f2fs: catch up to v4.4-rc1
The last patch is:
commit beaa57dd986d4f398728c060692fc2452895cfd8
Author: Chao Yu <chao2.yu@samsung.com>
Date: Thu Oct 22 18:24:12 2015 +0800
f2fs: fix to skip shrinking extent nodes
In f2fs_shrink_extent_tree we should stop shrink flow if we have already
shrunk enough nodes in extent cache.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
new file mode 100644
index 0000000..b102b43
--- /dev/null
+++ b/Documentation/filesystems/f2fs.txt
@@ -0,0 +1,579 @@
+================================================================================
+WHAT IS Flash-Friendly File System (F2FS)?
+================================================================================
+
+NAND flash memory-based storage devices, such as SSD, eMMC, and SD cards, have
+been equipped on a variety systems ranging from mobile to server systems. Since
+they are known to have different characteristics from the conventional rotating
+disks, a file system, an upper layer to the storage device, should adapt to the
+changes from the sketch in the design level.
+
+F2FS is a file system exploiting NAND flash memory-based storage devices, which
+is based on Log-structured File System (LFS). The design has been focused on
+addressing the fundamental issues in LFS, which are snowball effect of wandering
+tree and high cleaning overhead.
+
+Since a NAND flash memory-based storage device shows different characteristic
+according to its internal geometry or flash memory management scheme, namely FTL,
+F2FS and its tools support various parameters not only for configuring on-disk
+layout, but also for selecting allocation and cleaning algorithms.
+
+The following git tree provides the file system formatting tool (mkfs.f2fs),
+a consistency checking tool (fsck.f2fs), and a debugging tool (dump.f2fs).
+>> git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs-tools.git
+
+For reporting bugs and sending patches, please use the following mailing list:
+>> linux-f2fs-devel@lists.sourceforge.net
+
+================================================================================
+BACKGROUND AND DESIGN ISSUES
+================================================================================
+
+Log-structured File System (LFS)
+--------------------------------
+"A log-structured file system writes all modifications to disk sequentially in
+a log-like structure, thereby speeding up both file writing and crash recovery.
+The log is the only structure on disk; it contains indexing information so that
+files can be read back from the log efficiently. In order to maintain large free
+areas on disk for fast writing, we divide the log into segments and use a
+segment cleaner to compress the live information from heavily fragmented
+segments." from Rosenblum, M. and Ousterhout, J. K., 1992, "The design and
+implementation of a log-structured file system", ACM Trans. Computer Systems
+10, 1, 26–52.
+
+Wandering Tree Problem
+----------------------
+In LFS, when a file data is updated and written to the end of log, its direct
+pointer block is updated due to the changed location. Then the indirect pointer
+block is also updated due to the direct pointer block update. In this manner,
+the upper index structures such as inode, inode map, and checkpoint block are
+also updated recursively. This problem is called as wandering tree problem [1],
+and in order to enhance the performance, it should eliminate or relax the update
+propagation as much as possible.
+
+[1] Bityutskiy, A. 2005. JFFS3 design issues. http://www.linux-mtd.infradead.org/
+
+Cleaning Overhead
+-----------------
+Since LFS is based on out-of-place writes, it produces so many obsolete blocks
+scattered across the whole storage. In order to serve new empty log space, it
+needs to reclaim these obsolete blocks seamlessly to users. This job is called
+as a cleaning process.
+
+The process consists of three operations as follows.
+1. A victim segment is selected through referencing segment usage table.
+2. It loads parent index structures of all the data in the victim identified by
+ segment summary blocks.
+3. It checks the cross-reference between the data and its parent index structure.
+4. It moves valid data selectively.
+
+This cleaning job may cause unexpected long delays, so the most important goal
+is to hide the latencies to users. And also definitely, it should reduce the
+amount of valid data to be moved, and move them quickly as well.
+
+================================================================================
+KEY FEATURES
+================================================================================
+
+Flash Awareness
+---------------
+- Enlarge the random write area for better performance, but provide the high
+ spatial locality
+- Align FS data structures to the operational units in FTL as best efforts
+
+Wandering Tree Problem
+----------------------
+- Use a term, “node”, that represents inodes as well as various pointer blocks
+- Introduce Node Address Table (NAT) containing the locations of all the “node”
+ blocks; this will cut off the update propagation.
+
+Cleaning Overhead
+-----------------
+- Support a background cleaning process
+- Support greedy and cost-benefit algorithms for victim selection policies
+- Support multi-head logs for static/dynamic hot and cold data separation
+- Introduce adaptive logging for efficient block allocation
+
+================================================================================
+MOUNT OPTIONS
+================================================================================
+
+background_gc=%s Turn on/off cleaning operations, namely garbage
+ collection, triggered in background when I/O subsystem is
+ idle. If background_gc=on, it will turn on the garbage
+ collection and if background_gc=off, garbage collection
+ will be truned off. If background_gc=sync, it will turn
+ on synchronous garbage collection running in background.
+ Default value for this option is on. So garbage
+ collection is on by default.
+disable_roll_forward Disable the roll-forward recovery routine
+norecovery Disable the roll-forward recovery routine, mounted read-
+ only (i.e., -o ro,disable_roll_forward)
+discard Issue discard/TRIM commands when a segment is cleaned.
+no_heap Disable heap-style segment allocation which finds free
+ segments for data from the beginning of main area, while
+ for node from the end of main area.
+nouser_xattr Disable Extended User Attributes. Note: xattr is enabled
+ by default if CONFIG_F2FS_FS_XATTR is selected.
+noacl Disable POSIX Access Control List. Note: acl is enabled
+ by default if CONFIG_F2FS_FS_POSIX_ACL is selected.
+active_logs=%u Support configuring the number of active logs. In the
+ current design, f2fs supports only 2, 4, and 6 logs.
+ Default number is 6.
+disable_ext_identify Disable the extension list configured by mkfs, so f2fs
+ does not aware of cold files such as media files.
+inline_xattr Enable the inline xattrs feature.
+inline_data Enable the inline data feature: New created small(<~3.4k)
+ files can be written into inode block.
+inline_dentry Enable the inline dir feature: data in new created
+ directory entries can be written into inode block. The
+ space of inode block which is used to store inline
+ dentries is limited to ~3.4k.
+flush_merge Merge concurrent cache_flush commands as much as possible
+ to eliminate redundant command issues. If the underlying
+ device handles the cache_flush command relatively slowly,
+ recommend to enable this option.
+nobarrier This option can be used if underlying storage guarantees
+ its cached data should be written to the novolatile area.
+ If this option is set, no cache_flush commands are issued
+ but f2fs still guarantees the write ordering of all the
+ data writes.
+fastboot This option is used when a system wants to reduce mount
+ time as much as possible, even though normal performance
+ can be sacrificed.
+extent_cache Enable an extent cache based on rb-tree, it can cache
+ as many as extent which map between contiguous logical
+ address and physical address per inode, resulting in
+ increasing the cache hit ratio. Set by default.
+noextent_cache Diable an extent cache based on rb-tree explicitly, see
+ the above extent_cache mount option.
+noinline_data Disable the inline data feature, inline data feature is
+ enabled by default.
+
+================================================================================
+DEBUGFS ENTRIES
+================================================================================
+
+/sys/kernel/debug/f2fs/ contains information about all the partitions mounted as
+f2fs. Each file shows the whole f2fs information.
+
+/sys/kernel/debug/f2fs/status includes:
+ - major file system information managed by f2fs currently
+ - average SIT information about whole segments
+ - current memory footprint consumed by f2fs.
+
+================================================================================
+SYSFS ENTRIES
+================================================================================
+
+Information about mounted f2f2 file systems can be found in
+/sys/fs/f2fs. Each mounted filesystem will have a directory in
+/sys/fs/f2fs based on its device name (i.e., /sys/fs/f2fs/sda).
+The files in each per-device directory are shown in table below.
+
+Files in /sys/fs/f2fs/<devname>
+(see also Documentation/ABI/testing/sysfs-fs-f2fs)
+..............................................................................
+ File Content
+
+ gc_max_sleep_time This tuning parameter controls the maximum sleep
+ time for the garbage collection thread. Time is
+ in milliseconds.
+
+ gc_min_sleep_time This tuning parameter controls the minimum sleep
+ time for the garbage collection thread. Time is
+ in milliseconds.
+
+ gc_no_gc_sleep_time This tuning parameter controls the default sleep
+ time for the garbage collection thread. Time is
+ in milliseconds.
+
+ gc_idle This parameter controls the selection of victim
+ policy for garbage collection. Setting gc_idle = 0
+ (default) will disable this option. Setting
+ gc_idle = 1 will select the Cost Benefit approach
+ & setting gc_idle = 2 will select the greedy aproach.
+
+ reclaim_segments This parameter controls the number of prefree
+ segments to be reclaimed. If the number of prefree
+ segments is larger than the number of segments
+ in the proportion to the percentage over total
+ volume size, f2fs tries to conduct checkpoint to
+ reclaim the prefree segments to free segments.
+ By default, 5% over total # of segments.
+
+ max_small_discards This parameter controls the number of discard
+ commands that consist small blocks less than 2MB.
+ The candidates to be discarded are cached until
+ checkpoint is triggered, and issued during the
+ checkpoint. By default, it is disabled with 0.
+
+ trim_sections This parameter controls the number of sections
+ to be trimmed out in batch mode when FITRIM
+ conducts. 32 sections is set by default.
+
+ ipu_policy This parameter controls the policy of in-place
+ updates in f2fs. There are five policies:
+ 0x01: F2FS_IPU_FORCE, 0x02: F2FS_IPU_SSR,
+ 0x04: F2FS_IPU_UTIL, 0x08: F2FS_IPU_SSR_UTIL,
+ 0x10: F2FS_IPU_FSYNC.
+
+ min_ipu_util This parameter controls the threshold to trigger
+ in-place-updates. The number indicates percentage
+ of the filesystem utilization, and used by
+ F2FS_IPU_UTIL and F2FS_IPU_SSR_UTIL policies.
+
+ min_fsync_blocks This parameter controls the threshold to trigger
+ in-place-updates when F2FS_IPU_FSYNC mode is set.
+ The number indicates the number of dirty pages
+ when fsync needs to flush on its call path. If
+ the number is less than this value, it triggers
+ in-place-updates.
+
+ max_victim_search This parameter controls the number of trials to
+ find a victim segment when conducting SSR and
+ cleaning operations. The default value is 4096
+ which covers 8GB block address range.
+
+ dir_level This parameter controls the directory level to
+ support large directory. If a directory has a
+ number of files, it can reduce the file lookup
+ latency by increasing this dir_level value.
+ Otherwise, it needs to decrease this value to
+ reduce the space overhead. The default value is 0.
+
+ ram_thresh This parameter controls the memory footprint used
+ by free nids and cached nat entries. By default,
+ 10 is set, which indicates 10 MB / 1 GB RAM.
+
+================================================================================
+USAGE
+================================================================================
+
+1. Download userland tools and compile them.
+
+2. Skip, if f2fs was compiled statically inside kernel.
+ Otherwise, insert the f2fs.ko module.
+ # insmod f2fs.ko
+
+3. Create a directory trying to mount
+ # mkdir /mnt/f2fs
+
+4. Format the block device, and then mount as f2fs
+ # mkfs.f2fs -l label /dev/block_device
+ # mount -t f2fs /dev/block_device /mnt/f2fs
+
+mkfs.f2fs
+---------
+The mkfs.f2fs is for the use of formatting a partition as the f2fs filesystem,
+which builds a basic on-disk layout.
+
+The options consist of:
+-l [label] : Give a volume label, up to 512 unicode name.
+-a [0 or 1] : Split start location of each area for heap-based allocation.
+ 1 is set by default, which performs this.
+-o [int] : Set overprovision ratio in percent over volume size.
+ 5 is set by default.
+-s [int] : Set the number of segments per section.
+ 1 is set by default.
+-z [int] : Set the number of sections per zone.
+ 1 is set by default.
+-e [str] : Set basic extension list. e.g. "mp3,gif,mov"
+-t [0 or 1] : Disable discard command or not.
+ 1 is set by default, which conducts discard.
+
+fsck.f2fs
+---------
+The fsck.f2fs is a tool to check the consistency of an f2fs-formatted
+partition, which examines whether the filesystem metadata and user-made data
+are cross-referenced correctly or not.
+Note that, initial version of the tool does not fix any inconsistency.
+
+The options consist of:
+ -d debug level [default:0]
+
+dump.f2fs
+---------
+The dump.f2fs shows the information of specific inode and dumps SSA and SIT to
+file. Each file is dump_ssa and dump_sit.
+
+The dump.f2fs is used to debug on-disk data structures of the f2fs filesystem.
+It shows on-disk inode information reconized by a given inode number, and is
+able to dump all the SSA and SIT entries into predefined files, ./dump_ssa and
+./dump_sit respectively.
+
+The options consist of:
+ -d debug level [default:0]
+ -i inode no (hex)
+ -s [SIT dump segno from #1~#2 (decimal), for all 0~-1]
+ -a [SSA dump segno from #1~#2 (decimal), for all 0~-1]
+
+Examples:
+# dump.f2fs -i [ino] /dev/sdx
+# dump.f2fs -s 0~-1 /dev/sdx (SIT dump)
+# dump.f2fs -a 0~-1 /dev/sdx (SSA dump)
+
+================================================================================
+DESIGN
+================================================================================
+
+On-disk Layout
+--------------
+
+F2FS divides the whole volume into a number of segments, each of which is fixed
+to 2MB in size. A section is composed of consecutive segments, and a zone
+consists of a set of sections. By default, section and zone sizes are set to one
+segment size identically, but users can easily modify the sizes by mkfs.
+
+F2FS splits the entire volume into six areas, and all the areas except superblock
+consists of multiple segments as described below.
+
+ align with the zone size <-|
+ |-> align with the segment size
+ _________________________________________________________________________
+ | | | Segment | Node | Segment | |
+ | Superblock | Checkpoint | Info. | Address | Summary | Main |
+ | (SB) | (CP) | Table (SIT) | Table (NAT) | Area (SSA) | |
+ |____________|_____2______|______N______|______N______|______N_____|__N___|
+ . .
+ . .
+ . .
+ ._________________________________________.
+ |_Segment_|_..._|_Segment_|_..._|_Segment_|
+ . .
+ ._________._________
+ |_section_|__...__|_
+ . .
+ .________.
+ |__zone__|
+
+- Superblock (SB)
+ : It is located at the beginning of the partition, and there exist two copies
+ to avoid file system crash. It contains basic partition information and some
+ default parameters of f2fs.
+
+- Checkpoint (CP)
+ : It contains file system information, bitmaps for valid NAT/SIT sets, orphan
+ inode lists, and summary entries of current active segments.
+
+- Segment Information Table (SIT)
+ : It contains segment information such as valid block count and bitmap for the
+ validity of all the blocks.
+
+- Node Address Table (NAT)
+ : It is composed of a block address table for all the node blocks stored in
+ Main area.
+
+- Segment Summary Area (SSA)
+ : It contains summary entries which contains the owner information of all the
+ data and node blocks stored in Main area.
+
+- Main Area
+ : It contains file and directory data including their indices.
+
+In order to avoid misalignment between file system and flash-based storage, F2FS
+aligns the start block address of CP with the segment size. Also, it aligns the
+start block address of Main area with the zone size by reserving some segments
+in SSA area.
+
+Reference the following survey for additional technical details.
+https://wiki.linaro.org/WorkingGroups/Kernel/Projects/FlashCardSurvey
+
+File System Metadata Structure
+------------------------------
+
+F2FS adopts the checkpointing scheme to maintain file system consistency. At
+mount time, F2FS first tries to find the last valid checkpoint data by scanning
+CP area. In order to reduce the scanning time, F2FS uses only two copies of CP.
+One of them always indicates the last valid data, which is called as shadow copy
+mechanism. In addition to CP, NAT and SIT also adopt the shadow copy mechanism.
+
+For file system consistency, each CP points to which NAT and SIT copies are
+valid, as shown as below.
+
+ +--------+----------+---------+
+ | CP | SIT | NAT |
+ +--------+----------+---------+
+ . . . .
+ . . . .
+ . . . .
+ +-------+-------+--------+--------+--------+--------+
+ | CP #0 | CP #1 | SIT #0 | SIT #1 | NAT #0 | NAT #1 |
+ +-------+-------+--------+--------+--------+--------+
+ | ^ ^
+ | | |
+ `----------------------------------------'
+
+Index Structure
+---------------
+
+The key data structure to manage the data locations is a "node". Similar to
+traditional file structures, F2FS has three types of node: inode, direct node,
+indirect node. F2FS assigns 4KB to an inode block which contains 923 data block
+indices, two direct node pointers, two indirect node pointers, and one double
+indirect node pointer as described below. One direct node block contains 1018
+data blocks, and one indirect node block contains also 1018 node blocks. Thus,
+one inode block (i.e., a file) covers:
+
+ 4KB * (923 + 2 * 1018 + 2 * 1018 * 1018 + 1018 * 1018 * 1018) := 3.94TB.
+
+ Inode block (4KB)
+ |- data (923)
+ |- direct node (2)
+ | `- data (1018)
+ |- indirect node (2)
+ | `- direct node (1018)
+ | `- data (1018)
+ `- double indirect node (1)
+ `- indirect node (1018)
+ `- direct node (1018)
+ `- data (1018)
+
+Note that, all the node blocks are mapped by NAT which means the location of
+each node is translated by the NAT table. In the consideration of the wandering
+tree problem, F2FS is able to cut off the propagation of node updates caused by
+leaf data writes.
+
+Directory Structure
+-------------------
+
+A directory entry occupies 11 bytes, which consists of the following attributes.
+
+- hash hash value of the file name
+- ino inode number
+- len the length of file name
+- type file type such as directory, symlink, etc
+
+A dentry block consists of 214 dentry slots and file names. Therein a bitmap is
+used to represent whether each dentry is valid or not. A dentry block occupies
+4KB with the following composition.
+
+ Dentry Block(4 K) = bitmap (27 bytes) + reserved (3 bytes) +
+ dentries(11 * 214 bytes) + file name (8 * 214 bytes)
+
+ [Bucket]
+ +--------------------------------+
+ |dentry block 1 | dentry block 2 |
+ +--------------------------------+
+ . .
+ . .
+ . [Dentry Block Structure: 4KB] .
+ +--------+----------+----------+------------+
+ | bitmap | reserved | dentries | file names |
+ +--------+----------+----------+------------+
+ [Dentry Block: 4KB] . .
+ . .
+ . .
+ +------+------+-----+------+
+ | hash | ino | len | type |
+ +------+------+-----+------+
+ [Dentry Structure: 11 bytes]
+
+F2FS implements multi-level hash tables for directory structure. Each level has
+a hash table with dedicated number of hash buckets as shown below. Note that
+"A(2B)" means a bucket includes 2 data blocks.
+
+----------------------
+A : bucket
+B : block
+N : MAX_DIR_HASH_DEPTH
+----------------------
+
+level #0 | A(2B)
+ |
+level #1 | A(2B) - A(2B)
+ |
+level #2 | A(2B) - A(2B) - A(2B) - A(2B)
+ . | . . . .
+level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B)
+ . | . . . .
+level #N | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B)
+
+The number of blocks and buckets are determined by,
+
+ ,- 2, if n < MAX_DIR_HASH_DEPTH / 2,
+ # of blocks in level #n = |
+ `- 4, Otherwise
+
+ ,- 2^(n + dir_level),
+ | if n + dir_level < MAX_DIR_HASH_DEPTH / 2,
+ # of buckets in level #n = |
+ `- 2^((MAX_DIR_HASH_DEPTH / 2) - 1),
+ Otherwise
+
+When F2FS finds a file name in a directory, at first a hash value of the file
+name is calculated. Then, F2FS scans the hash table in level #0 to find the
+dentry consisting of the file name and its inode number. If not found, F2FS
+scans the next hash table in level #1. In this way, F2FS scans hash tables in
+each levels incrementally from 1 to N. In each levels F2FS needs to scan only
+one bucket determined by the following equation, which shows O(log(# of files))
+complexity.
+
+ bucket number to scan in level #n = (hash value) % (# of buckets in level #n)
+
+In the case of file creation, F2FS finds empty consecutive slots that cover the
+file name. F2FS searches the empty slots in the hash tables of whole levels from
+1 to N in the same way as the lookup operation.
+
+The following figure shows an example of two cases holding children.
+ --------------> Dir <--------------
+ | |
+ child child
+
+ child - child [hole] - child
+
+ child - child - child [hole] - [hole] - child
+
+ Case 1: Case 2:
+ Number of children = 6, Number of children = 3,
+ File size = 7 File size = 7
+
+Default Block Allocation
+------------------------
+
+At runtime, F2FS manages six active logs inside "Main" area: Hot/Warm/Cold node
+and Hot/Warm/Cold data.
+
+- Hot node contains direct node blocks of directories.
+- Warm node contains direct node blocks except hot node blocks.
+- Cold node contains indirect node blocks
+- Hot data contains dentry blocks
+- Warm data contains data blocks except hot and cold data blocks
+- Cold data contains multimedia data or migrated data blocks
+
+LFS has two schemes for free space management: threaded log and copy-and-compac-
+tion. The copy-and-compaction scheme which is known as cleaning, is well-suited
+for devices showing very good sequential write performance, since free segments
+are served all the time for writing new data. However, it suffers from cleaning
+overhead under high utilization. Contrarily, the threaded log scheme suffers
+from random writes, but no cleaning process is needed. F2FS adopts a hybrid
+scheme where the copy-and-compaction scheme is adopted by default, but the
+policy is dynamically changed to the threaded log scheme according to the file
+system status.
+
+In order to align F2FS with underlying flash-based storage, F2FS allocates a
+segment in a unit of section. F2FS expects that the section size would be the
+same as the unit size of garbage collection in FTL. Furthermore, with respect
+to the mapping granularity in FTL, F2FS allocates each section of the active
+logs from different zones as much as possible, since FTL can write the data in
+the active logs into one allocation unit according to its mapping granularity.
+
+Cleaning process
+----------------
+
+F2FS does cleaning both on demand and in the background. On-demand cleaning is
+triggered when there are not enough free segments to serve VFS calls. Background
+cleaner is operated by a kernel thread, and triggers the cleaning job when the
+system is idle.
+
+F2FS supports two victim selection policies: greedy and cost-benefit algorithms.
+In the greedy algorithm, F2FS selects a victim segment having the smallest number
+of valid blocks. In the cost-benefit algorithm, F2FS selects a victim segment
+according to the segment age and the number of valid blocks in order to address
+log block thrashing problem in the greedy algorithm. F2FS adopts the greedy
+algorithm for on-demand cleaner, while background cleaner adopts cost-benefit
+algorithm.
+
+In order to identify whether the data in the victim segment are valid or not,
+F2FS manages a bitmap. Each bit represents the validity of a block, and the
+bitmap is composed of a bit stream covering whole blocks in main area.
diff --git a/fs/Kconfig b/fs/Kconfig
index d0cc8ca..4599f08 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -39,6 +39,7 @@
source "fs/ocfs2/Kconfig"
source "fs/btrfs/Kconfig"
source "fs/nilfs2/Kconfig"
+source "fs/f2fs/Kconfig"
endif # BLOCK
diff --git a/fs/Makefile b/fs/Makefile
index 51fed46..c882eba 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -123,6 +123,7 @@
obj-$(CONFIG_OCFS2_FS) += ocfs2/
obj-$(CONFIG_BTRFS_FS) += btrfs/
obj-$(CONFIG_GFS2_FS) += gfs2/
+obj-$(CONFIG_F2FS_FS) += f2fs/
obj-y += exofs/ # Multiple modules
obj-$(CONFIG_CEPH_FS) += ceph/
obj-$(CONFIG_PSTORE) += pstore/
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
new file mode 100644
index 0000000..b0a9dc9
--- /dev/null
+++ b/fs/f2fs/Kconfig
@@ -0,0 +1,102 @@
+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
+ groups 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_FS_ENCRYPTION
+ bool "F2FS Encryption"
+ depends on F2FS_FS
+ depends on F2FS_FS_XATTR
+ select CRYPTO_AES
+ select CRYPTO_CBC
+ select CRYPTO_ECB
+ select CRYPTO_XTS
+ select CRYPTO_CTS
+ select CRYPTO_CTR
+ select CRYPTO_SHA256
+ select KEYS
+ select ENCRYPTED_KEYS
+ help
+ Enable encryption of f2fs files and directories. This
+ feature is similar to ecryptfs, but it is more memory
+ efficient since it avoids caching the encrypted and
+ decrypted pages in the page cache.
+
+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/fs/f2fs/Makefile b/fs/f2fs/Makefile
new file mode 100644
index 0000000..08e101e
--- /dev/null
+++ b/fs/f2fs/Makefile
@@ -0,0 +1,11 @@
+obj-$(CONFIG_F2FS_FS) += f2fs.o
+
+f2fs-y := dir.o file.o inode.o namei.o hash.o super.o inline.o
+f2fs-y += checkpoint.o gc.o data.o node.o segment.o recovery.o
+f2fs-y += shrinker.o extent_cache.o
+f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
+f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
+f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
+f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o
+f2fs-$(CONFIG_F2FS_FS_ENCRYPTION) += crypto_policy.o crypto.o \
+ crypto_key.o crypto_fname.o
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
new file mode 100644
index 0000000..df1a307
--- /dev/null
+++ b/fs/f2fs/acl.c
@@ -0,0 +1,403 @@
+/*
+ * 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:
+ case ACL_GROUP:
+ acl->a_entries[i].e_id = 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:
+ case ACL_GROUP:
+ entry->e_id = cpu_to_le32(acl->a_entries[i].e_id);
+ 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)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ int name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT;
+ void *value = NULL;
+ struct posix_acl *acl;
+ int retval;
+
+ if (!test_opt(sbi, POSIX_ACL))
+ return NULL;
+
+ acl = get_cached_acl(inode, type);
+ if (acl != ACL_NOT_CACHED)
+ return acl;
+
+ if (type == ACL_TYPE_ACCESS)
+ name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
+
+ retval = f2fs_getxattr(inode, name_index, "", NULL, 0, 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_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ int name_index;
+ void *value = NULL;
+ size_t size = 0;
+ int error;
+
+ if (!test_opt(sbi, POSIX_ACL))
+ return 0;
+ if (S_ISLNK(inode->i_mode))
+ return -EOPNOTSUPP;
+
+ switch (type) {
+ case ACL_TYPE_ACCESS:
+ name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
+ if (acl) {
+ error = posix_acl_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_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
+ struct page *dpage)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct posix_acl *acl = NULL;
+ int error = 0;
+
+ if (!S_ISLNK(inode->i_mode)) {
+ if (test_opt(sbi, POSIX_ACL)) {
+ acl = __f2fs_get_acl(dir, ACL_TYPE_DEFAULT, dpage);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ }
+ if (!acl)
+ inode->i_mode &= ~current_umask();
+ }
+
+ if (!test_opt(sbi, POSIX_ACL) || !acl)
+ goto cleanup;
+
+ if (S_ISDIR(inode->i_mode)) {
+ error = f2fs_set_acl(inode, ACL_TYPE_DEFAULT, acl, ipage);
+ if (error)
+ goto cleanup;
+ }
+ error = posix_acl_create(&acl, GFP_KERNEL, &inode->i_mode);
+ if (error < 0)
+ return error;
+ if (error > 0)
+ error = f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl, ipage);
+cleanup:
+ posix_acl_release(acl);
+ return error;
+}
+
+int f2fs_acl_chmod(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct posix_acl *acl;
+ int error;
+ umode_t mode = get_inode_mode(inode);
+
+ if (!test_opt(sbi, POSIX_ACL))
+ return 0;
+ if (S_ISLNK(mode))
+ return -EOPNOTSUPP;
+
+ acl = f2fs_get_acl(inode, ACL_TYPE_ACCESS);
+ if (IS_ERR(acl) || !acl)
+ return PTR_ERR(acl);
+
+ error = posix_acl_chmod(&acl, GFP_KERNEL, mode);
+ if (error)
+ return error;
+
+ error = f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl, NULL);
+ posix_acl_release(acl);
+ return error;
+}
+
+static size_t f2fs_xattr_list_acl(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+ const char *xname = POSIX_ACL_XATTR_DEFAULT;
+ size_t size;
+
+ if (!test_opt(sbi, POSIX_ACL))
+ return 0;
+
+ if (type == ACL_TYPE_ACCESS)
+ xname = POSIX_ACL_XATTR_ACCESS;
+
+ size = strlen(xname) + 1;
+ if (list && size <= list_size)
+ memcpy(list, xname, size);
+ return size;
+}
+
+static int f2fs_xattr_get_acl(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+ struct posix_acl *acl;
+ int error;
+
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ if (!test_opt(sbi, POSIX_ACL))
+ return -EOPNOTSUPP;
+
+ acl = f2fs_get_acl(dentry->d_inode, type);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ if (!acl)
+ return -ENODATA;
+ error = posix_acl_to_xattr(acl, buffer, size);
+ posix_acl_release(acl);
+
+ return error;
+}
+
+static int f2fs_xattr_set_acl(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+ struct inode *inode = dentry->d_inode;
+ struct posix_acl *acl = NULL;
+ int error;
+
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ if (!test_opt(sbi, POSIX_ACL))
+ return -EOPNOTSUPP;
+ if (!inode_owner_or_capable(inode))
+ return -EPERM;
+
+ if (value) {
+ acl = posix_acl_from_xattr(value, size);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ if (acl) {
+ error = posix_acl_valid(acl);
+ if (error)
+ goto release_and_out;
+ }
+ } else {
+ acl = NULL;
+ }
+
+ error = f2fs_set_acl(inode, type, acl, NULL);
+
+release_and_out:
+ posix_acl_release(acl);
+ return error;
+}
+
+const struct xattr_handler f2fs_xattr_acl_default_handler = {
+ .prefix = POSIX_ACL_XATTR_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
+ .list = f2fs_xattr_list_acl,
+ .get = f2fs_xattr_get_acl,
+ .set = f2fs_xattr_set_acl,
+};
+
+const struct xattr_handler f2fs_xattr_acl_access_handler = {
+ .prefix = POSIX_ACL_XATTR_ACCESS,
+ .flags = ACL_TYPE_ACCESS,
+ .list = f2fs_xattr_list_acl,
+ .get = f2fs_xattr_get_acl,
+ .set = f2fs_xattr_set_acl,
+};
diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h
new file mode 100644
index 0000000..b4ba686
--- /dev/null
+++ b/fs/f2fs/acl.h
@@ -0,0 +1,59 @@
+/*
+ * 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_acl_chmod(struct inode *);
+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_acl_chmod(struct inode *inode)
+{
+ return 0;
+}
+
+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/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
new file mode 100644
index 0000000..463a67c
--- /dev/null
+++ b/fs/f2fs/checkpoint.c
@@ -0,0 +1,1190 @@
+/*
+ * 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.
+ */
+static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
+ bool is_meta)
+{
+ struct address_space *mapping = META_MAPPING(sbi);
+ struct page *page;
+ struct f2fs_io_info fio = {
+ .sbi = sbi,
+ .type = META,
+ .rw = READ_SYNC | REQ_META | REQ_PRIO,
+ .blk_addr = index,
+ .encrypted_page = NULL,
+ };
+
+ if (unlikely(!is_meta))
+ fio.rw &= ~REQ_META;
+repeat:
+ page = grab_cache_page(mapping, index);
+ if (!page) {
+ cond_resched();
+ goto repeat;
+ }
+ if (PageUptodate(page))
+ goto out;
+
+ fio.page = page;
+
+ if (f2fs_submit_page_bio(&fio)) {
+ f2fs_put_page(page, 1);
+ goto repeat;
+ }
+
+ lock_page(page);
+ if (unlikely(page->mapping != mapping)) {
+ f2fs_put_page(page, 1);
+ goto repeat;
+ }
+
+ /*
+ * if there is any IO error when accessing device, make our filesystem
+ * readonly and make sure do not write checkpoint with non-uptodate
+ * meta page.
+ */
+ if (unlikely(!PageUptodate(page)))
+ f2fs_stop_checkpoint(sbi);
+out:
+ mark_page_accessed(page);
+ return page;
+}
+
+struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+ return __get_meta_page(sbi, index, true);
+}
+
+/* for POR only */
+struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+ return __get_meta_page(sbi, index, false);
+}
+
+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, bool sync)
+{
+ block_t prev_blk_addr = 0;
+ struct page *page;
+ block_t blkno = start;
+ struct f2fs_io_info fio = {
+ .sbi = sbi,
+ .type = META,
+ .rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA,
+ .encrypted_page = NULL,
+ };
+
+ if (unlikely(type == META_POR))
+ fio.rw &= ~REQ_META;
+
+ 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;
+ }
+
+ fio.page = page;
+ f2fs_submit_page_mbio(&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, true);
+}
+
+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, prev = 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];
+
+ if (prev == LONG_MAX)
+ prev = page->index - 1;
+ if (nr_to_write != LONG_MAX && page->index != prev + 1) {
+ pagevec_release(&pvec);
+ goto stop;
+ }
+
+ 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++;
+ prev = page->index;
+ if (unlikely(nwritten >= nr_to_write))
+ break;
+ }
+ pagevec_release(&pvec);
+ cond_resched();
+ }
+stop:
+ 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, *tmp;
+
+ tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS);
+retry:
+ radix_tree_preload(GFP_NOFS | __GFP_NOFAIL);
+
+ spin_lock(&im->ino_lock);
+ e = radix_tree_lookup(&im->ino_root, ino);
+ if (!e) {
+ e = tmp;
+ if (radix_tree_insert(&im->ino_root, ino, e)) {
+ spin_unlock(&im->ino_lock);
+ 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();
+
+ if (e != tmp)
+ kmem_cache_free(ino_entry_slab, tmp);
+}
+
+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 int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
+{
+ struct inode *inode;
+
+ inode = f2fs_iget(sbi->sb, ino);
+ if (IS_ERR(inode)) {
+ /*
+ * there should be a bug that we can't find the entry
+ * to orphan inode.
+ */
+ f2fs_bug_on(sbi, PTR_ERR(inode) == -ENOENT);
+ return PTR_ERR(inode);
+ }
+
+ clear_nlink(inode);
+
+ /* truncate all the data during iput */
+ iput(inode);
+ return 0;
+}
+
+int recover_orphan_inodes(struct f2fs_sb_info *sbi)
+{
+ block_t start_blk, orphan_blocks, i, j;
+ int err;
+
+ if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG))
+ return 0;
+
+ 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, true);
+
+ 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]);
+ err = recover_orphan_inode(sbi, ino);
+ if (err) {
+ f2fs_put_page(page, 1);
+ return err;
+ }
+ }
+ f2fs_put_page(page, 1);
+ }
+ /* clear Orphan Flag */
+ clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG);
+ return 0;
+}
+
+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 = 1;
+ 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);
+
+ /*
+ * we don't need to do spin_lock(&im->ino_lock) here, since all the
+ * orphan inode operations are covered under f2fs_lock_op().
+ * And, spin_lock should be avoided due to page operations below.
+ */
+ 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 = grab_meta_page(sbi, start_blk++);
+ orphan_blk =
+ (struct f2fs_orphan_block *)page_address(page);
+ memset(orphan_blk, 0, sizeof(*orphan_blk));
+ }
+
+ 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);
+ }
+}
+
+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) &&
+ !S_ISLNK(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;
+ unsigned int data_sum_blocks, orphan_blocks;
+ __u32 crc32 = 0;
+ int i;
+ int cp_payload_blks = __cp_payload(sbi);
+ block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg);
+ bool invalidate = false;
+
+ /*
+ * This avoids to conduct wrong roll-forward operations and uses
+ * metapages, so should be called prior to sync_meta_pages below.
+ */
+ if (discard_next_dnode(sbi, discard_blk))
+ invalidate = true;
+
+ /* 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);
+
+ /* need to wait for end_io results */
+ wait_on_all_pages_writeback(sbi);
+ if (unlikely(f2fs_cp_error(sbi)))
+ return;
+
+ /* write out checkpoint buffer at block 0 */
+ update_meta_page(sbi, ckpt, start_blk++);
+
+ for (i = 1; i < 1 + cp_payload_blks; i++)
+ update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE,
+ start_blk++);
+
+ 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 */
+ update_meta_page(sbi, ckpt, start_blk);
+
+ /* 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);
+
+ /*
+ * invalidate meta page which is used temporarily for zeroing out
+ * block at the end of warm node chain.
+ */
+ if (invalidate)
+ invalidate_mapping_pages(META_MAPPING(sbi), discard_blk,
+ discard_blk);
+
+ release_dirty_inode(sbi);
+
+ if (unlikely(f2fs_cp_error(sbi)))
+ return;
+
+ clear_prefree_segments(sbi, cpc);
+ 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 ||
+ (cpc->reason == CP_DISCARD && !sbi->discard_blks)))
+ 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);
+
+ /* do checkpoint periodically */
+ sbi->cp_expires = round_jiffies_up(jiffies + HZ * sbi->cp_interval);
+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/fs/f2fs/crypto.c b/fs/f2fs/crypto.c
new file mode 100644
index 0000000..4a62ef1
--- /dev/null
+++ b/fs/f2fs/crypto.c
@@ -0,0 +1,491 @@
+/*
+ * linux/fs/f2fs/crypto.c
+ *
+ * Copied from linux/fs/ext4/crypto.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * This contains encryption functions for f2fs
+ *
+ * Written by Michael Halcrow, 2014.
+ *
+ * Filename encryption additions
+ * Uday Savagaonkar, 2014
+ * Encryption policy handling additions
+ * Ildar Muslukhov, 2014
+ * Remove ext4_encrypted_zeroout(),
+ * add f2fs_restore_and_release_control_page()
+ * Jaegeuk Kim, 2015.
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ * The usage of AES-XTS should conform to recommendations in NIST
+ * Special Publication 800-38E and IEEE P1619/D16.
+ */
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+#include <keys/user-type.h>
+#include <keys/encrypted-type.h>
+#include <linux/crypto.h>
+#include <linux/ecryptfs.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/key.h>
+#include <linux/list.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <linux/spinlock_types.h>
+#include <linux/f2fs_fs.h>
+#include <linux/ratelimit.h>
+#include <linux/bio.h>
+
+#include "f2fs.h"
+#include "xattr.h"
+
+/* Encryption added and removed here! (L: */
+
+static unsigned int num_prealloc_crypto_pages = 32;
+static unsigned int num_prealloc_crypto_ctxs = 128;
+
+module_param(num_prealloc_crypto_pages, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_pages,
+ "Number of crypto pages to preallocate");
+module_param(num_prealloc_crypto_ctxs, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
+ "Number of crypto contexts to preallocate");
+
+static mempool_t *f2fs_bounce_page_pool;
+
+static LIST_HEAD(f2fs_free_crypto_ctxs);
+static DEFINE_SPINLOCK(f2fs_crypto_ctx_lock);
+
+static struct workqueue_struct *f2fs_read_workqueue;
+static DEFINE_MUTEX(crypto_init);
+
+static struct kmem_cache *f2fs_crypto_ctx_cachep;
+struct kmem_cache *f2fs_crypt_info_cachep;
+
+/**
+ * f2fs_release_crypto_ctx() - Releases an encryption context
+ * @ctx: The encryption context to release.
+ *
+ * If the encryption context was allocated from the pre-allocated pool, returns
+ * it to that pool. Else, frees it.
+ *
+ * If there's a bounce page in the context, this frees that.
+ */
+void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *ctx)
+{
+ unsigned long flags;
+
+ if (ctx->flags & F2FS_WRITE_PATH_FL && ctx->w.bounce_page) {
+ mempool_free(ctx->w.bounce_page, f2fs_bounce_page_pool);
+ ctx->w.bounce_page = NULL;
+ }
+ ctx->w.control_page = NULL;
+ if (ctx->flags & F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL) {
+ kmem_cache_free(f2fs_crypto_ctx_cachep, ctx);
+ } else {
+ spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags);
+ list_add(&ctx->free_list, &f2fs_free_crypto_ctxs);
+ spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags);
+ }
+}
+
+/**
+ * f2fs_get_crypto_ctx() - Gets an encryption context
+ * @inode: The inode for which we are doing the crypto
+ *
+ * Allocates and initializes an encryption context.
+ *
+ * Return: An allocated and initialized encryption context on success; error
+ * value or NULL otherwise.
+ */
+struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *inode)
+{
+ struct f2fs_crypto_ctx *ctx = NULL;
+ unsigned long flags;
+ struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
+
+ if (ci == NULL)
+ return ERR_PTR(-ENOKEY);
+
+ /*
+ * We first try getting the ctx from a free list because in
+ * the common case the ctx will have an allocated and
+ * initialized crypto tfm, so it's probably a worthwhile
+ * optimization. For the bounce page, we first try getting it
+ * from the kernel allocator because that's just about as fast
+ * as getting it from a list and because a cache of free pages
+ * should generally be a "last resort" option for a filesystem
+ * to be able to do its job.
+ */
+ spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags);
+ ctx = list_first_entry_or_null(&f2fs_free_crypto_ctxs,
+ struct f2fs_crypto_ctx, free_list);
+ if (ctx)
+ list_del(&ctx->free_list);
+ spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags);
+ if (!ctx) {
+ ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_NOFS);
+ if (!ctx)
+ return ERR_PTR(-ENOMEM);
+ ctx->flags |= F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
+ } else {
+ ctx->flags &= ~F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
+ }
+ ctx->flags &= ~F2FS_WRITE_PATH_FL;
+ return ctx;
+}
+
+/*
+ * Call f2fs_decrypt on every single page, reusing the encryption
+ * context.
+ */
+static void completion_pages(struct work_struct *work)
+{
+ struct f2fs_crypto_ctx *ctx =
+ container_of(work, struct f2fs_crypto_ctx, r.work);
+ struct bio *bio = ctx->r.bio;
+ struct bio_vec *bv;
+ int i;
+
+ bio_for_each_segment_all(bv, bio, i) {
+ struct page *page = bv->bv_page;
+ int ret = f2fs_decrypt(ctx, page);
+
+ if (ret) {
+ WARN_ON_ONCE(1);
+ SetPageError(page);
+ } else
+ SetPageUptodate(page);
+ unlock_page(page);
+ }
+ f2fs_release_crypto_ctx(ctx);
+ bio_put(bio);
+}
+
+void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *ctx, struct bio *bio)
+{
+ INIT_WORK(&ctx->r.work, completion_pages);
+ ctx->r.bio = bio;
+ queue_work(f2fs_read_workqueue, &ctx->r.work);
+}
+
+static void f2fs_crypto_destroy(void)
+{
+ struct f2fs_crypto_ctx *pos, *n;
+
+ list_for_each_entry_safe(pos, n, &f2fs_free_crypto_ctxs, free_list)
+ kmem_cache_free(f2fs_crypto_ctx_cachep, pos);
+ INIT_LIST_HEAD(&f2fs_free_crypto_ctxs);
+ if (f2fs_bounce_page_pool)
+ mempool_destroy(f2fs_bounce_page_pool);
+ f2fs_bounce_page_pool = NULL;
+}
+
+/**
+ * f2fs_crypto_initialize() - Set up for f2fs encryption.
+ *
+ * We only call this when we start accessing encrypted files, since it
+ * results in memory getting allocated that wouldn't otherwise be used.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int f2fs_crypto_initialize(void)
+{
+ int i, res = -ENOMEM;
+
+ if (f2fs_bounce_page_pool)
+ return 0;
+
+ mutex_lock(&crypto_init);
+ if (f2fs_bounce_page_pool)
+ goto already_initialized;
+
+ for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
+ struct f2fs_crypto_ctx *ctx;
+
+ ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_KERNEL);
+ if (!ctx)
+ goto fail;
+ list_add(&ctx->free_list, &f2fs_free_crypto_ctxs);
+ }
+
+ /* must be allocated at the last step to avoid race condition above */
+ f2fs_bounce_page_pool =
+ mempool_create_page_pool(num_prealloc_crypto_pages, 0);
+ if (!f2fs_bounce_page_pool)
+ goto fail;
+
+already_initialized:
+ mutex_unlock(&crypto_init);
+ return 0;
+fail:
+ f2fs_crypto_destroy();
+ mutex_unlock(&crypto_init);
+ return res;
+}
+
+/**
+ * f2fs_exit_crypto() - Shutdown the f2fs encryption system
+ */
+void f2fs_exit_crypto(void)
+{
+ f2fs_crypto_destroy();
+
+ if (f2fs_read_workqueue)
+ destroy_workqueue(f2fs_read_workqueue);
+ if (f2fs_crypto_ctx_cachep)
+ kmem_cache_destroy(f2fs_crypto_ctx_cachep);
+ if (f2fs_crypt_info_cachep)
+ kmem_cache_destroy(f2fs_crypt_info_cachep);
+}
+
+int __init f2fs_init_crypto(void)
+{
+ int res = -ENOMEM;
+
+ f2fs_read_workqueue = alloc_workqueue("f2fs_crypto", WQ_HIGHPRI, 0);
+ if (!f2fs_read_workqueue)
+ goto fail;
+
+ f2fs_crypto_ctx_cachep = KMEM_CACHE(f2fs_crypto_ctx,
+ SLAB_RECLAIM_ACCOUNT);
+ if (!f2fs_crypto_ctx_cachep)
+ goto fail;
+
+ f2fs_crypt_info_cachep = KMEM_CACHE(f2fs_crypt_info,
+ SLAB_RECLAIM_ACCOUNT);
+ if (!f2fs_crypt_info_cachep)
+ goto fail;
+
+ return 0;
+fail:
+ f2fs_exit_crypto();
+ return res;
+}
+
+void f2fs_restore_and_release_control_page(struct page **page)
+{
+ struct f2fs_crypto_ctx *ctx;
+ struct page *bounce_page;
+
+ /* The bounce data pages are unmapped. */
+ if ((*page)->mapping)
+ return;
+
+ /* The bounce data page is unmapped. */
+ bounce_page = *page;
+ ctx = (struct f2fs_crypto_ctx *)page_private(bounce_page);
+
+ /* restore control page */
+ *page = ctx->w.control_page;
+
+ f2fs_restore_control_page(bounce_page);
+}
+
+void f2fs_restore_control_page(struct page *data_page)
+{
+ struct f2fs_crypto_ctx *ctx =
+ (struct f2fs_crypto_ctx *)page_private(data_page);
+
+ set_page_private(data_page, (unsigned long)NULL);
+ ClearPagePrivate(data_page);
+ unlock_page(data_page);
+ f2fs_release_crypto_ctx(ctx);
+}
+
+/**
+ * f2fs_crypt_complete() - The completion callback for page encryption
+ * @req: The asynchronous encryption request context
+ * @res: The result of the encryption operation
+ */
+static void f2fs_crypt_complete(struct crypto_async_request *req, int res)
+{
+ struct f2fs_completion_result *ecr = req->data;
+
+ if (res == -EINPROGRESS)
+ return;
+ ecr->res = res;
+ complete(&ecr->completion);
+}
+
+typedef enum {
+ F2FS_DECRYPT = 0,
+ F2FS_ENCRYPT,
+} f2fs_direction_t;
+
+static int f2fs_page_crypto(struct f2fs_crypto_ctx *ctx,
+ struct inode *inode,
+ f2fs_direction_t rw,
+ pgoff_t index,
+ struct page *src_page,
+ struct page *dest_page)
+{
+ u8 xts_tweak[F2FS_XTS_TWEAK_SIZE];
+ struct ablkcipher_request *req = NULL;
+ DECLARE_F2FS_COMPLETION_RESULT(ecr);
+ struct scatterlist dst, src;
+ struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
+ struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+ int res = 0;
+
+ req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ if (!req) {
+ printk_ratelimited(KERN_ERR
+ "%s: crypto_request_alloc() failed\n",
+ __func__);
+ return -ENOMEM;
+ }
+ ablkcipher_request_set_callback(
+ req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ f2fs_crypt_complete, &ecr);
+
+ BUILD_BUG_ON(F2FS_XTS_TWEAK_SIZE < sizeof(index));
+ memcpy(xts_tweak, &index, sizeof(index));
+ memset(&xts_tweak[sizeof(index)], 0,
+ F2FS_XTS_TWEAK_SIZE - sizeof(index));
+
+ sg_init_table(&dst, 1);
+ sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0);
+ sg_init_table(&src, 1);
+ sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0);
+ ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
+ xts_tweak);
+ if (rw == F2FS_DECRYPT)
+ res = crypto_ablkcipher_decrypt(req);
+ else
+ res = crypto_ablkcipher_encrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ BUG_ON(req->base.data != &ecr);
+ wait_for_completion(&ecr.completion);
+ res = ecr.res;
+ }
+ ablkcipher_request_free(req);
+ if (res) {
+ printk_ratelimited(KERN_ERR
+ "%s: crypto_ablkcipher_encrypt() returned %d\n",
+ __func__, res);
+ return res;
+ }
+ return 0;
+}
+
+static struct page *alloc_bounce_page(struct f2fs_crypto_ctx *ctx)
+{
+ ctx->w.bounce_page = mempool_alloc(f2fs_bounce_page_pool, GFP_NOWAIT);
+ if (ctx->w.bounce_page == NULL)
+ return ERR_PTR(-ENOMEM);
+ ctx->flags |= F2FS_WRITE_PATH_FL;
+ return ctx->w.bounce_page;
+}
+
+/**
+ * f2fs_encrypt() - Encrypts a page
+ * @inode: The inode for which the encryption should take place
+ * @plaintext_page: The page to encrypt. Must be locked.
+ *
+ * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
+ * encryption context.
+ *
+ * Called on the page write path. The caller must call
+ * f2fs_restore_control_page() on the returned ciphertext page to
+ * release the bounce buffer and the encryption context.
+ *
+ * Return: An allocated page with the encrypted content on success. Else, an
+ * error value or NULL.
+ */
+struct page *f2fs_encrypt(struct inode *inode,
+ struct page *plaintext_page)
+{
+ struct f2fs_crypto_ctx *ctx;
+ struct page *ciphertext_page = NULL;
+ int err;
+
+ BUG_ON(!PageLocked(plaintext_page));
+
+ ctx = f2fs_get_crypto_ctx(inode);
+ if (IS_ERR(ctx))
+ return (struct page *)ctx;
+
+ /* The encryption operation will require a bounce page. */
+ ciphertext_page = alloc_bounce_page(ctx);
+ if (IS_ERR(ciphertext_page))
+ goto err_out;
+
+ ctx->w.control_page = plaintext_page;
+ err = f2fs_page_crypto(ctx, inode, F2FS_ENCRYPT, plaintext_page->index,
+ plaintext_page, ciphertext_page);
+ if (err) {
+ ciphertext_page = ERR_PTR(err);
+ goto err_out;
+ }
+
+ SetPagePrivate(ciphertext_page);
+ set_page_private(ciphertext_page, (unsigned long)ctx);
+ lock_page(ciphertext_page);
+ return ciphertext_page;
+
+err_out:
+ f2fs_release_crypto_ctx(ctx);
+ return ciphertext_page;
+}
+
+/**
+ * f2fs_decrypt() - Decrypts a page in-place
+ * @ctx: The encryption context.
+ * @page: The page to decrypt. Must be locked.
+ *
+ * Decrypts page in-place using the ctx encryption context.
+ *
+ * Called from the read completion callback.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int f2fs_decrypt(struct f2fs_crypto_ctx *ctx, struct page *page)
+{
+ BUG_ON(!PageLocked(page));
+
+ return f2fs_page_crypto(ctx, page->mapping->host,
+ F2FS_DECRYPT, page->index, page, page);
+}
+
+/*
+ * Convenience function which takes care of allocating and
+ * deallocating the encryption context
+ */
+int f2fs_decrypt_one(struct inode *inode, struct page *page)
+{
+ struct f2fs_crypto_ctx *ctx = f2fs_get_crypto_ctx(inode);
+ int ret;
+
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
+ ret = f2fs_decrypt(ctx, page);
+ f2fs_release_crypto_ctx(ctx);
+ return ret;
+}
+
+bool f2fs_valid_contents_enc_mode(uint32_t mode)
+{
+ return (mode == F2FS_ENCRYPTION_MODE_AES_256_XTS);
+}
+
+/**
+ * f2fs_validate_encryption_key_size() - Validate the encryption key size
+ * @mode: The key mode.
+ * @size: The key size to validate.
+ *
+ * Return: The validated key size for @mode. Zero if invalid.
+ */
+uint32_t f2fs_validate_encryption_key_size(uint32_t mode, uint32_t size)
+{
+ if (size == f2fs_encryption_key_size(mode))
+ return size;
+ return 0;
+}
diff --git a/fs/f2fs/crypto_fname.c b/fs/f2fs/crypto_fname.c
new file mode 100644
index 0000000..ab377d4
--- /dev/null
+++ b/fs/f2fs/crypto_fname.c
@@ -0,0 +1,440 @@
+/*
+ * linux/fs/f2fs/crypto_fname.c
+ *
+ * Copied from linux/fs/ext4/crypto.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * This contains functions for filename crypto management in f2fs
+ *
+ * Written by Uday Savagaonkar, 2014.
+ *
+ * Adjust f2fs dentry structure
+ * Jaegeuk Kim, 2015.
+ *
+ * This has not yet undergone a rigorous security audit.
+ */
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+#include <keys/encrypted-type.h>
+#include <keys/user-type.h>
+#include <linux/crypto.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/key.h>
+#include <linux/list.h>
+#include <linux/mempool.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <linux/spinlock_types.h>
+#include <linux/f2fs_fs.h>
+#include <linux/ratelimit.h>
+
+#include "f2fs.h"
+#include "f2fs_crypto.h"
+#include "xattr.h"
+
+/**
+ * f2fs_dir_crypt_complete() -
+ */
+static void f2fs_dir_crypt_complete(struct crypto_async_request *req, int res)
+{
+ struct f2fs_completion_result *ecr = req->data;
+
+ if (res == -EINPROGRESS)
+ return;
+ ecr->res = res;
+ complete(&ecr->completion);
+}
+
+bool f2fs_valid_filenames_enc_mode(uint32_t mode)
+{
+ return (mode == F2FS_ENCRYPTION_MODE_AES_256_CTS);
+}
+
+static unsigned max_name_len(struct inode *inode)
+{
+ return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
+ F2FS_NAME_LEN;
+}
+
+/**
+ * f2fs_fname_encrypt() -
+ *
+ * This function encrypts the input filename, and returns the length of the
+ * ciphertext. Errors are returned as negative numbers. We trust the caller to
+ * allocate sufficient memory to oname string.
+ */
+static int f2fs_fname_encrypt(struct inode *inode,
+ const struct qstr *iname, struct f2fs_str *oname)
+{
+ u32 ciphertext_len;
+ struct ablkcipher_request *req = NULL;
+ DECLARE_F2FS_COMPLETION_RESULT(ecr);
+ struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
+ struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+ int res = 0;
+ char iv[F2FS_CRYPTO_BLOCK_SIZE];
+ struct scatterlist src_sg, dst_sg;
+ int padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK);
+ char *workbuf, buf[32], *alloc_buf = NULL;
+ unsigned lim = max_name_len(inode);
+
+ if (iname->len <= 0 || iname->len > lim)
+ return -EIO;
+
+ ciphertext_len = (iname->len < F2FS_CRYPTO_BLOCK_SIZE) ?
+ F2FS_CRYPTO_BLOCK_SIZE : iname->len;
+ ciphertext_len = f2fs_fname_crypto_round_up(ciphertext_len, padding);
+ ciphertext_len = (ciphertext_len > lim) ? lim : ciphertext_len;
+
+ if (ciphertext_len <= sizeof(buf)) {
+ workbuf = buf;
+ } else {
+ alloc_buf = kmalloc(ciphertext_len, GFP_NOFS);
+ if (!alloc_buf)
+ return -ENOMEM;
+ workbuf = alloc_buf;
+ }
+
+ /* Allocate request */
+ req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ if (!req) {
+ printk_ratelimited(KERN_ERR
+ "%s: crypto_request_alloc() failed\n", __func__);
+ kfree(alloc_buf);
+ return -ENOMEM;
+ }
+ ablkcipher_request_set_callback(req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ f2fs_dir_crypt_complete, &ecr);
+
+ /* Copy the input */
+ memcpy(workbuf, iname->name, iname->len);
+ if (iname->len < ciphertext_len)
+ memset(workbuf + iname->len, 0, ciphertext_len - iname->len);
+
+ /* Initialize IV */
+ memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE);
+
+ /* Create encryption request */
+ sg_init_one(&src_sg, workbuf, ciphertext_len);
+ sg_init_one(&dst_sg, oname->name, ciphertext_len);
+ ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
+ res = crypto_ablkcipher_encrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ BUG_ON(req->base.data != &ecr);
+ wait_for_completion(&ecr.completion);
+ res = ecr.res;
+ }
+ kfree(alloc_buf);
+ ablkcipher_request_free(req);
+ if (res < 0) {
+ printk_ratelimited(KERN_ERR
+ "%s: Error (error code %d)\n", __func__, res);
+ }
+ oname->len = ciphertext_len;
+ return res;
+}
+
+/*
+ * f2fs_fname_decrypt()
+ * This function decrypts the input filename, and returns
+ * the length of the plaintext.
+ * Errors are returned as negative numbers.
+ * We trust the caller to allocate sufficient memory to oname string.
+ */
+static int f2fs_fname_decrypt(struct inode *inode,
+ const struct f2fs_str *iname, struct f2fs_str *oname)
+{
+ struct ablkcipher_request *req = NULL;
+ DECLARE_F2FS_COMPLETION_RESULT(ecr);
+ struct scatterlist src_sg, dst_sg;
+ struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
+ struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+ int res = 0;
+ char iv[F2FS_CRYPTO_BLOCK_SIZE];
+ unsigned lim = max_name_len(inode);
+
+ if (iname->len <= 0 || iname->len > lim)
+ return -EIO;
+
+ /* Allocate request */
+ req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ if (!req) {
+ printk_ratelimited(KERN_ERR
+ "%s: crypto_request_alloc() failed\n", __func__);
+ return -ENOMEM;
+ }
+ ablkcipher_request_set_callback(req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ f2fs_dir_crypt_complete, &ecr);
+
+ /* Initialize IV */
+ memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE);
+
+ /* Create decryption request */
+ sg_init_one(&src_sg, iname->name, iname->len);
+ sg_init_one(&dst_sg, oname->name, oname->len);
+ ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
+ res = crypto_ablkcipher_decrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ BUG_ON(req->base.data != &ecr);
+ wait_for_completion(&ecr.completion);
+ res = ecr.res;
+ }
+ ablkcipher_request_free(req);
+ if (res < 0) {
+ printk_ratelimited(KERN_ERR
+ "%s: Error in f2fs_fname_decrypt (error code %d)\n",
+ __func__, res);
+ return res;
+ }
+
+ oname->len = strnlen(oname->name, iname->len);
+ return oname->len;
+}
+
+static const char *lookup_table =
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
+
+/**
+ * f2fs_fname_encode_digest() -
+ *
+ * Encodes the input digest using characters from the set [a-zA-Z0-9_+].
+ * The encoded string is roughly 4/3 times the size of the input string.
+ */
+static int digest_encode(const char *src, int len, char *dst)
+{
+ int i = 0, bits = 0, ac = 0;
+ char *cp = dst;
+
+ while (i < len) {
+ ac += (((unsigned char) src[i]) << bits);
+ bits += 8;
+ do {
+ *cp++ = lookup_table[ac & 0x3f];
+ ac >>= 6;
+ bits -= 6;
+ } while (bits >= 6);
+ i++;
+ }
+ if (bits)
+ *cp++ = lookup_table[ac & 0x3f];
+ return cp - dst;
+}
+
+static int digest_decode(const char *src, int len, char *dst)
+{
+ int i = 0, bits = 0, ac = 0;
+ const char *p;
+ char *cp = dst;
+
+ while (i < len) {
+ p = strchr(lookup_table, src[i]);
+ if (p == NULL || src[i] == 0)
+ return -2;
+ ac += (p - lookup_table) << bits;
+ bits += 6;
+ if (bits >= 8) {
+ *cp++ = ac & 0xff;
+ ac >>= 8;
+ bits -= 8;
+ }
+ i++;
+ }
+ if (ac)
+ return -1;
+ return cp - dst;
+}
+
+/**
+ * f2fs_fname_crypto_round_up() -
+ *
+ * Return: The next multiple of block size
+ */
+u32 f2fs_fname_crypto_round_up(u32 size, u32 blksize)
+{
+ return ((size + blksize - 1) / blksize) * blksize;
+}
+
+/**
+ * f2fs_fname_crypto_alloc_obuff() -
+ *
+ * Allocates an output buffer that is sufficient for the crypto operation
+ * specified by the context and the direction.
+ */
+int f2fs_fname_crypto_alloc_buffer(struct inode *inode,
+ u32 ilen, struct f2fs_str *crypto_str)
+{
+ unsigned int olen;
+ int padding = 16;
+ struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
+
+ if (ci)
+ padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK);
+ if (padding < F2FS_CRYPTO_BLOCK_SIZE)
+ padding = F2FS_CRYPTO_BLOCK_SIZE;
+ olen = f2fs_fname_crypto_round_up(ilen, padding);
+ crypto_str->len = olen;
+ if (olen < F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2)
+ olen = F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
+ /* Allocated buffer can hold one more character to null-terminate the
+ * string */
+ crypto_str->name = kmalloc(olen + 1, GFP_NOFS);
+ if (!(crypto_str->name))
+ return -ENOMEM;
+ return 0;
+}
+
+/**
+ * f2fs_fname_crypto_free_buffer() -
+ *
+ * Frees the buffer allocated for crypto operation.
+ */
+void f2fs_fname_crypto_free_buffer(struct f2fs_str *crypto_str)
+{
+ if (!crypto_str)
+ return;
+ kfree(crypto_str->name);
+ crypto_str->name = NULL;
+}
+
+/**
+ * f2fs_fname_disk_to_usr() - converts a filename from disk space to user space
+ */
+int f2fs_fname_disk_to_usr(struct inode *inode,
+ f2fs_hash_t *hash,
+ const struct f2fs_str *iname,
+ struct f2fs_str *oname)
+{
+ const struct qstr qname = FSTR_TO_QSTR(iname);
+ char buf[24];
+ int ret;
+
+ if (is_dot_dotdot(&qname)) {
+ oname->name[0] = '.';
+ oname->name[iname->len - 1] = '.';
+ oname->len = iname->len;
+ return oname->len;
+ }
+
+ if (F2FS_I(inode)->i_crypt_info)
+ return f2fs_fname_decrypt(inode, iname, oname);
+
+ if (iname->len <= F2FS_FNAME_CRYPTO_DIGEST_SIZE) {
+ ret = digest_encode(iname->name, iname->len, oname->name);
+ oname->len = ret;
+ return ret;
+ }
+ if (hash) {
+ memcpy(buf, hash, 4);
+ memset(buf + 4, 0, 4);
+ } else
+ memset(buf, 0, 8);
+ memcpy(buf + 8, iname->name + iname->len - 16, 16);
+ oname->name[0] = '_';
+ ret = digest_encode(buf, 24, oname->name + 1);
+ oname->len = ret + 1;
+ return ret + 1;
+}
+
+/**
+ * f2fs_fname_usr_to_disk() - converts a filename from user space to disk space
+ */
+int f2fs_fname_usr_to_disk(struct inode *inode,
+ const struct qstr *iname,
+ struct f2fs_str *oname)
+{
+ int res;
+ struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
+
+ if (is_dot_dotdot(iname)) {
+ oname->name[0] = '.';
+ oname->name[iname->len - 1] = '.';
+ oname->len = iname->len;
+ return oname->len;
+ }
+
+ if (ci) {
+ res = f2fs_fname_encrypt(inode, iname, oname);
+ return res;
+ }
+ /* Without a proper key, a user is not allowed to modify the filenames
+ * in a directory. Consequently, a user space name cannot be mapped to
+ * a disk-space name */
+ return -EACCES;
+}
+
+int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname,
+ int lookup, struct f2fs_filename *fname)
+{
+ struct f2fs_crypt_info *ci;
+ int ret = 0, bigname = 0;
+
+ memset(fname, 0, sizeof(struct f2fs_filename));
+ fname->usr_fname = iname;
+
+ if (!f2fs_encrypted_inode(dir) || is_dot_dotdot(iname)) {
+ fname->disk_name.name = (unsigned char *)iname->name;
+ fname->disk_name.len = iname->len;
+ return 0;
+ }
+ ret = f2fs_get_encryption_info(dir);
+ if (ret)
+ return ret;
+ ci = F2FS_I(dir)->i_crypt_info;
+ if (ci) {
+ ret = f2fs_fname_crypto_alloc_buffer(dir, iname->len,
+ &fname->crypto_buf);
+ if (ret < 0)
+ return ret;
+ ret = f2fs_fname_encrypt(dir, iname, &fname->crypto_buf);
+ if (ret < 0)
+ goto errout;
+ fname->disk_name.name = fname->crypto_buf.name;
+ fname->disk_name.len = fname->crypto_buf.len;
+ return 0;
+ }
+ if (!lookup)
+ return -EACCES;
+
+ /* We don't have the key and we are doing a lookup; decode the
+ * user-supplied name
+ */
+ if (iname->name[0] == '_')
+ bigname = 1;
+ if ((bigname && (iname->len != 33)) ||
+ (!bigname && (iname->len > 43)))
+ return -ENOENT;
+
+ fname->crypto_buf.name = kmalloc(32, GFP_KERNEL);
+ if (fname->crypto_buf.name == NULL)
+ return -ENOMEM;
+ ret = digest_decode(iname->name + bigname, iname->len - bigname,
+ fname->crypto_buf.name);
+ if (ret < 0) {
+ ret = -ENOENT;
+ goto errout;
+ }
+ fname->crypto_buf.len = ret;
+ if (bigname) {
+ memcpy(&fname->hash, fname->crypto_buf.name, 4);
+ } else {
+ fname->disk_name.name = fname->crypto_buf.name;
+ fname->disk_name.len = fname->crypto_buf.len;
+ }
+ return 0;
+errout:
+ f2fs_fname_crypto_free_buffer(&fname->crypto_buf);
+ return ret;
+}
+
+void f2fs_fname_free_filename(struct f2fs_filename *fname)
+{
+ kfree(fname->crypto_buf.name);
+ fname->crypto_buf.name = NULL;
+ fname->usr_fname = NULL;
+ fname->disk_name.name = NULL;
+}
diff --git a/fs/f2fs/crypto_key.c b/fs/f2fs/crypto_key.c
new file mode 100644
index 0000000..9f77de2
--- /dev/null
+++ b/fs/f2fs/crypto_key.c
@@ -0,0 +1,254 @@
+/*
+ * linux/fs/f2fs/crypto_key.c
+ *
+ * Copied from linux/fs/f2fs/crypto_key.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption key functions for f2fs
+ *
+ * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
+ */
+#include <keys/encrypted-type.h>
+#include <keys/user-type.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <uapi/linux/keyctl.h>
+#include <crypto/hash.h>
+#include <linux/f2fs_fs.h>
+
+#include "f2fs.h"
+#include "xattr.h"
+
+static void derive_crypt_complete(struct crypto_async_request *req, int rc)
+{
+ struct f2fs_completion_result *ecr = req->data;
+
+ if (rc == -EINPROGRESS)
+ return;
+
+ ecr->res = rc;
+ complete(&ecr->completion);
+}
+
+/**
+ * f2fs_derive_key_aes() - Derive a key using AES-128-ECB
+ * @deriving_key: Encryption key used for derivatio.
+ * @source_key: Source key to which to apply derivation.
+ * @derived_key: Derived key.
+ *
+ * Return: Zero on success; non-zero otherwise.
+ */
+static int f2fs_derive_key_aes(char deriving_key[F2FS_AES_128_ECB_KEY_SIZE],
+ char source_key[F2FS_AES_256_XTS_KEY_SIZE],
+ char derived_key[F2FS_AES_256_XTS_KEY_SIZE])
+{
+ int res = 0;
+ struct ablkcipher_request *req = NULL;
+ DECLARE_F2FS_COMPLETION_RESULT(ecr);
+ struct scatterlist src_sg, dst_sg;
+ struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0,
+ 0);
+
+ if (IS_ERR(tfm)) {
+ res = PTR_ERR(tfm);
+ tfm = NULL;
+ goto out;
+ }
+ crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+ req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ if (!req) {
+ res = -ENOMEM;
+ goto out;
+ }
+ ablkcipher_request_set_callback(req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ derive_crypt_complete, &ecr);
+ res = crypto_ablkcipher_setkey(tfm, deriving_key,
+ F2FS_AES_128_ECB_KEY_SIZE);
+ if (res < 0)
+ goto out;
+
+ sg_init_one(&src_sg, source_key, F2FS_AES_256_XTS_KEY_SIZE);
+ sg_init_one(&dst_sg, derived_key, F2FS_AES_256_XTS_KEY_SIZE);
+ ablkcipher_request_set_crypt(req, &src_sg, &dst_sg,
+ F2FS_AES_256_XTS_KEY_SIZE, NULL);
+ res = crypto_ablkcipher_encrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ BUG_ON(req->base.data != &ecr);
+ wait_for_completion(&ecr.completion);
+ res = ecr.res;
+ }
+out:
+ if (req)
+ ablkcipher_request_free(req);
+ if (tfm)
+ crypto_free_ablkcipher(tfm);
+ return res;
+}
+
+static void f2fs_free_crypt_info(struct f2fs_crypt_info *ci)
+{
+ if (!ci)
+ return;
+
+ key_put(ci->ci_keyring_key);
+ crypto_free_ablkcipher(ci->ci_ctfm);
+ kmem_cache_free(f2fs_crypt_info_cachep, ci);
+}
+
+void f2fs_free_encryption_info(struct inode *inode, struct f2fs_crypt_info *ci)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct f2fs_crypt_info *prev;
+
+ if (ci == NULL)
+ ci = ACCESS_ONCE(fi->i_crypt_info);
+ if (ci == NULL)
+ return;
+ prev = cmpxchg(&fi->i_crypt_info, ci, NULL);
+ if (prev != ci)
+ return;
+
+ f2fs_free_crypt_info(ci);
+}
+
+int _f2fs_get_encryption_info(struct inode *inode)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct f2fs_crypt_info *crypt_info;
+ char full_key_descriptor[F2FS_KEY_DESC_PREFIX_SIZE +
+ (F2FS_KEY_DESCRIPTOR_SIZE * 2) + 1];
+ struct key *keyring_key = NULL;
+ struct f2fs_encryption_key *master_key;
+ struct f2fs_encryption_context ctx;
+ struct user_key_payload *ukp;
+ struct crypto_ablkcipher *ctfm;
+ const char *cipher_str;
+ char raw_key[F2FS_MAX_KEY_SIZE];
+ char mode;
+ int res;
+
+ res = f2fs_crypto_initialize();
+ if (res)
+ return res;
+retry:
+ crypt_info = ACCESS_ONCE(fi->i_crypt_info);
+ if (crypt_info) {
+ if (!crypt_info->ci_keyring_key ||
+ key_validate(crypt_info->ci_keyring_key) == 0)
+ return 0;
+ f2fs_free_encryption_info(inode, crypt_info);
+ goto retry;
+ }
+
+ res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+ F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &ctx, sizeof(ctx), NULL);
+ if (res < 0)
+ return res;
+ else if (res != sizeof(ctx))
+ return -EINVAL;
+ res = 0;
+
+ crypt_info = kmem_cache_alloc(f2fs_crypt_info_cachep, GFP_NOFS);
+ if (!crypt_info)
+ return -ENOMEM;
+
+ crypt_info->ci_flags = ctx.flags;
+ crypt_info->ci_data_mode = ctx.contents_encryption_mode;
+ crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
+ crypt_info->ci_ctfm = NULL;
+ crypt_info->ci_keyring_key = NULL;
+ memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
+ sizeof(crypt_info->ci_master_key));
+ if (S_ISREG(inode->i_mode))
+ mode = crypt_info->ci_data_mode;
+ else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+ mode = crypt_info->ci_filename_mode;
+ else
+ BUG();
+
+ switch (mode) {
+ case F2FS_ENCRYPTION_MODE_AES_256_XTS:
+ cipher_str = "xts(aes)";
+ break;
+ case F2FS_ENCRYPTION_MODE_AES_256_CTS:
+ cipher_str = "cts(cbc(aes))";
+ break;
+ default:
+ printk_once(KERN_WARNING
+ "f2fs: unsupported key mode %d (ino %u)\n",
+ mode, (unsigned) inode->i_ino);
+ res = -ENOKEY;
+ goto out;
+ }
+
+ memcpy(full_key_descriptor, F2FS_KEY_DESC_PREFIX,
+ F2FS_KEY_DESC_PREFIX_SIZE);
+ sprintf(full_key_descriptor + F2FS_KEY_DESC_PREFIX_SIZE,
+ "%*phN", F2FS_KEY_DESCRIPTOR_SIZE,
+ ctx.master_key_descriptor);
+ full_key_descriptor[F2FS_KEY_DESC_PREFIX_SIZE +
+ (2 * F2FS_KEY_DESCRIPTOR_SIZE)] = '\0';
+ keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
+ if (IS_ERR(keyring_key)) {
+ res = PTR_ERR(keyring_key);
+ keyring_key = NULL;
+ goto out;
+ }
+ crypt_info->ci_keyring_key = keyring_key;
+ BUG_ON(keyring_key->type != &key_type_logon);
+ ukp = ((struct user_key_payload *)keyring_key->payload.data);
+ if (ukp->datalen != sizeof(struct f2fs_encryption_key)) {
+ res = -EINVAL;
+ goto out;
+ }
+ master_key = (struct f2fs_encryption_key *)ukp->data;
+ BUILD_BUG_ON(F2FS_AES_128_ECB_KEY_SIZE !=
+ F2FS_KEY_DERIVATION_NONCE_SIZE);
+ BUG_ON(master_key->size != F2FS_AES_256_XTS_KEY_SIZE);
+ res = f2fs_derive_key_aes(ctx.nonce, master_key->raw,
+ raw_key);
+ if (res)
+ goto out;
+
+ ctfm = crypto_alloc_ablkcipher(cipher_str, 0, 0);
+ if (!ctfm || IS_ERR(ctfm)) {
+ res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
+ printk(KERN_DEBUG
+ "%s: error %d (inode %u) allocating crypto tfm\n",
+ __func__, res, (unsigned) inode->i_ino);
+ goto out;
+ }
+ crypt_info->ci_ctfm = ctfm;
+ crypto_ablkcipher_clear_flags(ctfm, ~0);
+ crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctfm),
+ CRYPTO_TFM_REQ_WEAK_KEY);
+ res = crypto_ablkcipher_setkey(ctfm, raw_key,
+ f2fs_encryption_key_size(mode));
+ if (res)
+ goto out;
+
+ memzero_explicit(raw_key, sizeof(raw_key));
+ if (cmpxchg(&fi->i_crypt_info, NULL, crypt_info) != NULL) {
+ f2fs_free_crypt_info(crypt_info);
+ goto retry;
+ }
+ return 0;
+
+out:
+ if (res == -ENOKEY && !S_ISREG(inode->i_mode))
+ res = 0;
+
+ f2fs_free_crypt_info(crypt_info);
+ memzero_explicit(raw_key, sizeof(raw_key));
+ return res;
+}
+
+int f2fs_has_encryption_key(struct inode *inode)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+
+ return (fi->i_crypt_info != NULL);
+}
diff --git a/fs/f2fs/crypto_policy.c b/fs/f2fs/crypto_policy.c
new file mode 100644
index 0000000..d4a96af
--- /dev/null
+++ b/fs/f2fs/crypto_policy.c
@@ -0,0 +1,209 @@
+/*
+ * copied from linux/fs/ext4/crypto_policy.c
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility.
+ *
+ * This contains encryption policy functions for f2fs with some modifications
+ * to support f2fs-specific xattr APIs.
+ *
+ * Written by Michael Halcrow, 2015.
+ * Modified by Jaegeuk Kim, 2015.
+ */
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/f2fs_fs.h>
+
+#include "f2fs.h"
+#include "xattr.h"
+
+static int f2fs_inode_has_encryption_context(struct inode *inode)
+{
+ int res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+ F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, NULL, 0, NULL);
+ return (res > 0);
+}
+
+/*
+ * check whether the policy is consistent with the encryption context
+ * for the inode
+ */
+static int f2fs_is_encryption_context_consistent_with_policy(
+ struct inode *inode, const struct f2fs_encryption_policy *policy)
+{
+ struct f2fs_encryption_context ctx;
+ int res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+ F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
+ sizeof(ctx), NULL);
+
+ if (res != sizeof(ctx))
+ return 0;
+
+ return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
+ F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+ (ctx.flags == policy->flags) &&
+ (ctx.contents_encryption_mode ==
+ policy->contents_encryption_mode) &&
+ (ctx.filenames_encryption_mode ==
+ policy->filenames_encryption_mode));
+}
+
+static int f2fs_create_encryption_context_from_policy(
+ struct inode *inode, const struct f2fs_encryption_policy *policy)
+{
+ struct f2fs_encryption_context ctx;
+
+ ctx.format = F2FS_ENCRYPTION_CONTEXT_FORMAT_V1;
+ memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
+ F2FS_KEY_DESCRIPTOR_SIZE);
+
+ if (!f2fs_valid_contents_enc_mode(policy->contents_encryption_mode)) {
+ printk(KERN_WARNING
+ "%s: Invalid contents encryption mode %d\n", __func__,
+ policy->contents_encryption_mode);
+ return -EINVAL;
+ }
+
+ if (!f2fs_valid_filenames_enc_mode(policy->filenames_encryption_mode)) {
+ printk(KERN_WARNING
+ "%s: Invalid filenames encryption mode %d\n", __func__,
+ policy->filenames_encryption_mode);
+ return -EINVAL;
+ }
+
+ if (policy->flags & ~F2FS_POLICY_FLAGS_VALID)
+ return -EINVAL;
+
+ ctx.contents_encryption_mode = policy->contents_encryption_mode;
+ ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
+ ctx.flags = policy->flags;
+ BUILD_BUG_ON(sizeof(ctx.nonce) != F2FS_KEY_DERIVATION_NONCE_SIZE);
+ get_random_bytes(ctx.nonce, F2FS_KEY_DERIVATION_NONCE_SIZE);
+
+ return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+ F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
+ sizeof(ctx), NULL, XATTR_CREATE);
+}
+
+int f2fs_process_policy(const struct f2fs_encryption_policy *policy,
+ struct inode *inode)
+{
+ if (policy->version != 0)
+ return -EINVAL;
+
+ if (!S_ISDIR(inode->i_mode))
+ return -EINVAL;
+
+ if (!f2fs_inode_has_encryption_context(inode)) {
+ if (!f2fs_empty_dir(inode))
+ return -ENOTEMPTY;
+ return f2fs_create_encryption_context_from_policy(inode,
+ policy);
+ }
+
+ if (f2fs_is_encryption_context_consistent_with_policy(inode, policy))
+ return 0;
+
+ printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
+ __func__);
+ return -EINVAL;
+}
+
+int f2fs_get_policy(struct inode *inode, struct f2fs_encryption_policy *policy)
+{
+ struct f2fs_encryption_context ctx;
+ int res;
+
+ if (!f2fs_encrypted_inode(inode))
+ return -ENODATA;
+
+ res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+ F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &ctx, sizeof(ctx), NULL);
+ if (res != sizeof(ctx))
+ return -ENODATA;
+ if (ctx.format != F2FS_ENCRYPTION_CONTEXT_FORMAT_V1)
+ return -EINVAL;
+
+ policy->version = 0;
+ policy->contents_encryption_mode = ctx.contents_encryption_mode;
+ policy->filenames_encryption_mode = ctx.filenames_encryption_mode;
+ policy->flags = ctx.flags;
+ memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor,
+ F2FS_KEY_DESCRIPTOR_SIZE);
+ return 0;
+}
+
+int f2fs_is_child_context_consistent_with_parent(struct inode *parent,
+ struct inode *child)
+{
+ struct f2fs_crypt_info *parent_ci, *child_ci;
+ int res;
+
+ if ((parent == NULL) || (child == NULL)) {
+ pr_err("parent %p child %p\n", parent, child);
+ BUG_ON(1);
+ }
+
+ /* no restrictions if the parent directory is not encrypted */
+ if (!f2fs_encrypted_inode(parent))
+ return 1;
+ /* if the child directory is not encrypted, this is always a problem */
+ if (!f2fs_encrypted_inode(child))
+ return 0;
+ res = f2fs_get_encryption_info(parent);
+ if (res)
+ return 0;
+ res = f2fs_get_encryption_info(child);
+ if (res)
+ return 0;
+ parent_ci = F2FS_I(parent)->i_crypt_info;
+ child_ci = F2FS_I(child)->i_crypt_info;
+ if (!parent_ci && !child_ci)
+ return 1;
+ if (!parent_ci || !child_ci)
+ return 0;
+
+ return (memcmp(parent_ci->ci_master_key,
+ child_ci->ci_master_key,
+ F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+ (parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
+ (parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
+ (parent_ci->ci_flags == child_ci->ci_flags));
+}
+
+/**
+ * f2fs_inherit_context() - Sets a child context from its parent
+ * @parent: Parent inode from which the context is inherited.
+ * @child: Child inode that inherits the context from @parent.
+ *
+ * Return: Zero on success, non-zero otherwise
+ */
+int f2fs_inherit_context(struct inode *parent, struct inode *child,
+ struct page *ipage)
+{
+ struct f2fs_encryption_context ctx;
+ struct f2fs_crypt_info *ci;
+ int res;
+
+ res = f2fs_get_encryption_info(parent);
+ if (res < 0)
+ return res;
+
+ ci = F2FS_I(parent)->i_crypt_info;
+ BUG_ON(ci == NULL);
+
+ ctx.format = F2FS_ENCRYPTION_CONTEXT_FORMAT_V1;
+
+ ctx.contents_encryption_mode = ci->ci_data_mode;
+ ctx.filenames_encryption_mode = ci->ci_filename_mode;
+ ctx.flags = ci->ci_flags;
+ memcpy(ctx.master_key_descriptor, ci->ci_master_key,
+ F2FS_KEY_DESCRIPTOR_SIZE);
+
+ get_random_bytes(ctx.nonce, F2FS_KEY_DERIVATION_NONCE_SIZE);
+ return f2fs_setxattr(child, F2FS_XATTR_INDEX_ENCRYPTION,
+ F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
+ sizeof(ctx), ipage, XATTR_CREATE);
+}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
new file mode 100644
index 0000000..890e736
--- /dev/null
+++ b/fs/f2fs/data.c
@@ -0,0 +1,1725 @@
+/*
+ * fs/f2fs/data.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/buffer_head.h>
+#include <linux/mpage.h>
+#include <linux/aio.h>
+#include <linux/writeback.h>
+#include <linux/backing-dev.h>
+#include <linux/pagevec.h>
+#include <linux/blkdev.h>
+#include <linux/bio.h>
+#include <linux/prefetch.h>
+#include <linux/uio.h>
+#include <linux/cleancache.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include "segment.h"
+#include "trace.h"
+#include <trace/events/f2fs.h>
+
+static void f2fs_read_end_io(struct bio *bio, int err)
+{
+ struct bio_vec *bvec;
+ int i;
+
+ if (f2fs_bio_encrypted(bio)) {
+ if (err) {
+ f2fs_release_crypto_ctx(bio->bi_private);
+ } else {
+ f2fs_end_io_crypto_work(bio->bi_private, bio);
+ return;
+ }
+ }
+
+ __bio_for_each_segment(bvec, bio, i, 0) {
+ 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(bvec, bio, i, 0) {
+ struct page *page = bvec->bv_page;
+
+ f2fs_restore_and_release_control_page(&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;
+
+ bio = f2fs_bio_alloc(npages);
+
+ bio->bi_bdev = sbi->sb->s_bdev;
+ bio->bi_sector = SECTOR_FROM_BLOCK(blk_addr);
+ bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
+ bio->bi_private = is_read ? NULL : 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_io_info *fio)
+{
+ struct bio *bio;
+ struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+
+ trace_f2fs_submit_page_bio(page, fio);
+ f2fs_trace_ios(fio, 0);
+
+ /* Allocate a new bio */
+ bio = __bio_alloc(fio->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);
+ return -EFAULT;
+ }
+
+ submit_bio(fio->rw, bio);
+ return 0;
+}
+
+void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
+{
+ struct f2fs_sb_info *sbi = fio->sbi;
+ enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
+ struct f2fs_bio_info *io;
+ bool is_read = is_read_io(fio->rw);
+ struct page *bio_page;
+
+ 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;
+ }
+
+ bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+
+ if (bio_add_page(io->bio, 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(fio, 0);
+
+ up_write(&io->io_rwsem);
+ trace_f2fs_submit_page_mbio(fio->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;
+}
+
+int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
+{
+ struct extent_info ei;
+ struct inode *inode = dn->inode;
+
+ if (f2fs_lookup_extent_cache(inode, index, &ei)) {
+ dn->data_blkaddr = ei.blk + index - ei.fofs;
+ return 0;
+ }
+
+ return f2fs_reserve_block(dn, index);
+}
+
+struct page *get_read_data_page(struct inode *inode, pgoff_t index,
+ int rw, bool for_write)
+{
+ 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 = {
+ .sbi = F2FS_I_SB(inode),
+ .type = DATA,
+ .rw = rw,
+ .encrypted_page = NULL,
+ };
+
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ return read_mapping_page(mapping, index, NULL);
+
+ page = f2fs_grab_cache_page(mapping, index, for_write);
+ 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)
+ goto put_err;
+ f2fs_put_dnode(&dn);
+
+ if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
+ err = -ENOENT;
+ goto put_err;
+ }
+got_it:
+ if (PageUptodate(page)) {
+ unlock_page(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);
+ unlock_page(page);
+ return page;
+ }
+
+ fio.blk_addr = dn.data_blkaddr;
+ fio.page = page;
+ err = f2fs_submit_page_bio(&fio);
+ if (err)
+ goto put_err;
+ return page;
+
+put_err:
+ f2fs_put_page(page, 1);
+ return ERR_PTR(err);
+}
+
+struct page *find_data_page(struct inode *inode, pgoff_t index)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct page *page;
+
+ page = find_get_page(mapping, index);
+ if (page && PageUptodate(page))
+ return page;
+ f2fs_put_page(page, 0);
+
+ page = get_read_data_page(inode, index, READ_SYNC, false);
+ if (IS_ERR(page))
+ return page;
+
+ if (PageUptodate(page))
+ return page;
+
+ 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,
+ bool for_write)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct page *page;
+repeat:
+ page = get_read_data_page(inode, index, READ_SYNC, for_write);
+ if (IS_ERR(page))
+ return page;
+
+ /* wait for read completion */
+ 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, and if any error occur,
+ * ipage should be released by this function.
+ */
+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;
+repeat:
+ page = f2fs_grab_cache_page(mapping, index, true);
+ if (!page) {
+ /*
+ * before exiting, we should make sure ipage will be released
+ * if any error occur.
+ */
+ f2fs_put_page(ipage, 1);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ set_new_dnode(&dn, inode, ipage, NULL, 0);
+ err = f2fs_reserve_block(&dn, index);
+ if (err) {
+ f2fs_put_page(page, 1);
+ return ERR_PTR(err);
+ }
+ if (!ipage)
+ f2fs_put_dnode(&dn);
+
+ if (PageUptodate(page))
+ goto got_it;
+
+ if (dn.data_blkaddr == NEW_ADDR) {
+ zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+ SetPageUptodate(page);
+ } else {
+ f2fs_put_page(page, 1);
+
+ page = get_read_data_page(inode, index, READ_SYNC, true);
+ if (IS_ERR(page))
+ goto repeat;
+
+ /* wait for read completion */
+ lock_page(page);
+ }
+got_it:
+ if (new_i_size && i_size_read(inode) <
+ ((loff_t)(index + 1) << PAGE_CACHE_SHIFT)) {
+ i_size_write(inode, ((loff_t)(index + 1) << PAGE_CACHE_SHIFT));
+ /* Only the directory inode sets new_i_size */
+ set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
+ }
+ return page;
+}
+
+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);
+ 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) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT))
+ i_size_write(dn->inode,
+ ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT));
+
+ /* direct IO doesn't use extent cache to maximize the performance */
+ f2fs_drop_largest_extent(dn->inode, fofs);
+
+ 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;
+
+ if (unlikely(f2fs_cp_error(sbi)))
+ goto sync_out;
+
+ 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;
+}
+
+/*
+ * f2fs_map_blocks() now supported readahead/bmap/rw direct_IO with
+ * f2fs_map_blocks structure.
+ * 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 f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
+ int create, int flag)
+{
+ unsigned int maxblocks = map->m_len;
+ struct dnode_of_data dn;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ 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;
+
+ map->m_len = 0;
+ map->m_flags = 0;
+
+ /* it only supports block size == page size */
+ pgofs = (pgoff_t)map->m_lblk;
+
+ if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
+ map->m_pblk = ei.blk + pgofs - ei.fofs;
+ map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
+ map->m_flags = F2FS_MAP_MAPPED;
+ 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 || dn.data_blkaddr == NULL_ADDR) {
+ if (create) {
+ if (unlikely(f2fs_cp_error(sbi))) {
+ err = -EIO;
+ goto put_out;
+ }
+ err = __allocate_data_block(&dn);
+ if (err)
+ goto put_out;
+ allocated = true;
+ map->m_flags = F2FS_MAP_NEW;
+ } else {
+ if (flag != F2FS_GET_BLOCK_FIEMAP ||
+ dn.data_blkaddr != NEW_ADDR) {
+ if (flag == F2FS_GET_BLOCK_BMAP)
+ err = -ENOENT;
+ goto put_out;
+ }
+
+ /*
+ * preallocated unwritten block should be mapped
+ * for fiemap.
+ */
+ if (dn.data_blkaddr == NEW_ADDR)
+ map->m_flags = F2FS_MAP_UNWRITTEN;
+ }
+ }
+
+ map->m_flags |= F2FS_MAP_MAPPED;
+ map->m_pblk = dn.data_blkaddr;
+ map->m_len = 1;
+
+ end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+ 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;
+ }
+
+ end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+ }
+
+ if (maxblocks > map->m_len) {
+ block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+
+ if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
+ if (create) {
+ if (unlikely(f2fs_cp_error(sbi))) {
+ err = -EIO;
+ goto sync_out;
+ }
+ err = __allocate_data_block(&dn);
+ if (err)
+ goto sync_out;
+ allocated = true;
+ map->m_flags |= F2FS_MAP_NEW;
+ blkaddr = dn.data_blkaddr;
+ } else {
+ /*
+ * we only merge preallocated unwritten blocks
+ * for fiemap.
+ */
+ if (flag != F2FS_GET_BLOCK_FIEMAP ||
+ blkaddr != NEW_ADDR)
+ goto sync_out;
+ }
+ }
+
+ /* Give more consecutive addresses for the readahead */
+ if ((map->m_pblk != NEW_ADDR &&
+ blkaddr == (map->m_pblk + ofs)) ||
+ (map->m_pblk == NEW_ADDR &&
+ blkaddr == NEW_ADDR)) {
+ ofs++;
+ dn.ofs_in_node++;
+ pgofs++;
+ map->m_len++;
+ 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_map_blocks(inode, map, err);
+ return err;
+}
+
+static int __get_data_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh, int create, int flag)
+{
+ struct f2fs_map_blocks map;
+ int ret;
+
+ map.m_lblk = iblock;
+ map.m_len = bh->b_size >> inode->i_blkbits;
+
+ ret = f2fs_map_blocks(inode, &map, create, flag);
+ if (!ret) {
+ map_bh(bh, inode->i_sb, map.m_pblk);
+ bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
+ bh->b_size = map.m_len << inode->i_blkbits;
+ }
+ return ret;
+}
+
+static int get_data_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create, int flag)
+{
+ return __get_data_block(inode, iblock, bh_result, create, flag);
+}
+
+static int get_data_block_dio(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ return __get_data_block(inode, iblock, bh_result, create,
+ F2FS_GET_BLOCK_DIO);
+}
+
+static int get_data_block_bmap(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ return __get_data_block(inode, iblock, bh_result, create,
+ F2FS_GET_BLOCK_BMAP);
+}
+
+static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
+{
+ return (offset >> inode->i_blkbits);
+}
+
+static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
+{
+ return (blk << inode->i_blkbits);
+}
+
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ struct buffer_head map_bh;
+ sector_t start_blk, last_blk;
+ loff_t isize = i_size_read(inode);
+ u64 logical = 0, phys = 0, size = 0;
+ u32 flags = 0;
+ bool past_eof = false, whole_file = false;
+ int ret = 0;
+
+ ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
+ if (ret)
+ return ret;
+
+ if (f2fs_has_inline_data(inode)) {
+ ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len);
+ if (ret != -EAGAIN)
+ return ret;
+ }
+
+ mutex_lock(&inode->i_mutex);
+
+ if (len >= isize) {
+ whole_file = true;
+ len = isize;
+ }
+
+ if (logical_to_blk(inode, len) == 0)
+ len = blk_to_logical(inode, 1);
+
+ start_blk = logical_to_blk(inode, start);
+ last_blk = logical_to_blk(inode, start + len - 1);
+next:
+ memset(&map_bh, 0, sizeof(struct buffer_head));
+ map_bh.b_size = len;
+
+ ret = get_data_block(inode, start_blk, &map_bh, 0,
+ F2FS_GET_BLOCK_FIEMAP);
+ if (ret)
+ goto out;
+
+ /* HOLE */
+ if (!buffer_mapped(&map_bh)) {
+ start_blk++;
+
+ if (!past_eof && blk_to_logical(inode, start_blk) >= isize)
+ past_eof = 1;
+
+ if (past_eof && size) {
+ flags |= FIEMAP_EXTENT_LAST;
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size, flags);
+ } else if (size) {
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size, flags);
+ size = 0;
+ }
+
+ /* if we have holes up to/past EOF then we're done */
+ if (start_blk > last_blk || past_eof || ret)
+ goto out;
+ } else {
+ if (start_blk > last_blk && !whole_file) {
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size, flags);
+ goto out;
+ }
+
+ /*
+ * if size != 0 then we know we already have an extent
+ * to add, so add it.
+ */
+ if (size) {
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size, flags);
+ if (ret)
+ goto out;
+ }
+
+ logical = blk_to_logical(inode, start_blk);
+ phys = blk_to_logical(inode, map_bh.b_blocknr);
+ size = map_bh.b_size;
+ flags = 0;
+ if (buffer_unwritten(&map_bh))
+ flags = FIEMAP_EXTENT_UNWRITTEN;
+
+ start_blk += logical_to_blk(inode, size);
+
+ /*
+ * If we are past the EOF, then we need to make sure as
+ * soon as we find a hole that the last extent we found
+ * is marked with FIEMAP_EXTENT_LAST
+ */
+ if (!past_eof && logical + size >= isize)
+ past_eof = true;
+ }
+ cond_resched();
+ if (fatal_signal_pending(current))
+ ret = -EINTR;
+ else
+ goto next;
+out:
+ if (ret == 1)
+ ret = 0;
+
+ mutex_unlock(&inode->i_mutex);
+ return ret;
+}
+
+/*
+ * This function was originally taken from fs/mpage.c, and customized for f2fs.
+ * Major change was from block_size == page_size in f2fs by default.
+ */
+static int f2fs_mpage_readpages(struct address_space *mapping,
+ struct list_head *pages, struct page *page,
+ unsigned nr_pages)
+{
+ struct bio *bio = NULL;
+ unsigned page_idx;
+ sector_t last_block_in_bio = 0;
+ struct inode *inode = mapping->host;
+ const unsigned blkbits = inode->i_blkbits;
+ const unsigned blocksize = 1 << blkbits;
+ sector_t block_in_file;
+ sector_t last_block;
+ sector_t last_block_in_file;
+ sector_t block_nr;
+ struct block_device *bdev = inode->i_sb->s_bdev;
+ struct f2fs_map_blocks map;
+
+ map.m_pblk = 0;
+ map.m_lblk = 0;
+ map.m_len = 0;
+ map.m_flags = 0;
+
+ for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
+
+ prefetchw(&page->flags);
+ if (pages) {
+ page = list_entry(pages->prev, struct page, lru);
+ list_del(&page->lru);
+ if (add_to_page_cache_lru(page, mapping,
+ page->index, GFP_KERNEL))
+ goto next_page;
+ }
+
+ block_in_file = (sector_t)page->index;
+ last_block = block_in_file + nr_pages;
+ last_block_in_file = (i_size_read(inode) + blocksize - 1) >>
+ blkbits;
+ if (last_block > last_block_in_file)
+ last_block = last_block_in_file;
+
+ /*
+ * Map blocks using the previous result first.
+ */
+ if ((map.m_flags & F2FS_MAP_MAPPED) &&
+ block_in_file > map.m_lblk &&
+ block_in_file < (map.m_lblk + map.m_len))
+ goto got_it;
+
+ /*
+ * Then do more f2fs_map_blocks() calls until we are
+ * done with this page.
+ */
+ map.m_flags = 0;
+
+ if (block_in_file < last_block) {
+ map.m_lblk = block_in_file;
+ map.m_len = last_block - block_in_file;
+
+ if (f2fs_map_blocks(inode, &map, 0,
+ F2FS_GET_BLOCK_READ))
+ goto set_error_page;
+ }
+got_it:
+ if ((map.m_flags & F2FS_MAP_MAPPED)) {
+ block_nr = map.m_pblk + block_in_file - map.m_lblk;
+ SetPageMappedToDisk(page);
+
+ if (!PageUptodate(page) && !cleancache_get_page(page)) {
+ SetPageUptodate(page);
+ goto confused;
+ }
+ } else {
+ zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+ SetPageUptodate(page);
+ unlock_page(page);
+ goto next_page;
+ }
+
+ /*
+ * This page will go to BIO. Do we need to send this
+ * BIO off first?
+ */
+ if (bio && (last_block_in_bio != block_nr - 1)) {
+submit_and_realloc:
+ submit_bio(READ, bio);
+ bio = NULL;
+ }
+ if (bio == NULL) {
+ struct f2fs_crypto_ctx *ctx = NULL;
+
+ if (f2fs_encrypted_inode(inode) &&
+ S_ISREG(inode->i_mode)) {
+
+ ctx = f2fs_get_crypto_ctx(inode);
+ if (IS_ERR(ctx))
+ goto set_error_page;
+
+ /* wait the page to be moved by cleaning */
+ f2fs_wait_on_encrypted_page_writeback(
+ F2FS_I_SB(inode), block_nr);
+ }
+
+ bio = bio_alloc(GFP_KERNEL,
+ min_t(int, nr_pages, BIO_MAX_PAGES));
+ if (!bio) {
+ if (ctx)
+ f2fs_release_crypto_ctx(ctx);
+ goto set_error_page;
+ }
+ bio->bi_bdev = bdev;
+ bio->bi_sector = SECTOR_FROM_BLOCK(block_nr);
+ bio->bi_end_io = f2fs_read_end_io;
+ bio->bi_private = ctx;
+ }
+
+ if (bio_add_page(bio, page, blocksize, 0) < blocksize)
+ goto submit_and_realloc;
+
+ last_block_in_bio = block_nr;
+ goto next_page;
+set_error_page:
+ SetPageError(page);
+ zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+ unlock_page(page);
+ goto next_page;
+confused:
+ if (bio) {
+ submit_bio(READ, bio);
+ bio = NULL;
+ }
+ unlock_page(page);
+next_page:
+ if (pages)
+ page_cache_release(page);
+ }
+ BUG_ON(pages && !list_empty(pages));
+ if (bio)
+ submit_bio(READ, bio);
+ return 0;
+}
+
+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 = f2fs_mpage_readpages(page->mapping, NULL, page, 1);
+ 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;
+ struct page *page = list_entry(pages->prev, struct page, lru);
+
+ trace_f2fs_readpages(inode, page, nr_pages);
+
+ /* If the file has inline data, skip readpages */
+ if (f2fs_has_inline_data(inode))
+ return 0;
+
+ return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages);
+}
+
+int do_write_data_page(struct f2fs_io_info *fio)
+{
+ struct page *page = fio->page;
+ 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;
+ }
+
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+
+ /* wait for GCed encrypted page writeback */
+ f2fs_wait_on_encrypted_page_writeback(F2FS_I_SB(inode),
+ fio->blk_addr);
+
+ fio->encrypted_page = f2fs_encrypt(inode, fio->page);
+ if (IS_ERR(fio->encrypted_page)) {
+ err = PTR_ERR(fio->encrypted_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(fio);
+ set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
+ trace_f2fs_do_write_data_page(page, IPU);
+ } else {
+ write_data_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 = {
+ .sbi = sbi,
+ .type = DATA,
+ .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
+ .page = page,
+ .encrypted_page = NULL,
+ };
+
+ 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(&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(&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;
+}
+
+/*
+ * This function was copied from write_cche_pages from mm/page-writeback.c.
+ * The major change is making write step of cold data page separately from
+ * warm/hot data page.
+ */
+static int f2fs_write_cache_pages(struct address_space *mapping,
+ struct writeback_control *wbc, writepage_t writepage,
+ void *data)
+{
+ int ret = 0;
+ int done = 0;
+ struct pagevec pvec;
+ int nr_pages;
+ pgoff_t uninitialized_var(writeback_index);
+ pgoff_t index;
+ pgoff_t end; /* Inclusive */
+ pgoff_t done_index;
+ int cycled;
+ int range_whole = 0;
+ int tag;
+ int step = 0;
+
+ pagevec_init(&pvec, 0);
+next:
+ if (wbc->range_cyclic) {
+ writeback_index = mapping->writeback_index; /* prev offset */
+ index = writeback_index;
+ if (index == 0)
+ cycled = 1;
+ else
+ cycled = 0;
+ end = -1;
+ } else {
+ index = wbc->range_start >> PAGE_CACHE_SHIFT;
+ end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+ range_whole = 1;
+ cycled = 1; /* ignore range_cyclic tests */
+ }
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+ tag = PAGECACHE_TAG_TOWRITE;
+ else
+ tag = PAGECACHE_TAG_DIRTY;
+retry:
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+ tag_pages_for_writeback(mapping, index, end);
+ done_index = index;
+ while (!done && (index <= end)) {
+ int i;
+
+ nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
+ 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];
+
+ if (page->index > end) {
+ done = 1;
+ break;
+ }
+
+ done_index = page->index;
+
+ 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 (step == is_cold_data(page))
+ goto continue_unlock;
+
+ if (PageWriteback(page)) {
+ if (wbc->sync_mode != WB_SYNC_NONE)
+ f2fs_wait_on_page_writeback(page, DATA);
+ else
+ goto continue_unlock;
+ }
+
+ BUG_ON(PageWriteback(page));
+ if (!clear_page_dirty_for_io(page))
+ goto continue_unlock;
+
+ ret = (*writepage)(page, wbc, data);
+ if (unlikely(ret)) {
+ if (ret == AOP_WRITEPAGE_ACTIVATE) {
+ unlock_page(page);
+ ret = 0;
+ } else {
+ done_index = page->index + 1;
+ done = 1;
+ break;
+ }
+ }
+
+ if (--wbc->nr_to_write <= 0 &&
+ wbc->sync_mode == WB_SYNC_NONE) {
+ done = 1;
+ break;
+ }
+ }
+ pagevec_release(&pvec);
+ cond_resched();
+ }
+
+ if (step < 1) {
+ step++;
+ goto next;
+ }
+
+ if (!cycled && !done) {
+ cycled = 1;
+ index = 0;
+ end = writeback_index - 1;
+ goto retry;
+ }
+ if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+ mapping->writeback_index = done_index;
+
+ 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;
+
+ /* skip writing if there is no dirty page in this inode */
+ if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE)
+ 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 = f2fs_write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
+ f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ if (locked)
+ mutex_unlock(&sbi->writepages);
+
+ 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, 0, 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 = NULL;
+ struct 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_get_block(&dn, index);
+ if (err)
+ goto put_fail;
+put_next:
+ f2fs_put_dnode(&dn);
+ f2fs_unlock_op(sbi);
+
+ f2fs_wait_on_page_writeback(page, DATA);
+
+ /* wait for GCed encrypted page writeback */
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
+
+ if (len == PAGE_CACHE_SIZE)
+ goto out_update;
+ if (PageUptodate(page))
+ goto out_clear;
+
+ 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_update;
+ }
+
+ if (dn.data_blkaddr == NEW_ADDR) {
+ zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+ } else {
+ struct f2fs_io_info fio = {
+ .sbi = sbi,
+ .type = DATA,
+ .rw = READ_SYNC,
+ .blk_addr = dn.data_blkaddr,
+ .page = page,
+ .encrypted_page = NULL,
+ };
+ err = f2fs_submit_page_bio(&fio);
+ if (err)
+ goto fail;
+
+ lock_page(page);
+ if (unlikely(!PageUptodate(page))) {
+ err = -EIO;
+ goto fail;
+ }
+ if (unlikely(page->mapping != mapping)) {
+ f2fs_put_page(page, 1);
+ goto repeat;
+ }
+
+ /* avoid symlink page */
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+ err = f2fs_decrypt_one(inode, page);
+ if (err)
+ goto fail;
+ }
+ }
+out_update:
+ SetPageUptodate(page);
+out_clear:
+ clear_cold_data(page);
+ return 0;
+
+put_fail:
+ f2fs_put_dnode(&dn);
+unlock_fail:
+ f2fs_unlock_op(sbi);
+fail:
+ f2fs_put_page(page, 1);
+ 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 ssize_t check_direct_IO(struct inode *inode, int rw,
+ const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+{
+ unsigned blocksize_mask = inode->i_sb->s_blocksize - 1;
+ int seg, i;
+ size_t size;
+ unsigned long addr;
+ ssize_t retval = -EINVAL;
+ loff_t end = offset;
+
+ if (offset & blocksize_mask)
+ return -EINVAL;
+
+ /* Check the memory alignment. Blocks cannot straddle pages */
+ for (seg = 0; seg < nr_segs; seg++) {
+ addr = (unsigned long)iov[seg].iov_base;
+ size = iov[seg].iov_len;
+ end += size;
+ if ((addr & blocksize_mask) || (size & blocksize_mask))
+ goto out;
+
+ /* If this is a write we don't need to check anymore */
+ if (rw & WRITE)
+ continue;
+
+ /*
+ * Check to make sure we don't have duplicate iov_base's in this
+ * iovec, if so return EINVAL, otherwise we'll get csum errors
+ * when reading back.
+ */
+ for (i = seg + 1; i < nr_segs; i++) {
+ if (iov[seg].iov_base == iov[i].iov_base)
+ goto out;
+ }
+ }
+ retval = 0;
+out:
+ return retval;
+}
+
+static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
+ const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs)
+{
+ struct file *file = iocb->ki_filp;
+ struct address_space *mapping = file->f_mapping;
+ struct inode *inode = mapping->host;
+ size_t count = iov_length(iov, nr_segs);
+ 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 (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ return 0;
+
+ err = check_direct_IO(inode, rw, iov, offset, nr_segs);
+ if (err)
+ return err;
+
+ trace_f2fs_direct_IO_enter(inode, offset, count, rw);
+
+ if (rw & WRITE) {
+ __allocate_data_blocks(inode, offset, count);
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) {
+ err = -EIO;
+ goto out;
+ }
+ }
+
+ err = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
+ get_data_block_dio);
+out:
+ if (err < 0 && (rw & WRITE))
+ f2fs_write_failed(mapping, offset + count);
+
+ trace_f2fs_direct_IO_exit(inode, offset, count, rw, err);
+
+ return err;
+}
+
+void f2fs_invalidate_page(struct page *page, unsigned long offset)
+{
+ 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))
+ 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);
+ }
+
+ /* This is atomic written page, keep Private */
+ if (IS_ATOMIC_WRITTEN_PAGE(page))
+ return;
+
+ ClearPagePrivate(page);
+}
+
+int f2fs_release_page(struct page *page, gfp_t wait)
+{
+ /* If this is dirty page, keep PagePrivate */
+ if (PageDirty(page))
+ return 0;
+
+ /* This is atomic written page, keep Private */
+ if (IS_ATOMIC_WRITTEN_PAGE(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)) {
+ if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
+ register_inmem_page(inode, page);
+ return 1;
+ }
+ /*
+ * Previously, this page has been registered, we just
+ * return here.
+ */
+ return 0;
+ }
+
+ 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;
+
+ if (f2fs_has_inline_data(inode))
+ return 0;
+
+ /* make sure allocating whole blocks */
+ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+ filemap_write_and_wait(mapping);
+
+ return generic_block_bmap(mapping, block, get_data_block_bmap);
+}
+
+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/fs/f2fs/debug.c b/fs/f2fs/debug.c
new file mode 100644
index 0000000..478e5d5
--- /dev/null
+++ b/fs/f2fs/debug.c
@@ -0,0 +1,432 @@
+/*
+ * 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_largest = atomic64_read(&sbi->read_hit_largest);
+ si->hit_cached = atomic64_read(&sbi->read_hit_cached);
+ si->hit_rbtree = atomic64_read(&sbi->read_hit_rbtree);
+ si->hit_total = si->hit_largest + si->hit_cached + si->hit_rbtree;
+ si->total_ext = atomic64_read(&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_xattr = atomic_read(&sbi->inline_xattr);
+ 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 long long blks_per_sec, hblks_per_sec, total_vblocks;
+ unsigned long long bimodal, dist;
+ unsigned int segno, vblocks;
+ int ndirty = 0;
+
+ bimodal = 0;
+ total_vblocks = 0;
+ blks_per_sec = 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 = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100);
+ si->bimodal = div64_u64(bimodal, dist);
+ if (si->dirty_count)
+ si->avg_vblocks = div_u64(total_vblocks, ndirty);
+ else
+ si->avg_vblocks = 0;
+}
+
+/*
+ * 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 += 3 * 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 += (unsigned long long)npages << PAGE_CACHE_SHIFT;
+ npages = META_MAPPING(sbi)->nrpages;
+ si->page_mem += (unsigned long long)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_xattr Inode: %u\n",
+ si->inline_xattr);
+ seq_printf(s, " - Inline_data Inode: %u\n",
+ si->inline_inode);
+ seq_printf(s, " - Inline_dentry Inode: %u\n",
+ si->inline_dir);
+ seq_printf(s, "\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_puts(s, "\nExtent Cache:\n");
+ seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n",
+ si->hit_largest, si->hit_cached,
+ si->hit_rbtree);
+ seq_printf(s, " - Hit Ratio: %llu%% (%llu / %llu)\n",
+ !si->total_ext ? 0 :
+ div64_u64(si->hit_total * 100, si->total_ext),
+ si->hit_total, si->total_ext);
+ seq_printf(s, " - Inner Struct Count: tree: %d, node: %d\n",
+ si->ext_tree, 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: %llu KB\n",
+ (si->base_mem + si->cache_mem + si->page_mem) >> 10);
+ seq_printf(s, " - static: %llu KB\n",
+ si->base_mem >> 10);
+ seq_printf(s, " - cached: %llu KB\n",
+ si->cache_mem >> 10);
+ seq_printf(s, " - paged : %llu 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;
+
+ atomic64_set(&sbi->total_hit_ext, 0);
+ atomic64_set(&sbi->read_hit_rbtree, 0);
+ atomic64_set(&sbi->read_hit_largest, 0);
+ atomic64_set(&sbi->read_hit_cached, 0);
+
+ atomic_set(&sbi->inline_xattr, 0);
+ 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/fs/f2fs/dir.c b/fs/f2fs/dir.c
new file mode 100644
index 0000000..f11d32b
--- /dev/null
+++ b/fs/f2fs/dir.c
@@ -0,0 +1,902 @@
+/*
+ * 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 struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
+ struct f2fs_filename *fname,
+ f2fs_hash_t namehash,
+ 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(NULL, &d, (void *)dentry_blk, 1);
+ de = find_target_dentry(fname, namehash, 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 f2fs_filename *fname,
+ f2fs_hash_t namehash, int *max_slots,
+ struct f2fs_dentry_ptr *d)
+{
+ struct f2fs_dir_entry *de;
+ unsigned long bit_pos = 0;
+ int max_len = 0;
+ struct f2fs_str de_name = FSTR_INIT(NULL, 0);
+ struct f2fs_str *name = &fname->disk_name;
+
+ 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];
+
+ /* encrypted case */
+ de_name.name = d->filename[bit_pos];
+ de_name.len = le16_to_cpu(de->name_len);
+
+ /* show encrypted name */
+ if (fname->hash) {
+ if (de->hash_code == fname->hash)
+ goto found;
+ } else if (de_name.len == name->len &&
+ de->hash_code == namehash &&
+ !memcmp(de_name.name, 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 f2fs_filename *fname,
+ struct page **res_page)
+{
+ struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
+ 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_hash_t namehash;
+
+ namehash = f2fs_dentry_hash(&name);
+
+ 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);
+ if (IS_ERR(dentry_page)) {
+ room = true;
+ continue;
+ }
+
+ de = find_in_block(dentry_page, fname, namehash, &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;
+ unsigned int max_depth;
+ unsigned int level;
+ struct f2fs_filename fname;
+ int err;
+
+ *res_page = NULL;
+
+ err = f2fs_fname_setup_filename(dir, child, 1, &fname);
+ if (err)
+ return NULL;
+
+ if (f2fs_has_inline_dentry(dir)) {
+ de = find_in_inline_dir(dir, &fname, res_page);
+ goto out;
+ }
+
+ if (npages == 0)
+ goto out;
+
+ max_depth = F2FS_I(dir)->i_current_depth;
+
+ for (level = 0; level < max_depth; level++) {
+ de = find_in_level(dir, level, &fname, res_page);
+ if (de)
+ break;
+ }
+out:
+ f2fs_fname_free_filename(&fname);
+ 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, false);
+ 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, struct inode *to,
+ const struct qstr *name)
+{
+ struct page *page;
+
+ if (file_enc_name(to))
+ return 0;
+
+ 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(NULL, &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;
+
+ if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) {
+ err = f2fs_inherit_context(dir, inode, 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;
+ struct page *dentry_page = NULL;
+ struct f2fs_dentry_block *dentry_blk = NULL;
+ struct f2fs_dentry_ptr d;
+ struct page *page = NULL;
+ struct f2fs_filename fname;
+ struct qstr new_name;
+ int slots, err;
+
+ err = f2fs_fname_setup_filename(dir, name, 0, &fname);
+ if (err)
+ return err;
+
+ new_name.name = fname_name(&fname);
+ new_name.len = fname_len(&fname);
+
+ if (f2fs_has_inline_dentry(dir)) {
+ err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
+ if (!err || err != -EAGAIN)
+ goto out;
+ else
+ err = 0;
+ }
+
+ level = 0;
+ slots = GET_DENTRY_SLOTS(new_name.len);
+ dentry_hash = f2fs_dentry_hash(&new_name);
+
+ 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)) {
+ err = -ENOSPC;
+ goto out;
+ }
+
+ /* 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)) {
+ err = PTR_ERR(dentry_page);
+ goto out;
+ }
+
+ 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, &new_name, NULL);
+ if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ goto fail;
+ }
+ if (f2fs_encrypted_inode(dir))
+ file_set_enc_name(inode);
+ }
+
+ make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
+ f2fs_update_dentry(ino, mode, &d, &new_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);
+out:
+ f2fs_fname_free_filename(&fname);
+ 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++)
+ test_and_clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
+
+ /* Let's check and deallocate this dentry page */
+ bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
+ NR_DENTRY_IN_BLOCK,
+ 0);
+ kunmap(page); /* kunmap - pair of f2fs_find_entry */
+ set_page_dirty(page);
+
+ dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+
+ if (inode)
+ 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, false);
+ 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 file *file, void *dirent, filldir_t filldir,
+ struct f2fs_dentry_ptr *d, unsigned int n, unsigned int bit_pos,
+ struct f2fs_str *fstr)
+{
+ unsigned int start_bit_pos = bit_pos;
+ unsigned char d_type;
+ struct f2fs_dir_entry *de = NULL;
+ struct f2fs_str de_name = FSTR_INIT(NULL, 0);
+ unsigned char *types = f2fs_filetype_table;
+ int over;
+
+ while (bit_pos < d->max) {
+ d_type = DT_UNKNOWN;
+ bit_pos = find_next_bit_le(d->bitmap, d->max, bit_pos);
+ if (bit_pos >= d->max)
+ break;
+
+ de = &d->dentry[bit_pos];
+
+ if (types && de->file_type < F2FS_FT_MAX)
+ d_type = types[de->file_type];
+
+ de_name.name = d->filename[bit_pos];
+ de_name.len = le16_to_cpu(de->name_len);
+
+ if (f2fs_encrypted_inode(d->inode)) {
+ int save_len = fstr->len;
+ int ret;
+
+ de_name.name = kmalloc(de_name.len, GFP_NOFS);
+ if (!de_name.name)
+ return false;
+
+ memcpy(de_name.name, d->filename[bit_pos], de_name.len);
+
+ ret = f2fs_fname_disk_to_usr(d->inode, &de->hash_code,
+ &de_name, fstr);
+ kfree(de_name.name);
+ if (ret < 0)
+ return true;
+
+ de_name = *fstr;
+ fstr->len = save_len;
+ }
+
+ over = filldir(dirent, de_name.name, de_name.len,
+ (n * d->max) + bit_pos,
+ le32_to_cpu(de->ino), d_type);
+ if (over) {
+ file->f_pos += bit_pos - start_bit_pos;
+ return true;
+ }
+
+ bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+ }
+ return false;
+}
+
+static int f2fs_readdir(struct file *file, void *dirent, filldir_t filldir)
+{
+ unsigned long pos = file->f_pos;
+ unsigned int bit_pos = 0;
+ 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;
+ struct f2fs_dentry_ptr d;
+ struct f2fs_str fstr = FSTR_INIT(NULL, 0);
+ unsigned int n = 0;
+ int err = 0;
+
+ if (f2fs_encrypted_inode(inode)) {
+ err = f2fs_get_encryption_info(inode);
+ if (err)
+ return err;
+
+ err = f2fs_fname_crypto_alloc_buffer(inode, F2FS_NAME_LEN,
+ &fstr);
+ if (err < 0)
+ return err;
+ }
+
+ if (f2fs_has_inline_dentry(inode)) {
+ err = f2fs_read_inline_dir(file, dirent, filldir, &fstr);
+ goto out;
+ }
+
+ bit_pos = (pos % NR_DENTRY_IN_BLOCK);
+ n = (pos / NR_DENTRY_IN_BLOCK);
+
+ /* 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, false);
+ if (IS_ERR(dentry_page))
+ continue;
+
+ dentry_blk = kmap(dentry_page);
+
+ make_dentry_ptr(inode, &d, (void *)dentry_blk, 1);
+
+ if (f2fs_fill_dentries(file, dirent, filldir, &d, n, bit_pos, &fstr))
+ goto stop;
+
+ bit_pos = 0;
+ file->f_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);
+ }
+out:
+ f2fs_fname_crypto_free_buffer(&fstr);
+ return err;
+}
+
+const struct file_operations f2fs_dir_operations = {
+ .llseek = generic_file_llseek,
+ .read = generic_read_dir,
+ .readdir = f2fs_readdir,
+ .fsync = f2fs_sync_file,
+ .unlocked_ioctl = f2fs_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = f2fs_compat_ioctl,
+#endif
+};
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
new file mode 100644
index 0000000..7ddba81
--- /dev/null
+++ b/fs/f2fs/extent_cache.c
@@ -0,0 +1,748 @@
+/*
+ * f2fs extent cache support
+ *
+ * Copyright (c) 2015 Motorola Mobility
+ * Copyright (c) 2015 Samsung Electronics
+ * Authors: Jaegeuk Kim <jaegeuk@kernel.org>
+ * Chao Yu <chao2.yu@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 <trace/events/f2fs.h>
+
+static struct kmem_cache *extent_tree_slab;
+static struct kmem_cache *extent_node_slab;
+
+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 *__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);
+
+ /* never died until evict_inode */
+ F2FS_I(inode)->extent_tree = et;
+
+ return et;
+}
+
+static struct extent_node *__lookup_extent_tree(struct f2fs_sb_info *sbi,
+ struct extent_tree *et, unsigned int fofs)
+{
+ struct rb_node *node = et->root.rb_node;
+ struct extent_node *en = et->cached_en;
+
+ if (en) {
+ struct extent_info *cei = &en->ei;
+
+ if (cei->fofs <= fofs && cei->fofs + cei->len > fofs) {
+ stat_inc_cached_node_hit(sbi);
+ return 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 {
+ stat_inc_rbtree_node_hit(sbi);
+ return en;
+ }
+ }
+ return NULL;
+}
+
+static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi,
+ struct extent_tree *et, struct extent_info *ei)
+{
+ struct rb_node **p = &et->root.rb_node;
+ struct extent_node *en;
+
+ en = __attach_extent_node(sbi, et, ei, NULL, p);
+ if (!en)
+ return NULL;
+
+ et->largest = en->ei;
+ et->cached_en = en;
+ return en;
+}
+
+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 __drop_largest_extent(struct inode *inode,
+ pgoff_t fofs, unsigned int len)
+{
+ struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest;
+
+ if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs)
+ largest->len = 0;
+}
+
+void f2fs_drop_largest_extent(struct inode *inode, pgoff_t fofs)
+{
+ if (!f2fs_may_extent_tree(inode))
+ return;
+
+ __drop_largest_extent(inode, fofs, 1);
+}
+
+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 (!f2fs_may_extent_tree(inode))
+ return;
+
+ et = __grab_extent_tree(inode);
+
+ if (!i_ext || le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN)
+ return;
+
+ set_extent_info(&ei, le32_to_cpu(i_ext->fofs),
+ le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len));
+
+ write_lock(&et->lock);
+ if (et->count)
+ goto out;
+
+ en = __init_extent_tree(sbi, et, &ei);
+ if (en) {
+ spin_lock(&sbi->extent_lock);
+ list_add_tail(&en->list, &sbi->extent_list);
+ spin_unlock(&sbi->extent_lock);
+ }
+out:
+ write_unlock(&et->lock);
+}
+
+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 = F2FS_I(inode)->extent_tree;
+ struct extent_node *en;
+ bool ret = false;
+
+ f2fs_bug_on(sbi, !et);
+
+ trace_f2fs_lookup_extent_tree_start(inode, pgofs);
+
+ read_lock(&et->lock);
+
+ if (et->largest.fofs <= pgofs &&
+ et->largest.fofs + et->largest.len > pgofs) {
+ *ei = et->largest;
+ ret = true;
+ stat_inc_largest_node_hit(sbi);
+ goto out;
+ }
+
+ en = __lookup_extent_tree(sbi, 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);
+ et->cached_en = en;
+ spin_unlock(&sbi->extent_lock);
+ ret = true;
+ }
+out:
+ stat_inc_total_hit(sbi);
+ read_unlock(&et->lock);
+
+ trace_f2fs_lookup_extent_tree_end(inode, pgofs, ei);
+ return ret;
+}
+
+
+/*
+ * lookup extent at @fofs, if hit, return the extent
+ * if not, return NULL and
+ * @prev_ex: extent before fofs
+ * @next_ex: extent after fofs
+ * @insert_p: insert point for new extent at fofs
+ * in order to simpfy the insertion after.
+ * tree must stay unchanged between lookup and insertion.
+ */
+static struct extent_node *__lookup_extent_tree_ret(struct extent_tree *et,
+ unsigned int fofs,
+ struct extent_node **prev_ex,
+ struct extent_node **next_ex,
+ struct rb_node ***insert_p,
+ struct rb_node **insert_parent)
+{
+ struct rb_node **pnode = &et->root.rb_node;
+ struct rb_node *parent = NULL, *tmp_node;
+ struct extent_node *en = et->cached_en;
+
+ *insert_p = NULL;
+ *insert_parent = NULL;
+ *prev_ex = NULL;
+ *next_ex = NULL;
+
+ if (RB_EMPTY_ROOT(&et->root))
+ return NULL;
+
+ if (en) {
+ struct extent_info *cei = &en->ei;
+
+ if (cei->fofs <= fofs && cei->fofs + cei->len > fofs)
+ goto lookup_neighbors;
+ }
+
+ while (*pnode) {
+ parent = *pnode;
+ en = rb_entry(*pnode, struct extent_node, rb_node);
+
+ if (fofs < en->ei.fofs)
+ pnode = &(*pnode)->rb_left;
+ else if (fofs >= en->ei.fofs + en->ei.len)
+ pnode = &(*pnode)->rb_right;
+ else
+ goto lookup_neighbors;
+ }
+
+ *insert_p = pnode;
+ *insert_parent = parent;
+
+ en = rb_entry(parent, struct extent_node, rb_node);
+ tmp_node = parent;
+ if (parent && fofs > en->ei.fofs)
+ tmp_node = rb_next(parent);
+ *next_ex = tmp_node ?
+ rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+
+ tmp_node = parent;
+ if (parent && fofs < en->ei.fofs)
+ tmp_node = rb_prev(parent);
+ *prev_ex = tmp_node ?
+ rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+ return NULL;
+
+lookup_neighbors:
+ if (fofs == en->ei.fofs) {
+ /* lookup prev node for merging backward later */
+ tmp_node = rb_prev(&en->rb_node);
+ *prev_ex = tmp_node ?
+ rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+ }
+ if (fofs == en->ei.fofs + en->ei.len - 1) {
+ /* lookup next node for merging frontward later */
+ tmp_node = rb_next(&en->rb_node);
+ *next_ex = tmp_node ?
+ rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+ }
+ return en;
+}
+
+static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
+ struct extent_tree *et, struct extent_info *ei,
+ struct extent_node **den,
+ struct extent_node *prev_ex,
+ struct extent_node *next_ex)
+{
+ struct extent_node *en = NULL;
+
+ if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) {
+ prev_ex->ei.len += ei->len;
+ ei = &prev_ex->ei;
+ en = prev_ex;
+ }
+
+ if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) {
+ if (en) {
+ __detach_extent_node(sbi, et, prev_ex);
+ *den = prev_ex;
+ }
+ next_ex->ei.fofs = ei->fofs;
+ next_ex->ei.blk = ei->blk;
+ next_ex->ei.len += ei->len;
+ en = next_ex;
+ }
+
+ if (en) {
+ __try_update_largest_extent(et, en);
+ et->cached_en = en;
+ }
+ return en;
+}
+
+static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
+ struct extent_tree *et, struct extent_info *ei,
+ struct rb_node **insert_p,
+ struct rb_node *insert_parent)
+{
+ struct rb_node **p = &et->root.rb_node;
+ struct rb_node *parent = NULL;
+ struct extent_node *en = NULL;
+
+ if (insert_p && insert_parent) {
+ parent = insert_parent;
+ p = insert_p;
+ goto do_insert;
+ }
+
+ while (*p) {
+ parent = *p;
+ en = rb_entry(parent, struct extent_node, rb_node);
+
+ if (ei->fofs < en->ei.fofs)
+ p = &(*p)->rb_left;
+ else if (ei->fofs >= en->ei.fofs + en->ei.len)
+ p = &(*p)->rb_right;
+ else
+ f2fs_bug_on(sbi, 1);
+ }
+do_insert:
+ en = __attach_extent_node(sbi, et, ei, parent, p);
+ if (!en)
+ return NULL;
+
+ __try_update_largest_extent(et, en);
+ et->cached_en = en;
+ return en;
+}
+
+static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
+ pgoff_t fofs, block_t blkaddr, unsigned int len)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct extent_tree *et = F2FS_I(inode)->extent_tree;
+ struct extent_node *en = NULL, *en1 = NULL;
+ struct extent_node *prev_en = NULL, *next_en = NULL;
+ struct extent_info ei, dei, prev;
+ struct rb_node **insert_p = NULL, *insert_parent = NULL;
+ unsigned int end = fofs + len;
+ unsigned int pos = (unsigned int)fofs;
+
+ if (!et)
+ return false;
+
+ trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len);
+
+ write_lock(&et->lock);
+
+ if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) {
+ write_unlock(&et->lock);
+ return false;
+ }
+
+ prev = et->largest;
+ dei.len = 0;
+
+ /*
+ * drop largest extent before lookup, in case it's already
+ * been shrunk from extent tree
+ */
+ __drop_largest_extent(inode, fofs, len);
+
+ /* 1. lookup first extent node in range [fofs, fofs + len - 1] */
+ en = __lookup_extent_tree_ret(et, fofs, &prev_en, &next_en,
+ &insert_p, &insert_parent);
+ if (!en)
+ en = next_en;
+
+ /* 2. invlidate all extent nodes in range [fofs, fofs + len - 1] */
+ while (en && en->ei.fofs < end) {
+ unsigned int org_end;
+ int parts = 0; /* # of parts current extent split into */
+
+ next_en = en1 = NULL;
+
+ dei = en->ei;
+ org_end = dei.fofs + dei.len;
+ f2fs_bug_on(sbi, pos >= org_end);
+
+ if (pos > dei.fofs && pos - dei.fofs >= F2FS_MIN_EXTENT_LEN) {
+ en->ei.len = pos - en->ei.fofs;
+ prev_en = en;
+ parts = 1;
+ }
+
+ if (end < org_end && org_end - end >= F2FS_MIN_EXTENT_LEN) {
+ if (parts) {
+ set_extent_info(&ei, end,
+ end - dei.fofs + dei.blk,
+ org_end - end);
+ en1 = __insert_extent_tree(sbi, et, &ei,
+ NULL, NULL);
+ next_en = en1;
+ } else {
+ en->ei.fofs = end;
+ en->ei.blk += end - dei.fofs;
+ en->ei.len -= end - dei.fofs;
+ next_en = en;
+ }
+ parts++;
+ }
+
+ if (!next_en) {
+ struct rb_node *node = rb_next(&en->rb_node);
+
+ next_en = node ?
+ rb_entry(node, struct extent_node, rb_node)
+ : NULL;
+ }
+
+ if (parts)
+ __try_update_largest_extent(et, en);
+ else
+ __detach_extent_node(sbi, et, en);
+
+ /*
+ * if original extent is split into zero or two parts, extent
+ * tree has been altered by deletion or insertion, therefore
+ * invalidate pointers regard to tree.
+ */
+ if (parts != 1) {
+ insert_p = NULL;
+ insert_parent = NULL;
+ }
+
+ /* update in global extent list */
+ spin_lock(&sbi->extent_lock);
+ if (!parts && !list_empty(&en->list))
+ list_del(&en->list);
+ if (en1)
+ list_add_tail(&en1->list, &sbi->extent_list);
+ spin_unlock(&sbi->extent_lock);
+
+ /* release extent node */
+ if (!parts)
+ kmem_cache_free(extent_node_slab, en);
+
+ en = next_en;
+ }
+
+ /* 3. update extent in extent cache */
+ if (blkaddr) {
+ struct extent_node *den = NULL;
+
+ set_extent_info(&ei, fofs, blkaddr, len);
+ en1 = __try_merge_extent_node(sbi, et, &ei, &den,
+ prev_en, next_en);
+ if (!en1)
+ en1 = __insert_extent_tree(sbi, et, &ei,
+ insert_p, insert_parent);
+
+ /* give up extent_cache, if split and small updates happen */
+ if (dei.len >= 1 &&
+ prev.len < F2FS_MIN_EXTENT_LEN &&
+ et->largest.len < F2FS_MIN_EXTENT_LEN) {
+ et->largest.len = 0;
+ set_inode_flag(F2FS_I(inode), FI_NO_EXTENT);
+ }
+
+ spin_lock(&sbi->extent_lock);
+ if (en1) {
+ if (list_empty(&en1->list))
+ list_add_tail(&en1->list, &sbi->extent_list);
+ else
+ list_move_tail(&en1->list, &sbi->extent_list);
+ }
+ if (den && !list_empty(&den->list))
+ list_del(&den->list);
+ spin_unlock(&sbi->extent_lock);
+
+ if (den)
+ kmem_cache_free(extent_node_slab, den);
+ }
+
+ if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
+ __free_extent_tree(sbi, et, true);
+
+ write_unlock(&et->lock);
+
+ return !__is_extent_same(&prev, &et->largest);
+}
+
+unsigned int 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_root *root = &sbi->extent_tree_root;
+ unsigned int found;
+ unsigned int node_cnt = 0, tree_cnt = 0;
+ int remained;
+
+ if (!test_opt(sbi, EXTENT_CACHE))
+ return 0;
+
+ if (!down_write_trylock(&sbi->extent_tree_lock))
+ goto out;
+
+ /* 1. remove unreferenced extent tree */
+ while ((found = radix_tree_gang_lookup(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];
+
+ if (!atomic_read(&et->refcount)) {
+ write_lock(&et->lock);
+ node_cnt += __free_extent_tree(sbi, et, true);
+ write_unlock(&et->lock);
+
+ radix_tree_delete(root, et->ino);
+ kmem_cache_free(extent_tree_slab, et);
+ sbi->total_ext_tree--;
+ tree_cnt++;
+
+ if (node_cnt + tree_cnt >= nr_shrink)
+ goto unlock_out;
+ }
+ }
+ }
+ up_write(&sbi->extent_tree_lock);
+
+ /* 2. remove LRU extent entries */
+ if (!down_write_trylock(&sbi->extent_tree_lock))
+ goto out;
+
+ remained = nr_shrink - (node_cnt + tree_cnt);
+
+ spin_lock(&sbi->extent_lock);
+ list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) {
+ if (!remained--)
+ break;
+ list_del_init(&en->list);
+ }
+ spin_unlock(&sbi->extent_lock);
+
+ /*
+ * reset ino for searching victims from beginning of global extent tree.
+ */
+ ino = F2FS_ROOT_INO(sbi);
+
+ while ((found = radix_tree_gang_lookup(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];
+
+ write_lock(&et->lock);
+ node_cnt += __free_extent_tree(sbi, et, false);
+ write_unlock(&et->lock);
+
+ if (node_cnt + tree_cnt >= nr_shrink)
+ goto unlock_out;
+ }
+ }
+unlock_out:
+ up_write(&sbi->extent_tree_lock);
+out:
+ trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt);
+
+ return node_cnt + tree_cnt;
+}
+
+unsigned int f2fs_destroy_extent_node(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct extent_tree *et = F2FS_I(inode)->extent_tree;
+ unsigned int node_cnt = 0;
+
+ if (!et)
+ return 0;
+
+ write_lock(&et->lock);
+ node_cnt = __free_extent_tree(sbi, et, true);
+ write_unlock(&et->lock);
+
+ return node_cnt;
+}
+
+void f2fs_destroy_extent_tree(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct extent_tree *et = F2FS_I(inode)->extent_tree;
+ unsigned int node_cnt = 0;
+
+ if (!et)
+ return;
+
+ if (inode->i_nlink && !is_bad_inode(inode) && et->count) {
+ atomic_dec(&et->refcount);
+ return;
+ }
+
+ /* free all extent info belong to this extent tree */
+ node_cnt = f2fs_destroy_extent_node(inode);
+
+ /* delete extent tree entry in radix tree */
+ down_write(&sbi->extent_tree_lock);
+ atomic_dec(&et->refcount);
+ 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);
+
+ F2FS_I(inode)->extent_tree = NULL;
+
+ trace_f2fs_destroy_extent_tree(inode, node_cnt);
+}
+
+bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
+ struct extent_info *ei)
+{
+ if (!f2fs_may_extent_tree(inode))
+ return false;
+
+ return f2fs_lookup_extent_tree(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;
+
+ if (!f2fs_may_extent_tree(dn->inode))
+ return;
+
+ f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
+
+
+ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+ dn->ofs_in_node;
+
+ if (f2fs_update_extent_tree_range(dn->inode, fofs, dn->data_blkaddr, 1))
+ sync_inode_page(dn);
+}
+
+void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
+ pgoff_t fofs, block_t blkaddr, unsigned int len)
+
+{
+ if (!f2fs_may_extent_tree(dn->inode))
+ return;
+
+ if (f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len))
+ sync_inode_page(dn);
+}
+
+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);
+}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
new file mode 100644
index 0000000..182154c
--- /dev/null
+++ b/fs/f2fs/f2fs.h
@@ -0,0 +1,2227 @@
+/*
+ * 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>
+#include <linux/vmalloc.h>
+#include <linux/bio.h>
+
+#ifdef CONFIG_F2FS_CHECK_FS
+#define f2fs_bug_on(sbi, condition) BUG_ON(condition)
+#define f2fs_down_write(x, y) down_write(x)
+#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_SUPER_MAGIC 0xF2F52010 /* F2FS Magic Number */
+#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 F2FS_MOUNT_FORCE_FG_GC 0x00004000
+
+#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 F2FS_FEATURE_ENCRYPT 0x0001
+
+#define F2FS_HAS_FEATURE(sb, mask) \
+ ((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
+#define F2FS_SET_FEATURE(sb, mask) \
+ F2FS_SB(sb)->raw_super->feature |= cpu_to_le32(mask)
+#define F2FS_CLEAR_FEATURE(sb, mask) \
+ F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask)
+
+#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)
+#define BATCHED_TRIM_BLOCKS(sbi) \
+ (BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
+#define DEF_CP_INTERVAL 60 /* 60 secs */
+
+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 FS_IOC_SHUTDOWN _IOR('X', 125, __u32) /* Shutdown */
+
+/*
+ * Flags for going down operation used by FS_IOC_GOINGDOWN
+ */
+#define FS_GOING_DOWN_FULLSYNC 0x0 /* going down with full sync */
+#define FS_GOING_DOWN_METASYNC 0x1 /* going down with metadata */
+#define FS_GOING_DOWN_NOSYNC 0x2 /* going down */
+#define FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */
+
+#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)
+#define F2FS_IOC_GARBAGE_COLLECT _IO(F2FS_IOCTL_MAGIC, 6)
+#define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7)
+
+#define F2FS_IOC_SET_ENCRYPTION_POLICY \
+ _IOR('f', 19, struct f2fs_encryption_policy)
+#define F2FS_IOC_GET_ENCRYPTION_PWSALT \
+ _IOW('f', 20, __u8[16])
+#define F2FS_IOC_GET_ENCRYPTION_POLICY \
+ _IOW('f', 21, struct f2fs_encryption_policy)
+
+#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_str {
+ unsigned char *name;
+ u32 len;
+};
+
+struct f2fs_filename {
+ const struct qstr *usr_fname;
+ struct f2fs_str disk_name;
+ f2fs_hash_t hash;
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ struct f2fs_str crypto_buf;
+#endif
+};
+
+#define QSTR_INIT(n, l) { .name = n, .len = l }
+#define FSTR_INIT(n, l) { .name = n, .len = l }
+#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len)
+#define fname_name(p) ((p)->disk_name.name)
+#define fname_len(p) ((p)->disk_name.len)
+
+struct f2fs_dentry_ptr {
+ struct inode *inode;
+ const void *bitmap;
+ struct f2fs_dir_entry *dentry;
+ __u8 (*filename)[F2FS_SLOT_LEN];
+ int max;
+};
+
+static inline void make_dentry_ptr(struct inode *inode,
+ struct f2fs_dentry_ptr *d, void *src, int type)
+{
+ d->inode = inode;
+
+ 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 0xffffffff /* 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 */
+ struct extent_info largest; /* largested extent info */
+ 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*/
+};
+
+/*
+ * This structure is taken from ext4_map_blocks.
+ *
+ * Note that, however, f2fs uses NEW and MAPPED flags for f2fs_map_blocks().
+ */
+#define F2FS_MAP_NEW (1 << BH_New)
+#define F2FS_MAP_MAPPED (1 << BH_Mapped)
+#define F2FS_MAP_UNWRITTEN (1 << BH_Unwritten)
+#define F2FS_MAP_FLAGS (F2FS_MAP_NEW | F2FS_MAP_MAPPED |\
+ F2FS_MAP_UNWRITTEN)
+
+struct f2fs_map_blocks {
+ block_t m_pblk;
+ block_t m_lblk;
+ unsigned int m_len;
+ unsigned int m_flags;
+};
+
+/* for flag in get_data_block */
+#define F2FS_GET_BLOCK_READ 0
+#define F2FS_GET_BLOCK_DIO 1
+#define F2FS_GET_BLOCK_FIEMAP 2
+#define F2FS_GET_BLOCK_BMAP 3
+
+/*
+ * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
+ */
+#define FADVISE_COLD_BIT 0x01
+#define FADVISE_LOST_PINO_BIT 0x02
+#define FADVISE_ENCRYPT_BIT 0x04
+#define FADVISE_ENC_NAME_BIT 0x08
+
+#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)
+#define file_is_encrypt(inode) is_file(inode, FADVISE_ENCRYPT_BIT)
+#define file_set_encrypt(inode) set_file(inode, FADVISE_ENCRYPT_BIT)
+#define file_clear_encrypt(inode) clear_file(inode, FADVISE_ENCRYPT_BIT)
+#define file_enc_name(inode) is_file(inode, FADVISE_ENC_NAME_BIT)
+#define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT)
+
+/* Encryption algorithms */
+#define F2FS_ENCRYPTION_MODE_INVALID 0
+#define F2FS_ENCRYPTION_MODE_AES_256_XTS 1
+#define F2FS_ENCRYPTION_MODE_AES_256_GCM 2
+#define F2FS_ENCRYPTION_MODE_AES_256_CBC 3
+#define F2FS_ENCRYPTION_MODE_AES_256_CTS 4
+
+#include "f2fs_crypto.h"
+
+#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 inode_entry *dirty_dir; /* the pointer of dirty dir */
+
+ struct list_head inmem_pages; /* inmemory pages managed by f2fs */
+ struct mutex inmem_lock; /* lock for inmemory pages */
+
+ struct extent_tree *extent_tree; /* cached extent_tree entry */
+
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ /* Encryption params */
+ struct f2fs_crypt_info *i_crypt_info;
+#endif
+};
+
+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);
+}
+
+static inline void __try_update_largest_extent(struct extent_tree *et,
+ struct extent_node *en)
+{
+ if (en->ei.len > et->largest.len)
+ et->largest = en->ei;
+}
+
+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 */
+ unsigned int ra_nid_pages; /* # of nid pages to be readaheaded */
+
+ /* 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 {
+ struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */
+ 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 */
+ struct page *page; /* page to be written */
+ struct page *encrypted_page; /* encrypted page */
+};
+
+#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;
+ long cp_expires, cp_interval; /* next expected periodic cp */
+
+ 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 discard_blks; /* discard command candidats */
+ 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 */
+ atomic64_t total_hit_ext; /* # of lookup extent cache */
+ atomic64_t read_hit_rbtree; /* # of hit rbtree extent node */
+ atomic64_t read_hit_largest; /* # of hit largest extent node */
+ atomic64_t read_hit_cached; /* # of hit cached extent node */
+ atomic_t inline_xattr; /* # of inline_xattr inodes */
+ 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;
+
+ /* For shrinker support */
+ struct list_head s_list;
+ struct mutex umount_mutex;
+ unsigned int shrinker_run_no;
+};
+
+/*
+ * 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) &&
+ !S_ISLNK(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 struct page *f2fs_grab_cache_page(struct address_space *mapping,
+ pgoff_t index, bool for_write)
+{
+ if (!for_write)
+ return grab_cache_page(mapping, index);
+ return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+}
+
+static inline void f2fs_copy_page(struct page *src, struct page *dst)
+{
+ char *src_kaddr = kmap(src);
+ char *dst_kaddr = kmap(dst);
+
+ memcpy(dst_kaddr, src_kaddr, PAGE_SIZE);
+ kunmap(dst);
+ kunmap(src);
+}
+
+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;
+
+ entry = kmem_cache_alloc(cachep, flags);
+ if (!entry)
+ entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL);
+ return entry;
+}
+
+static inline struct bio *f2fs_bio_alloc(int npages)
+{
+ struct bio *bio;
+
+ /* No failure on bio allocation */
+ bio = bio_alloc(GFP_NOIO, npages);
+ if (!bio)
+ bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
+ return bio;
+}
+
+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 void f2fs_set_bit(unsigned int nr, char *addr)
+{
+ int mask;
+
+ addr += (nr >> 3);
+ mask = 1 << (7 - (nr & 0x07));
+ *addr |= mask;
+}
+
+static inline void f2fs_clear_bit(unsigned int nr, char *addr)
+{
+ int mask;
+
+ addr += (nr >> 3);
+ mask = 1 << (7 - (nr & 0x07));
+ *addr &= ~mask;
+}
+
+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_FREE_NID, /* free allocated nide */
+ 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 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;
+}
+
+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;
+}
+
+static inline struct inode *file_inode(struct file *f)
+{
+ return f->f_path.dentry->d_inode;
+}
+
+static inline bool is_dot_dotdot(const struct qstr *str)
+{
+ if (str->len == 1 && str->name[0] == '.')
+ return true;
+
+ if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
+ return true;
+
+ return false;
+}
+
+static inline bool f2fs_may_extent_tree(struct inode *inode)
+{
+ mode_t mode = inode->i_mode;
+
+ if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) ||
+ is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
+ return false;
+
+ return S_ISREG(mode);
+}
+
+static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
+{
+ void *ret;
+
+ ret = kmalloc(size, flags | __GFP_NOWARN);
+ if (!ret)
+ ret = __vmalloc(size, flags, PAGE_KERNEL);
+ return ret;
+}
+
+static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
+{
+ void *ret;
+
+ ret = kzalloc(size, flags | __GFP_NOWARN);
+ if (!ret)
+ ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
+ return ret;
+}
+
+static inline void f2fs_kvfree(void *ptr)
+{
+ if (is_vmalloc_addr(ptr))
+ vfree(ptr);
+ else
+ kfree(ptr);
+}
+
+#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);
+int f2fs_truncate(struct inode *, bool);
+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 f2fs_filename *,
+ f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
+bool f2fs_fill_dentries(struct file *, void *, filldir_t,
+ struct f2fs_dentry_ptr *, unsigned int, unsigned int, struct f2fs_str *);
+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 *, 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 *);
+bool f2fs_empty_dir(struct inode *);
+
+static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
+{
+ return __f2fs_add_link(dentry->d_parent->d_inode, &dentry->d_name,
+ inode, inode->i_ino, inode->i_mode);
+}
+
+/*
+ * super.c
+ */
+int f2fs_commit_super(struct f2fs_sb_info *, bool);
+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);
+int need_dentry_mark(struct f2fs_sb_info *, nid_t);
+bool is_checkpointed_node(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);
+int 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);
+int try_to_free_nids(struct f2fs_sb_info *, int);
+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 *);
+int 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);
+bool is_checkpointed_data(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 *, struct cp_control *);
+void release_discard_addrs(struct f2fs_sb_info *);
+bool 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 update_meta_page(struct f2fs_sb_info *, void *, block_t);
+void write_meta_page(struct f2fs_sb_info *, struct page *);
+void write_node_page(unsigned int, struct f2fs_io_info *);
+void write_data_page(struct dnode_of_data *, struct f2fs_io_info *);
+void rewrite_data_page(struct f2fs_io_info *);
+void f2fs_replace_block(struct f2fs_sb_info *, struct dnode_of_data *,
+ block_t, block_t, unsigned char, bool);
+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 f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *, block_t);
+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);
+struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t);
+bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int);
+int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool);
+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);
+int 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_io_info *);
+void f2fs_submit_page_mbio(struct f2fs_io_info *);
+void set_data_blkaddr(struct dnode_of_data *);
+int reserve_new_block(struct dnode_of_data *);
+int f2fs_get_block(struct dnode_of_data *, pgoff_t);
+int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
+struct page *get_read_data_page(struct inode *, pgoff_t, int, bool);
+struct page *find_data_page(struct inode *, pgoff_t);
+struct page *get_lock_data_page(struct inode *, pgoff_t, bool);
+struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
+int do_write_data_page(struct f2fs_io_info *);
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
+void f2fs_invalidate_page(struct page *, unsigned long);
+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 *, bool);
+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;
+ unsigned long long hit_largest, hit_cached, hit_rbtree;
+ unsigned long long hit_total, total_ext;
+ int 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, inmem_pages, wb_pages;
+ int inline_xattr, inline_inode, inline_dir;
+ 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 long long 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(sbi) (atomic64_inc(&(sbi)->total_hit_ext))
+#define stat_inc_rbtree_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_rbtree))
+#define stat_inc_largest_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_largest))
+#define stat_inc_cached_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_cached))
+#define stat_inc_inline_xattr(inode) \
+ do { \
+ if (f2fs_has_inline_xattr(inode)) \
+ (atomic_inc(&F2FS_I_SB(inode)->inline_xattr)); \
+ } while (0)
+#define stat_dec_inline_xattr(inode) \
+ do { \
+ if (f2fs_has_inline_xattr(inode)) \
+ (atomic_dec(&F2FS_I_SB(inode)->inline_xattr)); \
+ } while (0)
+#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_rbtree_node_hit(sb)
+#define stat_inc_largest_node_hit(sbi)
+#define stat_inc_cached_node_hit(sbi)
+#define stat_inc_inline_xattr(inode)
+#define stat_dec_inline_xattr(inode)
+#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_encrypted_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_data(struct inode *);
+bool f2fs_may_inline_dentry(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 f2fs_filename *, 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 *, void *, filldir_t, struct f2fs_str *);
+int f2fs_inline_data_fiemap(struct inode *,
+ struct fiemap_extent_info *, __u64, __u64);
+
+/*
+ * shrinker.c
+ */
+int f2fs_shrink_count(struct shrinker *, struct shrink_control *);
+int f2fs_shrink_scan(struct shrinker *, struct shrink_control *);
+void f2fs_join_shrinker(struct f2fs_sb_info *);
+void f2fs_leave_shrinker(struct f2fs_sb_info *);
+
+/*
+ * extent_cache.c
+ */
+unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *, int);
+void f2fs_drop_largest_extent(struct inode *, pgoff_t);
+void f2fs_init_extent_tree(struct inode *, struct f2fs_extent *);
+unsigned int f2fs_destroy_extent_node(struct inode *);
+void f2fs_destroy_extent_tree(struct inode *);
+bool f2fs_lookup_extent_cache(struct inode *, pgoff_t, struct extent_info *);
+void f2fs_update_extent_cache(struct dnode_of_data *);
+void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
+ pgoff_t, block_t, unsigned int);
+void init_extent_cache_info(struct f2fs_sb_info *);
+int __init create_extent_cache(void);
+void destroy_extent_cache(void);
+
+/*
+ * crypto support
+ */
+static inline int f2fs_encrypted_inode(struct inode *inode)
+{
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ return file_is_encrypt(inode);
+#else
+ return 0;
+#endif
+}
+
+static inline void f2fs_set_encrypted_inode(struct inode *inode)
+{
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ file_set_encrypt(inode);
+#endif
+}
+
+static inline bool f2fs_bio_encrypted(struct bio *bio)
+{
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ return unlikely(bio->bi_private != NULL);
+#else
+ return false;
+#endif
+}
+
+static inline int f2fs_sb_has_crypto(struct super_block *sb)
+{
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT);
+#else
+ return 0;
+#endif
+}
+
+static inline bool f2fs_may_encrypt(struct inode *inode)
+{
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ mode_t mode = inode->i_mode;
+
+ return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
+#else
+ return 0;
+#endif
+}
+
+/* crypto_policy.c */
+int f2fs_is_child_context_consistent_with_parent(struct inode *,
+ struct inode *);
+int f2fs_inherit_context(struct inode *, struct inode *, struct page *);
+int f2fs_process_policy(const struct f2fs_encryption_policy *, struct inode *);
+int f2fs_get_policy(struct inode *, struct f2fs_encryption_policy *);
+
+/* crypt.c */
+extern struct kmem_cache *f2fs_crypt_info_cachep;
+bool f2fs_valid_contents_enc_mode(uint32_t);
+uint32_t f2fs_validate_encryption_key_size(uint32_t, uint32_t);
+struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *);
+void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *);
+struct page *f2fs_encrypt(struct inode *, struct page *);
+int f2fs_decrypt(struct f2fs_crypto_ctx *, struct page *);
+int f2fs_decrypt_one(struct inode *, struct page *);
+void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *, struct bio *);
+
+/* crypto_key.c */
+void f2fs_free_encryption_info(struct inode *, struct f2fs_crypt_info *);
+int _f2fs_get_encryption_info(struct inode *inode);
+
+/* crypto_fname.c */
+bool f2fs_valid_filenames_enc_mode(uint32_t);
+u32 f2fs_fname_crypto_round_up(u32, u32);
+int f2fs_fname_crypto_alloc_buffer(struct inode *, u32, struct f2fs_str *);
+int f2fs_fname_disk_to_usr(struct inode *, f2fs_hash_t *,
+ const struct f2fs_str *, struct f2fs_str *);
+int f2fs_fname_usr_to_disk(struct inode *, const struct qstr *,
+ struct f2fs_str *);
+
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+void f2fs_restore_and_release_control_page(struct page **);
+void f2fs_restore_control_page(struct page *);
+
+int __init f2fs_init_crypto(void);
+int f2fs_crypto_initialize(void);
+void f2fs_exit_crypto(void);
+
+int f2fs_has_encryption_key(struct inode *);
+
+static inline int f2fs_get_encryption_info(struct inode *inode)
+{
+ struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
+
+ if (!ci ||
+ (ci->ci_keyring_key &&
+ (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+ (1 << KEY_FLAG_REVOKED) |
+ (1 << KEY_FLAG_DEAD)))))
+ return _f2fs_get_encryption_info(inode);
+ return 0;
+}
+
+void f2fs_fname_crypto_free_buffer(struct f2fs_str *);
+int f2fs_fname_setup_filename(struct inode *, const struct qstr *,
+ int lookup, struct f2fs_filename *);
+void f2fs_fname_free_filename(struct f2fs_filename *);
+#else
+static inline void f2fs_restore_and_release_control_page(struct page **p) { }
+static inline void f2fs_restore_control_page(struct page *p) { }
+
+static inline int __init f2fs_init_crypto(void) { return 0; }
+static inline void f2fs_exit_crypto(void) { }
+
+static inline int f2fs_has_encryption_key(struct inode *i) { return 0; }
+static inline int f2fs_get_encryption_info(struct inode *i) { return 0; }
+static inline void f2fs_fname_crypto_free_buffer(struct f2fs_str *p) { }
+
+static inline int f2fs_fname_setup_filename(struct inode *dir,
+ const struct qstr *iname,
+ int lookup, struct f2fs_filename *fname)
+{
+ memset(fname, 0, sizeof(struct f2fs_filename));
+ fname->usr_fname = iname;
+ fname->disk_name.name = (unsigned char *)iname->name;
+ fname->disk_name.len = iname->len;
+ return 0;
+}
+
+static inline void f2fs_fname_free_filename(struct f2fs_filename *fname) { }
+#endif
+#endif
diff --git a/fs/f2fs/f2fs_crypto.h b/fs/f2fs/f2fs_crypto.h
new file mode 100644
index 0000000..c2c1c2b
--- /dev/null
+++ b/fs/f2fs/f2fs_crypto.h
@@ -0,0 +1,151 @@
+/*
+ * linux/fs/f2fs/f2fs_crypto.h
+ *
+ * Copied from linux/fs/ext4/ext4_crypto.h
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption header content for f2fs
+ *
+ * Written by Michael Halcrow, 2015.
+ * Modified by Jaegeuk Kim, 2015.
+ */
+#ifndef _F2FS_CRYPTO_H
+#define _F2FS_CRYPTO_H
+
+#include <linux/fs.h>
+
+#define F2FS_KEY_DESCRIPTOR_SIZE 8
+
+/* Policy provided via an ioctl on the topmost directory */
+struct f2fs_encryption_policy {
+ char version;
+ char contents_encryption_mode;
+ char filenames_encryption_mode;
+ char flags;
+ char master_key_descriptor[F2FS_KEY_DESCRIPTOR_SIZE];
+} __attribute__((__packed__));
+
+#define F2FS_ENCRYPTION_CONTEXT_FORMAT_V1 1
+#define F2FS_KEY_DERIVATION_NONCE_SIZE 16
+
+#define F2FS_POLICY_FLAGS_PAD_4 0x00
+#define F2FS_POLICY_FLAGS_PAD_8 0x01
+#define F2FS_POLICY_FLAGS_PAD_16 0x02
+#define F2FS_POLICY_FLAGS_PAD_32 0x03
+#define F2FS_POLICY_FLAGS_PAD_MASK 0x03
+#define F2FS_POLICY_FLAGS_VALID 0x03
+
+/**
+ * Encryption context for inode
+ *
+ * Protector format:
+ * 1 byte: Protector format (1 = this version)
+ * 1 byte: File contents encryption mode
+ * 1 byte: File names encryption mode
+ * 1 byte: Flags
+ * 8 bytes: Master Key descriptor
+ * 16 bytes: Encryption Key derivation nonce
+ */
+struct f2fs_encryption_context {
+ char format;
+ char contents_encryption_mode;
+ char filenames_encryption_mode;
+ char flags;
+ char master_key_descriptor[F2FS_KEY_DESCRIPTOR_SIZE];
+ char nonce[F2FS_KEY_DERIVATION_NONCE_SIZE];
+} __attribute__((__packed__));
+
+/* Encryption parameters */
+#define F2FS_XTS_TWEAK_SIZE 16
+#define F2FS_AES_128_ECB_KEY_SIZE 16
+#define F2FS_AES_256_GCM_KEY_SIZE 32
+#define F2FS_AES_256_CBC_KEY_SIZE 32
+#define F2FS_AES_256_CTS_KEY_SIZE 32
+#define F2FS_AES_256_XTS_KEY_SIZE 64
+#define F2FS_MAX_KEY_SIZE 64
+
+#define F2FS_KEY_DESC_PREFIX "f2fs:"
+#define F2FS_KEY_DESC_PREFIX_SIZE 5
+
+struct f2fs_encryption_key {
+ __u32 mode;
+ char raw[F2FS_MAX_KEY_SIZE];
+ __u32 size;
+} __attribute__((__packed__));
+
+struct f2fs_crypt_info {
+ char ci_data_mode;
+ char ci_filename_mode;
+ char ci_flags;
+ struct crypto_ablkcipher *ci_ctfm;
+ struct key *ci_keyring_key;
+ char ci_master_key[F2FS_KEY_DESCRIPTOR_SIZE];
+};
+
+#define F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001
+#define F2FS_WRITE_PATH_FL 0x00000002
+
+struct f2fs_crypto_ctx {
+ union {
+ struct {
+ struct page *bounce_page; /* Ciphertext page */
+ struct page *control_page; /* Original page */
+ } w;
+ struct {
+ struct bio *bio;
+ struct work_struct work;
+ } r;
+ struct list_head free_list; /* Free list */
+ };
+ char flags; /* Flags */
+};
+
+struct f2fs_completion_result {
+ struct completion completion;
+ int res;
+};
+
+#define DECLARE_F2FS_COMPLETION_RESULT(ecr) \
+ struct f2fs_completion_result ecr = { \
+ COMPLETION_INITIALIZER((ecr).completion), 0 }
+
+static inline int f2fs_encryption_key_size(int mode)
+{
+ switch (mode) {
+ case F2FS_ENCRYPTION_MODE_AES_256_XTS:
+ return F2FS_AES_256_XTS_KEY_SIZE;
+ case F2FS_ENCRYPTION_MODE_AES_256_GCM:
+ return F2FS_AES_256_GCM_KEY_SIZE;
+ case F2FS_ENCRYPTION_MODE_AES_256_CBC:
+ return F2FS_AES_256_CBC_KEY_SIZE;
+ case F2FS_ENCRYPTION_MODE_AES_256_CTS:
+ return F2FS_AES_256_CTS_KEY_SIZE;
+ default:
+ BUG();
+ }
+ return 0;
+}
+
+#define F2FS_FNAME_NUM_SCATTER_ENTRIES 4
+#define F2FS_CRYPTO_BLOCK_SIZE 16
+#define F2FS_FNAME_CRYPTO_DIGEST_SIZE 32
+
+/**
+ * For encrypted symlinks, the ciphertext length is stored at the beginning
+ * of the string in little-endian format.
+ */
+struct f2fs_encrypted_symlink_data {
+ __le16 len;
+ char encrypted_path[1];
+} __attribute__((__packed__));
+
+/**
+ * This function is used to calculate the disk space required to
+ * store a filename of length l in encrypted symlink format.
+ */
+static inline u32 encrypted_symlink_data_len(u32 l)
+{
+ return (l + sizeof(struct f2fs_encrypted_symlink_data) - 1);
+}
+#endif /* _F2FS_CRYPTO_H */
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
new file mode 100644
index 0000000..30a8d8c
--- /dev/null
+++ b/fs/f2fs/file.c
@@ -0,0 +1,1741 @@
+/*
+ * 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 <linux/random.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include "segment.h"
+#include "xattr.h"
+#include "acl.h"
+#include "gc.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);
+
+ vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+
+ 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 (((loff_t)(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);
+
+ /* wait for GCed encrypted page writeback */
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
+
+ /* if gced page is attached, don't write to cold segment */
+ clear_cold_data(page);
+out:
+ return block_page_mkwrite_return(err);
+}
+
+static const struct vm_operations_struct f2fs_file_vm_ops = {
+ .fault = filemap_fault,
+ .page_mkwrite = f2fs_vm_page_mkwrite,
+};
+
+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, 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_enc_name(inode) && need_dentry_mark(sbi, inode->i_ino))
+ 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) {
+ f2fs_write_inode(inode, NULL);
+ 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, 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 inline int unsigned_offsets(struct file *file)
+{
+ return file->f_mode & FMODE_UNSIGNED_OFFSET;
+}
+
+static loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize)
+{
+ if (offset < 0 && !unsigned_offsets(file))
+ return -EINVAL;
+ if (offset > maxsize)
+ return -EINVAL;
+
+ if (offset != file->f_pos) {
+ file->f_pos = offset;
+ file->f_version = 0;
+ }
+ return offset;
+}
+
+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 = (loff_t)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);
+ 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);
+
+ if (f2fs_encrypted_inode(inode)) {
+ int err = f2fs_get_encryption_info(inode);
+ if (err)
+ return 0;
+ }
+
+ /* 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;
+}
+
+static int f2fs_file_open(struct inode *inode, struct file *filp)
+{
+ int ret = generic_file_open(inode, filp);
+
+ if (!ret && f2fs_encrypted_inode(inode)) {
+ ret = f2fs_get_encryption_info(inode);
+ if (ret)
+ ret = -EACCES;
+ }
+ return ret;
+}
+
+int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ struct f2fs_node *raw_node;
+ int nr_free = 0, ofs = dn->ofs_in_node, len = count;
+ __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);
+ 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) {
+ pgoff_t fofs;
+ /*
+ * once we invalidate valid blkaddr in range [ofs, ofs + count],
+ * we will invalidate all blkaddr in the whole range.
+ */
+ fofs = start_bidx_of_node(ofs_of_node(dn->node_page),
+ F2FS_I(dn->inode)) + ofs;
+ f2fs_update_extent_cache_range(dn, fofs, 0, len);
+ 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 cache_only)
+{
+ unsigned offset = from & (PAGE_CACHE_SIZE - 1);
+ pgoff_t index = from >> PAGE_CACHE_SHIFT;
+ struct address_space *mapping = inode->i_mapping;
+ struct page *page;
+
+ if (!offset && !cache_only)
+ return 0;
+
+ if (cache_only) {
+ page = f2fs_grab_cache_page(mapping, index, false);
+ if (page && PageUptodate(page))
+ goto truncate_out;
+ f2fs_put_page(page, 1);
+ return 0;
+ }
+
+ page = get_lock_data_page(inode, index, true);
+ if (IS_ERR(page))
+ return 0;
+truncate_out:
+ f2fs_wait_on_page_writeback(page, DATA);
+ zero_user(page, offset, PAGE_CACHE_SIZE - offset);
+ if (!cache_only || !f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode))
+ set_page_dirty(page);
+ 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;
+}
+
+int f2fs_truncate(struct inode *inode, bool lock)
+{
+ int err;
+
+ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+ S_ISLNK(inode->i_mode)))
+ return 0;
+
+ trace_f2fs_truncate(inode);
+
+ /* we should check inline_data size */
+ if (f2fs_has_inline_data(inode) && !f2fs_may_inline_data(inode)) {
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
+ }
+
+ err = truncate_blocks(inode, i_size_read(inode), lock);
+ if (err)
+ return err;
+
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ mark_inode_dirty(inode);
+ return 0;
+}
+
+int f2fs_getattr(struct vfsmount *mnt,
+ struct dentry *dentry, struct kstat *stat)
+{
+ struct inode *inode = dentry->d_inode;
+ generic_fillattr(inode, stat);
+ stat->blocks <<= 3;
+ return 0;
+}
+
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+static void __setattr_copy(struct inode *inode, const struct iattr *attr)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ unsigned int ia_valid = attr->ia_valid;
+
+ if (ia_valid & ATTR_UID)
+ inode->i_uid = attr->ia_uid;
+ if (ia_valid & ATTR_GID)
+ inode->i_gid = attr->ia_gid;
+ if (ia_valid & ATTR_ATIME)
+ inode->i_atime = timespec_trunc(attr->ia_atime,
+ inode->i_sb->s_time_gran);
+ if (ia_valid & ATTR_MTIME)
+ inode->i_mtime = timespec_trunc(attr->ia_mtime,
+ inode->i_sb->s_time_gran);
+ if (ia_valid & ATTR_CTIME)
+ inode->i_ctime = timespec_trunc(attr->ia_ctime,
+ inode->i_sb->s_time_gran);
+ if (ia_valid & ATTR_MODE) {
+ umode_t mode = attr->ia_mode;
+
+ if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
+ mode &= ~S_ISGID;
+ set_acl_inode(fi, mode);
+ }
+}
+#else
+#define __setattr_copy setattr_copy
+#endif
+
+int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
+{
+ struct inode *inode = dentry->d_inode;
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ int err;
+
+ err = inode_change_ok(inode, attr);
+ if (err)
+ return err;
+
+ if (attr->ia_valid & ATTR_SIZE) {
+ if (f2fs_encrypted_inode(inode) &&
+ f2fs_get_encryption_info(inode))
+ return -EACCES;
+
+ if (attr->ia_size <= i_size_read(inode)) {
+ truncate_setsize(inode, attr->ia_size);
+ err = f2fs_truncate(inode, true);
+ if (err)
+ return err;
+ f2fs_balance_fs(F2FS_I_SB(inode));
+ } else {
+ /*
+ * do not trim all blocks after i_size if target size is
+ * larger than i_size.
+ */
+ truncate_setsize(inode, attr->ia_size);
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ }
+ }
+
+ __setattr_copy(inode, attr);
+
+ if (attr->ia_valid & ATTR_MODE) {
+ err = f2fs_acl_chmod(inode);
+ if (err || is_inode_flag_set(fi, FI_ACL_MODE)) {
+ inode->i_mode = fi->i_acl_mode;
+ clear_inode_flag(fi, FI_ACL_MODE);
+ }
+ }
+
+ mark_inode_dirty(inode);
+ return err;
+}
+
+const struct inode_operations f2fs_file_inode_operations = {
+ .getattr = f2fs_getattr,
+ .setattr = f2fs_setattr,
+ .get_acl = f2fs_get_acl,
+#ifdef CONFIG_F2FS_FS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = f2fs_listxattr,
+ .removexattr = generic_removexattr,
+#endif
+ .fiemap = f2fs_fiemap,
+};
+
+static int 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 0;
+
+ 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))
+ return PTR_ERR(page);
+
+ f2fs_wait_on_page_writeback(page, DATA);
+ zero_user(page, start, len);
+ set_page_dirty(page);
+ f2fs_put_page(page, 1);
+ return 0;
+}
+
+int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
+{
+ int err;
+
+ while (pg_start < pg_end) {
+ struct dnode_of_data dn;
+ pgoff_t end_offset, count;
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
+ if (err) {
+ if (err == -ENOENT) {
+ pg_start++;
+ continue;
+ }
+ return err;
+ }
+
+ end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+ count = min(end_offset - dn.ofs_in_node, pg_end - pg_start);
+
+ f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
+
+ truncate_data_blocks_range(&dn, count);
+ f2fs_put_dnode(&dn);
+
+ pg_start += count;
+ }
+ 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 (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) {
+ ret = fill_zero(inode, pg_start, off_start,
+ off_end - off_start);
+ if (ret)
+ return ret;
+ } else {
+ if (off_start) {
+ ret = fill_zero(inode, pg_start++, off_start,
+ PAGE_CACHE_SIZE - off_start);
+ if (ret)
+ return ret;
+ }
+ if (off_end) {
+ ret = fill_zero(inode, pg_end, 0, off_end);
+ if (ret)
+ return ret;
+ }
+
+ 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 = (loff_t)pg_start << PAGE_CACHE_SHIFT;
+ blk_end = (loff_t)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 __exchange_data_block(struct inode *inode, pgoff_t src,
+ pgoff_t dst, bool full)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct dnode_of_data dn;
+ block_t new_addr;
+ bool do_replace = false;
+ int ret;
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = get_dnode_of_data(&dn, src, LOOKUP_NODE_RA);
+ if (ret && ret != -ENOENT) {
+ return ret;
+ } else if (ret == -ENOENT) {
+ new_addr = NULL_ADDR;
+ } else {
+ new_addr = dn.data_blkaddr;
+ if (!is_checkpointed_data(sbi, new_addr)) {
+ dn.data_blkaddr = NULL_ADDR;
+ /* do not invalidate this block address */
+ set_data_blkaddr(&dn);
+ f2fs_update_extent_cache(&dn);
+ do_replace = true;
+ }
+ f2fs_put_dnode(&dn);
+ }
+
+ if (new_addr == NULL_ADDR)
+ return full ? truncate_hole(inode, dst, dst + 1) : 0;
+
+ if (do_replace) {
+ struct page *ipage = get_node_page(sbi, inode->i_ino);
+ struct node_info ni;
+
+ if (IS_ERR(ipage)) {
+ ret = PTR_ERR(ipage);
+ goto err_out;
+ }
+
+ set_new_dnode(&dn, inode, ipage, NULL, 0);
+ ret = f2fs_reserve_block(&dn, dst);
+ if (ret)
+ goto err_out;
+
+ truncate_data_blocks_range(&dn, 1);
+
+ get_node_info(sbi, dn.nid, &ni);
+ f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr,
+ ni.version, true);
+ f2fs_put_dnode(&dn);
+ } else {
+ struct page *psrc, *pdst;
+
+ psrc = get_lock_data_page(inode, src, true);
+ if (IS_ERR(psrc))
+ return PTR_ERR(psrc);
+ pdst = get_new_data_page(inode, NULL, dst, false);
+ if (IS_ERR(pdst)) {
+ f2fs_put_page(psrc, 1);
+ return PTR_ERR(pdst);
+ }
+ f2fs_copy_page(psrc, pdst);
+ set_page_dirty(pdst);
+ f2fs_put_page(pdst, 1);
+ f2fs_put_page(psrc, 1);
+
+ return truncate_hole(inode, src, src + 1);
+ }
+ return 0;
+
+err_out:
+ if (!get_dnode_of_data(&dn, src, LOOKUP_NODE)) {
+ dn.data_blkaddr = new_addr;
+ set_data_blkaddr(&dn);
+ f2fs_update_extent_cache(&dn);
+ f2fs_put_dnode(&dn);
+ }
+ return ret;
+}
+
+static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
+ int ret = 0;
+
+ for (; end < nrpages; start++, end++) {
+ f2fs_balance_fs(sbi);
+ f2fs_lock_op(sbi);
+ ret = __exchange_data_block(inode, end, start, true);
+ f2fs_unlock_op(sbi);
+ if (ret)
+ break;
+ }
+ return ret;
+}
+
+static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
+{
+ pgoff_t pg_start, pg_end;
+ loff_t new_size;
+ int ret;
+
+ if (offset + len >= i_size_read(inode))
+ return -EINVAL;
+
+ /* collapse range should be aligned to block size of f2fs. */
+ if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1))
+ return -EINVAL;
+
+ f2fs_balance_fs(F2FS_I_SB(inode));
+
+ if (f2fs_has_inline_data(inode)) {
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ return ret;
+ }
+
+ pg_start = offset >> PAGE_CACHE_SHIFT;
+ pg_end = (offset + len) >> PAGE_CACHE_SHIFT;
+
+ /* write out all dirty pages from offset */
+ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+ if (ret)
+ return ret;
+
+ truncate_pagecache(inode, 0, offset);
+
+ ret = f2fs_do_collapse(inode, pg_start, pg_end);
+ if (ret)
+ return ret;
+
+ /* write out all moved pages, if possible */
+ filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+ truncate_pagecache(inode, 0, offset);
+
+ new_size = i_size_read(inode) - len;
+ truncate_pagecache(inode, 0, new_size);
+
+ ret = truncate_blocks(inode, new_size, true);
+ if (!ret)
+ i_size_write(inode, new_size);
+
+ return ret;
+}
+
+static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
+ int mode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct address_space *mapping = inode->i_mapping;
+ pgoff_t index, pg_start, pg_end;
+ loff_t new_size = i_size_read(inode);
+ loff_t off_start, off_end;
+ int ret = 0;
+
+ ret = inode_newsize_ok(inode, (len + offset));
+ if (ret)
+ return ret;
+
+ f2fs_balance_fs(sbi);
+
+ if (f2fs_has_inline_data(inode)) {
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ return ret;
+ }
+
+ ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1);
+ if (ret)
+ return ret;
+
+ truncate_pagecache_range(inode, offset, offset + len - 1);
+
+ 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) {
+ ret = fill_zero(inode, pg_start, off_start,
+ off_end - off_start);
+ if (ret)
+ return ret;
+
+ if (offset + len > new_size)
+ new_size = offset + len;
+ new_size = max_t(loff_t, new_size, offset + len);
+ } else {
+ if (off_start) {
+ ret = fill_zero(inode, pg_start++, off_start,
+ PAGE_CACHE_SIZE - off_start);
+ if (ret)
+ return ret;
+
+ new_size = max_t(loff_t, new_size,
+ (loff_t)pg_start << PAGE_CACHE_SHIFT);
+ }
+
+ for (index = pg_start; index < pg_end; index++) {
+ struct dnode_of_data dn;
+ struct page *ipage;
+
+ f2fs_lock_op(sbi);
+
+ ipage = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(ipage)) {
+ ret = PTR_ERR(ipage);
+ f2fs_unlock_op(sbi);
+ goto out;
+ }
+
+ set_new_dnode(&dn, inode, ipage, NULL, 0);
+ ret = f2fs_reserve_block(&dn, index);
+ if (ret) {
+ f2fs_unlock_op(sbi);
+ goto out;
+ }
+
+ if (dn.data_blkaddr != NEW_ADDR) {
+ invalidate_blocks(sbi, dn.data_blkaddr);
+
+ dn.data_blkaddr = NEW_ADDR;
+ set_data_blkaddr(&dn);
+
+ dn.data_blkaddr = NULL_ADDR;
+ f2fs_update_extent_cache(&dn);
+ }
+ f2fs_put_dnode(&dn);
+ f2fs_unlock_op(sbi);
+
+ new_size = max_t(loff_t, new_size,
+ (loff_t)(index + 1) << PAGE_CACHE_SHIFT);
+ }
+
+ if (off_end) {
+ ret = fill_zero(inode, pg_end, 0, off_end);
+ if (ret)
+ goto out;
+
+ new_size = max_t(loff_t, new_size, offset + len);
+ }
+ }
+
+out:
+ 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);
+ }
+
+ return ret;
+}
+
+static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ pgoff_t pg_start, pg_end, delta, nrpages, idx;
+ loff_t new_size;
+ int ret = 0;
+
+ new_size = i_size_read(inode) + len;
+ if (new_size > inode->i_sb->s_maxbytes)
+ return -EFBIG;
+
+ if (offset >= i_size_read(inode))
+ return -EINVAL;
+
+ /* insert range should be aligned to block size of f2fs. */
+ if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1))
+ return -EINVAL;
+
+ f2fs_balance_fs(sbi);
+
+ if (f2fs_has_inline_data(inode)) {
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ return ret;
+ }
+
+ ret = truncate_blocks(inode, i_size_read(inode), true);
+ if (ret)
+ return ret;
+
+ /* write out all dirty pages from offset */
+ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+ if (ret)
+ return ret;
+
+ truncate_pagecache(inode, 0, offset);
+
+ pg_start = offset >> PAGE_CACHE_SHIFT;
+ pg_end = (offset + len) >> PAGE_CACHE_SHIFT;
+ delta = pg_end - pg_start;
+ nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
+
+ for (idx = nrpages - 1; idx >= pg_start && idx != -1; idx--) {
+ f2fs_lock_op(sbi);
+ ret = __exchange_data_block(inode, idx, idx + delta, false);
+ f2fs_unlock_op(sbi);
+ if (ret)
+ break;
+ }
+
+ /* write out all moved pages, if possible */
+ filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+ truncate_pagecache(inode, 0, offset);
+
+ if (!ret)
+ i_size_write(inode, new_size);
+ 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 = (loff_t)(index + 1) << PAGE_CACHE_SHIFT;
+ else if (index == pg_end)
+ new_size = ((loff_t)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;
+}
+
+#define FALLOC_FL_COLLAPSE_RANGE 0X08
+#define FALLOC_FL_ZERO_RANGE 0X10
+#define FALLOC_FL_INSERT_RANGE 0X20
+
+static long f2fs_fallocate(struct file *file, int mode,
+ loff_t offset, loff_t len)
+{
+ struct inode *inode = file_inode(file);
+ long ret = 0;
+
+ /* f2fs only support ->fallocate for regular file */
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
+ if (f2fs_encrypted_inode(inode) &&
+ (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
+ return -EOPNOTSUPP;
+
+ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+ FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
+ FALLOC_FL_INSERT_RANGE))
+ return -EOPNOTSUPP;
+
+ mutex_lock(&inode->i_mutex);
+
+ if (mode & FALLOC_FL_PUNCH_HOLE) {
+ if (offset >= inode->i_size)
+ goto out;
+
+ ret = punch_hole(inode, offset, len);
+ } else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
+ ret = f2fs_collapse_range(inode, offset, len);
+ } else if (mode & FALLOC_FL_ZERO_RANGE) {
+ ret = f2fs_zero_range(inode, offset, len, mode);
+ } else if (mode & FALLOC_FL_INSERT_RANGE) {
+ ret = f2fs_insert_range(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);
+ }
+
+out:
+ 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);
+ int ret;
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ f2fs_balance_fs(F2FS_I_SB(inode));
+
+ if (f2fs_is_atomic_file(inode))
+ return 0;
+
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ return ret;
+
+ set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+ return 0;
+}
+
+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)) {
+ clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+ ret = commit_inmem_pages(inode, false);
+ if (ret)
+ goto err_out;
+ }
+
+ ret = f2fs_sync_file(filp, 0, LLONG_MAX, 0);
+err_out:
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_ioc_start_volatile_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 = f2fs_convert_inline_inode(inode);
+ if (ret)
+ return ret;
+
+ set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+ return 0;
+}
+
+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);
+
+ return punch_hole(inode, 0, F2FS_BLKSIZE);
+}
+
+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));
+
+ clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+ clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
+ commit_inmem_pages(inode, true);
+
+ 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 FS_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 FS_GOING_DOWN_METASYNC:
+ /* do checkpoint only */
+ f2fs_sync_fs(sb, 1);
+ f2fs_stop_checkpoint(sbi);
+ break;
+ case FS_GOING_DOWN_NOSYNC:
+ f2fs_stop_checkpoint(sbi);
+ break;
+ case FS_GOING_DOWN_METAFLUSH:
+ sync_meta_pages(sbi, META, LONG_MAX);
+ 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;
+}
+
+static bool uuid_is_nonzero(__u8 u[16])
+{
+ int i;
+
+ for (i = 0; i < 16; i++)
+ if (u[i])
+ return true;
+ return false;
+}
+
+static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
+{
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ struct f2fs_encryption_policy policy;
+ struct inode *inode = file_inode(filp);
+
+ if (copy_from_user(&policy, (struct f2fs_encryption_policy __user *)arg,
+ sizeof(policy)))
+ return -EFAULT;
+
+ return f2fs_process_policy(&policy, inode);
+#else
+ return -EOPNOTSUPP;
+#endif
+}
+
+static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
+{
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ struct f2fs_encryption_policy policy;
+ struct inode *inode = file_inode(filp);
+ int err;
+
+ err = f2fs_get_policy(inode, &policy);
+ if (err)
+ return err;
+
+ if (copy_to_user((struct f2fs_encryption_policy __user *)arg, &policy,
+ sizeof(policy)))
+ return -EFAULT;
+ return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
+}
+
+static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int err;
+
+ if (!f2fs_sb_has_crypto(inode->i_sb))
+ return -EOPNOTSUPP;
+
+ if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt))
+ goto got_it;
+
+ err = mnt_want_write_file(filp);
+ if (err)
+ return err;
+
+ /* update superblock with uuid */
+ generate_random_uuid(sbi->raw_super->encrypt_pw_salt);
+
+ err = f2fs_commit_super(sbi, false);
+
+ mnt_drop_write_file(filp);
+ if (err) {
+ /* undo new data */
+ memset(sbi->raw_super->encrypt_pw_salt, 0, 16);
+ return err;
+ }
+got_it:
+ if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt,
+ 16))
+ return -EFAULT;
+ return 0;
+}
+
+static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ __u32 sync;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (get_user(sync, (__u32 __user *)arg))
+ return -EFAULT;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ if (!sync) {
+ if (!mutex_trylock(&sbi->gc_mutex))
+ return -EBUSY;
+ } else {
+ mutex_lock(&sbi->gc_mutex);
+ }
+
+ return f2fs_gc(sbi, sync);
+}
+
+static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct cp_control cpc;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ cpc.reason = __get_cp_reason(sbi);
+
+ mutex_lock(&sbi->gc_mutex);
+ write_checkpoint(sbi, &cpc);
+ mutex_unlock(&sbi->gc_mutex);
+
+ 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 FS_IOC_SHUTDOWN:
+ return f2fs_ioc_shutdown(filp, arg);
+ case FITRIM:
+ return f2fs_ioc_fitrim(filp, arg);
+ case F2FS_IOC_SET_ENCRYPTION_POLICY:
+ return f2fs_ioc_set_encryption_policy(filp, arg);
+ case F2FS_IOC_GET_ENCRYPTION_POLICY:
+ return f2fs_ioc_get_encryption_policy(filp, arg);
+ case F2FS_IOC_GET_ENCRYPTION_PWSALT:
+ return f2fs_ioc_get_encryption_pwsalt(filp, arg);
+ case F2FS_IOC_GARBAGE_COLLECT:
+ return f2fs_ioc_gc(filp, arg);
+ case F2FS_IOC_WRITE_CHECKPOINT:
+ return f2fs_ioc_write_checkpoint(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 = do_sync_read,
+ .write = do_sync_write,
+ .aio_read = generic_file_aio_read,
+ .aio_write = generic_file_aio_write,
+ .open = f2fs_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 = generic_file_splice_write,
+};
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
new file mode 100644
index 0000000..ee32e72
--- /dev/null
+++ b/fs/f2fs/gc.c
@@ -0,0 +1,886 @@
+/*
+ * 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_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, test_opt(sbi, FORCE_FG_GC)))
+ wait_ms = gc_th->no_gc_sleep_time;
+
+ trace_f2fs_background_gc(sbi->sb, wait_ms,
+ prefree_segments(sbi), free_segments(sbi));
+
+ /* 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;
+ unsigned int last_segment = MAIN_SEGS(sbi);
+ 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.max_search == 0)
+ goto out;
+
+ 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, last_segment, p.offset);
+ if (segno >= last_segment) {
+ if (sbi->last_victim[p.gc_mode]) {
+ last_segment = 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));
+ }
+out:
+ 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 int 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;
+ block_t start_addr;
+ int off;
+
+ start_addr = START_BLOCK(sbi, segno);
+
+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;
+ struct node_info ni;
+
+ /* stop BG_GC if there is not enough free sections. */
+ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
+ return 0;
+
+ 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;
+ }
+
+ get_node_info(sbi, nid, &ni);
+ if (ni.blk_addr != start_addr + off) {
+ 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);
+
+ /* return 1 only if FG_GC succefully reclaimed one */
+ if (get_valid_blocks(sbi, segno, 1) == 0)
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * 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 bool is_alive(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 false;
+
+ get_node_info(sbi, nid, dni);
+
+ if (sum->version != dni->version) {
+ f2fs_put_page(node_page, 1);
+ return false;
+ }
+
+ *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 false;
+ return true;
+}
+
+static void move_encrypted_block(struct inode *inode, block_t bidx)
+{
+ struct f2fs_io_info fio = {
+ .sbi = F2FS_I_SB(inode),
+ .type = DATA,
+ .rw = READ_SYNC,
+ .encrypted_page = NULL,
+ };
+ struct dnode_of_data dn;
+ struct f2fs_summary sum;
+ struct node_info ni;
+ struct page *page;
+ int err;
+
+ /* do not read out */
+ page = f2fs_grab_cache_page(inode->i_mapping, bidx, false);
+ if (!page)
+ return;
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
+ if (err)
+ goto out;
+
+ if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
+ ClearPageUptodate(page);
+ goto put_out;
+ }
+
+ /*
+ * don't cache encrypted data into meta inode until previous dirty
+ * data were writebacked to avoid racing between GC and flush.
+ */
+ f2fs_wait_on_page_writeback(page, DATA);
+
+ get_node_info(fio.sbi, dn.nid, &ni);
+ set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
+
+ /* read page */
+ fio.page = page;
+ fio.blk_addr = dn.data_blkaddr;
+
+ fio.encrypted_page = grab_cache_page(META_MAPPING(fio.sbi), fio.blk_addr);
+ if (!fio.encrypted_page)
+ goto put_out;
+
+ err = f2fs_submit_page_bio(&fio);
+ if (err)
+ goto put_page_out;
+
+ /* write page */
+ lock_page(fio.encrypted_page);
+
+ if (unlikely(!PageUptodate(fio.encrypted_page)))
+ goto put_page_out;
+ if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi)))
+ goto put_page_out;
+
+ set_page_dirty(fio.encrypted_page);
+ f2fs_wait_on_page_writeback(fio.encrypted_page, DATA);
+ if (clear_page_dirty_for_io(fio.encrypted_page))
+ dec_page_count(fio.sbi, F2FS_DIRTY_META);
+
+ set_page_writeback(fio.encrypted_page);
+
+ /* allocate block address */
+ f2fs_wait_on_page_writeback(dn.node_page, NODE);
+ allocate_data_block(fio.sbi, NULL, fio.blk_addr,
+ &fio.blk_addr, &sum, CURSEG_COLD_DATA);
+ fio.rw = WRITE_SYNC;
+ f2fs_submit_page_mbio(&fio);
+
+ dn.data_blkaddr = fio.blk_addr;
+ set_data_blkaddr(&dn);
+ f2fs_update_extent_cache(&dn);
+ set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
+ if (page->index == 0)
+ set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
+put_page_out:
+ f2fs_put_page(fio.encrypted_page, 1);
+put_out:
+ f2fs_put_dnode(&dn);
+out:
+ f2fs_put_page(page, 1);
+}
+
+static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
+{
+ struct page *page;
+
+ page = get_lock_data_page(inode, bidx, true);
+ if (IS_ERR(page))
+ return;
+
+ if (gc_type == BG_GC) {
+ if (PageWriteback(page))
+ goto out;
+ set_page_dirty(page);
+ set_cold_data(page);
+ } else {
+ struct f2fs_io_info fio = {
+ .sbi = F2FS_I_SB(inode),
+ .type = DATA,
+ .rw = WRITE_SYNC,
+ .page = page,
+ .encrypted_page = NULL,
+ };
+ set_page_dirty(page);
+ 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(&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 int 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 0;
+
+ 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 (!is_alive(sbi, entry, &dni, start_addr + off, &nofs))
+ 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;
+
+ /* if encrypted inode, let's go phase 3 */
+ if (f2fs_encrypted_inode(inode) &&
+ S_ISREG(inode->i_mode)) {
+ add_gc_inode(gc_list, inode);
+ continue;
+ }
+
+ start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
+ data_page = get_read_data_page(inode,
+ start_bidx + ofs_in_node, READA, true);
+ 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))
+ + ofs_in_node;
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ move_encrypted_block(inode, start_bidx);
+ else
+ move_data_page(inode, start_bidx, 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);
+
+ /* return 1 only if FG_GC succefully reclaimed one */
+ if (get_valid_blocks(sbi, segno, 1) == 0)
+ return 1;
+ }
+ return 0;
+}
+
+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 int 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;
+ int nfree = 0;
+
+ /* read segment summary of victim */
+ sum_page = get_sum_page(sbi, segno);
+
+ blk_start_plug(&plug);
+
+ sum = page_address(sum_page);
+
+ /*
+ * this is to avoid deadlock:
+ * - lock_page(sum_page) - f2fs_replace_block
+ * - check_valid_map() - mutex_lock(sentry_lock)
+ * - mutex_lock(sentry_lock) - change_curseg()
+ * - lock_page(sum_page)
+ */
+ unlock_page(sum_page);
+
+ switch (GET_SUM_TYPE((&sum->footer))) {
+ case SUM_TYPE_NODE:
+ nfree = gc_node_segment(sbi, sum->entries, segno, gc_type);
+ break;
+ case SUM_TYPE_DATA:
+ nfree = 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, 0);
+ return nfree;
+}
+
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
+{
+ unsigned int segno, i;
+ int gc_type = sync ? FG_GC : BG_GC;
+ int sec_freed = 0;
+ int ret = -EINVAL;
+ 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:
+ segno = NULL_SEGNO;
+
+ 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, sec_freed)) {
+ gc_type = FG_GC;
+ if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi))
+ write_checkpoint(sbi, &cpc);
+ }
+
+ if (segno == NULL_SEGNO && !__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, true);
+
+ for (i = 0; i < sbi->segs_per_sec; i++) {
+ /*
+ * for FG_GC case, halt gcing left segments once failed one
+ * of segments in selected section to avoid long latency.
+ */
+ if (!do_garbage_collect(sbi, segno + i, &gc_list, gc_type) &&
+ gc_type == FG_GC)
+ break;
+ }
+
+ if (i == sbi->segs_per_sec && gc_type == FG_GC)
+ sec_freed++;
+
+ if (gc_type == FG_GC)
+ sbi->cur_victim_sec = NULL_SEGNO;
+
+ if (!sync) {
+ if (has_not_enough_free_secs(sbi, sec_freed))
+ goto gc_more;
+
+ if (gc_type == FG_GC)
+ write_checkpoint(sbi, &cpc);
+ }
+stop:
+ mutex_unlock(&sbi->gc_mutex);
+
+ put_gc_inode(&gc_list);
+
+ if (sync)
+ ret = sec_freed ? 0 : -EAGAIN;
+ return ret;
+}
+
+void build_gc_manager(struct f2fs_sb_info *sbi)
+{
+ DIRTY_I(sbi)->v_ops = &default_v_ops;
+}
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
new file mode 100644
index 0000000..9091e0c
--- /dev/null
+++ b/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->rq;
+ return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]);
+}
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
new file mode 100644
index 0000000..71b7206
--- /dev/null
+++ b/fs/f2fs/hash.c
@@ -0,0 +1,103 @@
+/*
+ * 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 (is_dot_dotdot(name_info))
+ 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/fs/f2fs/inline.c b/fs/f2fs/inline.c
new file mode 100644
index 0000000..4d22fa7
--- /dev/null
+++ b/fs/f2fs/inline.c
@@ -0,0 +1,612 @@
+/*
+ * 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"
+#include "node.h"
+
+bool f2fs_may_inline_data(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;
+
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ return false;
+
+ return true;
+}
+
+bool f2fs_may_inline_dentry(struct inode *inode)
+{
+ if (!test_opt(F2FS_I_SB(inode), INLINE_DENTRY))
+ return false;
+
+ if (!S_ISDIR(inode->i_mode))
+ return false;
+
+ return true;
+}
+
+void 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 = {
+ .sbi = F2FS_I_SB(dn->inode),
+ .type = DATA,
+ .rw = WRITE_SYNC | REQ_PRIO,
+ .page = page,
+ .encrypted_page = NULL,
+ };
+ 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:
+ set_page_dirty(page);
+
+ /* 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(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));
+ if (!truncate_inline_inode(ipage, 0))
+ return false;
+ f2fs_clear_inline_inode(inode);
+ update_inode(inode, ipage);
+ f2fs_put_page(ipage, 1);
+ } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
+ if (truncate_blocks(inode, 0, false))
+ return false;
+ goto process_inline;
+ }
+ return false;
+}
+
+struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
+ struct f2fs_filename *fname, struct page **res_page)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+ struct f2fs_inline_dentry *inline_dentry;
+ struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
+ struct f2fs_dir_entry *de;
+ struct f2fs_dentry_ptr d;
+ struct page *ipage;
+ f2fs_hash_t namehash;
+
+ ipage = get_node_page(sbi, dir->i_ino);
+ if (IS_ERR(ipage))
+ return NULL;
+
+ namehash = f2fs_dentry_hash(&name);
+
+ inline_dentry = inline_data_addr(ipage);
+
+ make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
+ de = find_target_dentry(fname, namehash, 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(NULL, &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;
+}
+
+/*
+ * NOTE: ipage is grabbed by caller, but if any error occurs, we should
+ * release ipage in this function.
+ */
+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) {
+ f2fs_put_page(ipage, 1);
+ 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, MAX_INLINE_DATA, 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);
+ memset(dentry_blk->dentry_bitmap + INLINE_DENTRY_BITMAP_SIZE, 0,
+ SIZE_OF_DENTRY_BITMAP - INLINE_DENTRY_BITMAP_SIZE);
+ /*
+ * we do not need to zero out remainder part of dentry and filename
+ * field, since we have used bitmap for marking the usage status of
+ * them, besides, we can also ignore copying/zeroing reserved space
+ * of dentry block, because them haven't been used so far.
+ */
+ 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)
+ return 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(NULL, &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, void *dirent, filldir_t filldir,
+ struct f2fs_str *fstr)
+{
+ unsigned long pos = file->f_pos;
+ unsigned int bit_pos = 0;
+ struct inode *inode = file_inode(file);
+ struct f2fs_inline_dentry *inline_dentry = NULL;
+ struct page *ipage = NULL;
+ struct f2fs_dentry_ptr d;
+
+ if (pos >= NR_INLINE_DENTRY)
+ return 0;
+
+ bit_pos = (pos % NR_INLINE_DENTRY);
+
+ 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(inode, &d, (void *)inline_dentry, 2);
+
+ if (!f2fs_fill_dentries(file, dirent, filldir, &d, 0, bit_pos, fstr))
+ file->f_pos = NR_INLINE_DENTRY;
+
+ f2fs_put_page(ipage, 1);
+ return 0;
+}
+
+int f2fs_inline_data_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo, __u64 start, __u64 len)
+{
+ __u64 byteaddr, ilen;
+ __u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED |
+ FIEMAP_EXTENT_LAST;
+ struct node_info ni;
+ struct page *ipage;
+ int err = 0;
+
+ ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
+
+ if (!f2fs_has_inline_data(inode)) {
+ err = -EAGAIN;
+ goto out;
+ }
+
+ ilen = min_t(size_t, MAX_INLINE_DATA, i_size_read(inode));
+ if (start >= ilen)
+ goto out;
+ if (start + len < ilen)
+ ilen = start + len;
+ ilen -= start;
+
+ get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
+ byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits;
+ byteaddr += (char *)inline_data_addr(ipage) - (char *)F2FS_INODE(ipage);
+ err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags);
+out:
+ f2fs_put_page(ipage, 1);
+ return err;
+}
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
new file mode 100644
index 0000000..ad480e5
--- /dev/null
+++ b/fs/f2fs/inode.c
@@ -0,0 +1,429 @@
+/*
+ * fs/f2fs/inode.c
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/buffer_head.h>
+#include <linux/writeback.h>
+
+#include "f2fs.h"
+#include "node.h"
+
+#include <trace/events/f2fs.h>
+
+void f2fs_set_inode_flags(struct inode *inode)
+{
+ unsigned int flags = F2FS_I(inode)->i_flags;
+
+ inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE |
+ S_NOATIME | S_DIRSYNC);
+
+ if (flags & FS_SYNC_FL)
+ inode->i_flags |= S_SYNC;
+ if (flags & FS_APPEND_FL)
+ inode->i_flags |= S_APPEND;
+ if (flags & FS_IMMUTABLE_FL)
+ inode->i_flags |= S_IMMUTABLE;
+ if (flags & FS_NOATIME_FL)
+ inode->i_flags |= S_NOATIME;
+ if (flags & FS_DIRSYNC_FL)
+ inode->i_flags |= S_DIRSYNC;
+}
+
+static 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);
+ inode->i_uid = le32_to_cpu(ri->i_uid);
+ inode->i_gid = 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_tree(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_xattr(inode);
+ 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)) {
+ if (f2fs_encrypted_inode(inode))
+ inode->i_op = &f2fs_encrypted_symlink_inode_operations;
+ else
+ 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(inode->i_uid);
+ ri->i_gid = cpu_to_le32(inode->i_gid);
+ 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);
+
+ if (F2FS_I(inode)->extent_tree)
+ set_raw_extent(&F2FS_I(inode)->extent_tree->largest,
+ &ri->i_ext);
+ else
+ memset(&ri->i_ext, 0, sizeof(ri->i_ext));
+ 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 balance fs here to prevent from producing dirty node pages
+ * during the urgent cleaning time when runing out of free sections.
+ */
+ update_inode_page(inode);
+
+ 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);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ nid_t xnid = fi->i_xattr_nid;
+ int err = 0;
+
+ /* 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(&inode->i_data, 0);
+
+ 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);
+
+ f2fs_destroy_extent_tree(inode);
+
+ if (inode->i_nlink || is_bad_inode(inode))
+ goto no_delete;
+
+ set_inode_flag(fi, FI_NO_ALLOC);
+ i_size_write(inode, 0);
+
+ if (F2FS_HAS_BLOCKS(inode))
+ err = f2fs_truncate(inode, true);
+
+ if (!err) {
+ f2fs_lock_op(sbi);
+ err = remove_inode_page(inode);
+ f2fs_unlock_op(sbi);
+ }
+
+no_delete:
+ stat_dec_inline_xattr(inode);
+ stat_dec_inline_dir(inode);
+ stat_dec_inline_inode(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(fi, FI_APPEND_WRITE))
+ add_dirty_inode(sbi, inode->i_ino, APPEND_INO);
+ if (is_inode_flag_set(fi, FI_UPDATE_WRITE))
+ add_dirty_inode(sbi, inode->i_ino, UPDATE_INO);
+ if (is_inode_flag_set(fi, FI_FREE_NID)) {
+ if (err && err != -ENOENT)
+ alloc_nid_done(sbi, inode->i_ino);
+ else
+ alloc_nid_failed(sbi, inode->i_ino);
+ clear_inode_flag(fi, FI_FREE_NID);
+ }
+
+ if (err && err != -ENOENT) {
+ if (!exist_written_data(sbi, inode->i_ino, ORPHAN_INO)) {
+ /*
+ * get here because we failed to release resource
+ * of inode previously, reminder our user to run fsck
+ * for fixing.
+ */
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "inode (ino:%lu) resource leak, run fsck "
+ "to fix this issue!", inode->i_ino);
+ }
+ }
+out_clear:
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ if (fi->i_crypt_info)
+ f2fs_free_encryption_info(inode, fi->i_crypt_info);
+#endif
+ end_writeback(inode);
+}
+
+/* caller should call f2fs_lock_op() */
+void handle_failed_inode(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int err = 0;
+
+ clear_nlink(inode);
+ make_bad_inode(inode);
+ unlock_new_inode(inode);
+
+ i_size_write(inode, 0);
+ if (F2FS_HAS_BLOCKS(inode))
+ err = f2fs_truncate(inode, false);
+
+ if (!err)
+ err = remove_inode_page(inode);
+
+ /*
+ * if we skip truncate_node in remove_inode_page bacause we failed
+ * before, it's better to find another way to release resource of
+ * this inode (e.g. valid block count, node block or nid). Here we
+ * choose to add this inode to orphan list, so that we can call iput
+ * for releasing in orphan recovery flow.
+ *
+ * Note: we should add inode to orphan list before f2fs_unlock_op()
+ * so we can prevent losing this orphan when encoutering checkpoint
+ * and following suddenly power-off.
+ */
+ if (err && err != -ENOENT) {
+ err = acquire_orphan_inode(sbi);
+ if (!err)
+ add_orphan_inode(sbi, inode->i_ino);
+ }
+
+ set_inode_flag(F2FS_I(inode), FI_FREE_NID);
+ f2fs_unlock_op(sbi);
+
+ /* iput will drop the inode object */
+ iput(inode);
+}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
new file mode 100644
index 0000000..9e53673
--- /dev/null
+++ b/fs/f2fs/namei.c
@@ -0,0 +1,797 @@
+/*
+ * 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 fail;
+ }
+
+ /* If the directory encrypted, then we should encrypt the inode. */
+ if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
+ f2fs_set_encrypted_inode(inode);
+
+ if (f2fs_may_inline_data(inode))
+ set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
+ if (f2fs_may_inline_dentry(inode))
+ set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
+
+ f2fs_init_extent_tree(inode, NULL);
+
+ stat_inc_inline_xattr(inode);
+ stat_inc_inline_inode(inode);
+ stat_inc_inline_dir(inode);
+
+ trace_f2fs_new_inode(inode, 0);
+ mark_inode_dirty(inode);
+ return inode;
+
+fail:
+ trace_f2fs_new_inode(inode, err);
+ make_bad_inode(inode);
+ if (nid_free)
+ set_inode_flag(F2FS_I(inode), FI_FREE_NID);
+ iput(inode);
+ 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);
+
+ /*
+ * filename format of multimedia file should be defined as:
+ * "filename + '.' + extension".
+ */
+ if (slen < sublen + 2)
+ return 0;
+
+ if (s[slen - sublen - 1] != '.')
+ 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,
+ struct nameidata *nd)
+{
+ 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);
+
+ 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 = old_dentry->d_inode;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+ int err;
+
+ if (f2fs_encrypted_inode(dir) &&
+ !f2fs_is_child_context_consistent_with_parent(dir, inode))
+ return -EPERM;
+
+ 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 = {.len = 2, .name = ".."};
+ unsigned long ino = f2fs_inode_by_name(child->d_inode, &dotdot);
+ if (!ino)
+ return ERR_PTR(-ENOENT);
+ return d_obtain_alias(f2fs_iget(child->d_inode->i_sb, ino));
+}
+
+static int __recover_dot_dentries(struct inode *dir, nid_t pino)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+ struct qstr dot = {.len = 1, .name = "."};
+ struct qstr dotdot = {.len = 2, .name = ".."};
+ 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,
+ struct nameidata *nd)
+{
+ struct inode *inode = NULL;
+ struct f2fs_dir_entry *de;
+ struct page *page;
+ nid_t ino;
+ int err = 0;
+
+ if (dentry->d_name.len > F2FS_NAME_LEN)
+ return ERR_PTR(-ENAMETOOLONG);
+
+ de = f2fs_find_entry(dir, &dentry->d_name, &page);
+ if (!de)
+ return d_splice_alias(inode, dentry);
+
+ 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)) {
+ err = __recover_dot_dentries(inode, dir->i_ino);
+ if (err)
+ goto err_out;
+ }
+ return d_splice_alias(inode, dentry);
+
+err_out:
+ iget_failed(inode);
+ return ERR_PTR(err);
+}
+
+static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+ struct inode *inode = dentry->d_inode;
+ 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 = page_follow_link_light(dentry, nd);
+ if (IS_ERR(page))
+ return page;
+
+ /* this is broken symlink case */
+ if (*nd_get_link(nd) == 0) {
+ kunmap(page);
+ page_cache_release(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 len = strlen(symname);
+ size_t p_len;
+ char *p_str;
+ struct f2fs_str disk_link = FSTR_INIT(NULL, 0);
+ struct f2fs_encrypted_symlink_data *sd = NULL;
+ int err;
+
+ if (len > dir->i_sb->s_blocksize)
+ return -ENAMETOOLONG;
+
+ f2fs_balance_fs(sbi);
+
+ inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+
+ if (f2fs_encrypted_inode(inode))
+ inode->i_op = &f2fs_encrypted_symlink_inode_operations;
+ else
+ 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);
+ alloc_nid_done(sbi, inode->i_ino);
+
+ if (f2fs_encrypted_inode(dir)) {
+ struct qstr istr = QSTR_INIT(symname, len);
+
+ err = f2fs_get_encryption_info(inode);
+ if (err)
+ goto err_out;
+
+ err = f2fs_fname_crypto_alloc_buffer(inode, len, &disk_link);
+ if (err)
+ goto err_out;
+
+ err = f2fs_fname_usr_to_disk(inode, &istr, &disk_link);
+ if (err < 0)
+ goto err_out;
+
+ p_len = encrypted_symlink_data_len(disk_link.len) + 1;
+
+ if (p_len > dir->i_sb->s_blocksize) {
+ err = -ENAMETOOLONG;
+ goto err_out;
+ }
+
+ sd = kzalloc(p_len, GFP_NOFS);
+ if (!sd) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+ memcpy(sd->encrypted_path, disk_link.name, disk_link.len);
+ sd->len = cpu_to_le16(disk_link.len);
+ p_str = (char *)sd;
+ } else {
+ p_len = len + 1;
+ p_str = (char *)symname;
+ }
+
+ err = page_symlink(inode, p_str, p_len);
+
+err_out:
+ 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.
+ */
+ if (!err) {
+ filemap_write_and_wait_range(inode->i_mapping, 0, p_len - 1);
+
+ if (IS_DIRSYNC(dir))
+ f2fs_sync_fs(sbi->sb, 1);
+ } else {
+ f2fs_unlink(dir, dentry);
+ }
+
+ kfree(sd);
+ f2fs_fname_crypto_free_buffer(&disk_link);
+ 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);
+
+ 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 = dentry->d_inode;
+ if (f2fs_empty_dir(inode))
+ return f2fs_unlink(dir, dentry);
+ return -ENOTEMPTY;
+}
+
+static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
+ umode_t mode, dev_t rdev)
+{
+ struct 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 = old_dentry->d_inode;
+ struct inode *new_inode = new_dentry->d_inode;
+ 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;
+
+ if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) &&
+ !f2fs_is_child_context_consistent_with_parent(new_dir,
+ old_inode)) {
+ err = -EPERM;
+ goto out;
+ }
+
+ 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_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);
+ if (new_inode && file_enc_name(new_inode))
+ file_set_enc_name(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;
+}
+
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+static void *f2fs_encrypted_follow_link(struct dentry *dentry,
+ struct nameidata *nd)
+{
+ struct page *cpage = NULL;
+ char *caddr, *paddr = NULL;
+ struct f2fs_str cstr;
+ struct f2fs_str pstr = FSTR_INIT(NULL, 0);
+ struct inode *inode = dentry->d_inode;
+ struct f2fs_encrypted_symlink_data *sd;
+ loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
+ u32 max_size = inode->i_sb->s_blocksize;
+ int res;
+
+ res = f2fs_get_encryption_info(inode);
+ if (res)
+ return ERR_PTR(res);
+
+ cpage = read_mapping_page(inode->i_mapping, 0, NULL);
+ if (IS_ERR(cpage))
+ return cpage;
+ caddr = kmap(cpage);
+ caddr[size] = 0;
+
+ /* Symlink is encrypted */
+ sd = (struct f2fs_encrypted_symlink_data *)caddr;
+ cstr.len = le16_to_cpu(sd->len);
+ cstr.name = kmalloc(cstr.len, GFP_NOFS);
+ if (!cstr.name) {
+ res = -ENOMEM;
+ goto errout;
+ }
+ memcpy(cstr.name, sd->encrypted_path, cstr.len);
+
+ /* this is broken symlink case */
+ if (cstr.name[0] == 0 && cstr.len == 0) {
+ res = -ENOENT;
+ goto errout;
+ }
+
+ if ((cstr.len + sizeof(struct f2fs_encrypted_symlink_data) - 1) >
+ max_size) {
+ /* Symlink data on the disk is corrupted */
+ res = -EIO;
+ goto errout;
+ }
+ res = f2fs_fname_crypto_alloc_buffer(inode, cstr.len, &pstr);
+ if (res)
+ goto errout;
+
+ res = f2fs_fname_disk_to_usr(inode, NULL, &cstr, &pstr);
+ if (res < 0)
+ goto errout;
+
+ kfree(cstr.name);
+
+ paddr = pstr.name;
+
+ /* Null-terminate the name */
+ paddr[res] = '\0';
+ nd_set_link(nd, paddr);
+
+ kunmap(cpage);
+ page_cache_release(cpage);
+ return NULL;
+errout:
+ kfree(cstr.name);
+ f2fs_fname_crypto_free_buffer(&pstr);
+ kunmap(cpage);
+ page_cache_release(cpage);
+ return ERR_PTR(res);
+}
+
+void kfree_put_link(struct dentry *dentry, struct nameidata *nd,
+ void *cookie)
+{
+ char *s = nd_get_link(nd);
+ if (!IS_ERR(s))
+ kfree(s);
+}
+
+const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
+ .readlink = generic_readlink,
+ .follow_link = f2fs_encrypted_follow_link,
+ .put_link = kfree_put_link,
+ .getattr = f2fs_getattr,
+ .setattr = f2fs_setattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = f2fs_listxattr,
+ .removexattr = generic_removexattr,
+};
+#endif
+
+const struct inode_operations f2fs_dir_inode_operations = {
+ .create = f2fs_create,
+ .lookup = f2fs_lookup,
+ .link = f2fs_link,
+ .unlink = f2fs_unlink,
+ .symlink = f2fs_symlink,
+ .mkdir = f2fs_mkdir,
+ .rmdir = f2fs_rmdir,
+ .mknod = f2fs_mknod,
+ .rename = f2fs_rename,
+ .getattr = f2fs_getattr,
+ .setattr = f2fs_setattr,
+ .get_acl = f2fs_get_acl,
+#ifdef CONFIG_F2FS_FS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = f2fs_listxattr,
+ .removexattr = generic_removexattr,
+#endif
+};
+
+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,
+#ifdef CONFIG_F2FS_FS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = f2fs_listxattr,
+ .removexattr = generic_removexattr,
+#endif
+};
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
new file mode 100644
index 0000000..413d772
--- /dev/null
+++ b/fs/f2fs/node.c
@@ -0,0 +1,2140 @@
+/*
+ * 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_NOFS);
+
+ 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);
+}
+
+int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ struct nat_entry *e;
+ bool need = false;
+
+ down_read(&nm_i->nat_tree_lock);
+ e = __lookup_nat_cache(nm_i, nid);
+ if (e) {
+ if (!get_nat_flag(e, IS_CHECKPOINTED) &&
+ !get_nat_flag(e, HAS_FSYNCED_INODE))
+ need = true;
+ }
+ up_read(&nm_i->nat_tree_lock);
+ return need;
+}
+
+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 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_NOFS);
+ 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));
+
+ /* in order to reuse the nid */
+ if (nm_i->next_scan_nid > ni->nid)
+ nm_i->next_scan_nid = ni->nid;
+ }
+
+ /* 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 */
+ if (ni->nid != ni->ino)
+ 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);
+ int nr = nr_shrink;
+
+ if (!down_write_trylock(&nm_i->nat_tree_lock))
+ return 0;
+
+ 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 - 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().
+ */
+int remove_inode_page(struct inode *inode)
+{
+ struct dnode_of_data dn;
+ int err;
+
+ set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino);
+ err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
+ if (err)
+ return err;
+
+ err = truncate_xattr_node(inode, dn.inode_page);
+ if (err) {
+ f2fs_put_dnode(&dn);
+ return err;
+ }
+
+ /* 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);
+ return 0;
+}
+
+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 or error: f2fs_put_page(page, 1)
+ */
+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 = {
+ .sbi = sbi,
+ .type = NODE,
+ .rw = rw,
+ .page = page,
+ .encrypted_page = NULL,
+ };
+
+ get_node_info(sbi, page->index, &ni);
+
+ if (unlikely(ni.blk_addr == NULL_ADDR)) {
+ ClearPageUptodate(page);
+ return -ENOENT;
+ }
+
+ if (PageUptodate(page))
+ return LOCKED_PAGE;
+
+ fio.blk_addr = ni.blk_addr;
+ return f2fs_submit_page_bio(&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);
+ f2fs_put_page(apage, err ? 1 : 0);
+}
+
+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) {
+ f2fs_put_page(page, 1);
+ 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;
+ }
+ mark_page_accessed(page);
+ 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) {
+ f2fs_put_page(page, 1);
+ 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);
+ }
+ mark_page_accessed(page);
+ 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))
+ set_dentry_mark(page,
+ need_dentry_mark(sbi, ino));
+ 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 = {
+ .sbi = sbi,
+ .type = NODE,
+ .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
+ .page = page,
+ .encrypted_page = NULL,
+ };
+
+ 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);
+
+ if (wbc->for_reclaim) {
+ if (!down_read_trylock(&sbi->node_write))
+ goto redirty_out;
+ } else {
+ down_read(&sbi->node_write);
+ }
+
+ 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);
+ up_read(&sbi->node_write);
+ unlock_page(page);
+ return 0;
+ }
+
+ set_page_writeback(page);
+ fio.blk_addr = ni.blk_addr;
+ write_node_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, true);
+
+ 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);
+
+ ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
+ nm_i->ra_nid_pages, META_NAT, false);
+}
+
+/*
+ * 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)) {
+ struct node_info ni;
+
+ 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);
+
+ /* check nid is allocated already */
+ get_node_info(sbi, *nid, &ni);
+ if (ni.blk_addr != NULL_ADDR) {
+ alloc_nid_done(sbi, *nid);
+ goto retry;
+ }
+ 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);
+}
+
+int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ struct free_nid *i, *next;
+ int nr = nr_shrink;
+
+ if (!mutex_trylock(&nm_i->build_lock))
+ return 0;
+
+ spin_lock(&nm_i->free_nid_list_lock);
+ list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) {
+ if (nr_shrink <= 0 || nm_i->fcnt <= NAT_ENTRY_PER_BLOCK)
+ break;
+ if (i->state == NID_ALLOC)
+ continue;
+ __del_from_free_nid_list(nm_i, i);
+ kmem_cache_free(free_nid_slab, i);
+ nm_i->fcnt--;
+ nr_shrink--;
+ }
+ spin_unlock(&nm_i->free_nid_list_lock);
+ mutex_unlock(&nm_i->build_lock);
+
+ return nr - nr_shrink;
+}
+
+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, true);
+
+ for (idx = addr; idx < addr + nrpages; idx++) {
+ struct page *page = get_tmp_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;
+ nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
+
+ 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/fs/f2fs/node.h b/fs/f2fs/node.h
new file mode 100644
index 0000000..e4fffd2
--- /dev/null
+++ b/fs/f2fs/node.h
@@ -0,0 +1,396 @@
+/*
+ * 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 synchronous readahead before building free nids */
+#define FREE_NID_PAGES 4
+
+#define DEF_RA_NID_PAGES 4 /* # of nid pages to be readaheaded */
+
+/* maximum readahead size for node during getting data blocks */
+#define MAX_RA_NODE 128
+
+/* control the memory footprint threshold (10MB per 1GB ram) */
+#define DEF_RAM_THRESHOLD 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_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/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
new file mode 100644
index 0000000..6a3f04f
--- /dev/null
+++ b/fs/f2fs/recovery.c
@@ -0,0 +1,603 @@
+/*
+ * 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;
+ }
+
+ if (file_enc_name(inode)) {
+ iput(dir);
+ return 0;
+ }
+
+ 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);
+ char *name;
+
+ 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);
+
+ if (file_enc_name(inode))
+ name = "<encrypted>";
+ else
+ name = F2FS_INODE(page)->i_name;
+
+ f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s",
+ ino_of_node(page), 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, true);
+
+ while (1) {
+ struct fsync_inode_entry *entry;
+
+ if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
+ return 0;
+
+ page = get_tmp_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 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);
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+
+ err = get_dnode_of_data(&dn, start, ALLOC_NODE);
+ if (err)
+ 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++, dn.ofs_in_node++) {
+ block_t src, dest;
+
+ src = datablock_addr(dn.node_page, dn.ofs_in_node);
+ dest = datablock_addr(page, dn.ofs_in_node);
+
+ /* skip recovering if dest is the same as src */
+ if (src == dest)
+ continue;
+
+ /* dest is invalid, just invalidate src block */
+ if (dest == NULL_ADDR) {
+ truncate_data_blocks_range(&dn, 1);
+ continue;
+ }
+
+ /*
+ * dest is reserved block, invalidate src block
+ * and then reserve one new block in dnode page.
+ */
+ if (dest == NEW_ADDR) {
+ truncate_data_blocks_range(&dn, 1);
+ err = reserve_new_block(&dn);
+ f2fs_bug_on(sbi, err);
+ continue;
+ }
+
+ /* dest is valid block, try to recover from src to dest */
+ if (is_valid_blkaddr(sbi, dest, META_POR)) {
+
+ 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;
+
+ /* write dummy data page */
+ f2fs_replace_block(sbi, &dn, src, dest,
+ ni.version, false);
+ recovered++;
+ }
+ }
+
+ 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);
+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 (!is_valid_blkaddr(sbi, blkaddr, META_POR))
+ break;
+
+ ra_meta_pages_cond(sbi, blkaddr);
+
+ page = get_tmp_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);
+
+ /* prevent checkpoint */
+ mutex_lock(&sbi->cp_mutex);
+
+ blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
+
+ /* step #1: find fsynced inode numbers */
+ 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),
+ (loff_t)MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1);
+
+ if (err) {
+ truncate_inode_pages(NODE_MAPPING(sbi), 0);
+ truncate_inode_pages(META_MAPPING(sbi), 0);
+ }
+
+ clear_sbi_flag(sbi, SBI_POR_DOING);
+ if (err) {
+ bool invalidate = false;
+
+ if (discard_next_dnode(sbi, blkaddr))
+ invalidate = true;
+
+ /* Flush all the NAT/SIT pages */
+ while (get_pages(sbi, F2FS_DIRTY_META))
+ sync_meta_pages(sbi, META, LONG_MAX);
+
+ /* invalidate temporary meta page */
+ if (invalidate)
+ invalidate_mapping_pages(META_MAPPING(sbi),
+ blkaddr, blkaddr);
+
+ 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/fs/f2fs/segment.c b/fs/f2fs/segment.c
new file mode 100644
index 0000000..efebae3
--- /dev/null
+++ b/fs/f2fs/segment.c
@@ -0,0 +1,2560 @@
+/*
+ * 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/swap.h>
+#include <linux/timer.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;
+
+static unsigned long __reverse_ulong(unsigned char *str)
+{
+ unsigned long tmp = 0;
+ int shift = 24, idx = 0;
+
+#if BITS_PER_LONG == 64
+ shift = 56;
+#endif
+ while (shift >= 0) {
+ tmp |= (unsigned long)str[idx++] << shift;
+ shift -= BITS_PER_BYTE;
+ }
+ return tmp;
+}
+
+/**
+ * Copied from latest lib/llist.c
+ * llist_for_each_entry_safe - iterate over some deleted entries of
+ * lock-less list of given type
+ * safe against removal of list entry
+ * @pos: the type * to use as a loop cursor.
+ * @n: another type * to use as temporary storage
+ * @node: the first entry of deleted list entries.
+ * @member: the name of the llist_node with the struct.
+ *
+ * In general, some entries of the lock-less list can be traversed
+ * safely only after being removed from list, so start with an entry
+ * instead of list head.
+ *
+ * If being used on entries deleted from lock-less list directly, the
+ * traverse order is from the newest to the oldest added entry. If
+ * you want to traverse from the oldest to the newest, you must
+ * reverse the order by yourself before traversing.
+ */
+#define llist_for_each_entry_safe(pos, n, node, member) \
+ for (pos = llist_entry((node), typeof(*pos), member); \
+ &pos->member != NULL && \
+ (n = llist_entry(pos->member.next, typeof(*n), member), true); \
+ pos = n)
+
+/**
+ * Copied from latest lib/llist.c
+ * llist_reverse_order - reverse order of a llist chain
+ * @head: first item of the list to be reversed
+ *
+ * Reverse the order of a chain of llist entries and return the
+ * new first entry.
+ */
+struct llist_node *llist_reverse_order(struct llist_node *head)
+{
+ struct llist_node *new_head = NULL;
+
+ while (head) {
+ struct llist_node *tmp = head;
+ head = head->next;
+ tmp->next = new_head;
+ new_head = tmp;
+ }
+
+ return new_head;
+}
+
+/**
+ * Copied from latest linux/list.h
+ * list_last_entry - get the last element from a list
+ * @ptr: the list head to take the element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_struct within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_last_entry(ptr, type, member) \
+ list_entry((ptr)->prev, type, member)
+
+/*
+ * __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 & 0xffffffff00000000UL) == 0)
+ num += 32;
+ else
+ word >>= 32;
+#endif
+ if ((word & 0xffff0000) == 0)
+ num += 16;
+ else
+ word >>= 16;
+
+ if ((word & 0xff00) == 0)
+ num += 8;
+ else
+ 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:
+ * MSB <--> LSB
+ * f2fs_set_bit(0, bitmap) => 1000 0000
+ * f2fs_set_bit(7, bitmap) => 0000 0001
+ */
+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;
+
+ if (offset >= size)
+ return size;
+
+ size -= result;
+ offset %= BITS_PER_LONG;
+ if (!offset)
+ goto aligned;
+
+ tmp = __reverse_ulong((unsigned char *)p);
+ tmp &= ~0UL >> offset;
+
+ if (size < BITS_PER_LONG)
+ goto found_first;
+ if (tmp)
+ goto found_middle;
+
+ size -= BITS_PER_LONG;
+ result += BITS_PER_LONG;
+ p++;
+aligned:
+ while (size & ~(BITS_PER_LONG-1)) {
+ tmp = __reverse_ulong((unsigned char *)p);
+ if (tmp)
+ goto found_middle;
+ result += BITS_PER_LONG;
+ size -= BITS_PER_LONG;
+ p++;
+ }
+ if (!size)
+ return result;
+
+ tmp = __reverse_ulong((unsigned char *)p);
+found_first:
+ tmp &= (~0UL << (BITS_PER_LONG - size));
+ if (!tmp) /* 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;
+
+ if (offset >= size)
+ return size;
+
+ size -= result;
+ offset %= BITS_PER_LONG;
+ if (!offset)
+ goto aligned;
+
+ tmp = __reverse_ulong((unsigned char *)p);
+ tmp |= ~((~0UL << offset) >> offset);
+
+ if (size < BITS_PER_LONG)
+ goto found_first;
+ if (tmp != ~0UL)
+ goto found_middle;
+
+ size -= BITS_PER_LONG;
+ result += BITS_PER_LONG;
+ p++;
+aligned:
+ while (size & ~(BITS_PER_LONG - 1)) {
+ tmp = __reverse_ulong((unsigned char *)p);
+ if (tmp != ~0UL)
+ goto found_middle;
+ result += BITS_PER_LONG;
+ size -= BITS_PER_LONG;
+ p++;
+ }
+ if (!size)
+ return result;
+
+ tmp = __reverse_ulong((unsigned char *)p);
+found_first:
+ tmp |= ~(~0UL << (BITS_PER_LONG - 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;
+
+ f2fs_trace_pid(page);
+
+ set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE);
+ SetPagePrivate(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);
+
+ /* increase reference count with clean state */
+ mutex_lock(&fi->inmem_lock);
+ 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);
+}
+
+int 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 = {
+ .sbi = sbi,
+ .type = DATA,
+ .rw = WRITE_SYNC | REQ_PRIO,
+ .encrypted_page = NULL,
+ };
+ int err = 0;
+
+ /*
+ * 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) {
+ lock_page(cur->page);
+ if (!abort) {
+ if (cur->page->mapping == inode->i_mapping) {
+ set_page_dirty(cur->page);
+ 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);
+ fio.page = cur->page;
+ err = do_write_data_page(&fio);
+ if (err) {
+ unlock_page(cur->page);
+ break;
+ }
+ clear_cold_data(cur->page);
+ submit_bio = true;
+ }
+ } else {
+ trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP);
+ }
+ set_page_private(cur->page, 0);
+ ClearPagePrivate(cur->page);
+ f2fs_put_page(cur->page, 1);
+
+ 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);
+ }
+ return err;
+}
+
+/*
+ * 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, false);
+ }
+}
+
+void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
+{
+ /* try to shrink extent cache when there is no enough memory */
+ if (!available_free_memory(sbi, EXTENT_CACHE))
+ f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER);
+
+ /* check the # of cached NAT entries */
+ if (!available_free_memory(sbi, NAT_ENTRIES))
+ try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
+
+ if (!available_free_memory(sbi, FREE_NIDS))
+ try_to_free_nids(sbi, NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES);
+
+ /* checkpoint is the only way to shrink partial cached entries */
+ if (!available_free_memory(sbi, NAT_ENTRIES) ||
+ excess_prefree_segs(sbi) ||
+ !available_free_memory(sbi, INO_ENTRIES) ||
+ jiffies > sbi->cp_expires)
+ f2fs_sync_fs(sbi->sb, true);
+}
+
+struct __submit_bio_ret {
+ struct completion event;
+ int error;
+};
+
+static void __submit_bio_wait_endio(struct bio *bio, int error)
+{
+ struct __submit_bio_ret *ret = bio->bi_private;
+
+ ret->error = error;
+ complete(&ret->event);
+}
+
+static int __submit_bio_wait(int rw, struct bio *bio)
+{
+ struct __submit_bio_ret ret;
+
+ rw |= REQ_SYNC;
+ init_completion(&ret.event);
+ bio->bi_private = &ret;
+ bio->bi_end_io = __submit_bio_wait_endio;
+ submit_bio(rw, bio);
+ wait_for_completion(&ret.event);
+
+ return ret.error;
+}
+
+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;
+ struct flush_cmd *cmd, *next;
+ int ret;
+
+ bio = f2fs_bio_alloc(0);
+
+ 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)) {
+ struct bio *bio = f2fs_bio_alloc(0);
+ int ret;
+
+ bio->bi_bdev = sbi->sb->s_bdev;
+ ret = __submit_bio_wait(WRITE_FLUSH, bio);
+ bio_put(bio);
+ return ret;
+ }
+
+ 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);
+ struct seg_entry *se;
+ unsigned int offset;
+ block_t i;
+
+ for (i = blkstart; i < blkstart + blklen; i++) {
+ se = get_seg_entry(sbi, GET_SEGNO(sbi, i));
+ offset = GET_BLKOFF_FROM_SEG0(sbi, i);
+
+ if (!f2fs_test_and_set_bit(offset, se->discard_map))
+ sbi->discard_blks--;
+ }
+ trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
+ return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
+}
+
+bool discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+ int err = -ENOTSUPP;
+
+ if (test_opt(sbi, DISCARD)) {
+ struct seg_entry *se = get_seg_entry(sbi,
+ GET_SEGNO(sbi, blkaddr));
+ unsigned int offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
+
+ if (f2fs_test_bit(offset, se->discard_map))
+ return false;
+
+ err = f2fs_issue_discard(sbi, blkaddr, 1);
+ }
+
+ if (err) {
+ update_meta_page(sbi, NULL, blkaddr);
+ return true;
+ }
+ return false;
+}
+
+static void __add_discard_entry(struct f2fs_sb_info *sbi,
+ struct cp_control *cpc, struct seg_entry *se,
+ 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;
+}
+
+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 *discard_map = (unsigned long *)se->discard_map;
+ unsigned long *dmap = SIT_I(sbi)->tmp_map;
+ unsigned int start = 0, end = -1;
+ bool force = (cpc->reason == CP_DISCARD);
+ int i;
+
+ if (se->valid_blocks == max_blocks)
+ return;
+
+ if (!force) {
+ if (!test_opt(sbi, DISCARD) || !se->valid_blocks ||
+ SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards)
+ return;
+ }
+
+ /* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
+ for (i = 0; i < entries; i++)
+ dmap[i] = force ? ~ckpt_map[i] & ~discard_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);
+ __add_discard_entry(sbi, cpc, se, 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 cp_control *cpc)
+{
+ 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) {
+ if (cpc->reason == CP_DISCARD && entry->len < cpc->trim_minlen)
+ goto skip;
+ f2fs_issue_discard(sbi, entry->blkaddr, entry->len);
+ cpc->trimmed += entry->len;
+skip:
+ 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);
+ if (!f2fs_test_and_set_bit(offset, se->discard_map))
+ sbi->discard_blks--;
+ } else {
+ if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map))
+ f2fs_bug_on(sbi, 1);
+ if (f2fs_test_and_clear_bit(offset, se->discard_map))
+ sbi->discard_blks++;
+ }
+ 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);
+}
+
+bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+ struct sit_info *sit_i = SIT_I(sbi);
+ unsigned int segno, offset;
+ struct seg_entry *se;
+ bool is_cp = false;
+
+ if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+ return true;
+
+ mutex_lock(&sit_i->sentry_lock);
+
+ segno = GET_SEGNO(sbi, blkaddr);
+ se = get_seg_entry(sbi, segno);
+ offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
+
+ if (f2fs_test_bit(offset, se->ckpt_valid_map))
+ is_cp = true;
+
+ mutex_unlock(&sit_i->sentry_lock);
+
+ return is_cp;
+}
+
+/*
+ * 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));
+}
+
+void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr)
+{
+ struct page *page = grab_meta_page(sbi, blk_addr);
+ void *dst = page_address(page);
+
+ if (src)
+ memcpy(dst, src, PAGE_CACHE_SIZE);
+ else
+ memset(dst, 0, PAGE_CACHE_SIZE);
+ set_page_dirty(page);
+ f2fs_put_page(page, 1);
+}
+
+static void write_sum_page(struct f2fs_sb_info *sbi,
+ struct f2fs_summary_block *sum_blk, block_t blk_addr)
+{
+ update_meta_page(sbi, (void *)sum_blk, blk_addr);
+}
+
+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 (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 = max_t(__u64, 1, 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;
+
+ if (sbi->discard_blks == 0)
+ break;
+ else if (sbi->discard_blks < BATCHED_TRIM_BLOCKS(sbi))
+ cpc.trim_end = end_segno;
+ else
+ 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 &&
+ !has_not_enough_free_secs(sbi, 0))
+ __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_summary *sum, struct f2fs_io_info *fio)
+{
+ int type = __get_segment_type(fio->page, fio->type);
+
+ allocate_data_block(fio->sbi, fio->page, fio->blk_addr,
+ &fio->blk_addr, sum, type);
+
+ /* writeout dirty page into bdev */
+ f2fs_submit_page_mbio(fio);
+}
+
+void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
+{
+ struct f2fs_io_info fio = {
+ .sbi = sbi,
+ .type = META,
+ .rw = WRITE_SYNC | REQ_META | REQ_PRIO,
+ .blk_addr = page->index,
+ .page = page,
+ .encrypted_page = NULL,
+ };
+
+ if (unlikely(page->index >= MAIN_BLKADDR(sbi)))
+ fio.rw &= ~REQ_META;
+
+ set_page_writeback(page);
+ f2fs_submit_page_mbio(&fio);
+}
+
+void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
+{
+ struct f2fs_summary sum;
+
+ set_summary(&sum, nid, 0, 0);
+ do_write_page(&sum, fio);
+}
+
+void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
+{
+ struct f2fs_sb_info *sbi = fio->sbi;
+ 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(&sum, fio);
+ dn->data_blkaddr = fio->blk_addr;
+}
+
+void rewrite_data_page(struct f2fs_io_info *fio)
+{
+ stat_inc_inplace_blocks(fio->sbi);
+ f2fs_submit_page_mbio(fio);
+}
+
+static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
+ struct f2fs_summary *sum,
+ block_t old_blkaddr, block_t new_blkaddr,
+ bool recover_curseg)
+{
+ struct sit_info *sit_i = SIT_I(sbi);
+ struct curseg_info *curseg;
+ unsigned int segno, old_cursegno;
+ struct seg_entry *se;
+ int type;
+ unsigned short old_blkoff;
+
+ segno = GET_SEGNO(sbi, new_blkaddr);
+ se = get_seg_entry(sbi, segno);
+ type = se->type;
+
+ if (!recover_curseg) {
+ /* for recovery flow */
+ if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) {
+ if (old_blkaddr == NULL_ADDR)
+ type = CURSEG_COLD_DATA;
+ else
+ type = CURSEG_WARM_DATA;
+ }
+ } else {
+ if (!IS_CURSEG(sbi, segno))
+ type = CURSEG_WARM_DATA;
+ }
+
+ curseg = CURSEG_I(sbi, type);
+
+ mutex_lock(&curseg->curseg_mutex);
+ mutex_lock(&sit_i->sentry_lock);
+
+ old_cursegno = curseg->segno;
+ old_blkoff = curseg->next_blkoff;
+
+ /* 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);
+
+ if (!recover_curseg)
+ update_sit_entry(sbi, new_blkaddr, 1);
+ if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
+ update_sit_entry(sbi, old_blkaddr, -1);
+
+ locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
+ locate_dirty_segment(sbi, GET_SEGNO(sbi, new_blkaddr));
+
+ locate_dirty_segment(sbi, old_cursegno);
+
+ if (recover_curseg) {
+ if (old_cursegno != curseg->segno) {
+ curseg->next_segno = old_cursegno;
+ change_curseg(sbi, type, true);
+ }
+ curseg->next_blkoff = old_blkoff;
+ }
+
+ mutex_unlock(&sit_i->sentry_lock);
+ mutex_unlock(&curseg->curseg_mutex);
+}
+
+void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
+ block_t old_addr, block_t new_addr,
+ unsigned char version, bool recover_curseg)
+{
+ struct f2fs_summary sum;
+
+ set_summary(&sum, dn->nid, dn->ofs_in_node, version);
+
+ __f2fs_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg);
+
+ dn->data_blkaddr = new_addr;
+ set_data_blkaddr(dn);
+ f2fs_update_extent_cache(dn);
+}
+
+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;
+ struct page *target;
+ int i;
+
+ down_read(&io->io_rwsem);
+ if (!io->bio) {
+ up_read(&io->io_rwsem);
+ return false;
+ }
+
+ __bio_for_each_segment(bvec, io->bio, i, 0) {
+
+ if (bvec->bv_page->mapping) {
+ target = bvec->bv_page;
+ } else {
+ struct f2fs_crypto_ctx *ctx;
+
+ /* encrypted page */
+ ctx = (struct f2fs_crypto_ctx *)page_private(
+ bvec->bv_page);
+ target = ctx->w.control_page;
+ }
+
+ if (page == target) {
+ up_read(&io->io_rwsem);
+ return true;
+ }
+ }
+
+ 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);
+ }
+}
+
+void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
+ block_t blkaddr)
+{
+ struct page *cpage;
+
+ if (blkaddr == NEW_ADDR)
+ return;
+
+ f2fs_bug_on(sbi, blkaddr == NULL_ADDR);
+
+ cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
+ if (cpage) {
+ f2fs_wait_on_page_writeback(cpage, DATA);
+ f2fs_put_page(cpage, 1);
+ }
+}
+
+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, true);
+
+ /* 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, true);
+
+ 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_NOFS);
+
+ 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 = f2fs_kvzalloc(MAIN_SEGS(sbi) *
+ sizeof(struct seg_entry), GFP_KERNEL);
+ if (!sit_i->sentries)
+ return -ENOMEM;
+
+ bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
+ sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(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);
+ sit_i->sentries[start].discard_map
+ = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ if (!sit_i->sentries[start].cur_valid_map ||
+ !sit_i->sentries[start].ckpt_valid_map ||
+ !sit_i->sentries[start].discard_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 = f2fs_kvzalloc(MAIN_SECS(sbi) *
+ sizeof(struct sec_entry), GFP_KERNEL);
+ 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 = f2fs_kvmalloc(bitmap_size, GFP_KERNEL);
+ if (!free_i->free_segmap)
+ return -ENOMEM;
+
+ sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
+ free_i->free_secmap = f2fs_kvmalloc(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, true);
+
+ 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);
+
+ /* build discard map only one time */
+ memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
+ sbi->discard_blks += sbi->blocks_per_seg - se->valid_blocks;
+
+ 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 = f2fs_kvzalloc(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] = f2fs_kvzalloc(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);
+ f2fs_kvfree(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);
+ f2fs_kvfree(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;
+ f2fs_kvfree(free_i->free_segmap);
+ f2fs_kvfree(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->sentries[start].discard_map);
+ }
+ }
+ kfree(sit_i->tmp_map);
+
+ f2fs_kvfree(sit_i->sentries);
+ f2fs_kvfree(sit_i->sec_entries);
+ f2fs_kvfree(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/fs/f2fs/segment.h b/fs/f2fs/segment.h
new file mode 100644
index 0000000..3bbeca1
--- /dev/null
+++ b/fs/f2fs/segment.h
@@ -0,0 +1,733 @@
+/*
+ * 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.
+ * FORCE_FG_GC means on-demand cleaning job in background.
+ */
+enum {
+ BG_GC = 0,
+ FG_GC,
+ FORCE_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 *discard_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);
+};
+
+/*
+ * this value is set in page as a private data which indicate that
+ * the page is atomically written, and it is in inmem_pages list.
+ */
+#define ATOMIC_WRITTEN_PAGE 0x0000ffff
+
+#define IS_ATOMIC_WRITTEN_PAGE(page) \
+ (page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
+
+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;
+}
+
+static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
+{
+ f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1);
+}
+
+static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
+{
+ f2fs_bug_on(sbi, blk_addr < SEG0_BLKADDR(sbi)
+ || 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)
+{
+#ifdef CONFIG_F2FS_CHECK_FS
+ bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false;
+ int valid_blocks = 0;
+ int cur_pos = 0, next_pos;
+
+ /* 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);
+#endif
+ /* check segment usage, and check boundary of a given segment number */
+ f2fs_bug_on(sbi, GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
+ || segno > TOTAL_SEGS(sbi) - 1);
+}
+
+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/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c
new file mode 100644
index 0000000..420b233
--- /dev/null
+++ b/fs/f2fs/shrinker.c
@@ -0,0 +1,139 @@
+/*
+ * f2fs shrinker support
+ * the basic infra was copied from fs/ubifs/shrinker.c
+ *
+ * Copyright (c) 2015 Motorola Mobility
+ * Copyright (c) 2015 Jaegeuk Kim <jaegeuk@kernel.org>
+ *
+ * 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"
+
+static LIST_HEAD(f2fs_list);
+static DEFINE_SPINLOCK(f2fs_list_lock);
+static unsigned int shrinker_run_no;
+
+static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
+{
+ return NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt;
+}
+
+static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
+{
+ if (NM_I(sbi)->fcnt > NAT_ENTRY_PER_BLOCK)
+ return NM_I(sbi)->fcnt - NAT_ENTRY_PER_BLOCK;
+ return 0;
+}
+
+static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi)
+{
+ return sbi->total_ext_tree + atomic_read(&sbi->total_ext_node);
+}
+
+int f2fs_shrink_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ struct f2fs_sb_info *sbi;
+ struct list_head *p;
+ unsigned long count = 0;
+
+ spin_lock(&f2fs_list_lock);
+ p = f2fs_list.next;
+ while (p != &f2fs_list) {
+ sbi = list_entry(p, struct f2fs_sb_info, s_list);
+
+ /* stop f2fs_put_super */
+ if (!mutex_trylock(&sbi->umount_mutex)) {
+ p = p->next;
+ continue;
+ }
+ spin_unlock(&f2fs_list_lock);
+
+ /* count extent cache entries */
+ count += __count_extent_cache(sbi);
+
+ /* shrink clean nat cache entries */
+ count += __count_nat_entries(sbi);
+
+ /* count free nids cache entries */
+ count += __count_free_nids(sbi);
+
+ spin_lock(&f2fs_list_lock);
+ p = p->next;
+ mutex_unlock(&sbi->umount_mutex);
+ }
+ spin_unlock(&f2fs_list_lock);
+ return count;
+}
+
+int f2fs_shrink_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ unsigned long nr = sc->nr_to_scan;
+ struct f2fs_sb_info *sbi;
+ struct list_head *p;
+ unsigned int run_no;
+ unsigned long freed = 0;
+
+ spin_lock(&f2fs_list_lock);
+ do {
+ run_no = ++shrinker_run_no;
+ } while (run_no == 0);
+ p = f2fs_list.next;
+ while (p != &f2fs_list) {
+ sbi = list_entry(p, struct f2fs_sb_info, s_list);
+
+ if (sbi->shrinker_run_no == run_no)
+ break;
+
+ /* stop f2fs_put_super */
+ if (!mutex_trylock(&sbi->umount_mutex)) {
+ p = p->next;
+ continue;
+ }
+ spin_unlock(&f2fs_list_lock);
+
+ sbi->shrinker_run_no = run_no;
+
+ /* shrink extent cache entries */
+ freed += f2fs_shrink_extent_tree(sbi, nr >> 1);
+
+ /* shrink clean nat cache entries */
+ if (freed < nr)
+ freed += try_to_free_nats(sbi, nr - freed);
+
+ /* shrink free nids cache entries */
+ if (freed < nr)
+ freed += try_to_free_nids(sbi, nr - freed);
+
+ spin_lock(&f2fs_list_lock);
+ p = p->next;
+ list_move_tail(&sbi->s_list, &f2fs_list);
+ mutex_unlock(&sbi->umount_mutex);
+ if (freed >= nr)
+ break;
+ }
+ spin_unlock(&f2fs_list_lock);
+ return f2fs_shrink_count(NULL, NULL);
+}
+
+void f2fs_join_shrinker(struct f2fs_sb_info *sbi)
+{
+ spin_lock(&f2fs_list_lock);
+ list_add_tail(&sbi->s_list, &f2fs_list);
+ spin_unlock(&f2fs_list_lock);
+}
+
+void f2fs_leave_shrinker(struct f2fs_sb_info *sbi)
+{
+ f2fs_shrink_extent_tree(sbi, __count_extent_cache(sbi));
+
+ spin_lock(&f2fs_list_lock);
+ list_del(&sbi->s_list);
+ spin_unlock(&f2fs_list_lock);
+}
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
new file mode 100644
index 0000000..95ee32c
--- /dev/null
+++ b/fs/f2fs/super.c
@@ -0,0 +1,1515 @@
+/*
+ * 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;
+
+/* f2fs-wide shrinker description */
+static struct shrinker f2fs_shrinker_info = {
+ .shrink = f2fs_shrink_scan,
+ .seeks = DEFAULT_SEEKS,
+};
+
+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_noextent_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_noextent_cache, "noextent_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(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
+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);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, cp_interval);
+
+#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),
+ ATTR_LIST(ra_nid_pages),
+ ATTR_LIST(cp_interval),
+ 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);
+ struct request_queue *q;
+ 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);
+ clear_opt(sbi, FORCE_FG_GC);
+ } else if (strlen(name) == 3 && !strncmp(name, "off", 3)) {
+ clear_opt(sbi, BG_GC);
+ clear_opt(sbi, FORCE_FG_GC);
+ } else if (strlen(name) == 4 && !strncmp(name, "sync", 4)) {
+ set_opt(sbi, BG_GC);
+ set_opt(sbi, FORCE_FG_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:
+ q = bdev_get_queue(sb->s_bdev);
+ if (blk_queue_discard(q)) {
+ set_opt(sbi, DISCARD);
+ } else {
+ f2fs_msg(sb, KERN_WARNING,
+ "mounting with \"discard\" option, but "
+ "the device does not support 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_noextent_cache:
+ clear_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;
+ init_rwsem(&fi->i_sem);
+ 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;
+
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ fi->i_crypt_info = NULL;
+#endif
+ 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) {
+ if (!inode->i_nlink && !is_bad_inode(inode)) {
+ /* to avoid evict_inode call simultaneously */
+ atomic_inc(&inode->i_count);
+ spin_unlock(&inode->i_lock);
+
+ /* some remained atomic pages should discarded */
+ if (f2fs_is_atomic_file(inode))
+ commit_inmem_pages(inode, true);
+
+ i_size_write(inode, 0);
+
+ if (F2FS_HAS_BLOCKS(inode))
+ f2fs_truncate(inode, true);
+
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ if (F2FS_I(inode)->i_crypt_info)
+ f2fs_free_encryption_info(inode,
+ F2FS_I(inode)->i_crypt_info);
+#endif
+ spin_lock(&inode->i_lock);
+ atomic_dec(&inode->i_count);
+ }
+ 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);
+
+ stop_gc_thread(sbi);
+
+ /* prevent remaining shrinker jobs */
+ mutex_lock(&sbi->umount_mutex);
+
+ /*
+ * 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);
+ }
+
+ /* write_checkpoint can update stat informaion */
+ f2fs_destroy_stats(sbi);
+
+ /*
+ * 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);
+
+ f2fs_leave_shrinker(sbi);
+ mutex_unlock(&sbi->umount_mutex);
+
+ 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, 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)) {
+ if (test_opt(sbi, FORCE_FG_GC))
+ seq_printf(seq, ",background_gc=%s", "sync");
+ else
+ 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");
+ else
+ seq_puts(seq, ",noextent_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, "%-10d", 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(inode)->data);
+}
+
+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 void default_options(struct f2fs_sb_info *sbi)
+{
+ /* init some FS parameters */
+ sbi->active_logs = NR_CURSEG_TYPE;
+
+ set_opt(sbi, BG_GC);
+ set_opt(sbi, INLINE_DATA);
+ set_opt(sbi, EXTENT_CACHE);
+
+#ifdef CONFIG_F2FS_FS_XATTR
+ set_opt(sbi, XATTR_USER);
+#endif
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+ set_opt(sbi, POSIX_ACL);
+#endif
+}
+
+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;
+ bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
+
+ 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;
+ default_options(sbi);
+
+ /* 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;
+
+ /* disallow enable/disable extent_cache dynamically */
+ if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) {
+ err = -EINVAL;
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "switch extent_cache option is not allowed");
+ goto restore_opts;
+ }
+
+ /*
+ * 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;
+ sbi->cp_interval = DEF_CP_INTERVAL;
+ clear_sbi_flag(sbi, SBI_NEED_FSCK);
+
+ INIT_LIST_HEAD(&sbi->s_list);
+ mutex_init(&sbi->umount_mutex);
+}
+
+/*
+ * 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 *recovery)
+{
+ int block = 0;
+ struct buffer_head *buffer;
+ struct f2fs_super_block *super;
+ int err = 0;
+
+retry:
+ buffer = sb_bread(sb, block);
+ if (!buffer) {
+ *recovery = 1;
+ f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock",
+ block + 1);
+ if (block == 0) {
+ block++;
+ goto retry;
+ } else {
+ err = -EIO;
+ goto out;
+ }
+ }
+
+ super = (struct f2fs_super_block *)
+ ((char *)(buffer)->b_data + F2FS_SUPER_OFFSET);
+
+ /* sanity checking of raw super */
+ if (sanity_check_raw_super(sb, super)) {
+ brelse(buffer);
+ *recovery = 1;
+ f2fs_msg(sb, KERN_ERR,
+ "Can't find valid F2FS filesystem in %dth superblock",
+ block + 1);
+ if (block == 0) {
+ block++;
+ goto retry;
+ } else {
+ err = -EINVAL;
+ goto out;
+ }
+ }
+
+ if (!*raw_super) {
+ *raw_super_buf = buffer;
+ *raw_super = super;
+ } else {
+ /* already have a valid superblock */
+ brelse(buffer);
+ }
+
+ /* check the validity of the second superblock */
+ if (block == 0) {
+ block++;
+ goto retry;
+ }
+
+out:
+ /* No valid superblock */
+ if (!*raw_super)
+ return err;
+
+ return 0;
+}
+
+int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
+{
+ struct buffer_head *sbh = sbi->raw_super_buf;
+ sector_t block = sbh->b_blocknr;
+ int err;
+
+ /* write back-up superblock first */
+ sbh->b_blocknr = block ? 0 : 1;
+ mark_buffer_dirty(sbh);
+ err = sync_dirty_buffer(sbh);
+
+ sbh->b_blocknr = block;
+
+ /* if we are in recovery path, skip writing valid superblock */
+ if (recover || err)
+ goto out;
+
+ /* write current valid superblock */
+ mark_buffer_dirty(sbh);
+ err = sync_dirty_buffer(sbh);
+out:
+ clear_buffer_write_io_error(sbh);
+ set_buffer_uptodate(sbh);
+ return err;
+}
+
+static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
+{
+ struct f2fs_sb_info *sbi;
+ struct f2fs_super_block *raw_super;
+ struct buffer_head *raw_super_buf;
+ struct inode *root;
+ long err;
+ bool retry = true, need_fsck = false;
+ char *options = NULL;
+ int recovery, i;
+
+try_onemore:
+ err = -EINVAL;
+ raw_super = NULL;
+ raw_super_buf = NULL;
+ recovery = 0;
+
+ /* 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, &recovery);
+ if (err)
+ goto free_sbi;
+
+ sb->s_fs_info = sbi;
+ default_options(sbi);
+ /* 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);
+
+ /* disallow all the data/node/meta page writes */
+ set_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;
+ }
+
+ f2fs_join_shrinker(sbi);
+
+ /* if there are nt orphan nodes free them */
+ err = recover_orphan_inodes(sbi);
+ if (err)
+ goto free_node_inode;
+
+ /* read root inode and dentry */
+ root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
+ if (IS_ERR(root)) {
+ f2fs_msg(sb, KERN_ERR, "Failed to read root inode");
+ err = PTR_ERR(root);
+ goto free_node_inode;
+ }
+ if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
+ 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);
+
+ 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;
+ }
+ }
+ /* recover_fsync_data() cleared this already */
+ clear_sbi_flag(sbi, SBI_POR_DOING);
+
+ /*
+ * 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);
+
+ /* recover broken superblock */
+ if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) {
+ f2fs_msg(sb, KERN_INFO, "Recover invalid superblock");
+ f2fs_commit_super(sbi, true);
+ }
+
+ sbi->cp_expires = round_jiffies_up(jiffies);
+
+ 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:
+ mutex_lock(&sbi->umount_mutex);
+ f2fs_leave_shrinker(sbi);
+ iput(sbi->node_inode);
+ mutex_unlock(&sbi->umount_mutex);
+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,
+};
+
+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 = f2fs_init_crypto();
+ if (err)
+ goto free_kset;
+
+ register_shrinker(&f2fs_shrinker_info);
+
+ err = register_filesystem(&f2fs_fs_type);
+ if (err)
+ goto free_shrinker;
+ f2fs_create_root_stats();
+ f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+ return 0;
+
+free_shrinker:
+ unregister_shrinker(&f2fs_shrinker_info);
+ f2fs_exit_crypto();
+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_shrinker(&f2fs_shrinker_info);
+ unregister_filesystem(&f2fs_fs_type);
+ f2fs_exit_crypto();
+ 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/fs/f2fs/trace.c b/fs/f2fs/trace.c
new file mode 100644
index 0000000..145fb65
--- /dev/null
+++ b/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 f2fs_io_info *fio, int flush)
+{
+ struct inode *inode;
+ pid_t pid;
+ int major, minor;
+
+ if (flush) {
+ __print_last_io();
+ return;
+ }
+
+ inode = fio->page->mapping->host;
+ pid = page_private(fio->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/fs/f2fs/trace.h b/fs/f2fs/trace.h
new file mode 100644
index 0000000..67db24a
--- /dev/null
+++ b/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 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(i, n)
+#define f2fs_build_trace_ios()
+#define f2fs_destroy_trace_ios()
+
+#endif
+#endif /* __F2FS_TRACE_H__ */
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
new file mode 100644
index 0000000..dd0646a
--- /dev/null
+++ b/fs/f2fs/xattr.c
@@ -0,0 +1,623 @@
+/*
+ * 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 "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(dentry->d_inode, 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(dentry->d_inode, 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 = dentry->d_inode;
+
+ 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 = dentry->d_inode;
+
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ if (!inode_owner_or_capable(inode))
+ return -EPERM;
+ if (value == NULL)
+ return -EINVAL;
+
+ F2FS_I(inode)->i_advise |= *(char *)value;
+ 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] = &f2fs_xattr_acl_access_handler,
+ [F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &f2fs_xattr_acl_default_handler,
+#endif
+ [F2FS_XATTR_INDEX_TRUSTED] = &f2fs_xattr_trusted_handler,
+#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
+ &f2fs_xattr_acl_access_handler,
+ &f2fs_xattr_acl_default_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 = dentry->d_inode;
+ 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)
+ return -ERANGE;
+
+ if (size > MAX_VALUE_LEN(inode))
+ return -E2BIG;
+
+ 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 (index == F2FS_XATTR_INDEX_ENCRYPTION &&
+ !strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
+ f2fs_set_encrypted_inode(inode);
+
+ 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/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
new file mode 100644
index 0000000..47cf0e5
--- /dev/null
+++ b/fs/f2fs/xattr.h
@@ -0,0 +1,158 @@
+/*
+ * 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
+/* Should be same as EXT4_XATTR_INDEX_ENCRYPTION */
+#define F2FS_XATTR_INDEX_ENCRYPTION 9
+
+#define F2FS_XATTR_NAME_ENCRYPTION_CONTEXT "c"
+
+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_acl_access_handler;
+extern const struct xattr_handler f2fs_xattr_acl_default_handler;
+extern const struct xattr_handler f2fs_xattr_advise_handler;
+extern const struct xattr_handler f2fs_xattr_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__ */
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
new file mode 100644
index 0000000..25c6324
--- /dev/null
+++ b/include/linux/f2fs_fs.h
@@ -0,0 +1,494 @@
+/**
+ * include/linux/f2fs_fs.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_FS_H
+#define _LINUX_F2FS_FS_H
+
+#include <linux/pagemap.h>
+#include <linux/types.h>
+
+#define F2FS_SUPER_OFFSET 1024 /* byte-size offset */
+#define F2FS_MIN_LOG_SECTOR_SIZE 9 /* 9 bits for 512 bytes */
+#define F2FS_MAX_LOG_SECTOR_SIZE 12 /* 12 bits for 4096 bytes */
+#define F2FS_LOG_SECTORS_PER_BLOCK 3 /* log number for sector/blk */
+#define F2FS_BLKSIZE 4096 /* support only 4KB block */
+#define F2FS_BLKSIZE_BITS 12 /* bits for F2FS_BLKSIZE */
+#define F2FS_MAX_EXTENSION 64 /* # of extension entries */
+#define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) / F2FS_BLKSIZE)
+
+#define NULL_ADDR ((block_t)0) /* used as block_t addresses */
+#define NEW_ADDR ((block_t)-1) /* used as block_t addresses */
+
+#define F2FS_BYTES_TO_BLK(bytes) ((bytes) >> F2FS_BLKSIZE_BITS)
+#define F2FS_BLK_TO_BYTES(blk) ((blk) << F2FS_BLKSIZE_BITS)
+
+/* 0, 1(node nid), 2(meta nid) are reserved node id */
+#define F2FS_RESERVED_NODE_NUM 3
+
+#define F2FS_ROOT_INO(sbi) (sbi->root_ino_num)
+#define F2FS_NODE_INO(sbi) (sbi->node_ino_num)
+#define F2FS_META_INO(sbi) (sbi->meta_ino_num)
+
+/* This flag is used by node and meta inodes, and by recovery */
+#define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO)
+#define GFP_F2FS_HIGH_ZERO (GFP_NOFS | __GFP_ZERO | __GFP_HIGHMEM)
+
+/*
+ * For further optimization on multi-head logs, on-disk layout supports maximum
+ * 16 logs by default. The number, 16, is expected to cover all the cases
+ * enoughly. The implementaion currently uses no more than 6 logs.
+ * Half the logs are used for nodes, and the other half are used for data.
+ */
+#define MAX_ACTIVE_LOGS 16
+#define MAX_ACTIVE_NODE_LOGS 8
+#define MAX_ACTIVE_DATA_LOGS 8
+
+#define VERSION_LEN 256
+
+/*
+ * For superblock
+ */
+struct f2fs_super_block {
+ __le32 magic; /* Magic Number */
+ __le16 major_ver; /* Major Version */
+ __le16 minor_ver; /* Minor Version */
+ __le32 log_sectorsize; /* log2 sector size in bytes */
+ __le32 log_sectors_per_block; /* log2 # of sectors per block */
+ __le32 log_blocksize; /* log2 block size in bytes */
+ __le32 log_blocks_per_seg; /* log2 # of blocks per segment */
+ __le32 segs_per_sec; /* # of segments per section */
+ __le32 secs_per_zone; /* # of sections per zone */
+ __le32 checksum_offset; /* checksum offset inside super block */
+ __le64 block_count; /* total # of user blocks */
+ __le32 section_count; /* total # of sections */
+ __le32 segment_count; /* total # of segments */
+ __le32 segment_count_ckpt; /* # of segments for checkpoint */
+ __le32 segment_count_sit; /* # of segments for SIT */
+ __le32 segment_count_nat; /* # of segments for NAT */
+ __le32 segment_count_ssa; /* # of segments for SSA */
+ __le32 segment_count_main; /* # of segments for main area */
+ __le32 segment0_blkaddr; /* start block address of segment 0 */
+ __le32 cp_blkaddr; /* start block address of checkpoint */
+ __le32 sit_blkaddr; /* start block address of SIT */
+ __le32 nat_blkaddr; /* start block address of NAT */
+ __le32 ssa_blkaddr; /* start block address of SSA */
+ __le32 main_blkaddr; /* start block address of main area */
+ __le32 root_ino; /* root inode number */
+ __le32 node_ino; /* node inode number */
+ __le32 meta_ino; /* meta inode number */
+ __u8 uuid[16]; /* 128-bit uuid for volume */
+ __le16 volume_name[512]; /* volume name */
+ __le32 extension_count; /* # of extensions below */
+ __u8 extension_list[F2FS_MAX_EXTENSION][8]; /* extension array */
+ __le32 cp_payload;
+ __u8 version[VERSION_LEN]; /* the kernel version */
+ __u8 init_version[VERSION_LEN]; /* the initial kernel version */
+ __le32 feature; /* defined features */
+ __u8 encryption_level; /* versioning level for encryption */
+ __u8 encrypt_pw_salt[16]; /* Salt used for string2key algorithm */
+ __u8 reserved[871]; /* valid reserved region */
+} __packed;
+
+/*
+ * For checkpoint
+ */
+#define CP_FASTBOOT_FLAG 0x00000020
+#define CP_FSCK_FLAG 0x00000010
+#define CP_ERROR_FLAG 0x00000008
+#define CP_COMPACT_SUM_FLAG 0x00000004
+#define CP_ORPHAN_PRESENT_FLAG 0x00000002
+#define CP_UMOUNT_FLAG 0x00000001
+
+#define F2FS_CP_PACKS 2 /* # of checkpoint packs */
+
+struct f2fs_checkpoint {
+ __le64 checkpoint_ver; /* checkpoint block version number */
+ __le64 user_block_count; /* # of user blocks */
+ __le64 valid_block_count; /* # of valid blocks in main area */
+ __le32 rsvd_segment_count; /* # of reserved segments for gc */
+ __le32 overprov_segment_count; /* # of overprovision segments */
+ __le32 free_segment_count; /* # of free segments in main area */
+
+ /* information of current node segments */
+ __le32 cur_node_segno[MAX_ACTIVE_NODE_LOGS];
+ __le16 cur_node_blkoff[MAX_ACTIVE_NODE_LOGS];
+ /* information of current data segments */
+ __le32 cur_data_segno[MAX_ACTIVE_DATA_LOGS];
+ __le16 cur_data_blkoff[MAX_ACTIVE_DATA_LOGS];
+ __le32 ckpt_flags; /* Flags : umount and journal_present */
+ __le32 cp_pack_total_block_count; /* total # of one cp pack */
+ __le32 cp_pack_start_sum; /* start block number of data summary */
+ __le32 valid_node_count; /* Total number of valid nodes */
+ __le32 valid_inode_count; /* Total number of valid inodes */
+ __le32 next_free_nid; /* Next free node number */
+ __le32 sit_ver_bitmap_bytesize; /* Default value 64 */
+ __le32 nat_ver_bitmap_bytesize; /* Default value 256 */
+ __le32 checksum_offset; /* checksum offset inside cp block */
+ __le64 elapsed_time; /* mounted time */
+ /* allocation type of current segment */
+ unsigned char alloc_type[MAX_ACTIVE_LOGS];
+
+ /* SIT and NAT version bitmap */
+ unsigned char sit_nat_version_bitmap[1];
+} __packed;
+
+/*
+ * For orphan inode management
+ */
+#define F2FS_ORPHANS_PER_BLOCK 1020
+
+#define GET_ORPHAN_BLOCKS(n) ((n + F2FS_ORPHANS_PER_BLOCK - 1) / \
+ F2FS_ORPHANS_PER_BLOCK)
+
+struct f2fs_orphan_block {
+ __le32 ino[F2FS_ORPHANS_PER_BLOCK]; /* inode numbers */
+ __le32 reserved; /* reserved */
+ __le16 blk_addr; /* block index in current CP */
+ __le16 blk_count; /* Number of orphan inode blocks in CP */
+ __le32 entry_count; /* Total number of orphan nodes in current CP */
+ __le32 check_sum; /* CRC32 for orphan inode block */
+} __packed;
+
+/*
+ * For NODE structure
+ */
+struct f2fs_extent {
+ __le32 fofs; /* start file offset of the extent */
+ __le32 blk; /* start block address of the extent */
+ __le32 len; /* lengh of the extent */
+} __packed;
+
+#define F2FS_NAME_LEN 255
+#define F2FS_INLINE_XATTR_ADDRS 50 /* 200 bytes for inline xattrs */
+#define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */
+#define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */
+#define ADDRS_PER_INODE(fi) addrs_per_inode(fi)
+#define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */
+#define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */
+
+#define ADDRS_PER_PAGE(page, fi) \
+ (IS_INODE(page) ? ADDRS_PER_INODE(fi) : ADDRS_PER_BLOCK)
+
+#define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1)
+#define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2)
+#define NODE_IND1_BLOCK (DEF_ADDRS_PER_INODE + 3)
+#define NODE_IND2_BLOCK (DEF_ADDRS_PER_INODE + 4)
+#define NODE_DIND_BLOCK (DEF_ADDRS_PER_INODE + 5)
+
+#define F2FS_INLINE_XATTR 0x01 /* file inline xattr flag */
+#define F2FS_INLINE_DATA 0x02 /* file inline data flag */
+#define F2FS_INLINE_DENTRY 0x04 /* file inline dentry flag */
+#define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */
+#define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */
+
+#define MAX_INLINE_DATA (sizeof(__le32) * (DEF_ADDRS_PER_INODE - \
+ F2FS_INLINE_XATTR_ADDRS - 1))
+
+struct f2fs_inode {
+ __le16 i_mode; /* file mode */
+ __u8 i_advise; /* file hints */
+ __u8 i_inline; /* file inline flags */
+ __le32 i_uid; /* user ID */
+ __le32 i_gid; /* group ID */
+ __le32 i_links; /* links count */
+ __le64 i_size; /* file size in bytes */
+ __le64 i_blocks; /* file size in blocks */
+ __le64 i_atime; /* access time */
+ __le64 i_ctime; /* change time */
+ __le64 i_mtime; /* modification time */
+ __le32 i_atime_nsec; /* access time in nano scale */
+ __le32 i_ctime_nsec; /* change time in nano scale */
+ __le32 i_mtime_nsec; /* modification time in nano scale */
+ __le32 i_generation; /* file version (for NFS) */
+ __le32 i_current_depth; /* only for directory depth */
+ __le32 i_xattr_nid; /* nid to save xattr */
+ __le32 i_flags; /* file attributes */
+ __le32 i_pino; /* parent inode number */
+ __le32 i_namelen; /* file name length */
+ __u8 i_name[F2FS_NAME_LEN]; /* file name for SPOR */
+ __u8 i_dir_level; /* dentry_level for large dir */
+
+ struct f2fs_extent i_ext; /* caching a largest extent */
+
+ __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */
+
+ __le32 i_nid[DEF_NIDS_PER_INODE]; /* direct(2), indirect(2),
+ double_indirect(1) node id */
+} __packed;
+
+struct direct_node {
+ __le32 addr[ADDRS_PER_BLOCK]; /* array of data block address */
+} __packed;
+
+struct indirect_node {
+ __le32 nid[NIDS_PER_BLOCK]; /* array of data block address */
+} __packed;
+
+enum {
+ COLD_BIT_SHIFT = 0,
+ FSYNC_BIT_SHIFT,
+ DENT_BIT_SHIFT,
+ OFFSET_BIT_SHIFT
+};
+
+#define OFFSET_BIT_MASK (0x07) /* (0x01 << OFFSET_BIT_SHIFT) - 1 */
+
+struct node_footer {
+ __le32 nid; /* node id */
+ __le32 ino; /* inode nunmber */
+ __le32 flag; /* include cold/fsync/dentry marks and offset */
+ __le64 cp_ver; /* checkpoint version */
+ __le32 next_blkaddr; /* next node page block address */
+} __packed;
+
+struct f2fs_node {
+ /* can be one of three types: inode, direct, and indirect types */
+ union {
+ struct f2fs_inode i;
+ struct direct_node dn;
+ struct indirect_node in;
+ };
+ struct node_footer footer;
+} __packed;
+
+/*
+ * For NAT entries
+ */
+#define NAT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_nat_entry))
+
+struct f2fs_nat_entry {
+ __u8 version; /* latest version of cached nat entry */
+ __le32 ino; /* inode number */
+ __le32 block_addr; /* block address */
+} __packed;
+
+struct f2fs_nat_block {
+ struct f2fs_nat_entry entries[NAT_ENTRY_PER_BLOCK];
+} __packed;
+
+/*
+ * For SIT entries
+ *
+ * Each segment is 2MB in size by default so that a bitmap for validity of
+ * there-in blocks should occupy 64 bytes, 512 bits.
+ * Not allow to change this.
+ */
+#define SIT_VBLOCK_MAP_SIZE 64
+#define SIT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_sit_entry))
+
+/*
+ * Note that f2fs_sit_entry->vblocks has the following bit-field information.
+ * [15:10] : allocation type such as CURSEG_XXXX_TYPE
+ * [9:0] : valid block count
+ */
+#define SIT_VBLOCKS_SHIFT 10
+#define SIT_VBLOCKS_MASK ((1 << SIT_VBLOCKS_SHIFT) - 1)
+#define GET_SIT_VBLOCKS(raw_sit) \
+ (le16_to_cpu((raw_sit)->vblocks) & SIT_VBLOCKS_MASK)
+#define GET_SIT_TYPE(raw_sit) \
+ ((le16_to_cpu((raw_sit)->vblocks) & ~SIT_VBLOCKS_MASK) \
+ >> SIT_VBLOCKS_SHIFT)
+
+struct f2fs_sit_entry {
+ __le16 vblocks; /* reference above */
+ __u8 valid_map[SIT_VBLOCK_MAP_SIZE]; /* bitmap for valid blocks */
+ __le64 mtime; /* segment age for cleaning */
+} __packed;
+
+struct f2fs_sit_block {
+ struct f2fs_sit_entry entries[SIT_ENTRY_PER_BLOCK];
+} __packed;
+
+/*
+ * For segment summary
+ *
+ * One summary block contains exactly 512 summary entries, which represents
+ * exactly 2MB segment by default. Not allow to change the basic units.
+ *
+ * NOTE: For initializing fields, you must use set_summary
+ *
+ * - If data page, nid represents dnode's nid
+ * - If node page, nid represents the node page's nid.
+ *
+ * The ofs_in_node is used by only data page. It represents offset
+ * from node's page's beginning to get a data block address.
+ * ex) data_blkaddr = (block_t)(nodepage_start_address + ofs_in_node)
+ */
+#define ENTRIES_IN_SUM 512
+#define SUMMARY_SIZE (7) /* sizeof(struct summary) */
+#define SUM_FOOTER_SIZE (5) /* sizeof(struct summary_footer) */
+#define SUM_ENTRY_SIZE (SUMMARY_SIZE * ENTRIES_IN_SUM)
+
+/* a summary entry for a 4KB-sized block in a segment */
+struct f2fs_summary {
+ __le32 nid; /* parent node id */
+ union {
+ __u8 reserved[3];
+ struct {
+ __u8 version; /* node version number */
+ __le16 ofs_in_node; /* block index in parent node */
+ } __packed;
+ };
+} __packed;
+
+/* summary block type, node or data, is stored to the summary_footer */
+#define SUM_TYPE_NODE (1)
+#define SUM_TYPE_DATA (0)
+
+struct summary_footer {
+ unsigned char entry_type; /* SUM_TYPE_XXX */
+ __u32 check_sum; /* summary checksum */
+} __packed;
+
+#define SUM_JOURNAL_SIZE (F2FS_BLKSIZE - SUM_FOOTER_SIZE -\
+ SUM_ENTRY_SIZE)
+#define NAT_JOURNAL_ENTRIES ((SUM_JOURNAL_SIZE - 2) /\
+ sizeof(struct nat_journal_entry))
+#define NAT_JOURNAL_RESERVED ((SUM_JOURNAL_SIZE - 2) %\
+ sizeof(struct nat_journal_entry))
+#define SIT_JOURNAL_ENTRIES ((SUM_JOURNAL_SIZE - 2) /\
+ sizeof(struct sit_journal_entry))
+#define SIT_JOURNAL_RESERVED ((SUM_JOURNAL_SIZE - 2) %\
+ sizeof(struct sit_journal_entry))
+/*
+ * frequently updated NAT/SIT entries can be stored in the spare area in
+ * summary blocks
+ */
+enum {
+ NAT_JOURNAL = 0,
+ SIT_JOURNAL
+};
+
+struct nat_journal_entry {
+ __le32 nid;
+ struct f2fs_nat_entry ne;
+} __packed;
+
+struct nat_journal {
+ struct nat_journal_entry entries[NAT_JOURNAL_ENTRIES];
+ __u8 reserved[NAT_JOURNAL_RESERVED];
+} __packed;
+
+struct sit_journal_entry {
+ __le32 segno;
+ struct f2fs_sit_entry se;
+} __packed;
+
+struct sit_journal {
+ struct sit_journal_entry entries[SIT_JOURNAL_ENTRIES];
+ __u8 reserved[SIT_JOURNAL_RESERVED];
+} __packed;
+
+/* 4KB-sized summary block structure */
+struct f2fs_summary_block {
+ struct f2fs_summary entries[ENTRIES_IN_SUM];
+ union {
+ __le16 n_nats;
+ __le16 n_sits;
+ };
+ /* spare area is used by NAT or SIT journals */
+ union {
+ struct nat_journal nat_j;
+ struct sit_journal sit_j;
+ };
+ struct summary_footer footer;
+} __packed;
+
+/*
+ * For directory operations
+ */
+#define F2FS_DOT_HASH 0
+#define F2FS_DDOT_HASH F2FS_DOT_HASH
+#define F2FS_MAX_HASH (~((0x3ULL) << 62))
+#define F2FS_HASH_COL_BIT ((0x1ULL) << 63)
+
+typedef __le32 f2fs_hash_t;
+
+/* One directory entry slot covers 8bytes-long file name */
+#define F2FS_SLOT_LEN 8
+#define F2FS_SLOT_LEN_BITS 3
+
+#define GET_DENTRY_SLOTS(x) ((x + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS)
+
+/* MAX level for dir lookup */
+#define MAX_DIR_HASH_DEPTH 63
+
+/* MAX buckets in one level of dir */
+#define MAX_DIR_BUCKETS (1 << ((MAX_DIR_HASH_DEPTH / 2) - 1))
+
+/*
+ * space utilization of regular dentry and inline dentry
+ * regular dentry inline dentry
+ * bitmap 1 * 27 = 27 1 * 23 = 23
+ * reserved 1 * 3 = 3 1 * 7 = 7
+ * dentry 11 * 214 = 2354 11 * 182 = 2002
+ * filename 8 * 214 = 1712 8 * 182 = 1456
+ * total 4096 3488
+ *
+ * Note: there are more reserved space in inline dentry than in regular
+ * dentry, when converting inline dentry we should handle this carefully.
+ */
+#define NR_DENTRY_IN_BLOCK 214 /* the number of dentry in a block */
+#define SIZE_OF_DIR_ENTRY 11 /* by byte */
+#define SIZE_OF_DENTRY_BITMAP ((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \
+ BITS_PER_BYTE)
+#define SIZE_OF_RESERVED (PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \
+ F2FS_SLOT_LEN) * \
+ NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP))
+
+/* One directory entry slot representing F2FS_SLOT_LEN-sized file name */
+struct f2fs_dir_entry {
+ __le32 hash_code; /* hash code of file name */
+ __le32 ino; /* inode number */
+ __le16 name_len; /* lengh of file name */
+ __u8 file_type; /* file type */
+} __packed;
+
+/* 4KB-sized directory entry block */
+struct f2fs_dentry_block {
+ /* validity bitmap for directory entries in each block */
+ __u8 dentry_bitmap[SIZE_OF_DENTRY_BITMAP];
+ __u8 reserved[SIZE_OF_RESERVED];
+ struct f2fs_dir_entry dentry[NR_DENTRY_IN_BLOCK];
+ __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN];
+} __packed;
+
+/* for inline dir */
+#define NR_INLINE_DENTRY (MAX_INLINE_DATA * BITS_PER_BYTE / \
+ ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
+ BITS_PER_BYTE + 1))
+#define INLINE_DENTRY_BITMAP_SIZE ((NR_INLINE_DENTRY + \
+ BITS_PER_BYTE - 1) / BITS_PER_BYTE)
+#define INLINE_RESERVED_SIZE (MAX_INLINE_DATA - \
+ ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
+ NR_INLINE_DENTRY + INLINE_DENTRY_BITMAP_SIZE))
+
+/* inline directory entry structure */
+struct f2fs_inline_dentry {
+ __u8 dentry_bitmap[INLINE_DENTRY_BITMAP_SIZE];
+ __u8 reserved[INLINE_RESERVED_SIZE];
+ struct f2fs_dir_entry dentry[NR_INLINE_DENTRY];
+ __u8 filename[NR_INLINE_DENTRY][F2FS_SLOT_LEN];
+} __packed;
+
+/* file types used in inode_info->flags */
+enum {
+ F2FS_FT_UNKNOWN,
+ F2FS_FT_REG_FILE,
+ F2FS_FT_DIR,
+ F2FS_FT_CHRDEV,
+ F2FS_FT_BLKDEV,
+ F2FS_FT_FIFO,
+ F2FS_FT_SOCK,
+ F2FS_FT_SYMLINK,
+ F2FS_FT_MAX
+};
+
+#endif /* _LINUX_F2FS_FS_H */
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
new file mode 100644
index 0000000..1855020
--- /dev/null
+++ b/include/trace/events/f2fs.h
@@ -0,0 +1,1233 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM f2fs
+
+#if !defined(_TRACE_F2FS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_F2FS_H
+
+#include <linux/tracepoint.h>
+
+#define show_dev(entry) MAJOR(entry->dev), MINOR(entry->dev)
+#define show_dev_ino(entry) show_dev(entry), (unsigned long)entry->ino
+
+#define show_block_type(type) \
+ __print_symbolic(type, \
+ { NODE, "NODE" }, \
+ { DATA, "DATA" }, \
+ { META, "META" }, \
+ { META_FLUSH, "META_FLUSH" }, \
+ { INMEM, "INMEM" }, \
+ { INMEM_DROP, "INMEM_DROP" }, \
+ { IPU, "IN-PLACE" }, \
+ { OPU, "OUT-OF-PLACE" })
+
+#define F2FS_BIO_MASK(t) (t & (READA | WRITE_FLUSH_FUA))
+#define F2FS_BIO_EXTRA_MASK(t) (t & (REQ_META | REQ_PRIO))
+
+#define show_bio_type(type) show_bio_base(type), show_bio_extra(type)
+
+#define show_bio_base(type) \
+ __print_symbolic(F2FS_BIO_MASK(type), \
+ { READ, "READ" }, \
+ { READA, "READAHEAD" }, \
+ { READ_SYNC, "READ_SYNC" }, \
+ { WRITE, "WRITE" }, \
+ { WRITE_SYNC, "WRITE_SYNC" }, \
+ { WRITE_FLUSH, "WRITE_FLUSH" }, \
+ { WRITE_FUA, "WRITE_FUA" }, \
+ { WRITE_FLUSH_FUA, "WRITE_FLUSH_FUA" })
+
+#define show_bio_extra(type) \
+ __print_symbolic(F2FS_BIO_EXTRA_MASK(type), \
+ { REQ_META, "(M)" }, \
+ { REQ_PRIO, "(P)" }, \
+ { REQ_META | REQ_PRIO, "(MP)" }, \
+ { 0, " \b" })
+
+#define show_data_type(type) \
+ __print_symbolic(type, \
+ { CURSEG_HOT_DATA, "Hot DATA" }, \
+ { CURSEG_WARM_DATA, "Warm DATA" }, \
+ { CURSEG_COLD_DATA, "Cold DATA" }, \
+ { CURSEG_HOT_NODE, "Hot NODE" }, \
+ { CURSEG_WARM_NODE, "Warm NODE" }, \
+ { CURSEG_COLD_NODE, "Cold NODE" }, \
+ { NO_CHECK_TYPE, "No TYPE" })
+
+#define show_file_type(type) \
+ __print_symbolic(type, \
+ { 0, "FILE" }, \
+ { 1, "DIR" })
+
+#define show_gc_type(type) \
+ __print_symbolic(type, \
+ { FG_GC, "Foreground GC" }, \
+ { BG_GC, "Background GC" })
+
+#define show_alloc_mode(type) \
+ __print_symbolic(type, \
+ { LFS, "LFS-mode" }, \
+ { SSR, "SSR-mode" })
+
+#define show_victim_policy(type) \
+ __print_symbolic(type, \
+ { GC_GREEDY, "Greedy" }, \
+ { GC_CB, "Cost-Benefit" })
+
+#define show_cpreason(type) \
+ __print_symbolic(type, \
+ { CP_UMOUNT, "Umount" }, \
+ { CP_FASTBOOT, "Fastboot" }, \
+ { CP_SYNC, "Sync" }, \
+ { CP_RECOVERY, "Recovery" }, \
+ { CP_DISCARD, "Discard" })
+
+struct victim_sel_policy;
+struct f2fs_map_blocks;
+
+DECLARE_EVENT_CLASS(f2fs__inode,
+
+ TP_PROTO(struct inode *inode),
+
+ TP_ARGS(inode),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(ino_t, pino)
+ __field(umode_t, mode)
+ __field(loff_t, size)
+ __field(unsigned int, nlink)
+ __field(blkcnt_t, blocks)
+ __field(__u8, advise)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->pino = F2FS_I(inode)->i_pino;
+ __entry->mode = inode->i_mode;
+ __entry->nlink = inode->i_nlink;
+ __entry->size = inode->i_size;
+ __entry->blocks = inode->i_blocks;
+ __entry->advise = F2FS_I(inode)->i_advise;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, pino = %lu, i_mode = 0x%hx, "
+ "i_size = %lld, i_nlink = %u, i_blocks = %llu, i_advise = 0x%x",
+ show_dev_ino(__entry),
+ (unsigned long)__entry->pino,
+ __entry->mode,
+ __entry->size,
+ (unsigned int)__entry->nlink,
+ (unsigned long long)__entry->blocks,
+ (unsigned char)__entry->advise)
+);
+
+DECLARE_EVENT_CLASS(f2fs__inode_exit,
+
+ TP_PROTO(struct inode *inode, int ret),
+
+ TP_ARGS(inode, ret),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(int, ret)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, ret = %d",
+ show_dev_ino(__entry),
+ __entry->ret)
+);
+
+DEFINE_EVENT(f2fs__inode, f2fs_sync_file_enter,
+
+ TP_PROTO(struct inode *inode),
+
+ TP_ARGS(inode)
+);
+
+TRACE_EVENT(f2fs_sync_file_exit,
+
+ TP_PROTO(struct inode *inode, int need_cp, int datasync, int ret),
+
+ TP_ARGS(inode, need_cp, datasync, ret),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(int, need_cp)
+ __field(int, datasync)
+ __field(int, ret)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->need_cp = need_cp;
+ __entry->datasync = datasync;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, checkpoint is %s, "
+ "datasync = %d, ret = %d",
+ show_dev_ino(__entry),
+ __entry->need_cp ? "needed" : "not needed",
+ __entry->datasync,
+ __entry->ret)
+);
+
+TRACE_EVENT(f2fs_sync_fs,
+
+ TP_PROTO(struct super_block *sb, int wait),
+
+ TP_ARGS(sb, wait),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(int, dirty)
+ __field(int, wait)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->dirty = is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY);
+ __entry->wait = wait;
+ ),
+
+ TP_printk("dev = (%d,%d), superblock is %s, wait = %d",
+ show_dev(__entry),
+ __entry->dirty ? "dirty" : "not dirty",
+ __entry->wait)
+);
+
+DEFINE_EVENT(f2fs__inode, f2fs_iget,
+
+ TP_PROTO(struct inode *inode),
+
+ TP_ARGS(inode)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_iget_exit,
+
+ TP_PROTO(struct inode *inode, int ret),
+
+ TP_ARGS(inode, ret)
+);
+
+DEFINE_EVENT(f2fs__inode, f2fs_evict_inode,
+
+ TP_PROTO(struct inode *inode),
+
+ TP_ARGS(inode)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_new_inode,
+
+ TP_PROTO(struct inode *inode, int ret),
+
+ TP_ARGS(inode, ret)
+);
+
+TRACE_EVENT(f2fs_unlink_enter,
+
+ TP_PROTO(struct inode *dir, struct dentry *dentry),
+
+ TP_ARGS(dir, dentry),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(loff_t, size)
+ __field(blkcnt_t, blocks)
+ __field(const char *, name)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = dir->i_sb->s_dev;
+ __entry->ino = dir->i_ino;
+ __entry->size = dir->i_size;
+ __entry->blocks = dir->i_blocks;
+ __entry->name = dentry->d_name.name;
+ ),
+
+ TP_printk("dev = (%d,%d), dir ino = %lu, i_size = %lld, "
+ "i_blocks = %llu, name = %s",
+ show_dev_ino(__entry),
+ __entry->size,
+ (unsigned long long)__entry->blocks,
+ __entry->name)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_unlink_exit,
+
+ TP_PROTO(struct inode *inode, int ret),
+
+ TP_ARGS(inode, ret)
+);
+
+DEFINE_EVENT(f2fs__inode, f2fs_truncate,
+
+ TP_PROTO(struct inode *inode),
+
+ TP_ARGS(inode)
+);
+
+TRACE_EVENT(f2fs_truncate_data_blocks_range,
+
+ TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs, int free),
+
+ TP_ARGS(inode, nid, ofs, free),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(nid_t, nid)
+ __field(unsigned int, ofs)
+ __field(int, free)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->nid = nid;
+ __entry->ofs = ofs;
+ __entry->free = free;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, nid = %u, offset = %u, freed = %d",
+ show_dev_ino(__entry),
+ (unsigned int)__entry->nid,
+ __entry->ofs,
+ __entry->free)
+);
+
+DECLARE_EVENT_CLASS(f2fs__truncate_op,
+
+ TP_PROTO(struct inode *inode, u64 from),
+
+ TP_ARGS(inode, from),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(loff_t, size)
+ __field(blkcnt_t, blocks)
+ __field(u64, from)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->size = inode->i_size;
+ __entry->blocks = inode->i_blocks;
+ __entry->from = from;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, i_size = %lld, i_blocks = %llu, "
+ "start file offset = %llu",
+ show_dev_ino(__entry),
+ __entry->size,
+ (unsigned long long)__entry->blocks,
+ (unsigned long long)__entry->from)
+);
+
+DEFINE_EVENT(f2fs__truncate_op, f2fs_truncate_blocks_enter,
+
+ TP_PROTO(struct inode *inode, u64 from),
+
+ TP_ARGS(inode, from)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_truncate_blocks_exit,
+
+ TP_PROTO(struct inode *inode, int ret),
+
+ TP_ARGS(inode, ret)
+);
+
+DEFINE_EVENT(f2fs__truncate_op, f2fs_truncate_inode_blocks_enter,
+
+ TP_PROTO(struct inode *inode, u64 from),
+
+ TP_ARGS(inode, from)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_truncate_inode_blocks_exit,
+
+ TP_PROTO(struct inode *inode, int ret),
+
+ TP_ARGS(inode, ret)
+);
+
+DECLARE_EVENT_CLASS(f2fs__truncate_node,
+
+ TP_PROTO(struct inode *inode, nid_t nid, block_t blk_addr),
+
+ TP_ARGS(inode, nid, blk_addr),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(nid_t, nid)
+ __field(block_t, blk_addr)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->nid = nid;
+ __entry->blk_addr = blk_addr;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, nid = %u, block_address = 0x%llx",
+ show_dev_ino(__entry),
+ (unsigned int)__entry->nid,
+ (unsigned long long)__entry->blk_addr)
+);
+
+DEFINE_EVENT(f2fs__truncate_node, f2fs_truncate_nodes_enter,
+
+ TP_PROTO(struct inode *inode, nid_t nid, block_t blk_addr),
+
+ TP_ARGS(inode, nid, blk_addr)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_truncate_nodes_exit,
+
+ TP_PROTO(struct inode *inode, int ret),
+
+ TP_ARGS(inode, ret)
+);
+
+DEFINE_EVENT(f2fs__truncate_node, f2fs_truncate_node,
+
+ TP_PROTO(struct inode *inode, nid_t nid, block_t blk_addr),
+
+ TP_ARGS(inode, nid, blk_addr)
+);
+
+TRACE_EVENT(f2fs_truncate_partial_nodes,
+
+ TP_PROTO(struct inode *inode, nid_t nid[], int depth, int err),
+
+ TP_ARGS(inode, nid, depth, err),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(nid_t, nid[3])
+ __field(int, depth)
+ __field(int, err)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->nid[0] = nid[0];
+ __entry->nid[1] = nid[1];
+ __entry->nid[2] = nid[2];
+ __entry->depth = depth;
+ __entry->err = err;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, "
+ "nid[0] = %u, nid[1] = %u, nid[2] = %u, depth = %d, err = %d",
+ show_dev_ino(__entry),
+ (unsigned int)__entry->nid[0],
+ (unsigned int)__entry->nid[1],
+ (unsigned int)__entry->nid[2],
+ __entry->depth,
+ __entry->err)
+);
+
+TRACE_EVENT(f2fs_map_blocks,
+ TP_PROTO(struct inode *inode, struct f2fs_map_blocks *map, int ret),
+
+ TP_ARGS(inode, map, ret),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(block_t, m_lblk)
+ __field(block_t, m_pblk)
+ __field(unsigned int, m_len)
+ __field(int, ret)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->m_lblk = map->m_lblk;
+ __entry->m_pblk = map->m_pblk;
+ __entry->m_len = map->m_len;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, "
+ "start blkaddr = 0x%llx, len = 0x%llx, err = %d",
+ show_dev_ino(__entry),
+ (unsigned long long)__entry->m_lblk,
+ (unsigned long long)__entry->m_pblk,
+ (unsigned long long)__entry->m_len,
+ __entry->ret)
+);
+
+TRACE_EVENT(f2fs_background_gc,
+
+ TP_PROTO(struct super_block *sb, long wait_ms,
+ unsigned int prefree, unsigned int free),
+
+ TP_ARGS(sb, wait_ms, prefree, free),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(long, wait_ms)
+ __field(unsigned int, prefree)
+ __field(unsigned int, free)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->wait_ms = wait_ms;
+ __entry->prefree = prefree;
+ __entry->free = free;
+ ),
+
+ TP_printk("dev = (%d,%d), wait_ms = %ld, prefree = %u, free = %u",
+ show_dev(__entry),
+ __entry->wait_ms,
+ __entry->prefree,
+ __entry->free)
+);
+
+TRACE_EVENT(f2fs_get_victim,
+
+ TP_PROTO(struct super_block *sb, int type, int gc_type,
+ struct victim_sel_policy *p, unsigned int pre_victim,
+ unsigned int prefree, unsigned int free),
+
+ TP_ARGS(sb, type, gc_type, p, pre_victim, prefree, free),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(int, type)
+ __field(int, gc_type)
+ __field(int, alloc_mode)
+ __field(int, gc_mode)
+ __field(unsigned int, victim)
+ __field(unsigned int, ofs_unit)
+ __field(unsigned int, pre_victim)
+ __field(unsigned int, prefree)
+ __field(unsigned int, free)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->type = type;
+ __entry->gc_type = gc_type;
+ __entry->alloc_mode = p->alloc_mode;
+ __entry->gc_mode = p->gc_mode;
+ __entry->victim = p->min_segno;
+ __entry->ofs_unit = p->ofs_unit;
+ __entry->pre_victim = pre_victim;
+ __entry->prefree = prefree;
+ __entry->free = free;
+ ),
+
+ TP_printk("dev = (%d,%d), type = %s, policy = (%s, %s, %s), victim = %u "
+ "ofs_unit = %u, pre_victim_secno = %d, prefree = %u, free = %u",
+ show_dev(__entry),
+ show_data_type(__entry->type),
+ show_gc_type(__entry->gc_type),
+ show_alloc_mode(__entry->alloc_mode),
+ show_victim_policy(__entry->gc_mode),
+ __entry->victim,
+ __entry->ofs_unit,
+ (int)__entry->pre_victim,
+ __entry->prefree,
+ __entry->free)
+);
+
+TRACE_EVENT(f2fs_fallocate,
+
+ TP_PROTO(struct inode *inode, int mode,
+ loff_t offset, loff_t len, int ret),
+
+ TP_ARGS(inode, mode, offset, len, ret),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(int, mode)
+ __field(loff_t, offset)
+ __field(loff_t, len)
+ __field(loff_t, size)
+ __field(blkcnt_t, blocks)
+ __field(int, ret)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->mode = mode;
+ __entry->offset = offset;
+ __entry->len = len;
+ __entry->size = inode->i_size;
+ __entry->blocks = inode->i_blocks;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, mode = %x, offset = %lld, "
+ "len = %lld, i_size = %lld, i_blocks = %llu, ret = %d",
+ show_dev_ino(__entry),
+ __entry->mode,
+ (unsigned long long)__entry->offset,
+ (unsigned long long)__entry->len,
+ (unsigned long long)__entry->size,
+ (unsigned long long)__entry->blocks,
+ __entry->ret)
+);
+
+TRACE_EVENT(f2fs_direct_IO_enter,
+
+ TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, int rw),
+
+ TP_ARGS(inode, offset, len, rw),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(loff_t, pos)
+ __field(unsigned long, len)
+ __field(int, rw)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->pos = offset;
+ __entry->len = len;
+ __entry->rw = rw;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu rw = %d",
+ show_dev_ino(__entry),
+ __entry->pos,
+ __entry->len,
+ __entry->rw)
+);
+
+TRACE_EVENT(f2fs_direct_IO_exit,
+
+ TP_PROTO(struct inode *inode, loff_t offset, unsigned long len,
+ int rw, int ret),
+
+ TP_ARGS(inode, offset, len, rw, ret),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(loff_t, pos)
+ __field(unsigned long, len)
+ __field(int, rw)
+ __field(int, ret)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->pos = offset;
+ __entry->len = len;
+ __entry->rw = rw;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu "
+ "rw = %d ret = %d",
+ show_dev_ino(__entry),
+ __entry->pos,
+ __entry->len,
+ __entry->rw,
+ __entry->ret)
+);
+
+TRACE_EVENT(f2fs_reserve_new_block,
+
+ TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs_in_node),
+
+ TP_ARGS(inode, nid, ofs_in_node),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(nid_t, nid)
+ __field(unsigned int, ofs_in_node)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->nid = nid;
+ __entry->ofs_in_node = ofs_in_node;
+ ),
+
+ TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u",
+ show_dev(__entry),
+ (unsigned int)__entry->nid,
+ __entry->ofs_in_node)
+);
+
+DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
+
+ TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+
+ TP_ARGS(page, fio),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(pgoff_t, index)
+ __field(block_t, blkaddr)
+ __field(int, rw)
+ __field(int, type)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = page->mapping->host->i_sb->s_dev;
+ __entry->ino = page->mapping->host->i_ino;
+ __entry->index = page->index;
+ __entry->blkaddr = fio->blk_addr;
+ __entry->rw = fio->rw;
+ __entry->type = fio->type;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
+ "blkaddr = 0x%llx, rw = %s%s, type = %s",
+ show_dev_ino(__entry),
+ (unsigned long)__entry->index,
+ (unsigned long long)__entry->blkaddr,
+ show_bio_type(__entry->rw),
+ show_block_type(__entry->type))
+);
+
+DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_bio,
+
+ TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+
+ TP_ARGS(page, fio),
+
+ TP_CONDITION(page->mapping)
+);
+
+DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_mbio,
+
+ TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+
+ TP_ARGS(page, fio),
+
+ TP_CONDITION(page->mapping)
+);
+
+DECLARE_EVENT_CLASS(f2fs__submit_bio,
+
+ TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
+ struct bio *bio),
+
+ TP_ARGS(sb, fio, bio),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(int, rw)
+ __field(int, type)
+ __field(sector_t, sector)
+ __field(unsigned int, size)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->rw = fio->rw;
+ __entry->type = fio->type;
+ __entry->sector = bio->bi_sector;
+ __entry->size = bio->bi_size;
+ ),
+
+ TP_printk("dev = (%d,%d), %s%s, %s, sector = %lld, size = %u",
+ show_dev(__entry),
+ show_bio_type(__entry->rw),
+ show_block_type(__entry->type),
+ (unsigned long long)__entry->sector,
+ __entry->size)
+);
+
+DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_write_bio,
+
+ TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
+ struct bio *bio),
+
+ TP_ARGS(sb, fio, bio),
+
+ TP_CONDITION(bio)
+);
+
+DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_read_bio,
+
+ TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
+ struct bio *bio),
+
+ TP_ARGS(sb, fio, bio),
+
+ TP_CONDITION(bio)
+);
+
+TRACE_EVENT(f2fs_write_begin,
+
+ TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+ unsigned int flags),
+
+ TP_ARGS(inode, pos, len, flags),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(loff_t, pos)
+ __field(unsigned int, len)
+ __field(unsigned int, flags)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->pos = pos;
+ __entry->len = len;
+ __entry->flags = flags;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u, flags = %u",
+ show_dev_ino(__entry),
+ (unsigned long long)__entry->pos,
+ __entry->len,
+ __entry->flags)
+);
+
+TRACE_EVENT(f2fs_write_end,
+
+ TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+ unsigned int copied),
+
+ TP_ARGS(inode, pos, len, copied),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(loff_t, pos)
+ __field(unsigned int, len)
+ __field(unsigned int, copied)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->pos = pos;
+ __entry->len = len;
+ __entry->copied = copied;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u, copied = %u",
+ show_dev_ino(__entry),
+ (unsigned long long)__entry->pos,
+ __entry->len,
+ __entry->copied)
+);
+
+DECLARE_EVENT_CLASS(f2fs__page,
+
+ TP_PROTO(struct page *page, int type),
+
+ TP_ARGS(page, type),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(int, type)
+ __field(int, dir)
+ __field(pgoff_t, index)
+ __field(int, dirty)
+ __field(int, uptodate)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = page->mapping->host->i_sb->s_dev;
+ __entry->ino = page->mapping->host->i_ino;
+ __entry->type = type;
+ __entry->dir = S_ISDIR(page->mapping->host->i_mode);
+ __entry->index = page->index;
+ __entry->dirty = PageDirty(page);
+ __entry->uptodate = PageUptodate(page);
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, %s, %s, index = %lu, "
+ "dirty = %d, uptodate = %d",
+ show_dev_ino(__entry),
+ show_block_type(__entry->type),
+ show_file_type(__entry->dir),
+ (unsigned long)__entry->index,
+ __entry->dirty,
+ __entry->uptodate)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_writepage,
+
+ TP_PROTO(struct page *page, int type),
+
+ TP_ARGS(page, type)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_do_write_data_page,
+
+ TP_PROTO(struct page *page, int type),
+
+ TP_ARGS(page, type)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_readpage,
+
+ TP_PROTO(struct page *page, int type),
+
+ TP_ARGS(page, type)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_set_page_dirty,
+
+ TP_PROTO(struct page *page, int type),
+
+ TP_ARGS(page, type)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_vm_page_mkwrite,
+
+ TP_PROTO(struct page *page, int type),
+
+ TP_ARGS(page, type)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_register_inmem_page,
+
+ TP_PROTO(struct page *page, int type),
+
+ TP_ARGS(page, type)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_commit_inmem_page,
+
+ TP_PROTO(struct page *page, int type),
+
+ TP_ARGS(page, type)
+);
+
+TRACE_EVENT(f2fs_writepages,
+
+ TP_PROTO(struct inode *inode, struct writeback_control *wbc, int type),
+
+ TP_ARGS(inode, wbc, type),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(int, type)
+ __field(int, dir)
+ __field(long, nr_to_write)
+ __field(long, pages_skipped)
+ __field(loff_t, range_start)
+ __field(loff_t, range_end)
+ __field(pgoff_t, writeback_index)
+ __field(int, sync_mode)
+ __field(char, for_kupdate)
+ __field(char, for_background)
+ __field(char, tagged_writepages)
+ __field(char, for_reclaim)
+ __field(char, range_cyclic)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->type = type;
+ __entry->dir = S_ISDIR(inode->i_mode);
+ __entry->nr_to_write = wbc->nr_to_write;
+ __entry->pages_skipped = wbc->pages_skipped;
+ __entry->range_start = wbc->range_start;
+ __entry->range_end = wbc->range_end;
+ __entry->writeback_index = inode->i_mapping->writeback_index;
+ __entry->sync_mode = wbc->sync_mode;
+ __entry->for_kupdate = wbc->for_kupdate;
+ __entry->for_background = wbc->for_background;
+ __entry->tagged_writepages = wbc->tagged_writepages;
+ __entry->for_reclaim = wbc->for_reclaim;
+ __entry->range_cyclic = wbc->range_cyclic;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, %s, %s, nr_to_write %ld, "
+ "skipped %ld, start %lld, end %lld, wb_idx %lu, sync_mode %d, "
+ "kupdate %u background %u tagged %u reclaim %u cyclic %u",
+ show_dev_ino(__entry),
+ show_block_type(__entry->type),
+ show_file_type(__entry->dir),
+ __entry->nr_to_write,
+ __entry->pages_skipped,
+ __entry->range_start,
+ __entry->range_end,
+ (unsigned long)__entry->writeback_index,
+ __entry->sync_mode,
+ __entry->for_kupdate,
+ __entry->for_background,
+ __entry->tagged_writepages,
+ __entry->for_reclaim,
+ __entry->range_cyclic)
+);
+
+TRACE_EVENT(f2fs_readpages,
+
+ TP_PROTO(struct inode *inode, struct page *page, unsigned int nrpage),
+
+ TP_ARGS(inode, page, nrpage),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(pgoff_t, start)
+ __field(unsigned int, nrpage)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->start = page->index;
+ __entry->nrpage = nrpage;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, start = %lu nrpage = %u",
+ show_dev_ino(__entry),
+ (unsigned long)__entry->start,
+ __entry->nrpage)
+);
+
+TRACE_EVENT(f2fs_write_checkpoint,
+
+ TP_PROTO(struct super_block *sb, int reason, char *msg),
+
+ TP_ARGS(sb, reason, msg),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(int, reason)
+ __field(char *, msg)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->reason = reason;
+ __entry->msg = msg;
+ ),
+
+ TP_printk("dev = (%d,%d), checkpoint for %s, state = %s",
+ show_dev(__entry),
+ show_cpreason(__entry->reason),
+ __entry->msg)
+);
+
+TRACE_EVENT(f2fs_issue_discard,
+
+ TP_PROTO(struct super_block *sb, block_t blkstart, block_t blklen),
+
+ TP_ARGS(sb, blkstart, blklen),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(block_t, blkstart)
+ __field(block_t, blklen)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->blkstart = blkstart;
+ __entry->blklen = blklen;
+ ),
+
+ TP_printk("dev = (%d,%d), blkstart = 0x%llx, blklen = 0x%llx",
+ show_dev(__entry),
+ (unsigned long long)__entry->blkstart,
+ (unsigned long long)__entry->blklen)
+);
+
+TRACE_EVENT(f2fs_issue_flush,
+
+ TP_PROTO(struct super_block *sb, unsigned int nobarrier,
+ unsigned int flush_merge),
+
+ TP_ARGS(sb, nobarrier, flush_merge),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(unsigned int, nobarrier)
+ __field(unsigned int, flush_merge)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sb->s_dev;
+ __entry->nobarrier = nobarrier;
+ __entry->flush_merge = flush_merge;
+ ),
+
+ TP_printk("dev = (%d,%d), %s %s",
+ show_dev(__entry),
+ __entry->nobarrier ? "skip (nobarrier)" : "issue",
+ __entry->flush_merge ? " with flush_merge" : "")
+);
+
+TRACE_EVENT(f2fs_lookup_extent_tree_start,
+
+ TP_PROTO(struct inode *inode, unsigned int pgofs),
+
+ TP_ARGS(inode, pgofs),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(unsigned int, pgofs)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->pgofs = pgofs;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u",
+ show_dev_ino(__entry),
+ __entry->pgofs)
+);
+
+TRACE_EVENT_CONDITION(f2fs_lookup_extent_tree_end,
+
+ TP_PROTO(struct inode *inode, unsigned int pgofs,
+ struct extent_info *ei),
+
+ TP_ARGS(inode, pgofs, ei),
+
+ TP_CONDITION(ei),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(unsigned int, pgofs)
+ __field(unsigned int, fofs)
+ __field(u32, blk)
+ __field(unsigned int, len)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->pgofs = pgofs;
+ __entry->fofs = ei->fofs;
+ __entry->blk = ei->blk;
+ __entry->len = ei->len;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
+ "ext_info(fofs: %u, blk: %u, len: %u)",
+ show_dev_ino(__entry),
+ __entry->pgofs,
+ __entry->fofs,
+ __entry->blk,
+ __entry->len)
+);
+
+TRACE_EVENT(f2fs_update_extent_tree_range,
+
+ TP_PROTO(struct inode *inode, unsigned int pgofs, block_t blkaddr,
+ unsigned int len),
+
+ TP_ARGS(inode, pgofs, blkaddr, len),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(unsigned int, pgofs)
+ __field(u32, blk)
+ __field(unsigned int, len)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->pgofs = pgofs;
+ __entry->blk = blkaddr;
+ __entry->len = len;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
+ "blkaddr = %u, len = %u",
+ show_dev_ino(__entry),
+ __entry->pgofs,
+ __entry->blk,
+ __entry->len)
+);
+
+TRACE_EVENT(f2fs_shrink_extent_tree,
+
+ TP_PROTO(struct f2fs_sb_info *sbi, unsigned int node_cnt,
+ unsigned int tree_cnt),
+
+ TP_ARGS(sbi, node_cnt, tree_cnt),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(unsigned int, node_cnt)
+ __field(unsigned int, tree_cnt)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sbi->sb->s_dev;
+ __entry->node_cnt = node_cnt;
+ __entry->tree_cnt = tree_cnt;
+ ),
+
+ TP_printk("dev = (%d,%d), shrunk: node_cnt = %u, tree_cnt = %u",
+ show_dev(__entry),
+ __entry->node_cnt,
+ __entry->tree_cnt)
+);
+
+TRACE_EVENT(f2fs_destroy_extent_tree,
+
+ TP_PROTO(struct inode *inode, unsigned int node_cnt),
+
+ TP_ARGS(inode, node_cnt),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(ino_t, ino)
+ __field(unsigned int, node_cnt)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = inode->i_sb->s_dev;
+ __entry->ino = inode->i_ino;
+ __entry->node_cnt = node_cnt;
+ ),
+
+ TP_printk("dev = (%d,%d), ino = %lu, destroyed: node_cnt = %u",
+ show_dev_ino(__entry),
+ __entry->node_cnt)
+);
+
+#endif /* _TRACE_F2FS_H */
+
+ /* This part must be outside protection */
+#include <trace/define_trace.h>