diff options
Diffstat (limited to 'kernel/fs/f2fs')
-rw-r--r-- | kernel/fs/f2fs/Kconfig | 83 | ||||
-rw-r--r-- | kernel/fs/f2fs/Makefile | 8 | ||||
-rw-r--r-- | kernel/fs/f2fs/acl.c | 410 | ||||
-rw-r--r-- | kernel/fs/f2fs/acl.h | 54 | ||||
-rw-r--r-- | kernel/fs/f2fs/checkpoint.c | 1135 | ||||
-rw-r--r-- | kernel/fs/f2fs/data.c | 1864 | ||||
-rw-r--r-- | kernel/fs/f2fs/debug.c | 413 | ||||
-rw-r--r-- | kernel/fs/f2fs/dir.c | 811 | ||||
-rw-r--r-- | kernel/fs/f2fs/f2fs.h | 1814 | ||||
-rw-r--r-- | kernel/fs/f2fs/file.c | 1172 | ||||
-rw-r--r-- | kernel/fs/f2fs/gc.c | 746 | ||||
-rw-r--r-- | kernel/fs/f2fs/gc.h | 110 | ||||
-rw-r--r-- | kernel/fs/f2fs/hash.c | 104 | ||||
-rw-r--r-- | kernel/fs/f2fs/inline.c | 532 | ||||
-rw-r--r-- | kernel/fs/f2fs/inode.c | 387 | ||||
-rw-r--r-- | kernel/fs/f2fs/namei.c | 832 | ||||
-rw-r--r-- | kernel/fs/f2fs/node.c | 2084 | ||||
-rw-r--r-- | kernel/fs/f2fs/node.h | 416 | ||||
-rw-r--r-- | kernel/fs/f2fs/recovery.c | 575 | ||||
-rw-r--r-- | kernel/fs/f2fs/segment.c | 2307 | ||||
-rw-r--r-- | kernel/fs/f2fs/segment.h | 751 | ||||
-rw-r--r-- | kernel/fs/f2fs/super.c | 1350 | ||||
-rw-r--r-- | kernel/fs/f2fs/trace.c | 159 | ||||
-rw-r--r-- | kernel/fs/f2fs/trace.h | 46 | ||||
-rw-r--r-- | kernel/fs/f2fs/xattr.c | 618 | ||||
-rw-r--r-- | kernel/fs/f2fs/xattr.h | 152 |
26 files changed, 18933 insertions, 0 deletions
diff --git a/kernel/fs/f2fs/Kconfig b/kernel/fs/f2fs/Kconfig new file mode 100644 index 000000000..05f0f663f --- /dev/null +++ b/kernel/fs/f2fs/Kconfig @@ -0,0 +1,83 @@ +config F2FS_FS + tristate "F2FS filesystem support" + 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 filesystem information managed by f2fs currently + - average SIT information about whole segments + - current memory footprint consumed by f2fs. + +config F2FS_FS_XATTR + bool "F2FS extended attributes" + depends on F2FS_FS + default y + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page, 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 + +config F2FS_FS_SECURITY + bool "F2FS Security Labels" + depends on F2FS_FS_XATTR + help + Security labels provide an access control facility to support Linux + Security Models (LSMs) accepted by AppArmor, SELinux, Smack and TOMOYO + Linux. This option enables an extended attribute handler for file + security labels in the f2fs filesystem, so that it requires enabling + the extended attribute support in advance. + + If you are not using a security module, say N. + +config F2FS_CHECK_FS + bool "F2FS consistency checking feature" + depends on F2FS_FS + help + Enables BUG_ONs which check the filesystem consistency in runtime. + + If you want to improve the performance, say N. + +config F2FS_IO_TRACE + bool "F2FS IO tracer" + depends on F2FS_FS + depends on FUNCTION_TRACER + help + F2FS IO trace is based on a function trace, which gathers process + information and block IO patterns in the filesystem level. + + If unsure, say N. diff --git a/kernel/fs/f2fs/Makefile b/kernel/fs/f2fs/Makefile new file mode 100644 index 000000000..d92397731 --- /dev/null +++ b/kernel/fs/f2fs/Makefile @@ -0,0 +1,8 @@ +obj-$(CONFIG_F2FS_FS) += f2fs.o + +f2fs-y := dir.o file.o inode.o namei.o hash.o super.o inline.o +f2fs-y += checkpoint.o gc.o data.o node.o segment.o recovery.o +f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o +f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o +f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o +f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o diff --git a/kernel/fs/f2fs/acl.c b/kernel/fs/f2fs/acl.c new file mode 100644 index 000000000..4320ffab3 --- /dev/null +++ b/kernel/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" + +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_NOFS); + 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_NOFS); + if (!f2fs_acl) + return ERR_PTR(-ENOMEM); + + f2fs_acl->a_version = cpu_to_le32(F2FS_ACL_VERSION); + entry = (struct f2fs_acl_entry *)(f2fs_acl + 1); + + for (i = 0; i < acl->a_count; i++) { + + entry->e_tag = cpu_to_le16(acl->a_entries[i].e_tag); + entry->e_perm = cpu_to_le16(acl->a_entries[i].e_perm); + + switch (acl->a_entries[i].e_tag) { + case ACL_USER: + entry->e_id = cpu_to_le32( + from_kuid(&init_user_ns, + acl->a_entries[i].e_uid)); + entry = (struct f2fs_acl_entry *)((char *)entry + + sizeof(struct f2fs_acl_entry)); + break; + case ACL_GROUP: + entry->e_id = cpu_to_le32( + from_kgid(&init_user_ns, + acl->a_entries[i].e_gid)); + entry = (struct f2fs_acl_entry *)((char *)entry + + sizeof(struct f2fs_acl_entry)); + break; + case ACL_USER_OBJ: + case ACL_GROUP_OBJ: + case ACL_MASK: + case ACL_OTHER: + entry = (struct f2fs_acl_entry *)((char *)entry + + sizeof(struct f2fs_acl_entry_short)); + break; + default: + goto fail; + } + } + *size = f2fs_acl_size(acl->a_count); + return (void *)f2fs_acl; + +fail: + kfree(f2fs_acl); + return ERR_PTR(-EINVAL); +} + +static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type, + struct page *dpage) +{ + int name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT; + void *value = NULL; + struct posix_acl *acl; + int retval; + + if (type == ACL_TYPE_ACCESS) + name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; + + retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dpage); + if (retval > 0) { + value = kmalloc(retval, GFP_F2FS_ZERO); + if (!value) + return ERR_PTR(-ENOMEM); + retval = f2fs_getxattr(inode, name_index, "", value, + retval, dpage); + } + + 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; +} + +struct posix_acl *f2fs_get_acl(struct inode *inode, int type) +{ + return __f2fs_get_acl(inode, type, NULL); +} + +static int __f2fs_set_acl(struct inode *inode, int type, + struct posix_acl *acl, struct page *ipage) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + int name_index; + void *value = NULL; + size_t size = 0; + int error; + + switch (type) { + case ACL_TYPE_ACCESS: + name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; + if (acl) { + error = posix_acl_equiv_mode(acl, &inode->i_mode); + if (error < 0) + return error; + set_acl_inode(fi, inode->i_mode); + if (error == 0) + acl = NULL; + } + 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)) { + clear_inode_flag(fi, FI_ACL_MODE); + return (int)PTR_ERR(value); + } + } + + error = f2fs_setxattr(inode, name_index, "", value, size, ipage, 0); + + kfree(value); + if (!error) + set_cached_acl(inode, type, acl); + + clear_inode_flag(fi, FI_ACL_MODE); + return error; +} + +int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + return __f2fs_set_acl(inode, type, acl, NULL); +} + +/* + * Most part of f2fs_acl_clone, f2fs_acl_create_masq, f2fs_acl_create + * are copied from posix_acl.c + */ +static struct posix_acl *f2fs_acl_clone(const struct posix_acl *acl, + gfp_t flags) +{ + struct posix_acl *clone = NULL; + + if (acl) { + int size = sizeof(struct posix_acl) + acl->a_count * + sizeof(struct posix_acl_entry); + clone = kmemdup(acl, size, flags); + if (clone) + atomic_set(&clone->a_refcount, 1); + } + return clone; +} + +static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) +{ + struct posix_acl_entry *pa, *pe; + struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; + umode_t mode = *mode_p; + int not_equiv = 0; + + /* assert(atomic_read(acl->a_refcount) == 1); */ + + FOREACH_ACL_ENTRY(pa, acl, pe) { + switch(pa->e_tag) { + case ACL_USER_OBJ: + pa->e_perm &= (mode >> 6) | ~S_IRWXO; + mode &= (pa->e_perm << 6) | ~S_IRWXU; + break; + + case ACL_USER: + case ACL_GROUP: + not_equiv = 1; + break; + + case ACL_GROUP_OBJ: + group_obj = pa; + break; + + case ACL_OTHER: + pa->e_perm &= mode | ~S_IRWXO; + mode &= pa->e_perm | ~S_IRWXO; + break; + + case ACL_MASK: + mask_obj = pa; + not_equiv = 1; + break; + + default: + return -EIO; + } + } + + if (mask_obj) { + mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO; + mode &= (mask_obj->e_perm << 3) | ~S_IRWXG; + } else { + if (!group_obj) + return -EIO; + group_obj->e_perm &= (mode >> 3) | ~S_IRWXO; + mode &= (group_obj->e_perm << 3) | ~S_IRWXG; + } + + *mode_p = (*mode_p & ~S_IRWXUGO) | mode; + return not_equiv; +} + +static int f2fs_acl_create(struct inode *dir, umode_t *mode, + struct posix_acl **default_acl, struct posix_acl **acl, + struct page *dpage) +{ + struct posix_acl *p; + int ret; + + if (S_ISLNK(*mode) || !IS_POSIXACL(dir)) + goto no_acl; + + p = __f2fs_get_acl(dir, ACL_TYPE_DEFAULT, dpage); + if (IS_ERR(p)) { + if (p == ERR_PTR(-EOPNOTSUPP)) + goto apply_umask; + return PTR_ERR(p); + } + + if (!p) + goto apply_umask; + + *acl = f2fs_acl_clone(p, GFP_NOFS); + if (!*acl) + goto no_mem; + + ret = f2fs_acl_create_masq(*acl, mode); + if (ret < 0) + goto no_mem_clone; + + if (ret == 0) { + posix_acl_release(*acl); + *acl = NULL; + } + + if (!S_ISDIR(*mode)) { + posix_acl_release(p); + *default_acl = NULL; + } else { + *default_acl = p; + } + return 0; + +apply_umask: + *mode &= ~current_umask(); +no_acl: + *default_acl = NULL; + *acl = NULL; + return 0; + +no_mem_clone: + posix_acl_release(*acl); +no_mem: + posix_acl_release(p); + return -ENOMEM; +} + +int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage, + struct page *dpage) +{ + struct posix_acl *default_acl = NULL, *acl = NULL; + int error = 0; + + error = f2fs_acl_create(dir, &inode->i_mode, &default_acl, &acl, dpage); + if (error) + return error; + + if (default_acl) { + error = __f2fs_set_acl(inode, ACL_TYPE_DEFAULT, default_acl, + ipage); + posix_acl_release(default_acl); + } + if (acl) { + if (!error) + error = __f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl, + ipage); + posix_acl_release(acl); + } + + return error; +} diff --git a/kernel/fs/f2fs/acl.h b/kernel/fs/f2fs/acl.h new file mode 100644 index 000000000..997ca8edb --- /dev/null +++ b/kernel/fs/f2fs/acl.h @@ -0,0 +1,54 @@ +/* + * 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 *, int); +extern int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int f2fs_init_acl(struct inode *, struct inode *, struct page *, + struct page *); +#else +#define f2fs_check_acl NULL +#define f2fs_get_acl NULL +#define f2fs_set_acl NULL + +static inline int f2fs_init_acl(struct inode *inode, struct inode *dir, + struct page *ipage, struct page *dpage) +{ + return 0; +} +#endif +#endif /* __F2FS_ACL_H__ */ diff --git a/kernel/fs/f2fs/checkpoint.c b/kernel/fs/f2fs/checkpoint.c new file mode 100644 index 000000000..a5e17a2a0 --- /dev/null +++ b/kernel/fs/f2fs/checkpoint.c @@ -0,0 +1,1135 @@ +/* + * 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.h" +#include <trace/events/f2fs.h> + +static struct kmem_cache *ino_entry_slab; +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 = META_MAPPING(sbi); + struct page *page = NULL; +repeat: + page = grab_cache_page(mapping, index); + if (!page) { + cond_resched(); + goto repeat; + } + f2fs_wait_on_page_writeback(page, META); + 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 = META_MAPPING(sbi); + struct page *page; + struct f2fs_io_info fio = { + .type = META, + .rw = READ_SYNC | REQ_META | REQ_PRIO, + .blk_addr = index, + }; +repeat: + page = grab_cache_page(mapping, index); + if (!page) { + cond_resched(); + goto repeat; + } + if (PageUptodate(page)) + goto out; + + if (f2fs_submit_page_bio(sbi, page, &fio)) + goto repeat; + + lock_page(page); + if (unlikely(page->mapping != mapping)) { + f2fs_put_page(page, 1); + goto repeat; + } +out: + return page; +} + +static inline bool is_valid_blkaddr(struct f2fs_sb_info *sbi, + block_t blkaddr, int type) +{ + switch (type) { + case META_NAT: + break; + case META_SIT: + if (unlikely(blkaddr >= SIT_BLK_CNT(sbi))) + return false; + break; + case META_SSA: + if (unlikely(blkaddr >= MAIN_BLKADDR(sbi) || + blkaddr < SM_I(sbi)->ssa_blkaddr)) + return false; + break; + case META_CP: + if (unlikely(blkaddr >= SIT_I(sbi)->sit_base_addr || + blkaddr < __start_cp_addr(sbi))) + return false; + break; + case META_POR: + if (unlikely(blkaddr >= MAX_BLKADDR(sbi) || + blkaddr < MAIN_BLKADDR(sbi))) + return false; + break; + default: + BUG(); + } + + return true; +} + +/* + * Readahead CP/NAT/SIT/SSA pages + */ +int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type) +{ + block_t prev_blk_addr = 0; + struct page *page; + block_t blkno = start; + struct f2fs_io_info fio = { + .type = META, + .rw = READ_SYNC | REQ_META | REQ_PRIO + }; + + for (; nrpages-- > 0; blkno++) { + + if (!is_valid_blkaddr(sbi, blkno, type)) + goto out; + + switch (type) { + case META_NAT: + if (unlikely(blkno >= + NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid))) + blkno = 0; + /* get nat block addr */ + fio.blk_addr = current_nat_addr(sbi, + blkno * NAT_ENTRY_PER_BLOCK); + break; + case META_SIT: + /* get sit block addr */ + fio.blk_addr = current_sit_addr(sbi, + blkno * SIT_ENTRY_PER_BLOCK); + if (blkno != start && prev_blk_addr + 1 != fio.blk_addr) + goto out; + prev_blk_addr = fio.blk_addr; + break; + case META_SSA: + case META_CP: + case META_POR: + fio.blk_addr = blkno; + break; + default: + BUG(); + } + + page = grab_cache_page(META_MAPPING(sbi), fio.blk_addr); + if (!page) + continue; + if (PageUptodate(page)) { + f2fs_put_page(page, 1); + continue; + } + + f2fs_submit_page_mbio(sbi, page, &fio); + f2fs_put_page(page, 0); + } +out: + f2fs_submit_merged_bio(sbi, META, READ); + return blkno - start; +} + +void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) +{ + struct page *page; + bool readahead = false; + + page = find_get_page(META_MAPPING(sbi), index); + if (!page || (page && !PageUptodate(page))) + readahead = true; + f2fs_put_page(page, 0); + + if (readahead) + ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR); +} + +static int f2fs_write_meta_page(struct page *page, + struct writeback_control *wbc) +{ + struct f2fs_sb_info *sbi = F2FS_P_SB(page); + + trace_f2fs_writepage(page, META); + + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + goto redirty_out; + if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0)) + goto redirty_out; + if (unlikely(f2fs_cp_error(sbi))) + goto redirty_out; + + f2fs_wait_on_page_writeback(page, META); + write_meta_page(sbi, page); + dec_page_count(sbi, F2FS_DIRTY_META); + unlock_page(page); + + if (wbc->for_reclaim) + f2fs_submit_merged_bio(sbi, META, WRITE); + return 0; + +redirty_out: + redirty_page_for_writepage(wbc, page); + return AOP_WRITEPAGE_ACTIVATE; +} + +static int f2fs_write_meta_pages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); + long diff, written; + + trace_f2fs_writepages(mapping->host, wbc, META); + + /* collect a number of dirty meta pages and write together */ + if (wbc->for_kupdate || + get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META)) + goto skip_write; + + /* if mounting is failed, skip writing node pages */ + mutex_lock(&sbi->cp_mutex); + diff = nr_pages_to_write(sbi, META, wbc); + written = sync_meta_pages(sbi, META, wbc->nr_to_write); + mutex_unlock(&sbi->cp_mutex); + wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff); + return 0; + +skip_write: + wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_META); + return 0; +} + +long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, + long nr_to_write) +{ + struct address_space *mapping = META_MAPPING(sbi); + 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 (unlikely(nr_pages == 0)) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + lock_page(page); + + if (unlikely(page->mapping != mapping)) { +continue_unlock: + unlock_page(page); + continue; + } + if (!PageDirty(page)) { + /* someone wrote it for us */ + goto continue_unlock; + } + + if (!clear_page_dirty_for_io(page)) + goto continue_unlock; + + if (mapping->a_ops->writepage(page, &wbc)) { + unlock_page(page); + break; + } + nwritten++; + if (unlikely(nwritten >= nr_to_write)) + break; + } + pagevec_release(&pvec); + cond_resched(); + } + + if (nwritten) + f2fs_submit_merged_bio(sbi, type, WRITE); + + return nwritten; +} + +static int f2fs_set_meta_page_dirty(struct page *page) +{ + trace_f2fs_set_page_dirty(page, META); + + SetPageUptodate(page); + if (!PageDirty(page)) { + __set_page_dirty_nobuffers(page); + inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META); + SetPagePrivate(page); + f2fs_trace_pid(page); + 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, + .invalidatepage = f2fs_invalidate_page, + .releasepage = f2fs_release_page, +}; + +static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) +{ + struct inode_management *im = &sbi->im[type]; + struct ino_entry *e; +retry: + if (radix_tree_preload(GFP_NOFS)) { + cond_resched(); + goto retry; + } + + spin_lock(&im->ino_lock); + + e = radix_tree_lookup(&im->ino_root, ino); + if (!e) { + e = kmem_cache_alloc(ino_entry_slab, GFP_ATOMIC); + if (!e) { + spin_unlock(&im->ino_lock); + radix_tree_preload_end(); + goto retry; + } + if (radix_tree_insert(&im->ino_root, ino, e)) { + spin_unlock(&im->ino_lock); + kmem_cache_free(ino_entry_slab, e); + radix_tree_preload_end(); + goto retry; + } + memset(e, 0, sizeof(struct ino_entry)); + e->ino = ino; + + list_add_tail(&e->list, &im->ino_list); + if (type != ORPHAN_INO) + im->ino_num++; + } + spin_unlock(&im->ino_lock); + radix_tree_preload_end(); +} + +static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) +{ + struct inode_management *im = &sbi->im[type]; + struct ino_entry *e; + + spin_lock(&im->ino_lock); + e = radix_tree_lookup(&im->ino_root, ino); + if (e) { + list_del(&e->list); + radix_tree_delete(&im->ino_root, ino); + im->ino_num--; + spin_unlock(&im->ino_lock); + kmem_cache_free(ino_entry_slab, e); + return; + } + spin_unlock(&im->ino_lock); +} + +void add_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type) +{ + /* add new dirty ino entry into list */ + __add_ino_entry(sbi, ino, type); +} + +void remove_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type) +{ + /* remove dirty ino entry from list */ + __remove_ino_entry(sbi, ino, type); +} + +/* mode should be APPEND_INO or UPDATE_INO */ +bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) +{ + struct inode_management *im = &sbi->im[mode]; + struct ino_entry *e; + + spin_lock(&im->ino_lock); + e = radix_tree_lookup(&im->ino_root, ino); + spin_unlock(&im->ino_lock); + return e ? true : false; +} + +void release_dirty_inode(struct f2fs_sb_info *sbi) +{ + struct ino_entry *e, *tmp; + int i; + + for (i = APPEND_INO; i <= UPDATE_INO; i++) { + struct inode_management *im = &sbi->im[i]; + + spin_lock(&im->ino_lock); + list_for_each_entry_safe(e, tmp, &im->ino_list, list) { + list_del(&e->list); + radix_tree_delete(&im->ino_root, e->ino); + kmem_cache_free(ino_entry_slab, e); + im->ino_num--; + } + spin_unlock(&im->ino_lock); + } +} + +int acquire_orphan_inode(struct f2fs_sb_info *sbi) +{ + struct inode_management *im = &sbi->im[ORPHAN_INO]; + int err = 0; + + spin_lock(&im->ino_lock); + if (unlikely(im->ino_num >= sbi->max_orphans)) + err = -ENOSPC; + else + im->ino_num++; + spin_unlock(&im->ino_lock); + + return err; +} + +void release_orphan_inode(struct f2fs_sb_info *sbi) +{ + struct inode_management *im = &sbi->im[ORPHAN_INO]; + + spin_lock(&im->ino_lock); + f2fs_bug_on(sbi, im->ino_num == 0); + im->ino_num--; + spin_unlock(&im->ino_lock); +} + +void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +{ + /* add new orphan ino entry into list */ + __add_ino_entry(sbi, ino, ORPHAN_INO); +} + +void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +{ + /* remove orphan entry from orphan list */ + __remove_ino_entry(sbi, ino, ORPHAN_INO); +} + +static void recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct inode *inode = f2fs_iget(sbi->sb, ino); + f2fs_bug_on(sbi, IS_ERR(inode)); + clear_nlink(inode); + + /* truncate all the data during iput */ + iput(inode); +} + +void recover_orphan_inodes(struct f2fs_sb_info *sbi) +{ + block_t start_blk, orphan_blocks, i, j; + + if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG)) + return; + + set_sbi_flag(sbi, SBI_POR_DOING); + + start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi); + orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi); + + ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP); + + for (i = 0; i < orphan_blocks; 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); + clear_sbi_flag(sbi, SBI_POR_DOING); + return; +} + +static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) +{ + struct list_head *head; + struct f2fs_orphan_block *orphan_blk = NULL; + unsigned int nentries = 0; + unsigned short index; + unsigned short orphan_blocks; + struct page *page = NULL; + struct ino_entry *orphan = NULL; + struct inode_management *im = &sbi->im[ORPHAN_INO]; + + orphan_blocks = GET_ORPHAN_BLOCKS(im->ino_num); + + for (index = 0; index < orphan_blocks; index++) + grab_meta_page(sbi, start_blk + index); + + index = 1; + spin_lock(&im->ino_lock); + head = &im->ino_list; + + /* loop for each orphan inode entry and write them in Jornal block */ + list_for_each_entry(orphan, head, list) { + if (!page) { + page = find_get_page(META_MAPPING(sbi), start_blk++); + f2fs_bug_on(sbi, !page); + orphan_blk = + (struct f2fs_orphan_block *)page_address(page); + memset(orphan_blk, 0, sizeof(*orphan_blk)); + f2fs_put_page(page, 0); + } + + orphan_blk->ino[nentries++] = cpu_to_le32(orphan->ino); + + 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++; + nentries = 0; + page = NULL; + } + } + + if (page) { + 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); + } + + spin_unlock(&im->ino_lock); +} + +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; + size_t crc_offset; + __u32 crc = 0; + + /* 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 = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset))); + if (!f2fs_crc_valid(crc, cp_block, crc_offset)) + goto invalid_cp1; + + pre_version = cur_cp_version(cp_block); + + /* 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 = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset))); + if (!f2fs_crc_valid(crc, cp_block, crc_offset)) + goto invalid_cp2; + + cur_version = cur_cp_version(cp_block); + + 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; + unsigned int cp_blks = 1 + __cp_payload(sbi); + block_t cp_blk_no; + int i; + + sbi->ckpt = kzalloc(cp_blks * 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 += ((unsigned long long)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); + + if (cp_blks <= 1) + goto done; + + cp_blk_no = le32_to_cpu(fsb->cp_blkaddr); + if (cur_page == cp2) + cp_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg); + + for (i = 1; i < cp_blks; i++) { + void *sit_bitmap_ptr; + unsigned char *ckpt = (unsigned char *)sbi->ckpt; + + cur_page = get_meta_page(sbi, cp_blk_no + i); + sit_bitmap_ptr = page_address(cur_page); + memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size); + f2fs_put_page(cur_page, 1); + } +done: + f2fs_put_page(cp1, 1); + f2fs_put_page(cp2, 1); + return 0; + +fail_no_cp: + kfree(sbi->ckpt); + return -EINVAL; +} + +static int __add_dirty_inode(struct inode *inode, struct inode_entry *new) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) + return -EEXIST; + + set_inode_flag(F2FS_I(inode), FI_DIRTY_DIR); + F2FS_I(inode)->dirty_dir = new; + list_add_tail(&new->list, &sbi->dir_inode_list); + stat_inc_dirty_dir(sbi); + return 0; +} + +void update_dirty_page(struct inode *inode, struct page *page) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct inode_entry *new; + int ret = 0; + + if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode)) + return; + + if (!S_ISDIR(inode->i_mode)) { + inode_inc_dirty_pages(inode); + goto out; + } + + new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); + new->inode = inode; + INIT_LIST_HEAD(&new->list); + + spin_lock(&sbi->dir_inode_lock); + ret = __add_dirty_inode(inode, new); + inode_inc_dirty_pages(inode); + spin_unlock(&sbi->dir_inode_lock); + + if (ret) + kmem_cache_free(inode_entry_slab, new); +out: + SetPagePrivate(page); + f2fs_trace_pid(page); +} + +void add_dirty_dir_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct inode_entry *new = + f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); + int ret = 0; + + new->inode = inode; + INIT_LIST_HEAD(&new->list); + + spin_lock(&sbi->dir_inode_lock); + ret = __add_dirty_inode(inode, new); + spin_unlock(&sbi->dir_inode_lock); + + if (ret) + kmem_cache_free(inode_entry_slab, new); +} + +void remove_dirty_dir_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct inode_entry *entry; + + if (!S_ISDIR(inode->i_mode)) + return; + + spin_lock(&sbi->dir_inode_lock); + if (get_dirty_pages(inode) || + !is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) { + spin_unlock(&sbi->dir_inode_lock); + return; + } + + entry = F2FS_I(inode)->dirty_dir; + list_del(&entry->list); + F2FS_I(inode)->dirty_dir = NULL; + clear_inode_flag(F2FS_I(inode), FI_DIRTY_DIR); + stat_dec_dirty_dir(sbi); + spin_unlock(&sbi->dir_inode_lock); + kmem_cache_free(inode_entry_slab, entry); + + /* Only from the recovery routine */ + if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) { + clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT); + iput(inode); + } +} + +void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi) +{ + struct list_head *head; + struct inode_entry *entry; + struct inode *inode; +retry: + if (unlikely(f2fs_cp_error(sbi))) + return; + + spin_lock(&sbi->dir_inode_lock); + + head = &sbi->dir_inode_list; + if (list_empty(head)) { + spin_unlock(&sbi->dir_inode_lock); + return; + } + entry = list_entry(head->next, struct inode_entry, list); + inode = igrab(entry->inode); + spin_unlock(&sbi->dir_inode_lock); + if (inode) { + filemap_fdatawrite(inode->i_mapping); + iput(inode); + } else { + /* + * We should submit bio, since it exists several + * wribacking dentry pages in the freeing inode. + */ + f2fs_submit_merged_bio(sbi, DATA, WRITE); + cond_resched(); + } + goto retry; +} + +/* + * Freeze all the FS-operations for checkpoint. + */ +static int 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; + int err = 0; + + blk_start_plug(&plug); + +retry_flush_dents: + f2fs_lock_all(sbi); + /* write all the dirty dentry pages */ + if (get_pages(sbi, F2FS_DIRTY_DENTS)) { + f2fs_unlock_all(sbi); + sync_dirty_dir_inodes(sbi); + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; + goto out; + } + goto retry_flush_dents; + } + + /* + * POR: we should ensure that there are no dirty node pages + * until finishing nat/sit flush. + */ +retry_flush_nodes: + down_write(&sbi->node_write); + + if (get_pages(sbi, F2FS_DIRTY_NODES)) { + up_write(&sbi->node_write); + sync_node_pages(sbi, 0, &wbc); + if (unlikely(f2fs_cp_error(sbi))) { + f2fs_unlock_all(sbi); + err = -EIO; + goto out; + } + goto retry_flush_nodes; + } +out: + blk_finish_plug(&plug); + return err; +} + +static void unblock_operations(struct f2fs_sb_info *sbi) +{ + up_write(&sbi->node_write); + f2fs_unlock_all(sbi); +} + +static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi) +{ + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE); + + if (!get_pages(sbi, F2FS_WRITEBACK)) + break; + + io_schedule(); + } + finish_wait(&sbi->cp_wait, &wait); +} + +static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); + struct f2fs_nm_info *nm_i = NM_I(sbi); + unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num; + nid_t last_nid = nm_i->next_scan_nid; + block_t start_blk; + struct page *cp_page; + unsigned int data_sum_blocks, orphan_blocks; + __u32 crc32 = 0; + void *kaddr; + int i; + int cp_payload_blks = __cp_payload(sbi); + + /* + * This avoids to conduct wrong roll-forward operations and uses + * metapages, so should be called prior to sync_meta_pages below. + */ + discard_next_dnode(sbi, NEXT_FREE_BLKADDR(sbi, curseg)); + + /* Flush all the NAT/SIT pages */ + while (get_pages(sbi, F2FS_DIRTY_META)) { + sync_meta_pages(sbi, META, LONG_MAX); + if (unlikely(f2fs_cp_error(sbi))) + return; + } + + 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 < NR_CURSEG_NODE_TYPE; 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 < NR_CURSEG_DATA_TYPE; 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, false); + if (data_sum_blocks < NR_CURSEG_DATA_TYPE) + set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); + else + clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); + + orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num); + ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks + + orphan_blocks); + + if (__remain_node_summaries(cpc->reason)) + ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+ + cp_payload_blks + data_sum_blocks + + orphan_blocks + NR_CURSEG_NODE_TYPE); + else + ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS + + cp_payload_blks + data_sum_blocks + + orphan_blocks); + + if (cpc->reason == CP_UMOUNT) + set_ckpt_flags(ckpt, CP_UMOUNT_FLAG); + else + clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG); + + if (cpc->reason == CP_FASTBOOT) + set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG); + else + clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG); + + if (orphan_num) + set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); + else + clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); + + if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) + set_ckpt_flags(ckpt, CP_FSCK_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, F2FS_BLKSIZE); + set_page_dirty(cp_page); + f2fs_put_page(cp_page, 1); + + for (i = 1; i < 1 + cp_payload_blks; i++) { + cp_page = grab_meta_page(sbi, start_blk++); + kaddr = page_address(cp_page); + memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE, F2FS_BLKSIZE); + set_page_dirty(cp_page); + f2fs_put_page(cp_page, 1); + } + + if (orphan_num) { + write_orphan_inodes(sbi, start_blk); + start_blk += orphan_blocks; + } + + write_data_summaries(sbi, start_blk); + start_blk += data_sum_blocks; + if (__remain_node_summaries(cpc->reason)) { + 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, F2FS_BLKSIZE); + set_page_dirty(cp_page); + f2fs_put_page(cp_page, 1); + + /* wait for previous submitted node/meta pages writeback */ + wait_on_all_pages_writeback(sbi); + + if (unlikely(f2fs_cp_error(sbi))) + return; + + filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LONG_MAX); + filemap_fdatawait_range(META_MAPPING(sbi), 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); + + /* wait for previous submitted meta pages writeback */ + wait_on_all_pages_writeback(sbi); + + release_dirty_inode(sbi); + + if (unlikely(f2fs_cp_error(sbi))) + return; + + clear_prefree_segments(sbi); + clear_sbi_flag(sbi, SBI_IS_DIRTY); +} + +/* + * We guarantee that this checkpoint procedure will not fail. + */ +void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + unsigned long long ckpt_ver; + + mutex_lock(&sbi->cp_mutex); + + if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) && + (cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC)) + goto out; + if (unlikely(f2fs_cp_error(sbi))) + goto out; + if (f2fs_readonly(sbi->sb)) + goto out; + + trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops"); + + if (block_operations(sbi)) + goto out; + + trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops"); + + f2fs_submit_merged_bio(sbi, DATA, WRITE); + f2fs_submit_merged_bio(sbi, NODE, WRITE); + f2fs_submit_merged_bio(sbi, META, WRITE); + + /* + * update checkpoint pack index + * Increase the version number so that + * SIT entries and seg summaries are written at correct place + */ + ckpt_ver = cur_cp_version(ckpt); + 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, cpc); + + /* unlock all the fs_lock[] in do_checkpoint() */ + do_checkpoint(sbi, cpc); + + unblock_operations(sbi); + stat_inc_cp_count(sbi->stat_info); + + if (cpc->reason == CP_RECOVERY) + f2fs_msg(sbi->sb, KERN_NOTICE, + "checkpoint: version = %llx", ckpt_ver); +out: + mutex_unlock(&sbi->cp_mutex); + trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint"); +} + +void init_ino_entry_info(struct f2fs_sb_info *sbi) +{ + int i; + + for (i = 0; i < MAX_INO_ENTRY; i++) { + struct inode_management *im = &sbi->im[i]; + + INIT_RADIX_TREE(&im->ino_root, GFP_ATOMIC); + spin_lock_init(&im->ino_lock); + INIT_LIST_HEAD(&im->ino_list); + im->ino_num = 0; + } + + sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS - + NR_CURSEG_TYPE - __cp_payload(sbi)) * + F2FS_ORPHANS_PER_BLOCK; +} + +int __init create_checkpoint_caches(void) +{ + ino_entry_slab = f2fs_kmem_cache_create("f2fs_ino_entry", + sizeof(struct ino_entry)); + if (!ino_entry_slab) + return -ENOMEM; + inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry", + sizeof(struct inode_entry)); + if (!inode_entry_slab) { + kmem_cache_destroy(ino_entry_slab); + return -ENOMEM; + } + return 0; +} + +void destroy_checkpoint_caches(void) +{ + kmem_cache_destroy(ino_entry_slab); + kmem_cache_destroy(inode_entry_slab); +} diff --git a/kernel/fs/f2fs/data.c b/kernel/fs/f2fs/data.c new file mode 100644 index 000000000..1e1aae669 --- /dev/null +++ b/kernel/fs/f2fs/data.c @@ -0,0 +1,1864 @@ +/* + * 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/writeback.h> +#include <linux/backing-dev.h> +#include <linux/blkdev.h> +#include <linux/bio.h> +#include <linux/prefetch.h> +#include <linux/uio.h> + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include "trace.h" +#include <trace/events/f2fs.h> + +static struct kmem_cache *extent_tree_slab; +static struct kmem_cache *extent_node_slab; + +static void f2fs_read_end_io(struct bio *bio, int err) +{ + struct bio_vec *bvec; + int i; + + bio_for_each_segment_all(bvec, bio, i) { + struct page *page = bvec->bv_page; + + if (!err) { + SetPageUptodate(page); + } else { + ClearPageUptodate(page); + SetPageError(page); + } + unlock_page(page); + } + bio_put(bio); +} + +static void f2fs_write_end_io(struct bio *bio, int err) +{ + struct f2fs_sb_info *sbi = bio->bi_private; + struct bio_vec *bvec; + int i; + + bio_for_each_segment_all(bvec, bio, i) { + struct page *page = bvec->bv_page; + + if (unlikely(err)) { + set_page_dirty(page); + set_bit(AS_EIO, &page->mapping->flags); + f2fs_stop_checkpoint(sbi); + } + end_page_writeback(page); + dec_page_count(sbi, F2FS_WRITEBACK); + } + + if (!get_pages(sbi, F2FS_WRITEBACK) && + !list_empty(&sbi->cp_wait.task_list)) + wake_up(&sbi->cp_wait); + + bio_put(bio); +} + +/* + * Low-level block read/write IO operations. + */ +static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr, + int npages, bool is_read) +{ + struct bio *bio; + + /* No failure on bio allocation */ + bio = bio_alloc(GFP_NOIO, npages); + + bio->bi_bdev = sbi->sb->s_bdev; + bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr); + bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io; + bio->bi_private = sbi; + + return bio; +} + +static void __submit_merged_bio(struct f2fs_bio_info *io) +{ + struct f2fs_io_info *fio = &io->fio; + + if (!io->bio) + return; + + if (is_read_io(fio->rw)) + trace_f2fs_submit_read_bio(io->sbi->sb, fio, io->bio); + else + trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio); + + submit_bio(fio->rw, io->bio); + io->bio = NULL; +} + +void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, + enum page_type type, int rw) +{ + enum page_type btype = PAGE_TYPE_OF_BIO(type); + struct f2fs_bio_info *io; + + io = is_read_io(rw) ? &sbi->read_io : &sbi->write_io[btype]; + + down_write(&io->io_rwsem); + + /* change META to META_FLUSH in the checkpoint procedure */ + if (type >= META_FLUSH) { + io->fio.type = META_FLUSH; + if (test_opt(sbi, NOBARRIER)) + io->fio.rw = WRITE_FLUSH | REQ_META | REQ_PRIO; + else + io->fio.rw = WRITE_FLUSH_FUA | REQ_META | REQ_PRIO; + } + __submit_merged_bio(io); + up_write(&io->io_rwsem); +} + +/* + * Fill the locked page with data located in the block address. + * Return unlocked page. + */ +int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page, + struct f2fs_io_info *fio) +{ + struct bio *bio; + + trace_f2fs_submit_page_bio(page, fio); + f2fs_trace_ios(page, fio, 0); + + /* Allocate a new bio */ + bio = __bio_alloc(sbi, fio->blk_addr, 1, is_read_io(fio->rw)); + + if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { + bio_put(bio); + f2fs_put_page(page, 1); + return -EFAULT; + } + + submit_bio(fio->rw, bio); + return 0; +} + +void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page, + struct f2fs_io_info *fio) +{ + enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); + struct f2fs_bio_info *io; + bool is_read = is_read_io(fio->rw); + + io = is_read ? &sbi->read_io : &sbi->write_io[btype]; + + verify_block_addr(sbi, fio->blk_addr); + + down_write(&io->io_rwsem); + + if (!is_read) + inc_page_count(sbi, F2FS_WRITEBACK); + + if (io->bio && (io->last_block_in_bio != fio->blk_addr - 1 || + io->fio.rw != fio->rw)) + __submit_merged_bio(io); +alloc_new: + if (io->bio == NULL) { + int bio_blocks = MAX_BIO_BLOCKS(sbi); + + io->bio = __bio_alloc(sbi, fio->blk_addr, bio_blocks, is_read); + io->fio = *fio; + } + + if (bio_add_page(io->bio, page, PAGE_CACHE_SIZE, 0) < + PAGE_CACHE_SIZE) { + __submit_merged_bio(io); + goto alloc_new; + } + + io->last_block_in_bio = fio->blk_addr; + f2fs_trace_ios(page, fio, 0); + + up_write(&io->io_rwsem); + trace_f2fs_submit_page_mbio(page, fio); +} + +/* + * Lock ordering for the change of data block address: + * ->data_page + * ->node_page + * update block addresses in the node page + */ +void set_data_blkaddr(struct dnode_of_data *dn) +{ + struct f2fs_node *rn; + __le32 *addr_array; + struct page *node_page = dn->node_page; + unsigned int ofs_in_node = dn->ofs_in_node; + + f2fs_wait_on_page_writeback(node_page, NODE); + + rn = F2FS_NODE(node_page); + + /* Get physical address of data block */ + addr_array = blkaddr_in_node(rn); + addr_array[ofs_in_node] = cpu_to_le32(dn->data_blkaddr); + set_page_dirty(node_page); +} + +int reserve_new_block(struct dnode_of_data *dn) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + + if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC))) + return -EPERM; + if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1))) + return -ENOSPC; + + trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node); + + dn->data_blkaddr = NEW_ADDR; + set_data_blkaddr(dn); + mark_inode_dirty(dn->inode); + sync_inode_page(dn); + return 0; +} + +int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index) +{ + bool need_put = dn->inode_page ? false : true; + int err; + + err = get_dnode_of_data(dn, index, ALLOC_NODE); + if (err) + return err; + + if (dn->data_blkaddr == NULL_ADDR) + err = reserve_new_block(dn); + if (err || need_put) + f2fs_put_dnode(dn); + return err; +} + +static void f2fs_map_bh(struct super_block *sb, pgoff_t pgofs, + struct extent_info *ei, struct buffer_head *bh_result) +{ + unsigned int blkbits = sb->s_blocksize_bits; + size_t max_size = bh_result->b_size; + size_t mapped_size; + + clear_buffer_new(bh_result); + map_bh(bh_result, sb, ei->blk + pgofs - ei->fofs); + mapped_size = (ei->fofs + ei->len - pgofs) << blkbits; + bh_result->b_size = min(max_size, mapped_size); +} + +static bool lookup_extent_info(struct inode *inode, pgoff_t pgofs, + struct extent_info *ei) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + pgoff_t start_fofs, end_fofs; + block_t start_blkaddr; + + read_lock(&fi->ext_lock); + if (fi->ext.len == 0) { + read_unlock(&fi->ext_lock); + return false; + } + + stat_inc_total_hit(inode->i_sb); + + start_fofs = fi->ext.fofs; + end_fofs = fi->ext.fofs + fi->ext.len - 1; + start_blkaddr = fi->ext.blk; + + if (pgofs >= start_fofs && pgofs <= end_fofs) { + *ei = fi->ext; + stat_inc_read_hit(inode->i_sb); + read_unlock(&fi->ext_lock); + return true; + } + read_unlock(&fi->ext_lock); + return false; +} + +static bool update_extent_info(struct inode *inode, pgoff_t fofs, + block_t blkaddr) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + pgoff_t start_fofs, end_fofs; + block_t start_blkaddr, end_blkaddr; + int need_update = true; + + write_lock(&fi->ext_lock); + + start_fofs = fi->ext.fofs; + end_fofs = fi->ext.fofs + fi->ext.len - 1; + start_blkaddr = fi->ext.blk; + end_blkaddr = fi->ext.blk + 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 (blkaddr != NULL_ADDR) { + fi->ext.fofs = fofs; + fi->ext.blk = blkaddr; + fi->ext.len = 1; + } + goto end_update; + } + + /* Front merge */ + if (fofs == start_fofs - 1 && blkaddr == start_blkaddr - 1) { + fi->ext.fofs--; + fi->ext.blk--; + fi->ext.len++; + goto end_update; + } + + /* Back merge */ + if (fofs == end_fofs + 1 && blkaddr == 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 = start_blkaddr + fofs - start_fofs + 1; + fi->ext.len -= fofs - start_fofs + 1; + } + } else { + need_update = false; + } + + /* Finally, if the extent is very fragmented, let's drop the cache. */ + if (fi->ext.len < F2FS_MIN_EXTENT_LEN) { + fi->ext.len = 0; + set_inode_flag(fi, FI_NO_EXTENT); + need_update = true; + } +end_update: + write_unlock(&fi->ext_lock); + return need_update; +} + +static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_info *ei, + struct rb_node *parent, struct rb_node **p) +{ + struct extent_node *en; + + en = kmem_cache_alloc(extent_node_slab, GFP_ATOMIC); + if (!en) + return NULL; + + en->ei = *ei; + INIT_LIST_HEAD(&en->list); + + rb_link_node(&en->rb_node, parent, p); + rb_insert_color(&en->rb_node, &et->root); + et->count++; + atomic_inc(&sbi->total_ext_node); + return en; +} + +static void __detach_extent_node(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_node *en) +{ + rb_erase(&en->rb_node, &et->root); + et->count--; + atomic_dec(&sbi->total_ext_node); + + if (et->cached_en == en) + et->cached_en = NULL; +} + +static struct extent_tree *__find_extent_tree(struct f2fs_sb_info *sbi, + nid_t ino) +{ + struct extent_tree *et; + + down_read(&sbi->extent_tree_lock); + et = radix_tree_lookup(&sbi->extent_tree_root, ino); + if (!et) { + up_read(&sbi->extent_tree_lock); + return NULL; + } + atomic_inc(&et->refcount); + up_read(&sbi->extent_tree_lock); + + return et; +} + +static struct extent_tree *__grab_extent_tree(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et; + nid_t ino = inode->i_ino; + + down_write(&sbi->extent_tree_lock); + et = radix_tree_lookup(&sbi->extent_tree_root, ino); + if (!et) { + et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS); + f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et); + memset(et, 0, sizeof(struct extent_tree)); + et->ino = ino; + et->root = RB_ROOT; + et->cached_en = NULL; + rwlock_init(&et->lock); + atomic_set(&et->refcount, 0); + et->count = 0; + sbi->total_ext_tree++; + } + atomic_inc(&et->refcount); + up_write(&sbi->extent_tree_lock); + + return et; +} + +static struct extent_node *__lookup_extent_tree(struct extent_tree *et, + unsigned int fofs) +{ + struct rb_node *node = et->root.rb_node; + struct extent_node *en; + + if (et->cached_en) { + struct extent_info *cei = &et->cached_en->ei; + + if (cei->fofs <= fofs && cei->fofs + cei->len > fofs) + return et->cached_en; + } + + while (node) { + en = rb_entry(node, struct extent_node, rb_node); + + if (fofs < en->ei.fofs) { + node = node->rb_left; + } else if (fofs >= en->ei.fofs + en->ei.len) { + node = node->rb_right; + } else { + et->cached_en = en; + return en; + } + } + return NULL; +} + +static struct extent_node *__try_back_merge(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_node *en) +{ + struct extent_node *prev; + struct rb_node *node; + + node = rb_prev(&en->rb_node); + if (!node) + return NULL; + + prev = rb_entry(node, struct extent_node, rb_node); + if (__is_back_mergeable(&en->ei, &prev->ei)) { + en->ei.fofs = prev->ei.fofs; + en->ei.blk = prev->ei.blk; + en->ei.len += prev->ei.len; + __detach_extent_node(sbi, et, prev); + return prev; + } + return NULL; +} + +static struct extent_node *__try_front_merge(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_node *en) +{ + struct extent_node *next; + struct rb_node *node; + + node = rb_next(&en->rb_node); + if (!node) + return NULL; + + next = rb_entry(node, struct extent_node, rb_node); + if (__is_front_mergeable(&en->ei, &next->ei)) { + en->ei.len += next->ei.len; + __detach_extent_node(sbi, et, next); + return next; + } + return NULL; +} + +static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi, + struct extent_tree *et, struct extent_info *ei, + struct extent_node **den) +{ + struct rb_node **p = &et->root.rb_node; + struct rb_node *parent = NULL; + struct extent_node *en; + + while (*p) { + parent = *p; + en = rb_entry(parent, struct extent_node, rb_node); + + if (ei->fofs < en->ei.fofs) { + if (__is_front_mergeable(ei, &en->ei)) { + f2fs_bug_on(sbi, !den); + en->ei.fofs = ei->fofs; + en->ei.blk = ei->blk; + en->ei.len += ei->len; + *den = __try_back_merge(sbi, et, en); + return en; + } + p = &(*p)->rb_left; + } else if (ei->fofs >= en->ei.fofs + en->ei.len) { + if (__is_back_mergeable(ei, &en->ei)) { + f2fs_bug_on(sbi, !den); + en->ei.len += ei->len; + *den = __try_front_merge(sbi, et, en); + return en; + } + p = &(*p)->rb_right; + } else { + f2fs_bug_on(sbi, 1); + } + } + + return __attach_extent_node(sbi, et, ei, parent, p); +} + +static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, + struct extent_tree *et, bool free_all) +{ + struct rb_node *node, *next; + struct extent_node *en; + unsigned int count = et->count; + + node = rb_first(&et->root); + while (node) { + next = rb_next(node); + en = rb_entry(node, struct extent_node, rb_node); + + if (free_all) { + spin_lock(&sbi->extent_lock); + if (!list_empty(&en->list)) + list_del_init(&en->list); + spin_unlock(&sbi->extent_lock); + } + + if (free_all || list_empty(&en->list)) { + __detach_extent_node(sbi, et, en); + kmem_cache_free(extent_node_slab, en); + } + node = next; + } + + return count - et->count; +} + +static void f2fs_init_extent_tree(struct inode *inode, + struct f2fs_extent *i_ext) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et; + struct extent_node *en; + struct extent_info ei; + + if (le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN) + return; + + et = __grab_extent_tree(inode); + + write_lock(&et->lock); + if (et->count) + goto out; + + set_extent_info(&ei, le32_to_cpu(i_ext->fofs), + le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len)); + + en = __insert_extent_tree(sbi, et, &ei, NULL); + if (en) { + et->cached_en = en; + + spin_lock(&sbi->extent_lock); + list_add_tail(&en->list, &sbi->extent_list); + spin_unlock(&sbi->extent_lock); + } +out: + write_unlock(&et->lock); + atomic_dec(&et->refcount); +} + +static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, + struct extent_info *ei) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et; + struct extent_node *en; + + trace_f2fs_lookup_extent_tree_start(inode, pgofs); + + et = __find_extent_tree(sbi, inode->i_ino); + if (!et) + return false; + + read_lock(&et->lock); + en = __lookup_extent_tree(et, pgofs); + if (en) { + *ei = en->ei; + spin_lock(&sbi->extent_lock); + if (!list_empty(&en->list)) + list_move_tail(&en->list, &sbi->extent_list); + spin_unlock(&sbi->extent_lock); + stat_inc_read_hit(sbi->sb); + } + stat_inc_total_hit(sbi->sb); + read_unlock(&et->lock); + + trace_f2fs_lookup_extent_tree_end(inode, pgofs, en); + + atomic_dec(&et->refcount); + return en ? true : false; +} + +static void f2fs_update_extent_tree(struct inode *inode, pgoff_t fofs, + block_t blkaddr) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et; + struct extent_node *en = NULL, *en1 = NULL, *en2 = NULL, *en3 = NULL; + struct extent_node *den = NULL; + struct extent_info ei, dei; + unsigned int endofs; + + trace_f2fs_update_extent_tree(inode, fofs, blkaddr); + + et = __grab_extent_tree(inode); + + write_lock(&et->lock); + + /* 1. lookup and remove existing extent info in cache */ + en = __lookup_extent_tree(et, fofs); + if (!en) + goto update_extent; + + dei = en->ei; + __detach_extent_node(sbi, et, en); + + /* 2. if extent can be split more, split and insert the left part */ + if (dei.len > 1) { + /* insert left part of split extent into cache */ + if (fofs - dei.fofs >= F2FS_MIN_EXTENT_LEN) { + set_extent_info(&ei, dei.fofs, dei.blk, + fofs - dei.fofs); + en1 = __insert_extent_tree(sbi, et, &ei, NULL); + } + + /* insert right part of split extent into cache */ + endofs = dei.fofs + dei.len - 1; + if (endofs - fofs >= F2FS_MIN_EXTENT_LEN) { + set_extent_info(&ei, fofs + 1, + fofs - dei.fofs + dei.blk, endofs - fofs); + en2 = __insert_extent_tree(sbi, et, &ei, NULL); + } + } + +update_extent: + /* 3. update extent in extent cache */ + if (blkaddr) { + set_extent_info(&ei, fofs, blkaddr, 1); + en3 = __insert_extent_tree(sbi, et, &ei, &den); + } + + /* 4. update in global extent list */ + spin_lock(&sbi->extent_lock); + if (en && !list_empty(&en->list)) + list_del(&en->list); + /* + * en1 and en2 split from en, they will become more and more smaller + * fragments after splitting several times. So if the length is smaller + * than F2FS_MIN_EXTENT_LEN, we will not add them into extent tree. + */ + if (en1) + list_add_tail(&en1->list, &sbi->extent_list); + if (en2) + list_add_tail(&en2->list, &sbi->extent_list); + if (en3) { + if (list_empty(&en3->list)) + list_add_tail(&en3->list, &sbi->extent_list); + else + list_move_tail(&en3->list, &sbi->extent_list); + } + if (den && !list_empty(&den->list)) + list_del(&den->list); + spin_unlock(&sbi->extent_lock); + + /* 5. release extent node */ + if (en) + kmem_cache_free(extent_node_slab, en); + if (den) + kmem_cache_free(extent_node_slab, den); + + write_unlock(&et->lock); + atomic_dec(&et->refcount); +} + +void f2fs_preserve_extent_tree(struct inode *inode) +{ + struct extent_tree *et; + struct extent_info *ext = &F2FS_I(inode)->ext; + bool sync = false; + + if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE)) + return; + + et = __find_extent_tree(F2FS_I_SB(inode), inode->i_ino); + if (!et) { + if (ext->len) { + ext->len = 0; + update_inode_page(inode); + } + return; + } + + read_lock(&et->lock); + if (et->count) { + struct extent_node *en; + + if (et->cached_en) { + en = et->cached_en; + } else { + struct rb_node *node = rb_first(&et->root); + + if (!node) + node = rb_last(&et->root); + en = rb_entry(node, struct extent_node, rb_node); + } + + if (__is_extent_same(ext, &en->ei)) + goto out; + + *ext = en->ei; + sync = true; + } else if (ext->len) { + ext->len = 0; + sync = true; + } +out: + read_unlock(&et->lock); + atomic_dec(&et->refcount); + + if (sync) + update_inode_page(inode); +} + +void f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) +{ + struct extent_tree *treevec[EXT_TREE_VEC_SIZE]; + struct extent_node *en, *tmp; + unsigned long ino = F2FS_ROOT_INO(sbi); + struct radix_tree_iter iter; + void **slot; + unsigned int found; + unsigned int node_cnt = 0, tree_cnt = 0; + + if (!test_opt(sbi, EXTENT_CACHE)) + return; + + if (available_free_memory(sbi, EXTENT_CACHE)) + return; + + spin_lock(&sbi->extent_lock); + list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) { + if (!nr_shrink--) + break; + list_del_init(&en->list); + } + spin_unlock(&sbi->extent_lock); + + down_read(&sbi->extent_tree_lock); + while ((found = radix_tree_gang_lookup(&sbi->extent_tree_root, + (void **)treevec, ino, EXT_TREE_VEC_SIZE))) { + unsigned i; + + ino = treevec[found - 1]->ino + 1; + for (i = 0; i < found; i++) { + struct extent_tree *et = treevec[i]; + + atomic_inc(&et->refcount); + write_lock(&et->lock); + node_cnt += __free_extent_tree(sbi, et, false); + write_unlock(&et->lock); + atomic_dec(&et->refcount); + } + } + up_read(&sbi->extent_tree_lock); + + down_write(&sbi->extent_tree_lock); + radix_tree_for_each_slot(slot, &sbi->extent_tree_root, &iter, + F2FS_ROOT_INO(sbi)) { + struct extent_tree *et = (struct extent_tree *)*slot; + + if (!atomic_read(&et->refcount) && !et->count) { + radix_tree_delete(&sbi->extent_tree_root, et->ino); + kmem_cache_free(extent_tree_slab, et); + sbi->total_ext_tree--; + tree_cnt++; + } + } + up_write(&sbi->extent_tree_lock); + + trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt); +} + +void f2fs_destroy_extent_tree(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct extent_tree *et; + unsigned int node_cnt = 0; + + if (!test_opt(sbi, EXTENT_CACHE)) + return; + + et = __find_extent_tree(sbi, inode->i_ino); + if (!et) + goto out; + + /* free all extent info belong to this extent tree */ + write_lock(&et->lock); + node_cnt = __free_extent_tree(sbi, et, true); + write_unlock(&et->lock); + + atomic_dec(&et->refcount); + + /* try to find and delete extent tree entry in radix tree */ + down_write(&sbi->extent_tree_lock); + et = radix_tree_lookup(&sbi->extent_tree_root, inode->i_ino); + if (!et) { + up_write(&sbi->extent_tree_lock); + goto out; + } + f2fs_bug_on(sbi, atomic_read(&et->refcount) || et->count); + radix_tree_delete(&sbi->extent_tree_root, inode->i_ino); + kmem_cache_free(extent_tree_slab, et); + sbi->total_ext_tree--; + up_write(&sbi->extent_tree_lock); +out: + trace_f2fs_destroy_extent_tree(inode, node_cnt); + return; +} + +void f2fs_init_extent_cache(struct inode *inode, struct f2fs_extent *i_ext) +{ + if (test_opt(F2FS_I_SB(inode), EXTENT_CACHE)) + f2fs_init_extent_tree(inode, i_ext); + + write_lock(&F2FS_I(inode)->ext_lock); + get_extent_info(&F2FS_I(inode)->ext, *i_ext); + write_unlock(&F2FS_I(inode)->ext_lock); +} + +static bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs, + struct extent_info *ei) +{ + if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) + return false; + + if (test_opt(F2FS_I_SB(inode), EXTENT_CACHE)) + return f2fs_lookup_extent_tree(inode, pgofs, ei); + + return lookup_extent_info(inode, pgofs, ei); +} + +void f2fs_update_extent_cache(struct dnode_of_data *dn) +{ + struct f2fs_inode_info *fi = F2FS_I(dn->inode); + pgoff_t fofs; + + f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR); + + if (is_inode_flag_set(fi, FI_NO_EXTENT)) + return; + + fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + + dn->ofs_in_node; + + if (test_opt(F2FS_I_SB(dn->inode), EXTENT_CACHE)) + return f2fs_update_extent_tree(dn->inode, fofs, + dn->data_blkaddr); + + if (update_extent_info(dn->inode, fofs, dn->data_blkaddr)) + sync_inode_page(dn); +} + +struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync) +{ + struct address_space *mapping = inode->i_mapping; + struct dnode_of_data dn; + struct page *page; + struct extent_info ei; + int err; + struct f2fs_io_info fio = { + .type = DATA, + .rw = sync ? READ_SYNC : READA, + }; + + /* + * If sync is false, it needs to check its block allocation. + * This is need and triggered by two flows: + * gc and truncate_partial_data_page. + */ + if (!sync) + goto search; + + page = find_get_page(mapping, index); + if (page && PageUptodate(page)) + return page; + f2fs_put_page(page, 0); +search: + if (f2fs_lookup_extent_cache(inode, index, &ei)) { + dn.data_blkaddr = ei.blk + index - ei.fofs; + goto got_it; + } + + 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 (unlikely(dn.data_blkaddr == NEW_ADDR)) + return ERR_PTR(-EINVAL); + +got_it: + page = grab_cache_page(mapping, index); + if (!page) + return ERR_PTR(-ENOMEM); + + if (PageUptodate(page)) { + unlock_page(page); + return page; + } + + fio.blk_addr = dn.data_blkaddr; + err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio); + if (err) + return ERR_PTR(err); + + if (sync) { + wait_on_page_locked(page); + if (unlikely(!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 address_space *mapping = inode->i_mapping; + struct dnode_of_data dn; + struct page *page; + struct extent_info ei; + int err; + struct f2fs_io_info fio = { + .type = DATA, + .rw = READ_SYNC, + }; +repeat: + page = grab_cache_page(mapping, index); + if (!page) + return ERR_PTR(-ENOMEM); + + if (f2fs_lookup_extent_cache(inode, index, &ei)) { + dn.data_blkaddr = ei.blk + index - ei.fofs; + goto got_it; + } + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, index, LOOKUP_NODE); + if (err) { + f2fs_put_page(page, 1); + return ERR_PTR(err); + } + f2fs_put_dnode(&dn); + + if (unlikely(dn.data_blkaddr == NULL_ADDR)) { + f2fs_put_page(page, 1); + return ERR_PTR(-ENOENT); + } + +got_it: + if (PageUptodate(page)) + return page; + + /* + * A new dentry page is allocated but not able to be written, since its + * new inode page couldn't be allocated due to -ENOSPC. + * In such the case, its blkaddr can be remained as NEW_ADDR. + * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata. + */ + if (dn.data_blkaddr == NEW_ADDR) { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + SetPageUptodate(page); + return page; + } + + fio.blk_addr = dn.data_blkaddr; + err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio); + if (err) + return ERR_PTR(err); + + lock_page(page); + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 1); + return ERR_PTR(-EIO); + } + if (unlikely(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 rwsem by calling f2fs_lock_op() and + * f2fs_unlock_op(). + * Note that, ipage is set only by make_empty_dir. + */ +struct page *get_new_data_page(struct inode *inode, + struct page *ipage, pgoff_t index, bool new_i_size) +{ + struct address_space *mapping = inode->i_mapping; + struct page *page; + struct dnode_of_data dn; + int err; + + set_new_dnode(&dn, inode, ipage, NULL, 0); + err = f2fs_reserve_block(&dn, index); + if (err) + return ERR_PTR(err); +repeat: + page = grab_cache_page(mapping, index); + if (!page) { + err = -ENOMEM; + goto put_err; + } + + if (PageUptodate(page)) + return page; + + if (dn.data_blkaddr == NEW_ADDR) { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + SetPageUptodate(page); + } else { + struct f2fs_io_info fio = { + .type = DATA, + .rw = READ_SYNC, + .blk_addr = dn.data_blkaddr, + }; + err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio); + if (err) + goto put_err; + + lock_page(page); + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 1); + err = -EIO; + goto put_err; + } + if (unlikely(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)); + /* Only the directory inode sets new_i_size */ + set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR); + } + return page; + +put_err: + f2fs_put_dnode(&dn); + return ERR_PTR(err); +} + +static int __allocate_data_block(struct dnode_of_data *dn) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + struct f2fs_inode_info *fi = F2FS_I(dn->inode); + struct f2fs_summary sum; + struct node_info ni; + int seg = CURSEG_WARM_DATA; + pgoff_t fofs; + + if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC))) + return -EPERM; + + dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node); + if (dn->data_blkaddr == NEW_ADDR) + goto alloc; + + if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1))) + return -ENOSPC; + +alloc: + get_node_info(sbi, dn->nid, &ni); + set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); + + if (dn->ofs_in_node == 0 && dn->inode_page == dn->node_page) + seg = CURSEG_DIRECT_IO; + + allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr, + &sum, seg); + + /* direct IO doesn't use extent cache to maximize the performance */ + set_data_blkaddr(dn); + + /* update i_size */ + fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + + dn->ofs_in_node; + if (i_size_read(dn->inode) < ((fofs + 1) << PAGE_CACHE_SHIFT)) + i_size_write(dn->inode, ((fofs + 1) << PAGE_CACHE_SHIFT)); + + return 0; +} + +static void __allocate_data_blocks(struct inode *inode, loff_t offset, + size_t count) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct dnode_of_data dn; + u64 start = F2FS_BYTES_TO_BLK(offset); + u64 len = F2FS_BYTES_TO_BLK(count); + bool allocated; + u64 end_offset; + + while (len) { + f2fs_balance_fs(sbi); + f2fs_lock_op(sbi); + + /* When reading holes, we need its node page */ + set_new_dnode(&dn, inode, NULL, NULL, 0); + if (get_dnode_of_data(&dn, start, ALLOC_NODE)) + goto out; + + allocated = false; + end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); + + while (dn.ofs_in_node < end_offset && len) { + block_t blkaddr; + + blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); + if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) { + if (__allocate_data_block(&dn)) + goto sync_out; + allocated = true; + } + len--; + start++; + dn.ofs_in_node++; + } + + if (allocated) + sync_inode_page(&dn); + + f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); + } + return; + +sync_out: + if (allocated) + sync_inode_page(&dn); + f2fs_put_dnode(&dn); +out: + f2fs_unlock_op(sbi); + return; +} + +/* + * get_data_block() now supported readahead/bmap/rw direct_IO with mapped bh. + * If original data blocks are allocated, then give them to blockdev. + * Otherwise, + * a. preallocate requested block addresses + * b. do not use extent cache for better performance + * c. give the block addresses to blockdev + */ +static int __get_data_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create, bool fiemap) +{ + unsigned int blkbits = inode->i_sb->s_blocksize_bits; + unsigned maxblocks = bh_result->b_size >> blkbits; + struct dnode_of_data dn; + int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA; + pgoff_t pgofs, end_offset; + int err = 0, ofs = 1; + struct extent_info ei; + bool allocated = false; + + /* Get the page offset from the block offset(iblock) */ + pgofs = (pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits)); + + if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) { + f2fs_map_bh(inode->i_sb, pgofs, &ei, bh_result); + goto out; + } + + if (create) + f2fs_lock_op(F2FS_I_SB(inode)); + + /* When reading holes, we need its node page */ + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, pgofs, mode); + if (err) { + if (err == -ENOENT) + err = 0; + goto unlock_out; + } + if (dn.data_blkaddr == NEW_ADDR && !fiemap) + goto put_out; + + if (dn.data_blkaddr != NULL_ADDR) { + clear_buffer_new(bh_result); + map_bh(bh_result, inode->i_sb, dn.data_blkaddr); + } else if (create) { + err = __allocate_data_block(&dn); + if (err) + goto put_out; + allocated = true; + set_buffer_new(bh_result); + map_bh(bh_result, inode->i_sb, dn.data_blkaddr); + } else { + goto put_out; + } + + end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); + bh_result->b_size = (((size_t)1) << blkbits); + dn.ofs_in_node++; + pgofs++; + +get_next: + if (dn.ofs_in_node >= end_offset) { + if (allocated) + sync_inode_page(&dn); + allocated = false; + f2fs_put_dnode(&dn); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, pgofs, mode); + if (err) { + if (err == -ENOENT) + err = 0; + goto unlock_out; + } + if (dn.data_blkaddr == NEW_ADDR && !fiemap) + goto put_out; + + end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); + } + + if (maxblocks > (bh_result->b_size >> blkbits)) { + block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); + if (blkaddr == NULL_ADDR && create) { + err = __allocate_data_block(&dn); + if (err) + goto sync_out; + allocated = true; + set_buffer_new(bh_result); + blkaddr = dn.data_blkaddr; + } + /* Give more consecutive addresses for the readahead */ + if (blkaddr == (bh_result->b_blocknr + ofs)) { + ofs++; + dn.ofs_in_node++; + pgofs++; + bh_result->b_size += (((size_t)1) << blkbits); + goto get_next; + } + } +sync_out: + if (allocated) + sync_inode_page(&dn); +put_out: + f2fs_put_dnode(&dn); +unlock_out: + if (create) + f2fs_unlock_op(F2FS_I_SB(inode)); +out: + trace_f2fs_get_data_block(inode, iblock, bh_result, err); + return err; +} + +static int get_data_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + return __get_data_block(inode, iblock, bh_result, create, false); +} + +static int get_data_block_fiemap(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + return __get_data_block(inode, iblock, bh_result, create, true); +} + +int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len) +{ + return generic_block_fiemap(inode, fieinfo, + start, len, get_data_block_fiemap); +} + +static int f2fs_read_data_page(struct file *file, struct page *page) +{ + struct inode *inode = page->mapping->host; + int ret = -EAGAIN; + + trace_f2fs_readpage(page, DATA); + + /* If the file has inline data, try to read it directly */ + if (f2fs_has_inline_data(inode)) + ret = f2fs_read_inline_data(inode, page); + if (ret == -EAGAIN) + ret = mpage_readpage(page, get_data_block); + + return ret; +} + +static int f2fs_read_data_pages(struct file *file, + struct address_space *mapping, + struct list_head *pages, unsigned nr_pages) +{ + struct inode *inode = file->f_mapping->host; + + /* If the file has inline data, skip readpages */ + if (f2fs_has_inline_data(inode)) + return 0; + + return mpage_readpages(mapping, pages, nr_pages, get_data_block); +} + +int do_write_data_page(struct page *page, struct f2fs_io_info *fio) +{ + struct inode *inode = page->mapping->host; + 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; + + fio->blk_addr = dn.data_blkaddr; + + /* This page is already truncated */ + if (fio->blk_addr == NULL_ADDR) { + ClearPageUptodate(page); + goto out_writepage; + } + + set_page_writeback(page); + + /* + * If current allocation needs SSR, + * it had better in-place writes for updated data. + */ + if (unlikely(fio->blk_addr != NEW_ADDR && + !is_cold_data(page) && + need_inplace_update(inode))) { + rewrite_data_page(page, fio); + set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE); + trace_f2fs_do_write_data_page(page, IPU); + } else { + write_data_page(page, &dn, fio); + set_data_blkaddr(&dn); + f2fs_update_extent_cache(&dn); + trace_f2fs_do_write_data_page(page, OPU); + set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE); + if (page->index == 0) + set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); + } +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_I_SB(inode); + loff_t i_size = i_size_read(inode); + const pgoff_t end_index = ((unsigned long long) i_size) + >> PAGE_CACHE_SHIFT; + unsigned offset = 0; + bool need_balance_fs = false; + int err = 0; + struct f2fs_io_info fio = { + .type = DATA, + .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE, + }; + + trace_f2fs_writepage(page, DATA); + + 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) + goto out; + + zero_user_segment(page, offset, PAGE_CACHE_SIZE); +write: + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + goto redirty_out; + if (f2fs_is_drop_cache(inode)) + goto out; + if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim && + available_free_memory(sbi, BASE_CHECK)) + goto redirty_out; + + /* Dentry blocks are controlled by checkpoint */ + if (S_ISDIR(inode->i_mode)) { + if (unlikely(f2fs_cp_error(sbi))) + goto redirty_out; + err = do_write_data_page(page, &fio); + goto done; + } + + /* we should bypass data pages to proceed the kworkder jobs */ + if (unlikely(f2fs_cp_error(sbi))) { + SetPageError(page); + goto out; + } + + if (!wbc->for_reclaim) + need_balance_fs = true; + else if (has_not_enough_free_secs(sbi, 0)) + goto redirty_out; + + err = -EAGAIN; + f2fs_lock_op(sbi); + if (f2fs_has_inline_data(inode)) + err = f2fs_write_inline_data(inode, page); + if (err == -EAGAIN) + err = do_write_data_page(page, &fio); + f2fs_unlock_op(sbi); +done: + if (err && err != -ENOENT) + goto redirty_out; + + clear_cold_data(page); +out: + inode_dec_dirty_pages(inode); + if (err) + ClearPageUptodate(page); + unlock_page(page); + if (need_balance_fs) + f2fs_balance_fs(sbi); + if (wbc->for_reclaim) + f2fs_submit_merged_bio(sbi, DATA, WRITE); + return 0; + +redirty_out: + redirty_page_for_writepage(wbc, page); + return AOP_WRITEPAGE_ACTIVATE; +} + +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_I_SB(inode); + bool locked = false; + int ret; + long diff; + + trace_f2fs_writepages(mapping->host, wbc, DATA); + + /* deal with chardevs and other special file */ + if (!mapping->a_ops->writepage) + return 0; + + if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE && + get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) && + available_free_memory(sbi, DIRTY_DENTS)) + goto skip_write; + + /* during POR, we don't need to trigger writepage at all. */ + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + goto skip_write; + + diff = nr_pages_to_write(sbi, DATA, wbc); + + 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_merged_bio(sbi, DATA, WRITE); + + remove_dirty_dir_inode(inode); + + wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff); + return ret; + +skip_write: + wbc->pages_skipped += get_dirty_pages(inode); + return 0; +} + +static void f2fs_write_failed(struct address_space *mapping, loff_t to) +{ + struct inode *inode = mapping->host; + + if (to > inode->i_size) { + truncate_pagecache(inode, inode->i_size); + truncate_blocks(inode, inode->i_size, true); + } +} + +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_I_SB(inode); + struct page *page, *ipage; + pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT; + struct dnode_of_data dn; + int err = 0; + + trace_f2fs_write_begin(inode, pos, len, flags); + + f2fs_balance_fs(sbi); + + /* + * We should check this at this moment to avoid deadlock on inode page + * and #0 page. The locking rule for inline_data conversion should be: + * lock_page(page #0) -> lock_page(inode_page) + */ + if (index != 0) { + err = f2fs_convert_inline_inode(inode); + if (err) + goto fail; + } +repeat: + page = grab_cache_page_write_begin(mapping, index, flags); + if (!page) { + err = -ENOMEM; + goto fail; + } + + *pagep = page; + + f2fs_lock_op(sbi); + + /* check inline_data */ + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + err = PTR_ERR(ipage); + goto unlock_fail; + } + + set_new_dnode(&dn, inode, ipage, ipage, 0); + + if (f2fs_has_inline_data(inode)) { + if (pos + len <= MAX_INLINE_DATA) { + read_inline_data(page, ipage); + set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); + sync_inode_page(&dn); + goto put_next; + } + err = f2fs_convert_inline_page(&dn, page); + if (err) + goto put_fail; + } + err = f2fs_reserve_block(&dn, index); + if (err) + goto put_fail; +put_next: + f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); + + if ((len == PAGE_CACHE_SIZE) || PageUptodate(page)) + return 0; + + f2fs_wait_on_page_writeback(page, DATA); + + 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 { + struct f2fs_io_info fio = { + .type = DATA, + .rw = READ_SYNC, + .blk_addr = dn.data_blkaddr, + }; + err = f2fs_submit_page_bio(sbi, page, &fio); + if (err) + goto fail; + + lock_page(page); + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 1); + err = -EIO; + goto fail; + } + if (unlikely(page->mapping != mapping)) { + f2fs_put_page(page, 1); + goto repeat; + } + } +out: + SetPageUptodate(page); + clear_cold_data(page); + return 0; + +put_fail: + f2fs_put_dnode(&dn); +unlock_fail: + f2fs_unlock_op(sbi); + f2fs_put_page(page, 1); +fail: + f2fs_write_failed(mapping, pos + len); + return err; +} + +static int f2fs_write_end(struct file *file, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + struct inode *inode = page->mapping->host; + + trace_f2fs_write_end(inode, pos, len, copied); + + set_page_dirty(page); + + if (pos + copied > i_size_read(inode)) { + i_size_write(inode, pos + copied); + mark_inode_dirty(inode); + update_inode_page(inode); + } + + f2fs_put_page(page, 1); + return copied; +} + +static int check_direct_IO(struct inode *inode, struct iov_iter *iter, + loff_t offset) +{ + unsigned blocksize_mask = inode->i_sb->s_blocksize - 1; + + if (iov_iter_rw(iter) == READ) + return 0; + + if (offset & blocksize_mask) + return -EINVAL; + + if (iov_iter_alignment(iter) & blocksize_mask) + return -EINVAL; + + return 0; +} + +static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) +{ + struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); + int err; + + /* we don't need to use inline_data strictly */ + if (f2fs_has_inline_data(inode)) { + err = f2fs_convert_inline_inode(inode); + if (err) + return err; + } + + if (check_direct_IO(inode, iter, offset)) + return 0; + + trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); + + if (iov_iter_rw(iter) == WRITE) + __allocate_data_blocks(inode, offset, count); + + err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block); + if (err < 0 && iov_iter_rw(iter) == WRITE) + f2fs_write_failed(mapping, offset + count); + + trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err); + + return err; +} + +void f2fs_invalidate_page(struct page *page, unsigned int offset, + unsigned int length) +{ + struct inode *inode = page->mapping->host; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (inode->i_ino >= F2FS_ROOT_INO(sbi) && + (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE)) + return; + + if (PageDirty(page)) { + if (inode->i_ino == F2FS_META_INO(sbi)) + dec_page_count(sbi, F2FS_DIRTY_META); + else if (inode->i_ino == F2FS_NODE_INO(sbi)) + dec_page_count(sbi, F2FS_DIRTY_NODES); + else + inode_dec_dirty_pages(inode); + } + ClearPagePrivate(page); +} + +int f2fs_release_page(struct page *page, gfp_t wait) +{ + /* If this is dirty page, keep PagePrivate */ + if (PageDirty(page)) + return 0; + + 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; + + trace_f2fs_set_page_dirty(page, DATA); + + SetPageUptodate(page); + + if (f2fs_is_atomic_file(inode)) { + register_inmem_page(inode, page); + return 1; + } + + mark_inode_dirty(inode); + + if (!PageDirty(page)) { + __set_page_dirty_nobuffers(page); + update_dirty_page(inode, page); + return 1; + } + return 0; +} + +static sector_t f2fs_bmap(struct address_space *mapping, sector_t block) +{ + struct inode *inode = mapping->host; + + /* we don't need to use inline_data strictly */ + if (f2fs_has_inline_data(inode)) { + int err = f2fs_convert_inline_inode(inode); + if (err) + return err; + } + return generic_block_bmap(mapping, block, get_data_block); +} + +void init_extent_cache_info(struct f2fs_sb_info *sbi) +{ + INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO); + init_rwsem(&sbi->extent_tree_lock); + INIT_LIST_HEAD(&sbi->extent_list); + spin_lock_init(&sbi->extent_lock); + sbi->total_ext_tree = 0; + atomic_set(&sbi->total_ext_node, 0); +} + +int __init create_extent_cache(void) +{ + extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree", + sizeof(struct extent_tree)); + if (!extent_tree_slab) + return -ENOMEM; + extent_node_slab = f2fs_kmem_cache_create("f2fs_extent_node", + sizeof(struct extent_node)); + if (!extent_node_slab) { + kmem_cache_destroy(extent_tree_slab); + return -ENOMEM; + } + return 0; +} + +void destroy_extent_cache(void) +{ + kmem_cache_destroy(extent_node_slab); + kmem_cache_destroy(extent_tree_slab); +} + +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 = f2fs_write_end, + .set_page_dirty = f2fs_set_data_page_dirty, + .invalidatepage = f2fs_invalidate_page, + .releasepage = f2fs_release_page, + .direct_IO = f2fs_direct_IO, + .bmap = f2fs_bmap, +}; diff --git a/kernel/fs/f2fs/debug.c b/kernel/fs/f2fs/debug.c new file mode 100644 index 000000000..f5388f372 --- /dev/null +++ b/kernel/fs/f2fs/debug.c @@ -0,0 +1,413 @@ +/* + * 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 *f2fs_debugfs_root; +static DEFINE_MUTEX(f2fs_stat_mutex); + +static void update_general_status(struct f2fs_sb_info *sbi) +{ + struct f2fs_stat_info *si = F2FS_STAT(sbi); + int i; + + /* validation check of the segment numbers */ + si->hit_ext = sbi->read_hit_ext; + si->total_ext = sbi->total_hit_ext; + si->ext_tree = sbi->total_ext_tree; + si->ext_node = atomic_read(&sbi->total_ext_node); + 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->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES); + si->wb_pages = get_pages(sbi, F2FS_WRITEBACK); + 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->inline_inode = atomic_read(&sbi->inline_inode); + si->inline_dir = atomic_read(&sbi->inline_dir); + 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 = NODE_MAPPING(sbi)->nrpages; + si->meta_pages = META_MAPPING(sbi)->nrpages; + si->nats = NM_I(sbi)->nat_cnt; + si->dirty_nats = NM_I(sbi)->dirty_nat_cnt; + si->sits = MAIN_SEGS(sbi); + si->dirty_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]; + } + + si->inplace_count = atomic_read(&sbi->inplace_count); +} + +/* + * This function calculates BDF of every segments + */ +static void update_sit_info(struct f2fs_sb_info *sbi) +{ + struct f2fs_stat_info *si = F2FS_STAT(sbi); + unsigned int blks_per_sec, hblks_per_sec, total_vblocks, bimodal, dist; + 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; + for (segno = 0; segno < MAIN_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++; + } + } + dist = MAIN_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 = F2FS_STAT(sbi); + unsigned npages; + int i; + + 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 += MAIN_SEGS(sbi) * sizeof(struct seg_entry); + si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi)); + si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); + si->base_mem += SIT_VBLOCK_MAP_SIZE; + if (sbi->segs_per_sec > 1) + si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry); + si->base_mem += __bitmap_size(sbi, SIT_BITMAP); + + /* build free segmap */ + si->base_mem += sizeof(struct free_segmap_info); + si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi)); + si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi)); + + /* build curseg */ + si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE; + si->base_mem += PAGE_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(MAIN_SEGS(sbi)); + si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi)); + + /* build nm */ + si->base_mem += sizeof(struct f2fs_nm_info); + si->base_mem += __bitmap_size(sbi, NAT_BITMAP); + +get_cache: + si->cache_mem = 0; + + /* build gc */ + if (sbi->gc_thread) + si->cache_mem += sizeof(struct f2fs_gc_kthread); + + /* build merge flush thread */ + if (SM_I(sbi)->cmd_control_info) + si->cache_mem += sizeof(struct flush_cmd_control); + + /* free nids */ + si->cache_mem += NM_I(sbi)->fcnt * sizeof(struct free_nid); + si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry); + si->cache_mem += NM_I(sbi)->dirty_nat_cnt * + sizeof(struct nat_entry_set); + si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages); + si->cache_mem += sbi->n_dirty_dirs * sizeof(struct inode_entry); + for (i = 0; i <= UPDATE_INO; i++) + si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry); + si->cache_mem += sbi->total_ext_tree * sizeof(struct extent_tree); + si->cache_mem += atomic_read(&sbi->total_ext_node) * + sizeof(struct extent_node); + + si->page_mem = 0; + npages = NODE_MAPPING(sbi)->nrpages; + si->page_mem += npages << PAGE_CACHE_SHIFT; + npages = META_MAPPING(sbi)->nrpages; + si->page_mem += npages << PAGE_CACHE_SHIFT; +} + +static int stat_show(struct seq_file *s, void *v) +{ + struct f2fs_stat_info *si; + int i = 0; + int j; + + mutex_lock(&f2fs_stat_mutex); + list_for_each_entry(si, &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, " - Inline_data Inode: %u\n", + si->inline_inode); + seq_printf(s, " - Inline_dentry Inode: %u\n", + si->inline_dir); + 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, "CP calls: %d\n", si->cp_count); + seq_printf(s, "GC calls: %d (BG: %d)\n", + si->call_count, si->bg_gc); + seq_printf(s, " - data segments : %d (%d)\n", + si->data_segs, si->bg_data_segs); + seq_printf(s, " - node segments : %d (%d)\n", + si->node_segs, si->bg_node_segs); + seq_printf(s, "Try to move %d blocks (BG: %d)\n", si->tot_blks, + si->bg_data_blks + si->bg_node_blks); + seq_printf(s, " - data blocks : %d (%d)\n", si->data_blks, + si->bg_data_blks); + seq_printf(s, " - node blocks : %d (%d)\n", si->node_blks, + si->bg_node_blks); + seq_printf(s, "\nExtent Hit Ratio: %d / %d\n", + si->hit_ext, si->total_ext); + seq_printf(s, "\nExtent Tree Count: %d\n", si->ext_tree); + seq_printf(s, "\nExtent Node Count: %d\n", si->ext_node); + seq_puts(s, "\nBalancing F2FS Async:\n"); + seq_printf(s, " - inmem: %4d, wb: %4d\n", + si->inmem_pages, si->wb_pages); + 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: %9d/%9d\n - SITs: %9d/%9d\n", + si->dirty_nats, si->nats, si->dirty_sits, si->sits); + seq_printf(s, " - free_nids: %9d\n", + si->fnids); + seq_puts(s, "\nDistribution of User Blocks:"); + seq_puts(s, " [ valid | invalid | free ]\n"); + seq_puts(s, " ["); + + for (j = 0; j < si->util_valid; j++) + seq_putc(s, '-'); + seq_putc(s, '|'); + + for (j = 0; j < si->util_invalid; j++) + seq_putc(s, '-'); + seq_putc(s, '|'); + + for (j = 0; j < si->util_free; j++) + seq_putc(s, '-'); + seq_puts(s, "]\n\n"); + seq_printf(s, "IPU: %u blocks\n", si->inplace_count); + seq_printf(s, "SSR: %u blocks in %u segments\n", + si->block_count[SSR], si->segment_count[SSR]); + seq_printf(s, "LFS: %u blocks in %u segments\n", + si->block_count[LFS], si->segment_count[LFS]); + + /* segment usage info */ + 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\n", + (si->base_mem + si->cache_mem + si->page_mem) >> 10); + seq_printf(s, " - static: %u KB\n", + si->base_mem >> 10); + seq_printf(s, " - cached: %u KB\n", + si->cache_mem >> 10); + seq_printf(s, " - paged : %u KB\n", + si->page_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; + + si = kzalloc(sizeof(struct f2fs_stat_info), GFP_KERNEL); + if (!si) + return -ENOMEM; + + si->all_area_segs = le32_to_cpu(raw_super->segment_count); + si->sit_area_segs = le32_to_cpu(raw_super->segment_count_sit); + si->nat_area_segs = le32_to_cpu(raw_super->segment_count_nat); + si->ssa_area_segs = le32_to_cpu(raw_super->segment_count_ssa); + si->main_area_segs = le32_to_cpu(raw_super->segment_count_main); + si->main_area_sections = le32_to_cpu(raw_super->section_count); + si->main_area_zones = si->main_area_sections / + le32_to_cpu(raw_super->secs_per_zone); + si->sbi = sbi; + sbi->stat_info = si; + + atomic_set(&sbi->inline_inode, 0); + atomic_set(&sbi->inline_dir, 0); + atomic_set(&sbi->inplace_count, 0); + + 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 = F2FS_STAT(sbi); + + mutex_lock(&f2fs_stat_mutex); + list_del(&si->stat_list); + mutex_unlock(&f2fs_stat_mutex); + + kfree(si); +} + +void __init f2fs_create_root_stats(void) +{ + struct dentry *file; + + f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL); + if (!f2fs_debugfs_root) + return; + + file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, + NULL, &stat_fops); + if (!file) { + debugfs_remove(f2fs_debugfs_root); + f2fs_debugfs_root = NULL; + } +} + +void f2fs_destroy_root_stats(void) +{ + if (!f2fs_debugfs_root) + return; + + debugfs_remove_recursive(f2fs_debugfs_root); + f2fs_debugfs_root = NULL; +} diff --git a/kernel/fs/f2fs/dir.c b/kernel/fs/f2fs/dir.c new file mode 100644 index 000000000..3a3302ab7 --- /dev/null +++ b/kernel/fs/f2fs/dir.c @@ -0,0 +1,811 @@ +/* + * 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" +#include "xattr.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, int dir_level) +{ + if (level + dir_level < MAX_DIR_HASH_DEPTH / 2) + return 1 << (level + dir_level); + else + return MAX_DIR_BUCKETS; +} + +static unsigned int bucket_blocks(unsigned int level) +{ + if (level < MAX_DIR_HASH_DEPTH / 2) + return 2; + else + return 4; +} + +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, +}; + +void set_de_type(struct f2fs_dir_entry *de, umode_t mode) +{ + de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT]; +} + +static unsigned long dir_block_index(unsigned int level, + int dir_level, unsigned int idx) +{ + unsigned long i; + unsigned long bidx = 0; + + for (i = 0; i < level; i++) + bidx += dir_buckets(i, dir_level) * bucket_blocks(i); + bidx += idx * bucket_blocks(level); + return bidx; +} + +static bool early_match_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, + struct qstr *name, int *max_slots, + struct page **res_page) +{ + struct f2fs_dentry_block *dentry_blk; + struct f2fs_dir_entry *de; + struct f2fs_dentry_ptr d; + + dentry_blk = (struct f2fs_dentry_block *)kmap(dentry_page); + + make_dentry_ptr(&d, (void *)dentry_blk, 1); + de = find_target_dentry(name, max_slots, &d); + + if (de) + *res_page = dentry_page; + else + kunmap(dentry_page); + + /* + * For the most part, it should be a bug when name_len is zero. + * We stop here for figuring out where the bugs has occurred. + */ + f2fs_bug_on(F2FS_P_SB(dentry_page), d.max < 0); + return de; +} + +struct f2fs_dir_entry *find_target_dentry(struct qstr *name, int *max_slots, + struct f2fs_dentry_ptr *d) +{ + struct f2fs_dir_entry *de; + unsigned long bit_pos = 0; + f2fs_hash_t namehash = f2fs_dentry_hash(name); + int max_len = 0; + + if (max_slots) + *max_slots = 0; + while (bit_pos < d->max) { + if (!test_bit_le(bit_pos, d->bitmap)) { + bit_pos++; + max_len++; + continue; + } + + de = &d->dentry[bit_pos]; + if (early_match_name(name->len, namehash, de) && + !memcmp(d->filename[bit_pos], name->name, name->len)) + goto found; + + if (max_slots && max_len > *max_slots) + *max_slots = max_len; + max_len = 0; + + /* remain bug on condition */ + if (unlikely(!de->name_len)) + d->max = -1; + + bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); + } + + de = NULL; +found: + if (max_slots && max_len > *max_slots) + *max_slots = max_len; + return de; +} + +static struct f2fs_dir_entry *find_in_level(struct inode *dir, + unsigned int level, struct qstr *name, + f2fs_hash_t namehash, struct page **res_page) +{ + int s = GET_DENTRY_SLOTS(name->len); + 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; + + f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH); + + nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level); + nblock = bucket_blocks(level); + + bidx = dir_block_index(level, F2FS_I(dir)->i_dir_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, &max_slots, 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) +{ + unsigned long npages = dir_blocks(dir); + struct f2fs_dir_entry *de = NULL; + f2fs_hash_t name_hash; + unsigned int max_depth; + unsigned int level; + + *res_page = NULL; + + if (f2fs_has_inline_dentry(dir)) + return find_in_inline_dir(dir, child, res_page); + + if (npages == 0) + return NULL; + + name_hash = f2fs_dentry_hash(child); + max_depth = F2FS_I(dir)->i_current_depth; + + for (level = 0; level < max_depth; level++) { + de = find_in_level(dir, level, child, 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; + struct f2fs_dir_entry *de; + struct f2fs_dentry_block *dentry_blk; + + if (f2fs_has_inline_dentry(dir)) + return f2fs_parent_inline_dir(dir, p); + + 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); + f2fs_dentry_kunmap(dir, 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) +{ + enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA; + lock_page(page); + f2fs_wait_on_page_writeback(page, type); + de->ino = cpu_to_le32(inode->i_ino); + set_de_type(de, inode->i_mode); + f2fs_dentry_kunmap(dir, page); + set_page_dirty(page); + dir->i_mtime = dir->i_ctime = CURRENT_TIME; + mark_inode_dirty(dir); + + f2fs_put_page(page, 1); +} + +static void init_dent_inode(const struct qstr *name, struct page *ipage) +{ + struct f2fs_inode *ri; + + f2fs_wait_on_page_writeback(ipage, NODE); + + /* copy name info. to this inode page */ + ri = F2FS_INODE(ipage); + ri->i_namelen = cpu_to_le32(name->len); + memcpy(ri->i_name, name->name, name->len); + set_page_dirty(ipage); +} + +int update_dent_inode(struct inode *inode, const struct qstr *name) +{ + struct page *page; + + page = get_node_page(F2FS_I_SB(inode), inode->i_ino); + if (IS_ERR(page)) + return PTR_ERR(page); + + init_dent_inode(name, page); + f2fs_put_page(page, 1); + + return 0; +} + +void do_make_empty_dir(struct inode *inode, struct inode *parent, + struct f2fs_dentry_ptr *d) +{ + struct f2fs_dir_entry *de; + + de = &d->dentry[0]; + de->name_len = cpu_to_le16(1); + de->hash_code = 0; + de->ino = cpu_to_le32(inode->i_ino); + memcpy(d->filename[0], ".", 1); + set_de_type(de, inode->i_mode); + + de = &d->dentry[1]; + de->hash_code = 0; + de->name_len = cpu_to_le16(2); + de->ino = cpu_to_le32(parent->i_ino); + memcpy(d->filename[1], "..", 2); + set_de_type(de, parent->i_mode); + + test_and_set_bit_le(0, (void *)d->bitmap); + test_and_set_bit_le(1, (void *)d->bitmap); +} + +static int make_empty_dir(struct inode *inode, + struct inode *parent, struct page *page) +{ + struct page *dentry_page; + struct f2fs_dentry_block *dentry_blk; + struct f2fs_dentry_ptr d; + + if (f2fs_has_inline_dentry(inode)) + return make_empty_inline_dir(inode, parent, page); + + dentry_page = get_new_data_page(inode, page, 0, true); + if (IS_ERR(dentry_page)) + return PTR_ERR(dentry_page); + + dentry_blk = kmap_atomic(dentry_page); + + make_dentry_ptr(&d, (void *)dentry_blk, 1); + do_make_empty_dir(inode, parent, &d); + + kunmap_atomic(dentry_blk); + + set_page_dirty(dentry_page); + f2fs_put_page(dentry_page, 1); + return 0; +} + +struct page *init_inode_metadata(struct inode *inode, struct inode *dir, + const struct qstr *name, struct page *dpage) +{ + struct page *page; + int err; + + if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) { + page = new_inode_page(inode); + if (IS_ERR(page)) + return page; + + if (S_ISDIR(inode->i_mode)) { + err = make_empty_dir(inode, dir, page); + if (err) + goto error; + } + + err = f2fs_init_acl(inode, dir, page, dpage); + if (err) + goto put_error; + + err = f2fs_init_security(inode, dir, name, page); + if (err) + goto put_error; + } else { + page = get_node_page(F2FS_I_SB(dir), inode->i_ino); + if (IS_ERR(page)) + return page; + + set_cold_node(inode, page); + } + + if (name) + init_dent_inode(name, page); + + /* + * This file should be checkpointed during fsync. + * We lost i_pino from now on. + */ + if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) { + file_lost_pino(inode); + /* + * If link the tmpfile to alias through linkat path, + * we should remove this inode from orphan list. + */ + if (inode->i_nlink == 0) + remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino); + inc_nlink(inode); + } + return page; + +put_error: + f2fs_put_page(page, 1); +error: + /* once the failed inode becomes a bad inode, i_mode is S_IFREG */ + truncate_inode_pages(&inode->i_data, 0); + truncate_blocks(inode, 0, false); + remove_dirty_dir_inode(inode); + remove_inode_page(inode); + return ERR_PTR(err); +} + +void update_parent_metadata(struct inode *dir, struct inode *inode, + unsigned int current_depth) +{ + if (inode && is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) { + if (S_ISDIR(inode->i_mode)) { + inc_nlink(dir); + set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); + } + clear_inode_flag(F2FS_I(inode), FI_NEW_INODE); + } + dir->i_mtime = dir->i_ctime = CURRENT_TIME; + mark_inode_dirty(dir); + + if (F2FS_I(dir)->i_current_depth != current_depth) { + F2FS_I(dir)->i_current_depth = current_depth; + set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); + } + + if (inode && is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) + clear_inode_flag(F2FS_I(inode), FI_INC_LINK); +} + +int room_for_filename(const void *bitmap, int slots, int max_slots) +{ + int bit_start = 0; + int zero_start, zero_end; +next: + zero_start = find_next_zero_bit_le(bitmap, max_slots, bit_start); + if (zero_start >= max_slots) + return max_slots; + + zero_end = find_next_bit_le(bitmap, max_slots, zero_start); + if (zero_end - zero_start >= slots) + return zero_start; + + bit_start = zero_end + 1; + + if (zero_end + 1 >= max_slots) + return max_slots; + goto next; +} + +void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d, + const struct qstr *name, f2fs_hash_t name_hash, + unsigned int bit_pos) +{ + struct f2fs_dir_entry *de; + int slots = GET_DENTRY_SLOTS(name->len); + int i; + + de = &d->dentry[bit_pos]; + de->hash_code = name_hash; + de->name_len = cpu_to_le16(name->len); + memcpy(d->filename[bit_pos], name->name, name->len); + de->ino = cpu_to_le32(ino); + set_de_type(de, mode); + for (i = 0; i < slots; i++) + test_and_set_bit_le(bit_pos + i, (void *)d->bitmap); +} + +/* + * Caller should grab and release a rwsem by calling f2fs_lock_op() and + * f2fs_unlock_op(). + */ +int __f2fs_add_link(struct inode *dir, const struct qstr *name, + struct inode *inode, nid_t ino, umode_t mode) +{ + unsigned int bit_pos; + unsigned int level; + unsigned int current_depth; + unsigned long bidx, block; + f2fs_hash_t dentry_hash; + unsigned int nbucket, nblock; + size_t namelen = name->len; + struct page *dentry_page = NULL; + struct f2fs_dentry_block *dentry_blk = NULL; + struct f2fs_dentry_ptr d; + int slots = GET_DENTRY_SLOTS(namelen); + struct page *page = NULL; + int err = 0; + + if (f2fs_has_inline_dentry(dir)) { + err = f2fs_add_inline_entry(dir, name, inode, ino, mode); + if (!err || err != -EAGAIN) + return err; + else + err = 0; + } + + dentry_hash = f2fs_dentry_hash(name); + 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 (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) + return -ENOSPC; + + /* Increase the depth, if required */ + if (level == current_depth) + ++current_depth; + + nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level); + nblock = bucket_blocks(level); + + bidx = dir_block_index(level, F2FS_I(dir)->i_dir_level, + (le32_to_cpu(dentry_hash) % nbucket)); + + for (block = bidx; block <= (bidx + nblock - 1); block++) { + dentry_page = get_new_data_page(dir, NULL, block, true); + if (IS_ERR(dentry_page)) + return PTR_ERR(dentry_page); + + dentry_blk = kmap(dentry_page); + bit_pos = room_for_filename(&dentry_blk->dentry_bitmap, + slots, NR_DENTRY_IN_BLOCK); + 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: + f2fs_wait_on_page_writeback(dentry_page, DATA); + + if (inode) { + down_write(&F2FS_I(inode)->i_sem); + page = init_inode_metadata(inode, dir, name, NULL); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto fail; + } + } + + make_dentry_ptr(&d, (void *)dentry_blk, 1); + f2fs_update_dentry(ino, mode, &d, name, dentry_hash, bit_pos); + + set_page_dirty(dentry_page); + + if (inode) { + /* we don't need to mark_inode_dirty now */ + F2FS_I(inode)->i_pino = dir->i_ino; + update_inode(inode, page); + f2fs_put_page(page, 1); + } + + update_parent_metadata(dir, inode, current_depth); +fail: + if (inode) + up_write(&F2FS_I(inode)->i_sem); + + if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) { + update_inode_page(dir); + clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); + } + kunmap(dentry_page); + f2fs_put_page(dentry_page, 1); + return err; +} + +int f2fs_do_tmpfile(struct inode *inode, struct inode *dir) +{ + struct page *page; + int err = 0; + + down_write(&F2FS_I(inode)->i_sem); + page = init_inode_metadata(inode, dir, NULL, NULL); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto fail; + } + /* we don't need to mark_inode_dirty now */ + update_inode(inode, page); + f2fs_put_page(page, 1); + + clear_inode_flag(F2FS_I(inode), FI_NEW_INODE); +fail: + up_write(&F2FS_I(inode)->i_sem); + return err; +} + +void f2fs_drop_nlink(struct inode *dir, struct inode *inode, struct page *page) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + + down_write(&F2FS_I(inode)->i_sem); + + if (S_ISDIR(inode->i_mode)) { + drop_nlink(dir); + if (page) + update_inode(dir, page); + else + update_inode_page(dir); + } + inode->i_ctime = CURRENT_TIME; + + drop_nlink(inode); + if (S_ISDIR(inode->i_mode)) { + drop_nlink(inode); + i_size_write(inode, 0); + } + up_write(&F2FS_I(inode)->i_sem); + update_inode_page(inode); + + if (inode->i_nlink == 0) + add_orphan_inode(sbi, inode->i_ino); + else + release_orphan_inode(sbi); +} + +/* + * 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 *dir, struct inode *inode) +{ + struct f2fs_dentry_block *dentry_blk; + unsigned int bit_pos; + int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); + int i; + + if (f2fs_has_inline_dentry(dir)) + return f2fs_delete_inline_entry(dentry, page, dir, inode); + + lock_page(page); + f2fs_wait_on_page_writeback(page, DATA); + + dentry_blk = page_address(page); + bit_pos = dentry - dentry_blk->dentry; + for (i = 0; i < slots; i++) + 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) + f2fs_drop_nlink(dir, inode, NULL); + + if (bit_pos == NR_DENTRY_IN_BLOCK) { + truncate_hole(dir, page->index, page->index + 1); + clear_page_dirty_for_io(page); + ClearPagePrivate(page); + ClearPageUptodate(page); + inode_dec_dirty_pages(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); + + if (f2fs_has_inline_dentry(dir)) + return f2fs_empty_inline_dir(dir); + + for (bidx = 0; bidx < nblock; bidx++) { + dentry_page = get_lock_data_page(dir, bidx); + if (IS_ERR(dentry_page)) { + if (PTR_ERR(dentry_page) == -ENOENT) + continue; + else + return false; + } + + dentry_blk = kmap_atomic(dentry_page); + 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(dentry_blk); + + f2fs_put_page(dentry_page, 1); + + if (bit_pos < NR_DENTRY_IN_BLOCK) + return false; + } + return true; +} + +bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, + unsigned int start_pos) +{ + unsigned char d_type = DT_UNKNOWN; + unsigned int bit_pos; + struct f2fs_dir_entry *de = NULL; + + bit_pos = ((unsigned long)ctx->pos % d->max); + + while (bit_pos < d->max) { + bit_pos = find_next_bit_le(d->bitmap, d->max, bit_pos); + if (bit_pos >= d->max) + break; + + de = &d->dentry[bit_pos]; + if (de->file_type < F2FS_FT_MAX) + d_type = f2fs_filetype_table[de->file_type]; + else + d_type = DT_UNKNOWN; + if (!dir_emit(ctx, d->filename[bit_pos], + le16_to_cpu(de->name_len), + le32_to_cpu(de->ino), d_type)) + return true; + + bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); + ctx->pos = start_pos + bit_pos; + } + return false; +} + +static int f2fs_readdir(struct file *file, struct dir_context *ctx) +{ + struct inode *inode = file_inode(file); + unsigned long npages = dir_blocks(inode); + struct f2fs_dentry_block *dentry_blk = NULL; + struct page *dentry_page = NULL; + struct file_ra_state *ra = &file->f_ra; + unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK); + struct f2fs_dentry_ptr d; + + if (f2fs_has_inline_dentry(inode)) + return f2fs_read_inline_dir(file, ctx); + + /* readahead for multi pages of dir */ + if (npages - n > 1 && !ra_has_index(ra, n)) + page_cache_sync_readahead(inode->i_mapping, ra, file, n, + min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES)); + + for (; n < npages; n++) { + dentry_page = get_lock_data_page(inode, n); + if (IS_ERR(dentry_page)) + continue; + + dentry_blk = kmap(dentry_page); + + make_dentry_ptr(&d, (void *)dentry_blk, 1); + + if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK)) + goto stop; + + ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK; + kunmap(dentry_page); + f2fs_put_page(dentry_page, 1); + dentry_page = NULL; + } +stop: + 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, + .iterate = f2fs_readdir, + .fsync = f2fs_sync_file, + .unlocked_ioctl = f2fs_ioctl, +}; diff --git a/kernel/fs/f2fs/f2fs.h b/kernel/fs/f2fs/f2fs.h new file mode 100644 index 000000000..8de34ab6d --- /dev/null +++ b/kernel/fs/f2fs/f2fs.h @@ -0,0 +1,1814 @@ +/* + * fs/f2fs/f2fs.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. + */ +#ifndef _LINUX_F2FS_H +#define _LINUX_F2FS_H + +#include <linux/types.h> +#include <linux/page-flags.h> +#include <linux/buffer_head.h> +#include <linux/slab.h> +#include <linux/crc32.h> +#include <linux/magic.h> +#include <linux/kobject.h> +#include <linux/sched.h> + +#ifdef CONFIG_F2FS_CHECK_FS +#define f2fs_bug_on(sbi, condition) BUG_ON(condition) +#define f2fs_down_write(x, y) down_write_nest_lock(x, y) +#else +#define f2fs_bug_on(sbi, condition) \ + do { \ + if (unlikely(condition)) { \ + WARN_ON(1); \ + set_sbi_flag(sbi, SBI_NEED_FSCK); \ + } \ + } while (0) +#define f2fs_down_write(x, y) down_write(x) +#endif + +/* + * For mount options + */ +#define F2FS_MOUNT_BG_GC 0x00000001 +#define F2FS_MOUNT_DISABLE_ROLL_FORWARD 0x00000002 +#define F2FS_MOUNT_DISCARD 0x00000004 +#define F2FS_MOUNT_NOHEAP 0x00000008 +#define F2FS_MOUNT_XATTR_USER 0x00000010 +#define F2FS_MOUNT_POSIX_ACL 0x00000020 +#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000040 +#define F2FS_MOUNT_INLINE_XATTR 0x00000080 +#define F2FS_MOUNT_INLINE_DATA 0x00000100 +#define F2FS_MOUNT_INLINE_DENTRY 0x00000200 +#define F2FS_MOUNT_FLUSH_MERGE 0x00000400 +#define F2FS_MOUNT_NOBARRIER 0x00000800 +#define F2FS_MOUNT_FASTBOOT 0x00001000 +#define F2FS_MOUNT_EXTENT_CACHE 0x00002000 + +#define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option) +#define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option) +#define test_opt(sbi, option) (sbi->mount_opt.opt & F2FS_MOUNT_##option) + +#define ver_after(a, b) (typecheck(unsigned long long, a) && \ + typecheck(unsigned long long, b) && \ + ((long long)((a) - (b)) > 0)) + +typedef u32 block_t; /* + * should not change u32, since it is the on-disk block + * address format, __le32. + */ +typedef u32 nid_t; + +struct f2fs_mount_info { + unsigned int opt; +}; + +#define CRCPOLY_LE 0xedb88320 + +static inline __u32 f2fs_crc32(void *buf, size_t len) +{ + unsigned char *p = (unsigned char *)buf; + __u32 crc = F2FS_SUPER_MAGIC; + int i; + + while (len--) { + crc ^= *p++; + for (i = 0; i < 8; i++) + crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0); + } + return crc; +} + +static inline bool f2fs_crc_valid(__u32 blk_crc, void *buf, size_t buf_size) +{ + return f2fs_crc32(buf, buf_size) == blk_crc; +} + +/* + * For checkpoint manager + */ +enum { + NAT_BITMAP, + SIT_BITMAP +}; + +enum { + CP_UMOUNT, + CP_FASTBOOT, + CP_SYNC, + CP_RECOVERY, + CP_DISCARD, +}; + +#define DEF_BATCHED_TRIM_SECTIONS 32 +#define BATCHED_TRIM_SEGMENTS(sbi) \ + (SM_I(sbi)->trim_sections * (sbi)->segs_per_sec) + +struct cp_control { + int reason; + __u64 trim_start; + __u64 trim_end; + __u64 trim_minlen; + __u64 trimmed; +}; + +/* + * For CP/NAT/SIT/SSA readahead + */ +enum { + META_CP, + META_NAT, + META_SIT, + META_SSA, + META_POR, +}; + +/* for the list of ino */ +enum { + ORPHAN_INO, /* for orphan ino list */ + APPEND_INO, /* for append ino list */ + UPDATE_INO, /* for update ino list */ + MAX_INO_ENTRY, /* max. list */ +}; + +struct ino_entry { + struct list_head list; /* list head */ + nid_t ino; /* inode number */ +}; + +/* + * for the list of directory inodes or gc inodes. + * NOTE: there are two slab users for this structure, if we add/modify/delete + * fields in structure for one of slab users, it may affect fields or size of + * other one, in this condition, it's better to split both of slab and related + * data structure. + */ +struct inode_entry { + struct list_head list; /* list head */ + struct inode *inode; /* vfs inode pointer */ +}; + +/* for the list of blockaddresses to be discarded */ +struct discard_entry { + struct list_head list; /* list head */ + block_t blkaddr; /* block address to be discarded */ + int len; /* # of consecutive blocks of the discard */ +}; + +/* for the list of fsync inodes, used only during recovery */ +struct fsync_inode_entry { + struct list_head list; /* list head */ + struct inode *inode; /* vfs inode pointer */ + block_t blkaddr; /* block address locating the last fsync */ + block_t last_dentry; /* block address locating the last dentry */ + block_t last_inode; /* block address locating the last inode */ +}; + +#define nats_in_cursum(sum) (le16_to_cpu(sum->n_nats)) +#define sits_in_cursum(sum) (le16_to_cpu(sum->n_sits)) + +#define nat_in_journal(sum, i) (sum->nat_j.entries[i].ne) +#define nid_in_journal(sum, i) (sum->nat_j.entries[i].nid) +#define sit_in_journal(sum, i) (sum->sit_j.entries[i].se) +#define segno_in_journal(sum, i) (sum->sit_j.entries[i].segno) + +#define MAX_NAT_JENTRIES(sum) (NAT_JOURNAL_ENTRIES - nats_in_cursum(sum)) +#define MAX_SIT_JENTRIES(sum) (SIT_JOURNAL_ENTRIES - sits_in_cursum(sum)) + +static inline int update_nats_in_cursum(struct f2fs_summary_block *rs, int i) +{ + int before = nats_in_cursum(rs); + rs->n_nats = cpu_to_le16(before + i); + return before; +} + +static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i) +{ + int before = sits_in_cursum(rs); + rs->n_sits = cpu_to_le16(before + i); + return before; +} + +static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size, + int type) +{ + if (type == NAT_JOURNAL) + return size <= MAX_NAT_JENTRIES(sum); + return size <= MAX_SIT_JENTRIES(sum); +} + +/* + * ioctl commands + */ +#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS +#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS +#define F2FS_IOC_GETVERSION FS_IOC_GETVERSION + +#define F2FS_IOCTL_MAGIC 0xf5 +#define F2FS_IOC_START_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 1) +#define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2) +#define F2FS_IOC_START_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 3) +#define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4) +#define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5) + +/* + * should be same as XFS_IOC_GOINGDOWN. + * Flags for going down operation used by FS_IOC_GOINGDOWN + */ +#define F2FS_IOC_SHUTDOWN _IOR('X', 125, __u32) /* Shutdown */ +#define F2FS_GOING_DOWN_FULLSYNC 0x0 /* going down with full sync */ +#define F2FS_GOING_DOWN_METASYNC 0x1 /* going down with metadata */ +#define F2FS_GOING_DOWN_NOSYNC 0x2 /* going down */ + +#if defined(__KERNEL__) && defined(CONFIG_COMPAT) +/* + * ioctl commands in 32 bit emulation + */ +#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#endif + +/* + * For INODE and NODE manager + */ +/* for directory operations */ +struct f2fs_dentry_ptr { + const void *bitmap; + struct f2fs_dir_entry *dentry; + __u8 (*filename)[F2FS_SLOT_LEN]; + int max; +}; + +static inline void make_dentry_ptr(struct f2fs_dentry_ptr *d, + void *src, int type) +{ + if (type == 1) { + struct f2fs_dentry_block *t = (struct f2fs_dentry_block *)src; + d->max = NR_DENTRY_IN_BLOCK; + d->bitmap = &t->dentry_bitmap; + d->dentry = t->dentry; + d->filename = t->filename; + } else { + struct f2fs_inline_dentry *t = (struct f2fs_inline_dentry *)src; + d->max = NR_INLINE_DENTRY; + d->bitmap = &t->dentry_bitmap; + d->dentry = t->dentry; + d->filename = t->filename; + } +} + +/* + * XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1 + * as its node offset to distinguish from index node blocks. + * But some bits are used to mark the node block. + */ +#define XATTR_NODE_OFFSET ((((unsigned int)-1) << OFFSET_BIT_SHIFT) \ + >> OFFSET_BIT_SHIFT) +enum { + ALLOC_NODE, /* allocate a new node page if needed */ + LOOKUP_NODE, /* look up a node without readahead */ + LOOKUP_NODE_RA, /* + * look up a node with readahead called + * by get_data_block. + */ +}; + +#define F2FS_LINK_MAX 32000 /* maximum link count per file */ + +#define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */ + +/* vector size for gang look-up from extent cache that consists of radix tree */ +#define EXT_TREE_VEC_SIZE 64 + +/* for in-memory extent cache entry */ +#define F2FS_MIN_EXTENT_LEN 64 /* minimum extent length */ + +/* number of extent info in extent cache we try to shrink */ +#define EXTENT_CACHE_SHRINK_NUMBER 128 + +struct extent_info { + unsigned int fofs; /* start offset in a file */ + u32 blk; /* start block address of the extent */ + unsigned int len; /* length of the extent */ +}; + +struct extent_node { + struct rb_node rb_node; /* rb node located in rb-tree */ + struct list_head list; /* node in global extent list of sbi */ + struct extent_info ei; /* extent info */ +}; + +struct extent_tree { + nid_t ino; /* inode number */ + struct rb_root root; /* root of extent info rb-tree */ + struct extent_node *cached_en; /* recently accessed extent node */ + rwlock_t lock; /* protect extent info rb-tree */ + atomic_t refcount; /* reference count of rb-tree */ + unsigned int count; /* # of extent node in rb-tree*/ +}; + +/* + * i_advise uses FADVISE_XXX_BIT. We can add additional hints later. + */ +#define FADVISE_COLD_BIT 0x01 +#define FADVISE_LOST_PINO_BIT 0x02 + +#define DEF_DIR_LEVEL 0 + +struct f2fs_inode_info { + struct inode vfs_inode; /* serve a vfs inode */ + unsigned long i_flags; /* keep an inode flags for ioctl */ + unsigned char i_advise; /* use to give file attribute hints */ + unsigned char i_dir_level; /* use for dentry level for large dir */ + unsigned int i_current_depth; /* use only in directory structure */ + unsigned int i_pino; /* parent inode number */ + umode_t i_acl_mode; /* keep file acl mode temporarily */ + + /* Use below internally in f2fs*/ + unsigned long flags; /* use to pass per-file flags */ + struct rw_semaphore i_sem; /* protect fi info */ + atomic_t dirty_pages; /* # of dirty pages */ + f2fs_hash_t chash; /* hash value of given file name */ + unsigned int clevel; /* maximum level of given file name */ + nid_t i_xattr_nid; /* node id that contains xattrs */ + unsigned long long xattr_ver; /* cp version of xattr modification */ + struct extent_info ext; /* in-memory extent cache entry */ + rwlock_t ext_lock; /* rwlock for single extent cache */ + struct inode_entry *dirty_dir; /* the pointer of dirty dir */ + + struct radix_tree_root inmem_root; /* radix tree for inmem pages */ + struct list_head inmem_pages; /* inmemory pages managed by f2fs */ + struct mutex inmem_lock; /* lock for inmemory pages */ +}; + +static inline void get_extent_info(struct extent_info *ext, + struct f2fs_extent i_ext) +{ + ext->fofs = le32_to_cpu(i_ext.fofs); + ext->blk = le32_to_cpu(i_ext.blk); + ext->len = le32_to_cpu(i_ext.len); +} + +static inline void set_raw_extent(struct extent_info *ext, + struct f2fs_extent *i_ext) +{ + i_ext->fofs = cpu_to_le32(ext->fofs); + i_ext->blk = cpu_to_le32(ext->blk); + i_ext->len = cpu_to_le32(ext->len); +} + +static inline void set_extent_info(struct extent_info *ei, unsigned int fofs, + u32 blk, unsigned int len) +{ + ei->fofs = fofs; + ei->blk = blk; + ei->len = len; +} + +static inline bool __is_extent_same(struct extent_info *ei1, + struct extent_info *ei2) +{ + return (ei1->fofs == ei2->fofs && ei1->blk == ei2->blk && + ei1->len == ei2->len); +} + +static inline bool __is_extent_mergeable(struct extent_info *back, + struct extent_info *front) +{ + return (back->fofs + back->len == front->fofs && + back->blk + back->len == front->blk); +} + +static inline bool __is_back_mergeable(struct extent_info *cur, + struct extent_info *back) +{ + return __is_extent_mergeable(back, cur); +} + +static inline bool __is_front_mergeable(struct extent_info *cur, + struct extent_info *front) +{ + return __is_extent_mergeable(cur, front); +} + +struct f2fs_nm_info { + block_t nat_blkaddr; /* base disk address of NAT */ + nid_t max_nid; /* maximum possible node ids */ + nid_t available_nids; /* maximum available node ids */ + nid_t next_scan_nid; /* the next nid to be scanned */ + unsigned int ram_thresh; /* control the memory footprint */ + + /* NAT cache management */ + struct radix_tree_root nat_root;/* root of the nat entry cache */ + struct radix_tree_root nat_set_root;/* root of the nat set cache */ + struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */ + struct list_head nat_entries; /* cached nat entry list (clean) */ + unsigned int nat_cnt; /* the # of cached nat entries */ + unsigned int dirty_nat_cnt; /* total num of nat entries in set */ + + /* free node ids management */ + struct radix_tree_root free_nid_root;/* root of the free_nid cache */ + struct list_head free_nid_list; /* a list for free nids */ + spinlock_t free_nid_list_lock; /* protect free nid list */ + unsigned int fcnt; /* the number of free node id */ + struct mutex build_lock; /* lock for build free nids */ + + /* for checkpoint */ + char *nat_bitmap; /* NAT bitmap pointer */ + int bitmap_size; /* bitmap size */ +}; + +/* + * this structure is used as one of function parameters. + * all the information are dedicated to a given direct node block determined + * by the data offset in a file. + */ +struct dnode_of_data { + struct inode *inode; /* vfs inode pointer */ + struct page *inode_page; /* its inode page, NULL is possible */ + struct page *node_page; /* cached direct node page */ + nid_t nid; /* node id of the direct node block */ + unsigned int ofs_in_node; /* data offset in the node page */ + bool inode_page_locked; /* inode page is locked or not */ + block_t data_blkaddr; /* block address of the node block */ +}; + +static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode, + struct page *ipage, struct page *npage, nid_t nid) +{ + memset(dn, 0, sizeof(*dn)); + dn->inode = inode; + dn->inode_page = ipage; + dn->node_page = npage; + dn->nid = nid; +} + +/* + * For SIT manager + * + * By default, there are 6 active log areas across the whole main area. + * When considering hot and cold data separation to reduce cleaning overhead, + * we split 3 for data logs and 3 for node logs as hot, warm, and cold types, + * respectively. + * In the current design, you should not change the numbers intentionally. + * Instead, as a mount option such as active_logs=x, you can use 2, 4, and 6 + * logs individually according to the underlying devices. (default: 6) + * Just in case, on-disk layout covers maximum 16 logs that consist of 8 for + * data and 8 for node logs. + */ +#define NR_CURSEG_DATA_TYPE (3) +#define NR_CURSEG_NODE_TYPE (3) +#define NR_CURSEG_TYPE (NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE) + +enum { + CURSEG_HOT_DATA = 0, /* directory entry blocks */ + CURSEG_WARM_DATA, /* data blocks */ + CURSEG_COLD_DATA, /* multimedia or GCed data blocks */ + CURSEG_HOT_NODE, /* direct node blocks of directory files */ + CURSEG_WARM_NODE, /* direct node blocks of normal files */ + CURSEG_COLD_NODE, /* indirect node blocks */ + NO_CHECK_TYPE, + CURSEG_DIRECT_IO, /* to use for the direct IO path */ +}; + +struct flush_cmd { + struct completion wait; + struct llist_node llnode; + int ret; +}; + +struct flush_cmd_control { + struct task_struct *f2fs_issue_flush; /* flush thread */ + wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */ + struct llist_head issue_list; /* list for command issue */ + struct llist_node *dispatch_list; /* list for command dispatch */ +}; + +struct f2fs_sm_info { + struct sit_info *sit_info; /* whole segment information */ + struct free_segmap_info *free_info; /* free segment information */ + struct dirty_seglist_info *dirty_info; /* dirty segment information */ + struct curseg_info *curseg_array; /* active segment information */ + + block_t seg0_blkaddr; /* block address of 0'th segment */ + block_t main_blkaddr; /* start block address of main area */ + block_t ssa_blkaddr; /* start block address of SSA area */ + + unsigned int segment_count; /* total # of segments */ + unsigned int main_segments; /* # of segments in main area */ + unsigned int reserved_segments; /* # of reserved segments */ + unsigned int ovp_segments; /* # of overprovision segments */ + + /* a threshold to reclaim prefree segments */ + unsigned int rec_prefree_segments; + + /* for small discard management */ + struct list_head discard_list; /* 4KB discard list */ + int nr_discards; /* # of discards in the list */ + int max_discards; /* max. discards to be issued */ + + /* for batched trimming */ + unsigned int trim_sections; /* # of sections to trim */ + + struct list_head sit_entry_set; /* sit entry set list */ + + unsigned int ipu_policy; /* in-place-update policy */ + unsigned int min_ipu_util; /* in-place-update threshold */ + unsigned int min_fsync_blocks; /* threshold for fsync */ + + /* for flush command control */ + struct flush_cmd_control *cmd_control_info; + +}; + +/* + * For superblock + */ +/* + * COUNT_TYPE for monitoring + * + * f2fs monitors the number of several block types such as on-writeback, + * dirty dentry blocks, dirty node blocks, and dirty meta blocks. + */ +enum count_type { + F2FS_WRITEBACK, + F2FS_DIRTY_DENTS, + F2FS_DIRTY_NODES, + F2FS_DIRTY_META, + F2FS_INMEM_PAGES, + NR_COUNT_TYPE, +}; + +/* + * The below are the page types of bios used in submit_bio(). + * The available types are: + * DATA User data pages. It operates as async mode. + * NODE Node pages. It operates as async mode. + * META FS metadata pages such as SIT, NAT, CP. + * NR_PAGE_TYPE The number of page types. + * META_FLUSH Make sure the previous pages are written + * with waiting the bio's completion + * ... Only can be used with META. + */ +#define PAGE_TYPE_OF_BIO(type) ((type) > META ? META : (type)) +enum page_type { + DATA, + NODE, + META, + NR_PAGE_TYPE, + META_FLUSH, + INMEM, /* the below types are used by tracepoints only. */ + INMEM_DROP, + IPU, + OPU, +}; + +struct f2fs_io_info { + enum page_type type; /* contains DATA/NODE/META/META_FLUSH */ + int rw; /* contains R/RS/W/WS with REQ_META/REQ_PRIO */ + block_t blk_addr; /* block address to be written */ +}; + +#define is_read_io(rw) (((rw) & 1) == READ) +struct f2fs_bio_info { + struct f2fs_sb_info *sbi; /* f2fs superblock */ + struct bio *bio; /* bios to merge */ + sector_t last_block_in_bio; /* last block number */ + struct f2fs_io_info fio; /* store buffered io info. */ + struct rw_semaphore io_rwsem; /* blocking op for bio */ +}; + +/* for inner inode cache management */ +struct inode_management { + struct radix_tree_root ino_root; /* ino entry array */ + spinlock_t ino_lock; /* for ino entry lock */ + struct list_head ino_list; /* inode list head */ + unsigned long ino_num; /* number of entries */ +}; + +/* For s_flag in struct f2fs_sb_info */ +enum { + SBI_IS_DIRTY, /* dirty flag for checkpoint */ + SBI_IS_CLOSE, /* specify unmounting */ + SBI_NEED_FSCK, /* need fsck.f2fs to fix */ + SBI_POR_DOING, /* recovery is doing or not */ +}; + +struct f2fs_sb_info { + struct super_block *sb; /* pointer to VFS super block */ + struct proc_dir_entry *s_proc; /* proc entry */ + struct buffer_head *raw_super_buf; /* buffer head of raw sb */ + struct f2fs_super_block *raw_super; /* raw super block pointer */ + int s_flag; /* flags for sbi */ + + /* for node-related operations */ + struct f2fs_nm_info *nm_info; /* node manager */ + struct inode *node_inode; /* cache node blocks */ + + /* for segment-related operations */ + struct f2fs_sm_info *sm_info; /* segment manager */ + + /* for bio operations */ + struct f2fs_bio_info read_io; /* for read bios */ + struct f2fs_bio_info write_io[NR_PAGE_TYPE]; /* for write bios */ + + /* for checkpoint */ + struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */ + struct inode *meta_inode; /* cache meta blocks */ + struct mutex cp_mutex; /* checkpoint procedure lock */ + struct rw_semaphore cp_rwsem; /* blocking FS operations */ + struct rw_semaphore node_write; /* locking node writes */ + struct mutex writepages; /* mutex for writepages() */ + wait_queue_head_t cp_wait; + + struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ + + /* for orphan inode, use 0'th array */ + unsigned int max_orphans; /* max orphan inodes */ + + /* for directory inode management */ + struct list_head dir_inode_list; /* dir inode list */ + spinlock_t dir_inode_lock; /* for dir inode list lock */ + + /* for extent tree cache */ + struct radix_tree_root extent_tree_root;/* cache extent cache entries */ + struct rw_semaphore extent_tree_lock; /* locking extent radix tree */ + struct list_head extent_list; /* lru list for shrinker */ + spinlock_t extent_lock; /* locking extent lru list */ + int total_ext_tree; /* extent tree count */ + atomic_t total_ext_node; /* extent info count */ + + /* basic filesystem units */ + unsigned int log_sectors_per_block; /* log2 sectors per block */ + unsigned int log_blocksize; /* log2 block size */ + unsigned int blocksize; /* block size */ + unsigned int root_ino_num; /* root inode number*/ + unsigned int node_ino_num; /* node inode number*/ + unsigned int meta_ino_num; /* meta inode number*/ + unsigned int log_blocks_per_seg; /* log2 blocks per segment */ + unsigned int blocks_per_seg; /* blocks per segment */ + unsigned int segs_per_sec; /* segments per section */ + unsigned int secs_per_zone; /* sections per zone */ + unsigned int total_sections; /* total section count */ + unsigned int total_node_count; /* total node block count */ + unsigned int total_valid_node_count; /* valid node block count */ + unsigned int total_valid_inode_count; /* valid inode count */ + int active_logs; /* # of active logs */ + int dir_level; /* directory level */ + + block_t user_block_count; /* # of user blocks */ + block_t total_valid_block_count; /* # of valid blocks */ + block_t alloc_valid_block_count; /* # of allocated blocks */ + block_t last_valid_block_count; /* for recovery */ + u32 s_next_generation; /* for NFS support */ + atomic_t nr_pages[NR_COUNT_TYPE]; /* # of pages, see count_type */ + + struct f2fs_mount_info mount_opt; /* mount options */ + + /* for cleaning operations */ + struct mutex gc_mutex; /* mutex for GC */ + struct f2fs_gc_kthread *gc_thread; /* GC thread */ + unsigned int cur_victim_sec; /* current victim section num */ + + /* maximum # of trials to find a victim segment for SSR and GC */ + unsigned int max_victim_search; + + /* + * for stat information. + * one is for the LFS mode, and the other is for the SSR mode. + */ +#ifdef CONFIG_F2FS_STAT_FS + struct f2fs_stat_info *stat_info; /* FS status information */ + unsigned int segment_count[2]; /* # of allocated segments */ + unsigned int block_count[2]; /* # of allocated blocks */ + atomic_t inplace_count; /* # of inplace update */ + int total_hit_ext, read_hit_ext; /* extent cache hit ratio */ + atomic_t inline_inode; /* # of inline_data inodes */ + atomic_t inline_dir; /* # of inline_dentry inodes */ + int bg_gc; /* background gc calls */ + unsigned int n_dirty_dirs; /* # of dir inodes */ +#endif + unsigned int last_victim[2]; /* last victim segment # */ + spinlock_t stat_lock; /* lock for stat operations */ + + /* For sysfs suppport */ + struct kobject s_kobj; + struct completion s_kobj_unregister; +}; + +/* + * Inline functions + */ +static inline struct f2fs_inode_info *F2FS_I(struct inode *inode) +{ + return container_of(inode, struct f2fs_inode_info, vfs_inode); +} + +static inline struct f2fs_sb_info *F2FS_SB(struct super_block *sb) +{ + return sb->s_fs_info; +} + +static inline struct f2fs_sb_info *F2FS_I_SB(struct inode *inode) +{ + return F2FS_SB(inode->i_sb); +} + +static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping) +{ + return F2FS_I_SB(mapping->host); +} + +static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page) +{ + return F2FS_M_SB(page->mapping); +} + +static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi) +{ + return (struct f2fs_super_block *)(sbi->raw_super); +} + +static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi) +{ + return (struct f2fs_checkpoint *)(sbi->ckpt); +} + +static inline struct f2fs_node *F2FS_NODE(struct page *page) +{ + return (struct f2fs_node *)page_address(page); +} + +static inline struct f2fs_inode *F2FS_INODE(struct page *page) +{ + return &((struct f2fs_node *)page_address(page))->i; +} + +static inline struct f2fs_nm_info *NM_I(struct f2fs_sb_info *sbi) +{ + return (struct f2fs_nm_info *)(sbi->nm_info); +} + +static inline struct f2fs_sm_info *SM_I(struct f2fs_sb_info *sbi) +{ + return (struct f2fs_sm_info *)(sbi->sm_info); +} + +static inline struct sit_info *SIT_I(struct f2fs_sb_info *sbi) +{ + return (struct sit_info *)(SM_I(sbi)->sit_info); +} + +static inline struct free_segmap_info *FREE_I(struct f2fs_sb_info *sbi) +{ + return (struct free_segmap_info *)(SM_I(sbi)->free_info); +} + +static inline struct dirty_seglist_info *DIRTY_I(struct f2fs_sb_info *sbi) +{ + return (struct dirty_seglist_info *)(SM_I(sbi)->dirty_info); +} + +static inline struct address_space *META_MAPPING(struct f2fs_sb_info *sbi) +{ + return sbi->meta_inode->i_mapping; +} + +static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi) +{ + return sbi->node_inode->i_mapping; +} + +static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type) +{ + return sbi->s_flag & (0x01 << type); +} + +static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type) +{ + sbi->s_flag |= (0x01 << type); +} + +static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type) +{ + sbi->s_flag &= ~(0x01 << type); +} + +static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp) +{ + return le64_to_cpu(cp->checkpoint_ver); +} + +static inline bool is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) +{ + unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags); + return ckpt_flags & f; +} + +static inline void set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) +{ + unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags); + ckpt_flags |= f; + cp->ckpt_flags = cpu_to_le32(ckpt_flags); +} + +static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) +{ + unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags); + ckpt_flags &= (~f); + cp->ckpt_flags = cpu_to_le32(ckpt_flags); +} + +static inline void f2fs_lock_op(struct f2fs_sb_info *sbi) +{ + down_read(&sbi->cp_rwsem); +} + +static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi) +{ + up_read(&sbi->cp_rwsem); +} + +static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) +{ + f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex); +} + +static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) +{ + up_write(&sbi->cp_rwsem); +} + +static inline int __get_cp_reason(struct f2fs_sb_info *sbi) +{ + int reason = CP_SYNC; + + if (test_opt(sbi, FASTBOOT)) + reason = CP_FASTBOOT; + if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) + reason = CP_UMOUNT; + return reason; +} + +static inline bool __remain_node_summaries(int reason) +{ + return (reason == CP_UMOUNT || reason == CP_FASTBOOT); +} + +static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi) +{ + return (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) || + is_set_ckpt_flags(F2FS_CKPT(sbi), CP_FASTBOOT_FLAG)); +} + +/* + * Check whether the given nid is within node id range. + */ +static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) +{ + if (unlikely(nid < F2FS_ROOT_INO(sbi))) + return -EINVAL; + if (unlikely(nid >= NM_I(sbi)->max_nid)) + return -EINVAL; + return 0; +} + +#define F2FS_DEFAULT_ALLOCATED_BLOCKS 1 + +/* + * Check whether the inode has blocks or not + */ +static inline int F2FS_HAS_BLOCKS(struct inode *inode) +{ + if (F2FS_I(inode)->i_xattr_nid) + return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS + 1; + else + return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS; +} + +static inline bool f2fs_has_xattr_block(unsigned int ofs) +{ + return ofs == XATTR_NODE_OFFSET; +} + +static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi, + struct inode *inode, blkcnt_t count) +{ + block_t valid_block_count; + + spin_lock(&sbi->stat_lock); + valid_block_count = + sbi->total_valid_block_count + (block_t)count; + if (unlikely(valid_block_count > sbi->user_block_count)) { + spin_unlock(&sbi->stat_lock); + return false; + } + inode->i_blocks += count; + sbi->total_valid_block_count = valid_block_count; + sbi->alloc_valid_block_count += (block_t)count; + spin_unlock(&sbi->stat_lock); + return true; +} + +static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, + struct inode *inode, + blkcnt_t count) +{ + spin_lock(&sbi->stat_lock); + f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); + f2fs_bug_on(sbi, inode->i_blocks < count); + inode->i_blocks -= count; + sbi->total_valid_block_count -= (block_t)count; + spin_unlock(&sbi->stat_lock); +} + +static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) +{ + atomic_inc(&sbi->nr_pages[count_type]); + set_sbi_flag(sbi, SBI_IS_DIRTY); +} + +static inline void inode_inc_dirty_pages(struct inode *inode) +{ + atomic_inc(&F2FS_I(inode)->dirty_pages); + if (S_ISDIR(inode->i_mode)) + inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS); +} + +static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type) +{ + atomic_dec(&sbi->nr_pages[count_type]); +} + +static inline void inode_dec_dirty_pages(struct inode *inode) +{ + if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode)) + return; + + atomic_dec(&F2FS_I(inode)->dirty_pages); + + if (S_ISDIR(inode->i_mode)) + dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS); +} + +static inline int get_pages(struct f2fs_sb_info *sbi, int count_type) +{ + return atomic_read(&sbi->nr_pages[count_type]); +} + +static inline int get_dirty_pages(struct inode *inode) +{ + return atomic_read(&F2FS_I(inode)->dirty_pages); +} + +static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type) +{ + unsigned int pages_per_sec = sbi->segs_per_sec * + (1 << sbi->log_blocks_per_seg); + return ((get_pages(sbi, block_type) + pages_per_sec - 1) + >> sbi->log_blocks_per_seg) / sbi->segs_per_sec; +} + +static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi) +{ + return sbi->total_valid_block_count; +} + +static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + + /* return NAT or SIT bitmap */ + if (flag == NAT_BITMAP) + return le32_to_cpu(ckpt->nat_ver_bitmap_bytesize); + else if (flag == SIT_BITMAP) + return le32_to_cpu(ckpt->sit_ver_bitmap_bytesize); + + return 0; +} + +static inline block_t __cp_payload(struct f2fs_sb_info *sbi) +{ + return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload); +} + +static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + int offset; + + if (__cp_payload(sbi) > 0) { + if (flag == NAT_BITMAP) + return &ckpt->sit_nat_version_bitmap; + else + return (unsigned char *)ckpt + F2FS_BLKSIZE; + } else { + offset = (flag == NAT_BITMAP) ? + le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0; + return &ckpt->sit_nat_version_bitmap + offset; + } +} + +static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi) +{ + block_t start_addr; + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + unsigned long long ckpt_version = cur_cp_version(ckpt); + + start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr); + + /* + * odd numbered checkpoint should at cp segment 0 + * and even segment must be at cp segment 1 + */ + if (!(ckpt_version & 1)) + start_addr += sbi->blocks_per_seg; + + return start_addr; +} + +static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi) +{ + return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum); +} + +static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi, + struct inode *inode) +{ + block_t valid_block_count; + unsigned int valid_node_count; + + spin_lock(&sbi->stat_lock); + + valid_block_count = sbi->total_valid_block_count + 1; + if (unlikely(valid_block_count > sbi->user_block_count)) { + spin_unlock(&sbi->stat_lock); + return false; + } + + valid_node_count = sbi->total_valid_node_count + 1; + if (unlikely(valid_node_count > sbi->total_node_count)) { + spin_unlock(&sbi->stat_lock); + return false; + } + + if (inode) + inode->i_blocks++; + + sbi->alloc_valid_block_count++; + sbi->total_valid_node_count++; + sbi->total_valid_block_count++; + spin_unlock(&sbi->stat_lock); + + return true; +} + +static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, + struct inode *inode) +{ + spin_lock(&sbi->stat_lock); + + f2fs_bug_on(sbi, !sbi->total_valid_block_count); + f2fs_bug_on(sbi, !sbi->total_valid_node_count); + f2fs_bug_on(sbi, !inode->i_blocks); + + inode->i_blocks--; + sbi->total_valid_node_count--; + sbi->total_valid_block_count--; + + spin_unlock(&sbi->stat_lock); +} + +static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi) +{ + return sbi->total_valid_node_count; +} + +static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi) +{ + spin_lock(&sbi->stat_lock); + f2fs_bug_on(sbi, sbi->total_valid_inode_count == sbi->total_node_count); + sbi->total_valid_inode_count++; + spin_unlock(&sbi->stat_lock); +} + +static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi) +{ + spin_lock(&sbi->stat_lock); + f2fs_bug_on(sbi, !sbi->total_valid_inode_count); + sbi->total_valid_inode_count--; + spin_unlock(&sbi->stat_lock); +} + +static inline unsigned int valid_inode_count(struct f2fs_sb_info *sbi) +{ + return sbi->total_valid_inode_count; +} + +static inline void f2fs_put_page(struct page *page, int unlock) +{ + if (!page) + return; + + if (unlock) { + f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page)); + unlock_page(page); + } + page_cache_release(page); +} + +static inline void f2fs_put_dnode(struct dnode_of_data *dn) +{ + if (dn->node_page) + f2fs_put_page(dn->node_page, 1); + if (dn->inode_page && dn->node_page != dn->inode_page) + f2fs_put_page(dn->inode_page, 0); + dn->node_page = NULL; + dn->inode_page = NULL; +} + +static inline struct kmem_cache *f2fs_kmem_cache_create(const char *name, + size_t size) +{ + return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, NULL); +} + +static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep, + gfp_t flags) +{ + void *entry; +retry: + entry = kmem_cache_alloc(cachep, flags); + if (!entry) { + cond_resched(); + goto retry; + } + + return entry; +} + +static inline void f2fs_radix_tree_insert(struct radix_tree_root *root, + unsigned long index, void *item) +{ + while (radix_tree_insert(root, index, item)) + cond_resched(); +} + +#define RAW_IS_INODE(p) ((p)->footer.nid == (p)->footer.ino) + +static inline bool IS_INODE(struct page *page) +{ + struct f2fs_node *p = F2FS_NODE(page); + return RAW_IS_INODE(p); +} + +static inline __le32 *blkaddr_in_node(struct f2fs_node *node) +{ + return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr; +} + +static inline block_t datablock_addr(struct page *node_page, + unsigned int offset) +{ + struct f2fs_node *raw_node; + __le32 *addr_array; + raw_node = F2FS_NODE(node_page); + addr_array = blkaddr_in_node(raw_node); + return le32_to_cpu(addr_array[offset]); +} + +static inline int f2fs_test_bit(unsigned int nr, char *addr) +{ + int mask; + + addr += (nr >> 3); + mask = 1 << (7 - (nr & 0x07)); + return mask & *addr; +} + +static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr) +{ + int mask; + int ret; + + addr += (nr >> 3); + mask = 1 << (7 - (nr & 0x07)); + ret = mask & *addr; + *addr |= mask; + return ret; +} + +static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr) +{ + int mask; + int ret; + + addr += (nr >> 3); + mask = 1 << (7 - (nr & 0x07)); + ret = mask & *addr; + *addr &= ~mask; + return ret; +} + +static inline void f2fs_change_bit(unsigned int nr, char *addr) +{ + int mask; + + addr += (nr >> 3); + mask = 1 << (7 - (nr & 0x07)); + *addr ^= mask; +} + +/* used for f2fs_inode_info->flags */ +enum { + FI_NEW_INODE, /* indicate newly allocated inode */ + FI_DIRTY_INODE, /* indicate inode is dirty or not */ + FI_DIRTY_DIR, /* indicate directory has dirty pages */ + FI_INC_LINK, /* need to increment i_nlink */ + FI_ACL_MODE, /* indicate acl mode */ + FI_NO_ALLOC, /* should not allocate any blocks */ + FI_UPDATE_DIR, /* should update inode block for consistency */ + FI_DELAY_IPUT, /* used for the recovery */ + FI_NO_EXTENT, /* not to use the extent cache */ + FI_INLINE_XATTR, /* used for inline xattr */ + FI_INLINE_DATA, /* used for inline data*/ + FI_INLINE_DENTRY, /* used for inline dentry */ + FI_APPEND_WRITE, /* inode has appended data */ + FI_UPDATE_WRITE, /* inode has in-place-update data */ + FI_NEED_IPU, /* used for ipu per file */ + FI_ATOMIC_FILE, /* indicate atomic file */ + FI_VOLATILE_FILE, /* indicate volatile file */ + FI_FIRST_BLOCK_WRITTEN, /* indicate #0 data block was written */ + FI_DROP_CACHE, /* drop dirty page cache */ + FI_DATA_EXIST, /* indicate data exists */ + FI_INLINE_DOTS, /* indicate inline dot dentries */ +}; + +static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag) +{ + if (!test_bit(flag, &fi->flags)) + set_bit(flag, &fi->flags); +} + +static inline int is_inode_flag_set(struct f2fs_inode_info *fi, int flag) +{ + return test_bit(flag, &fi->flags); +} + +static inline void clear_inode_flag(struct f2fs_inode_info *fi, int flag) +{ + if (test_bit(flag, &fi->flags)) + clear_bit(flag, &fi->flags); +} + +static inline void set_acl_inode(struct f2fs_inode_info *fi, umode_t mode) +{ + fi->i_acl_mode = mode; + set_inode_flag(fi, FI_ACL_MODE); +} + +static inline void get_inline_info(struct f2fs_inode_info *fi, + struct f2fs_inode *ri) +{ + if (ri->i_inline & F2FS_INLINE_XATTR) + set_inode_flag(fi, FI_INLINE_XATTR); + if (ri->i_inline & F2FS_INLINE_DATA) + set_inode_flag(fi, FI_INLINE_DATA); + if (ri->i_inline & F2FS_INLINE_DENTRY) + set_inode_flag(fi, FI_INLINE_DENTRY); + if (ri->i_inline & F2FS_DATA_EXIST) + set_inode_flag(fi, FI_DATA_EXIST); + if (ri->i_inline & F2FS_INLINE_DOTS) + set_inode_flag(fi, FI_INLINE_DOTS); +} + +static inline void set_raw_inline(struct f2fs_inode_info *fi, + struct f2fs_inode *ri) +{ + ri->i_inline = 0; + + if (is_inode_flag_set(fi, FI_INLINE_XATTR)) + ri->i_inline |= F2FS_INLINE_XATTR; + if (is_inode_flag_set(fi, FI_INLINE_DATA)) + ri->i_inline |= F2FS_INLINE_DATA; + if (is_inode_flag_set(fi, FI_INLINE_DENTRY)) + ri->i_inline |= F2FS_INLINE_DENTRY; + if (is_inode_flag_set(fi, FI_DATA_EXIST)) + ri->i_inline |= F2FS_DATA_EXIST; + if (is_inode_flag_set(fi, FI_INLINE_DOTS)) + ri->i_inline |= F2FS_INLINE_DOTS; +} + +static inline int f2fs_has_inline_xattr(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR); +} + +static inline unsigned int addrs_per_inode(struct f2fs_inode_info *fi) +{ + if (f2fs_has_inline_xattr(&fi->vfs_inode)) + return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS; + return DEF_ADDRS_PER_INODE; +} + +static inline void *inline_xattr_addr(struct page *page) +{ + struct f2fs_inode *ri = F2FS_INODE(page); + return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE - + F2FS_INLINE_XATTR_ADDRS]); +} + +static inline int inline_xattr_size(struct inode *inode) +{ + if (f2fs_has_inline_xattr(inode)) + return F2FS_INLINE_XATTR_ADDRS << 2; + else + return 0; +} + +static inline int f2fs_has_inline_data(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DATA); +} + +static inline void f2fs_clear_inline_inode(struct inode *inode) +{ + clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + clear_inode_flag(F2FS_I(inode), FI_DATA_EXIST); +} + +static inline int f2fs_exist_data(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_DATA_EXIST); +} + +static inline int f2fs_has_inline_dots(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DOTS); +} + +static inline bool f2fs_is_atomic_file(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_ATOMIC_FILE); +} + +static inline bool f2fs_is_volatile_file(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE); +} + +static inline bool f2fs_is_first_block_written(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); +} + +static inline bool f2fs_is_drop_cache(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_DROP_CACHE); +} + +static inline void *inline_data_addr(struct page *page) +{ + struct f2fs_inode *ri = F2FS_INODE(page); + return (void *)&(ri->i_addr[1]); +} + +static inline int f2fs_has_inline_dentry(struct inode *inode) +{ + return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DENTRY); +} + +static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page) +{ + if (!f2fs_has_inline_dentry(dir)) + kunmap(page); +} + +static inline int f2fs_readonly(struct super_block *sb) +{ + return sb->s_flags & MS_RDONLY; +} + +static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi) +{ + return is_set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG); +} + +static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi) +{ + set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG); + sbi->sb->s_flags |= MS_RDONLY; +} + +#define get_inode_mode(i) \ + ((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \ + (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) + +/* get offset of first page in next direct node */ +#define PGOFS_OF_NEXT_DNODE(pgofs, fi) \ + ((pgofs < ADDRS_PER_INODE(fi)) ? ADDRS_PER_INODE(fi) : \ + (pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) / \ + ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi)) + +/* + * file.c + */ +int f2fs_sync_file(struct file *, loff_t, loff_t, int); +void truncate_data_blocks(struct dnode_of_data *); +int truncate_blocks(struct inode *, u64, bool); +void f2fs_truncate(struct inode *); +int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *); +int f2fs_setattr(struct dentry *, struct iattr *); +int truncate_hole(struct inode *, pgoff_t, pgoff_t); +int truncate_data_blocks_range(struct dnode_of_data *, int); +long f2fs_ioctl(struct file *, unsigned int, unsigned long); +long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long); + +/* + * inode.c + */ +void f2fs_set_inode_flags(struct inode *); +struct inode *f2fs_iget(struct super_block *, unsigned long); +int try_to_free_nats(struct f2fs_sb_info *, int); +void update_inode(struct inode *, struct page *); +void update_inode_page(struct inode *); +int f2fs_write_inode(struct inode *, struct writeback_control *); +void f2fs_evict_inode(struct inode *); +void handle_failed_inode(struct inode *); + +/* + * namei.c + */ +struct dentry *f2fs_get_parent(struct dentry *child); + +/* + * dir.c + */ +extern unsigned char f2fs_filetype_table[F2FS_FT_MAX]; +void set_de_type(struct f2fs_dir_entry *, umode_t); +struct f2fs_dir_entry *find_target_dentry(struct qstr *, int *, + struct f2fs_dentry_ptr *); +bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *, + unsigned int); +void do_make_empty_dir(struct inode *, struct inode *, + struct f2fs_dentry_ptr *); +struct page *init_inode_metadata(struct inode *, struct inode *, + const struct qstr *, struct page *); +void update_parent_metadata(struct inode *, struct inode *, unsigned int); +int room_for_filename(const void *, int, int); +void f2fs_drop_nlink(struct inode *, struct inode *, struct page *); +struct f2fs_dir_entry *f2fs_find_entry(struct inode *, struct qstr *, + struct page **); +struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **); +ino_t f2fs_inode_by_name(struct inode *, struct qstr *); +void f2fs_set_link(struct inode *, struct f2fs_dir_entry *, + struct page *, struct inode *); +int update_dent_inode(struct inode *, const struct qstr *); +void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *, + const struct qstr *, f2fs_hash_t , unsigned int); +int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t, + umode_t); +void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *, + struct inode *); +int f2fs_do_tmpfile(struct inode *, struct inode *); +int f2fs_make_empty(struct inode *, struct inode *); +bool f2fs_empty_dir(struct inode *); + +static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) +{ + return __f2fs_add_link(d_inode(dentry->d_parent), &dentry->d_name, + inode, inode->i_ino, inode->i_mode); +} + +/* + * super.c + */ +int f2fs_sync_fs(struct super_block *, int); +extern __printf(3, 4) +void f2fs_msg(struct super_block *, const char *, const char *, ...); + +/* + * hash.c + */ +f2fs_hash_t f2fs_dentry_hash(const struct qstr *); + +/* + * node.c + */ +struct dnode_of_data; +struct node_info; + +bool available_free_memory(struct f2fs_sb_info *, int); +bool is_checkpointed_node(struct f2fs_sb_info *, nid_t); +bool has_fsynced_inode(struct f2fs_sb_info *, nid_t); +bool need_inode_block_update(struct f2fs_sb_info *, nid_t); +void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *); +int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int); +int truncate_inode_blocks(struct inode *, pgoff_t); +int truncate_xattr_node(struct inode *, struct page *); +int wait_on_node_pages_writeback(struct f2fs_sb_info *, nid_t); +void remove_inode_page(struct inode *); +struct page *new_inode_page(struct inode *); +struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *); +void ra_node_page(struct f2fs_sb_info *, nid_t); +struct page *get_node_page(struct f2fs_sb_info *, pgoff_t); +struct page *get_node_page_ra(struct page *, int); +void sync_inode_page(struct dnode_of_data *); +int sync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *); +bool alloc_nid(struct f2fs_sb_info *, nid_t *); +void alloc_nid_done(struct f2fs_sb_info *, nid_t); +void alloc_nid_failed(struct f2fs_sb_info *, nid_t); +void recover_inline_xattr(struct inode *, struct page *); +void recover_xattr_data(struct inode *, struct page *, block_t); +int recover_inode_page(struct f2fs_sb_info *, struct page *); +int restore_node_summary(struct f2fs_sb_info *, unsigned int, + struct f2fs_summary_block *); +void flush_nat_entries(struct f2fs_sb_info *); +int build_node_manager(struct f2fs_sb_info *); +void destroy_node_manager(struct f2fs_sb_info *); +int __init create_node_manager_caches(void); +void destroy_node_manager_caches(void); + +/* + * segment.c + */ +void register_inmem_page(struct inode *, struct page *); +void commit_inmem_pages(struct inode *, bool); +void f2fs_balance_fs(struct f2fs_sb_info *); +void f2fs_balance_fs_bg(struct f2fs_sb_info *); +int f2fs_issue_flush(struct f2fs_sb_info *); +int create_flush_cmd_control(struct f2fs_sb_info *); +void destroy_flush_cmd_control(struct f2fs_sb_info *); +void invalidate_blocks(struct f2fs_sb_info *, block_t); +void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t); +void clear_prefree_segments(struct f2fs_sb_info *); +void release_discard_addrs(struct f2fs_sb_info *); +void discard_next_dnode(struct f2fs_sb_info *, block_t); +int npages_for_summary_flush(struct f2fs_sb_info *, bool); +void allocate_new_segments(struct f2fs_sb_info *); +int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *); +struct page *get_sum_page(struct f2fs_sb_info *, unsigned int); +void write_meta_page(struct f2fs_sb_info *, struct page *); +void write_node_page(struct f2fs_sb_info *, struct page *, + unsigned int, struct f2fs_io_info *); +void write_data_page(struct page *, struct dnode_of_data *, + struct f2fs_io_info *); +void rewrite_data_page(struct page *, struct f2fs_io_info *); +void recover_data_page(struct f2fs_sb_info *, struct page *, + struct f2fs_summary *, block_t, block_t); +void allocate_data_block(struct f2fs_sb_info *, struct page *, + block_t, block_t *, struct f2fs_summary *, int); +void f2fs_wait_on_page_writeback(struct page *, enum page_type); +void write_data_summaries(struct f2fs_sb_info *, block_t); +void write_node_summaries(struct f2fs_sb_info *, block_t); +int lookup_journal_in_cursum(struct f2fs_summary_block *, + int, unsigned int, int); +void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *); +int build_segment_manager(struct f2fs_sb_info *); +void destroy_segment_manager(struct f2fs_sb_info *); +int __init create_segment_manager_caches(void); +void destroy_segment_manager_caches(void); + +/* + * checkpoint.c + */ +struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t); +struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t); +int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int); +void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t); +long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long); +void add_dirty_inode(struct f2fs_sb_info *, nid_t, int type); +void remove_dirty_inode(struct f2fs_sb_info *, nid_t, int type); +void release_dirty_inode(struct f2fs_sb_info *); +bool exist_written_data(struct f2fs_sb_info *, nid_t, int); +int acquire_orphan_inode(struct f2fs_sb_info *); +void release_orphan_inode(struct f2fs_sb_info *); +void add_orphan_inode(struct f2fs_sb_info *, nid_t); +void remove_orphan_inode(struct f2fs_sb_info *, nid_t); +void recover_orphan_inodes(struct f2fs_sb_info *); +int get_valid_checkpoint(struct f2fs_sb_info *); +void update_dirty_page(struct inode *, struct page *); +void add_dirty_dir_inode(struct inode *); +void remove_dirty_dir_inode(struct inode *); +void sync_dirty_dir_inodes(struct f2fs_sb_info *); +void write_checkpoint(struct f2fs_sb_info *, struct cp_control *); +void init_ino_entry_info(struct f2fs_sb_info *); +int __init create_checkpoint_caches(void); +void destroy_checkpoint_caches(void); + +/* + * data.c + */ +void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int); +int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *, + struct f2fs_io_info *); +void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *, + struct f2fs_io_info *); +void set_data_blkaddr(struct dnode_of_data *); +int reserve_new_block(struct dnode_of_data *); +int f2fs_reserve_block(struct dnode_of_data *, pgoff_t); +void f2fs_shrink_extent_tree(struct f2fs_sb_info *, int); +void f2fs_destroy_extent_tree(struct inode *); +void f2fs_init_extent_cache(struct inode *, struct f2fs_extent *); +void f2fs_update_extent_cache(struct dnode_of_data *); +void f2fs_preserve_extent_tree(struct inode *); +struct page *find_data_page(struct inode *, pgoff_t, bool); +struct page *get_lock_data_page(struct inode *, pgoff_t); +struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool); +int do_write_data_page(struct page *, struct f2fs_io_info *); +int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64); +void init_extent_cache_info(struct f2fs_sb_info *); +int __init create_extent_cache(void); +void destroy_extent_cache(void); +void f2fs_invalidate_page(struct page *, unsigned int, unsigned int); +int f2fs_release_page(struct page *, gfp_t); + +/* + * gc.c + */ +int start_gc_thread(struct f2fs_sb_info *); +void stop_gc_thread(struct f2fs_sb_info *); +block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *); +int f2fs_gc(struct f2fs_sb_info *); +void build_gc_manager(struct f2fs_sb_info *); + +/* + * recovery.c + */ +int recover_fsync_data(struct f2fs_sb_info *); +bool space_for_roll_forward(struct f2fs_sb_info *); + +/* + * debug.c + */ +#ifdef CONFIG_F2FS_STAT_FS +struct f2fs_stat_info { + struct list_head stat_list; + struct f2fs_sb_info *sbi; + int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs; + int main_area_segs, main_area_sections, main_area_zones; + int hit_ext, total_ext, ext_tree, ext_node; + int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta; + int nats, dirty_nats, sits, dirty_sits, fnids; + int total_count, utilization; + int bg_gc, inline_inode, inline_dir, inmem_pages, wb_pages; + unsigned int valid_count, valid_node_count, valid_inode_count; + unsigned int bimodal, avg_vblocks; + int util_free, util_valid, util_invalid; + int rsvd_segs, overp_segs; + int dirty_count, node_pages, meta_pages; + int prefree_count, call_count, cp_count; + int tot_segs, node_segs, data_segs, free_segs, free_secs; + int bg_node_segs, bg_data_segs; + int tot_blks, data_blks, node_blks; + int bg_data_blks, bg_node_blks; + int curseg[NR_CURSEG_TYPE]; + int cursec[NR_CURSEG_TYPE]; + int curzone[NR_CURSEG_TYPE]; + + unsigned int segment_count[2]; + unsigned int block_count[2]; + unsigned int inplace_count; + unsigned base_mem, cache_mem, page_mem; +}; + +static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) +{ + return (struct f2fs_stat_info *)sbi->stat_info; +} + +#define stat_inc_cp_count(si) ((si)->cp_count++) +#define stat_inc_call_count(si) ((si)->call_count++) +#define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++) +#define stat_inc_dirty_dir(sbi) ((sbi)->n_dirty_dirs++) +#define stat_dec_dirty_dir(sbi) ((sbi)->n_dirty_dirs--) +#define stat_inc_total_hit(sb) ((F2FS_SB(sb))->total_hit_ext++) +#define stat_inc_read_hit(sb) ((F2FS_SB(sb))->read_hit_ext++) +#define stat_inc_inline_inode(inode) \ + do { \ + if (f2fs_has_inline_data(inode)) \ + (atomic_inc(&F2FS_I_SB(inode)->inline_inode)); \ + } while (0) +#define stat_dec_inline_inode(inode) \ + do { \ + if (f2fs_has_inline_data(inode)) \ + (atomic_dec(&F2FS_I_SB(inode)->inline_inode)); \ + } while (0) +#define stat_inc_inline_dir(inode) \ + do { \ + if (f2fs_has_inline_dentry(inode)) \ + (atomic_inc(&F2FS_I_SB(inode)->inline_dir)); \ + } while (0) +#define stat_dec_inline_dir(inode) \ + do { \ + if (f2fs_has_inline_dentry(inode)) \ + (atomic_dec(&F2FS_I_SB(inode)->inline_dir)); \ + } while (0) +#define stat_inc_seg_type(sbi, curseg) \ + ((sbi)->segment_count[(curseg)->alloc_type]++) +#define stat_inc_block_count(sbi, curseg) \ + ((sbi)->block_count[(curseg)->alloc_type]++) +#define stat_inc_inplace_blocks(sbi) \ + (atomic_inc(&(sbi)->inplace_count)) +#define stat_inc_seg_count(sbi, type, gc_type) \ + do { \ + struct f2fs_stat_info *si = F2FS_STAT(sbi); \ + (si)->tot_segs++; \ + if (type == SUM_TYPE_DATA) { \ + si->data_segs++; \ + si->bg_data_segs += (gc_type == BG_GC) ? 1 : 0; \ + } else { \ + si->node_segs++; \ + si->bg_node_segs += (gc_type == BG_GC) ? 1 : 0; \ + } \ + } while (0) + +#define stat_inc_tot_blk_count(si, blks) \ + (si->tot_blks += (blks)) + +#define stat_inc_data_blk_count(sbi, blks, gc_type) \ + do { \ + struct f2fs_stat_info *si = F2FS_STAT(sbi); \ + stat_inc_tot_blk_count(si, blks); \ + si->data_blks += (blks); \ + si->bg_data_blks += (gc_type == BG_GC) ? (blks) : 0; \ + } while (0) + +#define stat_inc_node_blk_count(sbi, blks, gc_type) \ + do { \ + struct f2fs_stat_info *si = F2FS_STAT(sbi); \ + stat_inc_tot_blk_count(si, blks); \ + si->node_blks += (blks); \ + si->bg_node_blks += (gc_type == BG_GC) ? (blks) : 0; \ + } while (0) + +int f2fs_build_stats(struct f2fs_sb_info *); +void f2fs_destroy_stats(struct f2fs_sb_info *); +void __init f2fs_create_root_stats(void); +void f2fs_destroy_root_stats(void); +#else +#define stat_inc_cp_count(si) +#define stat_inc_call_count(si) +#define stat_inc_bggc_count(si) +#define stat_inc_dirty_dir(sbi) +#define stat_dec_dirty_dir(sbi) +#define stat_inc_total_hit(sb) +#define stat_inc_read_hit(sb) +#define stat_inc_inline_inode(inode) +#define stat_dec_inline_inode(inode) +#define stat_inc_inline_dir(inode) +#define stat_dec_inline_dir(inode) +#define stat_inc_seg_type(sbi, curseg) +#define stat_inc_block_count(sbi, curseg) +#define stat_inc_inplace_blocks(sbi) +#define stat_inc_seg_count(sbi, type, gc_type) +#define stat_inc_tot_blk_count(si, blks) +#define stat_inc_data_blk_count(sbi, blks, gc_type) +#define stat_inc_node_blk_count(sbi, blks, gc_type) + +static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; } +static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { } +static inline void __init f2fs_create_root_stats(void) { } +static inline void f2fs_destroy_root_stats(void) { } +#endif + +extern const struct file_operations f2fs_dir_operations; +extern const struct file_operations f2fs_file_operations; +extern const struct inode_operations f2fs_file_inode_operations; +extern const struct address_space_operations f2fs_dblock_aops; +extern const struct address_space_operations f2fs_node_aops; +extern const struct address_space_operations f2fs_meta_aops; +extern const struct inode_operations f2fs_dir_inode_operations; +extern const struct inode_operations f2fs_symlink_inode_operations; +extern const struct inode_operations f2fs_special_inode_operations; +extern struct kmem_cache *inode_entry_slab; + +/* + * inline.c + */ +bool f2fs_may_inline(struct inode *); +void read_inline_data(struct page *, struct page *); +bool truncate_inline_inode(struct page *, u64); +int f2fs_read_inline_data(struct inode *, struct page *); +int f2fs_convert_inline_page(struct dnode_of_data *, struct page *); +int f2fs_convert_inline_inode(struct inode *); +int f2fs_write_inline_data(struct inode *, struct page *); +bool recover_inline_data(struct inode *, struct page *); +struct f2fs_dir_entry *find_in_inline_dir(struct inode *, struct qstr *, + struct page **); +struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *, struct page **); +int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *); +int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *, + nid_t, umode_t); +void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *, + struct inode *, struct inode *); +bool f2fs_empty_inline_dir(struct inode *); +int f2fs_read_inline_dir(struct file *, struct dir_context *); +#endif diff --git a/kernel/fs/f2fs/file.c b/kernel/fs/f2fs/file.c new file mode 100644 index 000000000..2b52e48d7 --- /dev/null +++ b/kernel/fs/f2fs/file.c @@ -0,0 +1,1172 @@ +/* + * 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 <linux/pagevec.h> + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include "xattr.h" +#include "acl.h" +#include "trace.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_I_SB(inode); + struct dnode_of_data dn; + int err; + + f2fs_balance_fs(sbi); + + sb_start_pagefault(inode->i_sb); + + f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); + + /* block allocation */ + f2fs_lock_op(sbi); + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = f2fs_reserve_block(&dn, page->index); + if (err) { + f2fs_unlock_op(sbi); + goto out; + } + f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); + + file_update_time(vma->vm_file); + lock_page(page); + if (unlikely(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 mapped; + + /* 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); + + trace_f2fs_vm_page_mkwrite(page, DATA); +mapped: + /* fill the page */ + f2fs_wait_on_page_writeback(page, DATA); +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, + .map_pages = filemap_map_pages, + .page_mkwrite = f2fs_vm_page_mkwrite, +}; + +static int get_parent_ino(struct inode *inode, nid_t *pino) +{ + struct dentry *dentry; + + inode = igrab(inode); + dentry = d_find_any_alias(inode); + iput(inode); + if (!dentry) + return 0; + + if (update_dent_inode(inode, &dentry->d_name)) { + dput(dentry); + return 0; + } + + *pino = parent_ino(dentry); + dput(dentry); + return 1; +} + +static inline bool need_do_checkpoint(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + bool need_cp = false; + + if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1) + need_cp = true; + else if (file_wrong_pino(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; + else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi))) + need_cp = true; + else if (test_opt(sbi, FASTBOOT)) + need_cp = true; + else if (sbi->active_logs == 2) + need_cp = true; + + return need_cp; +} + +static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct page *i = find_get_page(NODE_MAPPING(sbi), ino); + bool ret = false; + /* But we need to avoid that there are some inode updates */ + if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino)) + ret = true; + f2fs_put_page(i, 0); + return ret; +} + +static void try_to_fix_pino(struct inode *inode) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + nid_t pino; + + down_write(&fi->i_sem); + fi->xattr_ver = 0; + if (file_wrong_pino(inode) && inode->i_nlink == 1 && + get_parent_ino(inode, &pino)) { + fi->i_pino = pino; + file_got_pino(inode); + up_write(&fi->i_sem); + + mark_inode_dirty_sync(inode); + f2fs_write_inode(inode, NULL); + } else { + up_write(&fi->i_sem); + } +} + +int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) +{ + struct inode *inode = file->f_mapping->host; + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + nid_t ino = inode->i_ino; + 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 (unlikely(f2fs_readonly(inode->i_sb))) + return 0; + + trace_f2fs_sync_file_enter(inode); + + /* if fdatasync is triggered, let's do in-place-update */ + if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks) + set_inode_flag(fi, FI_NEED_IPU); + ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + clear_inode_flag(fi, FI_NEED_IPU); + + if (ret) { + trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); + return ret; + } + + /* if the inode is dirty, let's recover all the time */ + if (!datasync && is_inode_flag_set(fi, FI_DIRTY_INODE)) { + update_inode_page(inode); + goto go_write; + } + + /* + * if there is no written data, don't waste time to write recovery info. + */ + if (!is_inode_flag_set(fi, FI_APPEND_WRITE) && + !exist_written_data(sbi, ino, APPEND_INO)) { + + /* it may call write_inode just prior to fsync */ + if (need_inode_page_update(sbi, ino)) + goto go_write; + + if (is_inode_flag_set(fi, FI_UPDATE_WRITE) || + exist_written_data(sbi, ino, UPDATE_INO)) + goto flush_out; + goto out; + } +go_write: + /* guarantee free sections for fsync */ + f2fs_balance_fs(sbi); + + /* + * Both of fdatasync() and fsync() are able to be recovered from + * sudden-power-off. + */ + down_read(&fi->i_sem); + need_cp = need_do_checkpoint(inode); + up_read(&fi->i_sem); + + if (need_cp) { + /* all the dirty node pages should be flushed for POR */ + ret = f2fs_sync_fs(inode->i_sb, 1); + + /* + * We've secured consistency through sync_fs. Following pino + * will be used only for fsynced inodes after checkpoint. + */ + try_to_fix_pino(inode); + clear_inode_flag(fi, FI_APPEND_WRITE); + clear_inode_flag(fi, FI_UPDATE_WRITE); + goto out; + } +sync_nodes: + sync_node_pages(sbi, ino, &wbc); + + /* if cp_error was enabled, we should avoid infinite loop */ + if (unlikely(f2fs_cp_error(sbi))) + goto out; + + if (need_inode_block_update(sbi, ino)) { + mark_inode_dirty_sync(inode); + f2fs_write_inode(inode, NULL); + goto sync_nodes; + } + + ret = wait_on_node_pages_writeback(sbi, ino); + if (ret) + goto out; + + /* once recovery info is written, don't need to tack this */ + remove_dirty_inode(sbi, ino, APPEND_INO); + clear_inode_flag(fi, FI_APPEND_WRITE); +flush_out: + remove_dirty_inode(sbi, ino, UPDATE_INO); + clear_inode_flag(fi, FI_UPDATE_WRITE); + ret = f2fs_issue_flush(sbi); +out: + trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); + f2fs_trace_ios(NULL, NULL, 1); + return ret; +} + +static pgoff_t __get_first_dirty_index(struct address_space *mapping, + pgoff_t pgofs, int whence) +{ + struct pagevec pvec; + int nr_pages; + + if (whence != SEEK_DATA) + return 0; + + /* find first dirty page index */ + pagevec_init(&pvec, 0); + nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs, + PAGECACHE_TAG_DIRTY, 1); + pgofs = nr_pages ? pvec.pages[0]->index : LONG_MAX; + pagevec_release(&pvec); + return pgofs; +} + +static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs, + int whence) +{ + switch (whence) { + case SEEK_DATA: + if ((blkaddr == NEW_ADDR && dirty == pgofs) || + (blkaddr != NEW_ADDR && blkaddr != NULL_ADDR)) + return true; + break; + case SEEK_HOLE: + if (blkaddr == NULL_ADDR) + return true; + break; + } + return false; +} + +static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) +{ + struct inode *inode = file->f_mapping->host; + loff_t maxbytes = inode->i_sb->s_maxbytes; + struct dnode_of_data dn; + pgoff_t pgofs, end_offset, dirty; + loff_t data_ofs = offset; + loff_t isize; + int err = 0; + + mutex_lock(&inode->i_mutex); + + isize = i_size_read(inode); + if (offset >= isize) + goto fail; + + /* handle inline data case */ + if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) { + if (whence == SEEK_HOLE) + data_ofs = isize; + goto found; + } + + pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT); + + dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence); + + for (; data_ofs < isize; data_ofs = pgofs << PAGE_CACHE_SHIFT) { + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA); + if (err && err != -ENOENT) { + goto fail; + } else if (err == -ENOENT) { + /* direct node does not exists */ + if (whence == SEEK_DATA) { + pgofs = PGOFS_OF_NEXT_DNODE(pgofs, + F2FS_I(inode)); + continue; + } else { + goto found; + } + } + + end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); + + /* find data/hole in dnode block */ + for (; dn.ofs_in_node < end_offset; + dn.ofs_in_node++, pgofs++, + data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) { + block_t blkaddr; + blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); + + if (__found_offset(blkaddr, dirty, pgofs, whence)) { + f2fs_put_dnode(&dn); + goto found; + } + } + f2fs_put_dnode(&dn); + } + + if (whence == SEEK_DATA) + goto fail; +found: + if (whence == SEEK_HOLE && data_ofs > isize) + data_ofs = isize; + mutex_unlock(&inode->i_mutex); + return vfs_setpos(file, data_ofs, maxbytes); +fail: + mutex_unlock(&inode->i_mutex); + return -ENXIO; +} + +static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence) +{ + struct inode *inode = file->f_mapping->host; + loff_t maxbytes = inode->i_sb->s_maxbytes; + + switch (whence) { + case SEEK_SET: + case SEEK_CUR: + case SEEK_END: + return generic_file_llseek_size(file, offset, whence, + maxbytes, i_size_read(inode)); + case SEEK_DATA: + case SEEK_HOLE: + if (offset < 0) + return -ENXIO; + return f2fs_seek_block(file, offset, whence); + } + + return -EINVAL; +} + +static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct inode *inode = file_inode(file); + + /* we don't need to use inline_data strictly */ + if (f2fs_has_inline_data(inode)) { + int err = f2fs_convert_inline_inode(inode); + if (err) + return err; + } + + file_accessed(file); + vma->vm_ops = &f2fs_file_vm_ops; + return 0; +} + +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_I_SB(dn->inode); + struct f2fs_node *raw_node; + __le32 *addr; + + raw_node = F2FS_NODE(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; + + dn->data_blkaddr = NULL_ADDR; + set_data_blkaddr(dn); + f2fs_update_extent_cache(dn); + invalidate_blocks(sbi, blkaddr); + if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page)) + clear_inode_flag(F2FS_I(dn->inode), + FI_FIRST_BLOCK_WRITTEN); + nr_free++; + } + if (nr_free) { + dec_valid_block_count(sbi, dn->inode, 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 int truncate_partial_data_page(struct inode *inode, u64 from, + bool force) +{ + unsigned offset = from & (PAGE_CACHE_SIZE - 1); + struct page *page; + + if (!offset && !force) + return 0; + + page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, force); + if (IS_ERR(page)) + return 0; + + lock_page(page); + if (unlikely(!PageUptodate(page) || + page->mapping != inode->i_mapping)) + goto out; + + f2fs_wait_on_page_writeback(page, DATA); + zero_user(page, offset, PAGE_CACHE_SIZE - offset); + if (!force) + set_page_dirty(page); +out: + f2fs_put_page(page, 1); + return 0; +} + +int truncate_blocks(struct inode *inode, u64 from, bool lock) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + unsigned int blocksize = inode->i_sb->s_blocksize; + struct dnode_of_data dn; + pgoff_t free_from; + int count = 0, err = 0; + struct page *ipage; + bool truncate_page = false; + + trace_f2fs_truncate_blocks_enter(inode, from); + + free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1); + + if (lock) + f2fs_lock_op(sbi); + + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + err = PTR_ERR(ipage); + goto out; + } + + if (f2fs_has_inline_data(inode)) { + if (truncate_inline_inode(ipage, from)) + set_page_dirty(ipage); + f2fs_put_page(ipage, 1); + truncate_page = true; + goto out; + } + + set_new_dnode(&dn, inode, ipage, NULL, 0); + err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE); + if (err) { + if (err == -ENOENT) + goto free_next; + goto out; + } + + count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); + + count -= dn.ofs_in_node; + f2fs_bug_on(sbi, 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); +out: + if (lock) + f2fs_unlock_op(sbi); + + /* lastly zero out the first data page */ + if (!err) + err = truncate_partial_data_page(inode, from, truncate_page); + + 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); + + /* we should check inline_data size */ + if (f2fs_has_inline_data(inode) && !f2fs_may_inline(inode)) { + if (f2fs_convert_inline_inode(inode)) + return; + } + + if (!truncate_blocks(inode, i_size_read(inode), true)) { + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(inode); + } +} + +int f2fs_getattr(struct vfsmount *mnt, + struct dentry *dentry, struct kstat *stat) +{ + struct inode *inode = d_inode(dentry); + 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 = d_inode(dentry); + 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) { + if (attr->ia_size != i_size_read(inode)) { + truncate_setsize(inode, attr->ia_size); + f2fs_truncate(inode); + f2fs_balance_fs(F2FS_I_SB(inode)); + } else { + /* + * giving a chance to truncate blocks past EOF which + * are fallocated with FALLOC_FL_KEEP_SIZE. + */ + f2fs_truncate(inode); + } + } + + __setattr_copy(inode, attr); + + if (attr->ia_valid & ATTR_MODE) { + err = posix_acl_chmod(inode, get_inode_mode(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, + .set_acl = f2fs_set_acl, +#ifdef CONFIG_F2FS_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = f2fs_listxattr, + .removexattr = generic_removexattr, +#endif + .fiemap = f2fs_fiemap, +}; + +static void fill_zero(struct inode *inode, pgoff_t index, + loff_t start, loff_t len) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct page *page; + + if (!len) + return; + + f2fs_balance_fs(sbi); + + f2fs_lock_op(sbi); + page = get_new_data_page(inode, NULL, index, false); + f2fs_unlock_op(sbi); + + if (!IS_ERR(page)) { + f2fs_wait_on_page_writeback(page, DATA); + 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) +{ + pgoff_t pg_start, pg_end; + loff_t off_start, off_end; + int ret = 0; + + if (!S_ISREG(inode->i_mode)) + return -EOPNOTSUPP; + + /* skip punching hole beyond i_size */ + if (offset >= inode->i_size) + return ret; + + if (f2fs_has_inline_data(inode)) { + ret = f2fs_convert_inline_inode(inode); + 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); + + 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_I_SB(inode); + + 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); + + f2fs_lock_op(sbi); + ret = truncate_hole(inode, pg_start, pg_end); + f2fs_unlock_op(sbi); + } + } + + return ret; +} + +static int expand_inode_data(struct inode *inode, loff_t offset, + loff_t len, int mode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + pgoff_t index, pg_start, pg_end; + loff_t new_size = i_size_read(inode); + loff_t off_start, off_end; + int ret = 0; + + f2fs_balance_fs(sbi); + + ret = inode_newsize_ok(inode, (len + offset)); + if (ret) + return ret; + + if (f2fs_has_inline_data(inode)) { + ret = f2fs_convert_inline_inode(inode); + 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); + + f2fs_lock_op(sbi); + + for (index = pg_start; index <= pg_end; index++) { + struct dnode_of_data dn; + + if (index == pg_end && !off_end) + goto noalloc; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = f2fs_reserve_block(&dn, index); + if (ret) + break; +noalloc: + 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); + update_inode_page(inode); + } + f2fs_unlock_op(sbi); + + 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; + + mutex_lock(&inode->i_mutex); + + if (mode & FALLOC_FL_PUNCH_HOLE) + ret = punch_hole(inode, offset, len); + else + ret = expand_inode_data(inode, offset, len, mode); + + if (!ret) { + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(inode); + } + + mutex_unlock(&inode->i_mutex); + + trace_f2fs_fallocate(inode, mode, offset, len, ret); + return ret; +} + +static int f2fs_release_file(struct inode *inode, struct file *filp) +{ + /* some remained atomic pages should discarded */ + if (f2fs_is_atomic_file(inode)) + commit_inmem_pages(inode, true); + if (f2fs_is_volatile_file(inode)) { + set_inode_flag(F2FS_I(inode), FI_DROP_CACHE); + filemap_fdatawrite(inode->i_mapping); + clear_inode_flag(F2FS_I(inode), FI_DROP_CACHE); + } + return 0; +} + +#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; +} + +static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); + unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE; + return put_user(flags, (int __user *)arg); +} + +static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); + unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE; + unsigned int oldflags; + int ret; + + 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; +} + +static int f2fs_ioc_getversion(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + + return put_user(inode->i_generation, (int __user *)arg); +} + +static int f2fs_ioc_start_atomic_write(struct file *filp) +{ + struct inode *inode = file_inode(filp); + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + f2fs_balance_fs(F2FS_I_SB(inode)); + + if (f2fs_is_atomic_file(inode)) + return 0; + + set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); + + return f2fs_convert_inline_inode(inode); +} + +static int f2fs_ioc_commit_atomic_write(struct file *filp) +{ + struct inode *inode = file_inode(filp); + int ret; + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (f2fs_is_volatile_file(inode)) + return 0; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + if (f2fs_is_atomic_file(inode)) + commit_inmem_pages(inode, false); + + ret = f2fs_sync_file(filp, 0, LONG_MAX, 0); + mnt_drop_write_file(filp); + clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); + return ret; +} + +static int f2fs_ioc_start_volatile_write(struct file *filp) +{ + struct inode *inode = file_inode(filp); + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (f2fs_is_volatile_file(inode)) + return 0; + + set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); + + return f2fs_convert_inline_inode(inode); +} + +static int f2fs_ioc_release_volatile_write(struct file *filp) +{ + struct inode *inode = file_inode(filp); + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (!f2fs_is_volatile_file(inode)) + return 0; + + if (!f2fs_is_first_block_written(inode)) + return truncate_partial_data_page(inode, 0, true); + + punch_hole(inode, 0, F2FS_BLKSIZE); + return 0; +} + +static int f2fs_ioc_abort_volatile_write(struct file *filp) +{ + struct inode *inode = file_inode(filp); + int ret; + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + f2fs_balance_fs(F2FS_I_SB(inode)); + + if (f2fs_is_atomic_file(inode)) { + commit_inmem_pages(inode, false); + clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); + } + + if (f2fs_is_volatile_file(inode)) { + clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); + filemap_fdatawrite(inode->i_mapping); + set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE); + } + mnt_drop_write_file(filp); + return ret; +} + +static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct super_block *sb = sbi->sb; + __u32 in; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (get_user(in, (__u32 __user *)arg)) + return -EFAULT; + + switch (in) { + case F2FS_GOING_DOWN_FULLSYNC: + sb = freeze_bdev(sb->s_bdev); + if (sb && !IS_ERR(sb)) { + f2fs_stop_checkpoint(sbi); + thaw_bdev(sb->s_bdev, sb); + } + break; + case F2FS_GOING_DOWN_METASYNC: + /* do checkpoint only */ + f2fs_sync_fs(sb, 1); + f2fs_stop_checkpoint(sbi); + break; + case F2FS_GOING_DOWN_NOSYNC: + f2fs_stop_checkpoint(sbi); + break; + default: + return -EINVAL; + } + return 0; +} + +static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct super_block *sb = inode->i_sb; + struct request_queue *q = bdev_get_queue(sb->s_bdev); + struct fstrim_range range; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!blk_queue_discard(q)) + return -EOPNOTSUPP; + + if (copy_from_user(&range, (struct fstrim_range __user *)arg, + sizeof(range))) + return -EFAULT; + + range.minlen = max((unsigned int)range.minlen, + q->limits.discard_granularity); + ret = f2fs_trim_fs(F2FS_SB(sb), &range); + if (ret < 0) + return ret; + + if (copy_to_user((struct fstrim_range __user *)arg, &range, + sizeof(range))) + return -EFAULT; + return 0; +} + +long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + case F2FS_IOC_GETFLAGS: + return f2fs_ioc_getflags(filp, arg); + case F2FS_IOC_SETFLAGS: + return f2fs_ioc_setflags(filp, arg); + case F2FS_IOC_GETVERSION: + return f2fs_ioc_getversion(filp, arg); + case F2FS_IOC_START_ATOMIC_WRITE: + return f2fs_ioc_start_atomic_write(filp); + case F2FS_IOC_COMMIT_ATOMIC_WRITE: + return f2fs_ioc_commit_atomic_write(filp); + case F2FS_IOC_START_VOLATILE_WRITE: + return f2fs_ioc_start_volatile_write(filp); + case F2FS_IOC_RELEASE_VOLATILE_WRITE: + return f2fs_ioc_release_volatile_write(filp); + case F2FS_IOC_ABORT_VOLATILE_WRITE: + return f2fs_ioc_abort_volatile_write(filp); + case F2FS_IOC_SHUTDOWN: + return f2fs_ioc_shutdown(filp, arg); + case FITRIM: + return f2fs_ioc_fitrim(filp, arg); + 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 = f2fs_llseek, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, + .open = generic_file_open, + .release = f2fs_release_file, + .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 = iter_file_splice_write, +}; diff --git a/kernel/fs/f2fs/gc.c b/kernel/fs/f2fs/gc.c new file mode 100644 index 000000000..ed58211fe --- /dev/null +++ b/kernel/fs/f2fs/gc.c @@ -0,0 +1,746 @@ +/* + * 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 int gc_thread_func(void *data) +{ + struct f2fs_sb_info *sbi = data; + struct f2fs_gc_kthread *gc_th = sbi->gc_thread; + wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head; + long wait_ms; + + wait_ms = gc_th->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) { + increase_sleep_time(gc_th, &wait_ms); + 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 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)) { + increase_sleep_time(gc_th, &wait_ms); + mutex_unlock(&sbi->gc_mutex); + continue; + } + + if (has_enough_invalid_blocks(sbi)) + decrease_sleep_time(gc_th, &wait_ms); + else + increase_sleep_time(gc_th, &wait_ms); + + stat_inc_bggc_count(sbi); + + /* if return value is not zero, no victim was selected */ + if (f2fs_gc(sbi)) + wait_ms = gc_th->no_gc_sleep_time; + + /* balancing f2fs's metadata periodically */ + f2fs_balance_fs_bg(sbi); + + } 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; + int err = 0; + + gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL); + if (!gc_th) { + err = -ENOMEM; + goto out; + } + + gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME; + gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME; + gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME; + + gc_th->gc_idle = 0; + + 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)) { + err = PTR_ERR(gc_th->f2fs_gc_task); + kfree(gc_th); + sbi->gc_thread = NULL; + } +out: + return err; +} + +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(struct f2fs_gc_kthread *gc_th, int gc_type) +{ + int gc_mode = (gc_type == BG_GC) ? GC_CB : GC_GREEDY; + + if (gc_th && gc_th->gc_idle) { + if (gc_th->gc_idle == 1) + gc_mode = GC_CB; + else if (gc_th->gc_idle == 2) + gc_mode = GC_GREEDY; + } + return gc_mode; +} + +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->max_search = dirty_i->nr_dirty[type]; + p->ofs_unit = 1; + } else { + p->gc_mode = select_gc_type(sbi->gc_thread, gc_type); + p->dirty_segmap = dirty_i->dirty_segmap[DIRTY]; + p->max_search = dirty_i->nr_dirty[DIRTY]; + p->ofs_unit = sbi->segs_per_sec; + } + + if (p->max_search > sbi->max_victim_search) + p->max_search = sbi->max_victim_search; + + 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 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. + */ + for_each_set_bit(secno, dirty_i->victim_secmap, MAIN_SECS(sbi)) { + if (sec_usage_check(sbi, secno)) + continue; + 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 has changed by the 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 inline 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, max_cost; + int nsearched = 0; + + mutex_lock(&dirty_i->seglist_lock); + + p.alloc_mode = alloc_mode; + select_policy(sbi, gc_type, type, &p); + + p.min_segno = NULL_SEGNO; + p.min_cost = max_cost = get_max_cost(sbi, &p); + + 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, MAIN_SEGS(sbi), p.offset); + if (segno >= MAIN_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; + if (p.ofs_unit > 1) + p.offset -= segno % 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; + } else if (unlikely(cost == max_cost)) { + continue; + } + + if (nsearched++ >= p.max_search) { + sbi->last_victim[p.gc_mode] = segno; + break; + } + } + if (p.min_segno != NULL_SEGNO) { +got_it: + 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(struct gc_inode_list *gc_list, nid_t ino) +{ + struct inode_entry *ie; + + ie = radix_tree_lookup(&gc_list->iroot, ino); + if (ie) + return ie->inode; + return NULL; +} + +static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode) +{ + struct inode_entry *new_ie; + + if (inode == find_gc_inode(gc_list, inode->i_ino)) { + iput(inode); + return; + } + new_ie = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); + new_ie->inode = inode; + + f2fs_radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie); + list_add_tail(&new_ie->list, &gc_list->ilist); +} + +static void put_gc_inode(struct gc_inode_list *gc_list) +{ + struct inode_entry *ie, *next_ie; + list_for_each_entry_safe(ie, next_ie, &gc_list->ilist, list) { + radix_tree_delete(&gc_list->iroot, ie->inode->i_ino); + iput(ie->inode); + list_del(&ie->list); + kmem_cache_free(inode_entry_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; + + /* block may become invalid during get_node_page */ + if (check_valid_map(sbi, segno, off) == 0) { + f2fs_put_page(node_page, 1); + continue; + } + + /* set page dirty and write it */ + if (gc_type == FG_GC) { + f2fs_wait_on_page_writeback(node_page, NODE); + 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, gc_type); + } + + 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, struct f2fs_inode_info *fi) +{ + 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(fi); +} + +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) +{ + struct f2fs_io_info fio = { + .type = DATA, + .rw = WRITE_SYNC, + }; + + if (gc_type == BG_GC) { + if (PageWriteback(page)) + goto out; + set_page_dirty(page); + set_cold_data(page); + } else { + f2fs_wait_on_page_writeback(page, DATA); + + if (clear_page_dirty_for_io(page)) + inode_dec_dirty_pages(inode); + set_cold_data(page); + do_write_data_page(page, &fio); + 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 gc_inode_list *gc_list, 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; + } + + ofs_in_node = le16_to_cpu(entry->ofs_in_node); + + if (phase == 2) { + inode = f2fs_iget(sb, dni.ino); + if (IS_ERR(inode) || is_bad_inode(inode)) + continue; + + start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)); + + data_page = find_data_page(inode, + start_bidx + ofs_in_node, false); + if (IS_ERR(data_page)) { + iput(inode); + continue; + } + + f2fs_put_page(data_page, 0); + add_gc_inode(gc_list, inode); + continue; + } + + /* phase 3 */ + inode = find_gc_inode(gc_list, dni.ino); + if (inode) { + start_bidx = start_bidx_of_node(nofs, F2FS_I(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, gc_type); + } + } + + if (++phase < 4) + goto next_step; + + if (gc_type == FG_GC) { + f2fs_submit_merged_bio(sbi, DATA, WRITE); + + /* + * 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) +{ + 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, + NO_CHECK_TYPE, LFS); + mutex_unlock(&sit_i->sentry_lock); + return ret; +} + +static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, + struct gc_inode_list *gc_list, 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); + + 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, gc_list, segno, gc_type); + break; + } + blk_finish_plug(&plug); + + stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)), gc_type); + stat_inc_call_count(sbi->stat_info); + + f2fs_put_page(sum_page, 1); +} + +int f2fs_gc(struct f2fs_sb_info *sbi) +{ + unsigned int segno, i; + int gc_type = BG_GC; + int nfree = 0; + int ret = -1; + struct cp_control cpc; + struct gc_inode_list gc_list = { + .ilist = LIST_HEAD_INIT(gc_list.ilist), + .iroot = RADIX_TREE_INIT(GFP_NOFS), + }; + + cpc.reason = __get_cp_reason(sbi); +gc_more: + if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) + goto stop; + if (unlikely(f2fs_cp_error(sbi))) + goto stop; + + if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree)) { + gc_type = FG_GC; + write_checkpoint(sbi, &cpc); + } + + if (!__get_victim(sbi, &segno, gc_type)) + goto stop; + ret = 0; + + /* readahead multi ssa blocks those have contiguous address */ + if (sbi->segs_per_sec > 1) + ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), sbi->segs_per_sec, + META_SSA); + + for (i = 0; i < sbi->segs_per_sec; i++) + do_garbage_collect(sbi, segno + i, &gc_list, 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, &cpc); +stop: + mutex_unlock(&sbi->gc_mutex); + + put_gc_inode(&gc_list); + return ret; +} + +void build_gc_manager(struct f2fs_sb_info *sbi) +{ + DIRTY_I(sbi)->v_ops = &default_v_ops; +} diff --git a/kernel/fs/f2fs/gc.h b/kernel/fs/f2fs/gc.h new file mode 100644 index 000000000..b4a65be9f --- /dev/null +++ b/kernel/fs/f2fs/gc.h @@ -0,0 +1,110 @@ +/* + * 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 DEF_GC_THREAD_MIN_SLEEP_TIME 30000 /* milliseconds */ +#define DEF_GC_THREAD_MAX_SLEEP_TIME 60000 +#define DEF_GC_THREAD_NOGC_SLEEP_TIME 300000 /* wait 5 min */ +#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 DEF_MAX_VICTIM_SEARCH 4096 /* covers 8GB */ + +struct f2fs_gc_kthread { + struct task_struct *f2fs_gc_task; + wait_queue_head_t gc_wait_queue_head; + + /* for gc sleep time */ + unsigned int min_sleep_time; + unsigned int max_sleep_time; + unsigned int no_gc_sleep_time; + + /* for changing gc mode */ + unsigned int gc_idle; +}; + +struct gc_inode_list { + struct list_head ilist; + struct radix_tree_root iroot; +}; + +/* + * 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 void increase_sleep_time(struct f2fs_gc_kthread *gc_th, + long *wait) +{ + if (*wait == gc_th->no_gc_sleep_time) + return; + + *wait += gc_th->min_sleep_time; + if (*wait > gc_th->max_sleep_time) + *wait = gc_th->max_sleep_time; +} + +static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th, + long *wait) +{ + if (*wait == gc_th->no_gc_sleep_time) + *wait = gc_th->max_sleep_time; + + *wait -= gc_th->min_sleep_time; + if (*wait <= gc_th->min_sleep_time) + *wait = gc_th->min_sleep_time; +} + +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 conditions. + * 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]); +} diff --git a/kernel/fs/f2fs/hash.c b/kernel/fs/f2fs/hash.c new file mode 100644 index 000000000..a844fcfb9 --- /dev/null +++ b/kernel/fs/f2fs/hash.c @@ -0,0 +1,104 @@ +/* + * 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 unsigned char *msg, size_t len, + unsigned int *buf, int num) +{ + unsigned pad, val; + int i; + + pad = (__u32)len | ((__u32)len << 8); + pad |= pad << 16; + + val = pad; + if (len > num * 4) + len = num * 4; + for (i = 0; i < len; i++) { + if ((i % 4) == 0) + val = pad; + val = msg[i] + (val << 8); + if ((i % 4) == 3) { + *buf++ = val; + val = pad; + num--; + } + } + if (--num >= 0) + *buf++ = val; + while (--num >= 0) + *buf++ = pad; +} + +f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info) +{ + __u32 hash; + f2fs_hash_t f2fs_hash; + const unsigned char *p; + __u32 in[8], buf[4]; + const unsigned char *name = name_info->name; + size_t len = name_info->len; + + 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; +} diff --git a/kernel/fs/f2fs/inline.c b/kernel/fs/f2fs/inline.c new file mode 100644 index 000000000..8140e4f0e --- /dev/null +++ b/kernel/fs/f2fs/inline.c @@ -0,0 +1,532 @@ +/* + * fs/f2fs/inline.c + * Copyright (c) 2013, Intel Corporation + * Authors: Huajun Li <huajun.li@intel.com> + * Haicheng Li <haicheng.li@intel.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" + +bool f2fs_may_inline(struct inode *inode) +{ + if (!test_opt(F2FS_I_SB(inode), INLINE_DATA)) + return false; + + if (f2fs_is_atomic_file(inode)) + return false; + + if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode)) + return false; + + if (i_size_read(inode) > MAX_INLINE_DATA) + return false; + + return true; +} + +void read_inline_data(struct page *page, struct page *ipage) +{ + void *src_addr, *dst_addr; + + if (PageUptodate(page)) + return; + + f2fs_bug_on(F2FS_P_SB(page), page->index); + + zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE); + + /* Copy the whole inline data block */ + src_addr = inline_data_addr(ipage); + dst_addr = kmap_atomic(page); + memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + flush_dcache_page(page); + kunmap_atomic(dst_addr); + SetPageUptodate(page); +} + +bool truncate_inline_inode(struct page *ipage, u64 from) +{ + void *addr; + + if (from >= MAX_INLINE_DATA) + return false; + + addr = inline_data_addr(ipage); + + f2fs_wait_on_page_writeback(ipage, NODE); + memset(addr + from, 0, MAX_INLINE_DATA - from); + + return true; +} + +int f2fs_read_inline_data(struct inode *inode, struct page *page) +{ + struct page *ipage; + + ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + if (IS_ERR(ipage)) { + unlock_page(page); + return PTR_ERR(ipage); + } + + if (!f2fs_has_inline_data(inode)) { + f2fs_put_page(ipage, 1); + return -EAGAIN; + } + + if (page->index) + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + else + read_inline_data(page, ipage); + + SetPageUptodate(page); + f2fs_put_page(ipage, 1); + unlock_page(page); + return 0; +} + +int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) +{ + void *src_addr, *dst_addr; + struct f2fs_io_info fio = { + .type = DATA, + .rw = WRITE_SYNC | REQ_PRIO, + }; + int dirty, err; + + f2fs_bug_on(F2FS_I_SB(dn->inode), page->index); + + if (!f2fs_exist_data(dn->inode)) + goto clear_out; + + err = f2fs_reserve_block(dn, 0); + if (err) + return err; + + f2fs_wait_on_page_writeback(page, DATA); + + if (PageUptodate(page)) + goto no_update; + + zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE); + + /* Copy the whole inline data block */ + src_addr = inline_data_addr(dn->inode_page); + dst_addr = kmap_atomic(page); + memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + flush_dcache_page(page); + kunmap_atomic(dst_addr); + SetPageUptodate(page); +no_update: + /* clear dirty state */ + dirty = clear_page_dirty_for_io(page); + + /* write data page to try to make data consistent */ + set_page_writeback(page); + fio.blk_addr = dn->data_blkaddr; + write_data_page(page, dn, &fio); + set_data_blkaddr(dn); + f2fs_update_extent_cache(dn); + f2fs_wait_on_page_writeback(page, DATA); + if (dirty) + inode_dec_dirty_pages(dn->inode); + + /* this converted inline_data should be recovered. */ + set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE); + + /* clear inline data and flag after data writeback */ + truncate_inline_inode(dn->inode_page, 0); +clear_out: + stat_dec_inline_inode(dn->inode); + f2fs_clear_inline_inode(dn->inode); + sync_inode_page(dn); + f2fs_put_dnode(dn); + return 0; +} + +int f2fs_convert_inline_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct dnode_of_data dn; + struct page *ipage, *page; + int err = 0; + + page = grab_cache_page(inode->i_mapping, 0); + if (!page) + return -ENOMEM; + + f2fs_lock_op(sbi); + + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + err = PTR_ERR(ipage); + goto out; + } + + set_new_dnode(&dn, inode, ipage, ipage, 0); + + if (f2fs_has_inline_data(inode)) + err = f2fs_convert_inline_page(&dn, page); + + f2fs_put_dnode(&dn); +out: + f2fs_unlock_op(sbi); + + f2fs_put_page(page, 1); + return err; +} + +int f2fs_write_inline_data(struct inode *inode, struct page *page) +{ + void *src_addr, *dst_addr; + struct dnode_of_data dn; + int err; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, 0, LOOKUP_NODE); + if (err) + return err; + + if (!f2fs_has_inline_data(inode)) { + f2fs_put_dnode(&dn); + return -EAGAIN; + } + + f2fs_bug_on(F2FS_I_SB(inode), page->index); + + f2fs_wait_on_page_writeback(dn.inode_page, NODE); + src_addr = kmap_atomic(page); + dst_addr = inline_data_addr(dn.inode_page); + memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + kunmap_atomic(src_addr); + + set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE); + set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); + + sync_inode_page(&dn); + f2fs_put_dnode(&dn); + return 0; +} + +bool recover_inline_data(struct inode *inode, struct page *npage) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode *ri = NULL; + void *src_addr, *dst_addr; + struct page *ipage; + + /* + * The inline_data recovery policy is as follows. + * [prev.] [next] of inline_data flag + * o o -> recover inline_data + * o x -> remove inline_data, and then recover data blocks + * x o -> remove inline_data, and then recover inline_data + * x x -> recover data blocks + */ + if (IS_INODE(npage)) + ri = F2FS_INODE(npage); + + if (f2fs_has_inline_data(inode) && + ri && (ri->i_inline & F2FS_INLINE_DATA)) { +process_inline: + ipage = get_node_page(sbi, inode->i_ino); + f2fs_bug_on(sbi, IS_ERR(ipage)); + + f2fs_wait_on_page_writeback(ipage, NODE); + + src_addr = inline_data_addr(npage); + dst_addr = inline_data_addr(ipage); + memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + + set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); + + update_inode(inode, ipage); + f2fs_put_page(ipage, 1); + return true; + } + + if (f2fs_has_inline_data(inode)) { + ipage = get_node_page(sbi, inode->i_ino); + f2fs_bug_on(sbi, IS_ERR(ipage)); + truncate_inline_inode(ipage, 0); + f2fs_clear_inline_inode(inode); + update_inode(inode, ipage); + f2fs_put_page(ipage, 1); + } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { + truncate_blocks(inode, 0, false); + goto process_inline; + } + return false; +} + +struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, + struct qstr *name, struct page **res_page) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); + struct f2fs_inline_dentry *inline_dentry; + struct f2fs_dir_entry *de; + struct f2fs_dentry_ptr d; + struct page *ipage; + + ipage = get_node_page(sbi, dir->i_ino); + if (IS_ERR(ipage)) + return NULL; + + inline_dentry = inline_data_addr(ipage); + + make_dentry_ptr(&d, (void *)inline_dentry, 2); + de = find_target_dentry(name, NULL, &d); + + unlock_page(ipage); + if (de) + *res_page = ipage; + else + f2fs_put_page(ipage, 0); + + /* + * For the most part, it should be a bug when name_len is zero. + * We stop here for figuring out where the bugs has occurred. + */ + f2fs_bug_on(sbi, d.max < 0); + return de; +} + +struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *dir, + struct page **p) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct page *ipage; + struct f2fs_dir_entry *de; + struct f2fs_inline_dentry *dentry_blk; + + ipage = get_node_page(sbi, dir->i_ino); + if (IS_ERR(ipage)) + return NULL; + + dentry_blk = inline_data_addr(ipage); + de = &dentry_blk->dentry[1]; + *p = ipage; + unlock_page(ipage); + return de; +} + +int make_empty_inline_dir(struct inode *inode, struct inode *parent, + struct page *ipage) +{ + struct f2fs_inline_dentry *dentry_blk; + struct f2fs_dentry_ptr d; + + dentry_blk = inline_data_addr(ipage); + + make_dentry_ptr(&d, (void *)dentry_blk, 2); + do_make_empty_dir(inode, parent, &d); + + set_page_dirty(ipage); + + /* update i_size to MAX_INLINE_DATA */ + if (i_size_read(inode) < MAX_INLINE_DATA) { + i_size_write(inode, MAX_INLINE_DATA); + set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR); + } + return 0; +} + +static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, + struct f2fs_inline_dentry *inline_dentry) +{ + struct page *page; + struct dnode_of_data dn; + struct f2fs_dentry_block *dentry_blk; + int err; + + page = grab_cache_page(dir->i_mapping, 0); + if (!page) + return -ENOMEM; + + set_new_dnode(&dn, dir, ipage, NULL, 0); + err = f2fs_reserve_block(&dn, 0); + if (err) + goto out; + + f2fs_wait_on_page_writeback(page, DATA); + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + + dentry_blk = kmap_atomic(page); + + /* copy data from inline dentry block to new dentry block */ + memcpy(dentry_blk->dentry_bitmap, inline_dentry->dentry_bitmap, + INLINE_DENTRY_BITMAP_SIZE); + memcpy(dentry_blk->dentry, inline_dentry->dentry, + sizeof(struct f2fs_dir_entry) * NR_INLINE_DENTRY); + memcpy(dentry_blk->filename, inline_dentry->filename, + NR_INLINE_DENTRY * F2FS_SLOT_LEN); + + kunmap_atomic(dentry_blk); + SetPageUptodate(page); + set_page_dirty(page); + + /* clear inline dir and flag after data writeback */ + truncate_inline_inode(ipage, 0); + + stat_dec_inline_dir(dir); + clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY); + + if (i_size_read(dir) < PAGE_CACHE_SIZE) { + i_size_write(dir, PAGE_CACHE_SIZE); + set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); + } + + sync_inode_page(&dn); +out: + f2fs_put_page(page, 1); + return err; +} + +int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name, + struct inode *inode, nid_t ino, umode_t mode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct page *ipage; + unsigned int bit_pos; + f2fs_hash_t name_hash; + size_t namelen = name->len; + struct f2fs_inline_dentry *dentry_blk = NULL; + struct f2fs_dentry_ptr d; + int slots = GET_DENTRY_SLOTS(namelen); + struct page *page = NULL; + int err = 0; + + ipage = get_node_page(sbi, dir->i_ino); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); + + dentry_blk = inline_data_addr(ipage); + bit_pos = room_for_filename(&dentry_blk->dentry_bitmap, + slots, NR_INLINE_DENTRY); + if (bit_pos >= NR_INLINE_DENTRY) { + err = f2fs_convert_inline_dir(dir, ipage, dentry_blk); + if (!err) + err = -EAGAIN; + goto out; + } + + if (inode) { + down_write(&F2FS_I(inode)->i_sem); + page = init_inode_metadata(inode, dir, name, ipage); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto fail; + } + } + + f2fs_wait_on_page_writeback(ipage, NODE); + + name_hash = f2fs_dentry_hash(name); + make_dentry_ptr(&d, (void *)dentry_blk, 2); + f2fs_update_dentry(ino, mode, &d, name, name_hash, bit_pos); + + set_page_dirty(ipage); + + /* we don't need to mark_inode_dirty now */ + if (inode) { + F2FS_I(inode)->i_pino = dir->i_ino; + update_inode(inode, page); + f2fs_put_page(page, 1); + } + + update_parent_metadata(dir, inode, 0); +fail: + if (inode) + up_write(&F2FS_I(inode)->i_sem); + + if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) { + update_inode(dir, ipage); + clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); + } +out: + f2fs_put_page(ipage, 1); + return err; +} + +void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page, + struct inode *dir, struct inode *inode) +{ + struct f2fs_inline_dentry *inline_dentry; + int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); + unsigned int bit_pos; + int i; + + lock_page(page); + f2fs_wait_on_page_writeback(page, NODE); + + inline_dentry = inline_data_addr(page); + bit_pos = dentry - inline_dentry->dentry; + for (i = 0; i < slots; i++) + test_and_clear_bit_le(bit_pos + i, + &inline_dentry->dentry_bitmap); + + set_page_dirty(page); + + dir->i_ctime = dir->i_mtime = CURRENT_TIME; + + if (inode) + f2fs_drop_nlink(dir, inode, page); + + f2fs_put_page(page, 1); +} + +bool f2fs_empty_inline_dir(struct inode *dir) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct page *ipage; + unsigned int bit_pos = 2; + struct f2fs_inline_dentry *dentry_blk; + + ipage = get_node_page(sbi, dir->i_ino); + if (IS_ERR(ipage)) + return false; + + dentry_blk = inline_data_addr(ipage); + bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, + NR_INLINE_DENTRY, + bit_pos); + + f2fs_put_page(ipage, 1); + + if (bit_pos < NR_INLINE_DENTRY) + return false; + + return true; +} + +int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx) +{ + struct inode *inode = file_inode(file); + struct f2fs_inline_dentry *inline_dentry = NULL; + struct page *ipage = NULL; + struct f2fs_dentry_ptr d; + + if (ctx->pos == NR_INLINE_DENTRY) + return 0; + + ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); + + inline_dentry = inline_data_addr(ipage); + + make_dentry_ptr(&d, (void *)inline_dentry, 2); + + if (!f2fs_fill_dentries(ctx, &d, 0)) + ctx->pos = NR_INLINE_DENTRY; + + f2fs_put_page(ipage, 1); + return 0; +} diff --git a/kernel/fs/f2fs/inode.c b/kernel/fs/f2fs/inode.c new file mode 100644 index 000000000..e622ec954 --- /dev/null +++ b/kernel/fs/f2fs/inode.c @@ -0,0 +1,387 @@ +/* + * 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 <linux/bitops.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; + unsigned int new_fl = 0; + + if (flags & FS_SYNC_FL) + new_fl |= S_SYNC; + if (flags & FS_APPEND_FL) + new_fl |= S_APPEND; + if (flags & FS_IMMUTABLE_FL) + new_fl |= S_IMMUTABLE; + if (flags & FS_NOATIME_FL) + new_fl |= S_NOATIME; + if (flags & FS_DIRSYNC_FL) + new_fl |= S_DIRSYNC; + set_mask_bits(&inode->i_flags, + S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl); +} + +static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri) +{ + if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || + S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { + 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])); + } +} + +static bool __written_first_block(struct f2fs_inode *ri) +{ + block_t addr = le32_to_cpu(ri->i_addr[0]); + + if (addr != NEW_ADDR && addr != NULL_ADDR) + return true; + return false; +} + +static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri) +{ + 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; + } + } +} + +static void __recover_inline_status(struct inode *inode, struct page *ipage) +{ + void *inline_data = inline_data_addr(ipage); + __le32 *start = inline_data; + __le32 *end = start + MAX_INLINE_DATA / sizeof(__le32); + + while (start < end) { + if (*start++) { + f2fs_wait_on_page_writeback(ipage, NODE); + + set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); + set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage)); + set_page_dirty(ipage); + return; + } + } + return; +} + +static int do_read_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct page *node_page; + 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); + WARN_ON(1); + return -EINVAL; + } + + node_page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(node_page)) + return PTR_ERR(node_page); + + ri = F2FS_INODE(node_page); + + 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); + + 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); + fi->i_dir_level = ri->i_dir_level; + + f2fs_init_extent_cache(inode, &ri->i_ext); + + get_inline_info(fi, ri); + + /* check data exist */ + if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode)) + __recover_inline_status(inode, node_page); + + /* get rdev by using inline_info */ + __get_inode_rdev(inode, ri); + + if (__written_first_block(ri)) + set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); + + f2fs_put_page(node_page, 1); + + stat_inc_inline_inode(inode); + stat_inc_inline_dir(inode); + + 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; +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_F2FS_HIGH_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_inode *ri; + + f2fs_wait_on_page_writeback(node_page, NODE); + + ri = F2FS_INODE(node_page); + + 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); + + read_lock(&F2FS_I(inode)->ext_lock); + set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext); + read_unlock(&F2FS_I(inode)->ext_lock); + + set_raw_inline(F2FS_I(inode), ri); + + 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); + ri->i_dir_level = F2FS_I(inode)->i_dir_level; + + __set_inode_rdev(inode, ri); + set_cold_node(inode, node_page); + set_page_dirty(node_page); + + clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE); +} + +void update_inode_page(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct page *node_page; +retry: + node_page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(node_page)) { + int err = PTR_ERR(node_page); + if (err == -ENOMEM) { + cond_resched(); + goto retry; + } else if (err != -ENOENT) { + f2fs_stop_checkpoint(sbi); + } + return; + } + update_inode(inode, node_page); + f2fs_put_page(node_page, 1); +} + +int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (inode->i_ino == F2FS_NODE_INO(sbi) || + inode->i_ino == F2FS_META_INO(sbi)) + return 0; + + if (!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_INODE)) + return 0; + + /* + * We need to lock here to prevent from producing dirty node pages + * during the urgent cleaning time when runing out of free sections. + */ + f2fs_lock_op(sbi); + update_inode_page(inode); + f2fs_unlock_op(sbi); + + if (wbc) + f2fs_balance_fs(sbi); + + return 0; +} + +/* + * Called at the last iput() if i_nlink is zero + */ +void f2fs_evict_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + nid_t xnid = F2FS_I(inode)->i_xattr_nid; + + /* some remained atomic pages should discarded */ + if (f2fs_is_atomic_file(inode)) + commit_inmem_pages(inode, true); + + trace_f2fs_evict_inode(inode); + truncate_inode_pages_final(&inode->i_data); + + if (inode->i_ino == F2FS_NODE_INO(sbi) || + inode->i_ino == F2FS_META_INO(sbi)) + goto out_clear; + + f2fs_bug_on(sbi, get_dirty_pages(inode)); + 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); + + f2fs_lock_op(sbi); + remove_inode_page(inode); + f2fs_unlock_op(sbi); + + sb_end_intwrite(inode->i_sb); +no_delete: + stat_dec_inline_dir(inode); + stat_dec_inline_inode(inode); + + /* update extent info in inode */ + if (inode->i_nlink) + f2fs_preserve_extent_tree(inode); + f2fs_destroy_extent_tree(inode); + + invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino); + if (xnid) + invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid); + if (is_inode_flag_set(F2FS_I(inode), FI_APPEND_WRITE)) + add_dirty_inode(sbi, inode->i_ino, APPEND_INO); + if (is_inode_flag_set(F2FS_I(inode), FI_UPDATE_WRITE)) + add_dirty_inode(sbi, inode->i_ino, UPDATE_INO); +out_clear: + clear_inode(inode); +} + +/* caller should call f2fs_lock_op() */ +void handle_failed_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + clear_nlink(inode); + make_bad_inode(inode); + unlock_new_inode(inode); + + i_size_write(inode, 0); + if (F2FS_HAS_BLOCKS(inode)) + f2fs_truncate(inode); + + remove_inode_page(inode); + + clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + clear_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY); + alloc_nid_failed(sbi, inode->i_ino); + f2fs_unlock_op(sbi); + + /* iput will drop the inode object */ + iput(inode); +} diff --git a/kernel/fs/f2fs/namei.c b/kernel/fs/f2fs/namei.c new file mode 100644 index 000000000..658e8079a --- /dev/null +++ b/kernel/fs/f2fs/namei.c @@ -0,0 +1,832 @@ +/* + * 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 <linux/dcache.h> +#include <linux/namei.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 f2fs_sb_info *sbi = F2FS_I_SB(dir); + nid_t ino; + struct inode *inode; + bool nid_free = false; + int err; + + inode = new_inode(dir->i_sb); + if (!inode) + return ERR_PTR(-ENOMEM); + + f2fs_lock_op(sbi); + if (!alloc_nid(sbi, &ino)) { + f2fs_unlock_op(sbi); + err = -ENOSPC; + goto fail; + } + f2fs_unlock_op(sbi); + + inode_init_owner(inode, dir, mode); + + inode->i_ino = ino; + 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; + } + + if (f2fs_may_inline(inode)) + set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + if (test_opt(sbi, INLINE_DENTRY) && S_ISDIR(inode->i_mode)) + set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY); + + 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); + + if (sublen > slen) + return 0; + + return !strncasecmp(s + slen - sublen, sub, sublen); +} + +/* + * 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])) { + file_set_cold(inode); + break; + } + } +} + +static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool excl) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct inode *inode; + nid_t ino = 0; + int err; + + 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; + + f2fs_lock_op(sbi); + err = f2fs_add_link(dentry, inode); + if (err) + goto out; + f2fs_unlock_op(sbi); + + alloc_nid_done(sbi, ino); + + stat_inc_inline_inode(inode); + d_instantiate(dentry, inode); + unlock_new_inode(inode); + + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); + return 0; +out: + handle_failed_inode(inode); + return err; +} + +static int f2fs_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *dentry) +{ + struct inode *inode = d_inode(old_dentry); + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + int err; + + f2fs_balance_fs(sbi); + + inode->i_ctime = CURRENT_TIME; + ihold(inode); + + set_inode_flag(F2FS_I(inode), FI_INC_LINK); + f2fs_lock_op(sbi); + err = f2fs_add_link(dentry, inode); + if (err) + goto out; + f2fs_unlock_op(sbi); + + d_instantiate(dentry, inode); + + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); + return 0; +out: + clear_inode_flag(F2FS_I(inode), FI_INC_LINK); + iput(inode); + f2fs_unlock_op(sbi); + return err; +} + +struct dentry *f2fs_get_parent(struct dentry *child) +{ + struct qstr dotdot = QSTR_INIT("..", 2); + unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot); + if (!ino) + return ERR_PTR(-ENOENT); + return d_obtain_alias(f2fs_iget(d_inode(child)->i_sb, ino)); +} + +static int __recover_dot_dentries(struct inode *dir, nid_t pino) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct qstr dot = QSTR_INIT(".", 1); + struct qstr dotdot = QSTR_INIT("..", 2); + struct f2fs_dir_entry *de; + struct page *page; + int err = 0; + + f2fs_lock_op(sbi); + + de = f2fs_find_entry(dir, &dot, &page); + if (de) { + f2fs_dentry_kunmap(dir, page); + f2fs_put_page(page, 0); + } else { + err = __f2fs_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR); + if (err) + goto out; + } + + de = f2fs_find_entry(dir, &dotdot, &page); + if (de) { + f2fs_dentry_kunmap(dir, page); + f2fs_put_page(page, 0); + } else { + err = __f2fs_add_link(dir, &dotdot, NULL, pino, S_IFDIR); + } +out: + if (!err) { + clear_inode_flag(F2FS_I(dir), FI_INLINE_DOTS); + mark_inode_dirty(dir); + } + + f2fs_unlock_op(sbi); + return err; +} + +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); + f2fs_dentry_kunmap(dir, page); + f2fs_put_page(page, 0); + + inode = f2fs_iget(dir->i_sb, ino); + if (IS_ERR(inode)) + return ERR_CAST(inode); + + if (f2fs_has_inline_dots(inode)) { + int err; + + err = __recover_dot_dentries(inode, dir->i_ino); + if (err) { + iget_failed(inode); + return ERR_PTR(err); + } + } + } + + return d_splice_alias(inode, dentry); +} + +static int f2fs_unlink(struct inode *dir, struct dentry *dentry) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct inode *inode = d_inode(dentry); + struct f2fs_dir_entry *de; + struct page *page; + int err = -ENOENT; + + trace_f2fs_unlink_enter(dir, dentry); + f2fs_balance_fs(sbi); + + de = f2fs_find_entry(dir, &dentry->d_name, &page); + if (!de) + goto fail; + + f2fs_lock_op(sbi); + err = acquire_orphan_inode(sbi); + if (err) { + f2fs_unlock_op(sbi); + f2fs_dentry_kunmap(dir, page); + f2fs_put_page(page, 0); + goto fail; + } + f2fs_delete_entry(de, page, dir, inode); + f2fs_unlock_op(sbi); + + /* In order to evict this inode, we set it dirty */ + mark_inode_dirty(inode); + + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); +fail: + trace_f2fs_unlink_exit(inode, err); + return err; +} + +static void *f2fs_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + struct page *page = page_follow_link_light(dentry, nd); + + if (IS_ERR_OR_NULL(page)) + return page; + + /* this is broken symlink case */ + if (*nd_get_link(nd) == 0) { + page_put_link(dentry, nd, page); + return ERR_PTR(-ENOENT); + } + return page; +} + +static int f2fs_symlink(struct inode *dir, struct dentry *dentry, + const char *symname) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct inode *inode; + size_t symlen = strlen(symname) + 1; + int err; + + 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; + + f2fs_lock_op(sbi); + err = f2fs_add_link(dentry, inode); + if (err) + goto out; + f2fs_unlock_op(sbi); + + err = page_symlink(inode, symname, symlen); + alloc_nid_done(sbi, inode->i_ino); + + d_instantiate(dentry, inode); + unlock_new_inode(inode); + + /* + * Let's flush symlink data in order to avoid broken symlink as much as + * possible. Nevertheless, fsyncing is the best way, but there is no + * way to get a file descriptor in order to flush that. + * + * Note that, it needs to do dir->fsync to make this recoverable. + * If the symlink path is stored into inline_data, there is no + * performance regression. + */ + filemap_write_and_wait_range(inode->i_mapping, 0, symlen - 1); + + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); + return err; +out: + handle_failed_inode(inode); + return err; +} + +static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct inode *inode; + int err; + + 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_HIGH_ZERO); + + set_inode_flag(F2FS_I(inode), FI_INC_LINK); + f2fs_lock_op(sbi); + err = f2fs_add_link(dentry, inode); + if (err) + goto out_fail; + f2fs_unlock_op(sbi); + + stat_inc_inline_dir(inode); + alloc_nid_done(sbi, inode->i_ino); + + d_instantiate(dentry, inode); + unlock_new_inode(inode); + + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); + return 0; + +out_fail: + clear_inode_flag(F2FS_I(inode), FI_INC_LINK); + handle_failed_inode(inode); + return err; +} + +static int f2fs_rmdir(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + 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 f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct inode *inode; + int err = 0; + + 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; + + f2fs_lock_op(sbi); + err = f2fs_add_link(dentry, inode); + if (err) + goto out; + f2fs_unlock_op(sbi); + + alloc_nid_done(sbi, inode->i_ino); + + d_instantiate(dentry, inode); + unlock_new_inode(inode); + + if (IS_DIRSYNC(dir)) + f2fs_sync_fs(sbi->sb, 1); + return 0; +out: + handle_failed_inode(inode); + return err; +} + +static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir); + struct inode *old_inode = d_inode(old_dentry); + struct inode *new_inode = d_inode(new_dentry); + struct page *old_dir_page; + struct page *old_page, *new_page; + struct f2fs_dir_entry *old_dir_entry = NULL; + struct f2fs_dir_entry *old_entry; + struct f2fs_dir_entry *new_entry; + int err = -ENOENT; + + 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; + } + + if (new_inode) { + + 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_lock_op(sbi); + + err = acquire_orphan_inode(sbi); + if (err) + goto put_out_dir; + + if (update_dent_inode(old_inode, &new_dentry->d_name)) { + release_orphan_inode(sbi); + goto put_out_dir; + } + + f2fs_set_link(new_dir, new_entry, new_page, old_inode); + + new_inode->i_ctime = CURRENT_TIME; + down_write(&F2FS_I(new_inode)->i_sem); + if (old_dir_entry) + drop_nlink(new_inode); + drop_nlink(new_inode); + up_write(&F2FS_I(new_inode)->i_sem); + + mark_inode_dirty(new_inode); + + if (!new_inode->i_nlink) + add_orphan_inode(sbi, new_inode->i_ino); + else + release_orphan_inode(sbi); + + update_inode_page(old_inode); + update_inode_page(new_inode); + } else { + f2fs_lock_op(sbi); + + err = f2fs_add_link(new_dentry, old_inode); + if (err) { + f2fs_unlock_op(sbi); + goto out_dir; + } + + if (old_dir_entry) { + inc_nlink(new_dir); + update_inode_page(new_dir); + } + } + + down_write(&F2FS_I(old_inode)->i_sem); + file_lost_pino(old_inode); + up_write(&F2FS_I(old_inode)->i_sem); + + old_inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(old_inode); + + f2fs_delete_entry(old_entry, old_page, old_dir, NULL); + + if (old_dir_entry) { + if (old_dir != new_dir) { + f2fs_set_link(old_inode, old_dir_entry, + old_dir_page, new_dir); + update_inode_page(old_inode); + } else { + f2fs_dentry_kunmap(old_inode, old_dir_page); + f2fs_put_page(old_dir_page, 0); + } + drop_nlink(old_dir); + mark_inode_dirty(old_dir); + update_inode_page(old_dir); + } + + f2fs_unlock_op(sbi); + + if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) + f2fs_sync_fs(sbi->sb, 1); + return 0; + +put_out_dir: + f2fs_unlock_op(sbi); + f2fs_dentry_kunmap(new_dir, new_page); + f2fs_put_page(new_page, 0); +out_dir: + if (old_dir_entry) { + f2fs_dentry_kunmap(old_inode, old_dir_page); + f2fs_put_page(old_dir_page, 0); + } +out_old: + f2fs_dentry_kunmap(old_dir, old_page); + f2fs_put_page(old_page, 0); +out: + return err; +} + +static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir); + struct inode *old_inode = d_inode(old_dentry); + struct inode *new_inode = d_inode(new_dentry); + struct page *old_dir_page, *new_dir_page; + struct page *old_page, *new_page; + struct f2fs_dir_entry *old_dir_entry = NULL, *new_dir_entry = NULL; + struct f2fs_dir_entry *old_entry, *new_entry; + int old_nlink = 0, new_nlink = 0; + int err = -ENOENT; + + f2fs_balance_fs(sbi); + + old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); + if (!old_entry) + goto out; + + new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_page); + if (!new_entry) + goto out_old; + + /* prepare for updating ".." directory entry info later */ + if (old_dir != new_dir) { + 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_new; + } + + if (S_ISDIR(new_inode->i_mode)) { + err = -EIO; + new_dir_entry = f2fs_parent_dir(new_inode, + &new_dir_page); + if (!new_dir_entry) + goto out_old_dir; + } + } + + /* + * If cross rename between file and directory those are not + * in the same directory, we will inc nlink of file's parent + * later, so we should check upper boundary of its nlink. + */ + if ((!old_dir_entry || !new_dir_entry) && + old_dir_entry != new_dir_entry) { + old_nlink = old_dir_entry ? -1 : 1; + new_nlink = -old_nlink; + err = -EMLINK; + if ((old_nlink > 0 && old_inode->i_nlink >= F2FS_LINK_MAX) || + (new_nlink > 0 && new_inode->i_nlink >= F2FS_LINK_MAX)) + goto out_new_dir; + } + + f2fs_lock_op(sbi); + + err = update_dent_inode(old_inode, &new_dentry->d_name); + if (err) + goto out_unlock; + + err = update_dent_inode(new_inode, &old_dentry->d_name); + if (err) + goto out_undo; + + /* update ".." directory entry info of old dentry */ + if (old_dir_entry) + f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir); + + /* update ".." directory entry info of new dentry */ + if (new_dir_entry) + f2fs_set_link(new_inode, new_dir_entry, new_dir_page, old_dir); + + /* update directory entry info of old dir inode */ + f2fs_set_link(old_dir, old_entry, old_page, new_inode); + + down_write(&F2FS_I(old_inode)->i_sem); + file_lost_pino(old_inode); + up_write(&F2FS_I(old_inode)->i_sem); + + update_inode_page(old_inode); + + old_dir->i_ctime = CURRENT_TIME; + if (old_nlink) { + down_write(&F2FS_I(old_dir)->i_sem); + if (old_nlink < 0) + drop_nlink(old_dir); + else + inc_nlink(old_dir); + up_write(&F2FS_I(old_dir)->i_sem); + } + mark_inode_dirty(old_dir); + update_inode_page(old_dir); + + /* update directory entry info of new dir inode */ + f2fs_set_link(new_dir, new_entry, new_page, old_inode); + + down_write(&F2FS_I(new_inode)->i_sem); + file_lost_pino(new_inode); + up_write(&F2FS_I(new_inode)->i_sem); + + update_inode_page(new_inode); + + new_dir->i_ctime = CURRENT_TIME; + if (new_nlink) { + down_write(&F2FS_I(new_dir)->i_sem); + if (new_nlink < 0) + drop_nlink(new_dir); + else + inc_nlink(new_dir); + up_write(&F2FS_I(new_dir)->i_sem); + } + mark_inode_dirty(new_dir); + update_inode_page(new_dir); + + f2fs_unlock_op(sbi); + + if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) + f2fs_sync_fs(sbi->sb, 1); + return 0; +out_undo: + /* Still we may fail to recover name info of f2fs_inode here */ + update_dent_inode(old_inode, &old_dentry->d_name); +out_unlock: + f2fs_unlock_op(sbi); +out_new_dir: + if (new_dir_entry) { + f2fs_dentry_kunmap(new_inode, new_dir_page); + f2fs_put_page(new_dir_page, 0); + } +out_old_dir: + if (old_dir_entry) { + f2fs_dentry_kunmap(old_inode, old_dir_page); + f2fs_put_page(old_dir_page, 0); + } +out_new: + f2fs_dentry_kunmap(new_dir, new_page); + f2fs_put_page(new_page, 0); +out_old: + f2fs_dentry_kunmap(old_dir, old_page); + f2fs_put_page(old_page, 0); +out: + return err; +} + +static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + return -EINVAL; + + if (flags & RENAME_EXCHANGE) { + return f2fs_cross_rename(old_dir, old_dentry, + new_dir, new_dentry); + } + /* + * VFS has already handled the new dentry existence case, + * here, we just deal with "RENAME_NOREPLACE" as regular rename. + */ + return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry); +} + +static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + struct inode *inode; + int err; + + inode = f2fs_new_inode(dir, mode); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + inode->i_op = &f2fs_file_inode_operations; + inode->i_fop = &f2fs_file_operations; + inode->i_mapping->a_ops = &f2fs_dblock_aops; + + f2fs_lock_op(sbi); + err = acquire_orphan_inode(sbi); + if (err) + goto out; + + err = f2fs_do_tmpfile(inode, dir); + if (err) + goto release_out; + + /* + * add this non-linked tmpfile to orphan list, in this way we could + * remove all unused data of tmpfile after abnormal power-off. + */ + add_orphan_inode(sbi, inode->i_ino); + f2fs_unlock_op(sbi); + + alloc_nid_done(sbi, inode->i_ino); + + stat_inc_inline_inode(inode); + d_tmpfile(dentry, inode); + unlock_new_inode(inode); + return 0; + +release_out: + release_orphan_inode(sbi); +out: + handle_failed_inode(inode); + 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, + .rename2 = f2fs_rename2, + .tmpfile = f2fs_tmpfile, + .getattr = f2fs_getattr, + .setattr = f2fs_setattr, + .get_acl = f2fs_get_acl, + .set_acl = f2fs_set_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 = f2fs_follow_link, + .put_link = page_put_link, + .getattr = f2fs_getattr, + .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 = { + .getattr = f2fs_getattr, + .setattr = f2fs_setattr, + .get_acl = f2fs_get_acl, + .set_acl = f2fs_set_acl, +#ifdef CONFIG_F2FS_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = f2fs_listxattr, + .removexattr = generic_removexattr, +#endif +}; diff --git a/kernel/fs/f2fs/node.c b/kernel/fs/f2fs/node.c new file mode 100644 index 000000000..8ab0cf193 --- /dev/null +++ b/kernel/fs/f2fs/node.c @@ -0,0 +1,2084 @@ +/* + * fs/f2fs/node.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/mpage.h> +#include <linux/backing-dev.h> +#include <linux/blkdev.h> +#include <linux/pagevec.h> +#include <linux/swap.h> + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include "trace.h" +#include <trace/events/f2fs.h> + +#define on_build_free_nids(nmi) mutex_is_locked(&nm_i->build_lock) + +static struct kmem_cache *nat_entry_slab; +static struct kmem_cache *free_nid_slab; +static struct kmem_cache *nat_entry_set_slab; + +bool available_free_memory(struct f2fs_sb_info *sbi, int type) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct sysinfo val; + unsigned long avail_ram; + unsigned long mem_size = 0; + bool res = false; + + si_meminfo(&val); + + /* only uses low memory */ + avail_ram = val.totalram - val.totalhigh; + + /* + * give 25%, 25%, 50%, 50%, 50% memory for each components respectively + */ + if (type == FREE_NIDS) { + mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> + PAGE_CACHE_SHIFT; + res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); + } else if (type == NAT_ENTRIES) { + mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> + PAGE_CACHE_SHIFT; + res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); + } else if (type == DIRTY_DENTS) { + if (sbi->sb->s_bdi->dirty_exceeded) + return false; + mem_size = get_pages(sbi, F2FS_DIRTY_DENTS); + res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); + } else if (type == INO_ENTRIES) { + int i; + + for (i = 0; i <= UPDATE_INO; i++) + mem_size += (sbi->im[i].ino_num * + sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT; + res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); + } else if (type == EXTENT_CACHE) { + mem_size = (sbi->total_ext_tree * sizeof(struct extent_tree) + + atomic_read(&sbi->total_ext_node) * + sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT; + res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); + } else { + if (sbi->sb->s_bdi->dirty_exceeded) + return false; + } + return res; +} + +static void clear_node_page_dirty(struct page *page) +{ + struct address_space *mapping = page->mapping; + unsigned int long flags; + + if (PageDirty(page)) { + spin_lock_irqsave(&mapping->tree_lock, flags); + radix_tree_tag_clear(&mapping->page_tree, + page_index(page), + PAGECACHE_TAG_DIRTY); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + + clear_page_dirty_for_io(page); + dec_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES); + } + ClearPageUptodate(page); +} + +static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid) +{ + pgoff_t index = current_nat_addr(sbi, nid); + return get_meta_page(sbi, index); +} + +static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) +{ + struct page *src_page; + struct page *dst_page; + pgoff_t src_off; + pgoff_t dst_off; + void *src_addr; + void *dst_addr; + struct f2fs_nm_info *nm_i = NM_I(sbi); + + src_off = current_nat_addr(sbi, nid); + dst_off = next_nat_addr(sbi, src_off); + + /* get current nat block page with lock */ + src_page = get_meta_page(sbi, src_off); + dst_page = grab_meta_page(sbi, dst_off); + f2fs_bug_on(sbi, PageDirty(src_page)); + + src_addr = page_address(src_page); + dst_addr = page_address(dst_page); + memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE); + set_page_dirty(dst_page); + f2fs_put_page(src_page, 1); + + set_to_next_nat(nm_i, nid); + + return dst_page; +} + +static struct nat_entry *__lookup_nat_cache(struct f2fs_nm_info *nm_i, nid_t n) +{ + return radix_tree_lookup(&nm_i->nat_root, n); +} + +static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i, + nid_t start, unsigned int nr, struct nat_entry **ep) +{ + return radix_tree_gang_lookup(&nm_i->nat_root, (void **)ep, start, nr); +} + +static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e) +{ + list_del(&e->list); + radix_tree_delete(&nm_i->nat_root, nat_get_nid(e)); + nm_i->nat_cnt--; + kmem_cache_free(nat_entry_slab, e); +} + +static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, + struct nat_entry *ne) +{ + nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid); + struct nat_entry_set *head; + + if (get_nat_flag(ne, IS_DIRTY)) + return; + + head = radix_tree_lookup(&nm_i->nat_set_root, set); + if (!head) { + head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_ATOMIC); + + INIT_LIST_HEAD(&head->entry_list); + INIT_LIST_HEAD(&head->set_list); + head->set = set; + head->entry_cnt = 0; + f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head); + } + list_move_tail(&ne->list, &head->entry_list); + nm_i->dirty_nat_cnt++; + head->entry_cnt++; + set_nat_flag(ne, IS_DIRTY, true); +} + +static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i, + struct nat_entry *ne) +{ + nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid); + struct nat_entry_set *head; + + head = radix_tree_lookup(&nm_i->nat_set_root, set); + if (head) { + list_move_tail(&ne->list, &nm_i->nat_entries); + set_nat_flag(ne, IS_DIRTY, false); + head->entry_cnt--; + nm_i->dirty_nat_cnt--; + } +} + +static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i, + nid_t start, unsigned int nr, struct nat_entry_set **ep) +{ + return radix_tree_gang_lookup(&nm_i->nat_set_root, (void **)ep, + start, nr); +} + +bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct nat_entry *e; + bool is_cp = true; + + down_read(&nm_i->nat_tree_lock); + e = __lookup_nat_cache(nm_i, nid); + if (e && !get_nat_flag(e, IS_CHECKPOINTED)) + is_cp = false; + up_read(&nm_i->nat_tree_lock); + return is_cp; +} + +bool has_fsynced_inode(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct nat_entry *e; + bool fsynced = false; + + down_read(&nm_i->nat_tree_lock); + e = __lookup_nat_cache(nm_i, ino); + if (e && get_nat_flag(e, HAS_FSYNCED_INODE)) + fsynced = true; + up_read(&nm_i->nat_tree_lock); + return fsynced; +} + +bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct nat_entry *e; + bool need_update = true; + + down_read(&nm_i->nat_tree_lock); + e = __lookup_nat_cache(nm_i, ino); + if (e && get_nat_flag(e, HAS_LAST_FSYNC) && + (get_nat_flag(e, IS_CHECKPOINTED) || + get_nat_flag(e, HAS_FSYNCED_INODE))) + need_update = false; + up_read(&nm_i->nat_tree_lock); + return need_update; +} + +static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid) +{ + struct nat_entry *new; + + new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_ATOMIC); + f2fs_radix_tree_insert(&nm_i->nat_root, nid, new); + memset(new, 0, sizeof(struct nat_entry)); + nat_set_nid(new, nid); + nat_reset_flag(new); + list_add_tail(&new->list, &nm_i->nat_entries); + nm_i->nat_cnt++; + return new; +} + +static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid, + struct f2fs_nat_entry *ne) +{ + struct nat_entry *e; + + down_write(&nm_i->nat_tree_lock); + e = __lookup_nat_cache(nm_i, nid); + if (!e) { + e = grab_nat_entry(nm_i, nid); + node_info_from_raw_nat(&e->ni, ne); + } + up_write(&nm_i->nat_tree_lock); +} + +static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, + block_t new_blkaddr, bool fsync_done) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct nat_entry *e; + + down_write(&nm_i->nat_tree_lock); + e = __lookup_nat_cache(nm_i, ni->nid); + if (!e) { + e = grab_nat_entry(nm_i, ni->nid); + copy_node_info(&e->ni, ni); + f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR); + } else if (new_blkaddr == NEW_ADDR) { + /* + * when nid is reallocated, + * previous nat entry can be remained in nat cache. + * So, reinitialize it with new information. + */ + copy_node_info(&e->ni, ni); + f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR); + } + + /* sanity check */ + f2fs_bug_on(sbi, nat_get_blkaddr(e) != ni->blk_addr); + f2fs_bug_on(sbi, nat_get_blkaddr(e) == NULL_ADDR && + new_blkaddr == NULL_ADDR); + f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR && + new_blkaddr == NEW_ADDR); + f2fs_bug_on(sbi, nat_get_blkaddr(e) != NEW_ADDR && + nat_get_blkaddr(e) != NULL_ADDR && + new_blkaddr == NEW_ADDR); + + /* increment version no as node is removed */ + if (nat_get_blkaddr(e) != NEW_ADDR && new_blkaddr == NULL_ADDR) { + unsigned char version = nat_get_version(e); + nat_set_version(e, inc_node_version(version)); + } + + /* change address */ + nat_set_blkaddr(e, new_blkaddr); + if (new_blkaddr == NEW_ADDR || new_blkaddr == NULL_ADDR) + set_nat_flag(e, IS_CHECKPOINTED, false); + __set_nat_cache_dirty(nm_i, e); + + /* update fsync_mark if its inode nat entry is still alive */ + e = __lookup_nat_cache(nm_i, ni->ino); + if (e) { + if (fsync_done && ni->nid == ni->ino) + set_nat_flag(e, HAS_FSYNCED_INODE, true); + set_nat_flag(e, HAS_LAST_FSYNC, fsync_done); + } + up_write(&nm_i->nat_tree_lock); +} + +int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + + if (available_free_memory(sbi, NAT_ENTRIES)) + return 0; + + down_write(&nm_i->nat_tree_lock); + while (nr_shrink && !list_empty(&nm_i->nat_entries)) { + struct nat_entry *ne; + ne = list_first_entry(&nm_i->nat_entries, + struct nat_entry, list); + __del_from_nat_cache(nm_i, ne); + nr_shrink--; + } + up_write(&nm_i->nat_tree_lock); + return nr_shrink; +} + +/* + * This function always returns success + */ +void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); + struct f2fs_summary_block *sum = curseg->sum_blk; + nid_t start_nid = START_NID(nid); + struct f2fs_nat_block *nat_blk; + struct page *page = NULL; + struct f2fs_nat_entry ne; + struct nat_entry *e; + int i; + + ni->nid = nid; + + /* Check nat cache */ + down_read(&nm_i->nat_tree_lock); + e = __lookup_nat_cache(nm_i, nid); + if (e) { + ni->ino = nat_get_ino(e); + ni->blk_addr = nat_get_blkaddr(e); + ni->version = nat_get_version(e); + } + up_read(&nm_i->nat_tree_lock); + if (e) + return; + + memset(&ne, 0, sizeof(struct f2fs_nat_entry)); + + /* Check current segment summary */ + mutex_lock(&curseg->curseg_mutex); + i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0); + if (i >= 0) { + ne = nat_in_journal(sum, i); + node_info_from_raw_nat(ni, &ne); + } + mutex_unlock(&curseg->curseg_mutex); + if (i >= 0) + goto cache; + + /* Fill node_info from nat page */ + page = get_current_nat_page(sbi, start_nid); + nat_blk = (struct f2fs_nat_block *)page_address(page); + ne = nat_blk->entries[nid - start_nid]; + node_info_from_raw_nat(ni, &ne); + f2fs_put_page(page, 1); +cache: + /* cache nat entry */ + cache_nat_entry(NM_I(sbi), nid, &ne); +} + +/* + * The maximum depth is four. + * Offset[0] will have raw inode offset. + */ +static int get_node_path(struct f2fs_inode_info *fi, long block, + int offset[4], unsigned int noffset[4]) +{ + const long direct_index = ADDRS_PER_INODE(fi); + const long direct_blks = ADDRS_PER_BLOCK; + const long dptrs_per_blk = NIDS_PER_BLOCK; + const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; + const long dindirect_blks = indirect_blks * NIDS_PER_BLOCK; + int n = 0; + int level = 0; + + noffset[0] = 0; + + if (block < direct_index) { + offset[n] = block; + goto got; + } + block -= direct_index; + if (block < direct_blks) { + offset[n++] = NODE_DIR1_BLOCK; + noffset[n] = 1; + offset[n] = block; + level = 1; + goto got; + } + block -= direct_blks; + if (block < direct_blks) { + offset[n++] = NODE_DIR2_BLOCK; + noffset[n] = 2; + offset[n] = block; + level = 1; + goto got; + } + block -= direct_blks; + if (block < indirect_blks) { + offset[n++] = NODE_IND1_BLOCK; + noffset[n] = 3; + offset[n++] = block / direct_blks; + noffset[n] = 4 + offset[n - 1]; + offset[n] = block % direct_blks; + level = 2; + goto got; + } + block -= indirect_blks; + if (block < indirect_blks) { + offset[n++] = NODE_IND2_BLOCK; + noffset[n] = 4 + dptrs_per_blk; + offset[n++] = block / direct_blks; + noffset[n] = 5 + dptrs_per_blk + offset[n - 1]; + offset[n] = block % direct_blks; + level = 2; + goto got; + } + block -= indirect_blks; + if (block < dindirect_blks) { + offset[n++] = NODE_DIND_BLOCK; + noffset[n] = 5 + (dptrs_per_blk * 2); + offset[n++] = block / indirect_blks; + noffset[n] = 6 + (dptrs_per_blk * 2) + + offset[n - 1] * (dptrs_per_blk + 1); + offset[n++] = (block / direct_blks) % dptrs_per_blk; + noffset[n] = 7 + (dptrs_per_blk * 2) + + offset[n - 2] * (dptrs_per_blk + 1) + + offset[n - 1]; + offset[n] = block % direct_blks; + level = 3; + goto got; + } else { + BUG(); + } +got: + return level; +} + +/* + * Caller should call f2fs_put_dnode(dn). + * Also, it should grab and release a rwsem by calling f2fs_lock_op() and + * f2fs_unlock_op() only if ro is not set RDONLY_NODE. + * In the case of RDONLY_NODE, we don't need to care about mutex. + */ +int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + struct page *npage[4]; + struct page *parent = NULL; + int offset[4]; + unsigned int noffset[4]; + nid_t nids[4]; + int level, i; + int err = 0; + + level = get_node_path(F2FS_I(dn->inode), index, offset, noffset); + + nids[0] = dn->inode->i_ino; + npage[0] = dn->inode_page; + + if (!npage[0]) { + npage[0] = get_node_page(sbi, nids[0]); + if (IS_ERR(npage[0])) + return PTR_ERR(npage[0]); + } + + /* if inline_data is set, should not report any block indices */ + if (f2fs_has_inline_data(dn->inode) && index) { + err = -ENOENT; + f2fs_put_page(npage[0], 1); + goto release_out; + } + + parent = npage[0]; + if (level != 0) + nids[1] = get_nid(parent, offset[0], true); + dn->inode_page = npage[0]; + dn->inode_page_locked = true; + + /* get indirect or direct nodes */ + for (i = 1; i <= level; i++) { + bool done = false; + + if (!nids[i] && mode == ALLOC_NODE) { + /* alloc new node */ + if (!alloc_nid(sbi, &(nids[i]))) { + err = -ENOSPC; + goto release_pages; + } + + dn->nid = nids[i]; + npage[i] = new_node_page(dn, noffset[i], NULL); + if (IS_ERR(npage[i])) { + alloc_nid_failed(sbi, nids[i]); + err = PTR_ERR(npage[i]); + goto release_pages; + } + + set_nid(parent, offset[i - 1], nids[i], i == 1); + alloc_nid_done(sbi, nids[i]); + done = true; + } else if (mode == LOOKUP_NODE_RA && i == level && level > 1) { + npage[i] = get_node_page_ra(parent, offset[i - 1]); + if (IS_ERR(npage[i])) { + err = PTR_ERR(npage[i]); + goto release_pages; + } + done = true; + } + if (i == 1) { + dn->inode_page_locked = false; + unlock_page(parent); + } else { + f2fs_put_page(parent, 1); + } + + if (!done) { + npage[i] = get_node_page(sbi, nids[i]); + if (IS_ERR(npage[i])) { + err = PTR_ERR(npage[i]); + f2fs_put_page(npage[0], 0); + goto release_out; + } + } + if (i < level) { + parent = npage[i]; + nids[i + 1] = get_nid(parent, offset[i], false); + } + } + dn->nid = nids[level]; + dn->ofs_in_node = offset[level]; + dn->node_page = npage[level]; + dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node); + return 0; + +release_pages: + f2fs_put_page(parent, 1); + if (i > 1) + f2fs_put_page(npage[0], 0); +release_out: + dn->inode_page = NULL; + dn->node_page = NULL; + return err; +} + +static void truncate_node(struct dnode_of_data *dn) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + struct node_info ni; + + get_node_info(sbi, dn->nid, &ni); + if (dn->inode->i_blocks == 0) { + f2fs_bug_on(sbi, ni.blk_addr != NULL_ADDR); + goto invalidate; + } + f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR); + + /* Deallocate node address */ + invalidate_blocks(sbi, ni.blk_addr); + dec_valid_node_count(sbi, dn->inode); + set_node_addr(sbi, &ni, NULL_ADDR, false); + + if (dn->nid == dn->inode->i_ino) { + remove_orphan_inode(sbi, dn->nid); + dec_valid_inode_count(sbi); + } else { + sync_inode_page(dn); + } +invalidate: + clear_node_page_dirty(dn->node_page); + set_sbi_flag(sbi, SBI_IS_DIRTY); + + f2fs_put_page(dn->node_page, 1); + + invalidate_mapping_pages(NODE_MAPPING(sbi), + dn->node_page->index, dn->node_page->index); + + dn->node_page = NULL; + trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr); +} + +static int truncate_dnode(struct dnode_of_data *dn) +{ + struct page *page; + + if (dn->nid == 0) + return 1; + + /* get direct node */ + page = get_node_page(F2FS_I_SB(dn->inode), dn->nid); + if (IS_ERR(page) && PTR_ERR(page) == -ENOENT) + return 1; + else if (IS_ERR(page)) + return PTR_ERR(page); + + /* Make dnode_of_data for parameter */ + dn->node_page = page; + dn->ofs_in_node = 0; + truncate_data_blocks(dn); + truncate_node(dn); + return 1; +} + +static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, + int ofs, int depth) +{ + struct dnode_of_data rdn = *dn; + struct page *page; + struct f2fs_node *rn; + nid_t child_nid; + unsigned int child_nofs; + int freed = 0; + int i, ret; + + if (dn->nid == 0) + return NIDS_PER_BLOCK + 1; + + trace_f2fs_truncate_nodes_enter(dn->inode, dn->nid, dn->data_blkaddr); + + page = get_node_page(F2FS_I_SB(dn->inode), dn->nid); + if (IS_ERR(page)) { + trace_f2fs_truncate_nodes_exit(dn->inode, PTR_ERR(page)); + return PTR_ERR(page); + } + + rn = F2FS_NODE(page); + if (depth < 3) { + for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) { + child_nid = le32_to_cpu(rn->in.nid[i]); + if (child_nid == 0) + continue; + rdn.nid = child_nid; + ret = truncate_dnode(&rdn); + if (ret < 0) + goto out_err; + set_nid(page, i, 0, false); + } + } else { + child_nofs = nofs + ofs * (NIDS_PER_BLOCK + 1) + 1; + for (i = ofs; i < NIDS_PER_BLOCK; i++) { + child_nid = le32_to_cpu(rn->in.nid[i]); + if (child_nid == 0) { + child_nofs += NIDS_PER_BLOCK + 1; + continue; + } + rdn.nid = child_nid; + ret = truncate_nodes(&rdn, child_nofs, 0, depth - 1); + if (ret == (NIDS_PER_BLOCK + 1)) { + set_nid(page, i, 0, false); + child_nofs += ret; + } else if (ret < 0 && ret != -ENOENT) { + goto out_err; + } + } + freed = child_nofs; + } + + if (!ofs) { + /* remove current indirect node */ + dn->node_page = page; + truncate_node(dn); + freed++; + } else { + f2fs_put_page(page, 1); + } + trace_f2fs_truncate_nodes_exit(dn->inode, freed); + return freed; + +out_err: + f2fs_put_page(page, 1); + trace_f2fs_truncate_nodes_exit(dn->inode, ret); + return ret; +} + +static int truncate_partial_nodes(struct dnode_of_data *dn, + struct f2fs_inode *ri, int *offset, int depth) +{ + struct page *pages[2]; + nid_t nid[3]; + nid_t child_nid; + int err = 0; + int i; + int idx = depth - 2; + + nid[0] = le32_to_cpu(ri->i_nid[offset[0] - NODE_DIR1_BLOCK]); + if (!nid[0]) + return 0; + + /* get indirect nodes in the path */ + for (i = 0; i < idx + 1; i++) { + /* reference count'll be increased */ + pages[i] = get_node_page(F2FS_I_SB(dn->inode), nid[i]); + if (IS_ERR(pages[i])) { + err = PTR_ERR(pages[i]); + idx = i - 1; + goto fail; + } + nid[i + 1] = get_nid(pages[i], offset[i + 1], false); + } + + /* free direct nodes linked to a partial indirect node */ + for (i = offset[idx + 1]; i < NIDS_PER_BLOCK; i++) { + child_nid = get_nid(pages[idx], i, false); + if (!child_nid) + continue; + dn->nid = child_nid; + err = truncate_dnode(dn); + if (err < 0) + goto fail; + set_nid(pages[idx], i, 0, false); + } + + if (offset[idx + 1] == 0) { + dn->node_page = pages[idx]; + dn->nid = nid[idx]; + truncate_node(dn); + } else { + f2fs_put_page(pages[idx], 1); + } + offset[idx]++; + offset[idx + 1] = 0; + idx--; +fail: + for (i = idx; i >= 0; i--) + f2fs_put_page(pages[i], 1); + + trace_f2fs_truncate_partial_nodes(dn->inode, nid, depth, err); + + return err; +} + +/* + * All the block addresses of data and nodes should be nullified. + */ +int truncate_inode_blocks(struct inode *inode, pgoff_t from) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int err = 0, cont = 1; + int level, offset[4], noffset[4]; + unsigned int nofs = 0; + struct f2fs_inode *ri; + struct dnode_of_data dn; + struct page *page; + + trace_f2fs_truncate_inode_blocks_enter(inode, from); + + level = get_node_path(F2FS_I(inode), from, offset, noffset); +restart: + page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(page)) { + trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page)); + return PTR_ERR(page); + } + + set_new_dnode(&dn, inode, page, NULL, 0); + unlock_page(page); + + ri = F2FS_INODE(page); + switch (level) { + case 0: + case 1: + nofs = noffset[1]; + break; + case 2: + nofs = noffset[1]; + if (!offset[level - 1]) + goto skip_partial; + err = truncate_partial_nodes(&dn, ri, offset, level); + if (err < 0 && err != -ENOENT) + goto fail; + nofs += 1 + NIDS_PER_BLOCK; + break; + case 3: + nofs = 5 + 2 * NIDS_PER_BLOCK; + if (!offset[level - 1]) + goto skip_partial; + err = truncate_partial_nodes(&dn, ri, offset, level); + if (err < 0 && err != -ENOENT) + goto fail; + break; + default: + BUG(); + } + +skip_partial: + while (cont) { + dn.nid = le32_to_cpu(ri->i_nid[offset[0] - NODE_DIR1_BLOCK]); + switch (offset[0]) { + case NODE_DIR1_BLOCK: + case NODE_DIR2_BLOCK: + err = truncate_dnode(&dn); + break; + + case NODE_IND1_BLOCK: + case NODE_IND2_BLOCK: + err = truncate_nodes(&dn, nofs, offset[1], 2); + break; + + case NODE_DIND_BLOCK: + err = truncate_nodes(&dn, nofs, offset[1], 3); + cont = 0; + break; + + default: + BUG(); + } + if (err < 0 && err != -ENOENT) + goto fail; + if (offset[1] == 0 && + ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) { + lock_page(page); + if (unlikely(page->mapping != NODE_MAPPING(sbi))) { + f2fs_put_page(page, 1); + goto restart; + } + f2fs_wait_on_page_writeback(page, NODE); + ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0; + set_page_dirty(page); + unlock_page(page); + } + offset[1] = 0; + offset[0]++; + nofs += err; + } +fail: + f2fs_put_page(page, 0); + trace_f2fs_truncate_inode_blocks_exit(inode, err); + return err > 0 ? 0 : err; +} + +int truncate_xattr_node(struct inode *inode, struct page *page) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + nid_t nid = F2FS_I(inode)->i_xattr_nid; + struct dnode_of_data dn; + struct page *npage; + + if (!nid) + return 0; + + npage = get_node_page(sbi, nid); + if (IS_ERR(npage)) + return PTR_ERR(npage); + + F2FS_I(inode)->i_xattr_nid = 0; + + /* need to do checkpoint during fsync */ + F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi)); + + set_new_dnode(&dn, inode, page, npage, nid); + + if (page) + dn.inode_page_locked = true; + truncate_node(&dn); + return 0; +} + +/* + * Caller should grab and release a rwsem by calling f2fs_lock_op() and + * f2fs_unlock_op(). + */ +void remove_inode_page(struct inode *inode) +{ + struct dnode_of_data dn; + + set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); + if (get_dnode_of_data(&dn, 0, LOOKUP_NODE)) + return; + + if (truncate_xattr_node(inode, dn.inode_page)) { + f2fs_put_dnode(&dn); + return; + } + + /* remove potential inline_data blocks */ + if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode)) + truncate_data_blocks_range(&dn, 1); + + /* 0 is possible, after f2fs_new_inode() has failed */ + f2fs_bug_on(F2FS_I_SB(inode), + inode->i_blocks != 0 && inode->i_blocks != 1); + + /* will put inode & node pages */ + truncate_node(&dn); +} + +struct page *new_inode_page(struct inode *inode) +{ + struct dnode_of_data dn; + + /* allocate inode page for new inode */ + set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); + + /* caller should f2fs_put_page(page, 1); */ + return new_node_page(&dn, 0, NULL); +} + +struct page *new_node_page(struct dnode_of_data *dn, + unsigned int ofs, struct page *ipage) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + struct node_info old_ni, new_ni; + struct page *page; + int err; + + if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC))) + return ERR_PTR(-EPERM); + + page = grab_cache_page(NODE_MAPPING(sbi), dn->nid); + if (!page) + return ERR_PTR(-ENOMEM); + + if (unlikely(!inc_valid_node_count(sbi, dn->inode))) { + err = -ENOSPC; + goto fail; + } + + get_node_info(sbi, dn->nid, &old_ni); + + /* Reinitialize old_ni with new node page */ + f2fs_bug_on(sbi, old_ni.blk_addr != NULL_ADDR); + new_ni = old_ni; + new_ni.ino = dn->inode->i_ino; + set_node_addr(sbi, &new_ni, NEW_ADDR, false); + + f2fs_wait_on_page_writeback(page, NODE); + fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true); + set_cold_node(dn->inode, page); + SetPageUptodate(page); + set_page_dirty(page); + + if (f2fs_has_xattr_block(ofs)) + F2FS_I(dn->inode)->i_xattr_nid = dn->nid; + + dn->node_page = page; + if (ipage) + update_inode(dn->inode, ipage); + else + sync_inode_page(dn); + if (ofs == 0) + inc_valid_inode_count(sbi); + + return page; + +fail: + clear_node_page_dirty(page); + f2fs_put_page(page, 1); + return ERR_PTR(err); +} + +/* + * Caller should do after getting the following values. + * 0: f2fs_put_page(page, 0) + * LOCKED_PAGE: f2fs_put_page(page, 1) + * error: nothing + */ +static int read_node_page(struct page *page, int rw) +{ + struct f2fs_sb_info *sbi = F2FS_P_SB(page); + struct node_info ni; + struct f2fs_io_info fio = { + .type = NODE, + .rw = rw, + }; + + get_node_info(sbi, page->index, &ni); + + if (unlikely(ni.blk_addr == NULL_ADDR)) { + ClearPageUptodate(page); + f2fs_put_page(page, 1); + return -ENOENT; + } + + if (PageUptodate(page)) + return LOCKED_PAGE; + + fio.blk_addr = ni.blk_addr; + return f2fs_submit_page_bio(sbi, page, &fio); +} + +/* + * Readahead a node page + */ +void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) +{ + struct page *apage; + int err; + + apage = find_get_page(NODE_MAPPING(sbi), nid); + if (apage && PageUptodate(apage)) { + f2fs_put_page(apage, 0); + return; + } + f2fs_put_page(apage, 0); + + apage = grab_cache_page(NODE_MAPPING(sbi), nid); + if (!apage) + return; + + err = read_node_page(apage, READA); + if (err == 0) + f2fs_put_page(apage, 0); + else if (err == LOCKED_PAGE) + f2fs_put_page(apage, 1); +} + +struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) +{ + struct page *page; + int err; +repeat: + page = grab_cache_page(NODE_MAPPING(sbi), nid); + if (!page) + return ERR_PTR(-ENOMEM); + + err = read_node_page(page, READ_SYNC); + if (err < 0) + return ERR_PTR(err); + else if (err != LOCKED_PAGE) + lock_page(page); + + if (unlikely(!PageUptodate(page) || nid != nid_of_node(page))) { + ClearPageUptodate(page); + f2fs_put_page(page, 1); + return ERR_PTR(-EIO); + } + if (unlikely(page->mapping != NODE_MAPPING(sbi))) { + f2fs_put_page(page, 1); + goto repeat; + } + return page; +} + +/* + * Return a locked page for the desired node page. + * And, readahead MAX_RA_NODE number of node pages. + */ +struct page *get_node_page_ra(struct page *parent, int start) +{ + struct f2fs_sb_info *sbi = F2FS_P_SB(parent); + struct blk_plug plug; + struct page *page; + int err, i, end; + nid_t nid; + + /* First, try getting the desired direct node. */ + nid = get_nid(parent, start, false); + if (!nid) + return ERR_PTR(-ENOENT); +repeat: + page = grab_cache_page(NODE_MAPPING(sbi), nid); + if (!page) + return ERR_PTR(-ENOMEM); + + err = read_node_page(page, READ_SYNC); + if (err < 0) + return ERR_PTR(err); + else if (err == LOCKED_PAGE) + goto page_hit; + + blk_start_plug(&plug); + + /* Then, try readahead for siblings of the desired node */ + end = start + MAX_RA_NODE; + end = min(end, NIDS_PER_BLOCK); + for (i = start + 1; i < end; i++) { + nid = get_nid(parent, i, false); + if (!nid) + continue; + ra_node_page(sbi, nid); + } + + blk_finish_plug(&plug); + + lock_page(page); + if (unlikely(page->mapping != NODE_MAPPING(sbi))) { + f2fs_put_page(page, 1); + goto repeat; + } +page_hit: + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 1); + return ERR_PTR(-EIO); + } + return page; +} + +void sync_inode_page(struct dnode_of_data *dn) +{ + if (IS_INODE(dn->node_page) || dn->inode_page == dn->node_page) { + update_inode(dn->inode, dn->node_page); + } else if (dn->inode_page) { + if (!dn->inode_page_locked) + lock_page(dn->inode_page); + update_inode(dn->inode, dn->inode_page); + if (!dn->inode_page_locked) + unlock_page(dn->inode_page); + } else { + update_inode_page(dn->inode); + } +} + +int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino, + struct writeback_control *wbc) +{ + pgoff_t index, end; + struct pagevec pvec; + int step = ino ? 2 : 0; + int nwritten = 0, wrote = 0; + + pagevec_init(&pvec, 0); + +next_step: + index = 0; + end = LONG_MAX; + + while (index <= end) { + int i, nr_pages; + nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &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]; + + /* + * flushing sequence with step: + * 0. indirect nodes + * 1. dentry dnodes + * 2. file dnodes + */ + if (step == 0 && IS_DNODE(page)) + continue; + if (step == 1 && (!IS_DNODE(page) || + is_cold_node(page))) + continue; + if (step == 2 && (!IS_DNODE(page) || + !is_cold_node(page))) + continue; + + /* + * If an fsync mode, + * we should not skip writing node pages. + */ + if (ino && ino_of_node(page) == ino) + lock_page(page); + else if (!trylock_page(page)) + continue; + + if (unlikely(page->mapping != NODE_MAPPING(sbi))) { +continue_unlock: + unlock_page(page); + continue; + } + if (ino && ino_of_node(page) != ino) + goto continue_unlock; + + if (!PageDirty(page)) { + /* someone wrote it for us */ + goto continue_unlock; + } + + if (!clear_page_dirty_for_io(page)) + goto continue_unlock; + + /* called by fsync() */ + if (ino && IS_DNODE(page)) { + set_fsync_mark(page, 1); + if (IS_INODE(page)) { + if (!is_checkpointed_node(sbi, ino) && + !has_fsynced_inode(sbi, ino)) + set_dentry_mark(page, 1); + else + set_dentry_mark(page, 0); + } + nwritten++; + } else { + set_fsync_mark(page, 0); + set_dentry_mark(page, 0); + } + + if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc)) + unlock_page(page); + else + wrote++; + + if (--wbc->nr_to_write == 0) + break; + } + pagevec_release(&pvec); + cond_resched(); + + if (wbc->nr_to_write == 0) { + step = 2; + break; + } + } + + if (step < 2) { + step++; + goto next_step; + } + + if (wrote) + f2fs_submit_merged_bio(sbi, NODE, WRITE); + return nwritten; +} + +int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino) +{ + pgoff_t index = 0, end = LONG_MAX; + struct pagevec pvec; + int ret2 = 0, ret = 0; + + pagevec_init(&pvec, 0); + + while (index <= end) { + int i, nr_pages; + nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, + PAGECACHE_TAG_WRITEBACK, + 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]; + + /* until radix tree lookup accepts end_index */ + if (unlikely(page->index > end)) + continue; + + if (ino && ino_of_node(page) == ino) { + f2fs_wait_on_page_writeback(page, NODE); + if (TestClearPageError(page)) + ret = -EIO; + } + } + pagevec_release(&pvec); + cond_resched(); + } + + if (unlikely(test_and_clear_bit(AS_ENOSPC, &NODE_MAPPING(sbi)->flags))) + ret2 = -ENOSPC; + if (unlikely(test_and_clear_bit(AS_EIO, &NODE_MAPPING(sbi)->flags))) + ret2 = -EIO; + if (!ret) + ret = ret2; + return ret; +} + +static int f2fs_write_node_page(struct page *page, + struct writeback_control *wbc) +{ + struct f2fs_sb_info *sbi = F2FS_P_SB(page); + nid_t nid; + struct node_info ni; + struct f2fs_io_info fio = { + .type = NODE, + .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE, + }; + + trace_f2fs_writepage(page, NODE); + + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + goto redirty_out; + if (unlikely(f2fs_cp_error(sbi))) + goto redirty_out; + + f2fs_wait_on_page_writeback(page, NODE); + + /* get old block addr of this node page */ + nid = nid_of_node(page); + f2fs_bug_on(sbi, page->index != nid); + + get_node_info(sbi, nid, &ni); + + /* This page is already truncated */ + if (unlikely(ni.blk_addr == NULL_ADDR)) { + ClearPageUptodate(page); + dec_page_count(sbi, F2FS_DIRTY_NODES); + unlock_page(page); + return 0; + } + + if (wbc->for_reclaim) { + if (!down_read_trylock(&sbi->node_write)) + goto redirty_out; + } else { + down_read(&sbi->node_write); + } + + set_page_writeback(page); + fio.blk_addr = ni.blk_addr; + write_node_page(sbi, page, nid, &fio); + set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page)); + dec_page_count(sbi, F2FS_DIRTY_NODES); + up_read(&sbi->node_write); + unlock_page(page); + + if (wbc->for_reclaim) + f2fs_submit_merged_bio(sbi, NODE, WRITE); + + return 0; + +redirty_out: + redirty_page_for_writepage(wbc, page); + return AOP_WRITEPAGE_ACTIVATE; +} + +static int f2fs_write_node_pages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); + long diff; + + trace_f2fs_writepages(mapping->host, wbc, NODE); + + /* balancing f2fs's metadata in background */ + f2fs_balance_fs_bg(sbi); + + /* collect a number of dirty node pages and write together */ + if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE)) + goto skip_write; + + diff = nr_pages_to_write(sbi, NODE, wbc); + wbc->sync_mode = WB_SYNC_NONE; + sync_node_pages(sbi, 0, wbc); + wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff); + return 0; + +skip_write: + wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_NODES); + return 0; +} + +static int f2fs_set_node_page_dirty(struct page *page) +{ + trace_f2fs_set_page_dirty(page, NODE); + + SetPageUptodate(page); + if (!PageDirty(page)) { + __set_page_dirty_nobuffers(page); + inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); + SetPagePrivate(page); + f2fs_trace_pid(page); + return 1; + } + return 0; +} + +/* + * Structure of the f2fs node operations + */ +const struct address_space_operations f2fs_node_aops = { + .writepage = f2fs_write_node_page, + .writepages = f2fs_write_node_pages, + .set_page_dirty = f2fs_set_node_page_dirty, + .invalidatepage = f2fs_invalidate_page, + .releasepage = f2fs_release_page, +}; + +static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i, + nid_t n) +{ + return radix_tree_lookup(&nm_i->free_nid_root, n); +} + +static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i, + struct free_nid *i) +{ + list_del(&i->list); + radix_tree_delete(&nm_i->free_nid_root, i->nid); +} + +static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct free_nid *i; + struct nat_entry *ne; + bool allocated = false; + + if (!available_free_memory(sbi, FREE_NIDS)) + return -1; + + /* 0 nid should not be used */ + if (unlikely(nid == 0)) + return 0; + + if (build) { + /* do not add allocated nids */ + down_read(&nm_i->nat_tree_lock); + ne = __lookup_nat_cache(nm_i, nid); + if (ne && + (!get_nat_flag(ne, IS_CHECKPOINTED) || + nat_get_blkaddr(ne) != NULL_ADDR)) + allocated = true; + up_read(&nm_i->nat_tree_lock); + if (allocated) + return 0; + } + + i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS); + i->nid = nid; + i->state = NID_NEW; + + if (radix_tree_preload(GFP_NOFS)) { + kmem_cache_free(free_nid_slab, i); + return 0; + } + + spin_lock(&nm_i->free_nid_list_lock); + if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) { + spin_unlock(&nm_i->free_nid_list_lock); + radix_tree_preload_end(); + kmem_cache_free(free_nid_slab, i); + return 0; + } + list_add_tail(&i->list, &nm_i->free_nid_list); + nm_i->fcnt++; + spin_unlock(&nm_i->free_nid_list_lock); + radix_tree_preload_end(); + return 1; +} + +static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid) +{ + struct free_nid *i; + bool need_free = false; + + spin_lock(&nm_i->free_nid_list_lock); + i = __lookup_free_nid_list(nm_i, nid); + if (i && i->state == NID_NEW) { + __del_from_free_nid_list(nm_i, i); + nm_i->fcnt--; + need_free = true; + } + spin_unlock(&nm_i->free_nid_list_lock); + + if (need_free) + kmem_cache_free(free_nid_slab, i); +} + +static void scan_nat_page(struct f2fs_sb_info *sbi, + struct page *nat_page, nid_t start_nid) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct f2fs_nat_block *nat_blk = page_address(nat_page); + block_t blk_addr; + int i; + + i = start_nid % NAT_ENTRY_PER_BLOCK; + + for (; i < NAT_ENTRY_PER_BLOCK; i++, start_nid++) { + + if (unlikely(start_nid >= nm_i->max_nid)) + break; + + blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr); + f2fs_bug_on(sbi, blk_addr == NEW_ADDR); + if (blk_addr == NULL_ADDR) { + if (add_free_nid(sbi, start_nid, true) < 0) + break; + } + } +} + +static void build_free_nids(struct f2fs_sb_info *sbi) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); + struct f2fs_summary_block *sum = curseg->sum_blk; + int i = 0; + nid_t nid = nm_i->next_scan_nid; + + /* Enough entries */ + if (nm_i->fcnt > NAT_ENTRY_PER_BLOCK) + return; + + /* readahead nat pages to be scanned */ + ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT); + + while (1) { + struct page *page = get_current_nat_page(sbi, nid); + + scan_nat_page(sbi, page, nid); + f2fs_put_page(page, 1); + + nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK)); + if (unlikely(nid >= nm_i->max_nid)) + nid = 0; + + if (i++ == FREE_NID_PAGES) + break; + } + + /* go to the next free nat pages to find free nids abundantly */ + nm_i->next_scan_nid = nid; + + /* find free nids from current sum_pages */ + mutex_lock(&curseg->curseg_mutex); + for (i = 0; i < nats_in_cursum(sum); i++) { + block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr); + nid = le32_to_cpu(nid_in_journal(sum, i)); + if (addr == NULL_ADDR) + add_free_nid(sbi, nid, true); + else + remove_free_nid(nm_i, nid); + } + mutex_unlock(&curseg->curseg_mutex); +} + +/* + * If this function returns success, caller can obtain a new nid + * from second parameter of this function. + * The returned nid could be used ino as well as nid when inode is created. + */ +bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct free_nid *i = NULL; +retry: + if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids)) + return false; + + spin_lock(&nm_i->free_nid_list_lock); + + /* We should not use stale free nids created by build_free_nids */ + if (nm_i->fcnt && !on_build_free_nids(nm_i)) { + f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list)); + list_for_each_entry(i, &nm_i->free_nid_list, list) + if (i->state == NID_NEW) + break; + + f2fs_bug_on(sbi, i->state != NID_NEW); + *nid = i->nid; + i->state = NID_ALLOC; + nm_i->fcnt--; + spin_unlock(&nm_i->free_nid_list_lock); + return true; + } + spin_unlock(&nm_i->free_nid_list_lock); + + /* Let's scan nat pages and its caches to get free nids */ + mutex_lock(&nm_i->build_lock); + build_free_nids(sbi); + mutex_unlock(&nm_i->build_lock); + goto retry; +} + +/* + * alloc_nid() should be called prior to this function. + */ +void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct free_nid *i; + + spin_lock(&nm_i->free_nid_list_lock); + i = __lookup_free_nid_list(nm_i, nid); + f2fs_bug_on(sbi, !i || i->state != NID_ALLOC); + __del_from_free_nid_list(nm_i, i); + spin_unlock(&nm_i->free_nid_list_lock); + + kmem_cache_free(free_nid_slab, i); +} + +/* + * alloc_nid() should be called prior to this function. + */ +void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct free_nid *i; + bool need_free = false; + + if (!nid) + return; + + spin_lock(&nm_i->free_nid_list_lock); + i = __lookup_free_nid_list(nm_i, nid); + f2fs_bug_on(sbi, !i || i->state != NID_ALLOC); + if (!available_free_memory(sbi, FREE_NIDS)) { + __del_from_free_nid_list(nm_i, i); + need_free = true; + } else { + i->state = NID_NEW; + nm_i->fcnt++; + } + spin_unlock(&nm_i->free_nid_list_lock); + + if (need_free) + kmem_cache_free(free_nid_slab, i); +} + +void recover_inline_xattr(struct inode *inode, struct page *page) +{ + void *src_addr, *dst_addr; + size_t inline_size; + struct page *ipage; + struct f2fs_inode *ri; + + ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage)); + + ri = F2FS_INODE(page); + if (!(ri->i_inline & F2FS_INLINE_XATTR)) { + clear_inode_flag(F2FS_I(inode), FI_INLINE_XATTR); + goto update_inode; + } + + dst_addr = inline_xattr_addr(ipage); + src_addr = inline_xattr_addr(page); + inline_size = inline_xattr_size(inode); + + f2fs_wait_on_page_writeback(ipage, NODE); + memcpy(dst_addr, src_addr, inline_size); +update_inode: + update_inode(inode, ipage); + f2fs_put_page(ipage, 1); +} + +void recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid; + nid_t new_xnid = nid_of_node(page); + struct node_info ni; + + /* 1: invalidate the previous xattr nid */ + if (!prev_xnid) + goto recover_xnid; + + /* Deallocate node address */ + get_node_info(sbi, prev_xnid, &ni); + f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR); + invalidate_blocks(sbi, ni.blk_addr); + dec_valid_node_count(sbi, inode); + set_node_addr(sbi, &ni, NULL_ADDR, false); + +recover_xnid: + /* 2: allocate new xattr nid */ + if (unlikely(!inc_valid_node_count(sbi, inode))) + f2fs_bug_on(sbi, 1); + + remove_free_nid(NM_I(sbi), new_xnid); + get_node_info(sbi, new_xnid, &ni); + ni.ino = inode->i_ino; + set_node_addr(sbi, &ni, NEW_ADDR, false); + F2FS_I(inode)->i_xattr_nid = new_xnid; + + /* 3: update xattr blkaddr */ + refresh_sit_entry(sbi, NEW_ADDR, blkaddr); + set_node_addr(sbi, &ni, blkaddr, false); + + update_inode_page(inode); +} + +int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) +{ + struct f2fs_inode *src, *dst; + nid_t ino = ino_of_node(page); + struct node_info old_ni, new_ni; + struct page *ipage; + + get_node_info(sbi, ino, &old_ni); + + if (unlikely(old_ni.blk_addr != NULL_ADDR)) + return -EINVAL; + + ipage = grab_cache_page(NODE_MAPPING(sbi), ino); + if (!ipage) + return -ENOMEM; + + /* Should not use this inode from free nid list */ + remove_free_nid(NM_I(sbi), ino); + + SetPageUptodate(ipage); + fill_node_footer(ipage, ino, ino, 0, true); + + src = F2FS_INODE(page); + dst = F2FS_INODE(ipage); + + memcpy(dst, src, (unsigned long)&src->i_ext - (unsigned long)src); + dst->i_size = 0; + dst->i_blocks = cpu_to_le64(1); + dst->i_links = cpu_to_le32(1); + dst->i_xattr_nid = 0; + dst->i_inline = src->i_inline & F2FS_INLINE_XATTR; + + new_ni = old_ni; + new_ni.ino = ino; + + if (unlikely(!inc_valid_node_count(sbi, NULL))) + WARN_ON(1); + set_node_addr(sbi, &new_ni, NEW_ADDR, false); + inc_valid_inode_count(sbi); + set_page_dirty(ipage); + f2fs_put_page(ipage, 1); + return 0; +} + +int restore_node_summary(struct f2fs_sb_info *sbi, + unsigned int segno, struct f2fs_summary_block *sum) +{ + struct f2fs_node *rn; + struct f2fs_summary *sum_entry; + block_t addr; + int bio_blocks = MAX_BIO_BLOCKS(sbi); + int i, idx, last_offset, nrpages; + + /* scan the node segment */ + last_offset = sbi->blocks_per_seg; + addr = START_BLOCK(sbi, segno); + sum_entry = &sum->entries[0]; + + for (i = 0; i < last_offset; i += nrpages, addr += nrpages) { + nrpages = min(last_offset - i, bio_blocks); + + /* readahead node pages */ + ra_meta_pages(sbi, addr, nrpages, META_POR); + + for (idx = addr; idx < addr + nrpages; idx++) { + struct page *page = get_meta_page(sbi, idx); + + rn = F2FS_NODE(page); + sum_entry->nid = rn->footer.nid; + sum_entry->version = 0; + sum_entry->ofs_in_node = 0; + sum_entry++; + f2fs_put_page(page, 1); + } + + invalidate_mapping_pages(META_MAPPING(sbi), addr, + addr + nrpages); + } + return 0; +} + +static void remove_nats_in_journal(struct f2fs_sb_info *sbi) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); + struct f2fs_summary_block *sum = curseg->sum_blk; + int i; + + mutex_lock(&curseg->curseg_mutex); + for (i = 0; i < nats_in_cursum(sum); i++) { + struct nat_entry *ne; + struct f2fs_nat_entry raw_ne; + nid_t nid = le32_to_cpu(nid_in_journal(sum, i)); + + raw_ne = nat_in_journal(sum, i); + + down_write(&nm_i->nat_tree_lock); + ne = __lookup_nat_cache(nm_i, nid); + if (!ne) { + ne = grab_nat_entry(nm_i, nid); + node_info_from_raw_nat(&ne->ni, &raw_ne); + } + __set_nat_cache_dirty(nm_i, ne); + up_write(&nm_i->nat_tree_lock); + } + update_nats_in_cursum(sum, -i); + mutex_unlock(&curseg->curseg_mutex); +} + +static void __adjust_nat_entry_set(struct nat_entry_set *nes, + struct list_head *head, int max) +{ + struct nat_entry_set *cur; + + if (nes->entry_cnt >= max) + goto add_out; + + list_for_each_entry(cur, head, set_list) { + if (cur->entry_cnt >= nes->entry_cnt) { + list_add(&nes->set_list, cur->set_list.prev); + return; + } + } +add_out: + list_add_tail(&nes->set_list, head); +} + +static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, + struct nat_entry_set *set) +{ + struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); + struct f2fs_summary_block *sum = curseg->sum_blk; + nid_t start_nid = set->set * NAT_ENTRY_PER_BLOCK; + bool to_journal = true; + struct f2fs_nat_block *nat_blk; + struct nat_entry *ne, *cur; + struct page *page = NULL; + struct f2fs_nm_info *nm_i = NM_I(sbi); + + /* + * there are two steps to flush nat entries: + * #1, flush nat entries to journal in current hot data summary block. + * #2, flush nat entries to nat page. + */ + if (!__has_cursum_space(sum, set->entry_cnt, NAT_JOURNAL)) + to_journal = false; + + if (to_journal) { + mutex_lock(&curseg->curseg_mutex); + } else { + page = get_next_nat_page(sbi, start_nid); + nat_blk = page_address(page); + f2fs_bug_on(sbi, !nat_blk); + } + + /* flush dirty nats in nat entry set */ + list_for_each_entry_safe(ne, cur, &set->entry_list, list) { + struct f2fs_nat_entry *raw_ne; + nid_t nid = nat_get_nid(ne); + int offset; + + if (nat_get_blkaddr(ne) == NEW_ADDR) + continue; + + if (to_journal) { + offset = lookup_journal_in_cursum(sum, + NAT_JOURNAL, nid, 1); + f2fs_bug_on(sbi, offset < 0); + raw_ne = &nat_in_journal(sum, offset); + nid_in_journal(sum, offset) = cpu_to_le32(nid); + } else { + raw_ne = &nat_blk->entries[nid - start_nid]; + } + raw_nat_from_node_info(raw_ne, &ne->ni); + + down_write(&NM_I(sbi)->nat_tree_lock); + nat_reset_flag(ne); + __clear_nat_cache_dirty(NM_I(sbi), ne); + up_write(&NM_I(sbi)->nat_tree_lock); + + if (nat_get_blkaddr(ne) == NULL_ADDR) + add_free_nid(sbi, nid, false); + } + + if (to_journal) + mutex_unlock(&curseg->curseg_mutex); + else + f2fs_put_page(page, 1); + + f2fs_bug_on(sbi, set->entry_cnt); + + down_write(&nm_i->nat_tree_lock); + radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); + up_write(&nm_i->nat_tree_lock); + kmem_cache_free(nat_entry_set_slab, set); +} + +/* + * This function is called during the checkpointing process. + */ +void flush_nat_entries(struct f2fs_sb_info *sbi) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); + struct f2fs_summary_block *sum = curseg->sum_blk; + struct nat_entry_set *setvec[SETVEC_SIZE]; + struct nat_entry_set *set, *tmp; + unsigned int found; + nid_t set_idx = 0; + LIST_HEAD(sets); + + if (!nm_i->dirty_nat_cnt) + return; + /* + * if there are no enough space in journal to store dirty nat + * entries, remove all entries from journal and merge them + * into nat entry set. + */ + if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL)) + remove_nats_in_journal(sbi); + + down_write(&nm_i->nat_tree_lock); + while ((found = __gang_lookup_nat_set(nm_i, + set_idx, SETVEC_SIZE, setvec))) { + unsigned idx; + set_idx = setvec[found - 1]->set + 1; + for (idx = 0; idx < found; idx++) + __adjust_nat_entry_set(setvec[idx], &sets, + MAX_NAT_JENTRIES(sum)); + } + up_write(&nm_i->nat_tree_lock); + + /* flush dirty nats in nat entry set */ + list_for_each_entry_safe(set, tmp, &sets, set_list) + __flush_nat_entry_set(sbi, set); + + f2fs_bug_on(sbi, nm_i->dirty_nat_cnt); +} + +static int init_node_manager(struct f2fs_sb_info *sbi) +{ + struct f2fs_super_block *sb_raw = F2FS_RAW_SUPER(sbi); + struct f2fs_nm_info *nm_i = NM_I(sbi); + unsigned char *version_bitmap; + unsigned int nat_segs, nat_blocks; + + nm_i->nat_blkaddr = le32_to_cpu(sb_raw->nat_blkaddr); + + /* segment_count_nat includes pair segment so divide to 2. */ + nat_segs = le32_to_cpu(sb_raw->segment_count_nat) >> 1; + nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg); + + nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks; + + /* not used nids: 0, node, meta, (and root counted as valid node) */ + nm_i->available_nids = nm_i->max_nid - F2FS_RESERVED_NODE_NUM; + nm_i->fcnt = 0; + nm_i->nat_cnt = 0; + nm_i->ram_thresh = DEF_RAM_THRESHOLD; + + INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC); + INIT_LIST_HEAD(&nm_i->free_nid_list); + INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO); + INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO); + INIT_LIST_HEAD(&nm_i->nat_entries); + + mutex_init(&nm_i->build_lock); + spin_lock_init(&nm_i->free_nid_list_lock); + init_rwsem(&nm_i->nat_tree_lock); + + nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid); + nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP); + version_bitmap = __bitmap_ptr(sbi, NAT_BITMAP); + if (!version_bitmap) + return -EFAULT; + + nm_i->nat_bitmap = kmemdup(version_bitmap, nm_i->bitmap_size, + GFP_KERNEL); + if (!nm_i->nat_bitmap) + return -ENOMEM; + return 0; +} + +int build_node_manager(struct f2fs_sb_info *sbi) +{ + int err; + + sbi->nm_info = kzalloc(sizeof(struct f2fs_nm_info), GFP_KERNEL); + if (!sbi->nm_info) + return -ENOMEM; + + err = init_node_manager(sbi); + if (err) + return err; + + build_free_nids(sbi); + return 0; +} + +void destroy_node_manager(struct f2fs_sb_info *sbi) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct free_nid *i, *next_i; + struct nat_entry *natvec[NATVEC_SIZE]; + struct nat_entry_set *setvec[SETVEC_SIZE]; + nid_t nid = 0; + unsigned int found; + + if (!nm_i) + return; + + /* destroy free nid list */ + spin_lock(&nm_i->free_nid_list_lock); + list_for_each_entry_safe(i, next_i, &nm_i->free_nid_list, list) { + f2fs_bug_on(sbi, i->state == NID_ALLOC); + __del_from_free_nid_list(nm_i, i); + nm_i->fcnt--; + spin_unlock(&nm_i->free_nid_list_lock); + kmem_cache_free(free_nid_slab, i); + spin_lock(&nm_i->free_nid_list_lock); + } + f2fs_bug_on(sbi, nm_i->fcnt); + spin_unlock(&nm_i->free_nid_list_lock); + + /* destroy nat cache */ + down_write(&nm_i->nat_tree_lock); + while ((found = __gang_lookup_nat_cache(nm_i, + nid, NATVEC_SIZE, natvec))) { + unsigned idx; + + nid = nat_get_nid(natvec[found - 1]) + 1; + for (idx = 0; idx < found; idx++) + __del_from_nat_cache(nm_i, natvec[idx]); + } + f2fs_bug_on(sbi, nm_i->nat_cnt); + + /* destroy nat set cache */ + nid = 0; + while ((found = __gang_lookup_nat_set(nm_i, + nid, SETVEC_SIZE, setvec))) { + unsigned idx; + + nid = setvec[found - 1]->set + 1; + for (idx = 0; idx < found; idx++) { + /* entry_cnt is not zero, when cp_error was occurred */ + f2fs_bug_on(sbi, !list_empty(&setvec[idx]->entry_list)); + radix_tree_delete(&nm_i->nat_set_root, setvec[idx]->set); + kmem_cache_free(nat_entry_set_slab, setvec[idx]); + } + } + up_write(&nm_i->nat_tree_lock); + + kfree(nm_i->nat_bitmap); + sbi->nm_info = NULL; + kfree(nm_i); +} + +int __init create_node_manager_caches(void) +{ + nat_entry_slab = f2fs_kmem_cache_create("nat_entry", + sizeof(struct nat_entry)); + if (!nat_entry_slab) + goto fail; + + free_nid_slab = f2fs_kmem_cache_create("free_nid", + sizeof(struct free_nid)); + if (!free_nid_slab) + goto destroy_nat_entry; + + nat_entry_set_slab = f2fs_kmem_cache_create("nat_entry_set", + sizeof(struct nat_entry_set)); + if (!nat_entry_set_slab) + goto destroy_free_nid; + return 0; + +destroy_free_nid: + kmem_cache_destroy(free_nid_slab); +destroy_nat_entry: + kmem_cache_destroy(nat_entry_slab); +fail: + return -ENOMEM; +} + +void destroy_node_manager_caches(void) +{ + kmem_cache_destroy(nat_entry_set_slab); + kmem_cache_destroy(free_nid_slab); + kmem_cache_destroy(nat_entry_slab); +} diff --git a/kernel/fs/f2fs/node.h b/kernel/fs/f2fs/node.h new file mode 100644 index 000000000..c56026f17 --- /dev/null +++ b/kernel/fs/f2fs/node.h @@ -0,0 +1,416 @@ +/* + * 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 readahead size for node during getting data blocks */ +#define MAX_RA_NODE 128 + +/* control the memory footprint threshold (10MB per 1GB ram) */ +#define DEF_RAM_THRESHOLD 10 + +/* vector size for gang look-up from nat cache that consists of radix tree */ +#define NATVEC_SIZE 64 +#define SETVEC_SIZE 32 + +/* return value for read_node_page */ +#define LOCKED_PAGE 1 + +/* For flag in struct node_info */ +enum { + IS_CHECKPOINTED, /* is it checkpointed before? */ + HAS_FSYNCED_INODE, /* is the inode fsynced before? */ + HAS_LAST_FSYNC, /* has the latest node fsync mark? */ + IS_DIRTY, /* this nat entry is dirty? */ +}; + +/* + * For node information + */ +struct node_info { + nid_t nid; /* node id */ + nid_t ino; /* inode number of the node's owner */ + block_t blk_addr; /* block address of the node */ + unsigned char version; /* version of the node */ + unsigned char flag; /* for node information bits */ +}; + +struct nat_entry { + struct list_head list; /* for clean or dirty nat list */ + struct node_info ni; /* in-memory node information */ +}; + +#define nat_get_nid(nat) (nat->ni.nid) +#define nat_set_nid(nat, n) (nat->ni.nid = n) +#define nat_get_blkaddr(nat) (nat->ni.blk_addr) +#define nat_set_blkaddr(nat, b) (nat->ni.blk_addr = b) +#define nat_get_ino(nat) (nat->ni.ino) +#define nat_set_ino(nat, i) (nat->ni.ino = i) +#define nat_get_version(nat) (nat->ni.version) +#define nat_set_version(nat, v) (nat->ni.version = v) + +#define inc_node_version(version) (++version) + +static inline void copy_node_info(struct node_info *dst, + struct node_info *src) +{ + dst->nid = src->nid; + dst->ino = src->ino; + dst->blk_addr = src->blk_addr; + dst->version = src->version; + /* should not copy flag here */ +} + +static inline void set_nat_flag(struct nat_entry *ne, + unsigned int type, bool set) +{ + unsigned char mask = 0x01 << type; + if (set) + ne->ni.flag |= mask; + else + ne->ni.flag &= ~mask; +} + +static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type) +{ + unsigned char mask = 0x01 << type; + return ne->ni.flag & mask; +} + +static inline void nat_reset_flag(struct nat_entry *ne) +{ + /* these states can be set only after checkpoint was done */ + set_nat_flag(ne, IS_CHECKPOINTED, true); + set_nat_flag(ne, HAS_FSYNCED_INODE, false); + set_nat_flag(ne, HAS_LAST_FSYNC, true); +} + +static inline void node_info_from_raw_nat(struct node_info *ni, + struct f2fs_nat_entry *raw_ne) +{ + ni->ino = le32_to_cpu(raw_ne->ino); + ni->blk_addr = le32_to_cpu(raw_ne->block_addr); + ni->version = raw_ne->version; +} + +static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne, + struct node_info *ni) +{ + raw_ne->ino = cpu_to_le32(ni->ino); + raw_ne->block_addr = cpu_to_le32(ni->blk_addr); + raw_ne->version = ni->version; +} + +enum mem_type { + FREE_NIDS, /* indicates the free nid list */ + NAT_ENTRIES, /* indicates the cached nat entry */ + DIRTY_DENTS, /* indicates dirty dentry pages */ + INO_ENTRIES, /* indicates inode entries */ + EXTENT_CACHE, /* indicates extent cache */ + BASE_CHECK, /* check kernel status */ +}; + +struct nat_entry_set { + struct list_head set_list; /* link with other nat sets */ + struct list_head entry_list; /* link with dirty nat entries */ + nid_t set; /* set number*/ + unsigned int entry_cnt; /* the # of nat entries in set */ +}; + +/* + * 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 void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct free_nid *fnid; + + spin_lock(&nm_i->free_nid_list_lock); + if (nm_i->fcnt <= 0) { + spin_unlock(&nm_i->free_nid_list_lock); + return; + } + fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list); + *nid = fnid->nid; + spin_unlock(&nm_i->free_nid_list_lock); +} + +/* + * inline functions + */ +static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + 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); + + f2fs_change_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) +{ + struct f2fs_node *rn = F2FS_NODE(page); + unsigned int old_flag = 0; + + if (reset) + memset(rn, 0, sizeof(*rn)); + else + old_flag = le32_to_cpu(rn->footer.flag); + + rn->footer.nid = cpu_to_le32(nid); + rn->footer.ino = cpu_to_le32(ino); + + /* should remain old flag bits such as COLD_BIT_SHIFT */ + rn->footer.flag = cpu_to_le32((ofs << OFFSET_BIT_SHIFT) | + (old_flag & OFFSET_BIT_MASK)); +} + +static inline void copy_node_footer(struct page *dst, struct page *src) +{ + struct f2fs_node *src_rn = F2FS_NODE(src); + struct f2fs_node *dst_rn = F2FS_NODE(dst); + memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer)); +} + +static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page)); + struct f2fs_node *rn = F2FS_NODE(page); + + 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) +{ + struct f2fs_node *rn = F2FS_NODE(node_page); + return le32_to_cpu(rn->footer.ino); +} + +static inline nid_t nid_of_node(struct page *node_page) +{ + struct f2fs_node *rn = F2FS_NODE(node_page); + return le32_to_cpu(rn->footer.nid); +} + +static inline unsigned int ofs_of_node(struct page *node_page) +{ + struct f2fs_node *rn = F2FS_NODE(node_page); + 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) +{ + struct f2fs_node *rn = F2FS_NODE(node_page); + return le64_to_cpu(rn->footer.cp_ver); +} + +static inline block_t next_blkaddr_of_node(struct page *node_page) +{ + struct f2fs_node *rn = F2FS_NODE(node_page); + 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 + * ...... + * `- indirect node ((6 + 2N) + x(N + 1)) + * `- direct node + * ...... + * `- indirect node ((6 + 2N) + (N - 1)(N + 1)) + * `- direct node + */ +static inline bool IS_DNODE(struct page *node_page) +{ + unsigned int ofs = ofs_of_node(node_page); + + if (f2fs_has_xattr_block(ofs)) + return false; + + 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 = F2FS_NODE(p); + + f2fs_wait_on_page_writeback(p, NODE); + + 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 = F2FS_NODE(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_file(struct inode *inode, int type) +{ + return F2FS_I(inode)->i_advise & type; +} + +static inline void set_file(struct inode *inode, int type) +{ + F2FS_I(inode)->i_advise |= type; +} + +static inline void clear_file(struct inode *inode, int type) +{ + F2FS_I(inode)->i_advise &= ~type; +} + +#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT) +#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT) +#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT) +#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT) +#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT) +#define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_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_node(struct page *page, int type) +{ + struct f2fs_node *rn = F2FS_NODE(page); + return le32_to_cpu(rn->footer.flag) & (1 << type); +} + +#define is_cold_node(page) is_node(page, COLD_BIT_SHIFT) +#define is_fsync_dnode(page) is_node(page, FSYNC_BIT_SHIFT) +#define is_dent_dnode(page) is_node(page, DENT_BIT_SHIFT) + +static inline void set_cold_node(struct inode *inode, struct page *page) +{ + struct f2fs_node *rn = F2FS_NODE(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_mark(struct page *page, int mark, int type) +{ + struct f2fs_node *rn = F2FS_NODE(page); + unsigned int flag = le32_to_cpu(rn->footer.flag); + if (mark) + flag |= (0x1 << type); + else + flag &= ~(0x1 << type); + rn->footer.flag = cpu_to_le32(flag); +} +#define set_dentry_mark(page, mark) set_mark(page, mark, DENT_BIT_SHIFT) +#define set_fsync_mark(page, mark) set_mark(page, mark, FSYNC_BIT_SHIFT) diff --git a/kernel/fs/f2fs/recovery.c b/kernel/fs/f2fs/recovery.c new file mode 100644 index 000000000..8d8ea99f2 --- /dev/null +++ b/kernel/fs/f2fs/recovery.c @@ -0,0 +1,575 @@ +/* + * 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" + +/* + * Roll forward recovery scenarios. + * + * [Term] F: fsync_mark, D: dentry_mark + * + * 1. inode(x) | CP | inode(x) | dnode(F) + * -> Update the latest inode(x). + * + * 2. inode(x) | CP | inode(F) | dnode(F) + * -> No problem. + * + * 3. inode(x) | CP | dnode(F) | inode(x) + * -> Recover to the latest dnode(F), and drop the last inode(x) + * + * 4. inode(x) | CP | dnode(F) | inode(F) + * -> No problem. + * + * 5. CP | inode(x) | dnode(F) + * -> The inode(DF) was missing. Should drop this dnode(F). + * + * 6. CP | inode(DF) | dnode(F) + * -> No problem. + * + * 7. CP | dnode(F) | inode(DF) + * -> If f2fs_iget fails, then goto next to find inode(DF). + * + * 8. CP | dnode(F) | inode(x) + * -> If f2fs_iget fails, then goto next to find inode(DF). + * But it will fail due to no inode(DF). + */ + +static struct kmem_cache *fsync_entry_slab; + +bool 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 fsync_inode_entry *entry; + + list_for_each_entry(entry, head, list) + if (entry->inode->i_ino == ino) + return entry; + + return NULL; +} + +static int recover_dentry(struct inode *inode, struct page *ipage) +{ + struct f2fs_inode *raw_inode = F2FS_INODE(ipage); + nid_t pino = le32_to_cpu(raw_inode->i_pino); + struct f2fs_dir_entry *de; + struct qstr name; + struct page *page; + struct inode *dir, *einode; + int err = 0; + + dir = f2fs_iget(inode->i_sb, 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; + + if (unlikely(name.len > F2FS_NAME_LEN)) { + WARN_ON(1); + err = -ENAMETOOLONG; + goto out_err; + } +retry: + de = f2fs_find_entry(dir, &name, &page); + if (de && inode->i_ino == le32_to_cpu(de->ino)) + goto out_unmap_put; + + if (de) { + einode = f2fs_iget(inode->i_sb, le32_to_cpu(de->ino)); + if (IS_ERR(einode)) { + WARN_ON(1); + err = PTR_ERR(einode); + if (err == -ENOENT) + err = -EEXIST; + goto out_unmap_put; + } + err = acquire_orphan_inode(F2FS_I_SB(inode)); + if (err) { + iput(einode); + goto out_unmap_put; + } + f2fs_delete_entry(de, page, dir, einode); + iput(einode); + goto retry; + } + err = __f2fs_add_link(dir, &name, inode, inode->i_ino, inode->i_mode); + if (err) + goto out_err; + + if (is_inode_flag_set(F2FS_I(dir), FI_DELAY_IPUT)) { + iput(dir); + } else { + add_dirty_dir_inode(dir); + set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT); + } + + goto out; + +out_unmap_put: + f2fs_dentry_kunmap(dir, page); + f2fs_put_page(page, 0); +out_err: + iput(dir); +out: + f2fs_msg(inode->i_sb, KERN_NOTICE, + "%s: ino = %x, name = %s, dir = %lx, err = %d", + __func__, ino_of_node(ipage), raw_inode->i_name, + IS_ERR(dir) ? 0 : dir->i_ino, err); + return err; +} + +static void recover_inode(struct inode *inode, struct page *page) +{ + struct f2fs_inode *raw = F2FS_INODE(page); + + inode->i_mode = le16_to_cpu(raw->i_mode); + i_size_write(inode, le64_to_cpu(raw->i_size)); + inode->i_atime.tv_sec = le64_to_cpu(raw->i_mtime); + inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime); + inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime); + inode->i_atime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec); + inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec); + inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec); + + f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s", + ino_of_node(page), F2FS_INODE(page)->i_name); +} + +static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) +{ + unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi)); + struct curseg_info *curseg; + struct page *page = NULL; + block_t blkaddr; + int err = 0; + + /* get node pages in the current segment */ + curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); + blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); + + ra_meta_pages(sbi, blkaddr, 1, META_POR); + + while (1) { + struct fsync_inode_entry *entry; + + if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi)) + return 0; + + page = get_meta_page(sbi, blkaddr); + + if (cp_ver != cpver_of_node(page)) + break; + + if (!is_fsync_dnode(page)) + goto next; + + entry = get_fsync_inode(head, ino_of_node(page)); + if (!entry) { + if (IS_INODE(page) && is_dent_dnode(page)) { + err = recover_inode_page(sbi, page); + if (err) + break; + } + + /* add this fsync inode to the list */ + entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO); + if (!entry) { + err = -ENOMEM; + break; + } + /* + * CP | dnode(F) | inode(DF) + * For this case, we should not give up now. + */ + 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); + if (err == -ENOENT) { + err = 0; + goto next; + } + break; + } + list_add_tail(&entry->list, head); + } + entry->blkaddr = blkaddr; + + if (IS_INODE(page)) { + entry->last_inode = blkaddr; + if (is_dent_dnode(page)) + entry->last_dentry = blkaddr; + } +next: + /* check next segment */ + blkaddr = next_blkaddr_of_node(page); + f2fs_put_page(page, 1); + + ra_meta_pages_cond(sbi, blkaddr); + } + f2fs_put_page(page, 1); + return err; +} + +static void destroy_fsync_dnodes(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 int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, + block_t blkaddr, struct dnode_of_data *dn) +{ + struct seg_entry *sentry; + unsigned int segno = GET_SEGNO(sbi, blkaddr); + unsigned short blkoff = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); + struct f2fs_summary_block *sum_node; + struct f2fs_summary sum; + struct page *sum_page, *node_page; + struct dnode_of_data tdn = *dn; + nid_t ino, nid; + struct inode *inode; + unsigned int offset; + block_t bidx; + int i; + + sentry = get_seg_entry(sbi, segno); + if (!f2fs_test_bit(blkoff, sentry->cur_valid_map)) + return 0; + + /* Get the previous summary */ + for (i = CURSEG_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]; + goto got_it; + } + } + + sum_page = get_sum_page(sbi, segno); + sum_node = (struct f2fs_summary_block *)page_address(sum_page); + sum = sum_node->entries[blkoff]; + f2fs_put_page(sum_page, 1); +got_it: + /* Use the locked dnode page and inode */ + nid = le32_to_cpu(sum.nid); + if (dn->inode->i_ino == nid) { + tdn.nid = nid; + if (!dn->inode_page_locked) + lock_page(dn->inode_page); + tdn.node_page = dn->inode_page; + tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node); + goto truncate_out; + } else if (dn->nid == nid) { + tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node); + goto truncate_out; + } + + /* Get the node page */ + node_page = get_node_page(sbi, nid); + if (IS_ERR(node_page)) + return PTR_ERR(node_page); + + offset = ofs_of_node(node_page); + ino = ino_of_node(node_page); + f2fs_put_page(node_page, 1); + + if (ino != dn->inode->i_ino) { + /* Deallocate previous index in the node page */ + inode = f2fs_iget(sbi->sb, ino); + if (IS_ERR(inode)) + return PTR_ERR(inode); + } else { + inode = dn->inode; + } + + bidx = start_bidx_of_node(offset, F2FS_I(inode)) + + le16_to_cpu(sum.ofs_in_node); + + /* + * if inode page is locked, unlock temporarily, but its reference + * count keeps alive. + */ + if (ino == dn->inode->i_ino && dn->inode_page_locked) + unlock_page(dn->inode_page); + + set_new_dnode(&tdn, inode, NULL, NULL, 0); + if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE)) + goto out; + + if (tdn.data_blkaddr == blkaddr) + truncate_data_blocks_range(&tdn, 1); + + f2fs_put_dnode(&tdn); +out: + if (ino != dn->inode->i_ino) + iput(inode); + else if (dn->inode_page_locked) + lock_page(dn->inode_page); + return 0; + +truncate_out: + if (datablock_addr(tdn.node_page, tdn.ofs_in_node) == blkaddr) + truncate_data_blocks_range(&tdn, 1); + if (dn->inode->i_ino == nid && !dn->inode_page_locked) + unlock_page(dn->inode_page); + return 0; +} + +static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, + struct page *page, block_t blkaddr) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + unsigned int start, end; + struct dnode_of_data dn; + struct f2fs_summary sum; + struct node_info ni; + int err = 0, recovered = 0; + + /* step 1: recover xattr */ + if (IS_INODE(page)) { + recover_inline_xattr(inode, page); + } else if (f2fs_has_xattr_block(ofs_of_node(page))) { + /* + * Deprecated; xattr blocks should be found from cold log. + * But, we should remain this for backward compatibility. + */ + recover_xattr_data(inode, page, blkaddr); + goto out; + } + + /* step 2: recover inline data */ + if (recover_inline_data(inode, page)) + goto out; + + /* step 3: recover data indices */ + start = start_bidx_of_node(ofs_of_node(page), fi); + end = start + ADDRS_PER_PAGE(page, fi); + + f2fs_lock_op(sbi); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + + err = get_dnode_of_data(&dn, start, ALLOC_NODE); + if (err) { + f2fs_unlock_op(sbi); + goto out; + } + + f2fs_wait_on_page_writeback(dn.node_page, NODE); + + get_node_info(sbi, dn.nid, &ni); + f2fs_bug_on(sbi, ni.ino != ino_of_node(page)); + f2fs_bug_on(sbi, 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 && + dest >= MAIN_BLKADDR(sbi) && dest < MAX_BLKADDR(sbi)) { + + if (src == NULL_ADDR) { + err = reserve_new_block(&dn); + /* We should not get -ENOSPC */ + f2fs_bug_on(sbi, err); + } + + /* Check the previous node page having this index */ + err = check_index_in_prev_nodes(sbi, dest, &dn); + if (err) + goto err; + + set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); + + /* write dummy data page */ + recover_data_page(sbi, NULL, &sum, src, dest); + dn.data_blkaddr = dest; + set_data_blkaddr(&dn); + f2fs_update_extent_cache(&dn); + recovered++; + } + dn.ofs_in_node++; + } + + 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); +err: + f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); +out: + f2fs_msg(sbi->sb, KERN_NOTICE, + "recover_data: ino = %lx, recovered = %d blocks, err = %d", + inode->i_ino, recovered, err); + return err; +} + +static int recover_data(struct f2fs_sb_info *sbi, + struct list_head *head, int type) +{ + unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi)); + struct curseg_info *curseg; + struct page *page = NULL; + int err = 0; + block_t blkaddr; + + /* get node pages in the current segment */ + curseg = CURSEG_I(sbi, type); + blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); + + while (1) { + struct fsync_inode_entry *entry; + + if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi)) + break; + + ra_meta_pages_cond(sbi, blkaddr); + + page = get_meta_page(sbi, blkaddr); + + if (cp_ver != cpver_of_node(page)) { + f2fs_put_page(page, 1); + break; + } + + entry = get_fsync_inode(head, ino_of_node(page)); + if (!entry) + goto next; + /* + * inode(x) | CP | inode(x) | dnode(F) + * In this case, we can lose the latest inode(x). + * So, call recover_inode for the inode update. + */ + if (entry->last_inode == blkaddr) + recover_inode(entry->inode, page); + if (entry->last_dentry == blkaddr) { + err = recover_dentry(entry->inode, page); + if (err) { + f2fs_put_page(page, 1); + break; + } + } + err = do_recover_data(sbi, entry->inode, page, blkaddr); + if (err) { + f2fs_put_page(page, 1); + break; + } + + 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); + f2fs_put_page(page, 1); + } + if (!err) + allocate_new_segments(sbi); + return err; +} + +int recover_fsync_data(struct f2fs_sb_info *sbi) +{ + struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); + struct list_head inode_list; + block_t blkaddr; + int err; + bool need_writecp = false; + + fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry", + sizeof(struct fsync_inode_entry)); + if (!fsync_entry_slab) + return -ENOMEM; + + INIT_LIST_HEAD(&inode_list); + + /* step #1: find fsynced inode numbers */ + set_sbi_flag(sbi, SBI_POR_DOING); + + /* prevent checkpoint */ + mutex_lock(&sbi->cp_mutex); + + blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); + + err = find_fsync_dnodes(sbi, &inode_list); + if (err) + goto out; + + if (list_empty(&inode_list)) + goto out; + + need_writecp = true; + + /* step #2: recover data */ + err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE); + if (!err) + f2fs_bug_on(sbi, !list_empty(&inode_list)); +out: + destroy_fsync_dnodes(&inode_list); + kmem_cache_destroy(fsync_entry_slab); + + /* truncate meta pages to be used by the recovery */ + truncate_inode_pages_range(META_MAPPING(sbi), + MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1); + + if (err) { + truncate_inode_pages_final(NODE_MAPPING(sbi)); + truncate_inode_pages_final(META_MAPPING(sbi)); + } + + clear_sbi_flag(sbi, SBI_POR_DOING); + if (err) { + discard_next_dnode(sbi, blkaddr); + + /* Flush all the NAT/SIT pages */ + while (get_pages(sbi, F2FS_DIRTY_META)) + sync_meta_pages(sbi, META, LONG_MAX); + set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG); + mutex_unlock(&sbi->cp_mutex); + } else if (need_writecp) { + struct cp_control cpc = { + .reason = CP_RECOVERY, + }; + mutex_unlock(&sbi->cp_mutex); + write_checkpoint(sbi, &cpc); + } else { + mutex_unlock(&sbi->cp_mutex); + } + return err; +} diff --git a/kernel/fs/f2fs/segment.c b/kernel/fs/f2fs/segment.c new file mode 100644 index 000000000..f93966094 --- /dev/null +++ b/kernel/fs/f2fs/segment.c @@ -0,0 +1,2307 @@ +/* + * fs/f2fs/segment.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/bio.h> +#include <linux/blkdev.h> +#include <linux/prefetch.h> +#include <linux/kthread.h> +#include <linux/vmalloc.h> +#include <linux/swap.h> + +#include "f2fs.h" +#include "segment.h" +#include "node.h" +#include "trace.h" +#include <trace/events/f2fs.h> + +#define __reverse_ffz(x) __reverse_ffs(~(x)) + +static struct kmem_cache *discard_entry_slab; +static struct kmem_cache *sit_entry_set_slab; +static struct kmem_cache *inmem_entry_slab; + +/* + * __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since + * MSB and LSB are reversed in a byte by f2fs_set_bit. + */ +static inline unsigned long __reverse_ffs(unsigned long word) +{ + int num = 0; + +#if BITS_PER_LONG == 64 + if ((word & 0xffffffff) == 0) { + num += 32; + word >>= 32; + } +#endif + if ((word & 0xffff) == 0) { + num += 16; + word >>= 16; + } + if ((word & 0xff) == 0) { + num += 8; + word >>= 8; + } + if ((word & 0xf0) == 0) + num += 4; + else + word >>= 4; + if ((word & 0xc) == 0) + num += 2; + else + word >>= 2; + if ((word & 0x2) == 0) + num += 1; + return num; +} + +/* + * __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because + * f2fs_set_bit makes MSB and LSB reversed in a byte. + * Example: + * LSB <--> MSB + * f2fs_set_bit(0, bitmap) => 0000 0001 + * f2fs_set_bit(7, bitmap) => 1000 0000 + */ +static unsigned long __find_rev_next_bit(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + const unsigned long *p = addr + BIT_WORD(offset); + unsigned long result = offset & ~(BITS_PER_LONG - 1); + unsigned long tmp; + unsigned long mask, submask; + unsigned long quot, rest; + + if (offset >= size) + return size; + + size -= result; + offset %= BITS_PER_LONG; + if (!offset) + goto aligned; + + tmp = *(p++); + quot = (offset >> 3) << 3; + rest = offset & 0x7; + mask = ~0UL << quot; + submask = (unsigned char)(0xff << rest) >> rest; + submask <<= quot; + mask &= submask; + tmp &= mask; + if (size < BITS_PER_LONG) + goto found_first; + if (tmp) + goto found_middle; + + size -= BITS_PER_LONG; + result += BITS_PER_LONG; +aligned: + while (size & ~(BITS_PER_LONG-1)) { + tmp = *(p++); + if (tmp) + goto found_middle; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + tmp = *p; +found_first: + tmp &= (~0UL >> (BITS_PER_LONG - size)); + if (tmp == 0UL) /* Are any bits set? */ + return result + size; /* Nope. */ +found_middle: + return result + __reverse_ffs(tmp); +} + +static unsigned long __find_rev_next_zero_bit(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + const unsigned long *p = addr + BIT_WORD(offset); + unsigned long result = offset & ~(BITS_PER_LONG - 1); + unsigned long tmp; + unsigned long mask, submask; + unsigned long quot, rest; + + if (offset >= size) + return size; + + size -= result; + offset %= BITS_PER_LONG; + if (!offset) + goto aligned; + + tmp = *(p++); + quot = (offset >> 3) << 3; + rest = offset & 0x7; + mask = ~(~0UL << quot); + submask = (unsigned char)~((unsigned char)(0xff << rest) >> rest); + submask <<= quot; + mask += submask; + tmp |= mask; + if (size < BITS_PER_LONG) + goto found_first; + if (~tmp) + goto found_middle; + + size -= BITS_PER_LONG; + result += BITS_PER_LONG; +aligned: + while (size & ~(BITS_PER_LONG - 1)) { + tmp = *(p++); + if (~tmp) + goto found_middle; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + tmp = *p; + +found_first: + tmp |= ~0UL << size; + if (tmp == ~0UL) /* Are any bits zero? */ + return result + size; /* Nope. */ +found_middle: + return result + __reverse_ffz(tmp); +} + +void register_inmem_page(struct inode *inode, struct page *page) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct inmem_pages *new; + int err; + + SetPagePrivate(page); + f2fs_trace_pid(page); + + new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS); + + /* add atomic page indices to the list */ + new->page = page; + INIT_LIST_HEAD(&new->list); +retry: + /* increase reference count with clean state */ + mutex_lock(&fi->inmem_lock); + err = radix_tree_insert(&fi->inmem_root, page->index, new); + if (err == -EEXIST) { + mutex_unlock(&fi->inmem_lock); + kmem_cache_free(inmem_entry_slab, new); + return; + } else if (err) { + mutex_unlock(&fi->inmem_lock); + goto retry; + } + get_page(page); + list_add_tail(&new->list, &fi->inmem_pages); + inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); + mutex_unlock(&fi->inmem_lock); + + trace_f2fs_register_inmem_page(page, INMEM); +} + +void commit_inmem_pages(struct inode *inode, bool abort) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct inmem_pages *cur, *tmp; + bool submit_bio = false; + struct f2fs_io_info fio = { + .type = DATA, + .rw = WRITE_SYNC | REQ_PRIO, + }; + + /* + * The abort is true only when f2fs_evict_inode is called. + * Basically, the f2fs_evict_inode doesn't produce any data writes, so + * that we don't need to call f2fs_balance_fs. + * Otherwise, f2fs_gc in f2fs_balance_fs can wait forever until this + * inode becomes free by iget_locked in f2fs_iget. + */ + if (!abort) { + f2fs_balance_fs(sbi); + f2fs_lock_op(sbi); + } + + mutex_lock(&fi->inmem_lock); + list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) { + if (!abort) { + lock_page(cur->page); + if (cur->page->mapping == inode->i_mapping) { + f2fs_wait_on_page_writeback(cur->page, DATA); + if (clear_page_dirty_for_io(cur->page)) + inode_dec_dirty_pages(inode); + trace_f2fs_commit_inmem_page(cur->page, INMEM); + do_write_data_page(cur->page, &fio); + submit_bio = true; + } + f2fs_put_page(cur->page, 1); + } else { + trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP); + put_page(cur->page); + } + radix_tree_delete(&fi->inmem_root, cur->page->index); + list_del(&cur->list); + kmem_cache_free(inmem_entry_slab, cur); + dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); + } + mutex_unlock(&fi->inmem_lock); + + if (!abort) { + f2fs_unlock_op(sbi); + if (submit_bio) + f2fs_submit_merged_bio(sbi, DATA, WRITE); + } +} + +/* + * This function balances dirty node and dentry pages. + * In addition, it controls garbage collection. + */ +void f2fs_balance_fs(struct f2fs_sb_info *sbi) +{ + /* + * We should do GC or end up with checkpoint, if there are so many dirty + * dir/node pages without enough free segments. + */ + if (has_not_enough_free_secs(sbi, 0)) { + mutex_lock(&sbi->gc_mutex); + f2fs_gc(sbi); + } +} + +void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) +{ + /* try to shrink extent cache when there is no enough memory */ + f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER); + + /* check the # of cached NAT entries and prefree segments */ + if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) || + excess_prefree_segs(sbi) || + !available_free_memory(sbi, INO_ENTRIES)) + f2fs_sync_fs(sbi->sb, true); +} + +static int issue_flush_thread(void *data) +{ + struct f2fs_sb_info *sbi = data; + struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info; + wait_queue_head_t *q = &fcc->flush_wait_queue; +repeat: + if (kthread_should_stop()) + return 0; + + if (!llist_empty(&fcc->issue_list)) { + struct bio *bio = bio_alloc(GFP_NOIO, 0); + struct flush_cmd *cmd, *next; + int ret; + + fcc->dispatch_list = llist_del_all(&fcc->issue_list); + fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list); + + bio->bi_bdev = sbi->sb->s_bdev; + ret = submit_bio_wait(WRITE_FLUSH, bio); + + llist_for_each_entry_safe(cmd, next, + fcc->dispatch_list, llnode) { + cmd->ret = ret; + complete(&cmd->wait); + } + bio_put(bio); + fcc->dispatch_list = NULL; + } + + wait_event_interruptible(*q, + kthread_should_stop() || !llist_empty(&fcc->issue_list)); + goto repeat; +} + +int f2fs_issue_flush(struct f2fs_sb_info *sbi) +{ + struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info; + struct flush_cmd cmd; + + trace_f2fs_issue_flush(sbi->sb, test_opt(sbi, NOBARRIER), + test_opt(sbi, FLUSH_MERGE)); + + if (test_opt(sbi, NOBARRIER)) + return 0; + + if (!test_opt(sbi, FLUSH_MERGE)) + return blkdev_issue_flush(sbi->sb->s_bdev, GFP_KERNEL, NULL); + + init_completion(&cmd.wait); + + llist_add(&cmd.llnode, &fcc->issue_list); + + if (!fcc->dispatch_list) + wake_up(&fcc->flush_wait_queue); + + wait_for_completion(&cmd.wait); + + return cmd.ret; +} + +int create_flush_cmd_control(struct f2fs_sb_info *sbi) +{ + dev_t dev = sbi->sb->s_bdev->bd_dev; + struct flush_cmd_control *fcc; + int err = 0; + + fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL); + if (!fcc) + return -ENOMEM; + init_waitqueue_head(&fcc->flush_wait_queue); + init_llist_head(&fcc->issue_list); + SM_I(sbi)->cmd_control_info = fcc; + fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi, + "f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev)); + if (IS_ERR(fcc->f2fs_issue_flush)) { + err = PTR_ERR(fcc->f2fs_issue_flush); + kfree(fcc); + SM_I(sbi)->cmd_control_info = NULL; + return err; + } + + return err; +} + +void destroy_flush_cmd_control(struct f2fs_sb_info *sbi) +{ + struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info; + + if (fcc && fcc->f2fs_issue_flush) + kthread_stop(fcc->f2fs_issue_flush); + kfree(fcc); + SM_I(sbi)->cmd_control_info = NULL; +} + +static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, + enum dirty_type dirty_type) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + + /* need not be added */ + if (IS_CURSEG(sbi, segno)) + return; + + if (!test_and_set_bit(segno, dirty_i->dirty_segmap[dirty_type])) + dirty_i->nr_dirty[dirty_type]++; + + if (dirty_type == DIRTY) { + struct seg_entry *sentry = get_seg_entry(sbi, segno); + enum dirty_type t = sentry->type; + + if (unlikely(t >= DIRTY)) { + f2fs_bug_on(sbi, 1); + return; + } + if (!test_and_set_bit(segno, dirty_i->dirty_segmap[t])) + dirty_i->nr_dirty[t]++; + } +} + +static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, + enum dirty_type dirty_type) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + + if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type])) + dirty_i->nr_dirty[dirty_type]--; + + if (dirty_type == DIRTY) { + struct seg_entry *sentry = get_seg_entry(sbi, segno); + enum dirty_type t = sentry->type; + + if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t])) + dirty_i->nr_dirty[t]--; + + if (get_valid_blocks(sbi, segno, sbi->segs_per_sec) == 0) + clear_bit(GET_SECNO(sbi, segno), + dirty_i->victim_secmap); + } +} + +/* + * Should not occur error such as -ENOMEM. + * Adding dirty entry into seglist is not critical operation. + * If a given segment is one of current working segments, it won't be added. + */ +static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned short valid_blocks; + + if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno)) + return; + + mutex_lock(&dirty_i->seglist_lock); + + valid_blocks = get_valid_blocks(sbi, segno, 0); + + if (valid_blocks == 0) { + __locate_dirty_segment(sbi, segno, PRE); + __remove_dirty_segment(sbi, segno, DIRTY); + } else if (valid_blocks < sbi->blocks_per_seg) { + __locate_dirty_segment(sbi, segno, DIRTY); + } else { + /* Recovery routine with SSR needs this */ + __remove_dirty_segment(sbi, segno, DIRTY); + } + + mutex_unlock(&dirty_i->seglist_lock); +} + +static int f2fs_issue_discard(struct f2fs_sb_info *sbi, + block_t blkstart, block_t blklen) +{ + sector_t start = SECTOR_FROM_BLOCK(blkstart); + sector_t len = SECTOR_FROM_BLOCK(blklen); + trace_f2fs_issue_discard(sbi->sb, blkstart, blklen); + return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0); +} + +void discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr) +{ + if (f2fs_issue_discard(sbi, blkaddr, 1)) { + struct page *page = grab_meta_page(sbi, blkaddr); + /* zero-filled page */ + set_page_dirty(page); + f2fs_put_page(page, 1); + } +} + +static void __add_discard_entry(struct f2fs_sb_info *sbi, + struct cp_control *cpc, unsigned int start, unsigned int end) +{ + struct list_head *head = &SM_I(sbi)->discard_list; + struct discard_entry *new, *last; + + if (!list_empty(head)) { + last = list_last_entry(head, struct discard_entry, list); + if (START_BLOCK(sbi, cpc->trim_start) + start == + last->blkaddr + last->len) { + last->len += end - start; + goto done; + } + } + + new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS); + INIT_LIST_HEAD(&new->list); + new->blkaddr = START_BLOCK(sbi, cpc->trim_start) + start; + new->len = end - start; + list_add_tail(&new->list, head); +done: + SM_I(sbi)->nr_discards += end - start; + cpc->trimmed += end - start; +} + +static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc) +{ + int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long); + int max_blocks = sbi->blocks_per_seg; + struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start); + unsigned long *cur_map = (unsigned long *)se->cur_valid_map; + unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map; + unsigned long *dmap = SIT_I(sbi)->tmp_map; + unsigned int start = 0, end = -1; + bool force = (cpc->reason == CP_DISCARD); + int i; + + if (!force && (!test_opt(sbi, DISCARD) || + SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards)) + return; + + if (force && !se->valid_blocks) { + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + /* + * if this segment is registered in the prefree list, then + * we should skip adding a discard candidate, and let the + * checkpoint do that later. + */ + mutex_lock(&dirty_i->seglist_lock); + if (test_bit(cpc->trim_start, dirty_i->dirty_segmap[PRE])) { + mutex_unlock(&dirty_i->seglist_lock); + cpc->trimmed += sbi->blocks_per_seg; + return; + } + mutex_unlock(&dirty_i->seglist_lock); + + __add_discard_entry(sbi, cpc, 0, sbi->blocks_per_seg); + return; + } + + /* zero block will be discarded through the prefree list */ + if (!se->valid_blocks || se->valid_blocks == max_blocks) + return; + + /* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */ + for (i = 0; i < entries; i++) + dmap[i] = force ? ~ckpt_map[i] : + (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i]; + + while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) { + start = __find_rev_next_bit(dmap, max_blocks, end + 1); + if (start >= max_blocks) + break; + + end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1); + + if (force && end - start < cpc->trim_minlen) + continue; + + __add_discard_entry(sbi, cpc, start, end); + } +} + +void release_discard_addrs(struct f2fs_sb_info *sbi) +{ + struct list_head *head = &(SM_I(sbi)->discard_list); + struct discard_entry *entry, *this; + + /* drop caches */ + list_for_each_entry_safe(entry, this, head, list) { + list_del(&entry->list); + kmem_cache_free(discard_entry_slab, entry); + } +} + +/* + * Should call clear_prefree_segments after checkpoint is done. + */ +static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int segno; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[PRE], MAIN_SEGS(sbi)) + __set_test_and_free(sbi, segno); + mutex_unlock(&dirty_i->seglist_lock); +} + +void clear_prefree_segments(struct f2fs_sb_info *sbi) +{ + struct list_head *head = &(SM_I(sbi)->discard_list); + struct discard_entry *entry, *this; + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned long *prefree_map = dirty_i->dirty_segmap[PRE]; + unsigned int start = 0, end = -1; + + mutex_lock(&dirty_i->seglist_lock); + + while (1) { + int i; + start = find_next_bit(prefree_map, MAIN_SEGS(sbi), end + 1); + if (start >= MAIN_SEGS(sbi)) + break; + end = find_next_zero_bit(prefree_map, MAIN_SEGS(sbi), + start + 1); + + for (i = start; i < end; i++) + clear_bit(i, prefree_map); + + dirty_i->nr_dirty[PRE] -= end - start; + + if (!test_opt(sbi, DISCARD)) + continue; + + f2fs_issue_discard(sbi, START_BLOCK(sbi, start), + (end - start) << sbi->log_blocks_per_seg); + } + mutex_unlock(&dirty_i->seglist_lock); + + /* send small discards */ + list_for_each_entry_safe(entry, this, head, list) { + f2fs_issue_discard(sbi, entry->blkaddr, entry->len); + list_del(&entry->list); + SM_I(sbi)->nr_discards -= entry->len; + kmem_cache_free(discard_entry_slab, entry); + } +} + +static bool __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno) +{ + struct sit_info *sit_i = SIT_I(sbi); + + if (!__test_and_set_bit(segno, sit_i->dirty_sentries_bitmap)) { + sit_i->dirty_sentries++; + return false; + } + + return true; +} + +static void __set_sit_entry_type(struct f2fs_sb_info *sbi, int type, + unsigned int segno, int modified) +{ + struct seg_entry *se = get_seg_entry(sbi, segno); + se->type = type; + if (modified) + __mark_sit_entry_dirty(sbi, segno); +} + +static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) +{ + struct seg_entry *se; + unsigned int segno, offset; + long int new_vblocks; + + segno = GET_SEGNO(sbi, blkaddr); + + se = get_seg_entry(sbi, segno); + new_vblocks = se->valid_blocks + del; + offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); + + f2fs_bug_on(sbi, (new_vblocks >> (sizeof(unsigned short) << 3) || + (new_vblocks > sbi->blocks_per_seg))); + + se->valid_blocks = new_vblocks; + se->mtime = get_mtime(sbi); + SIT_I(sbi)->max_mtime = se->mtime; + + /* Update valid block bitmap */ + if (del > 0) { + if (f2fs_test_and_set_bit(offset, se->cur_valid_map)) + f2fs_bug_on(sbi, 1); + } else { + if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) + f2fs_bug_on(sbi, 1); + } + if (!f2fs_test_bit(offset, se->ckpt_valid_map)) + se->ckpt_valid_blocks += del; + + __mark_sit_entry_dirty(sbi, segno); + + /* update total number of valid blocks to be written in ckpt area */ + SIT_I(sbi)->written_valid_blocks += del; + + if (sbi->segs_per_sec > 1) + get_sec_entry(sbi, segno)->valid_blocks += del; +} + +void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new) +{ + update_sit_entry(sbi, new, 1); + if (GET_SEGNO(sbi, old) != NULL_SEGNO) + update_sit_entry(sbi, old, -1); + + locate_dirty_segment(sbi, GET_SEGNO(sbi, old)); + locate_dirty_segment(sbi, GET_SEGNO(sbi, new)); +} + +void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) +{ + unsigned int segno = GET_SEGNO(sbi, addr); + struct sit_info *sit_i = SIT_I(sbi); + + f2fs_bug_on(sbi, addr == NULL_ADDR); + if (addr == NEW_ADDR) + return; + + /* add it into sit main buffer */ + mutex_lock(&sit_i->sentry_lock); + + update_sit_entry(sbi, addr, -1); + + /* add it into dirty seglist */ + locate_dirty_segment(sbi, segno); + + mutex_unlock(&sit_i->sentry_lock); +} + +/* + * This function should be resided under the curseg_mutex lock + */ +static void __add_sum_entry(struct f2fs_sb_info *sbi, int type, + struct f2fs_summary *sum) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + void *addr = curseg->sum_blk; + addr += curseg->next_blkoff * sizeof(struct f2fs_summary); + memcpy(addr, sum, sizeof(struct f2fs_summary)); +} + +/* + * Calculate the number of current summary pages for writing + */ +int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) +{ + int valid_sum_count = 0; + int i, sum_in_page; + + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { + if (sbi->ckpt->alloc_type[i] == SSR) + valid_sum_count += sbi->blocks_per_seg; + else { + if (for_ra) + valid_sum_count += le16_to_cpu( + F2FS_CKPT(sbi)->cur_data_blkoff[i]); + else + valid_sum_count += curseg_blkoff(sbi, i); + } + } + + sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE - + SUM_FOOTER_SIZE) / SUMMARY_SIZE; + if (valid_sum_count <= sum_in_page) + return 1; + else if ((valid_sum_count - sum_in_page) <= + (PAGE_CACHE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE) + return 2; + return 3; +} + +/* + * Caller should put this summary page + */ +struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno) +{ + return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno)); +} + +static void write_sum_page(struct f2fs_sb_info *sbi, + struct f2fs_summary_block *sum_blk, block_t blk_addr) +{ + struct page *page = grab_meta_page(sbi, blk_addr); + void *kaddr = page_address(page); + memcpy(kaddr, sum_blk, PAGE_CACHE_SIZE); + set_page_dirty(page); + f2fs_put_page(page, 1); +} + +static int is_next_segment_free(struct f2fs_sb_info *sbi, int type) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + unsigned int segno = curseg->segno + 1; + struct free_segmap_info *free_i = FREE_I(sbi); + + if (segno < MAIN_SEGS(sbi) && segno % sbi->segs_per_sec) + return !test_bit(segno, free_i->free_segmap); + return 0; +} + +/* + * Find a new segment from the free segments bitmap to right order + * This function should be returned with success, otherwise BUG + */ +static void get_new_segment(struct f2fs_sb_info *sbi, + unsigned int *newseg, bool new_sec, int dir) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int segno, secno, zoneno; + unsigned int total_zones = MAIN_SECS(sbi) / sbi->secs_per_zone; + unsigned int hint = *newseg / sbi->segs_per_sec; + unsigned int old_zoneno = GET_ZONENO_FROM_SEGNO(sbi, *newseg); + unsigned int left_start = hint; + bool init = true; + int go_left = 0; + int i; + + spin_lock(&free_i->segmap_lock); + + if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) { + segno = find_next_zero_bit(free_i->free_segmap, + MAIN_SEGS(sbi), *newseg + 1); + if (segno - *newseg < sbi->segs_per_sec - + (*newseg % sbi->segs_per_sec)) + goto got_it; + } +find_other_zone: + secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint); + if (secno >= MAIN_SECS(sbi)) { + if (dir == ALLOC_RIGHT) { + secno = find_next_zero_bit(free_i->free_secmap, + MAIN_SECS(sbi), 0); + f2fs_bug_on(sbi, secno >= MAIN_SECS(sbi)); + } else { + go_left = 1; + left_start = hint - 1; + } + } + if (go_left == 0) + goto skip_left; + + while (test_bit(left_start, free_i->free_secmap)) { + if (left_start > 0) { + left_start--; + continue; + } + left_start = find_next_zero_bit(free_i->free_secmap, + MAIN_SECS(sbi), 0); + f2fs_bug_on(sbi, left_start >= MAIN_SECS(sbi)); + break; + } + secno = left_start; +skip_left: + hint = secno; + segno = secno * sbi->segs_per_sec; + zoneno = secno / sbi->secs_per_zone; + + /* give up on finding another zone */ + if (!init) + goto got_it; + if (sbi->secs_per_zone == 1) + goto got_it; + if (zoneno == old_zoneno) + goto got_it; + if (dir == ALLOC_LEFT) { + if (!go_left && zoneno + 1 >= total_zones) + goto got_it; + if (go_left && zoneno == 0) + goto got_it; + } + for (i = 0; i < NR_CURSEG_TYPE; i++) + if (CURSEG_I(sbi, i)->zone == zoneno) + break; + + if (i < NR_CURSEG_TYPE) { + /* zone is in user, try another */ + if (go_left) + hint = zoneno * sbi->secs_per_zone - 1; + else if (zoneno + 1 >= total_zones) + hint = 0; + else + hint = (zoneno + 1) * sbi->secs_per_zone; + init = false; + goto find_other_zone; + } +got_it: + /* set it as dirty segment in free segmap */ + f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap)); + __set_inuse(sbi, segno); + *newseg = segno; + spin_unlock(&free_i->segmap_lock); +} + +static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + struct summary_footer *sum_footer; + + curseg->segno = curseg->next_segno; + curseg->zone = GET_ZONENO_FROM_SEGNO(sbi, curseg->segno); + curseg->next_blkoff = 0; + curseg->next_segno = NULL_SEGNO; + + sum_footer = &(curseg->sum_blk->footer); + memset(sum_footer, 0, sizeof(struct summary_footer)); + if (IS_DATASEG(type)) + SET_SUM_TYPE(sum_footer, SUM_TYPE_DATA); + if (IS_NODESEG(type)) + SET_SUM_TYPE(sum_footer, SUM_TYPE_NODE); + __set_sit_entry_type(sbi, type, curseg->segno, modified); +} + +/* + * Allocate a current working segment. + * This function always allocates a free segment in LFS manner. + */ +static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + unsigned int segno = curseg->segno; + int dir = ALLOC_LEFT; + + write_sum_page(sbi, curseg->sum_blk, + GET_SUM_BLOCK(sbi, segno)); + if (type == CURSEG_WARM_DATA || type == CURSEG_COLD_DATA) + dir = ALLOC_RIGHT; + + if (test_opt(sbi, NOHEAP)) + dir = ALLOC_RIGHT; + + get_new_segment(sbi, &segno, new_sec, dir); + curseg->next_segno = segno; + reset_curseg(sbi, type, 1); + curseg->alloc_type = LFS; +} + +static void __next_free_blkoff(struct f2fs_sb_info *sbi, + struct curseg_info *seg, block_t start) +{ + struct seg_entry *se = get_seg_entry(sbi, seg->segno); + int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long); + unsigned long *target_map = SIT_I(sbi)->tmp_map; + unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map; + unsigned long *cur_map = (unsigned long *)se->cur_valid_map; + int i, pos; + + for (i = 0; i < entries; i++) + target_map[i] = ckpt_map[i] | cur_map[i]; + + pos = __find_rev_next_zero_bit(target_map, sbi->blocks_per_seg, start); + + seg->next_blkoff = pos; +} + +/* + * If a segment is written by LFS manner, next block offset is just obtained + * by increasing the current block offset. However, if a segment is written by + * SSR manner, next block offset obtained by calling __next_free_blkoff + */ +static void __refresh_next_blkoff(struct f2fs_sb_info *sbi, + struct curseg_info *seg) +{ + if (seg->alloc_type == SSR) + __next_free_blkoff(sbi, seg, seg->next_blkoff + 1); + else + seg->next_blkoff++; +} + +/* + * This function always allocates a used segment(from dirty seglist) by SSR + * manner, so it should recover the existing segment information of valid blocks + */ +static void change_curseg(struct f2fs_sb_info *sbi, int type, bool reuse) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + struct curseg_info *curseg = CURSEG_I(sbi, type); + unsigned int new_segno = curseg->next_segno; + struct f2fs_summary_block *sum_node; + struct page *sum_page; + + write_sum_page(sbi, curseg->sum_blk, + GET_SUM_BLOCK(sbi, curseg->segno)); + __set_test_and_inuse(sbi, new_segno); + + mutex_lock(&dirty_i->seglist_lock); + __remove_dirty_segment(sbi, new_segno, PRE); + __remove_dirty_segment(sbi, new_segno, DIRTY); + mutex_unlock(&dirty_i->seglist_lock); + + reset_curseg(sbi, type, 1); + curseg->alloc_type = SSR; + __next_free_blkoff(sbi, curseg, 0); + + if (reuse) { + sum_page = get_sum_page(sbi, new_segno); + sum_node = (struct f2fs_summary_block *)page_address(sum_page); + memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE); + f2fs_put_page(sum_page, 1); + } +} + +static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops; + + if (IS_NODESEG(type) || !has_not_enough_free_secs(sbi, 0)) + return v_ops->get_victim(sbi, + &(curseg)->next_segno, BG_GC, type, SSR); + + /* For data segments, let's do SSR more intensively */ + for (; type >= CURSEG_HOT_DATA; type--) + if (v_ops->get_victim(sbi, &(curseg)->next_segno, + BG_GC, type, SSR)) + return 1; + return 0; +} + +/* + * flush out current segment and replace it with new segment + * This function should be returned with success, otherwise BUG + */ +static void allocate_segment_by_default(struct f2fs_sb_info *sbi, + int type, bool force) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + + if (force) + new_curseg(sbi, type, true); + else if (type == CURSEG_WARM_NODE) + new_curseg(sbi, type, false); + else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type)) + new_curseg(sbi, type, false); + else if (need_SSR(sbi) && get_ssr_segment(sbi, type)) + change_curseg(sbi, type, true); + else + new_curseg(sbi, type, false); + + stat_inc_seg_type(sbi, curseg); +} + +static void __allocate_new_segments(struct f2fs_sb_info *sbi, int type) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + unsigned int old_segno; + + old_segno = curseg->segno; + SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true); + locate_dirty_segment(sbi, old_segno); +} + +void allocate_new_segments(struct f2fs_sb_info *sbi) +{ + int i; + + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) + __allocate_new_segments(sbi, i); +} + +static const struct segment_allocation default_salloc_ops = { + .allocate_segment = allocate_segment_by_default, +}; + +int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) +{ + __u64 start = F2FS_BYTES_TO_BLK(range->start); + __u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1; + unsigned int start_segno, end_segno; + struct cp_control cpc; + + if (range->minlen > SEGMENT_SIZE(sbi) || start >= MAX_BLKADDR(sbi) || + range->len < sbi->blocksize) + return -EINVAL; + + cpc.trimmed = 0; + if (end <= MAIN_BLKADDR(sbi)) + goto out; + + /* start/end segment number in main_area */ + start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start); + end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 : + GET_SEGNO(sbi, end); + cpc.reason = CP_DISCARD; + cpc.trim_minlen = F2FS_BYTES_TO_BLK(range->minlen); + + /* do checkpoint to issue discard commands safely */ + for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) { + cpc.trim_start = start_segno; + cpc.trim_end = min_t(unsigned int, rounddown(start_segno + + BATCHED_TRIM_SEGMENTS(sbi), + sbi->segs_per_sec) - 1, end_segno); + + mutex_lock(&sbi->gc_mutex); + write_checkpoint(sbi, &cpc); + mutex_unlock(&sbi->gc_mutex); + } +out: + range->len = F2FS_BLK_TO_BYTES(cpc.trimmed); + return 0; +} + +static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + if (curseg->next_blkoff < sbi->blocks_per_seg) + return true; + return false; +} + +static int __get_segment_type_2(struct page *page, enum page_type p_type) +{ + if (p_type == DATA) + return CURSEG_HOT_DATA; + else + return CURSEG_HOT_NODE; +} + +static int __get_segment_type_4(struct page *page, enum page_type p_type) +{ + if (p_type == DATA) { + struct inode *inode = page->mapping->host; + + if (S_ISDIR(inode->i_mode)) + return CURSEG_HOT_DATA; + else + return CURSEG_COLD_DATA; + } else { + if (IS_DNODE(page) && is_cold_node(page)) + return CURSEG_WARM_NODE; + else + return CURSEG_COLD_NODE; + } +} + +static int __get_segment_type_6(struct page *page, enum page_type p_type) +{ + if (p_type == DATA) { + struct inode *inode = page->mapping->host; + + if (S_ISDIR(inode->i_mode)) + return CURSEG_HOT_DATA; + else if (is_cold_data(page) || file_is_cold(inode)) + return CURSEG_COLD_DATA; + else + return CURSEG_WARM_DATA; + } else { + if (IS_DNODE(page)) + return is_cold_node(page) ? CURSEG_WARM_NODE : + CURSEG_HOT_NODE; + else + return CURSEG_COLD_NODE; + } +} + +static int __get_segment_type(struct page *page, enum page_type p_type) +{ + switch (F2FS_P_SB(page)->active_logs) { + case 2: + return __get_segment_type_2(page, p_type); + case 4: + return __get_segment_type_4(page, p_type); + } + /* NR_CURSEG_TYPE(6) logs by default */ + f2fs_bug_on(F2FS_P_SB(page), + F2FS_P_SB(page)->active_logs != NR_CURSEG_TYPE); + return __get_segment_type_6(page, p_type); +} + +void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, + block_t old_blkaddr, block_t *new_blkaddr, + struct f2fs_summary *sum, int type) +{ + struct sit_info *sit_i = SIT_I(sbi); + struct curseg_info *curseg; + bool direct_io = (type == CURSEG_DIRECT_IO); + + type = direct_io ? CURSEG_WARM_DATA : type; + + curseg = CURSEG_I(sbi, type); + + mutex_lock(&curseg->curseg_mutex); + mutex_lock(&sit_i->sentry_lock); + + /* direct_io'ed data is aligned to the segment for better performance */ + if (direct_io && curseg->next_blkoff) + __allocate_new_segments(sbi, type); + + *new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); + + /* + * __add_sum_entry should be resided under the curseg_mutex + * because, this function updates a summary entry in the + * current summary block. + */ + __add_sum_entry(sbi, type, sum); + + __refresh_next_blkoff(sbi, curseg); + + stat_inc_block_count(sbi, curseg); + + if (!__has_curseg_space(sbi, type)) + sit_i->s_ops->allocate_segment(sbi, type, false); + /* + * SIT information should be updated before segment allocation, + * since SSR needs latest valid block information. + */ + refresh_sit_entry(sbi, old_blkaddr, *new_blkaddr); + + mutex_unlock(&sit_i->sentry_lock); + + if (page && IS_NODESEG(type)) + fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg)); + + mutex_unlock(&curseg->curseg_mutex); +} + +static void do_write_page(struct f2fs_sb_info *sbi, struct page *page, + struct f2fs_summary *sum, + struct f2fs_io_info *fio) +{ + int type = __get_segment_type(page, fio->type); + + allocate_data_block(sbi, page, fio->blk_addr, &fio->blk_addr, sum, type); + + /* writeout dirty page into bdev */ + f2fs_submit_page_mbio(sbi, page, fio); +} + +void write_meta_page(struct f2fs_sb_info *sbi, struct page *page) +{ + struct f2fs_io_info fio = { + .type = META, + .rw = WRITE_SYNC | REQ_META | REQ_PRIO, + .blk_addr = page->index, + }; + + set_page_writeback(page); + f2fs_submit_page_mbio(sbi, page, &fio); +} + +void write_node_page(struct f2fs_sb_info *sbi, struct page *page, + unsigned int nid, struct f2fs_io_info *fio) +{ + struct f2fs_summary sum; + set_summary(&sum, nid, 0, 0); + do_write_page(sbi, page, &sum, fio); +} + +void write_data_page(struct page *page, struct dnode_of_data *dn, + struct f2fs_io_info *fio) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + struct f2fs_summary sum; + struct node_info ni; + + f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR); + get_node_info(sbi, dn->nid, &ni); + set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); + do_write_page(sbi, page, &sum, fio); + dn->data_blkaddr = fio->blk_addr; +} + +void rewrite_data_page(struct page *page, struct f2fs_io_info *fio) +{ + stat_inc_inplace_blocks(F2FS_P_SB(page)); + f2fs_submit_page_mbio(F2FS_P_SB(page), page, fio); +} + +void recover_data_page(struct f2fs_sb_info *sbi, + struct page *page, struct f2fs_summary *sum, + block_t old_blkaddr, block_t new_blkaddr) +{ + struct sit_info *sit_i = SIT_I(sbi); + struct curseg_info *curseg; + unsigned int segno, old_cursegno; + struct seg_entry *se; + int type; + + segno = GET_SEGNO(sbi, new_blkaddr); + se = get_seg_entry(sbi, segno); + type = se->type; + + if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) { + if (old_blkaddr == NULL_ADDR) + type = CURSEG_COLD_DATA; + else + type = CURSEG_WARM_DATA; + } + curseg = CURSEG_I(sbi, type); + + mutex_lock(&curseg->curseg_mutex); + mutex_lock(&sit_i->sentry_lock); + + old_cursegno = curseg->segno; + + /* change the current segment */ + if (segno != curseg->segno) { + curseg->next_segno = segno; + change_curseg(sbi, type, true); + } + + curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr); + __add_sum_entry(sbi, type, sum); + + refresh_sit_entry(sbi, old_blkaddr, new_blkaddr); + locate_dirty_segment(sbi, old_cursegno); + + mutex_unlock(&sit_i->sentry_lock); + mutex_unlock(&curseg->curseg_mutex); +} + +static inline bool is_merged_page(struct f2fs_sb_info *sbi, + struct page *page, enum page_type type) +{ + enum page_type btype = PAGE_TYPE_OF_BIO(type); + struct f2fs_bio_info *io = &sbi->write_io[btype]; + struct bio_vec *bvec; + int i; + + down_read(&io->io_rwsem); + if (!io->bio) + goto out; + + bio_for_each_segment_all(bvec, io->bio, i) { + if (page == bvec->bv_page) { + up_read(&io->io_rwsem); + return true; + } + } + +out: + up_read(&io->io_rwsem); + return false; +} + +void f2fs_wait_on_page_writeback(struct page *page, + enum page_type type) +{ + if (PageWriteback(page)) { + struct f2fs_sb_info *sbi = F2FS_P_SB(page); + + if (is_merged_page(sbi, page, type)) + f2fs_submit_merged_bio(sbi, type, WRITE); + wait_on_page_writeback(page); + } +} + +static int read_compacted_summaries(struct f2fs_sb_info *sbi) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + struct curseg_info *seg_i; + unsigned char *kaddr; + struct page *page; + block_t start; + int i, j, offset; + + start = start_sum_block(sbi); + + page = get_meta_page(sbi, start++); + kaddr = (unsigned char *)page_address(page); + + /* Step 1: restore nat cache */ + seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA); + memcpy(&seg_i->sum_blk->n_nats, kaddr, SUM_JOURNAL_SIZE); + + /* Step 2: restore sit cache */ + seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA); + memcpy(&seg_i->sum_blk->n_sits, kaddr + SUM_JOURNAL_SIZE, + SUM_JOURNAL_SIZE); + offset = 2 * SUM_JOURNAL_SIZE; + + /* Step 3: restore summary entries */ + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { + unsigned short blk_off; + unsigned int segno; + + seg_i = CURSEG_I(sbi, i); + segno = le32_to_cpu(ckpt->cur_data_segno[i]); + blk_off = le16_to_cpu(ckpt->cur_data_blkoff[i]); + seg_i->next_segno = segno; + reset_curseg(sbi, i, 0); + seg_i->alloc_type = ckpt->alloc_type[i]; + seg_i->next_blkoff = blk_off; + + if (seg_i->alloc_type == SSR) + blk_off = sbi->blocks_per_seg; + + for (j = 0; j < blk_off; j++) { + struct f2fs_summary *s; + s = (struct f2fs_summary *)(kaddr + offset); + seg_i->sum_blk->entries[j] = *s; + offset += SUMMARY_SIZE; + if (offset + SUMMARY_SIZE <= PAGE_CACHE_SIZE - + SUM_FOOTER_SIZE) + continue; + + f2fs_put_page(page, 1); + page = NULL; + + page = get_meta_page(sbi, start++); + kaddr = (unsigned char *)page_address(page); + offset = 0; + } + } + f2fs_put_page(page, 1); + return 0; +} + +static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + struct f2fs_summary_block *sum; + struct curseg_info *curseg; + struct page *new; + unsigned short blk_off; + unsigned int segno = 0; + block_t blk_addr = 0; + + /* get segment number and block addr */ + if (IS_DATASEG(type)) { + segno = le32_to_cpu(ckpt->cur_data_segno[type]); + blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type - + CURSEG_HOT_DATA]); + if (__exist_node_summaries(sbi)) + blk_addr = sum_blk_addr(sbi, NR_CURSEG_TYPE, type); + else + blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type); + } else { + segno = le32_to_cpu(ckpt->cur_node_segno[type - + CURSEG_HOT_NODE]); + blk_off = le16_to_cpu(ckpt->cur_node_blkoff[type - + CURSEG_HOT_NODE]); + if (__exist_node_summaries(sbi)) + blk_addr = sum_blk_addr(sbi, NR_CURSEG_NODE_TYPE, + type - CURSEG_HOT_NODE); + else + blk_addr = GET_SUM_BLOCK(sbi, segno); + } + + new = get_meta_page(sbi, blk_addr); + sum = (struct f2fs_summary_block *)page_address(new); + + if (IS_NODESEG(type)) { + if (__exist_node_summaries(sbi)) { + struct f2fs_summary *ns = &sum->entries[0]; + int i; + for (i = 0; i < sbi->blocks_per_seg; i++, ns++) { + ns->version = 0; + ns->ofs_in_node = 0; + } + } else { + int err; + + err = restore_node_summary(sbi, segno, sum); + if (err) { + f2fs_put_page(new, 1); + return err; + } + } + } + + /* set uncompleted segment to curseg */ + curseg = CURSEG_I(sbi, type); + mutex_lock(&curseg->curseg_mutex); + memcpy(curseg->sum_blk, sum, PAGE_CACHE_SIZE); + curseg->next_segno = segno; + reset_curseg(sbi, type, 0); + curseg->alloc_type = ckpt->alloc_type[type]; + curseg->next_blkoff = blk_off; + mutex_unlock(&curseg->curseg_mutex); + f2fs_put_page(new, 1); + return 0; +} + +static int restore_curseg_summaries(struct f2fs_sb_info *sbi) +{ + int type = CURSEG_HOT_DATA; + int err; + + if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) { + int npages = npages_for_summary_flush(sbi, true); + + if (npages >= 2) + ra_meta_pages(sbi, start_sum_block(sbi), npages, + META_CP); + + /* restore for compacted data summary */ + if (read_compacted_summaries(sbi)) + return -EINVAL; + type = CURSEG_HOT_NODE; + } + + if (__exist_node_summaries(sbi)) + ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type), + NR_CURSEG_TYPE - type, META_CP); + + for (; type <= CURSEG_COLD_NODE; type++) { + err = read_normal_summaries(sbi, type); + if (err) + return err; + } + + return 0; +} + +static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) +{ + struct page *page; + unsigned char *kaddr; + struct f2fs_summary *summary; + struct curseg_info *seg_i; + int written_size = 0; + int i, j; + + page = grab_meta_page(sbi, blkaddr++); + kaddr = (unsigned char *)page_address(page); + + /* Step 1: write nat cache */ + seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA); + memcpy(kaddr, &seg_i->sum_blk->n_nats, SUM_JOURNAL_SIZE); + written_size += SUM_JOURNAL_SIZE; + + /* Step 2: write sit cache */ + seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA); + memcpy(kaddr + written_size, &seg_i->sum_blk->n_sits, + SUM_JOURNAL_SIZE); + written_size += SUM_JOURNAL_SIZE; + + /* Step 3: write summary entries */ + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { + unsigned short blkoff; + seg_i = CURSEG_I(sbi, i); + if (sbi->ckpt->alloc_type[i] == SSR) + blkoff = sbi->blocks_per_seg; + else + blkoff = curseg_blkoff(sbi, i); + + for (j = 0; j < blkoff; j++) { + if (!page) { + page = grab_meta_page(sbi, blkaddr++); + kaddr = (unsigned char *)page_address(page); + written_size = 0; + } + summary = (struct f2fs_summary *)(kaddr + written_size); + *summary = seg_i->sum_blk->entries[j]; + written_size += SUMMARY_SIZE; + + if (written_size + SUMMARY_SIZE <= PAGE_CACHE_SIZE - + SUM_FOOTER_SIZE) + continue; + + set_page_dirty(page); + f2fs_put_page(page, 1); + page = NULL; + } + } + if (page) { + set_page_dirty(page); + f2fs_put_page(page, 1); + } +} + +static void write_normal_summaries(struct f2fs_sb_info *sbi, + block_t blkaddr, int type) +{ + int i, end; + if (IS_DATASEG(type)) + end = type + NR_CURSEG_DATA_TYPE; + else + end = type + NR_CURSEG_NODE_TYPE; + + for (i = type; i < end; i++) { + struct curseg_info *sum = CURSEG_I(sbi, i); + mutex_lock(&sum->curseg_mutex); + write_sum_page(sbi, sum->sum_blk, blkaddr + (i - type)); + mutex_unlock(&sum->curseg_mutex); + } +} + +void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk) +{ + if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) + write_compacted_summaries(sbi, start_blk); + else + write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA); +} + +void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk) +{ + write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE); +} + +int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type, + unsigned int val, int alloc) +{ + int i; + + if (type == NAT_JOURNAL) { + for (i = 0; i < nats_in_cursum(sum); i++) { + if (le32_to_cpu(nid_in_journal(sum, i)) == val) + return i; + } + if (alloc && nats_in_cursum(sum) < NAT_JOURNAL_ENTRIES) + return update_nats_in_cursum(sum, 1); + } else if (type == SIT_JOURNAL) { + for (i = 0; i < sits_in_cursum(sum); i++) + if (le32_to_cpu(segno_in_journal(sum, i)) == val) + return i; + if (alloc && sits_in_cursum(sum) < SIT_JOURNAL_ENTRIES) + return update_sits_in_cursum(sum, 1); + } + return -1; +} + +static struct page *get_current_sit_page(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + return get_meta_page(sbi, current_sit_addr(sbi, segno)); +} + +static struct page *get_next_sit_page(struct f2fs_sb_info *sbi, + unsigned int start) +{ + struct sit_info *sit_i = SIT_I(sbi); + struct page *src_page, *dst_page; + pgoff_t src_off, dst_off; + void *src_addr, *dst_addr; + + src_off = current_sit_addr(sbi, start); + dst_off = next_sit_addr(sbi, src_off); + + /* get current sit block page without lock */ + src_page = get_meta_page(sbi, src_off); + dst_page = grab_meta_page(sbi, dst_off); + f2fs_bug_on(sbi, PageDirty(src_page)); + + src_addr = page_address(src_page); + dst_addr = page_address(dst_page); + memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE); + + set_page_dirty(dst_page); + f2fs_put_page(src_page, 1); + + set_to_next_sit(sit_i, start); + + return dst_page; +} + +static struct sit_entry_set *grab_sit_entry_set(void) +{ + struct sit_entry_set *ses = + f2fs_kmem_cache_alloc(sit_entry_set_slab, GFP_ATOMIC); + + ses->entry_cnt = 0; + INIT_LIST_HEAD(&ses->set_list); + return ses; +} + +static void release_sit_entry_set(struct sit_entry_set *ses) +{ + list_del(&ses->set_list); + kmem_cache_free(sit_entry_set_slab, ses); +} + +static void adjust_sit_entry_set(struct sit_entry_set *ses, + struct list_head *head) +{ + struct sit_entry_set *next = ses; + + if (list_is_last(&ses->set_list, head)) + return; + + list_for_each_entry_continue(next, head, set_list) + if (ses->entry_cnt <= next->entry_cnt) + break; + + list_move_tail(&ses->set_list, &next->set_list); +} + +static void add_sit_entry(unsigned int segno, struct list_head *head) +{ + struct sit_entry_set *ses; + unsigned int start_segno = START_SEGNO(segno); + + list_for_each_entry(ses, head, set_list) { + if (ses->start_segno == start_segno) { + ses->entry_cnt++; + adjust_sit_entry_set(ses, head); + return; + } + } + + ses = grab_sit_entry_set(); + + ses->start_segno = start_segno; + ses->entry_cnt++; + list_add(&ses->set_list, head); +} + +static void add_sits_in_set(struct f2fs_sb_info *sbi) +{ + struct f2fs_sm_info *sm_info = SM_I(sbi); + struct list_head *set_list = &sm_info->sit_entry_set; + unsigned long *bitmap = SIT_I(sbi)->dirty_sentries_bitmap; + unsigned int segno; + + for_each_set_bit(segno, bitmap, MAIN_SEGS(sbi)) + add_sit_entry(segno, set_list); +} + +static void remove_sits_in_journal(struct f2fs_sb_info *sbi) +{ + struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA); + struct f2fs_summary_block *sum = curseg->sum_blk; + int i; + + for (i = sits_in_cursum(sum) - 1; i >= 0; i--) { + unsigned int segno; + bool dirtied; + + segno = le32_to_cpu(segno_in_journal(sum, i)); + dirtied = __mark_sit_entry_dirty(sbi, segno); + + if (!dirtied) + add_sit_entry(segno, &SM_I(sbi)->sit_entry_set); + } + update_sits_in_cursum(sum, -sits_in_cursum(sum)); +} + +/* + * CP calls this function, which flushes SIT entries including sit_journal, + * and moves prefree segs to free segs. + */ +void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) +{ + struct sit_info *sit_i = SIT_I(sbi); + unsigned long *bitmap = sit_i->dirty_sentries_bitmap; + struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA); + struct f2fs_summary_block *sum = curseg->sum_blk; + struct sit_entry_set *ses, *tmp; + struct list_head *head = &SM_I(sbi)->sit_entry_set; + bool to_journal = true; + struct seg_entry *se; + + mutex_lock(&curseg->curseg_mutex); + mutex_lock(&sit_i->sentry_lock); + + if (!sit_i->dirty_sentries) + goto out; + + /* + * add and account sit entries of dirty bitmap in sit entry + * set temporarily + */ + add_sits_in_set(sbi); + + /* + * if there are no enough space in journal to store dirty sit + * entries, remove all entries from journal and add and account + * them in sit entry set. + */ + if (!__has_cursum_space(sum, sit_i->dirty_sentries, SIT_JOURNAL)) + remove_sits_in_journal(sbi); + + /* + * there are two steps to flush sit entries: + * #1, flush sit entries to journal in current cold data summary block. + * #2, flush sit entries to sit page. + */ + list_for_each_entry_safe(ses, tmp, head, set_list) { + struct page *page = NULL; + struct f2fs_sit_block *raw_sit = NULL; + unsigned int start_segno = ses->start_segno; + unsigned int end = min(start_segno + SIT_ENTRY_PER_BLOCK, + (unsigned long)MAIN_SEGS(sbi)); + unsigned int segno = start_segno; + + if (to_journal && + !__has_cursum_space(sum, ses->entry_cnt, SIT_JOURNAL)) + to_journal = false; + + if (!to_journal) { + page = get_next_sit_page(sbi, start_segno); + raw_sit = page_address(page); + } + + /* flush dirty sit entries in region of current sit set */ + for_each_set_bit_from(segno, bitmap, end) { + int offset, sit_offset; + + se = get_seg_entry(sbi, segno); + + /* add discard candidates */ + if (cpc->reason != CP_DISCARD) { + cpc->trim_start = segno; + add_discard_addrs(sbi, cpc); + } + + if (to_journal) { + offset = lookup_journal_in_cursum(sum, + SIT_JOURNAL, segno, 1); + f2fs_bug_on(sbi, offset < 0); + segno_in_journal(sum, offset) = + cpu_to_le32(segno); + seg_info_to_raw_sit(se, + &sit_in_journal(sum, offset)); + } else { + sit_offset = SIT_ENTRY_OFFSET(sit_i, segno); + seg_info_to_raw_sit(se, + &raw_sit->entries[sit_offset]); + } + + __clear_bit(segno, bitmap); + sit_i->dirty_sentries--; + ses->entry_cnt--; + } + + if (!to_journal) + f2fs_put_page(page, 1); + + f2fs_bug_on(sbi, ses->entry_cnt); + release_sit_entry_set(ses); + } + + f2fs_bug_on(sbi, !list_empty(head)); + f2fs_bug_on(sbi, sit_i->dirty_sentries); +out: + if (cpc->reason == CP_DISCARD) { + for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++) + add_discard_addrs(sbi, cpc); + } + mutex_unlock(&sit_i->sentry_lock); + mutex_unlock(&curseg->curseg_mutex); + + set_prefree_as_free_segments(sbi); +} + +static int build_sit_info(struct f2fs_sb_info *sbi) +{ + struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + struct sit_info *sit_i; + unsigned int sit_segs, start; + char *src_bitmap, *dst_bitmap; + unsigned int bitmap_size; + + /* allocate memory for SIT information */ + sit_i = kzalloc(sizeof(struct sit_info), GFP_KERNEL); + if (!sit_i) + return -ENOMEM; + + SM_I(sbi)->sit_info = sit_i; + + sit_i->sentries = vzalloc(MAIN_SEGS(sbi) * sizeof(struct seg_entry)); + if (!sit_i->sentries) + return -ENOMEM; + + bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); + sit_i->dirty_sentries_bitmap = kzalloc(bitmap_size, GFP_KERNEL); + if (!sit_i->dirty_sentries_bitmap) + return -ENOMEM; + + for (start = 0; start < MAIN_SEGS(sbi); start++) { + sit_i->sentries[start].cur_valid_map + = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + sit_i->sentries[start].ckpt_valid_map + = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + if (!sit_i->sentries[start].cur_valid_map + || !sit_i->sentries[start].ckpt_valid_map) + return -ENOMEM; + } + + sit_i->tmp_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + if (!sit_i->tmp_map) + return -ENOMEM; + + if (sbi->segs_per_sec > 1) { + sit_i->sec_entries = vzalloc(MAIN_SECS(sbi) * + sizeof(struct sec_entry)); + if (!sit_i->sec_entries) + return -ENOMEM; + } + + /* get information related with SIT */ + sit_segs = le32_to_cpu(raw_super->segment_count_sit) >> 1; + + /* setup SIT bitmap from ckeckpoint pack */ + bitmap_size = __bitmap_size(sbi, SIT_BITMAP); + src_bitmap = __bitmap_ptr(sbi, SIT_BITMAP); + + dst_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL); + if (!dst_bitmap) + return -ENOMEM; + + /* init SIT information */ + sit_i->s_ops = &default_salloc_ops; + + sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr); + sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg; + sit_i->written_valid_blocks = le64_to_cpu(ckpt->valid_block_count); + sit_i->sit_bitmap = dst_bitmap; + sit_i->bitmap_size = bitmap_size; + sit_i->dirty_sentries = 0; + sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK; + sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time); + sit_i->mounted_time = CURRENT_TIME_SEC.tv_sec; + mutex_init(&sit_i->sentry_lock); + return 0; +} + +static int build_free_segmap(struct f2fs_sb_info *sbi) +{ + struct free_segmap_info *free_i; + unsigned int bitmap_size, sec_bitmap_size; + + /* allocate memory for free segmap information */ + free_i = kzalloc(sizeof(struct free_segmap_info), GFP_KERNEL); + if (!free_i) + return -ENOMEM; + + SM_I(sbi)->free_info = free_i; + + bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); + free_i->free_segmap = kmalloc(bitmap_size, GFP_KERNEL); + if (!free_i->free_segmap) + return -ENOMEM; + + sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); + free_i->free_secmap = kmalloc(sec_bitmap_size, GFP_KERNEL); + if (!free_i->free_secmap) + return -ENOMEM; + + /* set all segments as dirty temporarily */ + memset(free_i->free_segmap, 0xff, bitmap_size); + memset(free_i->free_secmap, 0xff, sec_bitmap_size); + + /* init free segmap information */ + free_i->start_segno = GET_SEGNO_FROM_SEG0(sbi, MAIN_BLKADDR(sbi)); + free_i->free_segments = 0; + free_i->free_sections = 0; + spin_lock_init(&free_i->segmap_lock); + return 0; +} + +static int build_curseg(struct f2fs_sb_info *sbi) +{ + struct curseg_info *array; + int i; + + array = kcalloc(NR_CURSEG_TYPE, sizeof(*array), GFP_KERNEL); + if (!array) + return -ENOMEM; + + SM_I(sbi)->curseg_array = array; + + for (i = 0; i < NR_CURSEG_TYPE; i++) { + mutex_init(&array[i].curseg_mutex); + array[i].sum_blk = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL); + if (!array[i].sum_blk) + return -ENOMEM; + array[i].segno = NULL_SEGNO; + array[i].next_blkoff = 0; + } + return restore_curseg_summaries(sbi); +} + +static void build_sit_entries(struct f2fs_sb_info *sbi) +{ + struct sit_info *sit_i = SIT_I(sbi); + struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA); + struct f2fs_summary_block *sum = curseg->sum_blk; + int sit_blk_cnt = SIT_BLK_CNT(sbi); + unsigned int i, start, end; + unsigned int readed, start_blk = 0; + int nrpages = MAX_BIO_BLOCKS(sbi); + + do { + readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT); + + start = start_blk * sit_i->sents_per_block; + end = (start_blk + readed) * sit_i->sents_per_block; + + for (; start < end && start < MAIN_SEGS(sbi); start++) { + struct seg_entry *se = &sit_i->sentries[start]; + struct f2fs_sit_block *sit_blk; + struct f2fs_sit_entry sit; + struct page *page; + + mutex_lock(&curseg->curseg_mutex); + for (i = 0; i < sits_in_cursum(sum); i++) { + if (le32_to_cpu(segno_in_journal(sum, i)) + == start) { + sit = sit_in_journal(sum, i); + mutex_unlock(&curseg->curseg_mutex); + goto got_it; + } + } + mutex_unlock(&curseg->curseg_mutex); + + page = get_current_sit_page(sbi, start); + sit_blk = (struct f2fs_sit_block *)page_address(page); + sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)]; + f2fs_put_page(page, 1); +got_it: + check_block_count(sbi, start, &sit); + seg_info_from_raw_sit(se, &sit); + if (sbi->segs_per_sec > 1) { + struct sec_entry *e = get_sec_entry(sbi, start); + e->valid_blocks += se->valid_blocks; + } + } + start_blk += readed; + } while (start_blk < sit_blk_cnt); +} + +static void init_free_segmap(struct f2fs_sb_info *sbi) +{ + unsigned int start; + int type; + + for (start = 0; start < MAIN_SEGS(sbi); start++) { + struct seg_entry *sentry = get_seg_entry(sbi, start); + if (!sentry->valid_blocks) + __set_free(sbi, start); + } + + /* set use the current segments */ + for (type = CURSEG_HOT_DATA; type <= CURSEG_COLD_NODE; type++) { + struct curseg_info *curseg_t = CURSEG_I(sbi, type); + __set_test_and_inuse(sbi, curseg_t->segno); + } +} + +static void init_dirty_segmap(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int segno = 0, offset = 0; + unsigned short valid_blocks; + + while (1) { + /* find dirty segment based on free segmap */ + segno = find_next_inuse(free_i, MAIN_SEGS(sbi), offset); + if (segno >= MAIN_SEGS(sbi)) + break; + offset = segno + 1; + valid_blocks = get_valid_blocks(sbi, segno, 0); + if (valid_blocks == sbi->blocks_per_seg || !valid_blocks) + continue; + if (valid_blocks > sbi->blocks_per_seg) { + f2fs_bug_on(sbi, 1); + continue; + } + mutex_lock(&dirty_i->seglist_lock); + __locate_dirty_segment(sbi, segno, DIRTY); + mutex_unlock(&dirty_i->seglist_lock); + } +} + +static int init_victim_secmap(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); + + dirty_i->victim_secmap = kzalloc(bitmap_size, GFP_KERNEL); + if (!dirty_i->victim_secmap) + return -ENOMEM; + return 0; +} + +static int build_dirty_segmap(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i; + unsigned int bitmap_size, i; + + /* allocate memory for dirty segments list information */ + dirty_i = kzalloc(sizeof(struct dirty_seglist_info), GFP_KERNEL); + if (!dirty_i) + return -ENOMEM; + + SM_I(sbi)->dirty_info = dirty_i; + mutex_init(&dirty_i->seglist_lock); + + bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); + + for (i = 0; i < NR_DIRTY_TYPE; i++) { + dirty_i->dirty_segmap[i] = kzalloc(bitmap_size, GFP_KERNEL); + if (!dirty_i->dirty_segmap[i]) + return -ENOMEM; + } + + init_dirty_segmap(sbi); + return init_victim_secmap(sbi); +} + +/* + * Update min, max modified time for cost-benefit GC algorithm + */ +static void init_min_max_mtime(struct f2fs_sb_info *sbi) +{ + struct sit_info *sit_i = SIT_I(sbi); + unsigned int segno; + + mutex_lock(&sit_i->sentry_lock); + + sit_i->min_mtime = LLONG_MAX; + + for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) { + unsigned int i; + unsigned long long mtime = 0; + + for (i = 0; i < sbi->segs_per_sec; i++) + mtime += get_seg_entry(sbi, segno + i)->mtime; + + mtime = div_u64(mtime, sbi->segs_per_sec); + + if (sit_i->min_mtime > mtime) + sit_i->min_mtime = mtime; + } + sit_i->max_mtime = get_mtime(sbi); + mutex_unlock(&sit_i->sentry_lock); +} + +int build_segment_manager(struct f2fs_sb_info *sbi) +{ + struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + struct f2fs_sm_info *sm_info; + int err; + + sm_info = kzalloc(sizeof(struct f2fs_sm_info), GFP_KERNEL); + if (!sm_info) + return -ENOMEM; + + /* init sm info */ + sbi->sm_info = sm_info; + sm_info->seg0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr); + sm_info->main_blkaddr = le32_to_cpu(raw_super->main_blkaddr); + sm_info->segment_count = le32_to_cpu(raw_super->segment_count); + sm_info->reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count); + sm_info->ovp_segments = le32_to_cpu(ckpt->overprov_segment_count); + sm_info->main_segments = le32_to_cpu(raw_super->segment_count_main); + sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr); + sm_info->rec_prefree_segments = sm_info->main_segments * + DEF_RECLAIM_PREFREE_SEGMENTS / 100; + sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC; + sm_info->min_ipu_util = DEF_MIN_IPU_UTIL; + sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS; + + INIT_LIST_HEAD(&sm_info->discard_list); + sm_info->nr_discards = 0; + sm_info->max_discards = 0; + + sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS; + + INIT_LIST_HEAD(&sm_info->sit_entry_set); + + if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) { + err = create_flush_cmd_control(sbi); + if (err) + return err; + } + + err = build_sit_info(sbi); + if (err) + return err; + err = build_free_segmap(sbi); + if (err) + return err; + err = build_curseg(sbi); + if (err) + return err; + + /* reinit free segmap based on SIT */ + build_sit_entries(sbi); + + init_free_segmap(sbi); + err = build_dirty_segmap(sbi); + if (err) + return err; + + init_min_max_mtime(sbi); + return 0; +} + +static void discard_dirty_segmap(struct f2fs_sb_info *sbi, + enum dirty_type dirty_type) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + + mutex_lock(&dirty_i->seglist_lock); + kfree(dirty_i->dirty_segmap[dirty_type]); + dirty_i->nr_dirty[dirty_type] = 0; + mutex_unlock(&dirty_i->seglist_lock); +} + +static void destroy_victim_secmap(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + kfree(dirty_i->victim_secmap); +} + +static void destroy_dirty_segmap(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + int i; + + if (!dirty_i) + return; + + /* discard pre-free/dirty segments list */ + for (i = 0; i < NR_DIRTY_TYPE; i++) + discard_dirty_segmap(sbi, i); + + destroy_victim_secmap(sbi); + SM_I(sbi)->dirty_info = NULL; + kfree(dirty_i); +} + +static void destroy_curseg(struct f2fs_sb_info *sbi) +{ + struct curseg_info *array = SM_I(sbi)->curseg_array; + int i; + + if (!array) + return; + SM_I(sbi)->curseg_array = NULL; + for (i = 0; i < NR_CURSEG_TYPE; i++) + kfree(array[i].sum_blk); + kfree(array); +} + +static void destroy_free_segmap(struct f2fs_sb_info *sbi) +{ + struct free_segmap_info *free_i = SM_I(sbi)->free_info; + if (!free_i) + return; + SM_I(sbi)->free_info = NULL; + kfree(free_i->free_segmap); + kfree(free_i->free_secmap); + kfree(free_i); +} + +static void destroy_sit_info(struct f2fs_sb_info *sbi) +{ + struct sit_info *sit_i = SIT_I(sbi); + unsigned int start; + + if (!sit_i) + return; + + if (sit_i->sentries) { + for (start = 0; start < MAIN_SEGS(sbi); start++) { + kfree(sit_i->sentries[start].cur_valid_map); + kfree(sit_i->sentries[start].ckpt_valid_map); + } + } + kfree(sit_i->tmp_map); + + vfree(sit_i->sentries); + vfree(sit_i->sec_entries); + kfree(sit_i->dirty_sentries_bitmap); + + SM_I(sbi)->sit_info = NULL; + kfree(sit_i->sit_bitmap); + kfree(sit_i); +} + +void destroy_segment_manager(struct f2fs_sb_info *sbi) +{ + struct f2fs_sm_info *sm_info = SM_I(sbi); + + if (!sm_info) + return; + destroy_flush_cmd_control(sbi); + destroy_dirty_segmap(sbi); + destroy_curseg(sbi); + destroy_free_segmap(sbi); + destroy_sit_info(sbi); + sbi->sm_info = NULL; + kfree(sm_info); +} + +int __init create_segment_manager_caches(void) +{ + discard_entry_slab = f2fs_kmem_cache_create("discard_entry", + sizeof(struct discard_entry)); + if (!discard_entry_slab) + goto fail; + + sit_entry_set_slab = f2fs_kmem_cache_create("sit_entry_set", + sizeof(struct sit_entry_set)); + if (!sit_entry_set_slab) + goto destory_discard_entry; + + inmem_entry_slab = f2fs_kmem_cache_create("inmem_page_entry", + sizeof(struct inmem_pages)); + if (!inmem_entry_slab) + goto destroy_sit_entry_set; + return 0; + +destroy_sit_entry_set: + kmem_cache_destroy(sit_entry_set_slab); +destory_discard_entry: + kmem_cache_destroy(discard_entry_slab); +fail: + return -ENOMEM; +} + +void destroy_segment_manager_caches(void) +{ + kmem_cache_destroy(sit_entry_set_slab); + kmem_cache_destroy(discard_entry_slab); + kmem_cache_destroy(inmem_entry_slab); +} diff --git a/kernel/fs/f2fs/segment.h b/kernel/fs/f2fs/segment.h new file mode 100644 index 000000000..85d7fa751 --- /dev/null +++ b/kernel/fs/f2fs/segment.h @@ -0,0 +1,751 @@ +/* + * 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)) + +#define DEF_RECLAIM_PREFREE_SEGMENTS 5 /* 5% over total segments */ + +/* 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_COLD_DATA) +#define IS_NODESEG(t) (t >= CURSEG_HOT_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 MAIN_BLKADDR(sbi) (SM_I(sbi)->main_blkaddr) +#define SEG0_BLKADDR(sbi) (SM_I(sbi)->seg0_blkaddr) + +#define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments) +#define MAIN_SECS(sbi) (sbi->total_sections) + +#define TOTAL_SEGS(sbi) (SM_I(sbi)->segment_count) +#define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << sbi->log_blocks_per_seg) + +#define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi)) +#define SEGMENT_SIZE(sbi) (1ULL << (sbi->log_blocksize + \ + sbi->log_blocks_per_seg)) + +#define START_BLOCK(sbi, segno) (SEG0_BLKADDR(sbi) + \ + (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 GET_SEGOFF_FROM_SEG0(sbi, blk_addr) ((blk_addr) - SEG0_BLKADDR(sbi)) +#define GET_SEGNO_FROM_SEG0(sbi, blk_addr) \ + (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> sbi->log_blocks_per_seg) +#define GET_BLKOFF_FROM_SEG0(sbi, blk_addr) \ + (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (sbi->blocks_per_seg - 1)) + +#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(segno) \ + (segno / SIT_ENTRY_PER_BLOCK) +#define START_SEGNO(segno) \ + (SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK) +#define SIT_BLK_CNT(sbi) \ + ((MAIN_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK) +#define f2fs_bitmap_size(nr) \ + (BITS_TO_LONGS(nr) * sizeof(unsigned long)) + +#define SECTOR_FROM_BLOCK(blk_addr) \ + (((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK) +#define SECTOR_TO_BLOCK(sectors) \ + (sectors >> F2FS_LOG_SECTORS_PER_BLOCK) +#define MAX_BIO_BLOCKS(sbi) \ + ((int)min((int)max_hw_blocks(sbi), BIO_MAX_PAGES)) + +/* + * 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 max_search; /* maximum # of segments to search */ + 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 inmem_pages { + struct list_head list; + struct page *page; +}; + +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 *tmp_map; /* bitmap for temporal use */ + 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 */ + spinlock_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 */ +}; + +struct sit_entry_set { + struct list_head set_list; /* link with all sit sets */ + unsigned int start_segno; /* start segno of sits in set */ + unsigned int entry_cnt; /* the # of sit entries in set */ +}; + +/* + * 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; + spin_lock(&free_i->segmap_lock); + ret = find_next_bit(free_i->free_segmap, max, segno); + spin_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; + + spin_lock(&free_i->segmap_lock); + clear_bit(segno, free_i->free_segmap); + free_i->free_segments++; + + next = find_next_bit(free_i->free_segmap, + start_segno + sbi->segs_per_sec, start_segno); + if (next >= start_segno + sbi->segs_per_sec) { + clear_bit(secno, free_i->free_secmap); + free_i->free_sections++; + } + spin_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; + + spin_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, + start_segno + sbi->segs_per_sec, start_segno); + if (next >= start_segno + sbi->segs_per_sec) { + if (test_and_clear_bit(secno, free_i->free_secmap)) + free_i->free_sections++; + } + } + spin_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; + spin_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--; + } + spin_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) +{ + return SIT_I(sbi)->written_valid_blocks; +} + +static inline unsigned int free_segments(struct f2fs_sb_info *sbi) +{ + return FREE_I(sbi)->free_segments; +} + +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) +{ + return FREE_I(sbi)->free_sections; +} + +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) +{ + int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES); + int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS); + return free_sections(sbi) <= (node_secs + 2 * dent_secs + + reserved_sections(sbi) + 1); +} + +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 (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + return false; + + return (free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs + + reserved_sections(sbi)); +} + +static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi) +{ + return prefree_segments(sbi) > SM_I(sbi)->rec_prefree_segments; +} + +static inline int utilization(struct f2fs_sb_info *sbi) +{ + return div_u64((u64)valid_user_blocks(sbi) * 100, + sbi->user_block_count); +} + +/* + * Sometimes f2fs may be better to drop out-of-place update policy. + * And, users can control the policy through sysfs entries. + * There are five policies with triggering conditions as follows. + * F2FS_IPU_FORCE - all the time, + * F2FS_IPU_SSR - if SSR mode is activated, + * F2FS_IPU_UTIL - if FS utilization is over threashold, + * F2FS_IPU_SSR_UTIL - if SSR mode is activated and FS utilization is over + * threashold, + * F2FS_IPU_FSYNC - activated in fsync path only for high performance flash + * storages. IPU will be triggered only if the # of dirty + * pages over min_fsync_blocks. + * F2FS_IPUT_DISABLE - disable IPU. (=default option) + */ +#define DEF_MIN_IPU_UTIL 70 +#define DEF_MIN_FSYNC_BLOCKS 8 + +enum { + F2FS_IPU_FORCE, + F2FS_IPU_SSR, + F2FS_IPU_UTIL, + F2FS_IPU_SSR_UTIL, + F2FS_IPU_FSYNC, +}; + +static inline bool need_inplace_update(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + unsigned int policy = SM_I(sbi)->ipu_policy; + + /* IPU can be done only for the user data */ + if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode)) + return false; + + if (policy & (0x1 << F2FS_IPU_FORCE)) + return true; + if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi)) + return true; + if (policy & (0x1 << F2FS_IPU_UTIL) && + utilization(sbi) > SM_I(sbi)->min_ipu_util) + return true; + if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && need_SSR(sbi) && + utilization(sbi) > SM_I(sbi)->min_ipu_util) + return true; + + /* this is only set during fdatasync */ + if (policy & (0x1 << F2FS_IPU_FSYNC) && + is_inode_flag_set(F2FS_I(inode), FI_NEED_IPU)) + 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; +} + +#ifdef CONFIG_F2FS_CHECK_FS +static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno) +{ + BUG_ON(segno > TOTAL_SEGS(sbi) - 1); +} + +static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr) +{ + BUG_ON(blk_addr < SEG0_BLKADDR(sbi)); + BUG_ON(blk_addr >= MAX_BLKADDR(sbi)); +} + +/* + * Summary block is always treated as an invalid block + */ +static inline void check_block_count(struct f2fs_sb_info *sbi, + int segno, struct f2fs_sit_entry *raw_sit) +{ + bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false; + int valid_blocks = 0; + int cur_pos = 0, next_pos; + + /* check segment usage */ + BUG_ON(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg); + + /* check boundary of a given segment number */ + BUG_ON(segno > TOTAL_SEGS(sbi) - 1); + + /* check bitmap with valid block count */ + do { + if (is_valid) { + next_pos = find_next_zero_bit_le(&raw_sit->valid_map, + sbi->blocks_per_seg, + cur_pos); + valid_blocks += next_pos - cur_pos; + } else + next_pos = find_next_bit_le(&raw_sit->valid_map, + sbi->blocks_per_seg, + cur_pos); + cur_pos = next_pos; + is_valid = !is_valid; + } while (cur_pos < sbi->blocks_per_seg); + BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks); +} +#else +static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno) +{ + if (segno > TOTAL_SEGS(sbi) - 1) + set_sbi_flag(sbi, SBI_NEED_FSCK); +} + +static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr) +{ + if (blk_addr < SEG0_BLKADDR(sbi) || blk_addr >= MAX_BLKADDR(sbi)) + set_sbi_flag(sbi, SBI_NEED_FSCK); +} + +/* + * Summary block is always treated as an invalid block + */ +static inline void check_block_count(struct f2fs_sb_info *sbi, + int segno, struct f2fs_sit_entry *raw_sit) +{ + /* check segment usage */ + if (GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg) + set_sbi_flag(sbi, SBI_NEED_FSCK); + + /* check boundary of a given segment number */ + if (segno > TOTAL_SEGS(sbi) - 1) + set_sbi_flag(sbi, SBI_NEED_FSCK); +} +#endif + +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(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(start); + + f2fs_change_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(queue_max_sectors(q)); +} + +/* + * It is very important to gather dirty pages and write at once, so that we can + * submit a big bio without interfering other data writes. + * By default, 512 pages for directory data, + * 512 pages (2MB) * 3 for three types of nodes, and + * max_bio_blocks for meta are set. + */ +static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type) +{ + if (sbi->sb->s_bdi->dirty_exceeded) + return 0; + + if (type == DATA) + return sbi->blocks_per_seg; + else if (type == NODE) + return 3 * sbi->blocks_per_seg; + else if (type == META) + return MAX_BIO_BLOCKS(sbi); + else + return 0; +} + +/* + * When writing pages, it'd better align nr_to_write for segment size. + */ +static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type, + struct writeback_control *wbc) +{ + long nr_to_write, desired; + + if (wbc->sync_mode != WB_SYNC_NONE) + return 0; + + nr_to_write = wbc->nr_to_write; + + if (type == DATA) + desired = 4096; + else if (type == NODE) + desired = 3 * max_hw_blocks(sbi); + else + desired = MAX_BIO_BLOCKS(sbi); + + wbc->nr_to_write = desired; + return desired - nr_to_write; +} diff --git a/kernel/fs/f2fs/super.c b/kernel/fs/f2fs/super.c new file mode 100644 index 000000000..b2dd1b01f --- /dev/null +++ b/kernel/fs/f2fs/super.c @@ -0,0 +1,1350 @@ +/* + * 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/proc_fs.h> +#include <linux/random.h> +#include <linux/exportfs.h> +#include <linux/blkdev.h> +#include <linux/f2fs_fs.h> +#include <linux/sysfs.h> + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include "xattr.h" +#include "gc.h" +#include "trace.h" + +#define CREATE_TRACE_POINTS +#include <trace/events/f2fs.h> + +static struct proc_dir_entry *f2fs_proc_root; +static struct kmem_cache *f2fs_inode_cachep; +static struct kset *f2fs_kset; + +enum { + Opt_gc_background, + Opt_disable_roll_forward, + Opt_norecovery, + Opt_discard, + Opt_noheap, + Opt_user_xattr, + Opt_nouser_xattr, + Opt_acl, + Opt_noacl, + Opt_active_logs, + Opt_disable_ext_identify, + Opt_inline_xattr, + Opt_inline_data, + Opt_inline_dentry, + Opt_flush_merge, + Opt_nobarrier, + Opt_fastboot, + Opt_extent_cache, + Opt_noinline_data, + Opt_err, +}; + +static match_table_t f2fs_tokens = { + {Opt_gc_background, "background_gc=%s"}, + {Opt_disable_roll_forward, "disable_roll_forward"}, + {Opt_norecovery, "norecovery"}, + {Opt_discard, "discard"}, + {Opt_noheap, "no_heap"}, + {Opt_user_xattr, "user_xattr"}, + {Opt_nouser_xattr, "nouser_xattr"}, + {Opt_acl, "acl"}, + {Opt_noacl, "noacl"}, + {Opt_active_logs, "active_logs=%u"}, + {Opt_disable_ext_identify, "disable_ext_identify"}, + {Opt_inline_xattr, "inline_xattr"}, + {Opt_inline_data, "inline_data"}, + {Opt_inline_dentry, "inline_dentry"}, + {Opt_flush_merge, "flush_merge"}, + {Opt_nobarrier, "nobarrier"}, + {Opt_fastboot, "fastboot"}, + {Opt_extent_cache, "extent_cache"}, + {Opt_noinline_data, "noinline_data"}, + {Opt_err, NULL}, +}; + +/* Sysfs support for f2fs */ +enum { + GC_THREAD, /* struct f2fs_gc_thread */ + SM_INFO, /* struct f2fs_sm_info */ + NM_INFO, /* struct f2fs_nm_info */ + F2FS_SBI, /* struct f2fs_sb_info */ +}; + +struct f2fs_attr { + struct attribute attr; + ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *); + ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *, + const char *, size_t); + int struct_type; + int offset; +}; + +static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type) +{ + if (struct_type == GC_THREAD) + return (unsigned char *)sbi->gc_thread; + else if (struct_type == SM_INFO) + return (unsigned char *)SM_I(sbi); + else if (struct_type == NM_INFO) + return (unsigned char *)NM_I(sbi); + else if (struct_type == F2FS_SBI) + return (unsigned char *)sbi; + return NULL; +} + +static ssize_t f2fs_sbi_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + unsigned char *ptr = NULL; + unsigned int *ui; + + ptr = __struct_ptr(sbi, a->struct_type); + if (!ptr) + return -EINVAL; + + ui = (unsigned int *)(ptr + a->offset); + + return snprintf(buf, PAGE_SIZE, "%u\n", *ui); +} + +static ssize_t f2fs_sbi_store(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, + const char *buf, size_t count) +{ + unsigned char *ptr; + unsigned long t; + unsigned int *ui; + ssize_t ret; + + ptr = __struct_ptr(sbi, a->struct_type); + if (!ptr) + return -EINVAL; + + ui = (unsigned int *)(ptr + a->offset); + + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret < 0) + return ret; + *ui = t; + return count; +} + +static ssize_t f2fs_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, + s_kobj); + struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); + + return a->show ? a->show(a, sbi, buf) : 0; +} + +static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t len) +{ + struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, + s_kobj); + struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); + + return a->store ? a->store(a, sbi, buf, len) : 0; +} + +static void f2fs_sb_release(struct kobject *kobj) +{ + struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, + s_kobj); + complete(&sbi->s_kobj_unregister); +} + +#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \ +static struct f2fs_attr f2fs_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .show = _show, \ + .store = _store, \ + .struct_type = _struct_type, \ + .offset = _offset \ +} + +#define F2FS_RW_ATTR(struct_type, struct_name, name, elname) \ + F2FS_ATTR_OFFSET(struct_type, name, 0644, \ + f2fs_sbi_show, f2fs_sbi_store, \ + offsetof(struct struct_name, elname)) + +F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time); +F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time); +F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time); +F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks); +F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level); + +#define ATTR_LIST(name) (&f2fs_attr_##name.attr) +static struct attribute *f2fs_attrs[] = { + ATTR_LIST(gc_min_sleep_time), + ATTR_LIST(gc_max_sleep_time), + ATTR_LIST(gc_no_gc_sleep_time), + ATTR_LIST(gc_idle), + ATTR_LIST(reclaim_segments), + ATTR_LIST(max_small_discards), + ATTR_LIST(batched_trim_sections), + ATTR_LIST(ipu_policy), + ATTR_LIST(min_ipu_util), + ATTR_LIST(min_fsync_blocks), + ATTR_LIST(max_victim_search), + ATTR_LIST(dir_level), + ATTR_LIST(ram_thresh), + NULL, +}; + +static const struct sysfs_ops f2fs_attr_ops = { + .show = f2fs_attr_show, + .store = f2fs_attr_store, +}; + +static struct kobj_type f2fs_ktype = { + .default_attrs = f2fs_attrs, + .sysfs_ops = &f2fs_attr_ops, + .release = f2fs_sb_release, +}; + +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 int parse_options(struct super_block *sb, char *options) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + substring_t args[MAX_OPT_ARGS]; + char *p, *name; + 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: + name = match_strdup(&args[0]); + + if (!name) + return -ENOMEM; + if (strlen(name) == 2 && !strncmp(name, "on", 2)) + set_opt(sbi, BG_GC); + else if (strlen(name) == 3 && !strncmp(name, "off", 3)) + clear_opt(sbi, BG_GC); + else { + kfree(name); + return -EINVAL; + } + kfree(name); + break; + case Opt_disable_roll_forward: + set_opt(sbi, DISABLE_ROLL_FORWARD); + break; + case Opt_norecovery: + /* this option mounts f2fs with ro */ + set_opt(sbi, DISABLE_ROLL_FORWARD); + if (!f2fs_readonly(sb)) + return -EINVAL; + break; + case Opt_discard: + set_opt(sbi, DISCARD); + break; + case Opt_noheap: + set_opt(sbi, NOHEAP); + break; +#ifdef CONFIG_F2FS_FS_XATTR + case Opt_user_xattr: + set_opt(sbi, XATTR_USER); + break; + case Opt_nouser_xattr: + clear_opt(sbi, XATTR_USER); + break; + case Opt_inline_xattr: + set_opt(sbi, INLINE_XATTR); + break; +#else + case Opt_user_xattr: + f2fs_msg(sb, KERN_INFO, + "user_xattr options not supported"); + break; + case Opt_nouser_xattr: + f2fs_msg(sb, KERN_INFO, + "nouser_xattr options not supported"); + break; + case Opt_inline_xattr: + f2fs_msg(sb, KERN_INFO, + "inline_xattr options not supported"); + break; +#endif +#ifdef CONFIG_F2FS_FS_POSIX_ACL + case Opt_acl: + set_opt(sbi, POSIX_ACL); + break; + case Opt_noacl: + clear_opt(sbi, POSIX_ACL); + break; +#else + case Opt_acl: + f2fs_msg(sb, KERN_INFO, "acl options not supported"); + break; + 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; + case Opt_inline_data: + set_opt(sbi, INLINE_DATA); + break; + case Opt_inline_dentry: + set_opt(sbi, INLINE_DENTRY); + break; + case Opt_flush_merge: + set_opt(sbi, FLUSH_MERGE); + break; + case Opt_nobarrier: + set_opt(sbi, NOBARRIER); + break; + case Opt_fastboot: + set_opt(sbi, FASTBOOT); + break; + case Opt_extent_cache: + set_opt(sbi, EXTENT_CACHE); + break; + case Opt_noinline_data: + clear_opt(sbi, INLINE_DATA); + break; + default: + f2fs_msg(sb, KERN_ERR, + "Unrecognized mount option \"%s\" or missing value", + p); + return -EINVAL; + } + } + return 0; +} + +static struct inode *f2fs_alloc_inode(struct super_block *sb) +{ + struct f2fs_inode_info *fi; + + fi = kmem_cache_alloc(f2fs_inode_cachep, GFP_F2FS_ZERO); + if (!fi) + return NULL; + + init_once((void *) fi); + + /* Initialize f2fs-specific inode info */ + fi->vfs_inode.i_version = 1; + atomic_set(&fi->dirty_pages, 0); + fi->i_current_depth = 1; + fi->i_advise = 0; + rwlock_init(&fi->ext_lock); + init_rwsem(&fi->i_sem); + INIT_RADIX_TREE(&fi->inmem_root, GFP_NOFS); + INIT_LIST_HEAD(&fi->inmem_pages); + mutex_init(&fi->inmem_lock); + + set_inode_flag(fi, FI_NEW_INODE); + + if (test_opt(F2FS_SB(sb), INLINE_XATTR)) + set_inode_flag(fi, FI_INLINE_XATTR); + + /* Will be used by directory only */ + fi->i_dir_level = F2FS_SB(sb)->dir_level; + + 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); +} + +/* + * f2fs_dirty_inode() is called from __mark_inode_dirty() + * + * We should call set_dirty_inode to write the dirty inode through write_inode. + */ +static void f2fs_dirty_inode(struct inode *inode, int flags) +{ + set_inode_flag(F2FS_I(inode), FI_DIRTY_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); + + if (sbi->s_proc) { + remove_proc_entry("segment_info", sbi->s_proc); + remove_proc_entry(sb->s_id, f2fs_proc_root); + } + kobject_del(&sbi->s_kobj); + + f2fs_destroy_stats(sbi); + stop_gc_thread(sbi); + + /* + * We don't need to do checkpoint when superblock is clean. + * But, the previous checkpoint was not done by umount, it needs to do + * clean checkpoint again. + */ + if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) || + !is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG)) { + struct cp_control cpc = { + .reason = CP_UMOUNT, + }; + write_checkpoint(sbi, &cpc); + } + + /* + * normally superblock is clean, so we need to release this. + * In addition, EIO will skip do checkpoint, we need this as well. + */ + release_dirty_inode(sbi); + release_discard_addrs(sbi); + + iput(sbi->node_inode); + iput(sbi->meta_inode); + + /* destroy f2fs internal modules */ + destroy_node_manager(sbi); + destroy_segment_manager(sbi); + + kfree(sbi->ckpt); + kobject_put(&sbi->s_kobj); + wait_for_completion(&sbi->s_kobj_unregister); + + 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 (sync) { + struct cp_control cpc; + + cpc.reason = __get_cp_reason(sbi); + + mutex_lock(&sbi->gc_mutex); + write_checkpoint(sbi, &cpc); + mutex_unlock(&sbi->gc_mutex); + } else { + f2fs_balance_fs(sbi); + } + f2fs_trace_ios(NULL, NULL, 1); + + return 0; +} + +static int f2fs_freeze(struct super_block *sb) +{ + int err; + + if (f2fs_readonly(sb)) + 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 - F2FS_RESERVED_NODE_NUM; + buf->f_ffree = buf->f_files - 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 (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC)) + seq_printf(seq, ",background_gc=%s", "on"); + else + seq_printf(seq, ",background_gc=%s", "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"); + if (test_opt(sbi, INLINE_XATTR)) + seq_puts(seq, ",inline_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"); + if (test_opt(sbi, INLINE_DATA)) + seq_puts(seq, ",inline_data"); + else + seq_puts(seq, ",noinline_data"); + if (test_opt(sbi, INLINE_DENTRY)) + seq_puts(seq, ",inline_dentry"); + if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE)) + seq_puts(seq, ",flush_merge"); + if (test_opt(sbi, NOBARRIER)) + seq_puts(seq, ",nobarrier"); + if (test_opt(sbi, FASTBOOT)) + seq_puts(seq, ",fastboot"); + if (test_opt(sbi, EXTENT_CACHE)) + seq_puts(seq, ",extent_cache"); + seq_printf(seq, ",active_logs=%u", sbi->active_logs); + + return 0; +} + +static int segment_info_seq_show(struct seq_file *seq, void *offset) +{ + struct super_block *sb = seq->private; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + unsigned int total_segs = + le32_to_cpu(sbi->raw_super->segment_count_main); + int i; + + seq_puts(seq, "format: segment_type|valid_blocks\n" + "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n"); + + for (i = 0; i < total_segs; i++) { + struct seg_entry *se = get_seg_entry(sbi, i); + + if ((i % 10) == 0) + seq_printf(seq, "%-5d", i); + seq_printf(seq, "%d|%-3u", se->type, + get_valid_blocks(sbi, i, 1)); + if ((i % 10) == 9 || i == (total_segs - 1)) + seq_putc(seq, '\n'); + else + seq_putc(seq, ' '); + } + + return 0; +} + +static int segment_info_open_fs(struct inode *inode, struct file *file) +{ + return single_open(file, segment_info_seq_show, PDE_DATA(inode)); +} + +static const struct file_operations f2fs_seq_segment_info_fops = { + .owner = THIS_MODULE, + .open = segment_info_open_fs, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int f2fs_remount(struct super_block *sb, int *flags, char *data) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct f2fs_mount_info org_mount_opt; + int err, active_logs; + bool need_restart_gc = false; + bool need_stop_gc = false; + + sync_filesystem(sb); + + /* + * Save the old mount options in case we + * need to restore them. + */ + org_mount_opt = sbi->mount_opt; + active_logs = sbi->active_logs; + + sbi->mount_opt.opt = 0; + sbi->active_logs = NR_CURSEG_TYPE; + + /* parse mount options */ + err = parse_options(sb, data); + if (err) + goto restore_opts; + + /* + * Previous and new state of filesystem is RO, + * so skip checking GC and FLUSH_MERGE conditions. + */ + if (f2fs_readonly(sb) && (*flags & MS_RDONLY)) + goto skip; + + /* + * We stop the GC thread if FS is mounted as RO + * or if background_gc = off is passed in mount + * option. Also sync the filesystem. + */ + if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) { + if (sbi->gc_thread) { + stop_gc_thread(sbi); + f2fs_sync_fs(sb, 1); + need_restart_gc = true; + } + } else if (!sbi->gc_thread) { + err = start_gc_thread(sbi); + if (err) + goto restore_opts; + need_stop_gc = true; + } + + /* + * We stop issue flush thread if FS is mounted as RO + * or if flush_merge is not passed in mount option. + */ + if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) { + destroy_flush_cmd_control(sbi); + } else if (!SM_I(sbi)->cmd_control_info) { + err = create_flush_cmd_control(sbi); + if (err) + goto restore_gc; + } +skip: + /* Update the POSIXACL Flag */ + sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | + (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0); + return 0; +restore_gc: + if (need_restart_gc) { + if (start_gc_thread(sbi)) + f2fs_msg(sbi->sb, KERN_WARNING, + "background gc thread has stopped"); + } else if (need_stop_gc) { + stop_gc_thread(sbi); + } +restore_opts: + sbi->mount_opt = org_mount_opt; + sbi->active_logs = active_logs; + return err; +} + +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, + .dirty_inode = f2fs_dirty_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, + .remount_fs = f2fs_remount, +}; + +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 (check_nid_range(sbi, ino)) + 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 (unlikely(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 loff_t max_file_size(unsigned bits) +{ + loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS); + 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; + } + + /* Currently, support 512/1024/2048/4096 bytes sector size */ + if (le32_to_cpu(raw_super->log_sectorsize) > + F2FS_MAX_LOG_SECTOR_SIZE || + le32_to_cpu(raw_super->log_sectorsize) < + F2FS_MIN_LOG_SECTOR_SIZE) { + f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize (%u)", + le32_to_cpu(raw_super->log_sectorsize)); + return 1; + } + if (le32_to_cpu(raw_super->log_sectors_per_block) + + le32_to_cpu(raw_super->log_sectorsize) != + F2FS_MAX_LOG_SECTOR_SIZE) { + f2fs_msg(sb, KERN_INFO, + "Invalid log sectors per block(%u) log sectorsize(%u)", + le32_to_cpu(raw_super->log_sectors_per_block), + le32_to_cpu(raw_super->log_sectorsize)); + 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); + + 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 (unlikely(fsmeta >= total)) + return 1; + + if (unlikely(f2fs_cp_error(sbi))) { + 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; + sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH; + + for (i = 0; i < NR_COUNT_TYPE; i++) + atomic_set(&sbi->nr_pages[i], 0); + + sbi->dir_level = DEF_DIR_LEVEL; + clear_sbi_flag(sbi, SBI_NEED_FSCK); +} + +/* + * Read f2fs raw super block. + * Because we have two copies of super block, so read the first one at first, + * if the first one is invalid, move to read the second one. + */ +static int read_raw_super_block(struct super_block *sb, + struct f2fs_super_block **raw_super, + struct buffer_head **raw_super_buf) +{ + int block = 0; + +retry: + *raw_super_buf = sb_bread(sb, block); + if (!*raw_super_buf) { + f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock", + block + 1); + if (block == 0) { + block++; + goto retry; + } else { + 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)) { + brelse(*raw_super_buf); + f2fs_msg(sb, KERN_ERR, + "Can't find valid F2FS filesystem in %dth superblock", + block + 1); + if (block == 0) { + block++; + goto retry; + } else { + return -EINVAL; + } + } + + return 0; +} + +static int f2fs_fill_super(struct super_block *sb, void *data, int silent) +{ + struct f2fs_sb_info *sbi; + struct f2fs_super_block *raw_super = NULL; + struct buffer_head *raw_super_buf; + struct inode *root; + long err = -EINVAL; + bool retry = true, need_fsck = false; + char *options = NULL; + int i; + +try_onemore: + /* 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 (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) { + f2fs_msg(sb, KERN_ERR, "unable to set blocksize"); + goto free_sbi; + } + + err = read_raw_super_block(sb, &raw_super, &raw_super_buf); + if (err) + goto free_sbi; + + sb->s_fs_info = sbi; + /* init some FS parameters */ + sbi->active_logs = NR_CURSEG_TYPE; + + set_opt(sbi, BG_GC); + set_opt(sbi, INLINE_DATA); + +#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 */ + options = kstrdup((const char *)data, GFP_KERNEL); + if (data && !options) { + err = -ENOMEM; + goto free_sb_buf; + } + + err = parse_options(sb, options); + if (err) + goto free_options; + + 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_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); + init_rwsem(&sbi->node_write); + clear_sbi_flag(sbi, SBI_POR_DOING); + spin_lock_init(&sbi->stat_lock); + + init_rwsem(&sbi->read_io.io_rwsem); + sbi->read_io.sbi = sbi; + sbi->read_io.bio = NULL; + for (i = 0; i < NR_PAGE_TYPE; i++) { + init_rwsem(&sbi->write_io[i].io_rwsem); + sbi->write_io[i].sbi = sbi; + sbi->write_io[i].bio = NULL; + } + + init_rwsem(&sbi->cp_rwsem); + init_waitqueue_head(&sbi->cp_wait); + 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_options; + } + + 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_extent_cache_info(sbi); + + init_ino_entry_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 */ + recover_orphan_inodes(sbi); + + /* 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) { + iput(root); + err = -EINVAL; + goto free_node_inode; + } + + sb->s_root = d_make_root(root); /* allocate root dentry */ + if (!sb->s_root) { + err = -ENOMEM; + goto free_root_inode; + } + + err = f2fs_build_stats(sbi); + if (err) + goto free_root_inode; + + if (f2fs_proc_root) + sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root); + + if (sbi->s_proc) + proc_create_data("segment_info", S_IRUGO, sbi->s_proc, + &f2fs_seq_segment_info_fops, sb); + + 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"); + } + + sbi->s_kobj.kset = f2fs_kset; + init_completion(&sbi->s_kobj_unregister); + err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL, + "%s", sb->s_id); + if (err) + goto free_proc; + + /* recover fsynced data */ + if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) { + /* + * mount should be failed, when device has readonly mode, and + * previous checkpoint was not done by clean system shutdown. + */ + if (bdev_read_only(sb->s_bdev) && + !is_set_ckpt_flags(sbi->ckpt, CP_UMOUNT_FLAG)) { + err = -EROFS; + goto free_kobj; + } + + if (need_fsck) + set_sbi_flag(sbi, SBI_NEED_FSCK); + + err = recover_fsync_data(sbi); + if (err) { + need_fsck = true; + f2fs_msg(sb, KERN_ERR, + "Cannot recover all fsync data errno=%ld", err); + goto free_kobj; + } + } + + /* + * If filesystem is not mounted as read-only then + * do start the gc_thread. + */ + if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) { + /* After POR, we can run background GC thread.*/ + err = start_gc_thread(sbi); + if (err) + goto free_kobj; + } + kfree(options); + return 0; + +free_kobj: + kobject_del(&sbi->s_kobj); +free_proc: + if (sbi->s_proc) { + remove_proc_entry("segment_info", sbi->s_proc); + remove_proc_entry(sb->s_id, f2fs_proc_root); + } + f2fs_destroy_stats(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_options: + kfree(options); +free_sb_buf: + brelse(raw_super_buf); +free_sbi: + kfree(sbi); + + /* give only one another chance */ + if (retry) { + retry = false; + shrink_dcache_sb(sb); + goto try_onemore; + } + 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 void kill_f2fs_super(struct super_block *sb) +{ + if (sb->s_root) + set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE); + kill_block_super(sb); +} + +static struct file_system_type f2fs_fs_type = { + .owner = THIS_MODULE, + .name = "f2fs", + .mount = f2fs_mount, + .kill_sb = kill_f2fs_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)); + if (!f2fs_inode_cachep) + 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; + + f2fs_build_trace_ios(); + + err = init_inodecache(); + if (err) + goto fail; + err = create_node_manager_caches(); + if (err) + goto free_inodecache; + err = create_segment_manager_caches(); + if (err) + goto free_node_manager_caches; + err = create_checkpoint_caches(); + if (err) + goto free_segment_manager_caches; + err = create_extent_cache(); + if (err) + goto free_checkpoint_caches; + f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj); + if (!f2fs_kset) { + err = -ENOMEM; + goto free_extent_cache; + } + err = register_filesystem(&f2fs_fs_type); + if (err) + goto free_kset; + f2fs_create_root_stats(); + f2fs_proc_root = proc_mkdir("fs/f2fs", NULL); + return 0; + +free_kset: + kset_unregister(f2fs_kset); +free_extent_cache: + destroy_extent_cache(); +free_checkpoint_caches: + destroy_checkpoint_caches(); +free_segment_manager_caches: + destroy_segment_manager_caches(); +free_node_manager_caches: + destroy_node_manager_caches(); +free_inodecache: + destroy_inodecache(); +fail: + return err; +} + +static void __exit exit_f2fs_fs(void) +{ + remove_proc_entry("fs/f2fs", NULL); + f2fs_destroy_root_stats(); + unregister_filesystem(&f2fs_fs_type); + destroy_extent_cache(); + destroy_checkpoint_caches(); + destroy_segment_manager_caches(); + destroy_node_manager_caches(); + destroy_inodecache(); + kset_unregister(f2fs_kset); + f2fs_destroy_trace_ios(); +} + +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"); diff --git a/kernel/fs/f2fs/trace.c b/kernel/fs/f2fs/trace.c new file mode 100644 index 000000000..875aa8179 --- /dev/null +++ b/kernel/fs/f2fs/trace.c @@ -0,0 +1,159 @@ +/* + * f2fs IO tracer + * + * Copyright (c) 2014 Motorola Mobility + * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.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/f2fs_fs.h> +#include <linux/sched.h> +#include <linux/radix-tree.h> + +#include "f2fs.h" +#include "trace.h" + +static RADIX_TREE(pids, GFP_ATOMIC); +static spinlock_t pids_lock; +static struct last_io_info last_io; + +static inline void __print_last_io(void) +{ + if (!last_io.len) + return; + + trace_printk("%3x:%3x %4x %-16s %2x %5x %12x %4x\n", + last_io.major, last_io.minor, + last_io.pid, "----------------", + last_io.type, + last_io.fio.rw, last_io.fio.blk_addr, + last_io.len); + memset(&last_io, 0, sizeof(last_io)); +} + +static int __file_type(struct inode *inode, pid_t pid) +{ + if (f2fs_is_atomic_file(inode)) + return __ATOMIC_FILE; + else if (f2fs_is_volatile_file(inode)) + return __VOLATILE_FILE; + else if (S_ISDIR(inode->i_mode)) + return __DIR_FILE; + else if (inode->i_ino == F2FS_NODE_INO(F2FS_I_SB(inode))) + return __NODE_FILE; + else if (inode->i_ino == F2FS_META_INO(F2FS_I_SB(inode))) + return __META_FILE; + else if (pid) + return __NORMAL_FILE; + else + return __MISC_FILE; +} + +void f2fs_trace_pid(struct page *page) +{ + struct inode *inode = page->mapping->host; + pid_t pid = task_pid_nr(current); + void *p; + + page->private = pid; + + if (radix_tree_preload(GFP_NOFS)) + return; + + spin_lock(&pids_lock); + p = radix_tree_lookup(&pids, pid); + if (p == current) + goto out; + if (p) + radix_tree_delete(&pids, pid); + + f2fs_radix_tree_insert(&pids, pid, current); + + trace_printk("%3x:%3x %4x %-16s\n", + MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), + pid, current->comm); +out: + spin_unlock(&pids_lock); + radix_tree_preload_end(); +} + +void f2fs_trace_ios(struct page *page, struct f2fs_io_info *fio, int flush) +{ + struct inode *inode; + pid_t pid; + int major, minor; + + if (flush) { + __print_last_io(); + return; + } + + inode = page->mapping->host; + pid = page_private(page); + + major = MAJOR(inode->i_sb->s_dev); + minor = MINOR(inode->i_sb->s_dev); + + if (last_io.major == major && last_io.minor == minor && + last_io.pid == pid && + last_io.type == __file_type(inode, pid) && + last_io.fio.rw == fio->rw && + last_io.fio.blk_addr + last_io.len == fio->blk_addr) { + last_io.len++; + return; + } + + __print_last_io(); + + last_io.major = major; + last_io.minor = minor; + last_io.pid = pid; + last_io.type = __file_type(inode, pid); + last_io.fio = *fio; + last_io.len = 1; + return; +} + +void f2fs_build_trace_ios(void) +{ + spin_lock_init(&pids_lock); +} + +#define PIDVEC_SIZE 128 +static unsigned int gang_lookup_pids(pid_t *results, unsigned long first_index, + unsigned int max_items) +{ + struct radix_tree_iter iter; + void **slot; + unsigned int ret = 0; + + if (unlikely(!max_items)) + return 0; + + radix_tree_for_each_slot(slot, &pids, &iter, first_index) { + results[ret] = iter.index; + if (++ret == PIDVEC_SIZE) + break; + } + return ret; +} + +void f2fs_destroy_trace_ios(void) +{ + pid_t pid[PIDVEC_SIZE]; + pid_t next_pid = 0; + unsigned int found; + + spin_lock(&pids_lock); + while ((found = gang_lookup_pids(pid, next_pid, PIDVEC_SIZE))) { + unsigned idx; + + next_pid = pid[found - 1] + 1; + for (idx = 0; idx < found; idx++) + radix_tree_delete(&pids, pid[idx]); + } + spin_unlock(&pids_lock); +} diff --git a/kernel/fs/f2fs/trace.h b/kernel/fs/f2fs/trace.h new file mode 100644 index 000000000..1041dbeb5 --- /dev/null +++ b/kernel/fs/f2fs/trace.h @@ -0,0 +1,46 @@ +/* + * f2fs IO tracer + * + * Copyright (c) 2014 Motorola Mobility + * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.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_TRACE_H__ +#define __F2FS_TRACE_H__ + +#ifdef CONFIG_F2FS_IO_TRACE +#include <trace/events/f2fs.h> + +enum file_type { + __NORMAL_FILE, + __DIR_FILE, + __NODE_FILE, + __META_FILE, + __ATOMIC_FILE, + __VOLATILE_FILE, + __MISC_FILE, +}; + +struct last_io_info { + int major, minor; + pid_t pid; + enum file_type type; + struct f2fs_io_info fio; + block_t len; +}; + +extern void f2fs_trace_pid(struct page *); +extern void f2fs_trace_ios(struct page *, struct f2fs_io_info *, int); +extern void f2fs_build_trace_ios(void); +extern void f2fs_destroy_trace_ios(void); +#else +#define f2fs_trace_pid(p) +#define f2fs_trace_ios(p, i, n) +#define f2fs_build_trace_ios() +#define f2fs_destroy_trace_ios() + +#endif +#endif /* __F2FS_TRACE_H__ */ diff --git a/kernel/fs/f2fs/xattr.c b/kernel/fs/f2fs/xattr.c new file mode 100644 index 000000000..9757f65a0 --- /dev/null +++ b/kernel/fs/f2fs/xattr.c @@ -0,0 +1,618 @@ +/* + * 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 <linux/security.h> +#include <linux/posix_acl_xattr.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 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; + case F2FS_XATTR_INDEX_SECURITY: + prefix = XATTR_SECURITY_PREFIX; + prefix_len = XATTR_SECURITY_PREFIX_LEN; + break; + default: + return -EINVAL; + } + + total_len = prefix_len + len + 1; + if (list && total_len <= list_size) { + memcpy(list, prefix, prefix_len); + memcpy(list + prefix_len, name, len); + list[prefix_len + 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; + case F2FS_XATTR_INDEX_SECURITY: + break; + default: + return -EINVAL; + } + if (strcmp(name, "") == 0) + return -EINVAL; + return f2fs_getxattr(d_inode(dentry), type, name, buffer, size, NULL); +} + +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; + case F2FS_XATTR_INDEX_SECURITY: + break; + default: + return -EINVAL; + } + if (strcmp(name, "") == 0) + return -EINVAL; + + return f2fs_setxattr(d_inode(dentry), type, name, + value, size, NULL, flags); +} + +static size_t f2fs_xattr_advise_list(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t 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 = d_inode(dentry); + + if (strcmp(name, "") != 0) + return -EINVAL; + + if (buffer) + *((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 = d_inode(dentry); + + 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; + mark_inode_dirty(inode); + return 0; +} + +#ifdef CONFIG_F2FS_FS_SECURITY +static int f2fs_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *page) +{ + const struct xattr *xattr; + int err = 0; + + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + err = f2fs_setxattr(inode, F2FS_XATTR_INDEX_SECURITY, + xattr->name, xattr->value, + xattr->value_len, (struct page *)page, 0); + if (err < 0) + break; + } + return err; +} + +int f2fs_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr, struct page *ipage) +{ + return security_inode_init_security(inode, dir, qstr, + &f2fs_initxattrs, ipage); +} +#endif + +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, +}; + +const struct xattr_handler f2fs_xattr_security_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .flags = F2FS_XATTR_INDEX_SECURITY, + .list = f2fs_xattr_generic_list, + .get = f2fs_xattr_generic_get, + .set = f2fs_xattr_generic_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] = &posix_acl_access_xattr_handler, + [F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler, +#endif + [F2FS_XATTR_INDEX_TRUSTED] = &f2fs_xattr_trusted_handler, +#ifdef CONFIG_F2FS_FS_SECURITY + [F2FS_XATTR_INDEX_SECURITY] = &f2fs_xattr_security_handler, +#endif + [F2FS_XATTR_INDEX_ADVISE] = &f2fs_xattr_advise_handler, +}; + +const struct xattr_handler *f2fs_xattr_handlers[] = { + &f2fs_xattr_user_handler, +#ifdef CONFIG_F2FS_FS_POSIX_ACL + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, +#endif + &f2fs_xattr_trusted_handler, +#ifdef CONFIG_F2FS_FS_SECURITY + &f2fs_xattr_security_handler, +#endif + &f2fs_xattr_advise_handler, + NULL, +}; + +static inline const struct xattr_handler *f2fs_xattr_handler(int index) +{ + const struct xattr_handler *handler = NULL; + + if (index > 0 && index < ARRAY_SIZE(f2fs_xattr_handler_map)) + handler = f2fs_xattr_handler_map[index]; + return handler; +} + +static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index, + size_t len, const char *name) +{ + struct f2fs_xattr_entry *entry; + + list_for_each_xattr(entry, base_addr) { + if (entry->e_name_index != index) + continue; + if (entry->e_name_len != len) + continue; + if (!memcmp(entry->e_name, name, len)) + break; + } + return entry; +} + +static void *read_all_xattrs(struct inode *inode, struct page *ipage) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_xattr_header *header; + size_t size = PAGE_SIZE, inline_size = 0; + void *txattr_addr; + + inline_size = inline_xattr_size(inode); + + txattr_addr = kzalloc(inline_size + size, GFP_F2FS_ZERO); + if (!txattr_addr) + return NULL; + + /* read from inline xattr */ + if (inline_size) { + struct page *page = NULL; + void *inline_addr; + + if (ipage) { + inline_addr = inline_xattr_addr(ipage); + } else { + page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(page)) + goto fail; + inline_addr = inline_xattr_addr(page); + } + memcpy(txattr_addr, inline_addr, inline_size); + f2fs_put_page(page, 1); + } + + /* read from xattr node block */ + if (F2FS_I(inode)->i_xattr_nid) { + struct page *xpage; + void *xattr_addr; + + /* The inode already has an extended attribute block. */ + xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid); + if (IS_ERR(xpage)) + goto fail; + + xattr_addr = page_address(xpage); + memcpy(txattr_addr + inline_size, xattr_addr, PAGE_SIZE); + f2fs_put_page(xpage, 1); + } + + header = XATTR_HDR(txattr_addr); + + /* never been allocated xattrs */ + if (le32_to_cpu(header->h_magic) != F2FS_XATTR_MAGIC) { + header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC); + header->h_refcount = cpu_to_le32(1); + } + return txattr_addr; +fail: + kzfree(txattr_addr); + return NULL; +} + +static inline int write_all_xattrs(struct inode *inode, __u32 hsize, + void *txattr_addr, struct page *ipage) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + size_t inline_size = 0; + void *xattr_addr; + struct page *xpage; + nid_t new_nid = 0; + int err; + + inline_size = inline_xattr_size(inode); + + if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid) + if (!alloc_nid(sbi, &new_nid)) + return -ENOSPC; + + /* write to inline xattr */ + if (inline_size) { + struct page *page = NULL; + void *inline_addr; + + if (ipage) { + inline_addr = inline_xattr_addr(ipage); + f2fs_wait_on_page_writeback(ipage, NODE); + } else { + page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(page)) { + alloc_nid_failed(sbi, new_nid); + return PTR_ERR(page); + } + inline_addr = inline_xattr_addr(page); + f2fs_wait_on_page_writeback(page, NODE); + } + memcpy(inline_addr, txattr_addr, inline_size); + f2fs_put_page(page, 1); + + /* no need to use xattr node block */ + if (hsize <= inline_size) { + err = truncate_xattr_node(inode, ipage); + alloc_nid_failed(sbi, new_nid); + return err; + } + } + + /* write to xattr node block */ + if (F2FS_I(inode)->i_xattr_nid) { + xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid); + if (IS_ERR(xpage)) { + alloc_nid_failed(sbi, new_nid); + return PTR_ERR(xpage); + } + f2fs_bug_on(sbi, new_nid); + f2fs_wait_on_page_writeback(xpage, NODE); + } else { + struct dnode_of_data dn; + set_new_dnode(&dn, inode, NULL, NULL, new_nid); + xpage = new_node_page(&dn, XATTR_NODE_OFFSET, ipage); + if (IS_ERR(xpage)) { + alloc_nid_failed(sbi, new_nid); + return PTR_ERR(xpage); + } + alloc_nid_done(sbi, new_nid); + } + + xattr_addr = page_address(xpage); + memcpy(xattr_addr, txattr_addr + inline_size, PAGE_SIZE - + sizeof(struct node_footer)); + set_page_dirty(xpage); + f2fs_put_page(xpage, 1); + + /* need to checkpoint during fsync */ + F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi)); + return 0; +} + +int f2fs_getxattr(struct inode *inode, int index, const char *name, + void *buffer, size_t buffer_size, struct page *ipage) +{ + struct f2fs_xattr_entry *entry; + void *base_addr; + int error = 0; + size_t size, len; + + if (name == NULL) + return -EINVAL; + + len = strlen(name); + if (len > F2FS_NAME_LEN) + return -ERANGE; + + base_addr = read_all_xattrs(inode, ipage); + if (!base_addr) + return -ENOMEM; + + entry = __find_xattr(base_addr, index, len, name); + if (IS_XATTR_LAST_ENTRY(entry)) { + error = -ENODATA; + goto cleanup; + } + + size = le16_to_cpu(entry->e_value_size); + + if (buffer && size > buffer_size) { + error = -ERANGE; + goto cleanup; + } + + if (buffer) { + char *pval = entry->e_name + entry->e_name_len; + memcpy(buffer, pval, size); + } + error = size; + +cleanup: + kzfree(base_addr); + return error; +} + +ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) +{ + struct inode *inode = d_inode(dentry); + struct f2fs_xattr_entry *entry; + void *base_addr; + int error = 0; + size_t rest = buffer_size; + + base_addr = read_all_xattrs(inode, NULL); + if (!base_addr) + return -ENOMEM; + + 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: + kzfree(base_addr); + return error; +} + +static int __f2fs_setxattr(struct inode *inode, int index, + const char *name, const void *value, size_t size, + struct page *ipage, int flags) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_xattr_entry *here, *last; + void *base_addr; + int found, newsize; + size_t len; + __u32 new_hsize; + int error = -ENOMEM; + + if (name == NULL) + return -EINVAL; + + if (value == NULL) + size = 0; + + len = strlen(name); + + if (len > F2FS_NAME_LEN || size > MAX_VALUE_LEN(inode)) + return -ERANGE; + + base_addr = read_all_xattrs(inode, ipage); + if (!base_addr) + goto exit; + + /* find entry with wanted name. */ + here = __find_xattr(base_addr, index, len, name); + + found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1; + + if ((flags & XATTR_REPLACE) && !found) { + error = -ENODATA; + goto exit; + } else if ((flags & XATTR_CREATE) && found) { + error = -EEXIST; + goto exit; + } + + last = here; + while (!IS_XATTR_LAST_ENTRY(last)) + last = XATTR_NEXT_ENTRY(last); + + newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + len + size); + + /* 1. Check space */ + if (value) { + int free; + /* + * If value is NULL, it is remove operation. + * In case of update operation, we calculate free. + */ + free = MIN_OFFSET(inode) - ((char *)last - (char *)base_addr); + if (found) + free = free + ENTRY_SIZE(here); + + if (unlikely(free < newsize)) { + error = -ENOSPC; + goto exit; + } + } + + /* 2. Remove old entry */ + if (found) { + /* + * If entry is found, remove old entry. + * If not found, remove operation is not needed. + */ + struct f2fs_xattr_entry *next = XATTR_NEXT_ENTRY(here); + int oldsize = ENTRY_SIZE(here); + + memmove(here, next, (char *)last - (char *)next); + last = (struct f2fs_xattr_entry *)((char *)last - oldsize); + memset(last, 0, oldsize); + } + + new_hsize = (char *)last - (char *)base_addr; + + /* 3. Write new entry */ + if (value) { + char *pval; + /* + * Before we come here, old entry is removed. + * We just write new entry. + */ + memset(last, 0, newsize); + last->e_name_index = index; + last->e_name_len = len; + memcpy(last->e_name, name, len); + pval = last->e_name + len; + memcpy(pval, value, size); + last->e_value_size = cpu_to_le16(size); + new_hsize += newsize; + } + + error = write_all_xattrs(inode, new_hsize, base_addr, ipage); + if (error) + goto exit; + + 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); + } + + if (ipage) + update_inode(inode, ipage); + else + update_inode_page(inode); +exit: + kzfree(base_addr); + return error; +} + +int f2fs_setxattr(struct inode *inode, int index, const char *name, + const void *value, size_t size, + struct page *ipage, int flags) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int err; + + /* this case is only from init_inode_metadata */ + if (ipage) + return __f2fs_setxattr(inode, index, name, value, + size, ipage, flags); + f2fs_balance_fs(sbi); + + f2fs_lock_op(sbi); + /* protect xattr_ver */ + down_write(&F2FS_I(inode)->i_sem); + err = __f2fs_setxattr(inode, index, name, value, size, ipage, flags); + up_write(&F2FS_I(inode)->i_sem); + f2fs_unlock_op(sbi); + + return err; +} diff --git a/kernel/fs/f2fs/xattr.h b/kernel/fs/f2fs/xattr.h new file mode 100644 index 000000000..969d792ca --- /dev/null +++ b/kernel/fs/f2fs/xattr.h @@ -0,0 +1,152 @@ +/* + * 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(i) XATTR_ALIGN(inline_xattr_size(i) + PAGE_SIZE - \ + sizeof(struct node_footer) - sizeof(__u32)) + +#define MAX_VALUE_LEN(i) (MIN_OFFSET(i) - \ + sizeof(struct f2fs_xattr_header) - \ + sizeof(struct f2fs_xattr_entry)) + +/* + * On-disk structure of f2fs_xattr + * We use inline xattrs space + 1 block for xattr. + * + * +--------------------+ + * | f2fs_xattr_header | + * | | + * +--------------------+ + * | f2fs_xattr_entry | + * | .e_name_index = 1 | + * | .e_name_len = 3 | + * | .e_value_size = 14 | + * | .e_name = "foo" | + * | "value_of_xattr" |<- value_offs = e_name + e_name_len + * +--------------------+ + * | f2fs_xattr_entry | + * | .e_name_index = 4 | + * | .e_name = "bar" | + * +--------------------+ + * | | + * | Free | + * | | + * +--------------------+<- MIN_OFFSET + * | node_footer | + * | (nid, ino, offset) | + * +--------------------+ + * + **/ + +#ifdef CONFIG_F2FS_FS_XATTR +extern const struct xattr_handler f2fs_xattr_user_handler; +extern const struct xattr_handler f2fs_xattr_trusted_handler; +extern const struct xattr_handler f2fs_xattr_advise_handler; +extern const struct xattr_handler f2fs_xattr_security_handler; + +extern const struct xattr_handler *f2fs_xattr_handlers[]; + +extern int f2fs_setxattr(struct inode *, int, const char *, + const void *, size_t, struct page *, int); +extern int f2fs_getxattr(struct inode *, int, const char *, void *, + size_t, struct page *); +extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t); +#else + +#define f2fs_xattr_handlers NULL +static inline int f2fs_setxattr(struct inode *inode, int index, + const char *name, const void *value, size_t size, int flags) +{ + return -EOPNOTSUPP; +} +static inline int f2fs_getxattr(struct inode *inode, int index, + const char *name, void *buffer, + size_t buffer_size, struct page *dpage) +{ + return -EOPNOTSUPP; +} +static inline ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, + size_t buffer_size) +{ + return -EOPNOTSUPP; +} +#endif + +#ifdef CONFIG_F2FS_FS_SECURITY +extern int f2fs_init_security(struct inode *, struct inode *, + const struct qstr *, struct page *); +#else +static inline int f2fs_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr, struct page *ipage) +{ + return 0; +} +#endif +#endif /* __F2FS_XATTR_H__ */ |