Initial commit; kernel source import

fs/f2fs/Kconfig

@@ -0,0 +1,53 @@
+config F2FS_FS
+	tristate "F2FS filesystem support (EXPERIMENTAL)"
+	depends on BLOCK
+	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 && DEBUG_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 file system 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, or visit
+	  <http://acl.bestbits.at/> 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
+	  gourps beyond the owner/group/world scheme.
+
+	  To learn more about Access Control Lists, visit the POSIX ACLs for
+	  Linux website <http://acl.bestbits.at/>.
+
+	  If you don't know what Access Control Lists are, say N

fs/f2fs/Makefile

@@ -0,0 +1,7 @@
+obj-$(CONFIG_F2FS_FS) += f2fs.o
+
+f2fs-y		:= dir.o file.o inode.o namei.o hash.o super.o
+f2fs-y		+= checkpoint.o gc.o data.o node.o segment.o recovery.o
+f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
+f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
+f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o

fs/f2fs/acl.c

@@ -0,0 +1,410 @@
+/*
+ * 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>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/f2fs_fs.h>
+#include "f2fs.h"
+#include "xattr.h"
+#include "acl.h"
+
+#define get_inode_mode(i)	((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \
+					(F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
+
+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;
+	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 (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_KERNEL);
+	if (!acl)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < count; i++) {
+
+		if ((char *)entry > end)
+			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:
+			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:
+			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(-EINVAL);
+}
+
+static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
+{
+	struct f2fs_acl_header *f2fs_acl;
+	struct f2fs_acl_entry *entry;
+	int i;
+
+	f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
+			sizeof(struct f2fs_acl_entry), GFP_KERNEL);
+	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);
+}
+
+struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	int name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT;
+	void *value = NULL;
+	struct posix_acl *acl;
+	int retval;
+
+	if (!test_opt(sbi, POSIX_ACL))
+		return NULL;
+
+	acl = get_cached_acl(inode, type);
+	if (acl != ACL_NOT_CACHED)
+		return acl;
+
+	if (type == ACL_TYPE_ACCESS)
+		name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
+
+	retval = f2fs_getxattr(inode, name_index, "", NULL, 0);
+	if (retval > 0) {
+		value = kmalloc(retval, GFP_KERNEL);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		retval = f2fs_getxattr(inode, name_index, "", value, retval);
+	}
+
+	if (retval > 0)
+		acl = f2fs_acl_from_disk(value, retval);
+	else if (retval == -ENODATA)
+		acl = NULL;
+	else
+		acl = ERR_PTR(retval);
+	kfree(value);
+
+	if (!IS_ERR(acl))
+		set_cached_acl(inode, type, acl);
+
+	return acl;
+}
+
+static int f2fs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	int name_index;
+	void *value = NULL;
+	size_t size = 0;
+	int error;
+
+	if (!test_opt(sbi, POSIX_ACL))
+		return 0;
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
+		if (acl) {
+			error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+			if (error)
+				return error;
+			set_acl_inode(fi, inode->i_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(acl, &size);
+		if (IS_ERR(value)) {
+			cond_clear_inode_flag(fi, FI_ACL_MODE);
+			return (int)PTR_ERR(value);
+		}
+	}
+
+	error = f2fs_setxattr(inode, name_index, "", value, size);
+
+	kfree(value);
+	if (!error)
+		set_cached_acl(inode, type, acl);
+
+	cond_clear_inode_flag(fi, FI_ACL_MODE);
+	return error;
+}
+
+int f2fs_init_acl(struct inode *inode, struct inode *dir)
+{
+	struct posix_acl *acl = NULL;
+	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+	int error = 0;
+
+	if (!S_ISLNK(inode->i_mode)) {
+		if (test_opt(sbi, POSIX_ACL)) {
+			acl = f2fs_get_acl(dir, ACL_TYPE_DEFAULT);
+			if (IS_ERR(acl))
+				return PTR_ERR(acl);
+		}
+		if (!acl)
+			inode->i_mode &= ~current_umask();
+	}
+
+	if (test_opt(sbi, POSIX_ACL) && acl) {
+
+		if (S_ISDIR(inode->i_mode)) {
+			error = f2fs_set_acl(inode, ACL_TYPE_DEFAULT, acl);
+			if (error)
+				goto cleanup;
+		}
+		error = posix_acl_create(&acl, GFP_KERNEL, &inode->i_mode);
+		if (error < 0)
+			return error;
+		if (error > 0)
+			error = f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl);
+	}
+cleanup:
+	posix_acl_release(acl);
+	return error;
+}
+
+int f2fs_acl_chmod(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct posix_acl *acl;
+	int error;
+	umode_t mode = get_inode_mode(inode);
+
+	if (!test_opt(sbi, POSIX_ACL))
+		return 0;
+	if (S_ISLNK(mode))
+		return -EOPNOTSUPP;
+
+	acl = f2fs_get_acl(inode, ACL_TYPE_ACCESS);
+	if (IS_ERR(acl) || !acl)
+		return PTR_ERR(acl);
+
+	error = posix_acl_chmod(&acl, GFP_KERNEL, mode);
+	if (error)
+		return error;
+	error = f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl);
+	posix_acl_release(acl);
+	return error;
+}
+
+static size_t f2fs_xattr_list_acl(struct dentry *dentry, char *list,
+		size_t list_size, const char *name, size_t name_len, int type)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+	const char *xname = POSIX_ACL_XATTR_DEFAULT;
+	size_t size;
+
+	if (!test_opt(sbi, POSIX_ACL))
+		return 0;
+
+	if (type == ACL_TYPE_ACCESS)
+		xname = POSIX_ACL_XATTR_ACCESS;
+
+	size = strlen(xname) + 1;
+	if (list && size <= list_size)
+		memcpy(list, xname, size);
+	return size;
+}
+
+static int f2fs_xattr_get_acl(struct dentry *dentry, const char *name,
+		void *buffer, size_t size, int type)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+	struct posix_acl *acl;
+	int error;
+
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	if (!test_opt(sbi, POSIX_ACL))
+		return -EOPNOTSUPP;
+
+	acl = f2fs_get_acl(dentry->d_inode, type);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (!acl)
+		return -ENODATA;
+	error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
+	posix_acl_release(acl);
+
+	return error;
+}
+
+static int f2fs_xattr_set_acl(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags, int type)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+	struct inode *inode = dentry->d_inode;
+	struct posix_acl *acl = NULL;
+	int error;
+
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	if (!test_opt(sbi, POSIX_ACL))
+		return -EOPNOTSUPP;
+	if (!inode_owner_or_capable(inode))
+		return -EPERM;
+
+	if (value) {
+		acl = posix_acl_from_xattr(&init_user_ns, value, size);
+		if (IS_ERR(acl))
+			return PTR_ERR(acl);
+		if (acl) {
+			error = posix_acl_valid(acl);
+			if (error)
+				goto release_and_out;
+		}
+	} else {
+		acl = NULL;
+	}
+
+	error = f2fs_set_acl(inode, type, acl);
+
+release_and_out:
+	posix_acl_release(acl);
+	return error;
+}
+
+const struct xattr_handler f2fs_xattr_acl_default_handler = {
+	.prefix = POSIX_ACL_XATTR_DEFAULT,
+	.flags = ACL_TYPE_DEFAULT,
+	.list = f2fs_xattr_list_acl,
+	.get = f2fs_xattr_get_acl,
+	.set = f2fs_xattr_set_acl,
+};
+
+const struct xattr_handler f2fs_xattr_acl_access_handler = {
+	.prefix = POSIX_ACL_XATTR_ACCESS,
+	.flags = ACL_TYPE_ACCESS,
+	.list = f2fs_xattr_list_acl,
+	.get = f2fs_xattr_get_acl,
+	.set = f2fs_xattr_set_acl,
+};

fs/f2fs/acl.h

@@ -0,0 +1,57 @@
+/*
+ * 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>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#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
+
+extern struct posix_acl *f2fs_get_acl(struct inode *inode, int type);
+extern int f2fs_acl_chmod(struct inode *inode);
+extern int f2fs_init_acl(struct inode *inode, struct inode *dir);
+#else
+#define f2fs_check_acl	NULL
+#define f2fs_get_acl	NULL
+#define f2fs_set_acl	NULL
+
+static inline int f2fs_acl_chmod(struct inode *inode)
+{
+	return 0;
+}
+
+static inline int f2fs_init_acl(struct inode *inode, struct inode *dir)
+{
+	return 0;
+}
+#endif
+#endif /* __F2FS_ACL_H__ */

fs/f2fs/checkpoint.c

@@ -0,0 +1,785 @@
+/*
+ * fs/f2fs/checkpoint.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/bio.h>
+#include <linux/mpage.h>
+#include <linux/writeback.h>
+#include <linux/blkdev.h>
+#include <linux/f2fs_fs.h>
+#include <linux/pagevec.h>
+#include <linux/swap.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include "segment.h"
+#include <trace/events/f2fs.h>
+
+static struct kmem_cache *orphan_entry_slab;
+static struct kmem_cache *inode_entry_slab;
+
+/*
+ * We guarantee no failure on the returned page.
+ */
+struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+	struct address_space *mapping = sbi->meta_inode->i_mapping;
+	struct page *page = NULL;
+repeat:
+	page = grab_cache_page(mapping, index);
+	if (!page) {
+		cond_resched();
+		goto repeat;
+	}
+
+	/* We wait writeback only inside grab_meta_page() */
+	wait_on_page_writeback(page);
+	SetPageUptodate(page);
+	return page;
+}
+
+/*
+ * We guarantee no failure on the returned page.
+ */
+struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+	struct address_space *mapping = sbi->meta_inode->i_mapping;
+	struct page *page;
+repeat:
+	page = grab_cache_page(mapping, index);
+	if (!page) {
+		cond_resched();
+		goto repeat;
+	}
+	if (PageUptodate(page))
+		goto out;
+
+	if (f2fs_readpage(sbi, page, index, READ_SYNC))
+		goto repeat;
+
+	lock_page(page);
+	if (page->mapping != mapping) {
+		f2fs_put_page(page, 1);
+		goto repeat;
+	}
+out:
+	mark_page_accessed(page);
+	return page;
+}
+
+static int f2fs_write_meta_page(struct page *page,
+				struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+
+	/* Should not write any meta pages, if any IO error was occurred */
+	if (wbc->for_reclaim ||
+			is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ERROR_FLAG)) {
+		dec_page_count(sbi, F2FS_DIRTY_META);
+		wbc->pages_skipped++;
+		set_page_dirty(page);
+		return AOP_WRITEPAGE_ACTIVATE;
+	}
+
+	wait_on_page_writeback(page);
+
+	write_meta_page(sbi, page);
+	dec_page_count(sbi, F2FS_DIRTY_META);
+	unlock_page(page);
+	return 0;
+}
+
+static int f2fs_write_meta_pages(struct address_space *mapping,
+				struct writeback_control *wbc)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
+	struct block_device *bdev = sbi->sb->s_bdev;
+	long written;
+
+	if (wbc->for_kupdate)
+		return 0;
+
+	if (get_pages(sbi, F2FS_DIRTY_META) == 0)
+		return 0;
+
+	/* if mounting is failed, skip writing node pages */
+	mutex_lock(&sbi->cp_mutex);
+	written = sync_meta_pages(sbi, META, bio_get_nr_vecs(bdev));
+	mutex_unlock(&sbi->cp_mutex);
+	wbc->nr_to_write -= written;
+	return 0;
+}
+
+long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
+						long nr_to_write)
+{
+	struct address_space *mapping = sbi->meta_inode->i_mapping;
+	pgoff_t index = 0, end = LONG_MAX;
+	struct pagevec pvec;
+	long nwritten = 0;
+	struct writeback_control wbc = {
+		.for_reclaim = 0,
+	};
+
+	pagevec_init(&pvec, 0);
+
+	while (index <= end) {
+		int i, nr_pages;
+		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+				PAGECACHE_TAG_DIRTY,
+				min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+		if (nr_pages == 0)
+			break;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+			lock_page(page);
+			BUG_ON(page->mapping != mapping);
+			BUG_ON(!PageDirty(page));
+			clear_page_dirty_for_io(page);
+			if (f2fs_write_meta_page(page, &wbc)) {
+				unlock_page(page);
+				break;
+			}
+			if (nwritten++ >= nr_to_write)
+				break;
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+
+	if (nwritten)
+		f2fs_submit_bio(sbi, type, nr_to_write == LONG_MAX);
+
+	return nwritten;
+}
+
+static int f2fs_set_meta_page_dirty(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
+
+	SetPageUptodate(page);
+	if (!PageDirty(page)) {
+		__set_page_dirty_nobuffers(page);
+		inc_page_count(sbi, F2FS_DIRTY_META);
+		return 1;
+	}
+	return 0;
+}
+
+const struct address_space_operations f2fs_meta_aops = {
+	.writepage	= f2fs_write_meta_page,
+	.writepages	= f2fs_write_meta_pages,
+	.set_page_dirty	= f2fs_set_meta_page_dirty,
+};
+
+int check_orphan_space(struct f2fs_sb_info *sbi)
+{
+	unsigned int max_orphans;
+	int err = 0;
+
+	/*
+	 * considering 512 blocks in a segment 5 blocks are needed for cp
+	 * and log segment summaries. Remaining blocks are used to keep
+	 * orphan entries with the limitation one reserved segment
+	 * for cp pack we can have max 1020*507 orphan entries
+	 */
+	max_orphans = (sbi->blocks_per_seg - 5) * F2FS_ORPHANS_PER_BLOCK;
+	mutex_lock(&sbi->orphan_inode_mutex);
+	if (sbi->n_orphans >= max_orphans)
+		err = -ENOSPC;
+	mutex_unlock(&sbi->orphan_inode_mutex);
+	return err;
+}
+
+void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
+{
+	struct list_head *head, *this;
+	struct orphan_inode_entry *new = NULL, *orphan = NULL;
+
+	mutex_lock(&sbi->orphan_inode_mutex);
+	head = &sbi->orphan_inode_list;
+	list_for_each(this, head) {
+		orphan = list_entry(this, struct orphan_inode_entry, list);
+		if (orphan->ino == ino)
+			goto out;
+		if (orphan->ino > ino)
+			break;
+		orphan = NULL;
+	}
+retry:
+	new = kmem_cache_alloc(orphan_entry_slab, GFP_ATOMIC);
+	if (!new) {
+		cond_resched();
+		goto retry;
+	}
+	new->ino = ino;
+
+	/* add new_oentry into list which is sorted by inode number */
+	if (orphan)
+		list_add(&new->list, this->prev);
+	else
+		list_add_tail(&new->list, head);
+
+	sbi->n_orphans++;
+out:
+	mutex_unlock(&sbi->orphan_inode_mutex);
+}
+
+void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
+{
+	struct list_head *this, *next, *head;
+	struct orphan_inode_entry *orphan;
+
+	mutex_lock(&sbi->orphan_inode_mutex);
+	head = &sbi->orphan_inode_list;
+	list_for_each_safe(this, next, head) {
+		orphan = list_entry(this, struct orphan_inode_entry, list);
+		if (orphan->ino == ino) {
+			list_del(&orphan->list);
+			kmem_cache_free(orphan_entry_slab, orphan);
+			sbi->n_orphans--;
+			break;
+		}
+	}
+	mutex_unlock(&sbi->orphan_inode_mutex);
+}
+
+static void recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
+{
+	struct inode *inode = f2fs_iget(sbi->sb, ino);
+	BUG_ON(IS_ERR(inode));
+	clear_nlink(inode);
+
+	/* truncate all the data during iput */
+	iput(inode);
+}
+
+int recover_orphan_inodes(struct f2fs_sb_info *sbi)
+{
+	block_t start_blk, orphan_blkaddr, i, j;
+
+	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG))
+		return 0;
+
+	sbi->por_doing = 1;
+	start_blk = __start_cp_addr(sbi) + 1;
+	orphan_blkaddr = __start_sum_addr(sbi) - 1;
+
+	for (i = 0; i < orphan_blkaddr; i++) {
+		struct page *page = get_meta_page(sbi, start_blk + i);
+		struct f2fs_orphan_block *orphan_blk;
+
+		orphan_blk = (struct f2fs_orphan_block *)page_address(page);
+		for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) {
+			nid_t ino = le32_to_cpu(orphan_blk->ino[j]);
+			recover_orphan_inode(sbi, ino);
+		}
+		f2fs_put_page(page, 1);
+	}
+	/* clear Orphan Flag */
+	clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG);
+	sbi->por_doing = 0;
+	return 0;
+}
+
+static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
+{
+	struct list_head *head, *this, *next;
+	struct f2fs_orphan_block *orphan_blk = NULL;
+	struct page *page = NULL;
+	unsigned int nentries = 0;
+	unsigned short index = 1;
+	unsigned short orphan_blocks;
+
+	orphan_blocks = (unsigned short)((sbi->n_orphans +
+		(F2FS_ORPHANS_PER_BLOCK - 1)) / F2FS_ORPHANS_PER_BLOCK);
+
+	mutex_lock(&sbi->orphan_inode_mutex);
+	head = &sbi->orphan_inode_list;
+
+	/* loop for each orphan inode entry and write them in Jornal block */
+	list_for_each_safe(this, next, head) {
+		struct orphan_inode_entry *orphan;
+
+		orphan = list_entry(this, struct orphan_inode_entry, list);
+
+		if (nentries == F2FS_ORPHANS_PER_BLOCK) {
+			/*
+			 * an orphan block is full of 1020 entries,
+			 * then we need to flush current orphan blocks
+			 * and bring another one in memory
+			 */
+			orphan_blk->blk_addr = cpu_to_le16(index);
+			orphan_blk->blk_count = cpu_to_le16(orphan_blocks);
+			orphan_blk->entry_count = cpu_to_le32(nentries);
+			set_page_dirty(page);
+			f2fs_put_page(page, 1);
+			index++;
+			start_blk++;
+			nentries = 0;
+			page = NULL;
+		}
+		if (page)
+			goto page_exist;
+
+		page = grab_meta_page(sbi, start_blk);
+		orphan_blk = (struct f2fs_orphan_block *)page_address(page);
+		memset(orphan_blk, 0, sizeof(*orphan_blk));
+page_exist:
+		orphan_blk->ino[nentries++] = cpu_to_le32(orphan->ino);
+	}
+	if (!page)
+		goto end;
+
+	orphan_blk->blk_addr = cpu_to_le16(index);
+	orphan_blk->blk_count = cpu_to_le16(orphan_blocks);
+	orphan_blk->entry_count = cpu_to_le32(nentries);
+	set_page_dirty(page);
+	f2fs_put_page(page, 1);
+end:
+	mutex_unlock(&sbi->orphan_inode_mutex);
+}
+
+static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
+				block_t cp_addr, unsigned long long *version)
+{
+	struct page *cp_page_1, *cp_page_2 = NULL;
+	unsigned long blk_size = sbi->blocksize;
+	struct f2fs_checkpoint *cp_block;
+	unsigned long long cur_version = 0, pre_version = 0;
+	unsigned int crc = 0;
+	size_t crc_offset;
+
+	/* Read the 1st cp block in this CP pack */
+	cp_page_1 = get_meta_page(sbi, cp_addr);
+
+	/* get the version number */
+	cp_block = (struct f2fs_checkpoint *)page_address(cp_page_1);
+	crc_offset = le32_to_cpu(cp_block->checksum_offset);
+	if (crc_offset >= blk_size)
+		goto invalid_cp1;
+
+	crc = *(unsigned int *)((unsigned char *)cp_block + crc_offset);
+	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
+		goto invalid_cp1;
+
+	pre_version = le64_to_cpu(cp_block->checkpoint_ver);
+
+	/* Read the 2nd cp block in this CP pack */
+	cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
+	cp_page_2 = get_meta_page(sbi, cp_addr);
+
+	cp_block = (struct f2fs_checkpoint *)page_address(cp_page_2);
+	crc_offset = le32_to_cpu(cp_block->checksum_offset);
+	if (crc_offset >= blk_size)
+		goto invalid_cp2;
+
+	crc = *(unsigned int *)((unsigned char *)cp_block + crc_offset);
+	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
+		goto invalid_cp2;
+
+	cur_version = le64_to_cpu(cp_block->checkpoint_ver);
+
+	if (cur_version == pre_version) {
+		*version = cur_version;
+		f2fs_put_page(cp_page_2, 1);
+		return cp_page_1;
+	}
+invalid_cp2:
+	f2fs_put_page(cp_page_2, 1);
+invalid_cp1:
+	f2fs_put_page(cp_page_1, 1);
+	return NULL;
+}
+
+int get_valid_checkpoint(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_checkpoint *cp_block;
+	struct f2fs_super_block *fsb = sbi->raw_super;
+	struct page *cp1, *cp2, *cur_page;
+	unsigned long blk_size = sbi->blocksize;
+	unsigned long long cp1_version = 0, cp2_version = 0;
+	unsigned long long cp_start_blk_no;
+
+	sbi->ckpt = kzalloc(blk_size, GFP_KERNEL);
+	if (!sbi->ckpt)
+		return -ENOMEM;
+	/*
+	 * Finding out valid cp block involves read both
+	 * sets( cp pack1 and cp pack 2)
+	 */
+	cp_start_blk_no = le32_to_cpu(fsb->cp_blkaddr);
+	cp1 = validate_checkpoint(sbi, cp_start_blk_no, &cp1_version);
+
+	/* The second checkpoint pack should start at the next segment */
+	cp_start_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg);
+	cp2 = validate_checkpoint(sbi, cp_start_blk_no, &cp2_version);
+
+	if (cp1 && cp2) {
+		if (ver_after(cp2_version, cp1_version))
+			cur_page = cp2;
+		else
+			cur_page = cp1;
+	} else if (cp1) {
+		cur_page = cp1;
+	} else if (cp2) {
+		cur_page = cp2;
+	} else {
+		goto fail_no_cp;
+	}
+
+	cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
+	memcpy(sbi->ckpt, cp_block, blk_size);
+
+	f2fs_put_page(cp1, 1);
+	f2fs_put_page(cp2, 1);
+	return 0;
+
+fail_no_cp:
+	kfree(sbi->ckpt);
+	return -EINVAL;
+}
+
+void set_dirty_dir_page(struct inode *inode, struct page *page)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct list_head *head = &sbi->dir_inode_list;
+	struct dir_inode_entry *new;
+	struct list_head *this;
+
+	if (!S_ISDIR(inode->i_mode))
+		return;
+retry:
+	new = kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
+	if (!new) {
+		cond_resched();
+		goto retry;
+	}
+	new->inode = inode;
+	INIT_LIST_HEAD(&new->list);
+
+	spin_lock(&sbi->dir_inode_lock);
+	list_for_each(this, head) {
+		struct dir_inode_entry *entry;
+		entry = list_entry(this, struct dir_inode_entry, list);
+		if (entry->inode == inode) {
+			kmem_cache_free(inode_entry_slab, new);
+			goto out;
+		}
+	}
+	list_add_tail(&new->list, head);
+	sbi->n_dirty_dirs++;
+
+	BUG_ON(!S_ISDIR(inode->i_mode));
+out:
+	inc_page_count(sbi, F2FS_DIRTY_DENTS);
+	inode_inc_dirty_dents(inode);
+	SetPagePrivate(page);
+
+	spin_unlock(&sbi->dir_inode_lock);
+}
+
+void remove_dirty_dir_inode(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct list_head *head = &sbi->dir_inode_list;
+	struct list_head *this;
+
+	if (!S_ISDIR(inode->i_mode))
+		return;
+
+	spin_lock(&sbi->dir_inode_lock);
+	if (atomic_read(&F2FS_I(inode)->dirty_dents))
+		goto out;
+
+	list_for_each(this, head) {
+		struct dir_inode_entry *entry;
+		entry = list_entry(this, struct dir_inode_entry, list);
+		if (entry->inode == inode) {
+			list_del(&entry->list);
+			kmem_cache_free(inode_entry_slab, entry);
+			sbi->n_dirty_dirs--;
+			break;
+		}
+	}
+out:
+	spin_unlock(&sbi->dir_inode_lock);
+}
+
+void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
+{
+	struct list_head *head = &sbi->dir_inode_list;
+	struct dir_inode_entry *entry;
+	struct inode *inode;
+retry:
+	spin_lock(&sbi->dir_inode_lock);
+	if (list_empty(head)) {
+		spin_unlock(&sbi->dir_inode_lock);
+		return;
+	}
+	entry = list_entry(head->next, struct dir_inode_entry, list);
+	inode = igrab(entry->inode);
+	spin_unlock(&sbi->dir_inode_lock);
+	if (inode) {
+		filemap_flush(inode->i_mapping);
+		iput(inode);
+	} else {
+		/*
+		 * We should submit bio, since it exists several
+		 * wribacking dentry pages in the freeing inode.
+		 */
+		f2fs_submit_bio(sbi, DATA, true);
+	}
+	goto retry;
+}
+
+/*
+ * Freeze all the FS-operations for checkpoint.
+ */
+static void block_operations(struct f2fs_sb_info *sbi)
+{
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_ALL,
+		.nr_to_write = LONG_MAX,
+		.for_reclaim = 0,
+	};
+	struct blk_plug plug;
+
+	blk_start_plug(&plug);
+
+retry_flush_dents:
+	mutex_lock_all(sbi);
+
+	/* write all the dirty dentry pages */
+	if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
+		mutex_unlock_all(sbi);
+		sync_dirty_dir_inodes(sbi);
+		goto retry_flush_dents;
+	}
+
+	/*
+	 * POR: we should ensure that there is no dirty node pages
+	 * until finishing nat/sit flush.
+	 */
+retry_flush_nodes:
+	mutex_lock(&sbi->node_write);
+
+	if (get_pages(sbi, F2FS_DIRTY_NODES)) {
+		mutex_unlock(&sbi->node_write);
+		sync_node_pages(sbi, 0, &wbc);
+		goto retry_flush_nodes;
+	}
+	blk_finish_plug(&plug);
+}
+
+static void unblock_operations(struct f2fs_sb_info *sbi)
+{
+	mutex_unlock(&sbi->node_write);
+	mutex_unlock_all(sbi);
+}
+
+static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
+{
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	nid_t last_nid = 0;
+	block_t start_blk;
+	struct page *cp_page;
+	unsigned int data_sum_blocks, orphan_blocks;
+	unsigned int crc32 = 0;
+	void *kaddr;
+	int i;
+
+	/* Flush all the NAT/SIT pages */
+	while (get_pages(sbi, F2FS_DIRTY_META))
+		sync_meta_pages(sbi, META, LONG_MAX);
+
+	next_free_nid(sbi, &last_nid);
+
+	/*
+	 * modify checkpoint
+	 * version number is already updated
+	 */
+	ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi));
+	ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi));
+	ckpt->free_segment_count = cpu_to_le32(free_segments(sbi));
+	for (i = 0; i < 3; i++) {
+		ckpt->cur_node_segno[i] =
+			cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_NODE));
+		ckpt->cur_node_blkoff[i] =
+			cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_NODE));
+		ckpt->alloc_type[i + CURSEG_HOT_NODE] =
+				curseg_alloc_type(sbi, i + CURSEG_HOT_NODE);
+	}
+	for (i = 0; i < 3; i++) {
+		ckpt->cur_data_segno[i] =
+			cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_DATA));
+		ckpt->cur_data_blkoff[i] =
+			cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_DATA));
+		ckpt->alloc_type[i + CURSEG_HOT_DATA] =
+				curseg_alloc_type(sbi, i + CURSEG_HOT_DATA);
+	}
+
+	ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
+	ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
+	ckpt->next_free_nid = cpu_to_le32(last_nid);
+
+	/* 2 cp  + n data seg summary + orphan inode blocks */
+	data_sum_blocks = npages_for_summary_flush(sbi);
+	if (data_sum_blocks < 3)
+		set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
+	else
+		clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
+
+	orphan_blocks = (sbi->n_orphans + F2FS_ORPHANS_PER_BLOCK - 1)
+					/ F2FS_ORPHANS_PER_BLOCK;
+	ckpt->cp_pack_start_sum = cpu_to_le32(1 + orphan_blocks);
+
+	if (is_umount) {
+		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+		ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
+			data_sum_blocks + orphan_blocks + NR_CURSEG_NODE_TYPE);
+	} else {
+		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+		ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
+			data_sum_blocks + orphan_blocks);
+	}
+
+	if (sbi->n_orphans)
+		set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
+	else
+		clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
+
+	/* update SIT/NAT bitmap */
+	get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
+	get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
+
+	crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset));
+	*(__le32 *)((unsigned char *)ckpt +
+				le32_to_cpu(ckpt->checksum_offset))
+				= cpu_to_le32(crc32);
+
+	start_blk = __start_cp_addr(sbi);
+
+	/* write out checkpoint buffer at block 0 */
+	cp_page = grab_meta_page(sbi, start_blk++);
+	kaddr = page_address(cp_page);
+	memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
+	set_page_dirty(cp_page);
+	f2fs_put_page(cp_page, 1);
+
+	if (sbi->n_orphans) {
+		write_orphan_inodes(sbi, start_blk);
+		start_blk += orphan_blocks;
+	}
+
+	write_data_summaries(sbi, start_blk);
+	start_blk += data_sum_blocks;
+	if (is_umount) {
+		write_node_summaries(sbi, start_blk);
+		start_blk += NR_CURSEG_NODE_TYPE;
+	}
+
+	/* writeout checkpoint block */
+	cp_page = grab_meta_page(sbi, start_blk);
+	kaddr = page_address(cp_page);
+	memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
+	set_page_dirty(cp_page);
+	f2fs_put_page(cp_page, 1);
+
+	/* wait for previous submitted node/meta pages writeback */
+	while (get_pages(sbi, F2FS_WRITEBACK))
+		congestion_wait(BLK_RW_ASYNC, HZ / 50);
+
+	filemap_fdatawait_range(sbi->node_inode->i_mapping, 0, LONG_MAX);
+	filemap_fdatawait_range(sbi->meta_inode->i_mapping, 0, LONG_MAX);
+
+	/* update user_block_counts */
+	sbi->last_valid_block_count = sbi->total_valid_block_count;
+	sbi->alloc_valid_block_count = 0;
+
+	/* Here, we only have one bio having CP pack */
+	sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
+
+	if (!is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) {
+		clear_prefree_segments(sbi);
+		F2FS_RESET_SB_DIRT(sbi);
+	}
+}
+
+/*
+ * We guarantee that this checkpoint procedure should not fail.
+ */
+void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
+{
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	unsigned long long ckpt_ver;
+
+	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "start block_ops");
+
+	mutex_lock(&sbi->cp_mutex);
+	block_operations(sbi);
+
+	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish block_ops");
+
+	f2fs_submit_bio(sbi, DATA, true);
+	f2fs_submit_bio(sbi, NODE, true);
+	f2fs_submit_bio(sbi, META, true);
+
+	/*
+	 * update checkpoint pack index
+	 * Increase the version number so that
+	 * SIT entries and seg summaries are written at correct place
+	 */
+	ckpt_ver = le64_to_cpu(ckpt->checkpoint_ver);
+	ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);
+
+	/* write cached NAT/SIT entries to NAT/SIT area */
+	flush_nat_entries(sbi);
+	flush_sit_entries(sbi);
+
+	/* unlock all the fs_lock[] in do_checkpoint() */
+	do_checkpoint(sbi, is_umount);
+
+	unblock_operations(sbi);
+	mutex_unlock(&sbi->cp_mutex);
+
+	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish checkpoint");
+}
+
+void init_orphan_info(struct f2fs_sb_info *sbi)
+{
+	mutex_init(&sbi->orphan_inode_mutex);
+	INIT_LIST_HEAD(&sbi->orphan_inode_list);
+	sbi->n_orphans = 0;
+}
+
+int __init create_checkpoint_caches(void)
+{
+	orphan_entry_slab = f2fs_kmem_cache_create("f2fs_orphan_entry",
+			sizeof(struct orphan_inode_entry), NULL);
+	if (unlikely(!orphan_entry_slab))
+		return -ENOMEM;
+	inode_entry_slab = f2fs_kmem_cache_create("f2fs_dirty_dir_entry",
+			sizeof(struct dir_inode_entry), NULL);
+	if (unlikely(!inode_entry_slab)) {
+		kmem_cache_destroy(orphan_entry_slab);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void destroy_checkpoint_caches(void)
+{
+	kmem_cache_destroy(orphan_entry_slab);
+	kmem_cache_destroy(inode_entry_slab);
+}

fs/f2fs/data.c

@@ -0,0 +1,749 @@
+/*
+ * fs/f2fs/data.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/buffer_head.h>
+#include <linux/mpage.h>
+#include <linux/aio.h>
+#include <linux/writeback.h>
+#include <linux/backing-dev.h>
+#include <linux/blkdev.h>
+#include <linux/bio.h>
+#include <linux/prefetch.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include "segment.h"
+#include <trace/events/f2fs.h>
+
+/*
+ * Lock ordering for the change of data block address:
+ * ->data_page
+ *  ->node_page
+ *    update block addresses in the node page
+ */
+static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
+{
+	struct f2fs_node *rn;
+	__le32 *addr_array;
+	struct page *node_page = dn->node_page;
+	unsigned int ofs_in_node = dn->ofs_in_node;
+
+	wait_on_page_writeback(node_page);
+
+	rn = (struct f2fs_node *)page_address(node_page);
+
+	/* Get physical address of data block */
+	addr_array = blkaddr_in_node(rn);
+	addr_array[ofs_in_node] = cpu_to_le32(new_addr);
+	set_page_dirty(node_page);
+}
+
+int reserve_new_block(struct dnode_of_data *dn)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+
+	if (is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC))
+		return -EPERM;
+	if (!inc_valid_block_count(sbi, dn->inode, 1))
+		return -ENOSPC;
+
+	trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
+
+	__set_data_blkaddr(dn, NEW_ADDR);
+	dn->data_blkaddr = NEW_ADDR;
+	sync_inode_page(dn);
+	return 0;
+}
+
+static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
+					struct buffer_head *bh_result)
+{
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	pgoff_t start_fofs, end_fofs;
+	block_t start_blkaddr;
+
+	read_lock(&fi->ext.ext_lock);
+	if (fi->ext.len == 0) {
+		read_unlock(&fi->ext.ext_lock);
+		return 0;
+	}
+
+	sbi->total_hit_ext++;
+	start_fofs = fi->ext.fofs;
+	end_fofs = fi->ext.fofs + fi->ext.len - 1;
+	start_blkaddr = fi->ext.blk_addr;
+
+	if (pgofs >= start_fofs && pgofs <= end_fofs) {
+		unsigned int blkbits = inode->i_sb->s_blocksize_bits;
+		size_t count;
+
+		clear_buffer_new(bh_result);
+		map_bh(bh_result, inode->i_sb,
+				start_blkaddr + pgofs - start_fofs);
+		count = end_fofs - pgofs + 1;
+		if (count < (UINT_MAX >> blkbits))
+			bh_result->b_size = (count << blkbits);
+		else
+			bh_result->b_size = UINT_MAX;
+
+		sbi->read_hit_ext++;
+		read_unlock(&fi->ext.ext_lock);
+		return 1;
+	}
+	read_unlock(&fi->ext.ext_lock);
+	return 0;
+}
+
+void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
+{
+	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
+	pgoff_t fofs, start_fofs, end_fofs;
+	block_t start_blkaddr, end_blkaddr;
+
+	BUG_ON(blk_addr == NEW_ADDR);
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page)) + dn->ofs_in_node;
+
+	/* Update the page address in the parent node */
+	__set_data_blkaddr(dn, blk_addr);
+
+	write_lock(&fi->ext.ext_lock);
+
+	start_fofs = fi->ext.fofs;
+	end_fofs = fi->ext.fofs + fi->ext.len - 1;
+	start_blkaddr = fi->ext.blk_addr;
+	end_blkaddr = fi->ext.blk_addr + fi->ext.len - 1;
+
+	/* Drop and initialize the matched extent */
+	if (fi->ext.len == 1 && fofs == start_fofs)
+		fi->ext.len = 0;
+
+	/* Initial extent */
+	if (fi->ext.len == 0) {
+		if (blk_addr != NULL_ADDR) {
+			fi->ext.fofs = fofs;
+			fi->ext.blk_addr = blk_addr;
+			fi->ext.len = 1;
+		}
+		goto end_update;
+	}
+
+	/* Front merge */
+	if (fofs == start_fofs - 1 && blk_addr == start_blkaddr - 1) {
+		fi->ext.fofs--;
+		fi->ext.blk_addr--;
+		fi->ext.len++;
+		goto end_update;
+	}
+
+	/* Back merge */
+	if (fofs == end_fofs + 1 && blk_addr == end_blkaddr + 1) {
+		fi->ext.len++;
+		goto end_update;
+	}
+
+	/* Split the existing extent */
+	if (fi->ext.len > 1 &&
+		fofs >= start_fofs && fofs <= end_fofs) {
+		if ((end_fofs - fofs) < (fi->ext.len >> 1)) {
+			fi->ext.len = fofs - start_fofs;
+		} else {
+			fi->ext.fofs = fofs + 1;
+			fi->ext.blk_addr = start_blkaddr +
+					fofs - start_fofs + 1;
+			fi->ext.len -= fofs - start_fofs + 1;
+		}
+		goto end_update;
+	}
+	write_unlock(&fi->ext.ext_lock);
+	return;
+
+end_update:
+	write_unlock(&fi->ext.ext_lock);
+	sync_inode_page(dn);
+	return;
+}
+
+struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct address_space *mapping = inode->i_mapping;
+	struct dnode_of_data dn;
+	struct page *page;
+	int err;
+
+	page = find_get_page(mapping, index);
+	if (page && PageUptodate(page))
+		return page;
+	f2fs_put_page(page, 0);
+
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
+	if (err)
+		return ERR_PTR(err);
+	f2fs_put_dnode(&dn);
+
+	if (dn.data_blkaddr == NULL_ADDR)
+		return ERR_PTR(-ENOENT);
+
+	/* By fallocate(), there is no cached page, but with NEW_ADDR */
+	if (dn.data_blkaddr == NEW_ADDR)
+		return ERR_PTR(-EINVAL);
+
+	page = grab_cache_page(mapping, index);
+	if (!page)
+		return ERR_PTR(-ENOMEM);
+
+	if (PageUptodate(page)) {
+		unlock_page(page);
+		return page;
+	}
+
+	err = f2fs_readpage(sbi, page, dn.data_blkaddr,
+					sync ? READ_SYNC : READA);
+	if (sync) {
+		wait_on_page_locked(page);
+		if (!PageUptodate(page)) {
+			f2fs_put_page(page, 0);
+			return ERR_PTR(-EIO);
+		}
+	}
+	return page;
+}
+
+/*
+ * If it tries to access a hole, return an error.
+ * Because, the callers, functions in dir.c and GC, should be able to know
+ * whether this page exists or not.
+ */
+struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct address_space *mapping = inode->i_mapping;
+	struct dnode_of_data dn;
+	struct page *page;
+	int err;
+
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
+	if (err)
+		return ERR_PTR(err);
+	f2fs_put_dnode(&dn);
+
+	if (dn.data_blkaddr == NULL_ADDR)
+		return ERR_PTR(-ENOENT);
+repeat:
+	page = grab_cache_page(mapping, index);
+	if (!page)
+		return ERR_PTR(-ENOMEM);
+
+	if (PageUptodate(page))
+		return page;
+
+	BUG_ON(dn.data_blkaddr == NEW_ADDR);
+	BUG_ON(dn.data_blkaddr == NULL_ADDR);
+
+	err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
+	if (err)
+		return ERR_PTR(err);
+
+	lock_page(page);
+	if (!PageUptodate(page)) {
+		f2fs_put_page(page, 1);
+		return ERR_PTR(-EIO);
+	}
+	if (page->mapping != mapping) {
+		f2fs_put_page(page, 1);
+		goto repeat;
+	}
+	return page;
+}
+
+/*
+ * Caller ensures that this data page is never allocated.
+ * A new zero-filled data page is allocated in the page cache.
+ *
+ * Also, caller should grab and release a mutex by calling mutex_lock_op() and
+ * mutex_unlock_op().
+ */
+struct page *get_new_data_page(struct inode *inode, pgoff_t index,
+						bool new_i_size)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct address_space *mapping = inode->i_mapping;
+	struct page *page;
+	struct dnode_of_data dn;
+	int err;
+
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	err = get_dnode_of_data(&dn, index, ALLOC_NODE);
+	if (err)
+		return ERR_PTR(err);
+
+	if (dn.data_blkaddr == NULL_ADDR) {
+		if (reserve_new_block(&dn)) {
+			f2fs_put_dnode(&dn);
+			return ERR_PTR(-ENOSPC);
+		}
+	}
+	f2fs_put_dnode(&dn);
+repeat:
+	page = grab_cache_page(mapping, index);
+	if (!page)
+		return ERR_PTR(-ENOMEM);
+
+	if (PageUptodate(page))
+		return page;
+
+	if (dn.data_blkaddr == NEW_ADDR) {
+		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		SetPageUptodate(page);
+	} else {
+		err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
+		if (err)
+			return ERR_PTR(err);
+		lock_page(page);
+		if (!PageUptodate(page)) {
+			f2fs_put_page(page, 1);
+			return ERR_PTR(-EIO);
+		}
+		if (page->mapping != mapping) {
+			f2fs_put_page(page, 1);
+			goto repeat;
+		}
+	}
+
+	if (new_i_size &&
+		i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) {
+		i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT));
+		mark_inode_dirty_sync(inode);
+	}
+	return page;
+}
+
+static void read_end_io(struct bio *bio, int err)
+{
+	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+
+	do {
+		struct page *page = bvec->bv_page;
+
+		if (--bvec >= bio->bi_io_vec)
+			prefetchw(&bvec->bv_page->flags);
+
+		if (uptodate) {
+			SetPageUptodate(page);
+		} else {
+			ClearPageUptodate(page);
+			SetPageError(page);
+		}
+		unlock_page(page);
+	} while (bvec >= bio->bi_io_vec);
+	kfree(bio->bi_private);
+	bio_put(bio);
+}
+
+/*
+ * Fill the locked page with data located in the block address.
+ * Return unlocked page.
+ */
+int f2fs_readpage(struct f2fs_sb_info *sbi, struct page *page,
+					block_t blk_addr, int type)
+{
+	struct block_device *bdev = sbi->sb->s_bdev;
+	struct bio *bio;
+
+	trace_f2fs_readpage(page, blk_addr, type);
+
+	down_read(&sbi->bio_sem);
+
+	/* Allocate a new bio */
+	bio = f2fs_bio_alloc(bdev, 1);
+
+	/* Initialize the bio */
+	bio->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr);
+	bio->bi_end_io = read_end_io;
+
+	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
+		kfree(bio->bi_private);
+		bio_put(bio);
+		up_read(&sbi->bio_sem);
+		f2fs_put_page(page, 1);
+		return -EFAULT;
+	}
+
+	submit_bio(type, bio);
+	up_read(&sbi->bio_sem);
+	return 0;
+}
+
+/*
+ * This function should be used by the data read flow only where it
+ * does not check the "create" flag that indicates block allocation.
+ * The reason for this special functionality is to exploit VFS readahead
+ * mechanism.
+ */
+static int get_data_block_ro(struct inode *inode, sector_t iblock,
+			struct buffer_head *bh_result, int create)
+{
+	unsigned int blkbits = inode->i_sb->s_blocksize_bits;
+	unsigned maxblocks = bh_result->b_size >> blkbits;
+	struct dnode_of_data dn;
+	pgoff_t pgofs;
+	int err;
+
+	/* Get the page offset from the block offset(iblock) */
+	pgofs =	(pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits));
+
+	if (check_extent_cache(inode, pgofs, bh_result)) {
+		trace_f2fs_get_data_block(inode, iblock, bh_result, 0);
+		return 0;
+	}
+
+	/* When reading holes, we need its node page */
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
+	if (err) {
+		trace_f2fs_get_data_block(inode, iblock, bh_result, err);
+		return (err == -ENOENT) ? 0 : err;
+	}
+
+	/* It does not support data allocation */
+	BUG_ON(create);
+
+	if (dn.data_blkaddr != NEW_ADDR && dn.data_blkaddr != NULL_ADDR) {
+		int i;
+		unsigned int end_offset;
+
+		end_offset = IS_INODE(dn.node_page) ?
+				ADDRS_PER_INODE :
+				ADDRS_PER_BLOCK;
+
+		clear_buffer_new(bh_result);
+
+		/* Give more consecutive addresses for the read ahead */
+		for (i = 0; i < end_offset - dn.ofs_in_node; i++)
+			if (((datablock_addr(dn.node_page,
+							dn.ofs_in_node + i))
+				!= (dn.data_blkaddr + i)) || maxblocks == i)
+				break;
+		map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
+		bh_result->b_size = (i << blkbits);
+	}
+	f2fs_put_dnode(&dn);
+	trace_f2fs_get_data_block(inode, iblock, bh_result, 0);
+	return 0;
+}
+
+static int f2fs_read_data_page(struct file *file, struct page *page)
+{
+	return mpage_readpage(page, get_data_block_ro);
+}
+
+static int f2fs_read_data_pages(struct file *file,
+			struct address_space *mapping,
+			struct list_head *pages, unsigned nr_pages)
+{
+	return mpage_readpages(mapping, pages, nr_pages, get_data_block_ro);
+}
+
+int do_write_data_page(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	block_t old_blk_addr, new_blk_addr;
+	struct dnode_of_data dn;
+	int err = 0;
+
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
+	if (err)
+		return err;
+
+	old_blk_addr = dn.data_blkaddr;
+
+	/* This page is already truncated */
+	if (old_blk_addr == NULL_ADDR)
+		goto out_writepage;
+
+	set_page_writeback(page);
+
+	/*
+	 * If current allocation needs SSR,
+	 * it had better in-place writes for updated data.
+	 */
+	if (old_blk_addr != NEW_ADDR && !is_cold_data(page) &&
+				need_inplace_update(inode)) {
+		rewrite_data_page(F2FS_SB(inode->i_sb), page,
+						old_blk_addr);
+	} else {
+		write_data_page(inode, page, &dn,
+				old_blk_addr, &new_blk_addr);
+		update_extent_cache(new_blk_addr, &dn);
+	}
+out_writepage:
+	f2fs_put_dnode(&dn);
+	return err;
+}
+
+static int f2fs_write_data_page(struct page *page,
+					struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	loff_t i_size = i_size_read(inode);
+	const pgoff_t end_index = ((unsigned long long) i_size)
+							>> PAGE_CACHE_SHIFT;
+	unsigned offset;
+	bool need_balance_fs = false;
+	int err = 0;
+
+	if (page->index < end_index)
+		goto write;
+
+	/*
+	 * If the offset is out-of-range of file size,
+	 * this page does not have to be written to disk.
+	 */
+	offset = i_size & (PAGE_CACHE_SIZE - 1);
+	if ((page->index >= end_index + 1) || !offset) {
+		if (S_ISDIR(inode->i_mode)) {
+			dec_page_count(sbi, F2FS_DIRTY_DENTS);
+			inode_dec_dirty_dents(inode);
+		}
+		goto out;
+	}
+
+	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+write:
+	if (sbi->por_doing) {
+		err = AOP_WRITEPAGE_ACTIVATE;
+		goto redirty_out;
+	}
+
+	/* Dentry blocks are controlled by checkpoint */
+	if (S_ISDIR(inode->i_mode)) {
+		dec_page_count(sbi, F2FS_DIRTY_DENTS);
+		inode_dec_dirty_dents(inode);
+		err = do_write_data_page(page);
+	} else {
+		int ilock = mutex_lock_op(sbi);
+		err = do_write_data_page(page);
+		mutex_unlock_op(sbi, ilock);
+		need_balance_fs = true;
+	}
+	if (err == -ENOENT)
+		goto out;
+	else if (err)
+		goto redirty_out;
+
+	if (wbc->for_reclaim)
+		f2fs_submit_bio(sbi, DATA, true);
+
+	clear_cold_data(page);
+out:
+	unlock_page(page);
+	if (need_balance_fs)
+		f2fs_balance_fs(sbi);
+	return 0;
+
+redirty_out:
+	wbc->pages_skipped++;
+	set_page_dirty(page);
+	return err;
+}
+
+#define MAX_DESIRED_PAGES_WP	4096
+
+static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
+			void *data)
+{
+	struct address_space *mapping = data;
+	int ret = mapping->a_ops->writepage(page, wbc);
+	mapping_set_error(mapping, ret);
+	return ret;
+}
+
+static int f2fs_write_data_pages(struct address_space *mapping,
+			    struct writeback_control *wbc)
+{
+	struct inode *inode = mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	bool locked = false;
+	int ret;
+	long excess_nrtw = 0, desired_nrtw;
+
+	/* deal with chardevs and other special file */
+	if (!mapping->a_ops->writepage)
+		return 0;
+
+	if (wbc->nr_to_write < MAX_DESIRED_PAGES_WP) {
+		desired_nrtw = MAX_DESIRED_PAGES_WP;
+		excess_nrtw = desired_nrtw - wbc->nr_to_write;
+		wbc->nr_to_write = desired_nrtw;
+	}
+
+	if (!S_ISDIR(inode->i_mode)) {
+		mutex_lock(&sbi->writepages);
+		locked = true;
+	}
+	ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
+	if (locked)
+		mutex_unlock(&sbi->writepages);
+	f2fs_submit_bio(sbi, DATA, (wbc->sync_mode == WB_SYNC_ALL));
+
+	remove_dirty_dir_inode(inode);
+
+	wbc->nr_to_write -= excess_nrtw;
+	return ret;
+}
+
+static int f2fs_write_begin(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, void **fsdata)
+{
+	struct inode *inode = mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct page *page;
+	pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
+	struct dnode_of_data dn;
+	int err = 0;
+	int ilock;
+
+	/* for nobh_write_end */
+	*fsdata = NULL;
+
+	f2fs_balance_fs(sbi);
+repeat:
+	page = grab_cache_page_write_begin(mapping, index, flags);
+	if (!page)
+		return -ENOMEM;
+	*pagep = page;
+
+	ilock = mutex_lock_op(sbi);
+
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	err = get_dnode_of_data(&dn, index, ALLOC_NODE);
+	if (err)
+		goto err;
+
+	if (dn.data_blkaddr == NULL_ADDR)
+		err = reserve_new_block(&dn);
+
+	f2fs_put_dnode(&dn);
+	if (err)
+		goto err;
+
+	mutex_unlock_op(sbi, ilock);
+
+	if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
+		return 0;
+
+	if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
+		unsigned start = pos & (PAGE_CACHE_SIZE - 1);
+		unsigned end = start + len;
+
+		/* Reading beyond i_size is simple: memset to zero */
+		zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE);
+		goto out;
+	}
+
+	if (dn.data_blkaddr == NEW_ADDR) {
+		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+	} else {
+		err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
+		if (err)
+			return err;
+		lock_page(page);
+		if (!PageUptodate(page)) {
+			f2fs_put_page(page, 1);
+			return -EIO;
+		}
+		if (page->mapping != mapping) {
+			f2fs_put_page(page, 1);
+			goto repeat;
+		}
+	}
+out:
+	SetPageUptodate(page);
+	clear_cold_data(page);
+	return 0;
+
+err:
+	mutex_unlock_op(sbi, ilock);
+	f2fs_put_page(page, 1);
+	return err;
+}
+
+static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
+		const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+
+	if (rw == WRITE)
+		return 0;
+
+	/* Needs synchronization with the cleaner */
+	return blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
+						  get_data_block_ro);
+}
+
+static void f2fs_invalidate_data_page(struct page *page, unsigned long offset)
+{
+	struct inode *inode = page->mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	if (S_ISDIR(inode->i_mode) && PageDirty(page)) {
+		dec_page_count(sbi, F2FS_DIRTY_DENTS);
+		inode_dec_dirty_dents(inode);
+	}
+	ClearPagePrivate(page);
+}
+
+static int f2fs_release_data_page(struct page *page, gfp_t wait)
+{
+	ClearPagePrivate(page);
+	return 1;
+}
+
+static int f2fs_set_data_page_dirty(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *inode = mapping->host;
+
+	SetPageUptodate(page);
+	if (!PageDirty(page)) {
+		__set_page_dirty_nobuffers(page);
+		set_dirty_dir_page(inode, page);
+		return 1;
+	}
+	return 0;
+}
+
+static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
+{
+	return generic_block_bmap(mapping, block, get_data_block_ro);
+}
+
+const struct address_space_operations f2fs_dblock_aops = {
+	.readpage	= f2fs_read_data_page,
+	.readpages	= f2fs_read_data_pages,
+	.writepage	= f2fs_write_data_page,
+	.writepages	= f2fs_write_data_pages,
+	.write_begin	= f2fs_write_begin,
+	.write_end	= nobh_write_end,
+	.set_page_dirty	= f2fs_set_data_page_dirty,
+	.invalidatepage	= f2fs_invalidate_data_page,
+	.releasepage	= f2fs_release_data_page,
+	.direct_IO	= f2fs_direct_IO,
+	.bmap		= f2fs_bmap,
+};

fs/f2fs/debug.c

@@ -0,0 +1,353 @@
+/*
+ * 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>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#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 struct dentry *debugfs_root;
+static DEFINE_MUTEX(f2fs_stat_mutex);
+
+static void update_general_status(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_stat_info *si = sbi->stat_info;
+	int i;
+
+	/* valid check of the segment numbers */
+	si->hit_ext = sbi->read_hit_ext;
+	si->total_ext = sbi->total_hit_ext;
+	si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES);
+	si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS);
+	si->ndirty_dirs = sbi->n_dirty_dirs;
+	si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META);
+	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
+	si->rsvd_segs = reserved_segments(sbi);
+	si->overp_segs = overprovision_segments(sbi);
+	si->valid_count = valid_user_blocks(sbi);
+	si->valid_node_count = valid_node_count(sbi);
+	si->valid_inode_count = valid_inode_count(sbi);
+	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);
+	si->node_pages = sbi->node_inode->i_mapping->nrpages;
+	si->meta_pages = sbi->meta_inode->i_mapping->nrpages;
+	si->nats = NM_I(sbi)->nat_cnt;
+	si->sits = SIT_I(sbi)->dirty_sentries;
+	si->fnids = NM_I(sbi)->fcnt;
+	si->bg_gc = sbi->bg_gc;
+	si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
+		* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
+		/ 2;
+	si->util_valid = (int)(written_block_count(sbi) >>
+						sbi->log_blocks_per_seg)
+		* 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 <= CURSEG_COLD_NODE; i++) {
+		struct curseg_info *curseg = CURSEG_I(sbi, i);
+		si->curseg[i] = curseg->segno;
+		si->cursec[i] = curseg->segno / sbi->segs_per_sec;
+		si->curzone[i] = si->cursec[i] / sbi->secs_per_zone;
+	}
+
+	for (i = 0; i < 2; i++) {
+		si->segment_count[i] = sbi->segment_count[i];
+		si->block_count[i] = sbi->block_count[i];
+	}
+}
+
+/*
+ * This function calculates BDF of every segments
+ */
+static void update_sit_info(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_stat_info *si = sbi->stat_info;
+	unsigned int blks_per_sec, hblks_per_sec, total_vblocks, bimodal, dist;
+	struct sit_info *sit_i = SIT_I(sbi);
+	unsigned int segno, vblocks;
+	int ndirty = 0;
+
+	bimodal = 0;
+	total_vblocks = 0;
+	blks_per_sec = sbi->segs_per_sec * (1 << sbi->log_blocks_per_seg);
+	hblks_per_sec = blks_per_sec / 2;
+	mutex_lock(&sit_i->sentry_lock);
+	for (segno = 0; segno < TOTAL_SEGS(sbi); segno += sbi->segs_per_sec) {
+		vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+		dist = abs(vblocks - hblks_per_sec);
+		bimodal += dist * dist;
+
+		if (vblocks > 0 && vblocks < blks_per_sec) {
+			total_vblocks += vblocks;
+			ndirty++;
+		}
+	}
+	mutex_unlock(&sit_i->sentry_lock);
+	dist = TOTAL_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100;
+	si->bimodal = bimodal / dist;
+	if (si->dirty_count)
+		si->avg_vblocks = total_vblocks / ndirty;
+	else
+		si->avg_vblocks = 0;
+}
+
+/*
+ * This function calculates memory footprint.
+ */
+static void update_mem_info(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_stat_info *si = sbi->stat_info;
+	unsigned npages;
+
+	if (si->base_mem)
+		goto get_cache;
+
+	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 += TOTAL_SEGS(sbi) * sizeof(struct seg_entry);
+	si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi));
+	si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * TOTAL_SEGS(sbi);
+	if (sbi->segs_per_sec > 1)
+		si->base_mem += TOTAL_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(TOTAL_SEGS(sbi));
+	si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi));
+
+	/* build curseg */
+	si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE;
+	si->base_mem += PAGE_CACHE_SIZE * NR_CURSEG_TYPE;
+
+	/* build dirty segmap */
+	si->base_mem += sizeof(struct dirty_seglist_info);
+	si->base_mem += NR_DIRTY_TYPE * f2fs_bitmap_size(TOTAL_SEGS(sbi));
+	si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi));
+
+	/* buld nm */
+	si->base_mem += sizeof(struct f2fs_nm_info);
+	si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
+
+	/* build gc */
+	si->base_mem += sizeof(struct f2fs_gc_kthread);
+
+get_cache:
+	/* free nids */
+	si->cache_mem = NM_I(sbi)->fcnt;
+	si->cache_mem += NM_I(sbi)->nat_cnt;
+	npages = sbi->node_inode->i_mapping->nrpages;
+	si->cache_mem += npages << PAGE_CACHE_SHIFT;
+	npages = sbi->meta_inode->i_mapping->nrpages;
+	si->cache_mem += npages << PAGE_CACHE_SHIFT;
+	si->cache_mem += sbi->n_orphans * sizeof(struct orphan_inode_entry);
+	si->cache_mem += sbi->n_dirty_dirs * sizeof(struct dir_inode_entry);
+}
+
+static int stat_show(struct seq_file *s, void *v)
+{
+	struct f2fs_stat_info *si, *next;
+	int i = 0;
+	int j;
+
+	mutex_lock(&f2fs_stat_mutex);
+	list_for_each_entry_safe(si, next, &f2fs_stat_list, stat_list) {
+		char devname[BDEVNAME_SIZE];
+
+		update_general_status(si->sbi);
+
+		seq_printf(s, "\n=====[ partition info(%s). #%d ]=====\n",
+			bdevname(si->sbi->sb->s_bdev, devname), i++);
+		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, "Utilization: %d%% (%d 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, "\nMain area: %d segs, %d secs %d zones\n",
+			   si->main_area_segs, si->main_area_sections,
+			   si->main_area_zones);
+		seq_printf(s, "  - COLD  data: %d, %d, %d\n",
+			   si->curseg[CURSEG_COLD_DATA],
+			   si->cursec[CURSEG_COLD_DATA],
+			   si->curzone[CURSEG_COLD_DATA]);
+		seq_printf(s, "  - WARM  data: %d, %d, %d\n",
+			   si->curseg[CURSEG_WARM_DATA],
+			   si->cursec[CURSEG_WARM_DATA],
+			   si->curzone[CURSEG_WARM_DATA]);
+		seq_printf(s, "  - HOT   data: %d, %d, %d\n",
+			   si->curseg[CURSEG_HOT_DATA],
+			   si->cursec[CURSEG_HOT_DATA],
+			   si->curzone[CURSEG_HOT_DATA]);
+		seq_printf(s, "  - Dir   dnode: %d, %d, %d\n",
+			   si->curseg[CURSEG_HOT_NODE],
+			   si->cursec[CURSEG_HOT_NODE],
+			   si->curzone[CURSEG_HOT_NODE]);
+		seq_printf(s, "  - File   dnode: %d, %d, %d\n",
+			   si->curseg[CURSEG_WARM_NODE],
+			   si->cursec[CURSEG_WARM_NODE],
+			   si->curzone[CURSEG_WARM_NODE]);
+		seq_printf(s, "  - Indir nodes: %d, %d, %d\n",
+			   si->curseg[CURSEG_COLD_NODE],
+			   si->cursec[CURSEG_COLD_NODE],
+			   si->curzone[CURSEG_COLD_NODE]);
+		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);
+		seq_printf(s, "GC calls: %d (BG: %d)\n",
+			   si->call_count, si->bg_gc);
+		seq_printf(s, "  - data segments : %d\n", si->data_segs);
+		seq_printf(s, "  - node segments : %d\n", si->node_segs);
+		seq_printf(s, "Try to move %d blocks\n", si->tot_blks);
+		seq_printf(s, "  - data blocks : %d\n", si->data_blks);
+		seq_printf(s, "  - node blocks : %d\n", si->node_blks);
+		seq_printf(s, "\nExtent Hit Ratio: %d / %d\n",
+			   si->hit_ext, si->total_ext);
+		seq_printf(s, "\nBalancing F2FS Async:\n");
+		seq_printf(s, "  - nodes %4d in %4d\n",
+			   si->ndirty_node, si->node_pages);
+		seq_printf(s, "  - dents %4d in dirs:%4d\n",
+			   si->ndirty_dent, si->ndirty_dirs);
+		seq_printf(s, "  - meta %4d in %4d\n",
+			   si->ndirty_meta, si->meta_pages);
+		seq_printf(s, "  - NATs %5d > %lu\n",
+			   si->nats, NM_WOUT_THRESHOLD);
+		seq_printf(s, "  - SITs: %5d\n  - free_nids: %5d\n",
+			   si->sits, si->fnids);
+		seq_printf(s, "\nDistribution of User Blocks:");
+		seq_printf(s, " [ valid | invalid | free ]\n");
+		seq_printf(s, "  [");
+
+		for (j = 0; j < si->util_valid; j++)
+			seq_printf(s, "-");
+		seq_printf(s, "|");
+
+		for (j = 0; j < si->util_invalid; j++)
+			seq_printf(s, "-");
+		seq_printf(s, "|");
+
+		for (j = 0; j < si->util_free; j++)
+			seq_printf(s, "-");
+		seq_printf(s, "]\n\n");
+		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 */
+		update_sit_info(si->sbi);
+		seq_printf(s, "\nBDF: %u, avg. vblocks: %u\n",
+			   si->bimodal, si->avg_vblocks);
+
+		/* memory footprint */
+		update_mem_info(si->sbi);
+		seq_printf(s, "\nMemory: %u KB = static: %u + cached: %u\n",
+				(si->base_mem + si->cache_mem) >> 10,
+				si->base_mem >> 10, si->cache_mem >> 10);
+	}
+	mutex_unlock(&f2fs_stat_mutex);
+	return 0;
+}
+
+static int stat_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, stat_show, inode->i_private);
+}
+
+static const struct file_operations stat_fops = {
+	.open = stat_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+int f2fs_build_stats(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	struct f2fs_stat_info *si;
+
+	sbi->stat_info = kzalloc(sizeof(struct f2fs_stat_info), GFP_KERNEL);
+	if (!sbi->stat_info)
+		return -ENOMEM;
+
+	si = sbi->stat_info;
+	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;
+
+	mutex_lock(&f2fs_stat_mutex);
+	list_add_tail(&si->stat_list, &f2fs_stat_list);
+	mutex_unlock(&f2fs_stat_mutex);
+
+	return 0;
+}
+
+void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_stat_info *si = sbi->stat_info;
+
+	mutex_lock(&f2fs_stat_mutex);
+	list_del(&si->stat_list);
+	mutex_unlock(&f2fs_stat_mutex);
+
+	kfree(sbi->stat_info);
+}
+
+void __init f2fs_create_root_stats(void)
+{
+	debugfs_root = debugfs_create_dir("f2fs", NULL);
+	if (debugfs_root)
+		debugfs_create_file("status", S_IRUGO, debugfs_root,
+					 NULL, &stat_fops);
+}
+
+void f2fs_destroy_root_stats(void)
+{
+	debugfs_remove_recursive(debugfs_root);
+	debugfs_root = NULL;
+}

fs/f2fs/dir.c

@@ -0,0 +1,665 @@
+/*
+ * fs/f2fs/dir.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include "f2fs.h"
+#include "node.h"
+#include "acl.h"
+
+static unsigned long dir_blocks(struct inode *inode)
+{
+	return ((unsigned long long) (i_size_read(inode) + PAGE_CACHE_SIZE - 1))
+							>> PAGE_CACHE_SHIFT;
+}
+
+static unsigned int dir_buckets(unsigned int level)
+{
+	if (level < MAX_DIR_HASH_DEPTH / 2)
+		return 1 << level;
+	else
+		return 1 << ((MAX_DIR_HASH_DEPTH / 2) - 1);
+}
+
+static unsigned int bucket_blocks(unsigned int level)
+{
+	if (level < MAX_DIR_HASH_DEPTH / 2)
+		return 2;
+	else
+		return 4;
+}
+
+static unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
+	[F2FS_FT_UNKNOWN]	= DT_UNKNOWN,
+	[F2FS_FT_REG_FILE]	= DT_REG,
+	[F2FS_FT_DIR]		= DT_DIR,
+	[F2FS_FT_CHRDEV]	= DT_CHR,
+	[F2FS_FT_BLKDEV]	= DT_BLK,
+	[F2FS_FT_FIFO]		= DT_FIFO,
+	[F2FS_FT_SOCK]		= DT_SOCK,
+	[F2FS_FT_SYMLINK]	= DT_LNK,
+};
+
+#define S_SHIFT 12
+static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
+	[S_IFREG >> S_SHIFT]	= F2FS_FT_REG_FILE,
+	[S_IFDIR >> S_SHIFT]	= F2FS_FT_DIR,
+	[S_IFCHR >> S_SHIFT]	= F2FS_FT_CHRDEV,
+	[S_IFBLK >> S_SHIFT]	= F2FS_FT_BLKDEV,
+	[S_IFIFO >> S_SHIFT]	= F2FS_FT_FIFO,
+	[S_IFSOCK >> S_SHIFT]	= F2FS_FT_SOCK,
+	[S_IFLNK >> S_SHIFT]	= F2FS_FT_SYMLINK,
+};
+
+static void set_de_type(struct f2fs_dir_entry *de, struct inode *inode)
+{
+	umode_t mode = inode->i_mode;
+	de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
+}
+
+static unsigned long dir_block_index(unsigned int level, unsigned int idx)
+{
+	unsigned long i;
+	unsigned long bidx = 0;
+
+	for (i = 0; i < level; i++)
+		bidx += dir_buckets(i) * bucket_blocks(i);
+	bidx += idx * bucket_blocks(level);
+	return bidx;
+}
+
+static bool early_match_name(const char *name, size_t namelen,
+			f2fs_hash_t namehash, struct f2fs_dir_entry *de)
+{
+	if (le16_to_cpu(de->name_len) != namelen)
+		return false;
+
+	if (de->hash_code != namehash)
+		return false;
+
+	return true;
+}
+
+static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
+			const char *name, size_t namelen, int *max_slots,
+			f2fs_hash_t namehash, struct page **res_page)
+{
+	struct f2fs_dir_entry *de;
+	unsigned long bit_pos, end_pos, next_pos;
+	struct f2fs_dentry_block *dentry_blk = kmap(dentry_page);
+	int slots;
+
+	bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
+					NR_DENTRY_IN_BLOCK, 0);
+	while (bit_pos < NR_DENTRY_IN_BLOCK) {
+		de = &dentry_blk->dentry[bit_pos];
+		slots = GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+
+		if (early_match_name(name, namelen, namehash, de)) {
+			if (!memcmp(dentry_blk->filename[bit_pos],
+							name, namelen)) {
+				*res_page = dentry_page;
+				goto found;
+			}
+		}
+		next_pos = bit_pos + slots;
+		bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
+				NR_DENTRY_IN_BLOCK, next_pos);
+		if (bit_pos >= NR_DENTRY_IN_BLOCK)
+			end_pos = NR_DENTRY_IN_BLOCK;
+		else
+			end_pos = bit_pos;
+		if (*max_slots < end_pos - next_pos)
+			*max_slots = end_pos - next_pos;
+	}
+
+	de = NULL;
+	kunmap(dentry_page);
+found:
+	return de;
+}
+
+static struct f2fs_dir_entry *find_in_level(struct inode *dir,
+		unsigned int level, const char *name, size_t namelen,
+			f2fs_hash_t namehash, struct page **res_page)
+{
+	int s = GET_DENTRY_SLOTS(namelen);
+	unsigned int nbucket, nblock;
+	unsigned int bidx, end_block;
+	struct page *dentry_page;
+	struct f2fs_dir_entry *de = NULL;
+	bool room = false;
+	int max_slots = 0;
+
+	BUG_ON(level > MAX_DIR_HASH_DEPTH);
+
+	nbucket = dir_buckets(level);
+	nblock = bucket_blocks(level);
+
+	bidx = dir_block_index(level, le32_to_cpu(namehash) % nbucket);
+	end_block = bidx + nblock;
+
+	for (; bidx < end_block; bidx++) {
+		/* no need to allocate new dentry pages to all the indices */
+		dentry_page = find_data_page(dir, bidx, true);
+		if (IS_ERR(dentry_page)) {
+			room = true;
+			continue;
+		}
+
+		de = find_in_block(dentry_page, name, namelen,
+					&max_slots, namehash, res_page);
+		if (de)
+			break;
+
+		if (max_slots >= s)
+			room = true;
+		f2fs_put_page(dentry_page, 0);
+	}
+
+	if (!de && room && F2FS_I(dir)->chash != namehash) {
+		F2FS_I(dir)->chash = namehash;
+		F2FS_I(dir)->clevel = level;
+	}
+
+	return de;
+}
+
+/*
+ * Find an entry in the specified directory with the wanted name.
+ * It returns the page where the entry was found (as a parameter - res_page),
+ * and the entry itself. Page is returned mapped and unlocked.
+ * Entry is guaranteed to be valid.
+ */
+struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
+			struct qstr *child, struct page **res_page)
+{
+	const char *name = child->name;
+	size_t namelen = child->len;
+	unsigned long npages = dir_blocks(dir);
+	struct f2fs_dir_entry *de = NULL;
+	f2fs_hash_t name_hash;
+	unsigned int max_depth;
+	unsigned int level;
+
+	if (namelen > F2FS_NAME_LEN)
+		return NULL;
+
+	if (npages == 0)
+		return NULL;
+
+	*res_page = NULL;
+
+	name_hash = f2fs_dentry_hash(name, namelen);
+	max_depth = F2FS_I(dir)->i_current_depth;
+
+	for (level = 0; level < max_depth; level++) {
+		de = find_in_level(dir, level, name,
+				namelen, name_hash, res_page);
+		if (de)
+			break;
+	}
+	if (!de && F2FS_I(dir)->chash != name_hash) {
+		F2FS_I(dir)->chash = name_hash;
+		F2FS_I(dir)->clevel = level - 1;
+	}
+	return de;
+}
+
+struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p)
+{
+	struct page *page = NULL;
+	struct f2fs_dir_entry *de = NULL;
+	struct f2fs_dentry_block *dentry_blk = NULL;
+
+	page = get_lock_data_page(dir, 0);
+	if (IS_ERR(page))
+		return NULL;
+
+	dentry_blk = kmap(page);
+	de = &dentry_blk->dentry[1];
+	*p = page;
+	unlock_page(page);
+	return de;
+}
+
+ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr)
+{
+	ino_t res = 0;
+	struct f2fs_dir_entry *de;
+	struct page *page;
+
+	de = f2fs_find_entry(dir, qstr, &page);
+	if (de) {
+		res = le32_to_cpu(de->ino);
+		kunmap(page);
+		f2fs_put_page(page, 0);
+	}
+
+	return res;
+}
+
+void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
+		struct page *page, struct inode *inode)
+{
+	lock_page(page);
+	wait_on_page_writeback(page);
+	de->ino = cpu_to_le32(inode->i_ino);
+	set_de_type(de, inode);
+	kunmap(page);
+	set_page_dirty(page);
+	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+	mark_inode_dirty(dir);
+
+	/* update parent inode number before releasing dentry page */
+	F2FS_I(inode)->i_pino = dir->i_ino;
+
+	f2fs_put_page(page, 1);
+}
+
+void init_dent_inode(const struct qstr *name, struct page *ipage)
+{
+	struct f2fs_node *rn;
+
+	if (IS_ERR(ipage))
+		return;
+
+	wait_on_page_writeback(ipage);
+
+	/* copy name info. to this inode page */
+	rn = (struct f2fs_node *)page_address(ipage);
+	rn->i.i_namelen = cpu_to_le32(name->len);
+	memcpy(rn->i.i_name, name->name, name->len);
+	set_page_dirty(ipage);
+}
+
+static int make_empty_dir(struct inode *inode, struct inode *parent)
+{
+	struct page *dentry_page;
+	struct f2fs_dentry_block *dentry_blk;
+	struct f2fs_dir_entry *de;
+	void *kaddr;
+
+	dentry_page = get_new_data_page(inode, 0, true);
+	if (IS_ERR(dentry_page))
+		return PTR_ERR(dentry_page);
+
+	kaddr = kmap_atomic(dentry_page);
+	dentry_blk = (struct f2fs_dentry_block *)kaddr;
+
+	de = &dentry_blk->dentry[0];
+	de->name_len = cpu_to_le16(1);
+	de->hash_code = 0;
+	de->ino = cpu_to_le32(inode->i_ino);
+	memcpy(dentry_blk->filename[0], ".", 1);
+	set_de_type(de, inode);
+
+	de = &dentry_blk->dentry[1];
+	de->hash_code = 0;
+	de->name_len = cpu_to_le16(2);
+	de->ino = cpu_to_le32(parent->i_ino);
+	memcpy(dentry_blk->filename[1], "..", 2);
+	set_de_type(de, inode);
+
+	test_and_set_bit_le(0, &dentry_blk->dentry_bitmap);
+	test_and_set_bit_le(1, &dentry_blk->dentry_bitmap);
+	kunmap_atomic(kaddr);
+
+	set_page_dirty(dentry_page);
+	f2fs_put_page(dentry_page, 1);
+	return 0;
+}
+
+static int init_inode_metadata(struct inode *inode,
+		struct inode *dir, const struct qstr *name)
+{
+	if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
+		int err;
+		err = new_inode_page(inode, name);
+		if (err)
+			return err;
+
+		if (S_ISDIR(inode->i_mode)) {
+			err = make_empty_dir(inode, dir);
+			if (err) {
+				remove_inode_page(inode);
+				return err;
+			}
+		}
+
+		err = f2fs_init_acl(inode, dir);
+		if (err) {
+			remove_inode_page(inode);
+			return err;
+		}
+	} else {
+		struct page *ipage;
+		ipage = get_node_page(F2FS_SB(dir->i_sb), inode->i_ino);
+		if (IS_ERR(ipage))
+			return PTR_ERR(ipage);
+		set_cold_node(inode, ipage);
+		init_dent_inode(name, ipage);
+		f2fs_put_page(ipage, 1);
+	}
+	if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) {
+		inc_nlink(inode);
+		update_inode_page(inode);
+	}
+	return 0;
+}
+
+static void update_parent_metadata(struct inode *dir, struct inode *inode,
+						unsigned int current_depth)
+{
+	bool need_dir_update = false;
+
+	if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
+		if (S_ISDIR(inode->i_mode)) {
+			inc_nlink(dir);
+			need_dir_update = true;
+		}
+		clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
+	}
+	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+	if (F2FS_I(dir)->i_current_depth != current_depth) {
+		F2FS_I(dir)->i_current_depth = current_depth;
+		need_dir_update = true;
+	}
+
+	if (need_dir_update)
+		update_inode_page(dir);
+	else
+		mark_inode_dirty(dir);
+
+	if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK))
+		clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+}
+
+static int room_for_filename(struct f2fs_dentry_block *dentry_blk, int slots)
+{
+	int bit_start = 0;
+	int zero_start, zero_end;
+next:
+	zero_start = find_next_zero_bit_le(&dentry_blk->dentry_bitmap,
+						NR_DENTRY_IN_BLOCK,
+						bit_start);
+	if (zero_start >= NR_DENTRY_IN_BLOCK)
+		return NR_DENTRY_IN_BLOCK;
+
+	zero_end = find_next_bit_le(&dentry_blk->dentry_bitmap,
+						NR_DENTRY_IN_BLOCK,
+						zero_start);
+	if (zero_end - zero_start >= slots)
+		return zero_start;
+
+	bit_start = zero_end + 1;
+
+	if (zero_end + 1 >= NR_DENTRY_IN_BLOCK)
+		return NR_DENTRY_IN_BLOCK;
+	goto next;
+}
+
+/*
+ * Caller should grab and release a mutex by calling mutex_lock_op() and
+ * mutex_unlock_op().
+ */
+int __f2fs_add_link(struct inode *dir, const struct qstr *name, struct inode *inode)
+{
+	unsigned int bit_pos;
+	unsigned int level;
+	unsigned int current_depth;
+	unsigned long bidx, block;
+	f2fs_hash_t dentry_hash;
+	struct f2fs_dir_entry *de;
+	unsigned int nbucket, nblock;
+	size_t namelen = name->len;
+	struct page *dentry_page = NULL;
+	struct f2fs_dentry_block *dentry_blk = NULL;
+	int slots = GET_DENTRY_SLOTS(namelen);
+	int err = 0;
+	int i;
+
+	dentry_hash = f2fs_dentry_hash(name->name, name->len);
+	level = 0;
+	current_depth = F2FS_I(dir)->i_current_depth;
+	if (F2FS_I(dir)->chash == dentry_hash) {
+		level = F2FS_I(dir)->clevel;
+		F2FS_I(dir)->chash = 0;
+	}
+
+start:
+	if (current_depth == MAX_DIR_HASH_DEPTH)
+		return -ENOSPC;
+
+	/* Increase the depth, if required */
+	if (level == current_depth)
+		++current_depth;
+
+	nbucket = dir_buckets(level);
+	nblock = bucket_blocks(level);
+
+	bidx = dir_block_index(level, (le32_to_cpu(dentry_hash) % nbucket));
+
+	for (block = bidx; block <= (bidx + nblock - 1); block++) {
+		dentry_page = get_new_data_page(dir, block, true);
+		if (IS_ERR(dentry_page))
+			return PTR_ERR(dentry_page);
+
+		dentry_blk = kmap(dentry_page);
+		bit_pos = room_for_filename(dentry_blk, slots);
+		if (bit_pos < NR_DENTRY_IN_BLOCK)
+			goto add_dentry;
+
+		kunmap(dentry_page);
+		f2fs_put_page(dentry_page, 1);
+	}
+
+	/* Move to next level to find the empty slot for new dentry */
+	++level;
+	goto start;
+add_dentry:
+	err = init_inode_metadata(inode, dir, name);
+	if (err)
+		goto fail;
+
+	wait_on_page_writeback(dentry_page);
+
+	de = &dentry_blk->dentry[bit_pos];
+	de->hash_code = dentry_hash;
+	de->name_len = cpu_to_le16(namelen);
+	memcpy(dentry_blk->filename[bit_pos], name->name, name->len);
+	de->ino = cpu_to_le32(inode->i_ino);
+	set_de_type(de, inode);
+	for (i = 0; i < slots; i++)
+		test_and_set_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
+	set_page_dirty(dentry_page);
+
+	update_parent_metadata(dir, inode, current_depth);
+
+	/* update parent inode number before releasing dentry page */
+	F2FS_I(inode)->i_pino = dir->i_ino;
+fail:
+	kunmap(dentry_page);
+	f2fs_put_page(dentry_page, 1);
+	return err;
+}
+
+/*
+ * It only removes the dentry from the dentry page,corresponding name
+ * entry in name page does not need to be touched during deletion.
+ */
+void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
+						struct inode *inode)
+{
+	struct	f2fs_dentry_block *dentry_blk;
+	unsigned int bit_pos;
+	struct address_space *mapping = page->mapping;
+	struct inode *dir = mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+	int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
+	void *kaddr = page_address(page);
+	int i;
+
+	lock_page(page);
+	wait_on_page_writeback(page);
+
+	dentry_blk = (struct f2fs_dentry_block *)kaddr;
+	bit_pos = dentry - (struct f2fs_dir_entry *)dentry_blk->dentry;
+	for (i = 0; i < slots; i++)
+		test_and_clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
+
+	/* Let's check and deallocate this dentry page */
+	bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
+			NR_DENTRY_IN_BLOCK,
+			0);
+	kunmap(page); /* kunmap - pair of f2fs_find_entry */
+	set_page_dirty(page);
+
+	dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+
+	if (inode && S_ISDIR(inode->i_mode)) {
+		drop_nlink(dir);
+		update_inode_page(dir);
+	} else {
+		mark_inode_dirty(dir);
+	}
+
+	if (inode) {
+		inode->i_ctime = CURRENT_TIME;
+		drop_nlink(inode);
+		if (S_ISDIR(inode->i_mode)) {
+			drop_nlink(inode);
+			i_size_write(inode, 0);
+		}
+		update_inode_page(inode);
+
+		if (inode->i_nlink == 0)
+			add_orphan_inode(sbi, inode->i_ino);
+	}
+
+	if (bit_pos == NR_DENTRY_IN_BLOCK) {
+		truncate_hole(dir, page->index, page->index + 1);
+		clear_page_dirty_for_io(page);
+		ClearPageUptodate(page);
+		dec_page_count(sbi, F2FS_DIRTY_DENTS);
+		inode_dec_dirty_dents(dir);
+	}
+	f2fs_put_page(page, 1);
+}
+
+bool f2fs_empty_dir(struct inode *dir)
+{
+	unsigned long bidx;
+	struct page *dentry_page;
+	unsigned int bit_pos;
+	struct	f2fs_dentry_block *dentry_blk;
+	unsigned long nblock = dir_blocks(dir);
+
+	for (bidx = 0; bidx < nblock; bidx++) {
+		void *kaddr;
+		dentry_page = get_lock_data_page(dir, bidx);
+		if (IS_ERR(dentry_page)) {
+			if (PTR_ERR(dentry_page) == -ENOENT)
+				continue;
+			else
+				return false;
+		}
+
+		kaddr = kmap_atomic(dentry_page);
+		dentry_blk = (struct f2fs_dentry_block *)kaddr;
+		if (bidx == 0)
+			bit_pos = 2;
+		else
+			bit_pos = 0;
+		bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
+						NR_DENTRY_IN_BLOCK,
+						bit_pos);
+		kunmap_atomic(kaddr);
+
+		f2fs_put_page(dentry_page, 1);
+
+		if (bit_pos < NR_DENTRY_IN_BLOCK)
+			return false;
+	}
+	return true;
+}
+
+static int f2fs_readdir(struct file *file, void *dirent, filldir_t filldir)
+{
+	unsigned long pos = file->f_pos;
+	struct inode *inode = file_inode(file);
+	unsigned long npages = dir_blocks(inode);
+	unsigned char *types = NULL;
+	unsigned int bit_pos = 0, start_bit_pos = 0;
+	int over = 0;
+	struct f2fs_dentry_block *dentry_blk = NULL;
+	struct f2fs_dir_entry *de = NULL;
+	struct page *dentry_page = NULL;
+	unsigned int n = 0;
+	unsigned char d_type = DT_UNKNOWN;
+	int slots;
+
+	types = f2fs_filetype_table;
+	bit_pos = (pos % NR_DENTRY_IN_BLOCK);
+	n = (pos / NR_DENTRY_IN_BLOCK);
+
+	for ( ; n < npages; n++) {
+		dentry_page = get_lock_data_page(inode, n);
+		if (IS_ERR(dentry_page))
+			continue;
+
+		start_bit_pos = bit_pos;
+		dentry_blk = kmap(dentry_page);
+		while (bit_pos < NR_DENTRY_IN_BLOCK) {
+			d_type = DT_UNKNOWN;
+			bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
+							NR_DENTRY_IN_BLOCK,
+							bit_pos);
+			if (bit_pos >= NR_DENTRY_IN_BLOCK)
+				break;
+
+			de = &dentry_blk->dentry[bit_pos];
+			if (types && de->file_type < F2FS_FT_MAX)
+				d_type = types[de->file_type];
+
+			over = filldir(dirent,
+					dentry_blk->filename[bit_pos],
+					le16_to_cpu(de->name_len),
+					(n * NR_DENTRY_IN_BLOCK) + bit_pos,
+					le32_to_cpu(de->ino), d_type);
+			if (over) {
+				file->f_pos += bit_pos - start_bit_pos;
+				goto success;
+			}
+			slots = GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+			bit_pos += slots;
+		}
+		bit_pos = 0;
+		file->f_pos = (n + 1) * NR_DENTRY_IN_BLOCK;
+		kunmap(dentry_page);
+		f2fs_put_page(dentry_page, 1);
+		dentry_page = NULL;
+	}
+success:
+	if (dentry_page && !IS_ERR(dentry_page)) {
+		kunmap(dentry_page);
+		f2fs_put_page(dentry_page, 1);
+	}
+
+	return 0;
+}
+
+const struct file_operations f2fs_dir_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_read_dir,
+	.readdir	= f2fs_readdir,
+	.fsync		= f2fs_sync_file,
+	.unlocked_ioctl	= f2fs_ioctl,
+};

fs/f2fs/file.c

@@ -0,0 +1,663 @@
+/*
+ * fs/f2fs/file.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/stat.h>
+#include <linux/buffer_head.h>
+#include <linux/writeback.h>
+#include <linux/blkdev.h>
+#include <linux/falloc.h>
+#include <linux/types.h>
+#include <linux/compat.h>
+#include <linux/uaccess.h>
+#include <linux/mount.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include "segment.h"
+#include "xattr.h"
+#include "acl.h"
+#include <trace/events/f2fs.h>
+
+static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
+						struct vm_fault *vmf)
+{
+	struct page *page = vmf->page;
+	struct inode *inode = file_inode(vma->vm_file);
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	block_t old_blk_addr;
+	struct dnode_of_data dn;
+	int err, ilock;
+
+	f2fs_balance_fs(sbi);
+
+	sb_start_pagefault(inode->i_sb);
+
+	/* block allocation */
+	ilock = mutex_lock_op(sbi);
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	err = get_dnode_of_data(&dn, page->index, ALLOC_NODE);
+	if (err) {
+		mutex_unlock_op(sbi, ilock);
+		goto out;
+	}
+
+	old_blk_addr = dn.data_blkaddr;
+
+	if (old_blk_addr == NULL_ADDR) {
+		err = reserve_new_block(&dn);
+		if (err) {
+			f2fs_put_dnode(&dn);
+			mutex_unlock_op(sbi, ilock);
+			goto out;
+		}
+	}
+	f2fs_put_dnode(&dn);
+	mutex_unlock_op(sbi, ilock);
+
+	lock_page(page);
+	if (page->mapping != inode->i_mapping ||
+			page_offset(page) >= i_size_read(inode) ||
+			!PageUptodate(page)) {
+		unlock_page(page);
+		err = -EFAULT;
+		goto out;
+	}
+
+	/*
+	 * check to see if the page is mapped already (no holes)
+	 */
+	if (PageMappedToDisk(page))
+		goto out;
+
+	/* fill the page */
+	wait_on_page_writeback(page);
+
+	/* page is wholly or partially inside EOF */
+	if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) {
+		unsigned offset;
+		offset = i_size_read(inode) & ~PAGE_CACHE_MASK;
+		zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+	}
+	set_page_dirty(page);
+	SetPageUptodate(page);
+
+	file_update_time(vma->vm_file);
+out:
+	sb_end_pagefault(inode->i_sb);
+	return block_page_mkwrite_return(err);
+}
+
+static const struct vm_operations_struct f2fs_file_vm_ops = {
+	.fault		= filemap_fault,
+	.page_mkwrite	= f2fs_vm_page_mkwrite,
+	.remap_pages	= generic_file_remap_pages,
+};
+
+int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	struct inode *inode = file->f_mapping->host;
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	int ret = 0;
+	bool need_cp = false;
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_ALL,
+		.nr_to_write = LONG_MAX,
+		.for_reclaim = 0,
+	};
+
+	if (inode->i_sb->s_flags & MS_RDONLY)
+		return 0;
+
+	trace_f2fs_sync_file_enter(inode);
+	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (ret) {
+		trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
+		return ret;
+	}
+
+	/* guarantee free sections for fsync */
+	f2fs_balance_fs(sbi);
+
+	mutex_lock(&inode->i_mutex);
+
+	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+		goto out;
+
+	if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
+		need_cp = true;
+	else if (is_cp_file(inode))
+		need_cp = true;
+	else if (!space_for_roll_forward(sbi))
+		need_cp = true;
+	else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
+		need_cp = true;
+
+	if (need_cp) {
+		/* all the dirty node pages should be flushed for POR */
+		ret = f2fs_sync_fs(inode->i_sb, 1);
+	} else {
+		/* if there is no written node page, write its inode page */
+		while (!sync_node_pages(sbi, inode->i_ino, &wbc)) {
+			ret = f2fs_write_inode(inode, NULL);
+			if (ret)
+				goto out;
+		}
+		filemap_fdatawait_range(sbi->node_inode->i_mapping,
+							0, LONG_MAX);
+		ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+	}
+out:
+	mutex_unlock(&inode->i_mutex);
+	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
+	return ret;
+}
+
+static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	file_accessed(file);
+	vma->vm_ops = &f2fs_file_vm_ops;
+	return 0;
+}
+
+static int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
+{
+	int nr_free = 0, ofs = dn->ofs_in_node;
+	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
+	struct f2fs_node *raw_node;
+	__le32 *addr;
+
+	raw_node = page_address(dn->node_page);
+	addr = blkaddr_in_node(raw_node) + ofs;
+
+	for ( ; count > 0; count--, addr++, dn->ofs_in_node++) {
+		block_t blkaddr = le32_to_cpu(*addr);
+		if (blkaddr == NULL_ADDR)
+			continue;
+
+		update_extent_cache(NULL_ADDR, dn);
+		invalidate_blocks(sbi, blkaddr);
+		dec_valid_block_count(sbi, dn->inode, 1);
+		nr_free++;
+	}
+	if (nr_free) {
+		set_page_dirty(dn->node_page);
+		sync_inode_page(dn);
+	}
+	dn->ofs_in_node = ofs;
+
+	trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
+					 dn->ofs_in_node, nr_free);
+	return nr_free;
+}
+
+void truncate_data_blocks(struct dnode_of_data *dn)
+{
+	truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
+}
+
+static void truncate_partial_data_page(struct inode *inode, u64 from)
+{
+	unsigned offset = from & (PAGE_CACHE_SIZE - 1);
+	struct page *page;
+
+	if (!offset)
+		return;
+
+	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, false);
+	if (IS_ERR(page))
+		return;
+
+	lock_page(page);
+	if (page->mapping != inode->i_mapping) {
+		f2fs_put_page(page, 1);
+		return;
+	}
+	wait_on_page_writeback(page);
+	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
+	set_page_dirty(page);
+	f2fs_put_page(page, 1);
+}
+
+static int truncate_blocks(struct inode *inode, u64 from)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	unsigned int blocksize = inode->i_sb->s_blocksize;
+	struct dnode_of_data dn;
+	pgoff_t free_from;
+	int count = 0, ilock = -1;
+	int err;
+
+	trace_f2fs_truncate_blocks_enter(inode, from);
+
+	free_from = (pgoff_t)
+			((from + blocksize - 1) >> (sbi->log_blocksize));
+
+	ilock = mutex_lock_op(sbi);
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
+	if (err) {
+		if (err == -ENOENT)
+			goto free_next;
+		mutex_unlock_op(sbi, ilock);
+		trace_f2fs_truncate_blocks_exit(inode, err);
+		return err;
+	}
+
+	if (IS_INODE(dn.node_page))
+		count = ADDRS_PER_INODE;
+	else
+		count = ADDRS_PER_BLOCK;
+
+	count -= dn.ofs_in_node;
+	BUG_ON(count < 0);
+
+	if (dn.ofs_in_node || IS_INODE(dn.node_page)) {
+		truncate_data_blocks_range(&dn, count);
+		free_from += count;
+	}
+
+	f2fs_put_dnode(&dn);
+free_next:
+	err = truncate_inode_blocks(inode, free_from);
+	mutex_unlock_op(sbi, ilock);
+
+	/* lastly zero out the first data page */
+	truncate_partial_data_page(inode, from);
+
+	trace_f2fs_truncate_blocks_exit(inode, err);
+	return err;
+}
+
+void f2fs_truncate(struct inode *inode)
+{
+	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+				S_ISLNK(inode->i_mode)))
+		return;
+
+	trace_f2fs_truncate(inode);
+
+	if (!truncate_blocks(inode, i_size_read(inode))) {
+		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		mark_inode_dirty(inode);
+	}
+}
+
+static int f2fs_getattr(struct vfsmount *mnt,
+			 struct dentry *dentry, struct kstat *stat)
+{
+	struct inode *inode = dentry->d_inode;
+	generic_fillattr(inode, stat);
+	stat->blocks <<= 3;
+	return 0;
+}
+
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+static void __setattr_copy(struct inode *inode, const struct iattr *attr)
+{
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	unsigned int ia_valid = attr->ia_valid;
+
+	if (ia_valid & ATTR_UID)
+		inode->i_uid = attr->ia_uid;
+	if (ia_valid & ATTR_GID)
+		inode->i_gid = attr->ia_gid;
+	if (ia_valid & ATTR_ATIME)
+		inode->i_atime = timespec_trunc(attr->ia_atime,
+						inode->i_sb->s_time_gran);
+	if (ia_valid & ATTR_MTIME)
+		inode->i_mtime = timespec_trunc(attr->ia_mtime,
+						inode->i_sb->s_time_gran);
+	if (ia_valid & ATTR_CTIME)
+		inode->i_ctime = timespec_trunc(attr->ia_ctime,
+						inode->i_sb->s_time_gran);
+	if (ia_valid & ATTR_MODE) {
+		umode_t mode = attr->ia_mode;
+
+		if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
+			mode &= ~S_ISGID;
+		set_acl_inode(fi, mode);
+	}
+}
+#else
+#define __setattr_copy setattr_copy
+#endif
+
+int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	struct inode *inode = dentry->d_inode;
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	int err;
+
+	err = inode_change_ok(inode, attr);
+	if (err)
+		return err;
+
+	if ((attr->ia_valid & ATTR_SIZE) &&
+			attr->ia_size != i_size_read(inode)) {
+		truncate_setsize(inode, attr->ia_size);
+		f2fs_truncate(inode);
+		f2fs_balance_fs(F2FS_SB(inode->i_sb));
+	}
+
+	__setattr_copy(inode, attr);
+
+	if (attr->ia_valid & ATTR_MODE) {
+		err = f2fs_acl_chmod(inode);
+		if (err || is_inode_flag_set(fi, FI_ACL_MODE)) {
+			inode->i_mode = fi->i_acl_mode;
+			clear_inode_flag(fi, FI_ACL_MODE);
+		}
+	}
+
+	mark_inode_dirty(inode);
+	return err;
+}
+
+const struct inode_operations f2fs_file_inode_operations = {
+	.getattr	= f2fs_getattr,
+	.setattr	= f2fs_setattr,
+	.get_acl	= f2fs_get_acl,
+#ifdef CONFIG_F2FS_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= f2fs_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+};
+
+static void fill_zero(struct inode *inode, pgoff_t index,
+					loff_t start, loff_t len)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct page *page;
+	int ilock;
+
+	if (!len)
+		return;
+
+	f2fs_balance_fs(sbi);
+
+	ilock = mutex_lock_op(sbi);
+	page = get_new_data_page(inode, index, false);
+	mutex_unlock_op(sbi, ilock);
+
+	if (!IS_ERR(page)) {
+		wait_on_page_writeback(page);
+		zero_user(page, start, len);
+		set_page_dirty(page);
+		f2fs_put_page(page, 1);
+	}
+}
+
+int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
+{
+	pgoff_t index;
+	int err;
+
+	for (index = pg_start; index < pg_end; index++) {
+		struct dnode_of_data dn;
+
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
+		if (err) {
+			if (err == -ENOENT)
+				continue;
+			return err;
+		}
+
+		if (dn.data_blkaddr != NULL_ADDR)
+			truncate_data_blocks_range(&dn, 1);
+		f2fs_put_dnode(&dn);
+	}
+	return 0;
+}
+
+static int punch_hole(struct inode *inode, loff_t offset, loff_t len, int mode)
+{
+	pgoff_t pg_start, pg_end;
+	loff_t off_start, off_end;
+	int ret = 0;
+
+	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
+	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
+
+	off_start = offset & (PAGE_CACHE_SIZE - 1);
+	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
+
+	if (pg_start == pg_end) {
+		fill_zero(inode, pg_start, off_start,
+						off_end - off_start);
+	} else {
+		if (off_start)
+			fill_zero(inode, pg_start++, off_start,
+					PAGE_CACHE_SIZE - off_start);
+		if (off_end)
+			fill_zero(inode, pg_end, 0, off_end);
+
+		if (pg_start < pg_end) {
+			struct address_space *mapping = inode->i_mapping;
+			loff_t blk_start, blk_end;
+			struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+			int ilock;
+
+			f2fs_balance_fs(sbi);
+
+			blk_start = pg_start << PAGE_CACHE_SHIFT;
+			blk_end = pg_end << PAGE_CACHE_SHIFT;
+			truncate_inode_pages_range(mapping, blk_start,
+					blk_end - 1);
+
+			ilock = mutex_lock_op(sbi);
+			ret = truncate_hole(inode, pg_start, pg_end);
+			mutex_unlock_op(sbi, ilock);
+		}
+	}
+
+	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+		i_size_read(inode) <= (offset + len)) {
+		i_size_write(inode, offset);
+		mark_inode_dirty(inode);
+	}
+
+	return ret;
+}
+
+static int expand_inode_data(struct inode *inode, loff_t offset,
+					loff_t len, int mode)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	pgoff_t index, pg_start, pg_end;
+	loff_t new_size = i_size_read(inode);
+	loff_t off_start, off_end;
+	int ret = 0;
+
+	ret = inode_newsize_ok(inode, (len + offset));
+	if (ret)
+		return ret;
+
+	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
+	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
+
+	off_start = offset & (PAGE_CACHE_SIZE - 1);
+	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
+
+	for (index = pg_start; index <= pg_end; index++) {
+		struct dnode_of_data dn;
+		int ilock;
+
+		ilock = mutex_lock_op(sbi);
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		ret = get_dnode_of_data(&dn, index, ALLOC_NODE);
+		if (ret) {
+			mutex_unlock_op(sbi, ilock);
+			break;
+		}
+
+		if (dn.data_blkaddr == NULL_ADDR) {
+			ret = reserve_new_block(&dn);
+			if (ret) {
+				f2fs_put_dnode(&dn);
+				mutex_unlock_op(sbi, ilock);
+				break;
+			}
+		}
+		f2fs_put_dnode(&dn);
+		mutex_unlock_op(sbi, ilock);
+
+		if (pg_start == pg_end)
+			new_size = offset + len;
+		else if (index == pg_start && off_start)
+			new_size = (index + 1) << PAGE_CACHE_SHIFT;
+		else if (index == pg_end)
+			new_size = (index << PAGE_CACHE_SHIFT) + off_end;
+		else
+			new_size += PAGE_CACHE_SIZE;
+	}
+
+	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
+		i_size_read(inode) < new_size) {
+		i_size_write(inode, new_size);
+		mark_inode_dirty(inode);
+	}
+
+	return ret;
+}
+
+static long f2fs_fallocate(struct file *file, int mode,
+				loff_t offset, loff_t len)
+{
+	struct inode *inode = file_inode(file);
+	long ret;
+
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
+
+	if (mode & FALLOC_FL_PUNCH_HOLE)
+		ret = punch_hole(inode, offset, len, mode);
+	else
+		ret = expand_inode_data(inode, offset, len, mode);
+
+	if (!ret) {
+		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		mark_inode_dirty(inode);
+	}
+	trace_f2fs_fallocate(inode, mode, offset, len, ret);
+	return ret;
+}
+
+#define F2FS_REG_FLMASK		(~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
+#define F2FS_OTHER_FLMASK	(FS_NODUMP_FL | FS_NOATIME_FL)
+
+static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
+{
+	if (S_ISDIR(mode))
+		return flags;
+	else if (S_ISREG(mode))
+		return flags & F2FS_REG_FLMASK;
+	else
+		return flags & F2FS_OTHER_FLMASK;
+}
+
+long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	unsigned int flags;
+	int ret;
+
+	switch (cmd) {
+	case FS_IOC_GETFLAGS:
+		flags = fi->i_flags & FS_FL_USER_VISIBLE;
+		return put_user(flags, (int __user *) arg);
+	case FS_IOC_SETFLAGS:
+	{
+		unsigned int oldflags;
+
+		ret = mnt_want_write_file(filp);
+		if (ret)
+			return ret;
+
+		if (!inode_owner_or_capable(inode)) {
+			ret = -EACCES;
+			goto out;
+		}
+
+		if (get_user(flags, (int __user *) arg)) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		flags = f2fs_mask_flags(inode->i_mode, flags);
+
+		mutex_lock(&inode->i_mutex);
+
+		oldflags = fi->i_flags;
+
+		if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
+			if (!capable(CAP_LINUX_IMMUTABLE)) {
+				mutex_unlock(&inode->i_mutex);
+				ret = -EPERM;
+				goto out;
+			}
+		}
+
+		flags = flags & FS_FL_USER_MODIFIABLE;
+		flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
+		fi->i_flags = flags;
+		mutex_unlock(&inode->i_mutex);
+
+		f2fs_set_inode_flags(inode);
+		inode->i_ctime = CURRENT_TIME;
+		mark_inode_dirty(inode);
+out:
+		mnt_drop_write_file(filp);
+		return ret;
+	}
+	default:
+		return -ENOTTY;
+	}
+}
+
+#ifdef CONFIG_COMPAT
+long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case F2FS_IOC32_GETFLAGS:
+		cmd = F2FS_IOC_GETFLAGS;
+		break;
+	case F2FS_IOC32_SETFLAGS:
+		cmd = F2FS_IOC_SETFLAGS;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+	return f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
+}
+#endif
+
+const struct file_operations f2fs_file_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= generic_file_aio_read,
+	.aio_write	= generic_file_aio_write,
+	.open		= generic_file_open,
+	.mmap		= f2fs_file_mmap,
+	.fsync		= f2fs_sync_file,
+	.fallocate	= f2fs_fallocate,
+	.unlocked_ioctl	= f2fs_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= f2fs_compat_ioctl,
+#endif
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
+};

fs/f2fs/gc.c

@@ -0,0 +1,729 @@
+/*
+ * fs/f2fs/gc.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/backing-dev.h>
+#include <linux/init.h>
+#include <linux/f2fs_fs.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
+#include <linux/freezer.h>
+#include <linux/blkdev.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include "segment.h"
+#include "gc.h"
+#include <trace/events/f2fs.h>
+
+static struct kmem_cache *winode_slab;
+
+static int gc_thread_func(void *data)
+{
+	struct f2fs_sb_info *sbi = data;
+	wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head;
+	long wait_ms;
+
+	wait_ms = GC_THREAD_MIN_SLEEP_TIME;
+
+	do {
+		if (try_to_freeze())
+			continue;
+		else
+			wait_event_interruptible_timeout(*wq,
+						kthread_should_stop(),
+						msecs_to_jiffies(wait_ms));
+		if (kthread_should_stop())
+			break;
+
+		if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
+			wait_ms = GC_THREAD_MAX_SLEEP_TIME;
+			continue;
+		}
+
+		/*
+		 * [GC triggering condition]
+		 * 0. GC is not conducted currently.
+		 * 1. There are enough dirty segments.
+		 * 2. IO subsystem is idle by checking the # of writeback pages.
+		 * 3. IO subsystem is idle by checking the # of requests in
+		 *    bdev's request list.
+		 *
+		 * Note) We have to avoid triggering GCs too much frequently.
+		 * Because it is possible that some segments can be
+		 * invalidated soon after by user update or deletion.
+		 * So, I'd like to wait some time to collect dirty segments.
+		 */
+		if (!mutex_trylock(&sbi->gc_mutex))
+			continue;
+
+		if (!is_idle(sbi)) {
+			wait_ms = increase_sleep_time(wait_ms);
+			mutex_unlock(&sbi->gc_mutex);
+			continue;
+		}
+
+		if (has_enough_invalid_blocks(sbi))
+			wait_ms = decrease_sleep_time(wait_ms);
+		else
+			wait_ms = increase_sleep_time(wait_ms);
+
+		sbi->bg_gc++;
+
+		/* if return value is not zero, no victim was selected */
+		if (f2fs_gc(sbi))
+			wait_ms = GC_THREAD_NOGC_SLEEP_TIME;
+	} while (!kthread_should_stop());
+	return 0;
+}
+
+int start_gc_thread(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_gc_kthread *gc_th;
+	dev_t dev = sbi->sb->s_bdev->bd_dev;
+
+	if (!test_opt(sbi, BG_GC))
+		return 0;
+	gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
+	if (!gc_th)
+		return -ENOMEM;
+
+	sbi->gc_thread = gc_th;
+	init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
+	sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi,
+			"f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev));
+	if (IS_ERR(gc_th->f2fs_gc_task)) {
+		kfree(gc_th);
+		sbi->gc_thread = NULL;
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void stop_gc_thread(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
+	if (!gc_th)
+		return;
+	kthread_stop(gc_th->f2fs_gc_task);
+	kfree(gc_th);
+	sbi->gc_thread = NULL;
+}
+
+static int select_gc_type(int gc_type)
+{
+	return (gc_type == BG_GC) ? GC_CB : GC_GREEDY;
+}
+
+static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
+			int type, struct victim_sel_policy *p)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+
+	if (p->alloc_mode == SSR) {
+		p->gc_mode = GC_GREEDY;
+		p->dirty_segmap = dirty_i->dirty_segmap[type];
+		p->ofs_unit = 1;
+	} else {
+		p->gc_mode = select_gc_type(gc_type);
+		p->dirty_segmap = dirty_i->dirty_segmap[DIRTY];
+		p->ofs_unit = sbi->segs_per_sec;
+	}
+	p->offset = sbi->last_victim[p->gc_mode];
+}
+
+static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
+				struct victim_sel_policy *p)
+{
+	/* SSR allocates in a segment unit */
+	if (p->alloc_mode == SSR)
+		return 1 << sbi->log_blocks_per_seg;
+	if (p->gc_mode == GC_GREEDY)
+		return (1 << sbi->log_blocks_per_seg) * p->ofs_unit;
+	else if (p->gc_mode == GC_CB)
+		return UINT_MAX;
+	else /* No other gc_mode */
+		return 0;
+}
+
+static unsigned int check_bg_victims(struct f2fs_sb_info *sbi)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+	unsigned int hint = 0;
+	unsigned int secno;
+
+	/*
+	 * If the gc_type is FG_GC, we can select victim segments
+	 * selected by background GC before.
+	 * Those segments guarantee they have small valid blocks.
+	 */
+next:
+	secno = find_next_bit(dirty_i->victim_secmap, TOTAL_SECS(sbi), hint++);
+	if (secno < TOTAL_SECS(sbi)) {
+		if (sec_usage_check(sbi, secno))
+			goto next;
+		clear_bit(secno, dirty_i->victim_secmap);
+		return secno * sbi->segs_per_sec;
+	}
+	return NULL_SEGNO;
+}
+
+static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	unsigned int secno = GET_SECNO(sbi, segno);
+	unsigned int start = secno * sbi->segs_per_sec;
+	unsigned long long mtime = 0;
+	unsigned int vblocks;
+	unsigned char age = 0;
+	unsigned char u;
+	unsigned int i;
+
+	for (i = 0; i < sbi->segs_per_sec; i++)
+		mtime += get_seg_entry(sbi, start + i)->mtime;
+	vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+
+	mtime = div_u64(mtime, sbi->segs_per_sec);
+	vblocks = div_u64(vblocks, sbi->segs_per_sec);
+
+	u = (vblocks * 100) >> sbi->log_blocks_per_seg;
+
+	/* Handle if the system time is changed by user */
+	if (mtime < sit_i->min_mtime)
+		sit_i->min_mtime = mtime;
+	if (mtime > sit_i->max_mtime)
+		sit_i->max_mtime = mtime;
+	if (sit_i->max_mtime != sit_i->min_mtime)
+		age = 100 - div64_u64(100 * (mtime - sit_i->min_mtime),
+				sit_i->max_mtime - sit_i->min_mtime);
+
+	return UINT_MAX - ((100 * (100 - u) * age) / (100 + u));
+}
+
+static unsigned int get_gc_cost(struct f2fs_sb_info *sbi, unsigned int segno,
+					struct victim_sel_policy *p)
+{
+	if (p->alloc_mode == SSR)
+		return get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+
+	/* alloc_mode == LFS */
+	if (p->gc_mode == GC_GREEDY)
+		return get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+	else
+		return get_cb_cost(sbi, segno);
+}
+
+/*
+ * This function is called from two paths.
+ * One is garbage collection and the other is SSR segment selection.
+ * When it is called during GC, it just gets a victim segment
+ * and it does not remove it from dirty seglist.
+ * When it is called from SSR segment selection, it finds a segment
+ * which has minimum valid blocks and removes it from dirty seglist.
+ */
+static int get_victim_by_default(struct f2fs_sb_info *sbi,
+		unsigned int *result, int gc_type, int type, char alloc_mode)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+	struct victim_sel_policy p;
+	unsigned int secno;
+	int nsearched = 0;
+
+	p.alloc_mode = alloc_mode;
+	select_policy(sbi, gc_type, type, &p);
+
+	p.min_segno = NULL_SEGNO;
+	p.min_cost = get_max_cost(sbi, &p);
+
+	mutex_lock(&dirty_i->seglist_lock);
+
+	if (p.alloc_mode == LFS && gc_type == FG_GC) {
+		p.min_segno = check_bg_victims(sbi);
+		if (p.min_segno != NULL_SEGNO)
+			goto got_it;
+	}
+
+	while (1) {
+		unsigned long cost;
+		unsigned int segno;
+
+		segno = find_next_bit(p.dirty_segmap,
+						TOTAL_SEGS(sbi), p.offset);
+		if (segno >= TOTAL_SEGS(sbi)) {
+			if (sbi->last_victim[p.gc_mode]) {
+				sbi->last_victim[p.gc_mode] = 0;
+				p.offset = 0;
+				continue;
+			}
+			break;
+		}
+		p.offset = ((segno / p.ofs_unit) * p.ofs_unit) + p.ofs_unit;
+		secno = GET_SECNO(sbi, segno);
+
+		if (sec_usage_check(sbi, secno))
+			continue;
+		if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
+			continue;
+
+		cost = get_gc_cost(sbi, segno, &p);
+
+		if (p.min_cost > cost) {
+			p.min_segno = segno;
+			p.min_cost = cost;
+		}
+
+		if (cost == get_max_cost(sbi, &p))
+			continue;
+
+		if (nsearched++ >= MAX_VICTIM_SEARCH) {
+			sbi->last_victim[p.gc_mode] = segno;
+			break;
+		}
+	}
+got_it:
+	if (p.min_segno != NULL_SEGNO) {
+		if (p.alloc_mode == LFS) {
+			secno = GET_SECNO(sbi, p.min_segno);
+			if (gc_type == FG_GC)
+				sbi->cur_victim_sec = secno;
+			else
+				set_bit(secno, dirty_i->victim_secmap);
+		}
+		*result = (p.min_segno / p.ofs_unit) * p.ofs_unit;
+
+		trace_f2fs_get_victim(sbi->sb, type, gc_type, &p,
+				sbi->cur_victim_sec,
+				prefree_segments(sbi), free_segments(sbi));
+	}
+	mutex_unlock(&dirty_i->seglist_lock);
+
+	return (p.min_segno == NULL_SEGNO) ? 0 : 1;
+}
+
+static const struct victim_selection default_v_ops = {
+	.get_victim = get_victim_by_default,
+};
+
+static struct inode *find_gc_inode(nid_t ino, struct list_head *ilist)
+{
+	struct list_head *this;
+	struct inode_entry *ie;
+
+	list_for_each(this, ilist) {
+		ie = list_entry(this, struct inode_entry, list);
+		if (ie->inode->i_ino == ino)
+			return ie->inode;
+	}
+	return NULL;
+}
+
+static void add_gc_inode(struct inode *inode, struct list_head *ilist)
+{
+	struct list_head *this;
+	struct inode_entry *new_ie, *ie;
+
+	list_for_each(this, ilist) {
+		ie = list_entry(this, struct inode_entry, list);
+		if (ie->inode == inode) {
+			iput(inode);
+			return;
+		}
+	}
+repeat:
+	new_ie = kmem_cache_alloc(winode_slab, GFP_NOFS);
+	if (!new_ie) {
+		cond_resched();
+		goto repeat;
+	}
+	new_ie->inode = inode;
+	list_add_tail(&new_ie->list, ilist);
+}
+
+static void put_gc_inode(struct list_head *ilist)
+{
+	struct inode_entry *ie, *next_ie;
+	list_for_each_entry_safe(ie, next_ie, ilist, list) {
+		iput(ie->inode);
+		list_del(&ie->list);
+		kmem_cache_free(winode_slab, ie);
+	}
+}
+
+static int check_valid_map(struct f2fs_sb_info *sbi,
+				unsigned int segno, int offset)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	struct seg_entry *sentry;
+	int ret;
+
+	mutex_lock(&sit_i->sentry_lock);
+	sentry = get_seg_entry(sbi, segno);
+	ret = f2fs_test_bit(offset, sentry->cur_valid_map);
+	mutex_unlock(&sit_i->sentry_lock);
+	return ret;
+}
+
+/*
+ * This function compares node address got in summary with that in NAT.
+ * On validity, copy that node with cold status, otherwise (invalid node)
+ * ignore that.
+ */
+static void gc_node_segment(struct f2fs_sb_info *sbi,
+		struct f2fs_summary *sum, unsigned int segno, int gc_type)
+{
+	bool initial = true;
+	struct f2fs_summary *entry;
+	int off;
+
+next_step:
+	entry = sum;
+
+	for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
+		nid_t nid = le32_to_cpu(entry->nid);
+		struct page *node_page;
+
+		/* stop BG_GC if there is not enough free sections. */
+		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
+			return;
+
+		if (check_valid_map(sbi, segno, off) == 0)
+			continue;
+
+		if (initial) {
+			ra_node_page(sbi, nid);
+			continue;
+		}
+		node_page = get_node_page(sbi, nid);
+		if (IS_ERR(node_page))
+			continue;
+
+		/* set page dirty and write it */
+		if (gc_type == FG_GC) {
+			f2fs_submit_bio(sbi, NODE, true);
+			wait_on_page_writeback(node_page);
+			set_page_dirty(node_page);
+		} else {
+			if (!PageWriteback(node_page))
+				set_page_dirty(node_page);
+		}
+		f2fs_put_page(node_page, 1);
+		stat_inc_node_blk_count(sbi, 1);
+	}
+
+	if (initial) {
+		initial = false;
+		goto next_step;
+	}
+
+	if (gc_type == FG_GC) {
+		struct writeback_control wbc = {
+			.sync_mode = WB_SYNC_ALL,
+			.nr_to_write = LONG_MAX,
+			.for_reclaim = 0,
+		};
+		sync_node_pages(sbi, 0, &wbc);
+
+		/*
+		 * In the case of FG_GC, it'd be better to reclaim this victim
+		 * completely.
+		 */
+		if (get_valid_blocks(sbi, segno, 1) != 0)
+			goto next_step;
+	}
+}
+
+/*
+ * Calculate start block index indicating the given node offset.
+ * Be careful, caller should give this node offset only indicating direct node
+ * blocks. If any node offsets, which point the other types of node blocks such
+ * as indirect or double indirect node blocks, are given, it must be a caller's
+ * bug.
+ */
+block_t start_bidx_of_node(unsigned int node_ofs)
+{
+	unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4;
+	unsigned int bidx;
+
+	if (node_ofs == 0)
+		return 0;
+
+	if (node_ofs <= 2) {
+		bidx = node_ofs - 1;
+	} else if (node_ofs <= indirect_blks) {
+		int dec = (node_ofs - 4) / (NIDS_PER_BLOCK + 1);
+		bidx = node_ofs - 2 - dec;
+	} else {
+		int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1);
+		bidx = node_ofs - 5 - dec;
+	}
+	return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE;
+}
+
+static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+		struct node_info *dni, block_t blkaddr, unsigned int *nofs)
+{
+	struct page *node_page;
+	nid_t nid;
+	unsigned int ofs_in_node;
+	block_t source_blkaddr;
+
+	nid = le32_to_cpu(sum->nid);
+	ofs_in_node = le16_to_cpu(sum->ofs_in_node);
+
+	node_page = get_node_page(sbi, nid);
+	if (IS_ERR(node_page))
+		return 0;
+
+	get_node_info(sbi, nid, dni);
+
+	if (sum->version != dni->version) {
+		f2fs_put_page(node_page, 1);
+		return 0;
+	}
+
+	*nofs = ofs_of_node(node_page);
+	source_blkaddr = datablock_addr(node_page, ofs_in_node);
+	f2fs_put_page(node_page, 1);
+
+	if (source_blkaddr != blkaddr)
+		return 0;
+	return 1;
+}
+
+static void move_data_page(struct inode *inode, struct page *page, int gc_type)
+{
+	if (gc_type == BG_GC) {
+		if (PageWriteback(page))
+			goto out;
+		set_page_dirty(page);
+		set_cold_data(page);
+	} else {
+		struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+
+		if (PageWriteback(page)) {
+			f2fs_submit_bio(sbi, DATA, true);
+			wait_on_page_writeback(page);
+		}
+
+		if (clear_page_dirty_for_io(page) &&
+			S_ISDIR(inode->i_mode)) {
+			dec_page_count(sbi, F2FS_DIRTY_DENTS);
+			inode_dec_dirty_dents(inode);
+		}
+		set_cold_data(page);
+		do_write_data_page(page);
+		clear_cold_data(page);
+	}
+out:
+	f2fs_put_page(page, 1);
+}
+
+/*
+ * This function tries to get parent node of victim data block, and identifies
+ * data block validity. If the block is valid, copy that with cold status and
+ * modify parent node.
+ * If the parent node is not valid or the data block address is different,
+ * the victim data block is ignored.
+ */
+static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+		struct list_head *ilist, unsigned int segno, int gc_type)
+{
+	struct super_block *sb = sbi->sb;
+	struct f2fs_summary *entry;
+	block_t start_addr;
+	int off;
+	int phase = 0;
+
+	start_addr = START_BLOCK(sbi, segno);
+
+next_step:
+	entry = sum;
+
+	for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
+		struct page *data_page;
+		struct inode *inode;
+		struct node_info dni; /* dnode info for the data */
+		unsigned int ofs_in_node, nofs;
+		block_t start_bidx;
+
+		/* stop BG_GC if there is not enough free sections. */
+		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
+			return;
+
+		if (check_valid_map(sbi, segno, off) == 0)
+			continue;
+
+		if (phase == 0) {
+			ra_node_page(sbi, le32_to_cpu(entry->nid));
+			continue;
+		}
+
+		/* Get an inode by ino with checking validity */
+		if (check_dnode(sbi, entry, &dni, start_addr + off, &nofs) == 0)
+			continue;
+
+		if (phase == 1) {
+			ra_node_page(sbi, dni.ino);
+			continue;
+		}
+
+		start_bidx = start_bidx_of_node(nofs);
+		ofs_in_node = le16_to_cpu(entry->ofs_in_node);
+
+		if (phase == 2) {
+			inode = f2fs_iget(sb, dni.ino);
+			if (IS_ERR(inode))
+				continue;
+
+			data_page = find_data_page(inode,
+					start_bidx + ofs_in_node, false);
+			if (IS_ERR(data_page))
+				goto next_iput;
+
+			f2fs_put_page(data_page, 0);
+			add_gc_inode(inode, ilist);
+		} else {
+			inode = find_gc_inode(dni.ino, ilist);
+			if (inode) {
+				data_page = get_lock_data_page(inode,
+						start_bidx + ofs_in_node);
+				if (IS_ERR(data_page))
+					continue;
+				move_data_page(inode, data_page, gc_type);
+				stat_inc_data_blk_count(sbi, 1);
+			}
+		}
+		continue;
+next_iput:
+		iput(inode);
+	}
+
+	if (++phase < 4)
+		goto next_step;
+
+	if (gc_type == FG_GC) {
+		f2fs_submit_bio(sbi, DATA, true);
+
+		/*
+		 * In the case of FG_GC, it'd be better to reclaim this victim
+		 * completely.
+		 */
+		if (get_valid_blocks(sbi, segno, 1) != 0) {
+			phase = 2;
+			goto next_step;
+		}
+	}
+}
+
+static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
+						int gc_type, int type)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	int ret;
+	mutex_lock(&sit_i->sentry_lock);
+	ret = DIRTY_I(sbi)->v_ops->get_victim(sbi, victim, gc_type, type, LFS);
+	mutex_unlock(&sit_i->sentry_lock);
+	return ret;
+}
+
+static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
+				struct list_head *ilist, int gc_type)
+{
+	struct page *sum_page;
+	struct f2fs_summary_block *sum;
+	struct blk_plug plug;
+
+	/* read segment summary of victim */
+	sum_page = get_sum_page(sbi, segno);
+	if (IS_ERR(sum_page))
+		return;
+
+	blk_start_plug(&plug);
+
+	sum = page_address(sum_page);
+
+	switch (GET_SUM_TYPE((&sum->footer))) {
+	case SUM_TYPE_NODE:
+		gc_node_segment(sbi, sum->entries, segno, gc_type);
+		break;
+	case SUM_TYPE_DATA:
+		gc_data_segment(sbi, sum->entries, ilist, segno, gc_type);
+		break;
+	}
+	blk_finish_plug(&plug);
+
+	stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)));
+	stat_inc_call_count(sbi->stat_info);
+
+	f2fs_put_page(sum_page, 1);
+}
+
+int f2fs_gc(struct f2fs_sb_info *sbi)
+{
+	struct list_head ilist;
+	unsigned int segno, i;
+	int gc_type = BG_GC;
+	int nfree = 0;
+	int ret = -1;
+
+	INIT_LIST_HEAD(&ilist);
+gc_more:
+	if (!(sbi->sb->s_flags & MS_ACTIVE))
+		goto stop;
+
+	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree)) {
+		gc_type = FG_GC;
+		write_checkpoint(sbi, false);
+	}
+
+	if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
+		goto stop;
+	ret = 0;
+
+	for (i = 0; i < sbi->segs_per_sec; i++)
+		do_garbage_collect(sbi, segno + i, &ilist, gc_type);
+
+	if (gc_type == FG_GC) {
+		sbi->cur_victim_sec = NULL_SEGNO;
+		nfree++;
+		WARN_ON(get_valid_blocks(sbi, segno, sbi->segs_per_sec));
+	}
+
+	if (has_not_enough_free_secs(sbi, nfree))
+		goto gc_more;
+
+	if (gc_type == FG_GC)
+		write_checkpoint(sbi, false);
+stop:
+	mutex_unlock(&sbi->gc_mutex);
+
+	put_gc_inode(&ilist);
+	return ret;
+}
+
+void build_gc_manager(struct f2fs_sb_info *sbi)
+{
+	DIRTY_I(sbi)->v_ops = &default_v_ops;
+}
+
+int __init create_gc_caches(void)
+{
+	winode_slab = f2fs_kmem_cache_create("f2fs_gc_inodes",
+			sizeof(struct inode_entry), NULL);
+	if (!winode_slab)
+		return -ENOMEM;
+	return 0;
+}
+
+void destroy_gc_caches(void)
+{
+	kmem_cache_destroy(winode_slab);
+}

fs/f2fs/gc.h

@@ -0,0 +1,102 @@
+/*
+ * fs/f2fs/gc.h
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#define GC_THREAD_MIN_WB_PAGES		1	/*
+						 * a threshold to determine
+						 * whether IO subsystem is idle
+						 * or not
+						 */
+#define GC_THREAD_MIN_SLEEP_TIME	30000	/* milliseconds */
+#define GC_THREAD_MAX_SLEEP_TIME	60000
+#define GC_THREAD_NOGC_SLEEP_TIME	300000	/* wait 5 min */
+#define LIMIT_INVALID_BLOCK	40 /* percentage over total user space */
+#define LIMIT_FREE_BLOCK	40 /* percentage over invalid + free space */
+
+/* Search max. number of dirty segments to select a victim segment */
+#define MAX_VICTIM_SEARCH	20
+
+struct f2fs_gc_kthread {
+	struct task_struct *f2fs_gc_task;
+	wait_queue_head_t gc_wait_queue_head;
+};
+
+struct inode_entry {
+	struct list_head list;
+	struct inode *inode;
+};
+
+/*
+ * inline functions
+ */
+static inline block_t free_user_blocks(struct f2fs_sb_info *sbi)
+{
+	if (free_segments(sbi) < overprovision_segments(sbi))
+		return 0;
+	else
+		return (free_segments(sbi) - overprovision_segments(sbi))
+			<< sbi->log_blocks_per_seg;
+}
+
+static inline block_t limit_invalid_user_blocks(struct f2fs_sb_info *sbi)
+{
+	return (long)(sbi->user_block_count * LIMIT_INVALID_BLOCK) / 100;
+}
+
+static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi)
+{
+	block_t reclaimable_user_blocks = sbi->user_block_count -
+		written_block_count(sbi);
+	return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100;
+}
+
+static inline long increase_sleep_time(long wait)
+{
+	if (wait == GC_THREAD_NOGC_SLEEP_TIME)
+		return wait;
+
+	wait += GC_THREAD_MIN_SLEEP_TIME;
+	if (wait > GC_THREAD_MAX_SLEEP_TIME)
+		wait = GC_THREAD_MAX_SLEEP_TIME;
+	return wait;
+}
+
+static inline long decrease_sleep_time(long wait)
+{
+	if (wait == GC_THREAD_NOGC_SLEEP_TIME)
+		wait = GC_THREAD_MAX_SLEEP_TIME;
+
+	wait -= GC_THREAD_MIN_SLEEP_TIME;
+	if (wait <= GC_THREAD_MIN_SLEEP_TIME)
+		wait = GC_THREAD_MIN_SLEEP_TIME;
+	return wait;
+}
+
+static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
+{
+	block_t invalid_user_blocks = sbi->user_block_count -
+					written_block_count(sbi);
+	/*
+	 * Background GC is triggered with the following condition.
+	 * 1. There are a number of invalid blocks.
+	 * 2. There is not enough free space.
+	 */
+	if (invalid_user_blocks > limit_invalid_user_blocks(sbi) &&
+			free_user_blocks(sbi) < limit_free_user_blocks(sbi))
+		return true;
+	return false;
+}
+
+static inline int is_idle(struct f2fs_sb_info *sbi)
+{
+	struct block_device *bdev = sbi->sb->s_bdev;
+	struct request_queue *q = bdev_get_queue(bdev);
+	struct request_list *rl = &q->root_rl;
+	return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]);
+}

fs/f2fs/hash.c

@@ -0,0 +1,101 @@
+/*
+ * 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
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/cryptohash.h>
+#include <linux/pagemap.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 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;
+}
+
+f2fs_hash_t f2fs_dentry_hash(const char *name, size_t len)
+{
+	__u32 hash;
+	f2fs_hash_t f2fs_hash;
+	const char *p;
+	__u32 in[8], buf[4];
+
+	if ((len <= 2) && (name[0] == '.') &&
+		(name[1] == '.' || name[1] == '\0'))
+		return 0;
+
+	/* Initialize the default seed for the hash checksum functions */
+	buf[0] = 0x67452301;
+	buf[1] = 0xefcdab89;
+	buf[2] = 0x98badcfe;
+	buf[3] = 0x10325476;
+
+	p = name;
+	while (1) {
+		str2hashbuf(p, len, in, 4);
+		TEA_transform(buf, in);
+		p += 16;
+		if (len <= 16)
+			break;
+		len -= 16;
+	}
+	hash = buf[0];
+	f2fs_hash = cpu_to_le32(hash & ~F2FS_HASH_COL_BIT);
+	return f2fs_hash;
+}

fs/f2fs/inode.c

@@ -0,0 +1,275 @@
+/*
+ * fs/f2fs/inode.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/buffer_head.h>
+#include <linux/writeback.h>
+
+#include "f2fs.h"
+#include "node.h"
+
+#include <trace/events/f2fs.h>
+
+void f2fs_set_inode_flags(struct inode *inode)
+{
+	unsigned int flags = F2FS_I(inode)->i_flags;
+
+	inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE |
+			S_NOATIME | S_DIRSYNC);
+
+	if (flags & FS_SYNC_FL)
+		inode->i_flags |= S_SYNC;
+	if (flags & FS_APPEND_FL)
+		inode->i_flags |= S_APPEND;
+	if (flags & FS_IMMUTABLE_FL)
+		inode->i_flags |= S_IMMUTABLE;
+	if (flags & FS_NOATIME_FL)
+		inode->i_flags |= S_NOATIME;
+	if (flags & FS_DIRSYNC_FL)
+		inode->i_flags |= S_DIRSYNC;
+}
+
+static int do_read_inode(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct page *node_page;
+	struct f2fs_node *rn;
+	struct f2fs_inode *ri;
+
+	/* Check if ino is within scope */
+	if (check_nid_range(sbi, inode->i_ino)) {
+		f2fs_msg(inode->i_sb, KERN_ERR, "bad inode number: %lu",
+			 (unsigned long) inode->i_ino);
+		return -EINVAL;
+	}
+
+	node_page = get_node_page(sbi, inode->i_ino);
+	if (IS_ERR(node_page))
+		return PTR_ERR(node_page);
+
+	rn = page_address(node_page);
+	ri = &(rn->i);
+
+	inode->i_mode = le16_to_cpu(ri->i_mode);
+	i_uid_write(inode, le32_to_cpu(ri->i_uid));
+	i_gid_write(inode, le32_to_cpu(ri->i_gid));
+	set_nlink(inode, le32_to_cpu(ri->i_links));
+	inode->i_size = le64_to_cpu(ri->i_size);
+	inode->i_blocks = le64_to_cpu(ri->i_blocks);
+
+	inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime);
+	inode->i_ctime.tv_sec = le64_to_cpu(ri->i_ctime);
+	inode->i_mtime.tv_sec = le64_to_cpu(ri->i_mtime);
+	inode->i_atime.tv_nsec = le32_to_cpu(ri->i_atime_nsec);
+	inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
+	inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
+	inode->i_generation = le32_to_cpu(ri->i_generation);
+	if (ri->i_addr[0])
+		inode->i_rdev = old_decode_dev(le32_to_cpu(ri->i_addr[0]));
+	else
+		inode->i_rdev = new_decode_dev(le32_to_cpu(ri->i_addr[1]));
+
+	fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
+	fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
+	fi->i_flags = le32_to_cpu(ri->i_flags);
+	fi->flags = 0;
+	fi->i_advise = ri->i_advise;
+	fi->i_pino = le32_to_cpu(ri->i_pino);
+	get_extent_info(&fi->ext, ri->i_ext);
+	f2fs_put_page(node_page, 1);
+	return 0;
+}
+
+struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	struct inode *inode;
+	int ret = 0;
+
+	inode = iget_locked(sb, ino);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	if (!(inode->i_state & I_NEW)) {
+		trace_f2fs_iget(inode);
+		return inode;
+	}
+	if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi))
+		goto make_now;
+
+	ret = do_read_inode(inode);
+	if (ret)
+		goto bad_inode;
+
+	if (!sbi->por_doing && inode->i_nlink == 0) {
+		ret = -ENOENT;
+		goto bad_inode;
+	}
+
+make_now:
+	if (ino == F2FS_NODE_INO(sbi)) {
+		inode->i_mapping->a_ops = &f2fs_node_aops;
+		mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
+	} else if (ino == F2FS_META_INO(sbi)) {
+		inode->i_mapping->a_ops = &f2fs_meta_aops;
+		mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
+	} else if (S_ISREG(inode->i_mode)) {
+		inode->i_op = &f2fs_file_inode_operations;
+		inode->i_fop = &f2fs_file_operations;
+		inode->i_mapping->a_ops = &f2fs_dblock_aops;
+	} else if (S_ISDIR(inode->i_mode)) {
+		inode->i_op = &f2fs_dir_inode_operations;
+		inode->i_fop = &f2fs_dir_operations;
+		inode->i_mapping->a_ops = &f2fs_dblock_aops;
+		mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER_MOVABLE |
+				__GFP_ZERO);
+	} else if (S_ISLNK(inode->i_mode)) {
+		inode->i_op = &f2fs_symlink_inode_operations;
+		inode->i_mapping->a_ops = &f2fs_dblock_aops;
+	} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
+			S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
+		inode->i_op = &f2fs_special_inode_operations;
+		init_special_inode(inode, inode->i_mode, inode->i_rdev);
+	} else {
+		ret = -EIO;
+		goto bad_inode;
+	}
+	unlock_new_inode(inode);
+	trace_f2fs_iget(inode);
+	return inode;
+
+bad_inode:
+	iget_failed(inode);
+	trace_f2fs_iget_exit(inode, ret);
+	return ERR_PTR(ret);
+}
+
+void update_inode(struct inode *inode, struct page *node_page)
+{
+	struct f2fs_node *rn;
+	struct f2fs_inode *ri;
+
+	wait_on_page_writeback(node_page);
+
+	rn = page_address(node_page);
+	ri = &(rn->i);
+
+	ri->i_mode = cpu_to_le16(inode->i_mode);
+	ri->i_advise = F2FS_I(inode)->i_advise;
+	ri->i_uid = cpu_to_le32(i_uid_read(inode));
+	ri->i_gid = cpu_to_le32(i_gid_read(inode));
+	ri->i_links = cpu_to_le32(inode->i_nlink);
+	ri->i_size = cpu_to_le64(i_size_read(inode));
+	ri->i_blocks = cpu_to_le64(inode->i_blocks);
+	set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext);
+
+	ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
+	ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
+	ri->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
+	ri->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
+	ri->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
+	ri->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+	ri->i_current_depth = cpu_to_le32(F2FS_I(inode)->i_current_depth);
+	ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid);
+	ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
+	ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
+	ri->i_generation = cpu_to_le32(inode->i_generation);
+
+	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
+		if (old_valid_dev(inode->i_rdev)) {
+			ri->i_addr[0] =
+				cpu_to_le32(old_encode_dev(inode->i_rdev));
+			ri->i_addr[1] = 0;
+		} else {
+			ri->i_addr[0] = 0;
+			ri->i_addr[1] =
+				cpu_to_le32(new_encode_dev(inode->i_rdev));
+			ri->i_addr[2] = 0;
+		}
+	}
+
+	set_cold_node(inode, node_page);
+	set_page_dirty(node_page);
+}
+
+int update_inode_page(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct page *node_page;
+
+	node_page = get_node_page(sbi, inode->i_ino);
+	if (IS_ERR(node_page))
+		return PTR_ERR(node_page);
+
+	update_inode(inode, node_page);
+	f2fs_put_page(node_page, 1);
+	return 0;
+}
+
+int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	int ret, ilock;
+
+	if (inode->i_ino == F2FS_NODE_INO(sbi) ||
+			inode->i_ino == F2FS_META_INO(sbi))
+		return 0;
+
+	if (wbc)
+		f2fs_balance_fs(sbi);
+
+	/*
+	 * We need to lock here to prevent from producing dirty node pages
+	 * during the urgent cleaning time when runing out of free sections.
+	 */
+	ilock = mutex_lock_op(sbi);
+	ret = update_inode_page(inode);
+	mutex_unlock_op(sbi, ilock);
+	return ret;
+}
+
+/*
+ * Called at the last iput() if i_nlink is zero
+ */
+void f2fs_evict_inode(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	int ilock;
+
+	trace_f2fs_evict_inode(inode);
+	truncate_inode_pages(&inode->i_data, 0);
+
+	if (inode->i_ino == F2FS_NODE_INO(sbi) ||
+			inode->i_ino == F2FS_META_INO(sbi))
+		goto no_delete;
+
+	BUG_ON(atomic_read(&F2FS_I(inode)->dirty_dents));
+	remove_dirty_dir_inode(inode);
+
+	if (inode->i_nlink || is_bad_inode(inode))
+		goto no_delete;
+
+	sb_start_intwrite(inode->i_sb);
+	set_inode_flag(F2FS_I(inode), FI_NO_ALLOC);
+	i_size_write(inode, 0);
+
+	if (F2FS_HAS_BLOCKS(inode))
+		f2fs_truncate(inode);
+
+	ilock = mutex_lock_op(sbi);
+	remove_inode_page(inode);
+	mutex_unlock_op(sbi, ilock);
+
+	sb_end_intwrite(inode->i_sb);
+no_delete:
+	clear_inode(inode);
+}

fs/f2fs/namei.c

@@ -0,0 +1,533 @@
+/*
+ * fs/f2fs/namei.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/pagemap.h>
+#include <linux/sched.h>
+#include <linux/ctype.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include "xattr.h"
+#include "acl.h"
+#include <trace/events/f2fs.h>
+
+static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
+{
+	struct super_block *sb = dir->i_sb;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	nid_t ino;
+	struct inode *inode;
+	bool nid_free = false;
+	int err, ilock;
+
+	inode = new_inode(sb);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	ilock = mutex_lock_op(sbi);
+	if (!alloc_nid(sbi, &ino)) {
+		mutex_unlock_op(sbi, ilock);
+		err = -ENOSPC;
+		goto fail;
+	}
+	mutex_unlock_op(sbi, ilock);
+
+	inode->i_uid = current_fsuid();
+
+	if (dir->i_mode & S_ISGID) {
+		inode->i_gid = dir->i_gid;
+		if (S_ISDIR(mode))
+			mode |= S_ISGID;
+	} else {
+		inode->i_gid = current_fsgid();
+	}
+
+	inode->i_ino = ino;
+	inode->i_mode = mode;
+	inode->i_blocks = 0;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+	inode->i_generation = sbi->s_next_generation++;
+
+	err = insert_inode_locked(inode);
+	if (err) {
+		err = -EINVAL;
+		nid_free = true;
+		goto out;
+	}
+	trace_f2fs_new_inode(inode, 0);
+	mark_inode_dirty(inode);
+	return inode;
+
+out:
+	clear_nlink(inode);
+	unlock_new_inode(inode);
+fail:
+	trace_f2fs_new_inode(inode, err);
+	make_bad_inode(inode);
+	iput(inode);
+	if (nid_free)
+		alloc_nid_failed(sbi, ino);
+	return ERR_PTR(err);
+}
+
+static int is_multimedia_file(const unsigned char *s, const char *sub)
+{
+	size_t slen = strlen(s);
+	size_t sublen = strlen(sub);
+	int ret;
+
+	if (sublen > slen)
+		return 0;
+
+	ret = memcmp(s + slen - sublen, sub, sublen);
+	if (ret) {	/* compare upper case */
+		int i;
+		char upper_sub[8];
+		for (i = 0; i < sublen && i < sizeof(upper_sub); i++)
+			upper_sub[i] = toupper(sub[i]);
+		return !memcmp(s + slen - sublen, upper_sub, sublen);
+	}
+
+	return !ret;
+}
+
+/*
+ * Set multimedia files as cold files for hot/cold data separation
+ */
+static inline void set_cold_files(struct f2fs_sb_info *sbi, struct inode *inode,
+		const unsigned char *name)
+{
+	int i;
+	__u8 (*extlist)[8] = sbi->raw_super->extension_list;
+
+	int count = le32_to_cpu(sbi->raw_super->extension_count);
+	for (i = 0; i < count; i++) {
+		if (is_multimedia_file(name, extlist[i])) {
+			set_cold_file(inode);
+			break;
+		}
+	}
+}
+
+static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
+						bool excl)
+{
+	struct super_block *sb = dir->i_sb;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	struct inode *inode;
+	nid_t ino = 0;
+	int err, ilock;
+
+	f2fs_balance_fs(sbi);
+
+	inode = f2fs_new_inode(dir, mode);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	if (!test_opt(sbi, DISABLE_EXT_IDENTIFY))
+		set_cold_files(sbi, inode, dentry->d_name.name);
+
+	inode->i_op = &f2fs_file_inode_operations;
+	inode->i_fop = &f2fs_file_operations;
+	inode->i_mapping->a_ops = &f2fs_dblock_aops;
+	ino = inode->i_ino;
+
+	ilock = mutex_lock_op(sbi);
+	err = f2fs_add_link(dentry, inode);
+	mutex_unlock_op(sbi, ilock);
+	if (err)
+		goto out;
+
+	alloc_nid_done(sbi, ino);
+
+	if (!sbi->por_doing)
+		d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
+	return 0;
+out:
+	clear_nlink(inode);
+	unlock_new_inode(inode);
+	make_bad_inode(inode);
+	iput(inode);
+	alloc_nid_failed(sbi, ino);
+	return err;
+}
+
+static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
+		struct dentry *dentry)
+{
+	struct inode *inode = old_dentry->d_inode;
+	struct super_block *sb = dir->i_sb;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	int err, ilock;
+
+	f2fs_balance_fs(sbi);
+
+	inode->i_ctime = CURRENT_TIME;
+	atomic_inc(&inode->i_count);
+
+	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	ilock = mutex_lock_op(sbi);
+	err = f2fs_add_link(dentry, inode);
+	mutex_unlock_op(sbi, ilock);
+	if (err)
+		goto out;
+
+	/*
+	 * This file should be checkpointed during fsync.
+	 * We lost i_pino from now on.
+	 */
+	set_cp_file(inode);
+
+	d_instantiate(dentry, inode);
+	return 0;
+out:
+	clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	make_bad_inode(inode);
+	iput(inode);
+	return err;
+}
+
+struct dentry *f2fs_get_parent(struct dentry *child)
+{
+	struct qstr dotdot = QSTR_INIT("..", 2);
+	unsigned long ino = f2fs_inode_by_name(child->d_inode, &dotdot);
+	if (!ino)
+		return ERR_PTR(-ENOENT);
+	return d_obtain_alias(f2fs_iget(child->d_inode->i_sb, ino));
+}
+
+static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
+		unsigned int flags)
+{
+	struct inode *inode = NULL;
+	struct f2fs_dir_entry *de;
+	struct page *page;
+
+	if (dentry->d_name.len > F2FS_NAME_LEN)
+		return ERR_PTR(-ENAMETOOLONG);
+
+	de = f2fs_find_entry(dir, &dentry->d_name, &page);
+	if (de) {
+		nid_t ino = le32_to_cpu(de->ino);
+		kunmap(page);
+		f2fs_put_page(page, 0);
+
+		inode = f2fs_iget(dir->i_sb, ino);
+		if (IS_ERR(inode))
+			return ERR_CAST(inode);
+	}
+
+	return d_splice_alias(inode, dentry);
+}
+
+static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
+{
+	struct super_block *sb = dir->i_sb;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	struct inode *inode = dentry->d_inode;
+	struct f2fs_dir_entry *de;
+	struct page *page;
+	int err = -ENOENT;
+	int ilock;
+
+	trace_f2fs_unlink_enter(dir, dentry);
+	f2fs_balance_fs(sbi);
+
+	de = f2fs_find_entry(dir, &dentry->d_name, &page);
+	if (!de)
+		goto fail;
+
+	err = check_orphan_space(sbi);
+	if (err) {
+		kunmap(page);
+		f2fs_put_page(page, 0);
+		goto fail;
+	}
+
+	ilock = mutex_lock_op(sbi);
+	f2fs_delete_entry(de, page, inode);
+	mutex_unlock_op(sbi, ilock);
+
+	/* In order to evict this inode,  we set it dirty */
+	mark_inode_dirty(inode);
+fail:
+	trace_f2fs_unlink_exit(inode, err);
+	return err;
+}
+
+static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
+					const char *symname)
+{
+	struct super_block *sb = dir->i_sb;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	struct inode *inode;
+	size_t symlen = strlen(symname) + 1;
+	int err, ilock;
+
+	f2fs_balance_fs(sbi);
+
+	inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	inode->i_op = &f2fs_symlink_inode_operations;
+	inode->i_mapping->a_ops = &f2fs_dblock_aops;
+
+	ilock = mutex_lock_op(sbi);
+	err = f2fs_add_link(dentry, inode);
+	mutex_unlock_op(sbi, ilock);
+	if (err)
+		goto out;
+
+	err = page_symlink(inode, symname, symlen);
+	alloc_nid_done(sbi, inode->i_ino);
+
+	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
+	return err;
+out:
+	clear_nlink(inode);
+	unlock_new_inode(inode);
+	make_bad_inode(inode);
+	iput(inode);
+	alloc_nid_failed(sbi, inode->i_ino);
+	return err;
+}
+
+static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+	struct inode *inode;
+	int err, ilock;
+
+	f2fs_balance_fs(sbi);
+
+	inode = f2fs_new_inode(dir, S_IFDIR | mode);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	inode->i_op = &f2fs_dir_inode_operations;
+	inode->i_fop = &f2fs_dir_operations;
+	inode->i_mapping->a_ops = &f2fs_dblock_aops;
+	mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
+
+	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	ilock = mutex_lock_op(sbi);
+	err = f2fs_add_link(dentry, inode);
+	mutex_unlock_op(sbi, ilock);
+	if (err)
+		goto out_fail;
+
+	alloc_nid_done(sbi, inode->i_ino);
+
+	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
+
+	return 0;
+
+out_fail:
+	clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	clear_nlink(inode);
+	unlock_new_inode(inode);
+	make_bad_inode(inode);
+	iput(inode);
+	alloc_nid_failed(sbi, inode->i_ino);
+	return err;
+}
+
+static int f2fs_rmdir(struct inode *dir, struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	if (f2fs_empty_dir(inode))
+		return f2fs_unlink(dir, dentry);
+	return -ENOTEMPTY;
+}
+
+static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
+				umode_t mode, dev_t rdev)
+{
+	struct super_block *sb = dir->i_sb;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	struct inode *inode;
+	int err = 0;
+	int ilock;
+
+	if (!new_valid_dev(rdev))
+		return -EINVAL;
+
+	f2fs_balance_fs(sbi);
+
+	inode = f2fs_new_inode(dir, mode);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	init_special_inode(inode, inode->i_mode, rdev);
+	inode->i_op = &f2fs_special_inode_operations;
+
+	ilock = mutex_lock_op(sbi);
+	err = f2fs_add_link(dentry, inode);
+	mutex_unlock_op(sbi, ilock);
+	if (err)
+		goto out;
+
+	alloc_nid_done(sbi, inode->i_ino);
+	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
+	return 0;
+out:
+	clear_nlink(inode);
+	unlock_new_inode(inode);
+	make_bad_inode(inode);
+	iput(inode);
+	alloc_nid_failed(sbi, inode->i_ino);
+	return err;
+}
+
+static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
+			struct inode *new_dir, struct dentry *new_dentry)
+{
+	struct super_block *sb = old_dir->i_sb;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	struct inode *old_inode = old_dentry->d_inode;
+	struct inode *new_inode = new_dentry->d_inode;
+	struct page *old_dir_page;
+	struct page *old_page;
+	struct f2fs_dir_entry *old_dir_entry = NULL;
+	struct f2fs_dir_entry *old_entry;
+	struct f2fs_dir_entry *new_entry;
+	int err = -ENOENT, ilock = -1;
+
+	f2fs_balance_fs(sbi);
+
+	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
+	if (!old_entry)
+		goto out;
+
+	if (S_ISDIR(old_inode->i_mode)) {
+		err = -EIO;
+		old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_page);
+		if (!old_dir_entry)
+			goto out_old;
+	}
+
+	ilock = mutex_lock_op(sbi);
+
+	if (new_inode) {
+		struct page *new_page;
+
+		err = -ENOTEMPTY;
+		if (old_dir_entry && !f2fs_empty_dir(new_inode))
+			goto out_dir;
+
+		err = -ENOENT;
+		new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
+						&new_page);
+		if (!new_entry)
+			goto out_dir;
+
+		f2fs_set_link(new_dir, new_entry, new_page, old_inode);
+
+		new_inode->i_ctime = CURRENT_TIME;
+		if (old_dir_entry)
+			drop_nlink(new_inode);
+		drop_nlink(new_inode);
+		if (!new_inode->i_nlink)
+			add_orphan_inode(sbi, new_inode->i_ino);
+		update_inode_page(new_inode);
+	} else {
+		err = f2fs_add_link(new_dentry, old_inode);
+		if (err)
+			goto out_dir;
+
+		if (old_dir_entry) {
+			inc_nlink(new_dir);
+			update_inode_page(new_dir);
+		}
+	}
+
+	old_inode->i_ctime = CURRENT_TIME;
+	mark_inode_dirty(old_inode);
+
+	f2fs_delete_entry(old_entry, old_page, NULL);
+
+	if (old_dir_entry) {
+		if (old_dir != new_dir) {
+			f2fs_set_link(old_inode, old_dir_entry,
+						old_dir_page, new_dir);
+		} else {
+			kunmap(old_dir_page);
+			f2fs_put_page(old_dir_page, 0);
+		}
+		drop_nlink(old_dir);
+		update_inode_page(old_dir);
+	}
+
+	mutex_unlock_op(sbi, ilock);
+	return 0;
+
+out_dir:
+	if (old_dir_entry) {
+		kunmap(old_dir_page);
+		f2fs_put_page(old_dir_page, 0);
+	}
+	mutex_unlock_op(sbi, ilock);
+out_old:
+	kunmap(old_page);
+	f2fs_put_page(old_page, 0);
+out:
+	return err;
+}
+
+const struct inode_operations f2fs_dir_inode_operations = {
+	.create		= f2fs_create,
+	.lookup		= f2fs_lookup,
+	.link		= f2fs_link,
+	.unlink		= f2fs_unlink,
+	.symlink	= f2fs_symlink,
+	.mkdir		= f2fs_mkdir,
+	.rmdir		= f2fs_rmdir,
+	.mknod		= f2fs_mknod,
+	.rename		= f2fs_rename,
+	.setattr	= f2fs_setattr,
+	.get_acl	= f2fs_get_acl,
+#ifdef CONFIG_F2FS_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= f2fs_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+};
+
+const struct inode_operations f2fs_symlink_inode_operations = {
+	.readlink       = generic_readlink,
+	.follow_link    = page_follow_link_light,
+	.put_link       = page_put_link,
+	.setattr	= f2fs_setattr,
+#ifdef CONFIG_F2FS_FS_XATTR
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.listxattr	= f2fs_listxattr,
+	.removexattr	= generic_removexattr,
+#endif
+};
+
+const struct inode_operations f2fs_special_inode_operations = {
+	.setattr        = f2fs_setattr,
+	.get_acl	= f2fs_get_acl,
+#ifdef CONFIG_F2FS_FS_XATTR
+	.setxattr       = generic_setxattr,
+	.getxattr       = generic_getxattr,
+	.listxattr	= f2fs_listxattr,
+	.removexattr    = generic_removexattr,
+#endif
+};

fs/f2fs/node.h

@@ -0,0 +1,371 @@
+/*
+ * fs/f2fs/node.h
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+/* 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 readahead before building free nids */
+#define FREE_NID_PAGES 4
+
+/* maximum # of free node ids to produce during build_free_nids */
+#define MAX_FREE_NIDS (NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES)
+
+/* maximum readahead size for node during getting data blocks */
+#define MAX_RA_NODE		128
+
+/* maximum cached nat entries to manage memory footprint */
+#define NM_WOUT_THRESHOLD	(64 * NAT_ENTRY_PER_BLOCK)
+
+/* vector size for gang look-up from nat cache that consists of radix tree */
+#define NATVEC_SIZE	64
+
+/* return value for read_node_page */
+#define LOCKED_PAGE	1
+
+/*
+ * 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 */
+};
+
+struct nat_entry {
+	struct list_head list;	/* for clean or dirty nat list */
+	bool checkpointed;	/* whether it is checkpointed or not */
+	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 __set_nat_cache_dirty(nm_i, ne)					\
+	list_move_tail(&ne->list, &nm_i->dirty_nat_entries);
+#define __clear_nat_cache_dirty(nm_i, ne)				\
+	list_move_tail(&ne->list, &nm_i->nat_entries);
+#define inc_node_version(version)	(++version)
+
+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;
+}
+
+/*
+ * For free nid mangement
+ */
+enum nid_state {
+	NID_NEW,	/* newly added to free nid list */
+	NID_ALLOC	/* it is allocated */
+};
+
+struct free_nid {
+	struct list_head list;	/* for free node id list */
+	nid_t nid;		/* node id */
+	int state;		/* in use or not: NID_NEW or NID_ALLOC */
+};
+
+static inline int next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	struct free_nid *fnid;
+
+	if (nm_i->fcnt <= 0)
+		return -1;
+	spin_lock(&nm_i->free_nid_list_lock);
+	fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list);
+	*nid = fnid->nid;
+	spin_unlock(&nm_i->free_nid_list_lock);
+	return 0;
+}
+
+/*
+ * inline functions
+ */
+static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	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;
+	int seg_off;
+
+	block_off = NAT_BLOCK_OFFSET(start);
+	seg_off = block_off >> sbi->log_blocks_per_seg;
+
+	block_addr = (pgoff_t)(nm_i->nat_blkaddr +
+		(seg_off << sbi->log_blocks_per_seg << 1) +
+		(block_off & ((1 << sbi->log_blocks_per_seg) - 1)));
+
+	if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
+		block_addr += sbi->blocks_per_seg;
+
+	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;
+	if ((block_addr >> sbi->log_blocks_per_seg) % 2)
+		block_addr -= sbi->blocks_per_seg;
+	else
+		block_addr += sbi->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);
+
+	if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
+		f2fs_clear_bit(block_off, nm_i->nat_bitmap);
+	else
+		f2fs_set_bit(block_off, nm_i->nat_bitmap);
+}
+
+static inline void fill_node_footer(struct page *page, nid_t nid,
+				nid_t ino, unsigned int ofs, bool reset)
+{
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	if (reset)
+		memset(rn, 0, sizeof(*rn));
+	rn->footer.nid = cpu_to_le32(nid);
+	rn->footer.ino = cpu_to_le32(ino);
+	rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT);
+}
+
+static inline void copy_node_footer(struct page *dst, struct page *src)
+{
+	void *src_addr = page_address(src);
+	void *dst_addr = page_address(dst);
+	struct f2fs_node *src_rn = (struct f2fs_node *)src_addr;
+	struct f2fs_node *dst_rn = (struct f2fs_node *)dst_addr;
+	memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer));
+}
+
+static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	rn->footer.cp_ver = ckpt->checkpoint_ver;
+	rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
+}
+
+static inline nid_t ino_of_node(struct page *node_page)
+{
+	void *kaddr = page_address(node_page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	return le32_to_cpu(rn->footer.ino);
+}
+
+static inline nid_t nid_of_node(struct page *node_page)
+{
+	void *kaddr = page_address(node_page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	return le32_to_cpu(rn->footer.nid);
+}
+
+static inline unsigned int ofs_of_node(struct page *node_page)
+{
+	void *kaddr = page_address(node_page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	unsigned flag = le32_to_cpu(rn->footer.flag);
+	return flag >> OFFSET_BIT_SHIFT;
+}
+
+static inline unsigned long long cpver_of_node(struct page *node_page)
+{
+	void *kaddr = page_address(node_page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	return le64_to_cpu(rn->footer.cp_ver);
+}
+
+static inline block_t next_blkaddr_of_node(struct page *node_page)
+{
+	void *kaddr = page_address(node_page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	return le32_to_cpu(rn->footer.next_blkaddr);
+}
+
+/*
+ * 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 (x(N + 1))
+ */
+static inline bool IS_DNODE(struct page *node_page)
+{
+	unsigned int ofs = ofs_of_node(node_page);
+	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 void set_nid(struct page *p, int off, nid_t nid, bool i)
+{
+	struct f2fs_node *rn = (struct f2fs_node *)page_address(p);
+
+	wait_on_page_writeback(p);
+
+	if (i)
+		rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
+	else
+		rn->in.nid[off] = cpu_to_le32(nid);
+	set_page_dirty(p);
+}
+
+static inline nid_t get_nid(struct page *p, int off, bool i)
+{
+	struct f2fs_node *rn = (struct f2fs_node *)page_address(p);
+	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_cold_file(struct inode *inode)
+{
+	return F2FS_I(inode)->i_advise & FADVISE_COLD_BIT;
+}
+
+static inline void set_cold_file(struct inode *inode)
+{
+	F2FS_I(inode)->i_advise |= FADVISE_COLD_BIT;
+}
+
+static inline int is_cp_file(struct inode *inode)
+{
+	return F2FS_I(inode)->i_advise & FADVISE_CP_BIT;
+}
+
+static inline void set_cp_file(struct inode *inode)
+{
+	F2FS_I(inode)->i_advise |= FADVISE_CP_BIT;
+}
+
+static inline int is_cold_data(struct page *page)
+{
+	return PageChecked(page);
+}
+
+static inline void set_cold_data(struct page *page)
+{
+	SetPageChecked(page);
+}
+
+static inline void clear_cold_data(struct page *page)
+{
+	ClearPageChecked(page);
+}
+
+static inline int is_cold_node(struct page *page)
+{
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+	return flag & (0x1 << COLD_BIT_SHIFT);
+}
+
+static inline unsigned char is_fsync_dnode(struct page *page)
+{
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+	return flag & (0x1 << FSYNC_BIT_SHIFT);
+}
+
+static inline unsigned char is_dent_dnode(struct page *page)
+{
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+	return flag & (0x1 << DENT_BIT_SHIFT);
+}
+
+static inline void set_cold_node(struct inode *inode, struct page *page)
+{
+	struct f2fs_node *rn = (struct f2fs_node *)page_address(page);
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+
+	if (S_ISDIR(inode->i_mode))
+		flag &= ~(0x1 << COLD_BIT_SHIFT);
+	else
+		flag |= (0x1 << COLD_BIT_SHIFT);
+	rn->footer.flag = cpu_to_le32(flag);
+}
+
+static inline void set_fsync_mark(struct page *page, int mark)
+{
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+	if (mark)
+		flag |= (0x1 << FSYNC_BIT_SHIFT);
+	else
+		flag &= ~(0x1 << FSYNC_BIT_SHIFT);
+	rn->footer.flag = cpu_to_le32(flag);
+}
+
+static inline void set_dentry_mark(struct page *page, int mark)
+{
+	void *kaddr = page_address(page);
+	struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+	unsigned int flag = le32_to_cpu(rn->footer.flag);
+	if (mark)
+		flag |= (0x1 << DENT_BIT_SHIFT);
+	else
+		flag &= ~(0x1 << DENT_BIT_SHIFT);
+	rn->footer.flag = cpu_to_le32(flag);
+}

fs/f2fs/recovery.c

@@ -0,0 +1,402 @@
+/*
+ * fs/f2fs/recovery.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include "f2fs.h"
+#include "node.h"
+#include "segment.h"
+
+static struct kmem_cache *fsync_entry_slab;
+
+bool space_for_roll_forward(struct f2fs_sb_info *sbi)
+{
+	if (sbi->last_valid_block_count + sbi->alloc_valid_block_count
+			> sbi->user_block_count)
+		return false;
+	return true;
+}
+
+static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
+								nid_t ino)
+{
+	struct list_head *this;
+	struct fsync_inode_entry *entry;
+
+	list_for_each(this, head) {
+		entry = list_entry(this, struct fsync_inode_entry, list);
+		if (entry->inode->i_ino == ino)
+			return entry;
+	}
+	return NULL;
+}
+
+static int recover_dentry(struct page *ipage, struct inode *inode)
+{
+	struct f2fs_node *raw_node = (struct f2fs_node *)kmap(ipage);
+	struct f2fs_inode *raw_inode = &(raw_node->i);
+	struct qstr name;
+	struct f2fs_dir_entry *de;
+	struct page *page;
+	struct inode *dir;
+	int err = 0;
+
+	if (!is_dent_dnode(ipage))
+		goto out;
+
+	dir = f2fs_iget(inode->i_sb, le32_to_cpu(raw_inode->i_pino));
+	if (IS_ERR(dir)) {
+		err = PTR_ERR(dir);
+		goto out;
+	}
+
+	name.len = le32_to_cpu(raw_inode->i_namelen);
+	name.name = raw_inode->i_name;
+
+	de = f2fs_find_entry(dir, &name, &page);
+	if (de) {
+		kunmap(page);
+		f2fs_put_page(page, 0);
+	} else {
+		err = __f2fs_add_link(dir, &name, inode);
+	}
+	iput(dir);
+out:
+	kunmap(ipage);
+	return err;
+}
+
+static int recover_inode(struct inode *inode, struct page *node_page)
+{
+	void *kaddr = page_address(node_page);
+	struct f2fs_node *raw_node = (struct f2fs_node *)kaddr;
+	struct f2fs_inode *raw_inode = &(raw_node->i);
+
+	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
+	i_size_write(inode, le64_to_cpu(raw_inode->i_size));
+	inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
+	inode->i_ctime.tv_sec = le64_to_cpu(raw_inode->i_ctime);
+	inode->i_mtime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
+	inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
+	inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
+	inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
+
+	return recover_dentry(node_page, inode);
+}
+
+static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
+{
+	unsigned long long cp_ver = le64_to_cpu(sbi->ckpt->checkpoint_ver);
+	struct curseg_info *curseg;
+	struct page *page;
+	block_t blkaddr;
+	int err = 0;
+
+	/* get node pages in the current segment */
+	curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
+	blkaddr = START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff;
+
+	/* read node page */
+	page = alloc_page(GFP_F2FS_ZERO);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+	lock_page(page);
+
+	while (1) {
+		struct fsync_inode_entry *entry;
+
+		err = f2fs_readpage(sbi, page, blkaddr, READ_SYNC);
+		if (err)
+			goto out;
+
+		lock_page(page);
+
+		if (cp_ver != cpver_of_node(page))
+			goto unlock_out;
+
+		if (!is_fsync_dnode(page))
+			goto next;
+
+		entry = get_fsync_inode(head, ino_of_node(page));
+		if (entry) {
+			entry->blkaddr = blkaddr;
+			if (IS_INODE(page) && is_dent_dnode(page))
+				set_inode_flag(F2FS_I(entry->inode),
+							FI_INC_LINK);
+		} else {
+			if (IS_INODE(page) && is_dent_dnode(page)) {
+				err = recover_inode_page(sbi, page);
+				if (err)
+					goto unlock_out;
+			}
+
+			/* add this fsync inode to the list */
+			entry = kmem_cache_alloc(fsync_entry_slab, GFP_NOFS);
+			if (!entry) {
+				err = -ENOMEM;
+				goto unlock_out;
+			}
+
+			entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
+			if (IS_ERR(entry->inode)) {
+				err = PTR_ERR(entry->inode);
+				kmem_cache_free(fsync_entry_slab, entry);
+				goto unlock_out;
+			}
+
+			list_add_tail(&entry->list, head);
+			entry->blkaddr = blkaddr;
+		}
+		if (IS_INODE(page)) {
+			err = recover_inode(entry->inode, page);
+			if (err == -ENOENT) {
+				goto next;
+			} else if (err) {
+				err = -EINVAL;
+				goto unlock_out;
+			}
+		}
+next:
+		/* check next segment */
+		blkaddr = next_blkaddr_of_node(page);
+	}
+unlock_out:
+	unlock_page(page);
+out:
+	__free_pages(page, 0);
+	return err;
+}
+
+static void destroy_fsync_dnodes(struct f2fs_sb_info *sbi,
+					struct list_head *head)
+{
+	struct fsync_inode_entry *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, head, list) {
+		iput(entry->inode);
+		list_del(&entry->list);
+		kmem_cache_free(fsync_entry_slab, entry);
+	}
+}
+
+static void check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
+						block_t blkaddr)
+{
+	struct seg_entry *sentry;
+	unsigned int segno = GET_SEGNO(sbi, blkaddr);
+	unsigned short blkoff = GET_SEGOFF_FROM_SEG0(sbi, blkaddr) &
+					(sbi->blocks_per_seg - 1);
+	struct f2fs_summary sum;
+	nid_t ino;
+	void *kaddr;
+	struct inode *inode;
+	struct page *node_page;
+	block_t bidx;
+	int i;
+
+	sentry = get_seg_entry(sbi, segno);
+	if (!f2fs_test_bit(blkoff, sentry->cur_valid_map))
+		return;
+
+	/* Get the previous summary */
+	for (i = CURSEG_WARM_DATA; i <= CURSEG_COLD_DATA; i++) {
+		struct curseg_info *curseg = CURSEG_I(sbi, i);
+		if (curseg->segno == segno) {
+			sum = curseg->sum_blk->entries[blkoff];
+			break;
+		}
+	}
+	if (i > CURSEG_COLD_DATA) {
+		struct page *sum_page = get_sum_page(sbi, segno);
+		struct f2fs_summary_block *sum_node;
+		kaddr = page_address(sum_page);
+		sum_node = (struct f2fs_summary_block *)kaddr;
+		sum = sum_node->entries[blkoff];
+		f2fs_put_page(sum_page, 1);
+	}
+
+	/* Get the node page */
+	node_page = get_node_page(sbi, le32_to_cpu(sum.nid));
+	bidx = start_bidx_of_node(ofs_of_node(node_page)) +
+				le16_to_cpu(sum.ofs_in_node);
+	ino = ino_of_node(node_page);
+	f2fs_put_page(node_page, 1);
+
+	/* Deallocate previous index in the node page */
+	inode = f2fs_iget(sbi->sb, ino);
+	if (IS_ERR(inode))
+		return;
+
+	truncate_hole(inode, bidx, bidx + 1);
+	iput(inode);
+}
+
+static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
+					struct page *page, block_t blkaddr)
+{
+	unsigned int start, end;
+	struct dnode_of_data dn;
+	struct f2fs_summary sum;
+	struct node_info ni;
+	int err = 0;
+	int ilock;
+
+	start = start_bidx_of_node(ofs_of_node(page));
+	if (IS_INODE(page))
+		end = start + ADDRS_PER_INODE;
+	else
+		end = start + ADDRS_PER_BLOCK;
+
+	ilock = mutex_lock_op(sbi);
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+
+	err = get_dnode_of_data(&dn, start, ALLOC_NODE);
+	if (err) {
+		mutex_unlock_op(sbi, ilock);
+		return err;
+	}
+
+	wait_on_page_writeback(dn.node_page);
+
+	get_node_info(sbi, dn.nid, &ni);
+	BUG_ON(ni.ino != ino_of_node(page));
+	BUG_ON(ofs_of_node(dn.node_page) != ofs_of_node(page));
+
+	for (; start < end; start++) {
+		block_t src, dest;
+
+		src = datablock_addr(dn.node_page, dn.ofs_in_node);
+		dest = datablock_addr(page, dn.ofs_in_node);
+
+		if (src != dest && dest != NEW_ADDR && dest != NULL_ADDR) {
+			if (src == NULL_ADDR) {
+				int err = reserve_new_block(&dn);
+				/* We should not get -ENOSPC */
+				BUG_ON(err);
+			}
+
+			/* Check the previous node page having this index */
+			check_index_in_prev_nodes(sbi, dest);
+
+			set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
+
+			/* write dummy data page */
+			recover_data_page(sbi, NULL, &sum, src, dest);
+			update_extent_cache(dest, &dn);
+		}
+		dn.ofs_in_node++;
+	}
+
+	/* write node page in place */
+	set_summary(&sum, dn.nid, 0, 0);
+	if (IS_INODE(dn.node_page))
+		sync_inode_page(&dn);
+
+	copy_node_footer(dn.node_page, page);
+	fill_node_footer(dn.node_page, dn.nid, ni.ino,
+					ofs_of_node(page), false);
+	set_page_dirty(dn.node_page);
+
+	recover_node_page(sbi, dn.node_page, &sum, &ni, blkaddr);
+	f2fs_put_dnode(&dn);
+	mutex_unlock_op(sbi, ilock);
+	return 0;
+}
+
+static int recover_data(struct f2fs_sb_info *sbi,
+				struct list_head *head, int type)
+{
+	unsigned long long cp_ver = le64_to_cpu(sbi->ckpt->checkpoint_ver);
+	struct curseg_info *curseg;
+	struct page *page;
+	int err = 0;
+	block_t blkaddr;
+
+	/* get node pages in the current segment */
+	curseg = CURSEG_I(sbi, type);
+	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
+
+	/* read node page */
+	page = alloc_page(GFP_NOFS | __GFP_ZERO);
+	if (IS_ERR(page))
+		return -ENOMEM;
+
+	lock_page(page);
+
+	while (1) {
+		struct fsync_inode_entry *entry;
+
+		err = f2fs_readpage(sbi, page, blkaddr, READ_SYNC);
+		if (err)
+			goto out;
+
+		lock_page(page);
+
+		if (cp_ver != cpver_of_node(page))
+			goto unlock_out;
+
+		entry = get_fsync_inode(head, ino_of_node(page));
+		if (!entry)
+			goto next;
+
+		err = do_recover_data(sbi, entry->inode, page, blkaddr);
+		if (err)
+			goto out;
+
+		if (entry->blkaddr == blkaddr) {
+			iput(entry->inode);
+			list_del(&entry->list);
+			kmem_cache_free(fsync_entry_slab, entry);
+		}
+next:
+		/* check next segment */
+		blkaddr = next_blkaddr_of_node(page);
+	}
+unlock_out:
+	unlock_page(page);
+out:
+	__free_pages(page, 0);
+
+	if (!err)
+		allocate_new_segments(sbi);
+	return err;
+}
+
+int recover_fsync_data(struct f2fs_sb_info *sbi)
+{
+	struct list_head inode_list;
+	int err;
+
+	fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
+			sizeof(struct fsync_inode_entry), NULL);
+	if (unlikely(!fsync_entry_slab))
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&inode_list);
+
+	/* step #1: find fsynced inode numbers */
+	err = find_fsync_dnodes(sbi, &inode_list);
+	if (err)
+		goto out;
+
+	if (list_empty(&inode_list))
+		goto out;
+
+	/* step #2: recover data */
+	sbi->por_doing = 1;
+	err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
+	sbi->por_doing = 0;
+	BUG_ON(!list_empty(&inode_list));
+out:
+	destroy_fsync_dnodes(sbi, &inode_list);
+	kmem_cache_destroy(fsync_entry_slab);
+	write_checkpoint(sbi, false);
+	return err;
+}

fs/f2fs/segment.h

@@ -0,0 +1,637 @@
+/*
+ * fs/f2fs/segment.h
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/blkdev.h>
+
+/* constant macro */
+#define NULL_SEGNO			((unsigned int)(~0))
+#define NULL_SECNO			((unsigned int)(~0))
+
+/* L: Logical segment # in volume, R: Relative segment # in main area */
+#define GET_L2R_SEGNO(free_i, segno)	(segno - free_i->start_segno)
+#define GET_R2L_SEGNO(free_i, segno)	(segno + free_i->start_segno)
+
+#define IS_DATASEG(t)							\
+	((t == CURSEG_HOT_DATA) || (t == CURSEG_COLD_DATA) ||		\
+	(t == CURSEG_WARM_DATA))
+
+#define IS_NODESEG(t)							\
+	((t == CURSEG_HOT_NODE) || (t == CURSEG_COLD_NODE) ||		\
+	(t == CURSEG_WARM_NODE))
+
+#define IS_CURSEG(sbi, seg)						\
+	((seg == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) ||	\
+	 (seg == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) ||	\
+	 (seg == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) ||	\
+	 (seg == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) ||	\
+	 (seg == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) ||	\
+	 (seg == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
+
+#define IS_CURSEC(sbi, secno)						\
+	((secno == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno /		\
+	  sbi->segs_per_sec) ||	\
+	 (secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno /		\
+	  sbi->segs_per_sec))	\
+
+#define START_BLOCK(sbi, segno)						\
+	(SM_I(sbi)->seg0_blkaddr +					\
+	 (GET_R2L_SEGNO(FREE_I(sbi), segno) << sbi->log_blocks_per_seg))
+#define NEXT_FREE_BLKADDR(sbi, curseg)					\
+	(START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff)
+
+#define MAIN_BASE_BLOCK(sbi)	(SM_I(sbi)->main_blkaddr)
+
+#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr)				\
+	((blk_addr) - SM_I(sbi)->seg0_blkaddr)
+#define GET_SEGNO_FROM_SEG0(sbi, blk_addr)				\
+	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> sbi->log_blocks_per_seg)
+#define GET_SEGNO(sbi, blk_addr)					\
+	(((blk_addr == NULL_ADDR) || (blk_addr == NEW_ADDR)) ?		\
+	NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi),			\
+		GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
+#define GET_SECNO(sbi, segno)					\
+	((segno) / sbi->segs_per_sec)
+#define GET_ZONENO_FROM_SEGNO(sbi, segno)				\
+	((segno / sbi->segs_per_sec) / sbi->secs_per_zone)
+
+#define GET_SUM_BLOCK(sbi, segno)				\
+	((sbi->sm_info->ssa_blkaddr) + segno)
+
+#define GET_SUM_TYPE(footer) ((footer)->entry_type)
+#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = type)
+
+#define SIT_ENTRY_OFFSET(sit_i, segno)					\
+	(segno % sit_i->sents_per_block)
+#define SIT_BLOCK_OFFSET(sit_i, segno)					\
+	(segno / SIT_ENTRY_PER_BLOCK)
+#define	START_SEGNO(sit_i, segno)		\
+	(SIT_BLOCK_OFFSET(sit_i, segno) * SIT_ENTRY_PER_BLOCK)
+#define f2fs_bitmap_size(nr)			\
+	(BITS_TO_LONGS(nr) * sizeof(unsigned long))
+#define TOTAL_SEGS(sbi)	(SM_I(sbi)->main_segments)
+#define TOTAL_SECS(sbi)	(sbi->total_sections)
+
+#define SECTOR_FROM_BLOCK(sbi, blk_addr)				\
+	(blk_addr << ((sbi)->log_blocksize - F2FS_LOG_SECTOR_SIZE))
+#define SECTOR_TO_BLOCK(sbi, sectors)					\
+	(sectors >> ((sbi)->log_blocksize - F2FS_LOG_SECTOR_SIZE))
+
+/* during checkpoint, bio_private is used to synchronize the last bio */
+struct bio_private {
+	struct f2fs_sb_info *sbi;
+	bool is_sync;
+	void *wait;
+};
+
+/*
+ * indicate a block allocation direction: RIGHT and LEFT.
+ * RIGHT means allocating new sections towards the end of volume.
+ * LEFT means the opposite direction.
+ */
+enum {
+	ALLOC_RIGHT = 0,
+	ALLOC_LEFT
+};
+
+/*
+ * In the victim_sel_policy->alloc_mode, there are two block allocation modes.
+ * LFS writes data sequentially with cleaning operations.
+ * SSR (Slack Space Recycle) reuses obsolete space without cleaning operations.
+ */
+enum {
+	LFS = 0,
+	SSR
+};
+
+/*
+ * In the victim_sel_policy->gc_mode, there are two gc, aka cleaning, modes.
+ * GC_CB is based on cost-benefit algorithm.
+ * GC_GREEDY is based on greedy algorithm.
+ */
+enum {
+	GC_CB = 0,
+	GC_GREEDY
+};
+
+/*
+ * BG_GC means the background cleaning job.
+ * FG_GC means the on-demand cleaning job.
+ */
+enum {
+	BG_GC = 0,
+	FG_GC
+};
+
+/* for a function parameter to select a victim segment */
+struct victim_sel_policy {
+	int alloc_mode;			/* LFS or SSR */
+	int gc_mode;			/* GC_CB or GC_GREEDY */
+	unsigned long *dirty_segmap;	/* dirty segment bitmap */
+	unsigned int offset;		/* last scanned bitmap offset */
+	unsigned int ofs_unit;		/* bitmap search unit */
+	unsigned int min_cost;		/* minimum cost */
+	unsigned int min_segno;		/* segment # having min. cost */
+};
+
+struct seg_entry {
+	unsigned short valid_blocks;	/* # of valid blocks */
+	unsigned char *cur_valid_map;	/* validity bitmap of blocks */
+	/*
+	 * # of valid blocks and the validity bitmap stored in the the last
+	 * checkpoint pack. This information is used by the SSR mode.
+	 */
+	unsigned short ckpt_valid_blocks;
+	unsigned char *ckpt_valid_map;
+	unsigned char type;		/* segment type like CURSEG_XXX_TYPE */
+	unsigned long long mtime;	/* modification time of the segment */
+};
+
+struct sec_entry {
+	unsigned int valid_blocks;	/* # of valid blocks in a section */
+};
+
+struct segment_allocation {
+	void (*allocate_segment)(struct f2fs_sb_info *, int, bool);
+};
+
+struct sit_info {
+	const struct segment_allocation *s_ops;
+
+	block_t sit_base_addr;		/* start block address of SIT area */
+	block_t sit_blocks;		/* # of blocks used by SIT area */
+	block_t written_valid_blocks;	/* # of valid blocks in main area */
+	char *sit_bitmap;		/* SIT bitmap pointer */
+	unsigned int bitmap_size;	/* SIT bitmap size */
+
+	unsigned long *dirty_sentries_bitmap;	/* bitmap for dirty sentries */
+	unsigned int dirty_sentries;		/* # of dirty sentries */
+	unsigned int sents_per_block;		/* # of SIT entries per block */
+	struct mutex sentry_lock;		/* to protect SIT cache */
+	struct seg_entry *sentries;		/* SIT segment-level cache */
+	struct sec_entry *sec_entries;		/* SIT section-level cache */
+
+	/* for cost-benefit algorithm in cleaning procedure */
+	unsigned long long elapsed_time;	/* elapsed time after mount */
+	unsigned long long mounted_time;	/* mount time */
+	unsigned long long min_mtime;		/* min. modification time */
+	unsigned long long max_mtime;		/* max. modification time */
+};
+
+struct free_segmap_info {
+	unsigned int start_segno;	/* start segment number logically */
+	unsigned int free_segments;	/* # of free segments */
+	unsigned int free_sections;	/* # of free sections */
+	rwlock_t segmap_lock;		/* free segmap lock */
+	unsigned long *free_segmap;	/* free segment bitmap */
+	unsigned long *free_secmap;	/* free section bitmap */
+};
+
+/* Notice: The order of dirty type is same with CURSEG_XXX in f2fs.h */
+enum dirty_type {
+	DIRTY_HOT_DATA,		/* dirty segments assigned as hot data logs */
+	DIRTY_WARM_DATA,	/* dirty segments assigned as warm data logs */
+	DIRTY_COLD_DATA,	/* dirty segments assigned as cold data logs */
+	DIRTY_HOT_NODE,		/* dirty segments assigned as hot node logs */
+	DIRTY_WARM_NODE,	/* dirty segments assigned as warm node logs */
+	DIRTY_COLD_NODE,	/* dirty segments assigned as cold node logs */
+	DIRTY,			/* to count # of dirty segments */
+	PRE,			/* to count # of entirely obsolete segments */
+	NR_DIRTY_TYPE
+};
+
+struct dirty_seglist_info {
+	const struct victim_selection *v_ops;	/* victim selction operation */
+	unsigned long *dirty_segmap[NR_DIRTY_TYPE];
+	struct mutex seglist_lock;		/* lock for segment bitmaps */
+	int nr_dirty[NR_DIRTY_TYPE];		/* # of dirty segments */
+	unsigned long *victim_secmap;		/* background GC victims */
+};
+
+/* victim selection function for cleaning and SSR */
+struct victim_selection {
+	int (*get_victim)(struct f2fs_sb_info *, unsigned int *,
+							int, int, char);
+};
+
+/* for active log information */
+struct curseg_info {
+	struct mutex curseg_mutex;		/* lock for consistency */
+	struct f2fs_summary_block *sum_blk;	/* cached summary block */
+	unsigned char alloc_type;		/* current allocation type */
+	unsigned int segno;			/* current segment number */
+	unsigned short next_blkoff;		/* next block offset to write */
+	unsigned int zone;			/* current zone number */
+	unsigned int next_segno;		/* preallocated segment */
+};
+
+/*
+ * inline functions
+ */
+static inline struct curseg_info *CURSEG_I(struct f2fs_sb_info *sbi, int type)
+{
+	return (struct curseg_info *)(SM_I(sbi)->curseg_array + type);
+}
+
+static inline struct seg_entry *get_seg_entry(struct f2fs_sb_info *sbi,
+						unsigned int segno)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	return &sit_i->sentries[segno];
+}
+
+static inline struct sec_entry *get_sec_entry(struct f2fs_sb_info *sbi,
+						unsigned int segno)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	return &sit_i->sec_entries[GET_SECNO(sbi, segno)];
+}
+
+static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi,
+				unsigned int segno, int section)
+{
+	/*
+	 * In order to get # of valid blocks in a section instantly from many
+	 * segments, f2fs manages two counting structures separately.
+	 */
+	if (section > 1)
+		return get_sec_entry(sbi, segno)->valid_blocks;
+	else
+		return get_seg_entry(sbi, segno)->valid_blocks;
+}
+
+static inline void seg_info_from_raw_sit(struct seg_entry *se,
+					struct f2fs_sit_entry *rs)
+{
+	se->valid_blocks = GET_SIT_VBLOCKS(rs);
+	se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs);
+	memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+	memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+	se->type = GET_SIT_TYPE(rs);
+	se->mtime = le64_to_cpu(rs->mtime);
+}
+
+static inline void seg_info_to_raw_sit(struct seg_entry *se,
+					struct f2fs_sit_entry *rs)
+{
+	unsigned short raw_vblocks = (se->type << SIT_VBLOCKS_SHIFT) |
+					se->valid_blocks;
+	rs->vblocks = cpu_to_le16(raw_vblocks);
+	memcpy(rs->valid_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
+	memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+	se->ckpt_valid_blocks = se->valid_blocks;
+	rs->mtime = cpu_to_le64(se->mtime);
+}
+
+static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
+		unsigned int max, unsigned int segno)
+{
+	unsigned int ret;
+	read_lock(&free_i->segmap_lock);
+	ret = find_next_bit(free_i->free_segmap, max, segno);
+	read_unlock(&free_i->segmap_lock);
+	return ret;
+}
+
+static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int secno = segno / sbi->segs_per_sec;
+	unsigned int start_segno = secno * sbi->segs_per_sec;
+	unsigned int next;
+
+	write_lock(&free_i->segmap_lock);
+	clear_bit(segno, free_i->free_segmap);
+	free_i->free_segments++;
+
+	next = find_next_bit(free_i->free_segmap, TOTAL_SEGS(sbi), start_segno);
+	if (next >= start_segno + sbi->segs_per_sec) {
+		clear_bit(secno, free_i->free_secmap);
+		free_i->free_sections++;
+	}
+	write_unlock(&free_i->segmap_lock);
+}
+
+static inline void __set_inuse(struct f2fs_sb_info *sbi,
+		unsigned int segno)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int secno = segno / sbi->segs_per_sec;
+	set_bit(segno, free_i->free_segmap);
+	free_i->free_segments--;
+	if (!test_and_set_bit(secno, free_i->free_secmap))
+		free_i->free_sections--;
+}
+
+static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
+		unsigned int segno)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int secno = segno / sbi->segs_per_sec;
+	unsigned int start_segno = secno * sbi->segs_per_sec;
+	unsigned int next;
+
+	write_lock(&free_i->segmap_lock);
+	if (test_and_clear_bit(segno, free_i->free_segmap)) {
+		free_i->free_segments++;
+
+		next = find_next_bit(free_i->free_segmap, TOTAL_SEGS(sbi),
+								start_segno);
+		if (next >= start_segno + sbi->segs_per_sec) {
+			if (test_and_clear_bit(secno, free_i->free_secmap))
+				free_i->free_sections++;
+		}
+	}
+	write_unlock(&free_i->segmap_lock);
+}
+
+static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
+		unsigned int segno)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int secno = segno / sbi->segs_per_sec;
+	write_lock(&free_i->segmap_lock);
+	if (!test_and_set_bit(segno, free_i->free_segmap)) {
+		free_i->free_segments--;
+		if (!test_and_set_bit(secno, free_i->free_secmap))
+			free_i->free_sections--;
+	}
+	write_unlock(&free_i->segmap_lock);
+}
+
+static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
+		void *dst_addr)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size);
+}
+
+static inline block_t written_block_count(struct f2fs_sb_info *sbi)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	block_t vblocks;
+
+	mutex_lock(&sit_i->sentry_lock);
+	vblocks = sit_i->written_valid_blocks;
+	mutex_unlock(&sit_i->sentry_lock);
+
+	return vblocks;
+}
+
+static inline unsigned int free_segments(struct f2fs_sb_info *sbi)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int free_segs;
+
+	read_lock(&free_i->segmap_lock);
+	free_segs = free_i->free_segments;
+	read_unlock(&free_i->segmap_lock);
+
+	return free_segs;
+}
+
+static inline int reserved_segments(struct f2fs_sb_info *sbi)
+{
+	return SM_I(sbi)->reserved_segments;
+}
+
+static inline unsigned int free_sections(struct f2fs_sb_info *sbi)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int free_secs;
+
+	read_lock(&free_i->segmap_lock);
+	free_secs = free_i->free_sections;
+	read_unlock(&free_i->segmap_lock);
+
+	return free_secs;
+}
+
+static inline unsigned int prefree_segments(struct f2fs_sb_info *sbi)
+{
+	return DIRTY_I(sbi)->nr_dirty[PRE];
+}
+
+static inline unsigned int dirty_segments(struct f2fs_sb_info *sbi)
+{
+	return DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_DATA] +
+		DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_DATA] +
+		DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_DATA] +
+		DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_NODE] +
+		DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_NODE] +
+		DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_NODE];
+}
+
+static inline int overprovision_segments(struct f2fs_sb_info *sbi)
+{
+	return SM_I(sbi)->ovp_segments;
+}
+
+static inline int overprovision_sections(struct f2fs_sb_info *sbi)
+{
+	return ((unsigned int) overprovision_segments(sbi)) / sbi->segs_per_sec;
+}
+
+static inline int reserved_sections(struct f2fs_sb_info *sbi)
+{
+	return ((unsigned int) reserved_segments(sbi)) / sbi->segs_per_sec;
+}
+
+static inline bool need_SSR(struct f2fs_sb_info *sbi)
+{
+	return (free_sections(sbi) < overprovision_sections(sbi));
+}
+
+static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
+{
+	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
+	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+
+	if (sbi->por_doing)
+		return false;
+
+	return ((free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs +
+						reserved_sections(sbi)));
+}
+
+static inline int utilization(struct f2fs_sb_info *sbi)
+{
+	return div_u64(valid_user_blocks(sbi) * 100, sbi->user_block_count);
+}
+
+/*
+ * Sometimes f2fs may be better to drop out-of-place update policy.
+ * So, if fs utilization is over MIN_IPU_UTIL, then f2fs tries to write
+ * data in the original place likewise other traditional file systems.
+ * But, currently set 100 in percentage, which means it is disabled.
+ * See below need_inplace_update().
+ */
+#define MIN_IPU_UTIL		100
+static inline bool need_inplace_update(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	if (S_ISDIR(inode->i_mode))
+		return false;
+	if (need_SSR(sbi) && utilization(sbi) > MIN_IPU_UTIL)
+		return true;
+	return false;
+}
+
+static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi,
+		int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	return curseg->segno;
+}
+
+static inline unsigned char curseg_alloc_type(struct f2fs_sb_info *sbi,
+		int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	return curseg->alloc_type;
+}
+
+static inline unsigned short curseg_blkoff(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	return curseg->next_blkoff;
+}
+
+static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
+{
+	unsigned int end_segno = SM_I(sbi)->segment_count - 1;
+	BUG_ON(segno > end_segno);
+}
+
+/*
+ * This function is used for only debugging.
+ * NOTE: In future, we have to remove this function.
+ */
+static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
+{
+	struct f2fs_sm_info *sm_info = SM_I(sbi);
+	block_t total_blks = sm_info->segment_count << sbi->log_blocks_per_seg;
+	block_t start_addr = sm_info->seg0_blkaddr;
+	block_t end_addr = start_addr + total_blks - 1;
+	BUG_ON(blk_addr < start_addr);
+	BUG_ON(blk_addr > end_addr);
+}
+
+/*
+ * Summary block is always treated as invalid block
+ */
+static inline void check_block_count(struct f2fs_sb_info *sbi,
+		int segno, struct f2fs_sit_entry *raw_sit)
+{
+	struct f2fs_sm_info *sm_info = SM_I(sbi);
+	unsigned int end_segno = sm_info->segment_count - 1;
+	int valid_blocks = 0;
+	int i;
+
+	/* check segment usage */
+	BUG_ON(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg);
+
+	/* check boundary of a given segment number */
+	BUG_ON(segno > end_segno);
+
+	/* check bitmap with valid block count */
+	for (i = 0; i < sbi->blocks_per_seg; i++)
+		if (f2fs_test_bit(i, raw_sit->valid_map))
+			valid_blocks++;
+	BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks);
+}
+
+static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
+						unsigned int start)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	unsigned int offset = SIT_BLOCK_OFFSET(sit_i, start);
+	block_t blk_addr = sit_i->sit_base_addr + offset;
+
+	check_seg_range(sbi, start);
+
+	/* calculate sit block address */
+	if (f2fs_test_bit(offset, sit_i->sit_bitmap))
+		blk_addr += sit_i->sit_blocks;
+
+	return blk_addr;
+}
+
+static inline pgoff_t next_sit_addr(struct f2fs_sb_info *sbi,
+						pgoff_t block_addr)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	block_addr -= sit_i->sit_base_addr;
+	if (block_addr < sit_i->sit_blocks)
+		block_addr += sit_i->sit_blocks;
+	else
+		block_addr -= sit_i->sit_blocks;
+
+	return block_addr + sit_i->sit_base_addr;
+}
+
+static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
+{
+	unsigned int block_off = SIT_BLOCK_OFFSET(sit_i, start);
+
+	if (f2fs_test_bit(block_off, sit_i->sit_bitmap))
+		f2fs_clear_bit(block_off, sit_i->sit_bitmap);
+	else
+		f2fs_set_bit(block_off, sit_i->sit_bitmap);
+}
+
+static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	return sit_i->elapsed_time + CURRENT_TIME_SEC.tv_sec -
+						sit_i->mounted_time;
+}
+
+static inline void set_summary(struct f2fs_summary *sum, nid_t nid,
+			unsigned int ofs_in_node, unsigned char version)
+{
+	sum->nid = cpu_to_le32(nid);
+	sum->ofs_in_node = cpu_to_le16(ofs_in_node);
+	sum->version = version;
+}
+
+static inline block_t start_sum_block(struct f2fs_sb_info *sbi)
+{
+	return __start_cp_addr(sbi) +
+		le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
+}
+
+static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type)
+{
+	return __start_cp_addr(sbi) +
+		le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_total_block_count)
+				- (base + 1) + type;
+}
+
+static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
+{
+	if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno))
+		return true;
+	return false;
+}
+
+static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi)
+{
+	struct block_device *bdev = sbi->sb->s_bdev;
+	struct request_queue *q = bdev_get_queue(bdev);
+	return SECTOR_TO_BLOCK(sbi, queue_max_sectors(q));
+}

fs/f2fs/super.c

@@ -0,0 +1,823 @@
+/*
+ * fs/f2fs/super.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/statfs.h>
+#include <linux/buffer_head.h>
+#include <linux/backing-dev.h>
+#include <linux/kthread.h>
+#include <linux/parser.h>
+#include <linux/mount.h>
+#include <linux/seq_file.h>
+#include <linux/random.h>
+#include <linux/exportfs.h>
+#include <linux/blkdev.h>
+#include <linux/f2fs_fs.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include "segment.h"
+#include "xattr.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/f2fs.h>
+
+static struct kmem_cache *f2fs_inode_cachep;
+
+enum {
+	Opt_gc_background_off,
+	Opt_disable_roll_forward,
+	Opt_discard,
+	Opt_noheap,
+	Opt_nouser_xattr,
+	Opt_noacl,
+	Opt_active_logs,
+	Opt_disable_ext_identify,
+	Opt_err,
+};
+
+static match_table_t f2fs_tokens = {
+	{Opt_gc_background_off, "background_gc_off"},
+	{Opt_disable_roll_forward, "disable_roll_forward"},
+	{Opt_discard, "discard"},
+	{Opt_noheap, "no_heap"},
+	{Opt_nouser_xattr, "nouser_xattr"},
+	{Opt_noacl, "noacl"},
+	{Opt_active_logs, "active_logs=%u"},
+	{Opt_disable_ext_identify, "disable_ext_identify"},
+	{Opt_err, NULL},
+};
+
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf);
+	va_end(args);
+}
+
+static void init_once(void *foo)
+{
+	struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo;
+
+	inode_init_once(&fi->vfs_inode);
+}
+
+static struct inode *f2fs_alloc_inode(struct super_block *sb)
+{
+	struct f2fs_inode_info *fi;
+
+	fi = kmem_cache_alloc(f2fs_inode_cachep, GFP_NOFS | __GFP_ZERO);
+	if (!fi)
+		return NULL;
+
+	init_once((void *) fi);
+
+	/* Initialize f2fs-specific inode info */
+	fi->vfs_inode.i_version = 1;
+	atomic_set(&fi->dirty_dents, 0);
+	fi->i_current_depth = 1;
+	fi->i_advise = 0;
+	rwlock_init(&fi->ext.ext_lock);
+
+	set_inode_flag(fi, FI_NEW_INODE);
+
+	return &fi->vfs_inode;
+}
+
+static int f2fs_drop_inode(struct inode *inode)
+{
+	/*
+	 * This is to avoid a deadlock condition like below.
+	 * writeback_single_inode(inode)
+	 *  - f2fs_write_data_page
+	 *    - f2fs_gc -> iput -> evict
+	 *       - inode_wait_for_writeback(inode)
+	 */
+	if (!inode_unhashed(inode) && inode->i_state & I_SYNC)
+		return 0;
+	return generic_drop_inode(inode);
+}
+
+static void f2fs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	kmem_cache_free(f2fs_inode_cachep, F2FS_I(inode));
+}
+
+static void f2fs_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, f2fs_i_callback);
+}
+
+static void f2fs_put_super(struct super_block *sb)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+
+	f2fs_destroy_stats(sbi);
+	stop_gc_thread(sbi);
+
+	write_checkpoint(sbi, true);
+
+	iput(sbi->node_inode);
+	iput(sbi->meta_inode);
+
+	/* destroy f2fs internal modules */
+	destroy_node_manager(sbi);
+	destroy_segment_manager(sbi);
+
+	kfree(sbi->ckpt);
+
+	sb->s_fs_info = NULL;
+	brelse(sbi->raw_super_buf);
+	kfree(sbi);
+}
+
+int f2fs_sync_fs(struct super_block *sb, int sync)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+
+	trace_f2fs_sync_fs(sb, sync);
+
+	if (!sbi->s_dirty && !get_pages(sbi, F2FS_DIRTY_NODES))
+		return 0;
+
+	if (sync) {
+		mutex_lock(&sbi->gc_mutex);
+		write_checkpoint(sbi, false);
+		mutex_unlock(&sbi->gc_mutex);
+	} else {
+		f2fs_balance_fs(sbi);
+	}
+
+	return 0;
+}
+
+static int f2fs_freeze(struct super_block *sb)
+{
+	int err;
+
+	if (sb->s_flags & MS_RDONLY)
+		return 0;
+
+	err = f2fs_sync_fs(sb, 1);
+	return err;
+}
+
+static int f2fs_unfreeze(struct super_block *sb)
+{
+	return 0;
+}
+
+static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct super_block *sb = dentry->d_sb;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+	block_t total_count, user_block_count, start_count, ovp_count;
+
+	total_count = le64_to_cpu(sbi->raw_super->block_count);
+	user_block_count = sbi->user_block_count;
+	start_count = le32_to_cpu(sbi->raw_super->segment0_blkaddr);
+	ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
+	buf->f_type = F2FS_SUPER_MAGIC;
+	buf->f_bsize = sbi->blocksize;
+
+	buf->f_blocks = total_count - start_count;
+	buf->f_bfree = buf->f_blocks - valid_user_blocks(sbi) - ovp_count;
+	buf->f_bavail = user_block_count - valid_user_blocks(sbi);
+
+	buf->f_files = sbi->total_node_count;
+	buf->f_ffree = sbi->total_node_count - valid_inode_count(sbi);
+
+	buf->f_namelen = F2FS_NAME_LEN;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
+
+	return 0;
+}
+
+static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
+
+	if (test_opt(sbi, BG_GC))
+		seq_puts(seq, ",background_gc_on");
+	else
+		seq_puts(seq, ",background_gc_off");
+	if (test_opt(sbi, DISABLE_ROLL_FORWARD))
+		seq_puts(seq, ",disable_roll_forward");
+	if (test_opt(sbi, DISCARD))
+		seq_puts(seq, ",discard");
+	if (test_opt(sbi, NOHEAP))
+		seq_puts(seq, ",no_heap_alloc");
+#ifdef CONFIG_F2FS_FS_XATTR
+	if (test_opt(sbi, XATTR_USER))
+		seq_puts(seq, ",user_xattr");
+	else
+		seq_puts(seq, ",nouser_xattr");
+#endif
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+	if (test_opt(sbi, POSIX_ACL))
+		seq_puts(seq, ",acl");
+	else
+		seq_puts(seq, ",noacl");
+#endif
+	if (test_opt(sbi, DISABLE_EXT_IDENTIFY))
+		seq_puts(seq, ",disable_ext_identify");
+
+	seq_printf(seq, ",active_logs=%u", sbi->active_logs);
+
+	return 0;
+}
+
+static struct super_operations f2fs_sops = {
+	.alloc_inode	= f2fs_alloc_inode,
+	.drop_inode	= f2fs_drop_inode,
+	.destroy_inode	= f2fs_destroy_inode,
+	.write_inode	= f2fs_write_inode,
+	.show_options	= f2fs_show_options,
+	.evict_inode	= f2fs_evict_inode,
+	.put_super	= f2fs_put_super,
+	.sync_fs	= f2fs_sync_fs,
+	.freeze_fs	= f2fs_freeze,
+	.unfreeze_fs	= f2fs_unfreeze,
+	.statfs		= f2fs_statfs,
+};
+
+static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
+		u64 ino, u32 generation)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	struct inode *inode;
+
+	if (ino < F2FS_ROOT_INO(sbi))
+		return ERR_PTR(-ESTALE);
+
+	/*
+	 * f2fs_iget isn't quite right if the inode is currently unallocated!
+	 * However f2fs_iget currently does appropriate checks to handle stale
+	 * inodes so everything is OK.
+	 */
+	inode = f2fs_iget(sb, ino);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+	if (generation && inode->i_generation != generation) {
+		/* we didn't find the right inode.. */
+		iput(inode);
+		return ERR_PTR(-ESTALE);
+	}
+	return inode;
+}
+
+static struct dentry *f2fs_fh_to_dentry(struct super_block *sb, struct fid *fid,
+		int fh_len, int fh_type)
+{
+	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
+				    f2fs_nfs_get_inode);
+}
+
+static struct dentry *f2fs_fh_to_parent(struct super_block *sb, struct fid *fid,
+		int fh_len, int fh_type)
+{
+	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
+				    f2fs_nfs_get_inode);
+}
+
+static const struct export_operations f2fs_export_ops = {
+	.fh_to_dentry = f2fs_fh_to_dentry,
+	.fh_to_parent = f2fs_fh_to_parent,
+	.get_parent = f2fs_get_parent,
+};
+
+static int parse_options(struct super_block *sb, struct f2fs_sb_info *sbi,
+				char *options)
+{
+	substring_t args[MAX_OPT_ARGS];
+	char *p;
+	int arg = 0;
+
+	if (!options)
+		return 0;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token;
+		if (!*p)
+			continue;
+		/*
+		 * Initialize args struct so we know whether arg was
+		 * found; some options take optional arguments.
+		 */
+		args[0].to = args[0].from = NULL;
+		token = match_token(p, f2fs_tokens, args);
+
+		switch (token) {
+		case Opt_gc_background_off:
+			clear_opt(sbi, BG_GC);
+			break;
+		case Opt_disable_roll_forward:
+			set_opt(sbi, DISABLE_ROLL_FORWARD);
+			break;
+		case Opt_discard:
+			set_opt(sbi, DISCARD);
+			break;
+		case Opt_noheap:
+			set_opt(sbi, NOHEAP);
+			break;
+#ifdef CONFIG_F2FS_FS_XATTR
+		case Opt_nouser_xattr:
+			clear_opt(sbi, XATTR_USER);
+			break;
+#else
+		case Opt_nouser_xattr:
+			f2fs_msg(sb, KERN_INFO,
+				"nouser_xattr options not supported");
+			break;
+#endif
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+		case Opt_noacl:
+			clear_opt(sbi, POSIX_ACL);
+			break;
+#else
+		case Opt_noacl:
+			f2fs_msg(sb, KERN_INFO, "noacl options not supported");
+			break;
+#endif
+		case Opt_active_logs:
+			if (args->from && match_int(args, &arg))
+				return -EINVAL;
+			if (arg != 2 && arg != 4 && arg != NR_CURSEG_TYPE)
+				return -EINVAL;
+			sbi->active_logs = arg;
+			break;
+		case Opt_disable_ext_identify:
+			set_opt(sbi, DISABLE_EXT_IDENTIFY);
+			break;
+		default:
+			f2fs_msg(sb, KERN_ERR,
+				"Unrecognized mount option \"%s\" or missing value",
+				p);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static loff_t max_file_size(unsigned bits)
+{
+	loff_t result = ADDRS_PER_INODE;
+	loff_t leaf_count = ADDRS_PER_BLOCK;
+
+	/* two direct node blocks */
+	result += (leaf_count * 2);
+
+	/* two indirect node blocks */
+	leaf_count *= NIDS_PER_BLOCK;
+	result += (leaf_count * 2);
+
+	/* one double indirect node block */
+	leaf_count *= NIDS_PER_BLOCK;
+	result += leaf_count;
+
+	result <<= bits;
+	return result;
+}
+
+static int sanity_check_raw_super(struct super_block *sb,
+			struct f2fs_super_block *raw_super)
+{
+	unsigned int blocksize;
+
+	if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
+		f2fs_msg(sb, KERN_INFO,
+			"Magic Mismatch, valid(0x%x) - read(0x%x)",
+			F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic));
+		return 1;
+	}
+
+	/* Currently, support only 4KB page cache size */
+	if (F2FS_BLKSIZE != PAGE_CACHE_SIZE) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid page_cache_size (%lu), supports only 4KB\n",
+			PAGE_CACHE_SIZE);
+		return 1;
+	}
+
+	/* Currently, support only 4KB block size */
+	blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
+	if (blocksize != F2FS_BLKSIZE) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid blocksize (%u), supports only 4KB\n",
+			blocksize);
+		return 1;
+	}
+
+	/* check log blocks per segment */
+	if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid log blocks per segment (%u)\n",
+			le32_to_cpu(raw_super->log_blocks_per_seg));
+		return 1;
+	}
+
+	if (le32_to_cpu(raw_super->log_sectorsize) !=
+					F2FS_LOG_SECTOR_SIZE) {
+		f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize");
+		return 1;
+	}
+	if (le32_to_cpu(raw_super->log_sectors_per_block) !=
+					F2FS_LOG_SECTORS_PER_BLOCK) {
+		f2fs_msg(sb, KERN_INFO, "Invalid log sectors per block");
+		return 1;
+	}
+
+	if (le32_to_cpu(raw_super->segment_count) > F2FS_MAX_SEGMENT) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid segment count (%u)",
+			le32_to_cpu(raw_super->segment_count));
+		return 1;
+	}
+
+	return 0;
+}
+
+static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
+{
+	unsigned int total, fsmeta;
+	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	unsigned int main_segs, blocks_per_seg;
+	int i;
+
+	total = le32_to_cpu(raw_super->segment_count);
+	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
+	fsmeta += le32_to_cpu(raw_super->segment_count_sit);
+	fsmeta += le32_to_cpu(raw_super->segment_count_nat);
+	fsmeta += le32_to_cpu(ckpt->rsvd_segment_count);
+	fsmeta += le32_to_cpu(raw_super->segment_count_ssa);
+
+	if (fsmeta >= total)
+		return 1;
+
+	main_segs = le32_to_cpu(raw_super->segment_count_main);
+	blocks_per_seg = sbi->blocks_per_seg;
+
+	for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
+		if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs ||
+			le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg)
+			return 1;
+	}
+	for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
+		if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs ||
+			le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg)
+			return 1;
+	}
+
+	if (is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) {
+		f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
+		return 1;
+	}
+	return 0;
+}
+
+static void init_sb_info(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_super_block *raw_super = sbi->raw_super;
+	int i;
+
+	sbi->log_sectors_per_block =
+		le32_to_cpu(raw_super->log_sectors_per_block);
+	sbi->log_blocksize = le32_to_cpu(raw_super->log_blocksize);
+	sbi->blocksize = 1 << sbi->log_blocksize;
+	sbi->log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
+	sbi->blocks_per_seg = 1 << sbi->log_blocks_per_seg;
+	sbi->segs_per_sec = le32_to_cpu(raw_super->segs_per_sec);
+	sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone);
+	sbi->total_sections = le32_to_cpu(raw_super->section_count);
+	sbi->total_node_count =
+		(le32_to_cpu(raw_super->segment_count_nat) / 2)
+			* sbi->blocks_per_seg * NAT_ENTRY_PER_BLOCK;
+	sbi->root_ino_num = le32_to_cpu(raw_super->root_ino);
+	sbi->node_ino_num = le32_to_cpu(raw_super->node_ino);
+	sbi->meta_ino_num = le32_to_cpu(raw_super->meta_ino);
+	sbi->cur_victim_sec = NULL_SECNO;
+
+	for (i = 0; i < NR_COUNT_TYPE; i++)
+		atomic_set(&sbi->nr_pages[i], 0);
+}
+
+static int validate_superblock(struct super_block *sb,
+		struct f2fs_super_block **raw_super,
+		struct buffer_head **raw_super_buf, sector_t block)
+{
+	const char *super = (block == 0 ? "first" : "second");
+
+	/* read f2fs raw super block */
+	*raw_super_buf = sb_bread(sb, block);
+	if (!*raw_super_buf) {
+		f2fs_msg(sb, KERN_ERR, "unable to read %s superblock",
+				super);
+		return -EIO;
+	}
+
+	*raw_super = (struct f2fs_super_block *)
+		((char *)(*raw_super_buf)->b_data + F2FS_SUPER_OFFSET);
+
+	/* sanity checking of raw super */
+	if (!sanity_check_raw_super(sb, *raw_super))
+		return 0;
+
+	f2fs_msg(sb, KERN_ERR, "Can't find a valid F2FS filesystem "
+				"in %s superblock", super);
+	return -EINVAL;
+}
+
+static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct f2fs_sb_info *sbi;
+	struct f2fs_super_block *raw_super;
+	struct buffer_head *raw_super_buf;
+	struct inode *root;
+	long err = -EINVAL;
+	int i;
+
+	/* allocate memory for f2fs-specific super block info */
+	sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL);
+	if (!sbi)
+		return -ENOMEM;
+
+	/* set a block size */
+	if (!sb_set_blocksize(sb, F2FS_BLKSIZE)) {
+		f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
+		goto free_sbi;
+	}
+
+	err = validate_superblock(sb, &raw_super, &raw_super_buf, 0);
+	if (err) {
+		brelse(raw_super_buf);
+		/* check secondary superblock when primary failed */
+		err = validate_superblock(sb, &raw_super, &raw_super_buf, 1);
+		if (err)
+			goto free_sb_buf;
+	}
+	/* init some FS parameters */
+	sbi->active_logs = NR_CURSEG_TYPE;
+
+	set_opt(sbi, BG_GC);
+
+#ifdef CONFIG_F2FS_FS_XATTR
+	set_opt(sbi, XATTR_USER);
+#endif
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+	set_opt(sbi, POSIX_ACL);
+#endif
+	/* parse mount options */
+	err = parse_options(sb, sbi, (char *)data);
+	if (err)
+		goto free_sb_buf;
+
+	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
+	sb->s_max_links = F2FS_LINK_MAX;
+	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
+
+	sb->s_op = &f2fs_sops;
+	sb->s_xattr = f2fs_xattr_handlers;
+	sb->s_export_op = &f2fs_export_ops;
+	sb->s_magic = F2FS_SUPER_MAGIC;
+	sb->s_fs_info = sbi;
+	sb->s_time_gran = 1;
+	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+		(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
+	memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
+
+	/* init f2fs-specific super block info */
+	sbi->sb = sb;
+	sbi->raw_super = raw_super;
+	sbi->raw_super_buf = raw_super_buf;
+	mutex_init(&sbi->gc_mutex);
+	mutex_init(&sbi->writepages);
+	mutex_init(&sbi->cp_mutex);
+	for (i = 0; i < NR_GLOBAL_LOCKS; i++)
+		mutex_init(&sbi->fs_lock[i]);
+	mutex_init(&sbi->node_write);
+	sbi->por_doing = 0;
+	spin_lock_init(&sbi->stat_lock);
+	init_rwsem(&sbi->bio_sem);
+	init_sb_info(sbi);
+
+	/* get an inode for meta space */
+	sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
+	if (IS_ERR(sbi->meta_inode)) {
+		f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
+		err = PTR_ERR(sbi->meta_inode);
+		goto free_sb_buf;
+	}
+
+	err = get_valid_checkpoint(sbi);
+	if (err) {
+		f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint");
+		goto free_meta_inode;
+	}
+
+	/* sanity checking of checkpoint */
+	err = -EINVAL;
+	if (sanity_check_ckpt(sbi)) {
+		f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
+		goto free_cp;
+	}
+
+	sbi->total_valid_node_count =
+				le32_to_cpu(sbi->ckpt->valid_node_count);
+	sbi->total_valid_inode_count =
+				le32_to_cpu(sbi->ckpt->valid_inode_count);
+	sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count);
+	sbi->total_valid_block_count =
+				le64_to_cpu(sbi->ckpt->valid_block_count);
+	sbi->last_valid_block_count = sbi->total_valid_block_count;
+	sbi->alloc_valid_block_count = 0;
+	INIT_LIST_HEAD(&sbi->dir_inode_list);
+	spin_lock_init(&sbi->dir_inode_lock);
+
+	init_orphan_info(sbi);
+
+	/* setup f2fs internal modules */
+	err = build_segment_manager(sbi);
+	if (err) {
+		f2fs_msg(sb, KERN_ERR,
+			"Failed to initialize F2FS segment manager");
+		goto free_sm;
+	}
+	err = build_node_manager(sbi);
+	if (err) {
+		f2fs_msg(sb, KERN_ERR,
+			"Failed to initialize F2FS node manager");
+		goto free_nm;
+	}
+
+	build_gc_manager(sbi);
+
+	/* get an inode for node space */
+	sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi));
+	if (IS_ERR(sbi->node_inode)) {
+		f2fs_msg(sb, KERN_ERR, "Failed to read node inode");
+		err = PTR_ERR(sbi->node_inode);
+		goto free_nm;
+	}
+
+	/* if there are nt orphan nodes free them */
+	err = -EINVAL;
+	if (recover_orphan_inodes(sbi))
+		goto free_node_inode;
+
+	/* read root inode and dentry */
+	root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
+	if (IS_ERR(root)) {
+		f2fs_msg(sb, KERN_ERR, "Failed to read root inode");
+		err = PTR_ERR(root);
+		goto free_node_inode;
+	}
+	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size)
+		goto free_root_inode;
+
+	sb->s_root = d_make_root(root); /* allocate root dentry */
+	if (!sb->s_root) {
+		err = -ENOMEM;
+		goto free_root_inode;
+	}
+
+	/* recover fsynced data */
+	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
+		err = recover_fsync_data(sbi);
+		if (err)
+			f2fs_msg(sb, KERN_ERR,
+				"Cannot recover all fsync data errno=%ld", err);
+	}
+
+	/* After POR, we can run background GC thread */
+	err = start_gc_thread(sbi);
+	if (err)
+		goto fail;
+
+	err = f2fs_build_stats(sbi);
+	if (err)
+		goto fail;
+
+	if (test_opt(sbi, DISCARD)) {
+		struct request_queue *q = bdev_get_queue(sb->s_bdev);
+		if (!blk_queue_discard(q))
+			f2fs_msg(sb, KERN_WARNING,
+					"mounting with \"discard\" option, but "
+					"the device does not support discard");
+	}
+
+	return 0;
+fail:
+	stop_gc_thread(sbi);
+free_root_inode:
+	dput(sb->s_root);
+	sb->s_root = NULL;
+free_node_inode:
+	iput(sbi->node_inode);
+free_nm:
+	destroy_node_manager(sbi);
+free_sm:
+	destroy_segment_manager(sbi);
+free_cp:
+	kfree(sbi->ckpt);
+free_meta_inode:
+	make_bad_inode(sbi->meta_inode);
+	iput(sbi->meta_inode);
+free_sb_buf:
+	brelse(raw_super_buf);
+free_sbi:
+	kfree(sbi);
+	return err;
+}
+
+static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
+			const char *dev_name, void *data)
+{
+	return mount_bdev(fs_type, flags, dev_name, data, f2fs_fill_super);
+}
+
+static struct file_system_type f2fs_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "f2fs",
+	.mount		= f2fs_mount,
+	.kill_sb	= kill_block_super,
+	.fs_flags	= FS_REQUIRES_DEV,
+};
+MODULE_ALIAS_FS("f2fs");
+
+static int __init init_inodecache(void)
+{
+	f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache",
+			sizeof(struct f2fs_inode_info), NULL);
+	if (f2fs_inode_cachep == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+static void destroy_inodecache(void)
+{
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
+	kmem_cache_destroy(f2fs_inode_cachep);
+}
+
+static int __init init_f2fs_fs(void)
+{
+	int err;
+
+	err = init_inodecache();
+	if (err)
+		goto fail;
+	err = create_node_manager_caches();
+	if (err)
+		goto fail;
+	err = create_gc_caches();
+	if (err)
+		goto fail;
+	err = create_checkpoint_caches();
+	if (err)
+		goto fail;
+	err = register_filesystem(&f2fs_fs_type);
+	if (err)
+		goto fail;
+	f2fs_create_root_stats();
+fail:
+	return err;
+}
+
+static void __exit exit_f2fs_fs(void)
+{
+	f2fs_destroy_root_stats();
+	unregister_filesystem(&f2fs_fs_type);
+	destroy_checkpoint_caches();
+	destroy_gc_caches();
+	destroy_node_manager_caches();
+	destroy_inodecache();
+}
+
+module_init(init_f2fs_fs)
+module_exit(exit_f2fs_fs)
+
+MODULE_AUTHOR("Samsung Electronics's Praesto Team");
+MODULE_DESCRIPTION("Flash Friendly File System");
+MODULE_LICENSE("GPL");

fs/f2fs/xattr.c

@@ -0,0 +1,447 @@
+/*
+ * 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.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/rwsem.h>
+#include <linux/f2fs_fs.h>
+#include "f2fs.h"
+#include "xattr.h"
+
+static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list,
+		size_t list_size, const char *name, size_t name_len, int type)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+	int total_len, prefix_len = 0;
+	const char *prefix = NULL;
+
+	switch (type) {
+	case F2FS_XATTR_INDEX_USER:
+		if (!test_opt(sbi, XATTR_USER))
+			return -EOPNOTSUPP;
+		prefix = XATTR_USER_PREFIX;
+		prefix_len = XATTR_USER_PREFIX_LEN;
+		break;
+	case F2FS_XATTR_INDEX_TRUSTED:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		prefix = XATTR_TRUSTED_PREFIX;
+		prefix_len = XATTR_TRUSTED_PREFIX_LEN;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	total_len = prefix_len + name_len + 1;
+	if (list && total_len <= list_size) {
+		memcpy(list, prefix, prefix_len);
+		memcpy(list+prefix_len, name, name_len);
+		list[prefix_len + name_len] = '\0';
+	}
+	return total_len;
+}
+
+static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name,
+		void *buffer, size_t size, int type)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+
+	switch (type) {
+	case F2FS_XATTR_INDEX_USER:
+		if (!test_opt(sbi, XATTR_USER))
+			return -EOPNOTSUPP;
+		break;
+	case F2FS_XATTR_INDEX_TRUSTED:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+	return f2fs_getxattr(dentry->d_inode, type, name,
+			buffer, size);
+}
+
+static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags, int type)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+
+	switch (type) {
+	case F2FS_XATTR_INDEX_USER:
+		if (!test_opt(sbi, XATTR_USER))
+			return -EOPNOTSUPP;
+		break;
+	case F2FS_XATTR_INDEX_TRUSTED:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+
+	return f2fs_setxattr(dentry->d_inode, type, name, value, size);
+}
+
+static size_t f2fs_xattr_advise_list(struct dentry *dentry, char *list,
+		size_t list_size, const char *name, size_t name_len, int type)
+{
+	const char *xname = F2FS_SYSTEM_ADVISE_PREFIX;
+	size_t size;
+
+	if (type != F2FS_XATTR_INDEX_ADVISE)
+		return 0;
+
+	size = strlen(xname) + 1;
+	if (list && size <= list_size)
+		memcpy(list, xname, size);
+	return size;
+}
+
+static int f2fs_xattr_advise_get(struct dentry *dentry, const char *name,
+		void *buffer, size_t size, int type)
+{
+	struct inode *inode = dentry->d_inode;
+
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+
+	*((char *)buffer) = F2FS_I(inode)->i_advise;
+	return sizeof(char);
+}
+
+static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name,
+		const void *value, size_t size, int flags, int type)
+{
+	struct inode *inode = dentry->d_inode;
+
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	if (!inode_owner_or_capable(inode))
+		return -EPERM;
+	if (value == NULL)
+		return -EINVAL;
+
+	F2FS_I(inode)->i_advise |= *(char *)value;
+	return 0;
+}
+
+const struct xattr_handler f2fs_xattr_user_handler = {
+	.prefix	= XATTR_USER_PREFIX,
+	.flags	= F2FS_XATTR_INDEX_USER,
+	.list	= f2fs_xattr_generic_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_generic_list,
+	.get	= f2fs_xattr_generic_get,
+	.set	= f2fs_xattr_generic_set,
+};
+
+const struct xattr_handler f2fs_xattr_advise_handler = {
+	.prefix = F2FS_SYSTEM_ADVISE_PREFIX,
+	.flags	= F2FS_XATTR_INDEX_ADVISE,
+	.list   = f2fs_xattr_advise_list,
+	.get    = f2fs_xattr_advise_get,
+	.set    = f2fs_xattr_advise_set,
+};
+
+static const struct xattr_handler *f2fs_xattr_handler_map[] = {
+	[F2FS_XATTR_INDEX_USER] = &f2fs_xattr_user_handler,
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+	[F2FS_XATTR_INDEX_POSIX_ACL_ACCESS] = &f2fs_xattr_acl_access_handler,
+	[F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &f2fs_xattr_acl_default_handler,
+#endif
+	[F2FS_XATTR_INDEX_TRUSTED] = &f2fs_xattr_trusted_handler,
+	[F2FS_XATTR_INDEX_ADVISE] = &f2fs_xattr_advise_handler,
+};
+
+const struct xattr_handler *f2fs_xattr_handlers[] = {
+	&f2fs_xattr_user_handler,
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+	&f2fs_xattr_acl_access_handler,
+	&f2fs_xattr_acl_default_handler,
+#endif
+	&f2fs_xattr_trusted_handler,
+	&f2fs_xattr_advise_handler,
+	NULL,
+};
+
+static inline const struct xattr_handler *f2fs_xattr_handler(int name_index)
+{
+	const struct xattr_handler *handler = NULL;
+
+	if (name_index > 0 && name_index < ARRAY_SIZE(f2fs_xattr_handler_map))
+		handler = f2fs_xattr_handler_map[name_index];
+	return handler;
+}
+
+int f2fs_getxattr(struct inode *inode, int name_index, const char *name,
+		void *buffer, size_t buffer_size)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct f2fs_xattr_entry *entry;
+	struct page *page;
+	void *base_addr;
+	int error = 0, found = 0;
+	size_t value_len, name_len;
+
+	if (name == NULL)
+		return -EINVAL;
+	name_len = strlen(name);
+
+	if (!fi->i_xattr_nid)
+		return -ENODATA;
+
+	page = get_node_page(sbi, fi->i_xattr_nid);
+	base_addr = page_address(page);
+
+	list_for_each_xattr(entry, base_addr) {
+		if (entry->e_name_index != name_index)
+			continue;
+		if (entry->e_name_len != name_len)
+			continue;
+		if (!memcmp(entry->e_name, name, name_len)) {
+			found = 1;
+			break;
+		}
+	}
+	if (!found) {
+		error = -ENODATA;
+		goto cleanup;
+	}
+
+	value_len = le16_to_cpu(entry->e_value_size);
+
+	if (buffer && value_len > buffer_size) {
+		error = -ERANGE;
+		goto cleanup;
+	}
+
+	if (buffer) {
+		char *pval = entry->e_name + entry->e_name_len;
+		memcpy(buffer, pval, value_len);
+	}
+	error = value_len;
+
+cleanup:
+	f2fs_put_page(page, 1);
+	return error;
+}
+
+ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
+{
+	struct inode *inode = dentry->d_inode;
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct f2fs_xattr_entry *entry;
+	struct page *page;
+	void *base_addr;
+	int error = 0;
+	size_t rest = buffer_size;
+
+	if (!fi->i_xattr_nid)
+		return 0;
+
+	page = get_node_page(sbi, fi->i_xattr_nid);
+	base_addr = page_address(page);
+
+	list_for_each_xattr(entry, base_addr) {
+		const struct xattr_handler *handler =
+			f2fs_xattr_handler(entry->e_name_index);
+		size_t size;
+
+		if (!handler)
+			continue;
+
+		size = handler->list(dentry, buffer, rest, entry->e_name,
+				entry->e_name_len, handler->flags);
+		if (buffer && size > rest) {
+			error = -ERANGE;
+			goto cleanup;
+		}
+
+		if (buffer)
+			buffer += size;
+		rest -= size;
+	}
+	error = buffer_size - rest;
+cleanup:
+	f2fs_put_page(page, 1);
+	return error;
+}
+
+int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
+					const void *value, size_t value_len)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct f2fs_xattr_header *header = NULL;
+	struct f2fs_xattr_entry *here, *last;
+	struct page *page;
+	void *base_addr;
+	int error, found, free, newsize;
+	size_t name_len;
+	char *pval;
+	int ilock;
+
+	if (name == NULL)
+		return -EINVAL;
+
+	if (value == NULL)
+		value_len = 0;
+
+	name_len = strlen(name);
+
+	if (name_len > F2FS_NAME_LEN || value_len > MAX_VALUE_LEN)
+		return -ERANGE;
+
+	f2fs_balance_fs(sbi);
+
+	ilock = mutex_lock_op(sbi);
+
+	if (!fi->i_xattr_nid) {
+		/* Allocate new attribute block */
+		struct dnode_of_data dn;
+
+		if (!alloc_nid(sbi, &fi->i_xattr_nid)) {
+			error = -ENOSPC;
+			goto exit;
+		}
+		set_new_dnode(&dn, inode, NULL, NULL, fi->i_xattr_nid);
+		mark_inode_dirty(inode);
+
+		page = new_node_page(&dn, XATTR_NODE_OFFSET);
+		if (IS_ERR(page)) {
+			alloc_nid_failed(sbi, fi->i_xattr_nid);
+			fi->i_xattr_nid = 0;
+			error = PTR_ERR(page);
+			goto exit;
+		}
+
+		alloc_nid_done(sbi, fi->i_xattr_nid);
+		base_addr = page_address(page);
+		header = XATTR_HDR(base_addr);
+		header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC);
+		header->h_refcount = cpu_to_le32(1);
+	} else {
+		/* The inode already has an extended attribute block. */
+		page = get_node_page(sbi, fi->i_xattr_nid);
+		if (IS_ERR(page)) {
+			error = PTR_ERR(page);
+			goto exit;
+		}
+
+		base_addr = page_address(page);
+		header = XATTR_HDR(base_addr);
+	}
+
+	if (le32_to_cpu(header->h_magic) != F2FS_XATTR_MAGIC) {
+		error = -EIO;
+		goto cleanup;
+	}
+
+	/* find entry with wanted name. */
+	found = 0;
+	list_for_each_xattr(here, base_addr) {
+		if (here->e_name_index != name_index)
+			continue;
+		if (here->e_name_len != name_len)
+			continue;
+		if (!memcmp(here->e_name, name, name_len)) {
+			found = 1;
+			break;
+		}
+	}
+
+	last = here;
+
+	while (!IS_XATTR_LAST_ENTRY(last))
+		last = XATTR_NEXT_ENTRY(last);
+
+	newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) +
+			name_len + value_len);
+
+	/* 1. Check space */
+	if (value) {
+		/* If value is NULL, it is remove operation.
+		 * In case of update operation, we caculate free.
+		 */
+		free = MIN_OFFSET - ((char *)last - (char *)header);
+		if (found)
+			free = free - ENTRY_SIZE(here);
+
+		if (free < newsize) {
+			error = -ENOSPC;
+			goto cleanup;
+		}
+	}
+
+	/* 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);
+	}
+
+	/* 3. Write new entry */
+	if (value) {
+		/* Before we come here, old entry is removed.
+		 * We just write new entry. */
+		memset(last, 0, newsize);
+		last->e_name_index = name_index;
+		last->e_name_len = name_len;
+		memcpy(last->e_name, name, name_len);
+		pval = last->e_name + name_len;
+		memcpy(pval, value, value_len);
+		last->e_value_size = cpu_to_le16(value_len);
+	}
+
+	set_page_dirty(page);
+	f2fs_put_page(page, 1);
+
+	if (is_inode_flag_set(fi, FI_ACL_MODE)) {
+		inode->i_mode = fi->i_acl_mode;
+		inode->i_ctime = CURRENT_TIME;
+		clear_inode_flag(fi, FI_ACL_MODE);
+	}
+	update_inode_page(inode);
+	mutex_unlock_op(sbi, ilock);
+
+	return 0;
+cleanup:
+	f2fs_put_page(page, 1);
+exit:
+	mutex_unlock_op(sbi, ilock);
+	return error;
+}

fs/f2fs/xattr.h

@@ -0,0 +1,145 @@
+/*
+ * 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>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#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_PREFIX		"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
+
+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[0];      /* 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 MIN_OFFSET	XATTR_ALIGN(PAGE_SIZE - \
+			sizeof(struct node_footer) - \
+			sizeof(__u32))
+
+#define MAX_VALUE_LEN	(MIN_OFFSET - sizeof(struct f2fs_xattr_header) - \
+			sizeof(struct f2fs_xattr_entry))
+
+/*
+ * On-disk structure of f2fs_xattr
+ * We use only 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_acl_access_handler;
+extern const struct xattr_handler f2fs_xattr_acl_default_handler;
+extern const struct xattr_handler f2fs_xattr_advise_handler;
+
+extern const struct xattr_handler *f2fs_xattr_handlers[];
+
+extern int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
+		const void *value, size_t value_len);
+extern int f2fs_getxattr(struct inode *inode, int name_index, const char *name,
+		void *buffer, size_t buffer_size);
+extern ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer,
+		size_t buffer_size);
+
+#else
+
+#define f2fs_xattr_handlers	NULL
+static inline int f2fs_setxattr(struct inode *inode, int name_index,
+	const char *name, const void *value, size_t value_len)
+{
+	return -EOPNOTSUPP;
+}
+static inline int f2fs_getxattr(struct inode *inode, int name_index,
+		const char *name, void *buffer, size_t buffer_size)
+{
+	return -EOPNOTSUPP;
+}
+static inline ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer,
+		size_t buffer_size)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#endif /* __F2FS_XATTR_H__ */