struct fsync_inode_entry *entry;
+		struct folio *folio;
+
+		if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
+			return 0;
+
+		folio = f2fs_get_tmp_folio(sbi, blkaddr);
+		if (IS_ERR(folio)) {
+			err = PTR_ERR(folio);
+			break;
+		}
+
+		if (!is_recoverable_dnode(folio)) {
+			f2fs_folio_put(folio, true);
+			break;
+		}
+
+		if (!is_fsync_dnode(folio))
+			goto next;
+
+		entry = get_fsync_inode(head, ino_of_node(folio));
+		if (!entry) {
+			bool quota_inode = false;
+
+			if (!check_only &&
+					IS_INODE(folio) &&
+					is_dent_dnode(folio)) {
+				err = f2fs_recover_inode_page(sbi, folio);
+				if (err) {
+					f2fs_folio_put(folio, true);
+					break;
+				}
+				quota_inode = true;
+			}
+
+			entry = add_fsync_inode(sbi, head, ino_of_node(folio),
+								quota_inode);
+			if (IS_ERR(entry)) {
+				err = PTR_ERR(entry);
+				/*
+				 * CP | dnode(F) | inode(DF)
+				 * For this case, we should not give up now.
+				 */
+				if (err == -ENOENT) {
+					if (check_only)
+						*new_inode = true;
+					goto next;
+				}
+				f2fs_folio_put(folio, true);
+				break;
+			}
+		}
+		entry->blkaddr = blkaddr;
+
+		if (IS_INODE(folio) && is_dent_dnode(folio))
+			entry->last_dentry = blkaddr;
+next:
+		/* check next segment */
+		blkaddr = next_blkaddr_of_node(folio);
+		f2fs_folio_put(folio, true);
+
+		err = sanity_check_node_chain(sbi, blkaddr, &blkaddr_fast,
+				&is_detecting);
+		if (err)
+			break;
+	}
+	return err;
+}
+
+static void destroy_fsync_dnodes(struct list_head *head, int drop)
+{
+	struct fsync_inode_entry *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, head, list)
+		del_fsync_inode(entry, drop);
+}
+
+static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
+			block_t blkaddr, struct dnode_of_data *dn)
+{
+	struct seg_entry *sentry;
+	unsigned int segno = GET_SEGNO(sbi, blkaddr);
+	unsigned short blkoff = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
+	struct f2fs_summary_block *sum_node;
+	struct f2fs_summary sum;
+	struct folio *sum_folio, *node_folio;
+	struct dnode_of_data tdn = *dn;
+	nid_t ino, nid;
+	struct inode *inode;
+	unsigned int offset, ofs_in_node, max_addrs;
+	block_t bidx;
+	int i;
+
+	sentry = get_seg_entry(sbi, segno);
+	if (!f2fs_test_bit(blkoff, sentry->cur_valid_map))
+		return 0;
+
+	/* Get the previous summary */
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
+		struct curseg_info *curseg = CURSEG_I(sbi, i);
+
+		if (curseg->segno == segno) {
+			sum = sum_entries(curseg->sum_blk)[blkoff];
+			goto got_it;
+		}
+	}
+
+	sum_folio = f2fs_get_sum_folio(sbi, segno);
+	if (IS_ERR(sum_folio))
+		return PTR_ERR(sum_folio);
+	sum_node = SUM_BLK_PAGE_ADDR(sbi, sum_folio, segno);
+	sum = sum_entries(sum_node)[blkoff];
+	f2fs_folio_put(sum_folio, true);
+got_it:
+	/* Use the locked dnode page and inode */
+	nid = le32_to_cpu(sum.nid);
+	ofs_in_node = le16_to_cpu(sum.ofs_in_node);
+
+	max_addrs = ADDRS_PER_PAGE(dn->node_folio, dn->inode);
+	if (ofs_in_node >= max_addrs) {
+		f2fs_err(sbi, "Inconsistent ofs_in_node:%u in summary, ino:%llu, nid:%u, max:%u",
+			ofs_in_node, dn->inode->i_ino, nid, max_addrs);
+		f2fs_handle_error(sbi, ERROR_INCONSISTENT_SUMMARY);
+		return -EFSCORRUPTED;
+	}
+
+	if (dn->inode->i_ino == nid) {
+		tdn.nid = nid;
+		if (!dn->inode_folio_locked)
+			folio_lock(dn->inode_folio);
+		tdn.node_folio = dn->inode_folio;
+		tdn.ofs_in_node = ofs_in_node;
+		goto truncate_out;
+	} else if (dn->nid == nid) {
+		tdn.ofs_in_node = ofs_in_node;
+		goto truncate_out;
+	}
+
+	/* Get the node page */
+	node_folio = f2fs_get_node_folio(sbi, nid, NODE_TYPE_REGULAR);
+	if (IS_ERR(node_folio))
+		return PTR_ERR(node_folio);
+
+	offset = ofs_of_node(node_folio);
+	ino = ino_of_node(node_folio);
+	f2fs_folio_put(node_folio, true);
+
+	if (ino != dn->inode->i_ino) {
+		int ret;
+
+		/* Deallocate previous index in the node page */
+		inode = f2fs_iget_retry(sbi->sb, ino);
+		if (IS_ERR(inode))
+			return PTR_ERR(inode);
+
+		ret = f2fs_dquot_initialize(inode);
+		if (ret) {
+			iput(inode);
+			return ret;
+		}
+	} else {
+		inode = dn->inode;
+	}
+
+	bidx = f2fs_start_bidx_of_node(offset, inode) +
+				le16_to_cpu(sum.ofs_in_node);
+
+	/*
+	 * if inode page is locked, unlock temporarily, but its reference
+	 * count keeps alive.
+	 */
+	if (ino == dn->inode->i_ino && dn->inode_folio_locked)
+		folio_unlock(dn->inode_folio);
+
+	set_new_dnode(&tdn, inode, NULL, NULL, 0);
+	if (f2fs_get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
+		goto out;
+
+	if (tdn.data_blkaddr == blkaddr)
+		f2fs_truncate_data_blocks_range(&tdn, 1);
+
+	f2fs_put_dnode(&tdn);
+out:
+	if (ino != dn->inode->i_ino)
+		iput(inode);
+	else if (dn->inode_folio_locked)
+		folio_lock(dn->inode_folio);
+	return 0;
+
+truncate_out:
+	if (f2fs_data_blkaddr(&tdn) == blkaddr)
+		f2fs_truncate_data_blocks_range(&tdn, 1);
+	if (dn->inode->i_ino == nid && !dn->inode_folio_locked)
+		folio_unlock(dn->inode_folio);
+	return 0;
+}
+
+static int f2fs_reserve_new_block_retry(struct dnode_of_data *dn)
+{
+	int i, err = 0;
+
+	for (i = DEFAULT_FAILURE_RETRY_COUNT; i > 0; i--) {
+		err = f2fs_reserve_new_block(dn);
+		if (!err)
+			break;
+	}
+
+	return err;
+}
+
+static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
+					struct folio *folio)
+{
+	struct dnode_of_data dn;
+	struct node_info ni;
+	unsigned int start = 0, end = 0, index;
+	int err = 0, recovered = 0;
+
+	/* step 1: recover xattr */
+	if (IS_INODE(folio)) {
+		err = f2fs_recover_inline_xattr(inode, folio);
+		if (err)
+			goto out;
+	} else if (f2fs_has_xattr_block(ofs_of_node(folio))) {
+		err = f2fs_recover_xattr_data(inode, folio);
+		if (!err)
+			recovered++;
+		goto out;
+	}
+
+	/* step 2: recover inline data */
+	err = f2fs_recover_inline_data(inode, folio);
+	if (err) {
+		if (err == 1)
+			err = 0;
+		goto out;
+	}
+
+	/* step 3: recover data indices */
+	start = f2fs_start_bidx_of_node(ofs_of_node(folio), inode);
+	end = start + ADDRS_PER_PAGE(folio, inode);
+
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+retry_dn:
+	err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE);
+	if (err) {
+		if (err == -ENOMEM) {
+			memalloc_retry_wait(GFP_NOFS);
+			goto retry_dn;
+		}
+		goto out;
+	}
+
+	f2fs_folio_wait_writeback(dn.node_folio, NODE, true, true);
+
+	err = f2fs_get_node_info(sbi, dn.nid, &ni, false);
+	if (err)
+		goto err;
+
+	f2fs_bug_on(sbi, ni.ino != ino_of_node(folio));
+
+	if (ofs_of_node(dn.node_folio) != ofs_of_node(folio)) {
+		f2fs_warn(sbi, "Inconsistent ofs_of_node, ino:%llu, ofs:%u, %u",
+			  inode->i_ino, ofs_of_node(dn.node_folio),
+			  ofs_of_node(folio));
+		err = -EFSCORRUPTED;
+		f2fs_handle_error(sbi, ERROR_INCONSISTENT_FOOTER);
+		fserror_report_file_metadata(dn.inode, err, GFP_NOFS);
+		goto err;
+	}
+
+	for (index = start; index < end; index++, dn.ofs_in_node++) {
+		block_t src, dest;
+
+		src = f2fs_data_blkaddr(&dn);
+		dest = data_blkaddr(dn.inode, folio, dn.ofs_in_node);
+
+		if (__is_valid_data_blkaddr(src) &&
+			!f2fs_is_valid_blkaddr(sbi, src, META_POR)) {
+			err = -EFSCORRUPTED;
+			goto err;
+		}
+
+		if (__is_valid_data_blkaddr(dest) &&
+			!f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
+			err = -EFSCORRUPTED;
+			goto err;
+		}
+
+		/* skip recovering if dest is the same as src */
+		if (src == dest)
+			continue;
+
+		/* dest is invalid, just invalidate src block */
+		if (dest == NULL_ADDR) {
+			f2fs_truncate_data_blocks_range(&dn, 1);
+			continue;
+		}
+
+		if (!file_keep_isize(inode) &&
+			(i_size_read(inode) <= ((loff_t)index << PAGE_SHIFT)))
+			f2fs_i_size_write(inode,
+				(loff_t)(index + 1) << PAGE_SHIFT);
+
+		/*
+		 * dest is reserved block, invalidate src block
+		 * and then reserve one new block in dnode page.
+		 */
+		if (dest == NEW_ADDR) {
+			f2fs_truncate_data_blocks_range(&dn, 1);
+
+			err = f2fs_reserve_new_block_retry(&dn);
+			if (err)
+				goto err;
+			continue;
+		}
+
+		/* dest is valid block, try to recover from src to dest */
+		if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
+			if (src == NULL_ADDR) {
+				err = f2fs_reserve_new_block_retry(&dn);
+				if (err)
+					goto err;
+			}
+retry_prev:
+			/* Check the previous node page having this index */
+			err = check_index_in_prev_nodes(sbi, dest, &dn);
+			if (err) {
+				if (err == -ENOMEM) {
+					memalloc_retry_wait(GFP_NOFS);
+					goto retry_prev;
+				}
+				goto err;
+			}
+
+			if (f2fs_is_valid_blkaddr(sbi, dest,
+					DATA_GENERIC_ENHANCE_UPDATE)) {
+				f2fs_err(sbi, "Inconsistent dest blkaddr:%u, ino:%llu, ofs:%u",
+					dest, inode->i_ino, dn.ofs_in_node);
+				err = -EFSCORRUPTED;
+				goto err;
+			}
+
+			/* write dummy data page */
+			f2fs_replace_block(sbi, &dn, src, dest,
+						ni.version, false, false);
+			recovered++;
+		}
+	}
+
+	copy_node_footer(dn.node_folio, folio);
+	fill_node_footer(dn.node_folio, dn.nid, ni.ino,
+					ofs_of_node(folio), false);
+	folio_mark_dirty(dn.node_folio);
+err:
+	f2fs_put_dnode(&dn);
+out:
+	f2fs_notice(sbi, "recover_data: ino = %llx, nid = %x (i_size: %s), "
+		    "range (%u, %u), recovered = %d, err = %d",
+		    inode->i_ino, nid_of_node(folio),
+		    file_keep_isize(inode) ? "keep" : "recover",
+		    start, end, recovered, err);
+	return err;
+}
+
+static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
+		struct list_head *tmp_inode_list, struct list_head *dir_list)
+{
+	struct curseg_info *curseg;
+	int err = 0;
+	block_t blkaddr;
+	unsigned int ra_blocks = RECOVERY_MAX_RA_BLOCKS;
+	unsigned int recoverable_dnode = 0;
+	unsigned int fsynced_dnode = 0;
+	unsigned int total_dnode = 0;
+	unsigned int recovered_inode = 0;
+	unsigned int recovered_dentry = 0;
+	unsigned int recovered_dnode = 0;
+
+	f2fs_notice(sbi, "do_recover_data: start to recover dnode");
+
+	/* get node pages in the current segment */
+	curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
+	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
+
+	while (1) {
+		struct fsync_inode_entry *entry;
+		struct folio *folio;
+
+		if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
+			break;
+
+		folio = f2fs_get_tmp_folio(sbi, blkaddr);
+		if (IS_ERR(folio)) {
+			err = PTR_ERR(folio);
+			break;
+		}
+
+		if (!is_recoverable_dnode(folio)) {
+			f2fs_folio_put(folio, true);
+			break;
+		}
+		recoverable_dnode++;
+
+		entry = get_fsync_inode(inode_list, ino_of_node(folio));
+		if (!entry)
+			goto next;
+		fsynced_dnode++;
+		/*
+		 * inode(x) | CP | inode(x) | dnode(F)
+		 * In this case, we can lose the latest inode(x).
+		 * So, call recover_inode for the inode update.
+		 */
+		if (IS_INODE(folio)) {
+			err = recover_inode(entry->inode, folio);
+			if (err) {
+				f2fs_folio_put(folio, true);
+				break;
+			}
+			recovered_inode++;
+		}
+		if (entry->last_dentry == blkaddr) {
+			err = recover_dentry(entry->inode, folio, dir_list);
+			if (err) {
+				f2fs_folio_put(folio, true);
+				break;
+			}
+			recovered_dentry++;
+		}
+		err = do_recover_data(sbi, entry->inode, folio);
+		if (err) {
+			f2fs_folio_put(folio, true);
+			break;
+		}
+		recovered_dnode++;
+
+		if (entry->blkaddr == blkaddr)
+			list_move_tail(&entry->list, tmp_inode_list);
+next:
+		ra_blocks = adjust_por_ra_blocks(sbi, ra_blocks, blkaddr,
+					next_blkaddr_of_node(folio));
+
+		/* check next segment */
+		blkaddr = next_blkaddr_of_node(folio);
+		f2fs_folio_put(folio, true);
+
+		f2fs_ra_meta_pages_cond(sbi, blkaddr, ra_blocks);
+		total_dnode++;
+	}
+	if (!err)
+		err = f2fs_allocate_new_segments(sbi);
+
+	f2fs_notice(sbi, "do_recover_data: dnode: (recoverable: %u, fsynced: %u, "
+		"total: %u), recovered: (inode: %u, dentry: %u, dnode: %u), err: %d",
+		recoverable_dnode, fsynced_dnode, total_dnode, recovered_inode,
+		recovered_dentry, recovered_dnode, err);
+	return err;
+}
+
+int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
+{
+	LIST_HEAD(inode_list);
+	LIST_HEAD(tmp_inode_list);
+	LIST_HEAD(dir_list);
+	struct f2fs_lock_context lc;
+	int err;
+	int ret = 0;
+	unsigned long s_flags = sbi->sb->s_flags;
+	bool need_writecp = false;
+	bool new_inode = false;
+
+	f2fs_notice(sbi, "f2fs_recover_fsync_data: recovery fsync data, "
+					"check_only: %d", check_only);
+
+	if (is_sbi_flag_set(sbi, SBI_IS_WRITABLE))
+		f2fs_info(sbi, "recover fsync data on readonly fs");
+
+	/* prevent checkpoint */
+	f2fs_down_write_trace(&sbi->cp_global_sem, &lc);
+
+	/* step #1: find fsynced inode numbers */
+	err = find_fsync_dnodes(sbi, &inode_list, check_only, &new_inode);
+	if (err < 0 || (list_empty(&inode_list) && (!check_only || !new_inode)))
+		goto skip;
+
+	if (check_only) {
+		ret = 1;
+		goto skip;
+	}
+
+	need_writecp = true;
+
+	/* step #2: recover data */
+	err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list);
+	if (!err)
+		f2fs_bug_on(sbi, !list_empty(&inode_list));
+	else
+		f2fs_bug_on(sbi, sbi->sb->s_flags & SB_ACTIVE);
+skip:
+	destroy_fsync_dnodes(&inode_list, err);
+	destroy_fsync_dnodes(&tmp_inode_list, err);
+
+	/* truncate meta pages to be used by the recovery */
+	truncate_inode_pages_range(META_MAPPING(sbi),
+			(loff_t)MAIN_BLKADDR(sbi) << PAGE_SHIFT, -1);
+
+	if (err) {
+		truncate_inode_pages_final(NODE_MAPPING(sbi));
+		truncate_inode_pages_final(META_MAPPING(sbi));
+	}
+
+	/*
+	 * If fsync data succeeds or there is no fsync data to recover,
+	 * and the f2fs is not read only, check and fix zoned block devices'
+	 * write pointer consistency.
+	 */
+	if (!err)
+		err = f2fs_check_and_fix_write_pointer(sbi);
+
+	if (!err)
+		clear_sbi_flag(sbi, SBI_POR_DOING);
+
+	f2fs_up_write_trace(&sbi->cp_global_sem, &lc);
+
+	/* let's drop all the directory inodes for clean checkpoint */
+	destroy_fsync_dnodes(&dir_list, err);
+
+	if (need_writecp) {
+		set_sbi_flag(sbi, SBI_IS_RECOVERED);
+
+		if (!err) {
+			struct cp_control cpc = {
+				.reason = CP_RECOVERY,
+			};
+			stat_inc_cp_call_count(sbi, TOTAL_CALL);
+			err = f2fs_write_checkpoint(sbi, &cpc);
+		}
+	}
+
+	sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */
+
+	return ret ? ret : err;
+}
+
+int __init f2fs_create_recovery_cache(void)
+{
+	fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
+					sizeof(struct fsync_inode_entry));
+	return fsync_entry_slab ? 0 : -ENOMEM;
+}
+
+void f2fs_destroy_recovery_cache(void)
+{
+	kmem_cache_destroy(fsync_entry_slab);
+}

linux-7.2.3/fs/f2fs/shrinker.c

@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * f2fs shrinker support
+ *   the basic infra was copied from fs/ubifs/shrinker.c
+ *
+ * Copyright (c) 2015 Motorola Mobility
+ * Copyright (c) 2015 Jaegeuk Kim <jaegeuk@kernel.org>
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+
+#include "f2fs.h"
+#include "node.h"
+
+static LIST_HEAD(f2fs_list);
+static DEFINE_SPINLOCK(f2fs_list_lock);
+static unsigned int shrinker_run_no;
+
+static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
+{
+	return NM_I(sbi)->nat_cnt[RECLAIMABLE_NAT];
+}
+
+static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
+{
+	long count = NM_I(sbi)->nid_cnt[FREE_NID] - MAX_FREE_NIDS;
+
+	return count > 0 ? count : 0;
+}
+
+static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi,
+					enum extent_type type)
+{
+	struct extent_tree_info *eti = &sbi->extent_tree[type];
+
+	return atomic_read(&eti->total_zombie_tree) +
+				atomic_read(&eti->total_ext_node);
+}
+
+unsigned long f2fs_shrink_count(struct shrinker *shrink,
+				struct shrink_control *sc)
+{
+	struct f2fs_sb_info *sbi;
+	struct list_head *p;
+	unsigned long count = 0;
+
+	spin_lock(&f2fs_list_lock);
+	p = f2fs_list.next;
+	while (p != &f2fs_list) {
+		sbi = list_entry(p, struct f2fs_sb_info, s_list);
+
+		/* stop f2fs_put_super */
+		if (!mutex_trylock(&sbi->umount_mutex)) {
+			p = p->next;
+			continue;
+		}
+		spin_unlock(&f2fs_list_lock);
+
+		/* count read extent cache entries */
+		count += __count_extent_cache(sbi, EX_READ);
+
+		/* count block age extent cache entries */
+		count += __count_extent_cache(sbi, EX_BLOCK_AGE);
+
+		/* count clean nat cache entries */
+		count += __count_nat_entries(sbi);
+
+		/* count free nids cache entries */
+		count += __count_free_nids(sbi);
+
+		spin_lock(&f2fs_list_lock);
+		p = p->next;
+		mutex_unlock(&sbi->umount_mutex);
+	}
+	spin_unlock(&f2fs_list_lock);
+	return count ?: SHRINK_EMPTY;
+}
+
+unsigned long f2fs_shrink_scan(struct shrinker *shrink,
+				struct shrink_control *sc)
+{
+	unsigned long nr = sc->nr_to_scan;
+	struct f2fs_sb_info *sbi;
+	struct list_head *p;
+	unsigned int run_no;
+	unsigned long freed = 0;
+
+	spin_lock(&f2fs_list_lock);
+	do {
+		run_no = ++shrinker_run_no;
+	} while (run_no == 0);
+	p = f2fs_list.next;
+	while (p != &f2fs_list) {
+		sbi = list_entry(p, struct f2fs_sb_info, s_list);
+
+		if (sbi->shrinker_run_no == run_no)
+			break;
+
+		/* stop f2fs_put_super */
+		if (!mutex_trylock(&sbi->umount_mutex)) {
+			p = p->next;
+			continue;
+		}
+		spin_unlock(&f2fs_list_lock);
+
+		sbi->shrinker_run_no = run_no;
+
+		/* shrink extent cache entries */
+		freed += f2fs_shrink_age_extent_tree(sbi, nr >> 2);
+
+		/* shrink read extent cache entries */
+		freed += f2fs_shrink_read_extent_tree(sbi, nr >> 2);
+
+		/* shrink clean nat cache entries */
+		if (freed < nr)
+			freed += f2fs_try_to_free_nats(sbi, nr - freed);
+
+		/* shrink free nids cache entries */
+		if (freed < nr)
+			freed += f2fs_try_to_free_nids(sbi, nr - freed);
+
+		spin_lock(&f2fs_list_lock);
+		p = p->next;
+		list_move_tail(&sbi->s_list, &f2fs_list);
+		mutex_unlock(&sbi->umount_mutex);
+		if (freed >= nr)
+			break;
+	}
+	spin_unlock(&f2fs_list_lock);
+	return freed;
+}
+
+unsigned int f2fs_donate_files(void)
+{
+	struct f2fs_sb_info *sbi;
+	struct list_head *p;
+	unsigned int donate_files = 0;
+
+	spin_lock(&f2fs_list_lock);
+	p = f2fs_list.next;
+	while (p != &f2fs_list) {
+		sbi = list_entry(p, struct f2fs_sb_info, s_list);
+
+		/* stop f2fs_put_super */
+		if (!mutex_trylock(&sbi->umount_mutex)) {
+			p = p->next;
+			continue;
+		}
+		spin_unlock(&f2fs_list_lock);
+
+		donate_files += sbi->donate_files;
+
+		spin_lock(&f2fs_list_lock);
+		p = p->next;
+		mutex_unlock(&sbi->umount_mutex);
+	}
+	spin_unlock(&f2fs_list_lock);
+
+	return donate_files;
+}
+
+static unsigned int do_reclaim_caches(struct f2fs_sb_info *sbi,
+				unsigned int reclaim_caches_kb)
+{
+	struct inode *inode;
+	struct f2fs_inode_info *fi;
+	unsigned int nfiles = sbi->donate_files;
+	pgoff_t npages = reclaim_caches_kb >> (PAGE_SHIFT - 10);
+
+	while (npages && nfiles--) {
+		pgoff_t len;
+
+		spin_lock(&sbi->inode_lock[DONATE_INODE]);
+		if (list_empty(&sbi->inode_list[DONATE_INODE])) {
+			spin_unlock(&sbi->inode_lock[DONATE_INODE]);
+			break;
+		}
+		fi = list_first_entry(&sbi->inode_list[DONATE_INODE],
+					struct f2fs_inode_info, gdonate_list);
+		list_move_tail(&fi->gdonate_list, &sbi->inode_list[DONATE_INODE]);
+		inode = igrab(&fi->vfs_inode);
+		spin_unlock(&sbi->inode_lock[DONATE_INODE]);
+
+		if (!inode)
+			continue;
+
+		inode_lock(inode);
+		if (!is_inode_flag_set(inode, FI_DONATE_FINISHED)) {
+			len = fi->donate_end - fi->donate_start + 1;
+			npages = npages < len ? 0 : npages - len;
+
+			invalidate_inode_pages2_range(inode->i_mapping,
+					fi->donate_start, fi->donate_end);
+			set_inode_flag(inode, FI_DONATE_FINISHED);
+		}
+		inode_unlock(inode);
+
+		iput(inode);
+		cond_resched();
+	}
+	return npages << (PAGE_SHIFT - 10);
+}
+
+void f2fs_reclaim_caches(unsigned int reclaim_caches_kb)
+{
+	struct f2fs_sb_info *sbi;
+	struct list_head *p;
+
+	spin_lock(&f2fs_list_lock);
+	p = f2fs_list.next;
+	while (p != &f2fs_list && reclaim_caches_kb) {
+		sbi = list_entry(p, struct f2fs_sb_info, s_list);
+
+		/* stop f2fs_put_super */
+		if (!mutex_trylock(&sbi->umount_mutex)) {
+			p = p->next;
+			continue;
+		}
+		spin_unlock(&f2fs_list_lock);
+
+		reclaim_caches_kb = do_reclaim_caches(sbi, reclaim_caches_kb);
+
+		spin_lock(&f2fs_list_lock);
+		p = p->next;
+		mutex_unlock(&sbi->umount_mutex);
+	}
+	spin_unlock(&f2fs_list_lock);
+}
+
+void f2fs_join_shrinker(struct f2fs_sb_info *sbi)
+{
+	spin_lock(&f2fs_list_lock);
+	list_add_tail(&sbi->s_list, &f2fs_list);
+	spin_unlock(&f2fs_list_lock);
+}
+
+void f2fs_leave_shrinker(struct f2fs_sb_info *sbi)
+{
+	f2fs_shrink_read_extent_tree(sbi, __count_extent_cache(sbi, EX_READ));
+	f2fs_shrink_age_extent_tree(sbi,
+				__count_extent_cache(sbi, EX_BLOCK_AGE));
+
+	spin_lock(&f2fs_list_lock);
+	list_del_init(&sbi->s_list);
+	spin_unlock(&f2fs_list_lock);
+}

linux-7.2.3/fs/f2fs/verity.c

@@ -0,0 +1,289 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fs/f2fs/verity.c: fs-verity support for f2fs
+ *
+ * Copyright 2019 Google LLC
+ */
+
+/*
+ * Implementation of fsverity_operations for f2fs.
+ *
+ * Like ext4, f2fs stores the verity metadata (Merkle tree and
+ * fsverity_descriptor) past the end of the file, starting at the first 64K
+ * boundary beyond i_size.  This approach works because (a) verity files are
+ * readonly, and (b) pages fully beyond i_size aren't visible to userspace but
+ * can be read/written internally by f2fs with only some relatively small
+ * changes to f2fs.  Extended attributes cannot be used because (a) f2fs limits
+ * the total size of an inode's xattr entries to 4096 bytes, which wouldn't be
+ * enough for even a single Merkle tree block, and (b) f2fs encryption doesn't
+ * encrypt xattrs, yet the verity metadata *must* be encrypted when the file is
+ * because it contains hashes of the plaintext data.
+ *
+ * Using a 64K boundary rather than a 4K one keeps things ready for
+ * architectures with 64K pages, and it doesn't necessarily waste space on-disk
+ * since there can be a hole between i_size and the start of the Merkle tree.
+ */
+
+#include <linux/f2fs_fs.h>
+#include <linux/fserror.h>
+
+#include "f2fs.h"
+#include "xattr.h"
+
+#define F2FS_VERIFY_VER	(1)
+
+static inline loff_t f2fs_verity_metadata_pos(const struct inode *inode)
+{
+	return round_up(inode->i_size, 65536);
+}
+
+/*
+ * Read some verity metadata from the inode.  __vfs_read() can't be used because
+ * we need to read beyond i_size.
+ */
+static int pagecache_read(struct inode *inode, void *buf, size_t count,
+			  loff_t pos)
+{
+	while (count) {
+		size_t n = min_t(size_t, count,
+				 PAGE_SIZE - offset_in_page(pos));
+		struct page *page;
+
+		page = read_mapping_page(inode->i_mapping, pos >> PAGE_SHIFT,
+					 NULL);
+		if (IS_ERR(page))
+			return PTR_ERR(page);
+
+		memcpy_from_page(buf, page, offset_in_page(pos), n);
+
+		put_page(page);
+
+		buf += n;
+		pos += n;
+		count -= n;
+	}
+	return 0;
+}
+
+/*
+ * Write some verity metadata to the inode for FS_IOC_ENABLE_VERITY.
+ * kernel_write() can't be used because the file descriptor is readonly.
+ */
+static int pagecache_write(struct inode *inode, const void *buf, size_t count,
+			   loff_t pos)
+{
+	struct address_space *mapping = inode->i_mapping;
+	const struct address_space_operations *aops = mapping->a_ops;
+
+	if (pos + count > F2FS_BLK_TO_BYTES(max_file_blocks(inode)))
+		return -EFBIG;
+
+	while (count) {
+		size_t n = min_t(size_t, count,
+				 PAGE_SIZE - offset_in_page(pos));
+		struct folio *folio;
+		void *fsdata = NULL;
+		int res;
+
+		res = aops->write_begin(NULL, mapping, pos, n, &folio, &fsdata);
+		if (res)
+			return res;
+
+		memcpy_to_folio(folio, offset_in_folio(folio, pos), buf, n);
+
+		res = aops->write_end(NULL, mapping, pos, n, n, folio, fsdata);
+		if (res < 0)
+			return res;
+		if (res != n)
+			return -EIO;
+
+		buf += n;
+		pos += n;
+		count -= n;
+	}
+	return 0;
+}
+
+/*
+ * Format of f2fs verity xattr.  This points to the location of the verity
+ * descriptor within the file data rather than containing it directly because
+ * the verity descriptor *must* be encrypted when f2fs encryption is used.  But,
+ * f2fs encryption does not encrypt xattrs.
+ */
+struct fsverity_descriptor_location {
+	__le32 version;
+	__le32 size;
+	__le64 pos;
+};
+
+static int f2fs_begin_enable_verity(struct file *filp)
+{
+	struct inode *inode = file_inode(filp);
+	int err;
+
+	if (f2fs_verity_in_progress(inode))
+		return -EBUSY;
+
+	if (f2fs_is_atomic_file(inode))
+		return -EOPNOTSUPP;
+
+	/*
+	 * Since the file was opened readonly, we have to initialize the quotas
+	 * here and not rely on ->open() doing it.  This must be done before
+	 * evicting the inline data.
+	 */
+	err = f2fs_dquot_initialize(inode);
+	if (err)
+		return err;
+
+	err = f2fs_convert_inline_inode(inode);
+	if (err)
+		return err;
+
+	set_inode_flag(inode, FI_VERITY_IN_PROGRESS);
+	return 0;
+}
+
+static int f2fs_end_enable_verity(struct file *filp, const void *desc,
+				  size_t desc_size, u64 merkle_tree_size)
+{
+	struct inode *inode = file_inode(filp);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	u64 desc_pos = f2fs_verity_metadata_pos(inode) + merkle_tree_size;
+	struct fsverity_descriptor_location dloc = {
+		.version = cpu_to_le32(F2FS_VERIFY_VER),
+		.size = cpu_to_le32(desc_size),
+		.pos = cpu_to_le64(desc_pos),
+	};
+	int err = 0, err2 = 0;
+
+	/*
+	 * If an error already occurred (which fs/verity/ signals by passing
+	 * desc == NULL), then only clean-up is needed.
+	 */
+	if (desc == NULL)
+		goto cleanup;
+
+	/* Append the verity descriptor. */
+	err = pagecache_write(inode, desc, desc_size, desc_pos);
+	if (err)
+		goto cleanup;
+
+	/*
+	 * Write all pages (both data and verity metadata).  Note that this must
+	 * happen before clearing FI_VERITY_IN_PROGRESS; otherwise pages beyond
+	 * i_size won't be written properly.  For crash consistency, this also
+	 * must happen before the verity inode flag gets persisted.
+	 */
+	err = filemap_write_and_wait(inode->i_mapping);
+	if (err)
+		goto cleanup;
+
+	/* Set the verity xattr. */
+	err = f2fs_setxattr(inode, F2FS_XATTR_INDEX_VERITY,
+			    F2FS_XATTR_NAME_VERITY, &dloc, sizeof(dloc),
+			    NULL, XATTR_CREATE);
+	if (err)
+		goto cleanup;
+
+	/* Finally, set the verity inode flag. */
+	file_set_verity(inode);
+	f2fs_set_inode_flags(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
+
+	clear_inode_flag(inode, FI_VERITY_IN_PROGRESS);
+	return 0;
+
+cleanup:
+	/*
+	 * Verity failed to be enabled, so clean up by truncating any verity
+	 * metadata that was written beyond i_size (both from cache and from
+	 * disk) and clearing FI_VERITY_IN_PROGRESS.
+	 *
+	 * Taking i_gc_rwsem[WRITE] is needed to stop f2fs garbage collection
+	 * from re-instantiating cached pages we are truncating (since unlike
+	 * normal file accesses, garbage collection isn't limited by i_size).
+	 */
+	f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	truncate_inode_pages(inode->i_mapping, inode->i_size);
+	err2 = f2fs_truncate(inode);
+	if (err2) {
+		f2fs_err(sbi, "Truncating verity metadata failed (errno=%d)",
+			 err2);
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+	}
+	f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+	clear_inode_flag(inode, FI_VERITY_IN_PROGRESS);
+	return err ?: err2;
+}
+
+static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
+				      size_t buf_size)
+{
+	struct fsverity_descriptor_location dloc;
+	int res;
+	u32 size;
+	u64 pos;
+
+	/* Get the descriptor location */
+	res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_VERITY,
+			    F2FS_XATTR_NAME_VERITY, &dloc, sizeof(dloc), NULL);
+	if (res < 0 && res != -ERANGE)
+		return res;
+	if (res != sizeof(dloc) || dloc.version != cpu_to_le32(F2FS_VERIFY_VER)) {
+		f2fs_warn(F2FS_I_SB(inode), "unknown verity xattr format");
+		return -EINVAL;
+	}
+	size = le32_to_cpu(dloc.size);
+	pos = le64_to_cpu(dloc.pos);
+
+	/* Get the descriptor */
+	if (pos + size < pos ||
+	    pos + size > F2FS_BLK_TO_BYTES(max_file_blocks(inode)) ||
+	    pos < f2fs_verity_metadata_pos(inode) || size > INT_MAX) {
+		f2fs_warn(F2FS_I_SB(inode), "invalid verity xattr");
+		f2fs_handle_error(F2FS_I_SB(inode),
+				ERROR_CORRUPTED_VERITY_XATTR);
+		fserror_report_file_metadata(inode, -EFSCORRUPTED, GFP_NOFS);
+		return -EFSCORRUPTED;
+	}
+	if (buf_size) {
+		if (size > buf_size)
+			return -ERANGE;
+		res = pagecache_read(inode, buf, size, pos);
+		if (res)
+			return res;
+	}
+	return size;
+}
+
+static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
+					       pgoff_t index)
+{
+	index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT;
+	return generic_read_merkle_tree_page(inode, index);
+}
+
+static void f2fs_readahead_merkle_tree(struct inode *inode, pgoff_t index,
+				       unsigned long nr_pages)
+{
+	index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT;
+	generic_readahead_merkle_tree(inode, index, nr_pages);
+}
+
+static int f2fs_write_merkle_tree_block(struct file *file, const void *buf,
+					u64 pos, unsigned int size)
+{
+	pos += f2fs_verity_metadata_pos(file_inode(file));
+
+	return pagecache_write(file_inode(file), buf, size, pos);
+}
+
+const struct fsverity_operations f2fs_verityops = {
+	.begin_enable_verity	= f2fs_begin_enable_verity,
+	.end_enable_verity	= f2fs_end_enable_verity,
+	.get_verity_descriptor	= f2fs_get_verity_descriptor,
+	.read_merkle_tree_page	= f2fs_read_merkle_tree_page,
+	.readahead_merkle_tree	= f2fs_readahead_merkle_tree,
+	.write_merkle_tree_block = f2fs_write_merkle_tree_block,
+};

linux-7.2.3/fs/f2fs/xattr.c

@@ -0,0 +1,851 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fs/f2fs/xattr.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * Portions of this code from linux/fs/ext2/xattr.c
+ *
+ * Copyright (C) 2001-2003 Andreas Gruenbacher <agruen@suse.de>
+ *
+ * Fix by Harrison Xing <harrison@mountainviewdata.com>.
+ * Extended attributes for symlinks and special files added per
+ *  suggestion of Luka Renko <luka.renko@hermes.si>.
+ * xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>,
+ *  Red Hat Inc.
+ */
+#include <linux/rwsem.h>
+#include <linux/f2fs_fs.h>
+#include <linux/security.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/fserror.h>
+#include "f2fs.h"
+#include "xattr.h"
+#include "segment.h"
+
+static struct kmem_cache *inline_xattr_slab;
+static void *xattr_alloc(struct f2fs_sb_info *sbi, int size, bool *is_inline)
+{
+	if (likely(size == DEFAULT_XATTR_SLAB_SIZE)) {
+		*is_inline = true;
+		return f2fs_kmem_cache_alloc(inline_xattr_slab,
+					GFP_F2FS_ZERO, false, sbi);
+	}
+	*is_inline = false;
+	return f2fs_kzalloc(sbi, size, GFP_NOFS);
+}
+
+static void xattr_free(struct f2fs_sb_info *sbi, void *xattr_addr,
+							bool is_inline)
+{
+	if (is_inline)
+		kmem_cache_free(inline_xattr_slab, xattr_addr);
+	else
+		kfree(xattr_addr);
+}
+
+static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
+		struct dentry *unused, struct inode *inode,
+		const char *name, void *buffer, size_t size)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+
+	switch (handler->flags) {
+	case F2FS_XATTR_INDEX_USER:
+		if (!test_opt(sbi, XATTR_USER))
+			return -EOPNOTSUPP;
+		break;
+	case F2FS_XATTR_INDEX_TRUSTED:
+	case F2FS_XATTR_INDEX_SECURITY:
+		break;
+	default:
+		return -EINVAL;
+	}
+	return f2fs_getxattr(inode, handler->flags, name,
+			     buffer, size, NULL);
+}
+
+static int f2fs_xattr_generic_set(const struct xattr_handler *handler,
+		struct mnt_idmap *idmap,
+		struct dentry *unused, struct inode *inode,
+		const char *name, const void *value,
+		size_t size, int flags)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+
+	switch (handler->flags) {
+	case F2FS_XATTR_INDEX_USER:
+		if (!test_opt(sbi, XATTR_USER))
+			return -EOPNOTSUPP;
+		break;
+	case F2FS_XATTR_INDEX_TRUSTED:
+	case F2FS_XATTR_INDEX_SECURITY:
+		break;
+	default:
+		return -EINVAL;
+	}
+	return f2fs_setxattr(inode, handler->flags, name,
+					value, size, NULL, flags);
+}
+
+static bool f2fs_xattr_user_list(struct dentry *dentry)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+
+	return test_opt(sbi, XATTR_USER);
+}
+
+static bool f2fs_xattr_trusted_list(struct dentry *dentry)
+{
+	return capable(CAP_SYS_ADMIN);
+}
+
+static int f2fs_xattr_advise_get(const struct xattr_handler *handler,
+		struct dentry *unused, struct inode *inode,
+		const char *name, void *buffer, size_t size)
+{
+	if (buffer)
+		*((char *)buffer) = F2FS_I(inode)->i_advise;
+	return sizeof(char);
+}
+
+static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
+		struct mnt_idmap *idmap,
+		struct dentry *unused, struct inode *inode,
+		const char *name, const void *value,
+		size_t size, int flags)
+{
+	unsigned char old_advise = F2FS_I(inode)->i_advise;
+	unsigned char new_advise;
+
+	if (!inode_owner_or_capable(&nop_mnt_idmap, inode))
+		return -EPERM;
+	if (value == NULL)
+		return -EINVAL;
+
+	new_advise = *(char *)value;
+	if (new_advise & ~FADVISE_MODIFIABLE_BITS)
+		return -EINVAL;
+
+	new_advise = new_advise & FADVISE_MODIFIABLE_BITS;
+	new_advise |= old_advise & ~FADVISE_MODIFIABLE_BITS;
+
+	F2FS_I(inode)->i_advise = new_advise;
+	f2fs_mark_inode_dirty_sync(inode, true);
+	return 0;
+}
+
+#ifdef CONFIG_F2FS_FS_SECURITY
+static int f2fs_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+		void *folio)
+{
+	const struct xattr *xattr;
+	int err = 0;
+
+	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
+		err = f2fs_setxattr(inode, F2FS_XATTR_INDEX_SECURITY,
+				xattr->name, xattr->value,
+				xattr->value_len, folio, 0);
+		if (err < 0)
+			break;
+	}
+	return err;
+}
+
+int f2fs_init_security(struct inode *inode, struct inode *dir,
+				const struct qstr *qstr, struct folio *ifolio)
+{
+	return security_inode_init_security(inode, dir, qstr,
+				f2fs_initxattrs, ifolio);
+}
+#endif
+
+const struct xattr_handler f2fs_xattr_user_handler = {
+	.prefix	= XATTR_USER_PREFIX,
+	.flags	= F2FS_XATTR_INDEX_USER,
+	.list	= f2fs_xattr_user_list,
+	.get	= f2fs_xattr_generic_get,
+	.set	= f2fs_xattr_generic_set,
+};
+
+const struct xattr_handler f2fs_xattr_trusted_handler = {
+	.prefix	= XATTR_TRUSTED_PREFIX,
+	.flags	= F2FS_XATTR_INDEX_TRUSTED,
+	.list	= f2fs_xattr_trusted_list,
+	.get	= f2fs_xattr_generic_get,
+	.set	= f2fs_xattr_generic_set,
+};
+
+const struct xattr_handler f2fs_xattr_advise_handler = {
+	.name	= F2FS_SYSTEM_ADVISE_NAME,
+	.flags	= F2FS_XATTR_INDEX_ADVISE,
+	.get	= f2fs_xattr_advise_get,
+	.set	= f2fs_xattr_advise_set,
+};
+
+const struct xattr_handler f2fs_xattr_security_handler = {
+	.prefix	= XATTR_SECURITY_PREFIX,
+	.flags	= F2FS_XATTR_INDEX_SECURITY,
+	.get	= f2fs_xattr_generic_get,
+	.set	= f2fs_xattr_generic_set,
+};
+
+static const struct xattr_handler * const f2fs_xattr_handler_map[] = {
+	[F2FS_XATTR_INDEX_USER] = &f2fs_xattr_user_handler,
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+	[F2FS_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access,
+	[F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default,
+#endif
+	[F2FS_XATTR_INDEX_TRUSTED] = &f2fs_xattr_trusted_handler,
+#ifdef CONFIG_F2FS_FS_SECURITY
+	[F2FS_XATTR_INDEX_SECURITY] = &f2fs_xattr_security_handler,
+#endif
+	[F2FS_XATTR_INDEX_ADVISE] = &f2fs_xattr_advise_handler,
+};
+
+const struct xattr_handler * const f2fs_xattr_handlers[] = {
+	&f2fs_xattr_user_handler,
+	&f2fs_xattr_trusted_handler,
+#ifdef CONFIG_F2FS_FS_SECURITY
+	&f2fs_xattr_security_handler,
+#endif
+	&f2fs_xattr_advise_handler,
+	NULL,
+};
+
+static inline const char *f2fs_xattr_prefix(int index,
+					    struct dentry *dentry)
+{
+	const struct xattr_handler *handler = NULL;
+
+	if (index > 0 && index < ARRAY_SIZE(f2fs_xattr_handler_map))
+		handler = f2fs_xattr_handler_map[index];
+
+	if (!xattr_handler_can_list(handler, dentry))
+		return NULL;
+
+	return xattr_prefix(handler);
+}
+
+static struct f2fs_xattr_entry *__find_xattr(void *base_addr,
+				void *last_base_addr, void **last_addr,
+				int index, size_t len, const char *name)
+{
+	struct f2fs_xattr_entry *entry;
+
+	list_for_each_xattr(entry, base_addr) {
+		if ((void *)(entry) + sizeof(__u32) > last_base_addr ||
+			(void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) {
+			if (last_addr)
+				*last_addr = entry;
+			return NULL;
+		}
+
+		if (entry->e_name_index != index)
+			continue;
+		if (entry->e_name_len != len)
+			continue;
+		if (!memcmp(entry->e_name, name, len))
+			break;
+	}
+	return entry;
+}
+
+static struct f2fs_xattr_entry *__find_inline_xattr(struct inode *inode,
+				void *base_addr, void **last_addr, int index,
+				size_t len, const char *name)
+{
+	struct f2fs_xattr_entry *entry;
+	unsigned int inline_size = inline_xattr_size(inode);
+	void *max_addr = base_addr + inline_size;
+
+	entry = __find_xattr(base_addr, max_addr, last_addr, index, len, name);
+	if (!entry)
+		return NULL;
+
+	/* inline xattr header or entry across max inline xattr size */
+	if (IS_XATTR_LAST_ENTRY(entry) &&
+		(void *)entry + sizeof(__u32) > max_addr) {
+		*last_addr = entry;
+		return NULL;
+	}
+	return entry;
+}
+
+static int read_inline_xattr(struct inode *inode, struct folio *ifolio,
+							void *txattr_addr)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	unsigned int inline_size = inline_xattr_size(inode);
+	struct folio *folio = NULL;
+	void *inline_addr;
+
+	if (ifolio) {
+		inline_addr = inline_xattr_addr(inode, ifolio);
+	} else {
+		folio = f2fs_get_inode_folio(sbi, inode->i_ino);
+		if (IS_ERR(folio))
+			return PTR_ERR(folio);
+
+		inline_addr = inline_xattr_addr(inode, folio);
+	}
+	memcpy(txattr_addr, inline_addr, inline_size);
+	f2fs_folio_put(folio, true);
+
+	return 0;
+}
+
+static int read_xattr_block(struct inode *inode, void *txattr_addr)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+	unsigned int inline_size = inline_xattr_size(inode);
+	struct folio *xfolio;
+	void *xattr_addr;
+
+	/* The inode already has an extended attribute block. */
+	xfolio = f2fs_get_xnode_folio(sbi, xnid);
+	if (IS_ERR(xfolio))
+		return PTR_ERR(xfolio);
+
+	xattr_addr = folio_address(xfolio);
+	memcpy(txattr_addr + inline_size, xattr_addr, VALID_XATTR_BLOCK_SIZE);
+	f2fs_folio_put(xfolio, true);
+
+	return 0;
+}
+
+static int lookup_all_xattrs(struct inode *inode, struct folio *ifolio,
+				unsigned int index, unsigned int len,
+				const char *name, struct f2fs_xattr_entry **xe,
+				void **base_addr, int *base_size,
+				bool *is_inline)
+{
+	void *cur_addr, *txattr_addr, *last_txattr_addr;
+	void *last_addr = NULL;
+	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+	unsigned int inline_size = inline_xattr_size(inode);
+	int err;
+
+	if (!xnid && !inline_size)
+		return -ENODATA;
+
+	*base_size = XATTR_SIZE(inode) + XATTR_PADDING_SIZE;
+	txattr_addr = xattr_alloc(F2FS_I_SB(inode), *base_size, is_inline);
+	if (!txattr_addr)
+		return -ENOMEM;
+
+	last_txattr_addr = (void *)txattr_addr + XATTR_SIZE(inode);
+
+	/* read from inline xattr */
+	if (inline_size) {
+		err = read_inline_xattr(inode, ifolio, txattr_addr);
+		if (err)
+			goto out;
+
+		*xe = __find_inline_xattr(inode, txattr_addr, &last_addr,
+						index, len, name);
+		if (*xe) {
+			*base_size = inline_size;
+			goto check;
+		}
+	}
+
+	/* read from xattr node block */
+	if (xnid) {
+		err = read_xattr_block(inode, txattr_addr);
+		if (err)
+			goto out;
+	}
+
+	if (last_addr)
+		cur_addr = XATTR_HDR(last_addr) - 1;
+	else
+		cur_addr = txattr_addr;
+
+	*xe = __find_xattr(cur_addr, last_txattr_addr, NULL, index, len, name);
+	if (!*xe) {
+		f2fs_err(F2FS_I_SB(inode), "lookup inode (%llu) has corrupted xattr",
+								inode->i_ino);
+		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+		err = -ENODATA;
+		f2fs_handle_error(F2FS_I_SB(inode),
+					ERROR_CORRUPTED_XATTR);
+		fserror_report_file_metadata(inode, err, GFP_NOFS);
+		goto out;
+	}
+check:
+	if (IS_XATTR_LAST_ENTRY(*xe)) {
+		err = -ENODATA;
+		goto out;
+	}
+
+	*base_addr = txattr_addr;
+	return 0;
+out:
+	xattr_free(F2FS_I_SB(inode), txattr_addr, *is_inline);
+	return err;
+}
+
+static int read_all_xattrs(struct inode *inode, struct folio *ifolio,
+							void **base_addr)
+{
+	struct f2fs_xattr_header *header;
+	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+	unsigned int size = VALID_XATTR_BLOCK_SIZE;
+	unsigned int inline_size = inline_xattr_size(inode);
+	void *txattr_addr;
+	int err;
+
+	txattr_addr = f2fs_kzalloc(F2FS_I_SB(inode),
+			inline_size + size + XATTR_PADDING_SIZE, GFP_NOFS);
+	if (!txattr_addr)
+		return -ENOMEM;
+
+	/* read from inline xattr */
+	if (inline_size) {
+		err = read_inline_xattr(inode, ifolio, txattr_addr);
+		if (err)
+			goto fail;
+	}
+
+	/* read from xattr node block */
+	if (xnid) {
+		err = read_xattr_block(inode, txattr_addr);
+		if (err)
+			goto fail;
+	}
+
+	header = XATTR_HDR(txattr_addr);
+
+	/* never been allocated xattrs */
+	if (le32_to_cpu(header->h_magic) != F2FS_XATTR_MAGIC) {
+		header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC);
+		header->h_refcount = cpu_to_le32(1);
+	}
+	*base_addr = txattr_addr;
+	return 0;
+fail:
+	kfree(txattr_addr);
+	return err;
+}
+
+static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
+				void *txattr_addr, struct folio *ifolio)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	size_t inline_size = inline_xattr_size(inode);
+	struct folio *in_folio = NULL;
+	void *xattr_addr;
+	void *inline_addr = NULL;
+	struct folio *xfolio;
+	nid_t new_nid = 0;
+	int err = 0;
+
+	if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid)
+		if (!f2fs_alloc_nid(sbi, &new_nid))
+			return -ENOSPC;
+
+	/* write to inline xattr */
+	if (inline_size) {
+		if (ifolio) {
+			inline_addr = inline_xattr_addr(inode, ifolio);
+		} else {
+			in_folio = f2fs_get_inode_folio(sbi, inode->i_ino);
+			if (IS_ERR(in_folio)) {
+				f2fs_alloc_nid_failed(sbi, new_nid);
+				return PTR_ERR(in_folio);
+			}
+			inline_addr = inline_xattr_addr(inode, in_folio);
+		}
+
+		f2fs_folio_wait_writeback(ifolio ? ifolio : in_folio,
+							NODE, true, true);
+		/* no need to use xattr node block */
+		if (hsize <= inline_size) {
+			err = f2fs_truncate_xattr_node(inode);
+			f2fs_alloc_nid_failed(sbi, new_nid);
+			if (err) {
+				f2fs_folio_put(in_folio, true);
+				return err;
+			}
+			memcpy(inline_addr, txattr_addr, inline_size);
+			folio_mark_dirty(ifolio ? ifolio : in_folio);
+			goto in_page_out;
+		}
+	}
+
+	/* write to xattr node block */
+	if (F2FS_I(inode)->i_xattr_nid) {
+		xfolio = f2fs_get_xnode_folio(sbi, F2FS_I(inode)->i_xattr_nid);
+		if (IS_ERR(xfolio)) {
+			err = PTR_ERR(xfolio);
+			f2fs_alloc_nid_failed(sbi, new_nid);
+			goto in_page_out;
+		}
+		f2fs_bug_on(sbi, new_nid);
+		f2fs_folio_wait_writeback(xfolio, NODE, true, true);
+	} else {
+		struct dnode_of_data dn;
+
+		set_new_dnode(&dn, inode, NULL, NULL, new_nid);
+		xfolio = f2fs_new_node_folio(&dn, XATTR_NODE_OFFSET);
+		if (IS_ERR(xfolio)) {
+			err = PTR_ERR(xfolio);
+			f2fs_alloc_nid_failed(sbi, new_nid);
+			goto in_page_out;
+		}
+		f2fs_alloc_nid_done(sbi, new_nid);
+	}
+	xattr_addr = folio_address(xfolio);
+
+	if (inline_size)
+		memcpy(inline_addr, txattr_addr, inline_size);
+	memcpy(xattr_addr, txattr_addr + inline_size, VALID_XATTR_BLOCK_SIZE);
+
+	if (inline_size)
+		folio_mark_dirty(ifolio ? ifolio : in_folio);
+	folio_mark_dirty(xfolio);
+
+	f2fs_folio_put(xfolio, true);
+in_page_out:
+	f2fs_folio_put(in_folio, true);
+	return err;
+}
+
+int f2fs_getxattr(struct inode *inode, int index, const char *name,
+		void *buffer, size_t buffer_size, struct folio *ifolio)
+{
+	struct f2fs_xattr_entry *entry = NULL;
+	int error;
+	unsigned int size, len;
+	void *base_addr = NULL;
+	int base_size;
+	bool is_inline;
+
+	if (name == NULL)
+		return -EINVAL;
+
+	len = strlen(name);
+	if (len > F2FS_NAME_LEN)
+		return -ERANGE;
+
+	if (!ifolio)
+		f2fs_down_read(&F2FS_I(inode)->i_xattr_sem);
+	error = lookup_all_xattrs(inode, ifolio, index, len, name,
+				&entry, &base_addr, &base_size, &is_inline);
+	if (!ifolio)
+		f2fs_up_read(&F2FS_I(inode)->i_xattr_sem);
+	if (error)
+		return error;
+
+	size = le16_to_cpu(entry->e_value_size);
+
+	if (buffer && size > buffer_size) {
+		error = -ERANGE;
+		goto out;
+	}
+
+	if (buffer) {
+		char *pval = entry->e_name + entry->e_name_len;
+
+		if (base_size - (pval - (char *)base_addr) < size) {
+			error = -ERANGE;
+			goto out;
+		}
+		memcpy(buffer, pval, size);
+	}
+	error = size;
+out:
+	xattr_free(F2FS_I_SB(inode), base_addr, is_inline);
+	return error;
+}
+
+ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
+{
+	struct inode *inode = d_inode(dentry);
+	struct f2fs_xattr_entry *entry;
+	void *base_addr, *last_base_addr;
+	int error;
+	size_t rest = buffer_size;
+
+	f2fs_down_read(&F2FS_I(inode)->i_xattr_sem);
+	error = read_all_xattrs(inode, NULL, &base_addr);
+	f2fs_up_read(&F2FS_I(inode)->i_xattr_sem);
+	if (error)
+		return error;
+
+	last_base_addr = (void *)base_addr + XATTR_SIZE(inode);
+
+	list_for_each_xattr(entry, base_addr) {
+		const char *prefix;
+		size_t prefix_len;
+		size_t size;
+
+		if ((void *)(entry) + sizeof(__u32) > last_base_addr ||
+			(void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) {
+			f2fs_err(F2FS_I_SB(inode), "list inode (%llu) has corrupted xattr",
+						inode->i_ino);
+			set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+			f2fs_handle_error(F2FS_I_SB(inode),
+						ERROR_CORRUPTED_XATTR);
+			fserror_report_file_metadata(inode,
+						-EFSCORRUPTED, GFP_NOFS);
+			error = -EFSCORRUPTED;
+			goto cleanup;
+		}
+
+		prefix = f2fs_xattr_prefix(entry->e_name_index, dentry);
+		if (!prefix)
+			continue;
+
+		prefix_len = strlen(prefix);
+		size = prefix_len + entry->e_name_len + 1;
+		if (buffer) {
+			if (size > rest) {
+				error = -ERANGE;
+				goto cleanup;
+			}
+			memcpy(buffer, prefix, prefix_len);
+			buffer += prefix_len;
+			memcpy(buffer, entry->e_name, entry->e_name_len);
+			buffer += entry->e_name_len;
+			*buffer++ = 0;
+		}
+		rest -= size;
+	}
+	error = buffer_size - rest;
+cleanup:
+	kfree(base_addr);
+	return error;
+}
+
+static bool f2fs_xattr_value_same(struct f2fs_xattr_entry *entry,
+					const void *value, size_t size)
+{
+	void *pval = entry->e_name + entry->e_name_len;
+
+	return (le16_to_cpu(entry->e_value_size) == size) &&
+					!memcmp(pval, value, size);
+}
+
+static int __f2fs_setxattr(struct inode *inode, int index,
+			const char *name, const void *value, size_t size,
+			struct folio *ifolio, int flags)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_xattr_entry *here, *last;
+	void *base_addr, *last_base_addr;
+	int found, newsize;
+	size_t len;
+	__u32 new_hsize;
+	int error;
+
+	if (name == NULL)
+		return -EINVAL;
+
+	if (value == NULL)
+		size = 0;
+
+	len = strlen(name);
+
+	if (len > F2FS_NAME_LEN)
+		return -ERANGE;
+
+	if (size > MAX_VALUE_LEN(inode))
+		return -E2BIG;
+retry:
+	error = read_all_xattrs(inode, ifolio, &base_addr);
+	if (error)
+		return error;
+
+	last_base_addr = (void *)base_addr + XATTR_SIZE(inode);
+
+	/* find entry with wanted name. */
+	here = __find_xattr(base_addr, last_base_addr, NULL, index, len, name);
+	if (!here) {
+		if (!F2FS_I(inode)->i_xattr_nid) {
+			error = f2fs_recover_xattr_data(inode, NULL);
+			f2fs_notice(F2FS_I_SB(inode),
+				"recover xattr in inode (%llu), error(%d)",
+					inode->i_ino, error);
+			if (!error) {
+				kfree(base_addr);
+				goto retry;
+			}
+		}
+		f2fs_err(F2FS_I_SB(inode), "set inode (%llu) has corrupted xattr",
+								inode->i_ino);
+		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+		error = -EFSCORRUPTED;
+		f2fs_handle_error(F2FS_I_SB(inode),
+					ERROR_CORRUPTED_XATTR);
+		fserror_report_file_metadata(inode, error, GFP_NOFS);
+		goto exit;
+	}
+
+	found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
+
+	if (found) {
+		if ((flags & XATTR_CREATE)) {
+			error = -EEXIST;
+			goto exit;
+		}
+
+		if (value && f2fs_xattr_value_same(here, value, size))
+			goto same;
+	} else if ((flags & XATTR_REPLACE)) {
+		error = -ENODATA;
+		goto exit;
+	}
+
+	last = here;
+	while (!IS_XATTR_LAST_ENTRY(last)) {
+		if ((void *)(last) + sizeof(__u32) > last_base_addr ||
+			(void *)XATTR_NEXT_ENTRY(last) > last_base_addr) {
+			f2fs_err(F2FS_I_SB(inode), "inode (%llu) has invalid last xattr entry, entry_size: %zu",
+					inode->i_ino, ENTRY_SIZE(last));
+			set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+			error = -EFSCORRUPTED;
+			f2fs_handle_error(F2FS_I_SB(inode),
+						ERROR_CORRUPTED_XATTR);
+			fserror_report_file_metadata(inode, error, GFP_NOFS);
+			goto exit;
+		}
+		last = XATTR_NEXT_ENTRY(last);
+	}
+
+	newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + len + size);
+
+	/* 1. Check space */
+	if (value) {
+		int free;
+		/*
+		 * If value is NULL, it is remove operation.
+		 * In case of update operation, we calculate free.
+		 */
+		free = MIN_OFFSET(inode) - ((char *)last - (char *)base_addr);
+		if (found)
+			free = free + ENTRY_SIZE(here);
+
+		if (unlikely(free < newsize)) {
+			error = -E2BIG;
+			goto exit;
+		}
+	}
+
+	/* 2. Remove old entry */
+	if (found) {
+		/*
+		 * If entry is found, remove old entry.
+		 * If not found, remove operation is not needed.
+		 */
+		struct f2fs_xattr_entry *next = XATTR_NEXT_ENTRY(here);
+		int oldsize = ENTRY_SIZE(here);
+
+		memmove(here, next, (char *)last - (char *)next);
+		last = (struct f2fs_xattr_entry *)((char *)last - oldsize);
+		memset(last, 0, oldsize);
+	}
+
+	new_hsize = (char *)last - (char *)base_addr;
+
+	/* 3. Write new entry */
+	if (value) {
+		char *pval;
+		/*
+		 * Before we come here, old entry is removed.
+		 * We just write new entry.
+		 */
+		last->e_name_index = index;
+		last->e_name_len = len;
+		memcpy(last->e_name, name, len);
+		pval = last->e_name + len;
+		memcpy(pval, value, size);
+		last->e_value_size = cpu_to_le16(size);
+		new_hsize += newsize;
+		/*
+		 * Explicitly add the null terminator.  The unused xattr space
+		 * is supposed to always be zeroed, which would make this
+		 * unnecessary, but don't depend on that.
+		 */
+		*(u32 *)((u8 *)last + newsize) = 0;
+	}
+
+	error = write_all_xattrs(inode, new_hsize, base_addr, ifolio);
+	if (error)
+		goto exit;
+
+	if (index == F2FS_XATTR_INDEX_ENCRYPTION &&
+			!strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
+		f2fs_set_encrypted_inode(inode);
+
+	if (!S_ISDIR(inode->i_mode))
+		goto same;
+	/*
+	 * In restrict mode, fsync() always try to trigger checkpoint for all
+	 * metadata consistency, in other mode, it triggers checkpoint when
+	 * parent's xattr metadata was updated.
+	 */
+	if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT)
+		set_sbi_flag(sbi, SBI_NEED_CP);
+	else
+		f2fs_add_ino_entry(sbi, inode->i_ino, XATTR_DIR_INO);
+same:
+	if (is_inode_flag_set(inode, FI_ACL_MODE)) {
+		inode->i_mode = F2FS_I(inode)->i_acl_mode;
+		clear_inode_flag(inode, FI_ACL_MODE);
+	}
+
+	inode_set_ctime_current(inode);
+	f2fs_mark_inode_dirty_sync(inode, true);
+exit:
+	kfree(base_addr);
+	return error;
+}
+
+int f2fs_setxattr(struct inode *inode, int index, const char *name,
+				const void *value, size_t size,
+				struct folio *ifolio, int flags)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_lock_context lc;
+	int err;
+
+	if (unlikely(f2fs_cp_error(sbi)))
+		return -EIO;
+	if (!f2fs_is_checkpoint_ready(sbi))
+		return -ENOSPC;
+
+	err = f2fs_dquot_initialize(inode);
+	if (err)
+		return err;
+
+	/* this case is only from f2fs_init_inode_metadata */
+	if (ifolio)
+		return __f2fs_setxattr(inode, index, name, value,
+						size, ifolio, flags);
+	f2fs_balance_fs(sbi, true);
+
+	f2fs_lock_op(sbi, &lc);
+	f2fs_down_write(&F2FS_I(inode)->i_xattr_sem);
+	err = __f2fs_setxattr(inode, index, name, value, size, NULL, flags);
+	f2fs_up_write(&F2FS_I(inode)->i_xattr_sem);
+	f2fs_unlock_op(sbi, &lc);
+
+	f2fs_update_time(sbi, REQ_TIME);
+	return err;
+}
+
+int __init f2fs_init_xattr_cache(void)
+{
+	inline_xattr_slab = f2fs_kmem_cache_create("f2fs_xattr_entry",
+					DEFAULT_XATTR_SLAB_SIZE);
+	return inline_xattr_slab ? 0 : -ENOMEM;
+}
+
+void f2fs_destroy_xattr_cache(void)
+{
+	kmem_cache_destroy(inline_xattr_slab);
+}

linux-7.2.3/fs/f2fs/xattr.h

@@ -0,0 +1,169 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * fs/f2fs/xattr.h
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * Portions of this code from linux/fs/ext2/xattr.h
+ *
+ * On-disk format of extended attributes for the ext2 filesystem.
+ *
+ * (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ */
+#ifndef __F2FS_XATTR_H__
+#define __F2FS_XATTR_H__
+
+#include <linux/init.h>
+#include <linux/xattr.h>
+
+/* Magic value in attribute blocks */
+#define F2FS_XATTR_MAGIC                0xF2F52011
+
+/* Maximum number of references to one attribute block */
+#define F2FS_XATTR_REFCOUNT_MAX         1024
+
+/* Name indexes */
+#define F2FS_SYSTEM_ADVISE_NAME			"system.advise"
+#define F2FS_XATTR_INDEX_USER			1
+#define F2FS_XATTR_INDEX_POSIX_ACL_ACCESS	2
+#define F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT	3
+#define F2FS_XATTR_INDEX_TRUSTED		4
+#define F2FS_XATTR_INDEX_LUSTRE			5
+#define F2FS_XATTR_INDEX_SECURITY		6
+#define F2FS_XATTR_INDEX_ADVISE			7
+/* Should be same as EXT4_XATTR_INDEX_ENCRYPTION */
+#define F2FS_XATTR_INDEX_ENCRYPTION		9
+#define F2FS_XATTR_INDEX_VERITY			11
+
+#define F2FS_XATTR_NAME_ENCRYPTION_CONTEXT	"c"
+#define F2FS_XATTR_NAME_VERITY			"v"
+
+struct f2fs_xattr_header {
+	__le32  h_magic;        /* magic number for identification */
+	__le32  h_refcount;     /* reference count */
+	__u32   h_reserved[4];  /* zero right now */
+};
+
+struct f2fs_xattr_entry {
+	__u8    e_name_index;
+	__u8    e_name_len;
+	__le16  e_value_size;   /* size of attribute value */
+	char    e_name[];      /* attribute name */
+};
+
+#define XATTR_HDR(ptr)		((struct f2fs_xattr_header *)(ptr))
+#define XATTR_ENTRY(ptr)	((struct f2fs_xattr_entry *)(ptr))
+#define XATTR_FIRST_ENTRY(ptr)	(XATTR_ENTRY(XATTR_HDR(ptr) + 1))
+#define XATTR_ROUND		(3)
+
+#define XATTR_ALIGN(size)	(((size) + XATTR_ROUND) & ~XATTR_ROUND)
+
+#define ENTRY_SIZE(entry) (XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + \
+			(entry)->e_name_len + le16_to_cpu((entry)->e_value_size)))
+
+#define XATTR_NEXT_ENTRY(entry)	((struct f2fs_xattr_entry *)((char *)(entry) +\
+			ENTRY_SIZE(entry)))
+
+#define IS_XATTR_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0)
+
+#define list_for_each_xattr(entry, addr) \
+		for (entry = XATTR_FIRST_ENTRY(addr);\
+				!IS_XATTR_LAST_ENTRY(entry);\
+				entry = XATTR_NEXT_ENTRY(entry))
+#define VALID_XATTR_BLOCK_SIZE	(PAGE_SIZE - sizeof(struct node_footer))
+#define XATTR_PADDING_SIZE	(sizeof(__u32))
+#define XATTR_SIZE(i)		((F2FS_I(i)->i_xattr_nid ?		\
+					VALID_XATTR_BLOCK_SIZE : 0) +	\
+						(inline_xattr_size(i)))
+#define MIN_OFFSET(i)		XATTR_ALIGN(inline_xattr_size(i) +	\
+						VALID_XATTR_BLOCK_SIZE)
+
+#define MAX_VALUE_LEN(i)	(MIN_OFFSET(i) -			\
+				sizeof(struct f2fs_xattr_header) -	\
+				sizeof(struct f2fs_xattr_entry))
+
+#define MIN_INLINE_XATTR_SIZE (sizeof(struct f2fs_xattr_header) / sizeof(__le32))
+#define MAX_INLINE_XATTR_SIZE						\
+			(DEF_ADDRS_PER_INODE -				\
+			F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) -	\
+			DEF_INLINE_RESERVED_SIZE -			\
+			MIN_INLINE_DENTRY_SIZE / sizeof(__le32))
+#define DEFAULT_XATTR_SLAB_SIZE	(DEFAULT_INLINE_XATTR_ADDRS *		\
+				sizeof(__le32) + XATTR_PADDING_SIZE)
+
+/*
+ * On-disk structure of f2fs_xattr
+ * We use inline xattrs space + 1 block for xattr.
+ *
+ * +--------------------+
+ * | f2fs_xattr_header  |
+ * |                    |
+ * +--------------------+
+ * | f2fs_xattr_entry   |
+ * | .e_name_index = 1  |
+ * | .e_name_len = 3    |
+ * | .e_value_size = 14 |
+ * | .e_name = "foo"    |
+ * | "value_of_xattr"   |<- value_offs = e_name + e_name_len
+ * +--------------------+
+ * | f2fs_xattr_entry   |
+ * | .e_name_index = 4  |
+ * | .e_name = "bar"    |
+ * +--------------------+
+ * |                    |
+ * |        Free        |
+ * |                    |
+ * +--------------------+<- MIN_OFFSET
+ * |   node_footer      |
+ * | (nid, ino, offset) |
+ * +--------------------+
+ *
+ **/
+
+#ifdef CONFIG_F2FS_FS_XATTR
+extern const struct xattr_handler f2fs_xattr_user_handler;
+extern const struct xattr_handler f2fs_xattr_trusted_handler;
+extern const struct xattr_handler f2fs_xattr_advise_handler;
+extern const struct xattr_handler f2fs_xattr_security_handler;
+
+extern const struct xattr_handler * const f2fs_xattr_handlers[];
+
+int f2fs_setxattr(struct inode *, int, const char *, const void *,
+		size_t, struct folio *, int);
+int f2fs_getxattr(struct inode *, int, const char *, void *,
+		size_t, struct folio *);
+ssize_t f2fs_listxattr(struct dentry *, char *, size_t);
+int __init f2fs_init_xattr_cache(void);
+void f2fs_destroy_xattr_cache(void);
+#else
+
+#define f2fs_xattr_handlers	NULL
+#define f2fs_listxattr		NULL
+static inline int f2fs_setxattr(struct inode *inode, int index,
+		const char *name, const void *value, size_t size,
+		struct folio *folio, int flags)
+{
+	return -EOPNOTSUPP;
+}
+static inline int f2fs_getxattr(struct inode *inode, int index,
+			const char *name, void *buffer,
+			size_t buffer_size, struct folio *dfolio)
+{
+	return -EOPNOTSUPP;
+}
+static inline int __init f2fs_init_xattr_cache(void) { return 0; }
+static inline void f2fs_destroy_xattr_cache(void) { }
+#endif
+
+#ifdef CONFIG_F2FS_FS_SECURITY
+int f2fs_init_security(struct inode *, struct inode *,
+				const struct qstr *, struct folio *);
+#else
+static inline int f2fs_init_security(struct inode *inode, struct inode *dir,
+				const struct qstr *qstr, struct folio *ifolio)
+{
+	return 0;
+}
+#endif
+#endif /* __F2FS_XATTR_H__ */