From f389bc031ba96adf1b924bfb7e06e08b257cf3b3 Mon Sep 17 00:00:00 2001 From: arter97 Date: Tue, 7 Jan 2014 14:26:23 +0900 Subject: fs: import f2fs from git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git (branch dev) Up-to-date with git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git @04a17fb17fafada39f96bfb41ceb2dc1c11b2af6 (f2fs: avoid to read inline data except first page) Change-Id: I1fc76a61defd530c4e97587980ba43e98db6119e Signed-off-by: Park Ju Hyung --- Documentation/ABI/testing/sysfs-fs-f2fs | 26 + Documentation/filesystems/00-INDEX | 2 + Documentation/filesystems/f2fs.txt | 521 +++++++++ MAINTAINERS | 10 + fs/Kconfig | 1 + fs/Makefile | 1 + fs/f2fs/Kconfig | 73 ++ fs/f2fs/Makefile | 7 + fs/f2fs/acl.c | 414 +++++++ fs/f2fs/acl.h | 58 + fs/f2fs/checkpoint.c | 858 ++++++++++++++ fs/f2fs/data.c | 1086 +++++++++++++++++ fs/f2fs/debug.c | 374 ++++++ fs/f2fs/dir.c | 682 +++++++++++ fs/f2fs/f2fs.h | 1327 +++++++++++++++++++++ fs/f2fs/file.c | 681 +++++++++++ fs/f2fs/gc.c | 752 ++++++++++++ fs/f2fs/gc.h | 110 ++ fs/f2fs/hash.c | 101 ++ fs/f2fs/inline.c | 222 ++++ fs/f2fs/inode.c | 286 +++++ fs/f2fs/namei.c | 533 +++++++++ fs/f2fs/node.c | 1909 ++++++++++++++++++++++++++++++ fs/f2fs/node.h | 351 ++++++ fs/f2fs/recovery.c | 467 ++++++++ fs/f2fs/segment.c | 1940 +++++++++++++++++++++++++++++++ fs/f2fs/segment.h | 683 +++++++++++ fs/f2fs/super.c | 1158 ++++++++++++++++++ fs/f2fs/xattr.c | 596 ++++++++++ fs/f2fs/xattr.h | 152 +++ include/linux/f2fs_fs.h | 431 +++++++ include/linux/magic.h | 1 + include/trace/events/f2fs.h | 790 +++++++++++++ 33 files changed, 16603 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-fs-f2fs create mode 100644 Documentation/filesystems/f2fs.txt create mode 100644 fs/f2fs/Kconfig create mode 100644 fs/f2fs/Makefile create mode 100644 fs/f2fs/acl.c create mode 100644 fs/f2fs/acl.h create mode 100644 fs/f2fs/checkpoint.c create mode 100644 fs/f2fs/data.c create mode 100644 fs/f2fs/debug.c create mode 100644 fs/f2fs/dir.c create mode 100644 fs/f2fs/f2fs.h create mode 100644 fs/f2fs/file.c create mode 100644 fs/f2fs/gc.c create mode 100644 fs/f2fs/gc.h create mode 100644 fs/f2fs/hash.c create mode 100644 fs/f2fs/inline.c create mode 100644 fs/f2fs/inode.c create mode 100644 fs/f2fs/namei.c create mode 100644 fs/f2fs/node.c create mode 100644 fs/f2fs/node.h create mode 100644 fs/f2fs/recovery.c create mode 100644 fs/f2fs/segment.c create mode 100644 fs/f2fs/segment.h create mode 100644 fs/f2fs/super.c create mode 100644 fs/f2fs/xattr.c create mode 100644 fs/f2fs/xattr.h create mode 100644 include/linux/f2fs_fs.h create mode 100644 include/trace/events/f2fs.h diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs new file mode 100644 index 0000000..31942ef --- /dev/null +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -0,0 +1,26 @@ +What: /sys/fs/f2fs//gc_max_sleep_time +Date: July 2013 +Contact: "Namjae Jeon" +Description: + Controls the maximun sleep time for gc_thread. Time + is in milliseconds. + +What: /sys/fs/f2fs//gc_min_sleep_time +Date: July 2013 +Contact: "Namjae Jeon" +Description: + Controls the minimum sleep time for gc_thread. Time + is in milliseconds. + +What: /sys/fs/f2fs//gc_no_gc_sleep_time +Date: July 2013 +Contact: "Namjae Jeon" +Description: + Controls the default sleep time for gc_thread. Time + is in milliseconds. + +What: /sys/fs/f2fs//gc_idle +Date: July 2013 +Contact: "Namjae Jeon" +Description: + Controls the victim selection policy for garbage collection. diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX index 8c624a1..ce5fd46 100644 --- a/Documentation/filesystems/00-INDEX +++ b/Documentation/filesystems/00-INDEX @@ -48,6 +48,8 @@ ext4.txt - info, mount options and specifications for the Ext4 filesystem. files.txt - info on file management in the Linux kernel. +f2fs.txt + - info and mount options for the F2FS filesystem. fuse.txt - info on the Filesystem in User SpacE including mount options. gfs2.txt diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt new file mode 100644 index 0000000..998e698 --- /dev/null +++ b/Documentation/filesystems/f2fs.txt @@ -0,0 +1,521 @@ +================================================================================ +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. + Default value for this option is on. So garbage + collection is on by default. +disable_roll_forward Disable the roll-forward recovery routine +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. + +================================================================================ +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/ +(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 this number, f2fs tries to + conduct checkpoint to reclaim the prefree segments + to free segments. By default, 100 segments, 200MB. + + 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. + + ipu_policy This parameter controls the policy of in-place + updates in f2fs. There are five policies: + 0: F2FS_IPU_FORCE, 1: F2FS_IPU_SSR, + 2: F2FS_IPU_UTIL, 3: F2FS_IPU_SSR_UTIL, + 4: F2FS_IPU_DISABLE. + + 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. + +================================================================================ +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, if n < 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/MAINTAINERS b/MAINTAINERS index 08e6f61..c0f2c98 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2728,6 +2728,16 @@ F: Documentation/filesystems/caching/ F: fs/fscache/ F: include/linux/fscache*.h +F2FS FILE SYSTEM +M: Jaegeuk Kim +L: linux-f2fs-devel@lists.sourceforge.net +W: http://en.wikipedia.org/wiki/F2FS +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git +S: Maintained +F: Documentation/filesystems/f2fs.txt +F: fs/f2fs/ +F: include/linux/f2fs_fs.h + FUJITSU FR-V (FRV) PORT M: David Howells S: Maintained diff --git a/fs/Kconfig b/fs/Kconfig index 88701cc..ec035f1 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -212,6 +212,7 @@ source "fs/pstore/Kconfig" source "fs/sysv/Kconfig" source "fs/ufs/Kconfig" source "fs/exofs/Kconfig" +source "fs/f2fs/Kconfig" endif # MISC_FILESYSTEMS diff --git a/fs/Makefile b/fs/Makefile index 2999b4d..059d27a 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -121,6 +121,7 @@ obj-$(CONFIG_DEBUG_FS) += debugfs/ obj-$(CONFIG_OCFS2_FS) += ocfs2/ obj-$(CONFIG_BTRFS_FS) += btrfs/ obj-$(CONFIG_GFS2_FS) += gfs2/ +obj-$(CONFIG_F2FS_FS) += f2fs/ obj-$(CONFIG_EXOFS_FS) += exofs/ 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..214fe10 --- /dev/null +++ b/fs/f2fs/Kconfig @@ -0,0 +1,73 @@ +config F2FS_FS + tristate "F2FS filesystem support (EXPERIMENTAL)" + depends on BLOCK + help + F2FS is based on Log-structured File System (LFS), which supports + versatile "flash-friendly" features. The design has been focused on + addressing the fundamental issues in LFS, which are snowball effect + of wandering tree and high cleaning overhead. + + Since flash-based storages show different characteristics according to + the internal geometry or flash memory management schemes aka FTL, F2FS + and tools support various parameters not only for configuring on-disk + layout, but also for selecting allocation and cleaning algorithms. + + If unsure, say N. + +config F2FS_STAT_FS + bool "F2FS Status Information" + depends on F2FS_FS && DEBUG_FS + default y + help + /sys/kernel/debug/f2fs/ contains information about all the partitions + mounted as f2fs. Each file shows the whole f2fs information. + + /sys/kernel/debug/f2fs/status includes: + - major file system information managed by f2fs currently + - average SIT information about whole segments + - current memory footprint consumed by f2fs. + +config F2FS_FS_XATTR + bool "F2FS extended attributes" + depends on F2FS_FS + default y + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page, or visit + for details). + + If unsure, say N. + +config F2FS_FS_POSIX_ACL + bool "F2FS Access Control Lists" + depends on F2FS_FS_XATTR + select FS_POSIX_ACL + default y + help + Posix Access Control Lists (ACLs) support permissions for users and + gourps beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the POSIX ACLs for + Linux website . + + 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 file system consistency in runtime. + + If you want to improve the performance, say N. diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile new file mode 100644 index 0000000..2e35da1 --- /dev/null +++ b/fs/f2fs/Makefile @@ -0,0 +1,7 @@ +obj-$(CONFIG_F2FS_FS) += f2fs.o + +f2fs-y := dir.o file.o inode.o namei.o hash.o super.o inline.o +f2fs-y += checkpoint.o gc.o data.o node.o segment.o recovery.o +f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o +f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o +f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c new file mode 100644 index 0000000..d0fc287 --- /dev/null +++ b/fs/f2fs/acl.c @@ -0,0 +1,414 @@ +/* + * 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, + * + * 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 +#include "f2fs.h" +#include "xattr.h" +#include "acl.h" + +#define get_inode_mode(i) ((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \ + (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) + +static inline size_t f2fs_acl_size(int count) +{ + if (count <= 4) { + return sizeof(struct f2fs_acl_header) + + count * sizeof(struct f2fs_acl_entry_short); + } else { + return sizeof(struct f2fs_acl_header) + + 4 * sizeof(struct f2fs_acl_entry_short) + + (count - 4) * sizeof(struct f2fs_acl_entry); + } +} + +static inline int f2fs_acl_count(size_t size) +{ + ssize_t s; + size -= sizeof(struct f2fs_acl_header); + s = size - 4 * sizeof(struct f2fs_acl_entry_short); + if (s < 0) { + if (size % sizeof(struct f2fs_acl_entry_short)) + return -1; + return size / sizeof(struct f2fs_acl_entry_short); + } else { + if (s % sizeof(struct f2fs_acl_entry)) + return -1; + return s / sizeof(struct f2fs_acl_entry) + 4; + } +} + +static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) +{ + int i, count; + struct posix_acl *acl; + struct f2fs_acl_header *hdr = (struct f2fs_acl_header *)value; + struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1); + const char *end = value + size; + + if (hdr->a_version != cpu_to_le32(F2FS_ACL_VERSION)) + return ERR_PTR(-EINVAL); + + count = f2fs_acl_count(size); + if (count < 0) + return ERR_PTR(-EINVAL); + if (count == 0) + return NULL; + + acl = posix_acl_alloc(count, GFP_KERNEL); + if (!acl) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < count; i++) { + + if ((char *)entry > end) + goto fail; + + acl->a_entries[i].e_tag = le16_to_cpu(entry->e_tag); + acl->a_entries[i].e_perm = le16_to_cpu(entry->e_perm); + + switch (acl->a_entries[i].e_tag) { + case ACL_USER_OBJ: + case ACL_GROUP_OBJ: + case ACL_MASK: + case ACL_OTHER: + entry = (struct f2fs_acl_entry *)((char *)entry + + sizeof(struct f2fs_acl_entry_short)); + break; + + case ACL_USER: + acl->a_entries[i].e_uid = + make_kuid(&init_user_ns, + le32_to_cpu(entry->e_id)); + entry = (struct f2fs_acl_entry *)((char *)entry + + sizeof(struct f2fs_acl_entry)); + break; + case ACL_GROUP: + acl->a_entries[i].e_gid = + make_kgid(&init_user_ns, + le32_to_cpu(entry->e_id)); + entry = (struct f2fs_acl_entry *)((char *)entry + + sizeof(struct f2fs_acl_entry)); + break; + default: + goto fail; + } + } + if ((char *)entry != end) + goto fail; + return acl; +fail: + posix_acl_release(acl); + return ERR_PTR(-EINVAL); +} + +static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size) +{ + struct f2fs_acl_header *f2fs_acl; + struct f2fs_acl_entry *entry; + int i; + + f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count * + sizeof(struct f2fs_acl_entry), GFP_KERNEL); + if (!f2fs_acl) + return ERR_PTR(-ENOMEM); + + f2fs_acl->a_version = cpu_to_le32(F2FS_ACL_VERSION); + entry = (struct f2fs_acl_entry *)(f2fs_acl + 1); + + for (i = 0; i < acl->a_count; i++) { + + entry->e_tag = cpu_to_le16(acl->a_entries[i].e_tag); + entry->e_perm = cpu_to_le16(acl->a_entries[i].e_perm); + + switch (acl->a_entries[i].e_tag) { + case ACL_USER: + entry->e_id = cpu_to_le32( + from_kuid(&init_user_ns, + acl->a_entries[i].e_uid)); + entry = (struct f2fs_acl_entry *)((char *)entry + + sizeof(struct f2fs_acl_entry)); + break; + case ACL_GROUP: + entry->e_id = cpu_to_le32( + from_kgid(&init_user_ns, + acl->a_entries[i].e_gid)); + entry = (struct f2fs_acl_entry *)((char *)entry + + sizeof(struct f2fs_acl_entry)); + break; + case ACL_USER_OBJ: + case ACL_GROUP_OBJ: + case ACL_MASK: + case ACL_OTHER: + entry = (struct f2fs_acl_entry *)((char *)entry + + sizeof(struct f2fs_acl_entry_short)); + break; + default: + goto fail; + } + } + *size = f2fs_acl_size(acl->a_count); + return (void *)f2fs_acl; + +fail: + kfree(f2fs_acl); + return ERR_PTR(-EINVAL); +} + +struct posix_acl *f2fs_get_acl(struct inode *inode, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + int name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT; + void *value = NULL; + struct posix_acl *acl; + int retval; + + if (!test_opt(sbi, POSIX_ACL)) + return NULL; + + acl = get_cached_acl(inode, type); + if (acl != ACL_NOT_CACHED) + return acl; + + if (type == ACL_TYPE_ACCESS) + name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; + + retval = f2fs_getxattr(inode, name_index, "", NULL, 0); + if (retval > 0) { + value = kmalloc(retval, GFP_KERNEL); + if (!value) + return ERR_PTR(-ENOMEM); + retval = f2fs_getxattr(inode, name_index, "", value, retval); + } + + if (retval > 0) + acl = f2fs_acl_from_disk(value, retval); + else if (retval == -ENODATA) + acl = NULL; + else + acl = ERR_PTR(retval); + kfree(value); + + if (!IS_ERR(acl)) + set_cached_acl(inode, type, acl); + + return acl; +} + +static int f2fs_set_acl(struct inode *inode, int type, + struct posix_acl *acl, struct 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)) { + cond_clear_inode_flag(fi, FI_ACL_MODE); + return (int)PTR_ERR(value); + } + } + + error = f2fs_setxattr(inode, name_index, "", value, size, ipage); + + kfree(value); + if (!error) + set_cached_acl(inode, type, acl); + + cond_clear_inode_flag(fi, FI_ACL_MODE); + return error; +} + +int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage) +{ + 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); + 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(&init_user_ns, acl, buffer, size); + posix_acl_release(acl); + + return error; +} + +static int f2fs_xattr_set_acl(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); + struct inode *inode = dentry->d_inode; + struct posix_acl *acl = NULL; + int error; + + if (strcmp(name, "") != 0) + return -EINVAL; + if (!test_opt(sbi, POSIX_ACL)) + return -EOPNOTSUPP; + if (!inode_owner_or_capable(inode)) + return -EPERM; + + if (value) { + acl = posix_acl_from_xattr(&init_user_ns, value, size); + if (IS_ERR(acl)) + return PTR_ERR(acl); + if (acl) { + error = posix_acl_valid(acl); + if (error) + goto release_and_out; + } + } else { + acl = NULL; + } + + error = f2fs_set_acl(inode, type, acl, 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..4963313 --- /dev/null +++ b/fs/f2fs/acl.h @@ -0,0 +1,58 @@ +/* + * 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, + * + * 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 + +#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 *); +#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 *page) +{ + 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..0d78bbe --- /dev/null +++ b/fs/f2fs/checkpoint.c @@ -0,0 +1,858 @@ +/* + * 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 +#include +#include +#include +#include +#include +#include +#include + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include + +static struct kmem_cache *orphan_entry_slab; +static struct kmem_cache *inode_entry_slab; + +/* + * We guarantee no failure on the returned page. + */ +struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) +{ + struct address_space *mapping = sbi->meta_inode->i_mapping; + struct page *page = NULL; +repeat: + page = grab_cache_page(mapping, index); + if (!page) { + cond_resched(); + goto repeat; + } + + /* We wait writeback only inside grab_meta_page() */ + wait_on_page_writeback(page); + SetPageUptodate(page); + return page; +} + +/* + * We guarantee no failure on the returned page. + */ +struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) +{ + struct address_space *mapping = sbi->meta_inode->i_mapping; + struct page *page; +repeat: + page = grab_cache_page(mapping, index); + if (!page) { + cond_resched(); + goto repeat; + } + if (PageUptodate(page)) + goto out; + + if (f2fs_submit_page_bio(sbi, page, index, + READ_SYNC | REQ_META | REQ_PRIO)) + goto repeat; + + lock_page(page); + if (unlikely(page->mapping != mapping)) { + f2fs_put_page(page, 1); + goto repeat; + } +out: + mark_page_accessed(page); + return page; +} + +static int f2fs_write_meta_page(struct page *page, + struct writeback_control *wbc) +{ + struct inode *inode = page->mapping->host; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + + /* Should not write any meta pages, if any IO error was occurred */ + if (unlikely(sbi->por_doing || + is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ERROR_FLAG))) + goto redirty_out; + + if (wbc->for_reclaim) + goto redirty_out; + + wait_on_page_writeback(page); + + write_meta_page(sbi, page); + dec_page_count(sbi, F2FS_DIRTY_META); + unlock_page(page); + return 0; + +redirty_out: + dec_page_count(sbi, F2FS_DIRTY_META); + wbc->pages_skipped++; + set_page_dirty(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_SB(mapping->host->i_sb); + int nrpages = MAX_BIO_BLOCKS(max_hw_blocks(sbi)); + long written; + + if (wbc->for_kupdate) + return 0; + + /* collect a number of dirty meta pages and write together */ + if (get_pages(sbi, F2FS_DIRTY_META) < nrpages) + return 0; + + /* if mounting is failed, skip writing node pages */ + mutex_lock(&sbi->cp_mutex); + written = sync_meta_pages(sbi, META, nrpages); + mutex_unlock(&sbi->cp_mutex); + wbc->nr_to_write -= written; + return 0; +} + +long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, + long nr_to_write) +{ + struct address_space *mapping = sbi->meta_inode->i_mapping; + pgoff_t index = 0, end = LONG_MAX; + struct pagevec pvec; + long nwritten = 0; + struct writeback_control wbc = { + .for_reclaim = 0, + }; + + pagevec_init(&pvec, 0); + + while (index <= end) { + int i, nr_pages; + nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_DIRTY, + min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); + if (unlikely(nr_pages == 0)) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + lock_page(page); + f2fs_bug_on(page->mapping != mapping); + f2fs_bug_on(!PageDirty(page)); + clear_page_dirty_for_io(page); + if (f2fs_write_meta_page(page, &wbc)) { + unlock_page(page); + break; + } + nwritten++; + if (unlikely(nwritten >= nr_to_write)) + break; + } + pagevec_release(&pvec); + cond_resched(); + } + + if (nwritten) + f2fs_submit_merged_bio(sbi, type, WRITE); + + return nwritten; +} + +static int f2fs_set_meta_page_dirty(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb); + + trace_f2fs_set_page_dirty(page, META); + + SetPageUptodate(page); + if (!PageDirty(page)) { + __set_page_dirty_nobuffers(page); + inc_page_count(sbi, F2FS_DIRTY_META); + return 1; + } + return 0; +} + +const struct address_space_operations f2fs_meta_aops = { + .writepage = f2fs_write_meta_page, + .writepages = f2fs_write_meta_pages, + .set_page_dirty = f2fs_set_meta_page_dirty, +}; + +int acquire_orphan_inode(struct f2fs_sb_info *sbi) +{ + int err = 0; + + mutex_lock(&sbi->orphan_inode_mutex); + if (unlikely(sbi->n_orphans >= sbi->max_orphans)) + err = -ENOSPC; + else + sbi->n_orphans++; + mutex_unlock(&sbi->orphan_inode_mutex); + + return err; +} + +void release_orphan_inode(struct f2fs_sb_info *sbi) +{ + mutex_lock(&sbi->orphan_inode_mutex); + f2fs_bug_on(sbi->n_orphans == 0); + sbi->n_orphans--; + mutex_unlock(&sbi->orphan_inode_mutex); +} + +void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct list_head *head, *this; + struct orphan_inode_entry *new = NULL, *orphan = NULL; + + mutex_lock(&sbi->orphan_inode_mutex); + head = &sbi->orphan_inode_list; + list_for_each(this, head) { + orphan = list_entry(this, struct orphan_inode_entry, list); + if (orphan->ino == ino) + goto out; + if (orphan->ino > ino) + break; + orphan = NULL; + } + + new = f2fs_kmem_cache_alloc(orphan_entry_slab, GFP_ATOMIC); + new->ino = ino; + + /* add new_oentry into list which is sorted by inode number */ + if (orphan) + list_add(&new->list, this->prev); + else + list_add_tail(&new->list, head); +out: + mutex_unlock(&sbi->orphan_inode_mutex); +} + +void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct list_head *head; + struct orphan_inode_entry *orphan; + + mutex_lock(&sbi->orphan_inode_mutex); + head = &sbi->orphan_inode_list; + list_for_each_entry(orphan, head, list) { + if (orphan->ino == ino) { + list_del(&orphan->list); + kmem_cache_free(orphan_entry_slab, orphan); + f2fs_bug_on(sbi->n_orphans == 0); + sbi->n_orphans--; + break; + } + } + mutex_unlock(&sbi->orphan_inode_mutex); +} + +static void recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct inode *inode = f2fs_iget(sbi->sb, ino); + f2fs_bug_on(IS_ERR(inode)); + clear_nlink(inode); + + /* truncate all the data during iput */ + iput(inode); +} + +void recover_orphan_inodes(struct f2fs_sb_info *sbi) +{ + block_t start_blk, orphan_blkaddr, i, j; + + if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG)) + return; + + sbi->por_doing = true; + start_blk = __start_cp_addr(sbi) + 1; + orphan_blkaddr = __start_sum_addr(sbi) - 1; + + for (i = 0; i < orphan_blkaddr; i++) { + struct page *page = get_meta_page(sbi, start_blk + i); + struct f2fs_orphan_block *orphan_blk; + + orphan_blk = (struct f2fs_orphan_block *)page_address(page); + for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) { + nid_t ino = le32_to_cpu(orphan_blk->ino[j]); + recover_orphan_inode(sbi, ino); + } + f2fs_put_page(page, 1); + } + /* clear Orphan Flag */ + clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG); + sbi->por_doing = false; + return; +} + +static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) +{ + struct list_head *head; + struct f2fs_orphan_block *orphan_blk = NULL; + struct page *page = NULL; + unsigned int nentries = 0; + unsigned short index = 1; + unsigned short orphan_blocks; + struct orphan_inode_entry *orphan = NULL; + + orphan_blocks = (unsigned short)((sbi->n_orphans + + (F2FS_ORPHANS_PER_BLOCK - 1)) / F2FS_ORPHANS_PER_BLOCK); + + mutex_lock(&sbi->orphan_inode_mutex); + head = &sbi->orphan_inode_list; + + /* loop for each orphan inode entry and write them in Jornal block */ + list_for_each_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++; + start_blk++; + 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); + } + + mutex_unlock(&sbi->orphan_inode_mutex); +} + +static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, + block_t cp_addr, unsigned long long *version) +{ + struct page *cp_page_1, *cp_page_2 = NULL; + unsigned long blk_size = sbi->blocksize; + struct f2fs_checkpoint *cp_block; + unsigned long long cur_version = 0, pre_version = 0; + 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(*((__u32 *)((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(*((__u32 *)((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; + + sbi->ckpt = kzalloc(blk_size, GFP_KERNEL); + if (!sbi->ckpt) + return -ENOMEM; + /* + * Finding out valid cp block involves read both + * sets( cp pack1 and cp pack 2) + */ + cp_start_blk_no = le32_to_cpu(fsb->cp_blkaddr); + cp1 = validate_checkpoint(sbi, cp_start_blk_no, &cp1_version); + + /* The second checkpoint pack should start at the next segment */ + cp_start_blk_no += ((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); + + 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 dir_inode_entry *new) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct list_head *head = &sbi->dir_inode_list; + struct list_head *this; + + list_for_each(this, head) { + struct dir_inode_entry *entry; + entry = list_entry(this, struct dir_inode_entry, list); + if (unlikely(entry->inode == inode)) + return -EEXIST; + } + list_add_tail(&new->list, head); + stat_inc_dirty_dir(sbi); + return 0; +} + +void set_dirty_dir_page(struct inode *inode, struct page *page) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct dir_inode_entry *new; + + if (!S_ISDIR(inode->i_mode)) + return; + + new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); + new->inode = inode; + INIT_LIST_HEAD(&new->list); + + spin_lock(&sbi->dir_inode_lock); + if (__add_dirty_inode(inode, new)) + kmem_cache_free(inode_entry_slab, new); + + inc_page_count(sbi, F2FS_DIRTY_DENTS); + inode_inc_dirty_dents(inode); + SetPagePrivate(page); + spin_unlock(&sbi->dir_inode_lock); +} + +void add_dirty_dir_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct dir_inode_entry *new = + f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); + + new->inode = inode; + INIT_LIST_HEAD(&new->list); + + spin_lock(&sbi->dir_inode_lock); + if (__add_dirty_inode(inode, new)) + kmem_cache_free(inode_entry_slab, new); + spin_unlock(&sbi->dir_inode_lock); +} + +void remove_dirty_dir_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + + struct list_head *this, *head; + + if (!S_ISDIR(inode->i_mode)) + return; + + spin_lock(&sbi->dir_inode_lock); + if (atomic_read(&F2FS_I(inode)->dirty_dents)) { + spin_unlock(&sbi->dir_inode_lock); + return; + } + + head = &sbi->dir_inode_list; + list_for_each(this, head) { + struct dir_inode_entry *entry; + entry = list_entry(this, struct dir_inode_entry, list); + if (entry->inode == inode) { + list_del(&entry->list); + kmem_cache_free(inode_entry_slab, entry); + stat_dec_dirty_dir(sbi); + break; + } + } + spin_unlock(&sbi->dir_inode_lock); + + /* 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); + } +} + +struct inode *check_dirty_dir_inode(struct f2fs_sb_info *sbi, nid_t ino) +{ + + struct list_head *this, *head; + struct inode *inode = NULL; + + spin_lock(&sbi->dir_inode_lock); + + head = &sbi->dir_inode_list; + list_for_each(this, head) { + struct dir_inode_entry *entry; + entry = list_entry(this, struct dir_inode_entry, list); + if (entry->inode->i_ino == ino) { + inode = entry->inode; + break; + } + } + spin_unlock(&sbi->dir_inode_lock); + return inode; +} + +void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi) +{ + struct list_head *head; + struct dir_inode_entry *entry; + struct inode *inode; +retry: + 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 dir_inode_entry, list); + inode = igrab(entry->inode); + spin_unlock(&sbi->dir_inode_lock); + if (inode) { + filemap_flush(inode->i_mapping); + iput(inode); + } else { + /* + * We should submit bio, since it exists several + * wribacking dentry pages in the freeing inode. + */ + f2fs_submit_merged_bio(sbi, DATA, WRITE); + } + goto retry; +} + +/* + * Freeze all the FS-operations for checkpoint. + */ +static void block_operations(struct f2fs_sb_info *sbi) +{ + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = LONG_MAX, + .for_reclaim = 0, + }; + struct blk_plug plug; + + blk_start_plug(&plug); + +retry_flush_dents: + 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); + goto retry_flush_dents; + } + + /* + * POR: we should ensure that there is no dirty node pages + * until finishing nat/sit flush. + */ +retry_flush_nodes: + mutex_lock(&sbi->node_write); + + if (get_pages(sbi, F2FS_DIRTY_NODES)) { + mutex_unlock(&sbi->node_write); + sync_node_pages(sbi, 0, &wbc); + goto retry_flush_nodes; + } + blk_finish_plug(&plug); +} + +static void unblock_operations(struct f2fs_sb_info *sbi) +{ + mutex_unlock(&sbi->node_write); + 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, bool is_umount) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + nid_t last_nid = 0; + block_t start_blk; + struct page *cp_page; + unsigned int data_sum_blocks, orphan_blocks; + __u32 crc32 = 0; + void *kaddr; + int i; + + /* Flush all the NAT/SIT pages */ + while (get_pages(sbi, F2FS_DIRTY_META)) + sync_meta_pages(sbi, META, LONG_MAX); + + next_free_nid(sbi, &last_nid); + + /* + * modify checkpoint + * version number is already updated + */ + ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi)); + ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi)); + ckpt->free_segment_count = cpu_to_le32(free_segments(sbi)); + for (i = 0; i < 3; i++) { + ckpt->cur_node_segno[i] = + cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_NODE)); + ckpt->cur_node_blkoff[i] = + cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_NODE)); + ckpt->alloc_type[i + CURSEG_HOT_NODE] = + curseg_alloc_type(sbi, i + CURSEG_HOT_NODE); + } + for (i = 0; i < 3; i++) { + ckpt->cur_data_segno[i] = + cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_DATA)); + ckpt->cur_data_blkoff[i] = + cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_DATA)); + ckpt->alloc_type[i + CURSEG_HOT_DATA] = + curseg_alloc_type(sbi, i + CURSEG_HOT_DATA); + } + + ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi)); + ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi)); + ckpt->next_free_nid = cpu_to_le32(last_nid); + + /* 2 cp + n data seg summary + orphan inode blocks */ + data_sum_blocks = npages_for_summary_flush(sbi); + if (data_sum_blocks < 3) + set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); + else + clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); + + orphan_blocks = (sbi->n_orphans + F2FS_ORPHANS_PER_BLOCK - 1) + / F2FS_ORPHANS_PER_BLOCK; + ckpt->cp_pack_start_sum = cpu_to_le32(1 + orphan_blocks); + + if (is_umount) { + set_ckpt_flags(ckpt, CP_UMOUNT_FLAG); + ckpt->cp_pack_total_block_count = cpu_to_le32(2 + + data_sum_blocks + orphan_blocks + NR_CURSEG_NODE_TYPE); + } else { + clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG); + ckpt->cp_pack_total_block_count = cpu_to_le32(2 + + data_sum_blocks + orphan_blocks); + } + + if (sbi->n_orphans) + set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); + else + clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); + + /* update SIT/NAT bitmap */ + get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP)); + get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP)); + + crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset)); + *((__le32 *)((unsigned char *)ckpt + + le32_to_cpu(ckpt->checksum_offset))) + = cpu_to_le32(crc32); + + start_blk = __start_cp_addr(sbi); + + /* write out checkpoint buffer at block 0 */ + cp_page = grab_meta_page(sbi, start_blk++); + kaddr = page_address(cp_page); + memcpy(kaddr, ckpt, (1 << sbi->log_blocksize)); + set_page_dirty(cp_page); + f2fs_put_page(cp_page, 1); + + if (sbi->n_orphans) { + write_orphan_inodes(sbi, start_blk); + start_blk += orphan_blocks; + } + + write_data_summaries(sbi, start_blk); + start_blk += data_sum_blocks; + if (is_umount) { + write_node_summaries(sbi, start_blk); + start_blk += NR_CURSEG_NODE_TYPE; + } + + /* writeout checkpoint block */ + cp_page = grab_meta_page(sbi, start_blk); + kaddr = page_address(cp_page); + memcpy(kaddr, ckpt, (1 << sbi->log_blocksize)); + set_page_dirty(cp_page); + f2fs_put_page(cp_page, 1); + + /* wait for previous submitted node/meta pages writeback */ + wait_on_all_pages_writeback(sbi); + + filemap_fdatawait_range(sbi->node_inode->i_mapping, 0, LONG_MAX); + filemap_fdatawait_range(sbi->meta_inode->i_mapping, 0, LONG_MAX); + + /* update user_block_counts */ + sbi->last_valid_block_count = sbi->total_valid_block_count; + sbi->alloc_valid_block_count = 0; + + /* Here, we only have one bio having CP pack */ + sync_meta_pages(sbi, META_FLUSH, LONG_MAX); + + if (unlikely(!is_set_ckpt_flags(ckpt, CP_ERROR_FLAG))) { + clear_prefree_segments(sbi); + F2FS_RESET_SB_DIRT(sbi); + } +} + +/* + * We guarantee that this checkpoint procedure should not fail. + */ +void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + unsigned long long ckpt_ver; + + trace_f2fs_write_checkpoint(sbi->sb, is_umount, "start block_ops"); + + mutex_lock(&sbi->cp_mutex); + block_operations(sbi); + + trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish block_ops"); + + f2fs_submit_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); + + /* unlock all the fs_lock[] in do_checkpoint() */ + do_checkpoint(sbi, is_umount); + + unblock_operations(sbi); + mutex_unlock(&sbi->cp_mutex); + + trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish checkpoint"); +} + +void init_orphan_info(struct f2fs_sb_info *sbi) +{ + mutex_init(&sbi->orphan_inode_mutex); + INIT_LIST_HEAD(&sbi->orphan_inode_list); + sbi->n_orphans = 0; + /* + * considering 512 blocks in a segment 8 blocks are needed for cp + * and log segment summaries. Remaining blocks are used to keep + * orphan entries with the limitation one reserved segment + * for cp pack we can have max 1020*504 orphan entries + */ + sbi->max_orphans = (sbi->blocks_per_seg - 2 - NR_CURSEG_TYPE) + * F2FS_ORPHANS_PER_BLOCK; +} + +int __init create_checkpoint_caches(void) +{ + orphan_entry_slab = f2fs_kmem_cache_create("f2fs_orphan_entry", + sizeof(struct orphan_inode_entry), NULL); + if (!orphan_entry_slab) + return -ENOMEM; + inode_entry_slab = f2fs_kmem_cache_create("f2fs_dirty_dir_entry", + sizeof(struct dir_inode_entry), NULL); + if (!inode_entry_slab) { + kmem_cache_destroy(orphan_entry_slab); + return -ENOMEM; + } + return 0; +} + +void destroy_checkpoint_caches(void) +{ + kmem_cache_destroy(orphan_entry_slab); + kmem_cache_destroy(inode_entry_slab); +} diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c new file mode 100644 index 0000000..63d1902 --- /dev/null +++ b/fs/f2fs/data.c @@ -0,0 +1,1086 @@ +/* + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include + +static void f2fs_read_end_io(struct bio *bio, int err) +{ + const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); + struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; + + do { + struct page *page = bvec->bv_page; + + if (--bvec >= bio->bi_io_vec) + prefetchw(&bvec->bv_page->flags); + + if (unlikely(!uptodate)) { + ClearPageUptodate(page); + SetPageError(page); + } else { + SetPageUptodate(page); + } + unlock_page(page); + } while (bvec >= bio->bi_io_vec); + + bio_put(bio); +} + +static void f2fs_write_end_io(struct bio *bio, int err) +{ + const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); + struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; + struct f2fs_sb_info *sbi = F2FS_SB(bvec->bv_page->mapping->host->i_sb); + + do { + struct page *page = bvec->bv_page; + + if (--bvec >= bio->bi_io_vec) + prefetchw(&bvec->bv_page->flags); + + if (unlikely(!uptodate)) { + SetPageError(page); + set_bit(AS_EIO, &page->mapping->flags); + set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG); + sbi->sb->s_flags |= MS_RDONLY; + } + end_page_writeback(page); + dec_page_count(sbi, F2FS_WRITEBACK); + } while (bvec >= bio->bi_io_vec); + + if (bio->bi_private) + complete(bio->bi_private); + + if (!get_pages(sbi, F2FS_WRITEBACK) && + !list_empty(&sbi->cp_wait.task_list)) + wake_up(&sbi->cp_wait); + + bio_put(bio); +} + +/* + * Low-level block read/write IO operations. + */ +static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr, + int npages, bool is_read) +{ + struct bio *bio; + + /* No failure on bio allocation */ + bio = bio_alloc(GFP_NOIO, npages); + + bio->bi_bdev = sbi->sb->s_bdev; + bio->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr); + bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io; + + return bio; +} + +static void __submit_merged_bio(struct f2fs_bio_info *io) +{ + struct f2fs_io_info *fio = &io->fio; + int rw; + + if (!io->bio) + return; + + rw = fio->rw; + + if (is_read_io(rw)) { + trace_f2fs_submit_read_bio(io->sbi->sb, rw, + fio->type, io->bio); + submit_bio(rw, io->bio); + } else { + trace_f2fs_submit_write_bio(io->sbi->sb, rw, + fio->type, io->bio); + /* + * META_FLUSH is only from the checkpoint procedure, and we + * should wait this metadata bio for FS consistency. + */ + if (fio->type == META_FLUSH) { + DECLARE_COMPLETION_ONSTACK(wait); + io->bio->bi_private = &wait; + submit_bio(rw, io->bio); + wait_for_completion(&wait); + } else { + submit_bio(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]; + + mutex_lock(&io->io_mutex); + + /* change META to META_FLUSH in the checkpoint procedure */ + if (type >= META_FLUSH) { + io->fio.type = META_FLUSH; + io->fio.rw = WRITE_FLUSH_FUA; + } + __submit_merged_bio(io); + mutex_unlock(&io->io_mutex); +} + +/* + * Fill the locked page with data located in the block address. + * Return unlocked page. + */ +int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page, + block_t blk_addr, int rw) +{ + struct bio *bio; + + trace_f2fs_submit_page_bio(page, blk_addr, rw); + + /* Allocate a new bio */ + bio = __bio_alloc(sbi, blk_addr, 1, is_read_io(rw)); + + if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { + bio_put(bio); + f2fs_put_page(page, 1); + return -EFAULT; + } + + submit_bio(rw, bio); + return 0; +} + +void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page, + block_t blk_addr, struct f2fs_io_info *fio) +{ + enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); + struct f2fs_bio_info *io; + bool is_read = is_read_io(fio->rw); + + io = is_read ? &sbi->read_io : &sbi->write_io[btype]; + + verify_block_addr(sbi, blk_addr); + + mutex_lock(&io->io_mutex); + + if (!is_read) + inc_page_count(sbi, F2FS_WRITEBACK); + + if (io->bio && (io->last_block_in_bio != blk_addr - 1 || + io->fio.rw != fio->rw)) + __submit_merged_bio(io); +alloc_new: + if (io->bio == NULL) { + int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi)); + + io->bio = __bio_alloc(sbi, blk_addr, bio_blocks, is_read); + io->fio = *fio; + } + + if (bio_add_page(io->bio, page, PAGE_CACHE_SIZE, 0) < + PAGE_CACHE_SIZE) { + __submit_merged_bio(io); + goto alloc_new; + } + + io->last_block_in_bio = blk_addr; + + mutex_unlock(&io->io_mutex); + trace_f2fs_submit_page_mbio(page, fio->rw, fio->type, blk_addr); +} + +/* + * Lock ordering for the change of data block address: + * ->data_page + * ->node_page + * update block addresses in the node page + */ +static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr) +{ + struct f2fs_node *rn; + __le32 *addr_array; + struct page *node_page = dn->node_page; + unsigned int ofs_in_node = dn->ofs_in_node; + + f2fs_wait_on_page_writeback(node_page, NODE, false); + + 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(new_addr); + set_page_dirty(node_page); +} + +int reserve_new_block(struct dnode_of_data *dn) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb); + + if (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); + + __set_data_blkaddr(dn, NEW_ADDR); + dn->data_blkaddr = NEW_ADDR; + 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; + + /* if inode_page exists, index should be zero */ + f2fs_bug_on(!need_put && index); + + err = get_dnode_of_data(dn, index, ALLOC_NODE); + if (err) + return err; + + if (dn->data_blkaddr == NULL_ADDR) + err = reserve_new_block(dn); + if (err || need_put) + f2fs_put_dnode(dn); + return err; +} + +static int check_extent_cache(struct inode *inode, pgoff_t pgofs, + struct buffer_head *bh_result) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + pgoff_t start_fofs, end_fofs; + block_t start_blkaddr; + + if (is_inode_flag_set(fi, FI_NO_EXTENT)) + return 0; + + read_lock(&fi->ext.ext_lock); + if (fi->ext.len == 0) { + read_unlock(&fi->ext.ext_lock); + return 0; + } + + stat_inc_total_hit(inode->i_sb); + + start_fofs = fi->ext.fofs; + end_fofs = fi->ext.fofs + fi->ext.len - 1; + start_blkaddr = fi->ext.blk_addr; + + if (pgofs >= start_fofs && pgofs <= end_fofs) { + unsigned int blkbits = inode->i_sb->s_blocksize_bits; + size_t count; + + clear_buffer_new(bh_result); + map_bh(bh_result, inode->i_sb, + start_blkaddr + pgofs - start_fofs); + count = end_fofs - pgofs + 1; + if (count < (UINT_MAX >> blkbits)) + bh_result->b_size = (count << blkbits); + else + bh_result->b_size = UINT_MAX; + + stat_inc_read_hit(inode->i_sb); + read_unlock(&fi->ext.ext_lock); + return 1; + } + read_unlock(&fi->ext.ext_lock); + return 0; +} + +void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn) +{ + struct f2fs_inode_info *fi = F2FS_I(dn->inode); + pgoff_t fofs, start_fofs, end_fofs; + block_t start_blkaddr, end_blkaddr; + int need_update = true; + + f2fs_bug_on(blk_addr == NEW_ADDR); + fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) + + dn->ofs_in_node; + + /* Update the page address in the parent node */ + __set_data_blkaddr(dn, blk_addr); + + if (is_inode_flag_set(fi, FI_NO_EXTENT)) + return; + + write_lock(&fi->ext.ext_lock); + + start_fofs = fi->ext.fofs; + end_fofs = fi->ext.fofs + fi->ext.len - 1; + start_blkaddr = fi->ext.blk_addr; + end_blkaddr = fi->ext.blk_addr + fi->ext.len - 1; + + /* Drop and initialize the matched extent */ + if (fi->ext.len == 1 && fofs == start_fofs) + fi->ext.len = 0; + + /* Initial extent */ + if (fi->ext.len == 0) { + if (blk_addr != NULL_ADDR) { + fi->ext.fofs = fofs; + fi->ext.blk_addr = blk_addr; + fi->ext.len = 1; + } + goto end_update; + } + + /* Front merge */ + if (fofs == start_fofs - 1 && blk_addr == start_blkaddr - 1) { + fi->ext.fofs--; + fi->ext.blk_addr--; + fi->ext.len++; + goto end_update; + } + + /* Back merge */ + if (fofs == end_fofs + 1 && blk_addr == end_blkaddr + 1) { + fi->ext.len++; + goto end_update; + } + + /* Split the existing extent */ + if (fi->ext.len > 1 && + fofs >= start_fofs && fofs <= end_fofs) { + if ((end_fofs - fofs) < (fi->ext.len >> 1)) { + fi->ext.len = fofs - start_fofs; + } else { + fi->ext.fofs = fofs + 1; + fi->ext.blk_addr = start_blkaddr + + fofs - start_fofs + 1; + fi->ext.len -= fofs - start_fofs + 1; + } + } else { + need_update = false; + } + + /* Finally, if the extent is very fragmented, let's drop the cache. */ + if (fi->ext.len < F2FS_MIN_EXTENT_LEN) { + fi->ext.len = 0; + set_inode_flag(fi, FI_NO_EXTENT); + need_update = true; + } +end_update: + write_unlock(&fi->ext.ext_lock); + if (need_update) + sync_inode_page(dn); + return; +} + +struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct address_space *mapping = inode->i_mapping; + struct dnode_of_data dn; + struct page *page; + int err; + + page = find_get_page(mapping, index); + if (page && PageUptodate(page)) + return page; + f2fs_put_page(page, 0); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, index, LOOKUP_NODE); + if (err) + return ERR_PTR(err); + f2fs_put_dnode(&dn); + + if (dn.data_blkaddr == NULL_ADDR) + return ERR_PTR(-ENOENT); + + /* By fallocate(), there is no cached page, but with NEW_ADDR */ + if (unlikely(dn.data_blkaddr == NEW_ADDR)) + return ERR_PTR(-EINVAL); + + page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS); + if (!page) + return ERR_PTR(-ENOMEM); + + if (PageUptodate(page)) { + unlock_page(page); + return page; + } + + err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr, + sync ? READ_SYNC : READA); + if (err) + return ERR_PTR(err); + + if (sync) { + wait_on_page_locked(page); + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 0); + return ERR_PTR(-EIO); + } + } + return page; +} + +/* + * If it tries to access a hole, return an error. + * Because, the callers, functions in dir.c and GC, should be able to know + * whether this page exists or not. + */ +struct page *get_lock_data_page(struct inode *inode, pgoff_t index) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct address_space *mapping = inode->i_mapping; + struct dnode_of_data dn; + struct page *page; + int err; + +repeat: + page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS); + if (!page) + return ERR_PTR(-ENOMEM); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, index, LOOKUP_NODE); + if (err) { + f2fs_put_page(page, 1); + return ERR_PTR(err); + } + f2fs_put_dnode(&dn); + + if (unlikely(dn.data_blkaddr == NULL_ADDR)) { + f2fs_put_page(page, 1); + return ERR_PTR(-ENOENT); + } + + if (PageUptodate(page)) + return page; + + /* + * A new dentry page is allocated but not able to be written, since its + * new inode page couldn't be allocated due to -ENOSPC. + * In such the case, its blkaddr can be remained as NEW_ADDR. + * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata. + */ + if (dn.data_blkaddr == NEW_ADDR) { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + SetPageUptodate(page); + return page; + } + + err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr, READ_SYNC); + if (err) + return ERR_PTR(err); + + lock_page(page); + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 1); + return ERR_PTR(-EIO); + } + if (unlikely(page->mapping != mapping)) { + f2fs_put_page(page, 1); + goto repeat; + } + return page; +} + +/* + * Caller ensures that this data page is never allocated. + * A new zero-filled data page is allocated in the page cache. + * + * Also, caller should grab and release a rwsem by calling f2fs_lock_op() and + * f2fs_unlock_op(). + * Note that, ipage is set only by make_empty_dir. + */ +struct page *get_new_data_page(struct inode *inode, + struct page *ipage, pgoff_t index, bool new_i_size) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct address_space *mapping = inode->i_mapping; + struct page *page; + struct dnode_of_data dn; + int err; + + set_new_dnode(&dn, inode, ipage, NULL, 0); + err = f2fs_reserve_block(&dn, index); + if (err) + return ERR_PTR(err); +repeat: + page = grab_cache_page(mapping, index); + if (!page) { + err = -ENOMEM; + goto put_err; + } + + if (PageUptodate(page)) + return page; + + if (dn.data_blkaddr == NEW_ADDR) { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + SetPageUptodate(page); + } else { + err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr, + READ_SYNC); + if (err) + goto put_err; + + lock_page(page); + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 1); + err = -EIO; + goto put_err; + } + if (unlikely(page->mapping != mapping)) { + f2fs_put_page(page, 1); + goto repeat; + } + } + + if (new_i_size && + i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) { + i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT)); + /* Only the directory inode sets new_i_size */ + set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR); + mark_inode_dirty_sync(inode); + } + return page; + +put_err: + f2fs_put_dnode(&dn); + return ERR_PTR(err); +} + +static int __allocate_data_block(struct dnode_of_data *dn) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb); + struct f2fs_summary sum; + block_t new_blkaddr; + struct node_info ni; + int type; + + 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; + + __set_data_blkaddr(dn, NEW_ADDR); + dn->data_blkaddr = NEW_ADDR; + + get_node_info(sbi, dn->nid, &ni); + set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); + + type = CURSEG_WARM_DATA; + + allocate_data_block(sbi, NULL, NULL_ADDR, &new_blkaddr, &sum, type); + + /* direct IO doesn't use extent cache to maximize the performance */ + set_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT); + update_extent_cache(new_blkaddr, dn); + clear_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT); + + dn->data_blkaddr = new_blkaddr; + return 0; +} + +/* + * get_data_block() now supported readahead/bmap/rw direct_IO with mapped bh. + * If original data blocks are allocated, then give them to blockdev. + * Otherwise, + * a. preallocate requested block addresses + * b. do not use extent cache for better performance + * c. give the block addresses to blockdev + */ +static int get_data_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + unsigned int blkbits = inode->i_sb->s_blocksize_bits; + unsigned maxblocks = bh_result->b_size >> blkbits; + struct dnode_of_data dn; + int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA; + pgoff_t pgofs, end_offset; + int err = 0, ofs = 1; + bool allocated = false; + + /* Get the page offset from the block offset(iblock) */ + pgofs = (pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits)); + + if (check_extent_cache(inode, pgofs, bh_result)) + goto out; + + if (create) + f2fs_lock_op(sbi); + + /* 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) + goto put_out; + + if (dn.data_blkaddr != NULL_ADDR) { + map_bh(bh_result, inode->i_sb, dn.data_blkaddr); + } else if (create) { + err = __allocate_data_block(&dn); + if (err) + goto put_out; + allocated = true; + map_bh(bh_result, inode->i_sb, dn.data_blkaddr); + } else { + goto put_out; + } + + end_offset = IS_INODE(dn.node_page) ? + ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK; + bh_result->b_size = (((size_t)1) << blkbits); + dn.ofs_in_node++; + pgofs++; + +get_next: + if (dn.ofs_in_node >= end_offset) { + if (allocated) + sync_inode_page(&dn); + allocated = false; + f2fs_put_dnode(&dn); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, pgofs, mode); + if (err) { + if (err == -ENOENT) + err = 0; + goto unlock_out; + } + if (dn.data_blkaddr == NEW_ADDR) + goto put_out; + + end_offset = IS_INODE(dn.node_page) ? + ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK; + } + + if (maxblocks > (bh_result->b_size >> blkbits)) { + block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); + if (blkaddr == NULL_ADDR && create) { + err = __allocate_data_block(&dn); + if (err) + goto sync_out; + allocated = true; + blkaddr = dn.data_blkaddr; + } + /* Give more consecutive addresses for the read ahead */ + if (blkaddr == (bh_result->b_blocknr + ofs)) { + ofs++; + dn.ofs_in_node++; + pgofs++; + bh_result->b_size += (((size_t)1) << blkbits); + goto get_next; + } + } +sync_out: + if (allocated) + sync_inode_page(&dn); +put_out: + f2fs_put_dnode(&dn); +unlock_out: + if (create) + f2fs_unlock_op(sbi); +out: + trace_f2fs_get_data_block(inode, iblock, bh_result, err); + return err; +} + +static int f2fs_read_data_page(struct file *file, struct page *page) +{ + struct inode *inode = page->mapping->host; + int ret; + + /* If the file has inline data, try to read it directlly */ + if (f2fs_has_inline_data(inode)) + ret = f2fs_read_inline_data(inode, page); + else + ret = mpage_readpage(page, get_data_block); + + return ret; +} + +static int f2fs_read_data_pages(struct file *file, + struct address_space *mapping, + struct list_head *pages, unsigned nr_pages) +{ + struct inode *inode = file->f_mapping->host; + + /* If the file has inline data, skip readpages */ + if (f2fs_has_inline_data(inode)) + return 0; + + return mpage_readpages(mapping, pages, nr_pages, get_data_block); +} + +int do_write_data_page(struct page *page, struct f2fs_io_info *fio) +{ + struct inode *inode = page->mapping->host; + block_t old_blkaddr, new_blkaddr; + struct dnode_of_data dn; + int err = 0; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE); + if (err) + return err; + + old_blkaddr = dn.data_blkaddr; + + /* This page is already truncated */ + if (old_blkaddr == NULL_ADDR) + goto out_writepage; + + set_page_writeback(page); + + /* + * If current allocation needs SSR, + * it had better in-place writes for updated data. + */ + if (unlikely(old_blkaddr != NEW_ADDR && + !is_cold_data(page) && + need_inplace_update(inode))) { + rewrite_data_page(page, old_blkaddr, fio); + } else { + write_data_page(page, &dn, &new_blkaddr, fio); + update_extent_cache(new_blkaddr, &dn); + } +out_writepage: + f2fs_put_dnode(&dn); + return err; +} + +static int f2fs_write_data_page(struct page *page, + struct writeback_control *wbc) +{ + struct inode *inode = page->mapping->host; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + loff_t i_size = i_size_read(inode); + const pgoff_t end_index = ((unsigned long long) i_size) + >> PAGE_CACHE_SHIFT; + unsigned offset = 0; + bool need_balance_fs = false; + int err = 0; + struct f2fs_io_info fio = { + .type = DATA, + .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC: WRITE, + }; + + if (page->index < end_index) + goto write; + + /* + * If the offset is out-of-range of file size, + * this page does not have to be written to disk. + */ + offset = i_size & (PAGE_CACHE_SIZE - 1); + if ((page->index >= end_index + 1) || !offset) { + if (S_ISDIR(inode->i_mode)) { + dec_page_count(sbi, F2FS_DIRTY_DENTS); + inode_dec_dirty_dents(inode); + } + goto out; + } + + zero_user_segment(page, offset, PAGE_CACHE_SIZE); +write: + if (unlikely(sbi->por_doing)) { + err = AOP_WRITEPAGE_ACTIVATE; + goto redirty_out; + } + + /* Dentry blocks are controlled by checkpoint */ + if (S_ISDIR(inode->i_mode)) { + dec_page_count(sbi, F2FS_DIRTY_DENTS); + inode_dec_dirty_dents(inode); + err = do_write_data_page(page, &fio); + } else { + f2fs_lock_op(sbi); + + if (f2fs_has_inline_data(inode) || f2fs_may_inline(inode)) { + err = f2fs_write_inline_data(inode, page, offset); + f2fs_unlock_op(sbi); + goto out; + } else { + err = do_write_data_page(page, &fio); + } + + f2fs_unlock_op(sbi); + need_balance_fs = true; + } + if (err == -ENOENT) + goto out; + else if (err) + goto redirty_out; + + if (wbc->for_reclaim) + f2fs_submit_merged_bio(sbi, DATA, WRITE); + + clear_cold_data(page); +out: + unlock_page(page); + if (need_balance_fs) + f2fs_balance_fs(sbi); + return 0; + +redirty_out: + wbc->pages_skipped++; + set_page_dirty(page); + return err; +} + +#define MAX_DESIRED_PAGES_WP 4096 + +static int __f2fs_writepage(struct page *page, struct writeback_control *wbc, + void *data) +{ + struct address_space *mapping = data; + int ret = mapping->a_ops->writepage(page, wbc); + mapping_set_error(mapping, ret); + return ret; +} + +static int f2fs_write_data_pages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct inode *inode = mapping->host; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + bool locked = false; + int ret; + long excess_nrtw = 0, desired_nrtw; + + /* deal with chardevs and other special file */ + if (!mapping->a_ops->writepage) + return 0; + + if (wbc->nr_to_write < MAX_DESIRED_PAGES_WP) { + desired_nrtw = MAX_DESIRED_PAGES_WP; + excess_nrtw = desired_nrtw - wbc->nr_to_write; + wbc->nr_to_write = desired_nrtw; + } + + if (!S_ISDIR(inode->i_mode)) { + mutex_lock(&sbi->writepages); + locked = true; + } + ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping); + if (locked) + mutex_unlock(&sbi->writepages); + + f2fs_submit_merged_bio(sbi, DATA, WRITE); + + remove_dirty_dir_inode(inode); + + wbc->nr_to_write -= excess_nrtw; + return ret; +} + +static int f2fs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) +{ + struct inode *inode = mapping->host; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct page *page; + pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT; + struct dnode_of_data dn; + int err = 0; + + f2fs_balance_fs(sbi); +repeat: + err = f2fs_convert_inline_data(inode, pos + len); + if (err) + return err; + + page = grab_cache_page_write_begin(mapping, index, flags); + if (!page) + return -ENOMEM; + *pagep = page; + + if (f2fs_has_inline_data(inode) && (pos + len) <= MAX_INLINE_DATA) + goto inline_data; + + f2fs_lock_op(sbi); + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = f2fs_reserve_block(&dn, index); + f2fs_unlock_op(sbi); + + if (err) { + f2fs_put_page(page, 1); + return err; + } +inline_data: + if ((len == PAGE_CACHE_SIZE) || PageUptodate(page)) + return 0; + + if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) { + unsigned start = pos & (PAGE_CACHE_SIZE - 1); + unsigned end = start + len; + + /* Reading beyond i_size is simple: memset to zero */ + zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE); + goto out; + } + + if (dn.data_blkaddr == NEW_ADDR) { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + } else { + if (f2fs_has_inline_data(inode)) + err = f2fs_read_inline_data(inode, page); + else + err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr, + READ_SYNC); + if (err) + return err; + lock_page(page); + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 1); + return -EIO; + } + if (unlikely(page->mapping != mapping)) { + f2fs_put_page(page, 1); + goto repeat; + } + } +out: + SetPageUptodate(page); + clear_cold_data(page); + return 0; +} + +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; + + SetPageUptodate(page); + set_page_dirty(page); + + if (pos + copied > i_size_read(inode)) { + i_size_write(inode, pos + copied); + mark_inode_dirty(inode); + update_inode_page(inode); + } + + f2fs_put_page(page, 1); + return copied; +} + +static int check_direct_IO(struct inode *inode, int rw, + const struct iovec *iov, loff_t offset, unsigned long nr_segs) +{ + unsigned blocksize_mask = inode->i_sb->s_blocksize - 1; + int i; + + if (rw == READ) + return 0; + + if (offset & blocksize_mask) + return -EINVAL; + + for (i = 0; i < nr_segs; i++) + if (iov[i].iov_len & blocksize_mask) + return -EINVAL; + return 0; +} + +static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb, + const struct iovec *iov, loff_t offset, unsigned long nr_segs) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + + /* Let buffer I/O handle the inline data case. */ + if (f2fs_has_inline_data(inode)) + return 0; + + if (check_direct_IO(inode, rw, iov, offset, nr_segs)) + return 0; + + return blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + get_data_block); +} + +static void f2fs_invalidate_data_page(struct page *page, unsigned int offset, + unsigned int length) +{ + struct inode *inode = page->mapping->host; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + if (S_ISDIR(inode->i_mode) && PageDirty(page)) { + dec_page_count(sbi, F2FS_DIRTY_DENTS); + inode_dec_dirty_dents(inode); + } + ClearPagePrivate(page); +} + +static int f2fs_release_data_page(struct page *page, gfp_t wait) +{ + ClearPagePrivate(page); + return 1; +} + +static int f2fs_set_data_page_dirty(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct inode *inode = mapping->host; + + trace_f2fs_set_page_dirty(page, DATA); + + SetPageUptodate(page); + if (!PageDirty(page)) { + __set_page_dirty_nobuffers(page); + set_dirty_dir_page(inode, page); + return 1; + } + return 0; +} + +static sector_t f2fs_bmap(struct address_space *mapping, sector_t block) +{ + return generic_block_bmap(mapping, block, get_data_block); +} + +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_data_page, + .releasepage = f2fs_release_data_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..711a0d4 --- /dev/null +++ b/fs/f2fs/debug.c @@ -0,0 +1,374 @@ +/* + * 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 + * + * 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 +#include +#include +#include +#include +#include + +#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; + + /* valid check of the segment numbers */ + si->hit_ext = sbi->read_hit_ext; + si->total_ext = sbi->total_hit_ext; + si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES); + si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS); + si->ndirty_dirs = sbi->n_dirty_dirs; + si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META); + si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg; + si->rsvd_segs = reserved_segments(sbi); + si->overp_segs = overprovision_segments(sbi); + si->valid_count = valid_user_blocks(sbi); + si->valid_node_count = valid_node_count(sbi); + si->valid_inode_count = valid_inode_count(sbi); + si->inline_inode = sbi->inline_inode; + si->utilization = utilization(sbi); + + si->free_segs = free_segments(sbi); + si->free_secs = free_sections(sbi); + si->prefree_count = prefree_segments(sbi); + si->dirty_count = dirty_segments(sbi); + si->node_pages = sbi->node_inode->i_mapping->nrpages; + si->meta_pages = sbi->meta_inode->i_mapping->nrpages; + si->nats = NM_I(sbi)->nat_cnt; + si->sits = SIT_I(sbi)->dirty_sentries; + si->fnids = NM_I(sbi)->fcnt; + si->bg_gc = sbi->bg_gc; + si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg) + * 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg) + / 2; + si->util_valid = (int)(written_block_count(sbi) >> + sbi->log_blocks_per_seg) + * 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg) + / 2; + si->util_invalid = 50 - si->util_free - si->util_valid; + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_NODE; i++) { + struct curseg_info *curseg = CURSEG_I(sbi, i); + si->curseg[i] = curseg->segno; + si->cursec[i] = curseg->segno / sbi->segs_per_sec; + si->curzone[i] = si->cursec[i] / sbi->secs_per_zone; + } + + for (i = 0; i < 2; i++) { + si->segment_count[i] = sbi->segment_count[i]; + si->block_count[i] = sbi->block_count[i]; + } +} + +/* + * This function calculates BDF of every segments + */ +static void update_sit_info(struct f2fs_sb_info *sbi) +{ + struct f2fs_stat_info *si = F2FS_STAT(sbi); + unsigned int blks_per_sec, hblks_per_sec, total_vblocks, bimodal, dist; + struct sit_info *sit_i = SIT_I(sbi); + unsigned int segno, vblocks; + int ndirty = 0; + + bimodal = 0; + total_vblocks = 0; + blks_per_sec = sbi->segs_per_sec * (1 << sbi->log_blocks_per_seg); + hblks_per_sec = blks_per_sec / 2; + mutex_lock(&sit_i->sentry_lock); + for (segno = 0; segno < TOTAL_SEGS(sbi); segno += sbi->segs_per_sec) { + vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec); + dist = abs(vblocks - hblks_per_sec); + bimodal += dist * dist; + + if (vblocks > 0 && vblocks < blks_per_sec) { + total_vblocks += vblocks; + ndirty++; + } + } + mutex_unlock(&sit_i->sentry_lock); + dist = TOTAL_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100; + si->bimodal = bimodal / dist; + if (si->dirty_count) + si->avg_vblocks = total_vblocks / ndirty; + else + si->avg_vblocks = 0; +} + +/* + * This function calculates memory footprint. + */ +static void update_mem_info(struct f2fs_sb_info *sbi) +{ + struct f2fs_stat_info *si = F2FS_STAT(sbi); + unsigned npages; + + if (si->base_mem) + goto get_cache; + + si->base_mem = sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize; + si->base_mem += 2 * sizeof(struct f2fs_inode_info); + si->base_mem += sizeof(*sbi->ckpt); + + /* build sm */ + si->base_mem += sizeof(struct f2fs_sm_info); + + /* build sit */ + si->base_mem += sizeof(struct sit_info); + si->base_mem += TOTAL_SEGS(sbi) * sizeof(struct seg_entry); + si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi)); + si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * TOTAL_SEGS(sbi); + if (sbi->segs_per_sec > 1) + si->base_mem += TOTAL_SECS(sbi) * sizeof(struct sec_entry); + si->base_mem += __bitmap_size(sbi, SIT_BITMAP); + + /* build free segmap */ + si->base_mem += sizeof(struct free_segmap_info); + si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi)); + si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi)); + + /* build curseg */ + si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE; + si->base_mem += PAGE_CACHE_SIZE * NR_CURSEG_TYPE; + + /* build dirty segmap */ + si->base_mem += sizeof(struct dirty_seglist_info); + si->base_mem += NR_DIRTY_TYPE * f2fs_bitmap_size(TOTAL_SEGS(sbi)); + si->base_mem += f2fs_bitmap_size(TOTAL_SECS(sbi)); + + /* buld nm */ + si->base_mem += sizeof(struct f2fs_nm_info); + si->base_mem += __bitmap_size(sbi, NAT_BITMAP); + + /* build gc */ + si->base_mem += sizeof(struct f2fs_gc_kthread); + +get_cache: + /* free nids */ + si->cache_mem = NM_I(sbi)->fcnt; + si->cache_mem += NM_I(sbi)->nat_cnt; + npages = sbi->node_inode->i_mapping->nrpages; + si->cache_mem += npages << PAGE_CACHE_SHIFT; + npages = sbi->meta_inode->i_mapping->nrpages; + si->cache_mem += npages << PAGE_CACHE_SHIFT; + si->cache_mem += sbi->n_orphans * sizeof(struct orphan_inode_entry); + si->cache_mem += sbi->n_dirty_dirs * sizeof(struct dir_inode_entry); +} + +static int stat_show(struct seq_file *s, void *v) +{ + struct f2fs_stat_info *si; + int i = 0; + int j; + + mutex_lock(&f2fs_stat_mutex); + list_for_each_entry(si, &f2fs_stat_list, stat_list) { + char devname[BDEVNAME_SIZE]; + + update_general_status(si->sbi); + + seq_printf(s, "\n=====[ partition info(%s). #%d ]=====\n", + bdevname(si->sbi->sb->s_bdev, devname), i++); + seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ", + si->sit_area_segs, si->nat_area_segs); + seq_printf(s, "[SSA: %d] [MAIN: %d", + si->ssa_area_segs, si->main_area_segs); + seq_printf(s, "(OverProv:%d Resv:%d)]\n\n", + si->overp_segs, si->rsvd_segs); + seq_printf(s, "Utilization: %d%% (%d valid blocks)\n", + si->utilization, si->valid_count); + seq_printf(s, " - Node: %u (Inode: %u, ", + si->valid_node_count, si->valid_inode_count); + seq_printf(s, "Other: %u)\n - Data: %u\n", + si->valid_node_count - si->valid_inode_count, + si->valid_count - si->valid_node_count); + seq_printf(s, " - Inline_data Inode: %u\n", + si->inline_inode); + seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n", + si->main_area_segs, si->main_area_sections, + si->main_area_zones); + seq_printf(s, " - COLD data: %d, %d, %d\n", + si->curseg[CURSEG_COLD_DATA], + si->cursec[CURSEG_COLD_DATA], + si->curzone[CURSEG_COLD_DATA]); + seq_printf(s, " - WARM data: %d, %d, %d\n", + si->curseg[CURSEG_WARM_DATA], + si->cursec[CURSEG_WARM_DATA], + si->curzone[CURSEG_WARM_DATA]); + seq_printf(s, " - HOT data: %d, %d, %d\n", + si->curseg[CURSEG_HOT_DATA], + si->cursec[CURSEG_HOT_DATA], + si->curzone[CURSEG_HOT_DATA]); + seq_printf(s, " - Dir dnode: %d, %d, %d\n", + si->curseg[CURSEG_HOT_NODE], + si->cursec[CURSEG_HOT_NODE], + si->curzone[CURSEG_HOT_NODE]); + seq_printf(s, " - File dnode: %d, %d, %d\n", + si->curseg[CURSEG_WARM_NODE], + si->cursec[CURSEG_WARM_NODE], + si->curzone[CURSEG_WARM_NODE]); + seq_printf(s, " - Indir nodes: %d, %d, %d\n", + si->curseg[CURSEG_COLD_NODE], + si->cursec[CURSEG_COLD_NODE], + si->curzone[CURSEG_COLD_NODE]); + seq_printf(s, "\n - Valid: %d\n - Dirty: %d\n", + si->main_area_segs - si->dirty_count - + si->prefree_count - si->free_segs, + si->dirty_count); + seq_printf(s, " - Prefree: %d\n - Free: %d (%d)\n\n", + si->prefree_count, si->free_segs, si->free_secs); + seq_printf(s, "GC calls: %d (BG: %d)\n", + si->call_count, si->bg_gc); + seq_printf(s, " - data segments : %d\n", si->data_segs); + seq_printf(s, " - node segments : %d\n", si->node_segs); + seq_printf(s, "Try to move %d blocks\n", si->tot_blks); + seq_printf(s, " - data blocks : %d\n", si->data_blks); + seq_printf(s, " - node blocks : %d\n", si->node_blks); + seq_printf(s, "\nExtent Hit Ratio: %d / %d\n", + si->hit_ext, si->total_ext); + seq_printf(s, "\nBalancing F2FS Async:\n"); + seq_printf(s, " - nodes %4d in %4d\n", + si->ndirty_node, si->node_pages); + seq_printf(s, " - dents %4d in dirs:%4d\n", + si->ndirty_dent, si->ndirty_dirs); + seq_printf(s, " - meta %4d in %4d\n", + si->ndirty_meta, si->meta_pages); + seq_printf(s, " - NATs %5d > %lu\n", + si->nats, NM_WOUT_THRESHOLD); + seq_printf(s, " - SITs: %5d\n - free_nids: %5d\n", + si->sits, si->fnids); + seq_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, "SSR: %u blocks in %u segments\n", + si->block_count[SSR], si->segment_count[SSR]); + seq_printf(s, "LFS: %u blocks in %u segments\n", + si->block_count[LFS], si->segment_count[LFS]); + + /* segment usage info */ + update_sit_info(si->sbi); + seq_printf(s, "\nBDF: %u, avg. vblocks: %u\n", + si->bimodal, si->avg_vblocks); + + /* memory footprint */ + update_mem_info(si->sbi); + seq_printf(s, "\nMemory: %u KB = static: %u + cached: %u\n", + (si->base_mem + si->cache_mem) >> 10, + si->base_mem >> 10, si->cache_mem >> 10); + } + mutex_unlock(&f2fs_stat_mutex); + return 0; +} + +static int stat_open(struct inode *inode, struct file *file) +{ + return single_open(file, stat_show, inode->i_private); +} + +static const struct file_operations stat_fops = { + .open = stat_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +int f2fs_build_stats(struct f2fs_sb_info *sbi) +{ + struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); + struct f2fs_stat_info *si; + + 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; + + 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) + goto bail; + + file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, + NULL, &stat_fops); + if (!file) + goto free_debugfs_dir; + + return; + +free_debugfs_dir: + debugfs_remove(f2fs_debugfs_root); + +bail: + f2fs_debugfs_root = NULL; + return; +} + +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..f815ca0 --- /dev/null +++ b/fs/f2fs/dir.c @@ -0,0 +1,682 @@ +/* + * 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 +#include +#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) +{ + if (level < MAX_DIR_HASH_DEPTH / 2) + return 1 << level; + else + return 1 << ((MAX_DIR_HASH_DEPTH / 2) - 1); +} + +static unsigned int bucket_blocks(unsigned int level) +{ + if (level < MAX_DIR_HASH_DEPTH / 2) + return 2; + else + return 4; +} + +static unsigned char f2fs_filetype_table[F2FS_FT_MAX] = { + [F2FS_FT_UNKNOWN] = DT_UNKNOWN, + [F2FS_FT_REG_FILE] = DT_REG, + [F2FS_FT_DIR] = DT_DIR, + [F2FS_FT_CHRDEV] = DT_CHR, + [F2FS_FT_BLKDEV] = DT_BLK, + [F2FS_FT_FIFO] = DT_FIFO, + [F2FS_FT_SOCK] = DT_SOCK, + [F2FS_FT_SYMLINK] = DT_LNK, +}; + +#define S_SHIFT 12 +static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = { + [S_IFREG >> S_SHIFT] = F2FS_FT_REG_FILE, + [S_IFDIR >> S_SHIFT] = F2FS_FT_DIR, + [S_IFCHR >> S_SHIFT] = F2FS_FT_CHRDEV, + [S_IFBLK >> S_SHIFT] = F2FS_FT_BLKDEV, + [S_IFIFO >> S_SHIFT] = F2FS_FT_FIFO, + [S_IFSOCK >> S_SHIFT] = F2FS_FT_SOCK, + [S_IFLNK >> S_SHIFT] = F2FS_FT_SYMLINK, +}; + +static void set_de_type(struct f2fs_dir_entry *de, struct inode *inode) +{ + umode_t mode = inode->i_mode; + de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT]; +} + +static unsigned long dir_block_index(unsigned int level, unsigned int idx) +{ + unsigned long i; + unsigned long bidx = 0; + + for (i = 0; i < level; i++) + bidx += dir_buckets(i) * bucket_blocks(i); + bidx += idx * bucket_blocks(level); + return bidx; +} + +static bool early_match_name(const char *name, size_t namelen, + f2fs_hash_t namehash, struct f2fs_dir_entry *de) +{ + if (le16_to_cpu(de->name_len) != namelen) + return false; + + if (de->hash_code != namehash) + return false; + + return true; +} + +static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, + const char *name, size_t namelen, int *max_slots, + f2fs_hash_t namehash, struct page **res_page) +{ + struct f2fs_dir_entry *de; + unsigned long bit_pos, end_pos, next_pos; + struct f2fs_dentry_block *dentry_blk = kmap(dentry_page); + int slots; + + bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, + NR_DENTRY_IN_BLOCK, 0); + while (bit_pos < NR_DENTRY_IN_BLOCK) { + de = &dentry_blk->dentry[bit_pos]; + slots = GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); + + if (early_match_name(name, namelen, namehash, de)) { + if (!memcmp(dentry_blk->filename[bit_pos], + name, namelen)) { + *res_page = dentry_page; + goto found; + } + } + next_pos = bit_pos + slots; + bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, + NR_DENTRY_IN_BLOCK, next_pos); + if (bit_pos >= NR_DENTRY_IN_BLOCK) + end_pos = NR_DENTRY_IN_BLOCK; + else + end_pos = bit_pos; + if (*max_slots < end_pos - next_pos) + *max_slots = end_pos - next_pos; + } + + de = NULL; + kunmap(dentry_page); +found: + return de; +} + +static struct f2fs_dir_entry *find_in_level(struct inode *dir, + unsigned int level, const char *name, size_t namelen, + f2fs_hash_t namehash, struct page **res_page) +{ + int s = GET_DENTRY_SLOTS(namelen); + unsigned int nbucket, nblock; + unsigned int bidx, end_block; + struct page *dentry_page; + struct f2fs_dir_entry *de = NULL; + bool room = false; + int max_slots = 0; + + f2fs_bug_on(level > MAX_DIR_HASH_DEPTH); + + nbucket = dir_buckets(level); + nblock = bucket_blocks(level); + + bidx = dir_block_index(level, le32_to_cpu(namehash) % nbucket); + end_block = bidx + nblock; + + for (; bidx < end_block; bidx++) { + /* no need to allocate new dentry pages to all the indices */ + dentry_page = find_data_page(dir, bidx, true); + if (IS_ERR(dentry_page)) { + room = true; + continue; + } + + de = find_in_block(dentry_page, name, namelen, + &max_slots, namehash, res_page); + if (de) + break; + + if (max_slots >= s) + room = true; + f2fs_put_page(dentry_page, 0); + } + + if (!de && room && F2FS_I(dir)->chash != namehash) { + F2FS_I(dir)->chash = namehash; + F2FS_I(dir)->clevel = level; + } + + return de; +} + +/* + * Find an entry in the specified directory with the wanted name. + * It returns the page where the entry was found (as a parameter - res_page), + * and the entry itself. Page is returned mapped and unlocked. + * Entry is guaranteed to be valid. + */ +struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir, + struct qstr *child, struct page **res_page) +{ + const char *name = child->name; + size_t namelen = child->len; + unsigned long npages = dir_blocks(dir); + struct f2fs_dir_entry *de = NULL; + f2fs_hash_t name_hash; + unsigned int max_depth; + unsigned int level; + + if (npages == 0) + return NULL; + + *res_page = NULL; + + name_hash = f2fs_dentry_hash(name, namelen); + max_depth = F2FS_I(dir)->i_current_depth; + + for (level = 0; level < max_depth; level++) { + de = find_in_level(dir, level, name, + namelen, name_hash, res_page); + if (de) + break; + } + if (!de && F2FS_I(dir)->chash != name_hash) { + F2FS_I(dir)->chash = name_hash; + F2FS_I(dir)->clevel = level - 1; + } + return de; +} + +struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p) +{ + struct page *page; + struct f2fs_dir_entry *de; + struct f2fs_dentry_block *dentry_blk; + + page = get_lock_data_page(dir, 0); + if (IS_ERR(page)) + return NULL; + + dentry_blk = kmap(page); + de = &dentry_blk->dentry[1]; + *p = page; + unlock_page(page); + return de; +} + +ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr) +{ + ino_t res = 0; + struct f2fs_dir_entry *de; + struct page *page; + + de = f2fs_find_entry(dir, qstr, &page); + if (de) { + res = le32_to_cpu(de->ino); + kunmap(page); + f2fs_put_page(page, 0); + } + + return res; +} + +void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de, + struct page *page, struct inode *inode) +{ + lock_page(page); + wait_on_page_writeback(page); + de->ino = cpu_to_le32(inode->i_ino); + set_de_type(de, inode); + kunmap(page); + set_page_dirty(page); + dir->i_mtime = dir->i_ctime = CURRENT_TIME; + mark_inode_dirty(dir); + + f2fs_put_page(page, 1); +} + +static void init_dent_inode(const struct qstr *name, struct page *ipage) +{ + struct f2fs_inode *ri; + + /* copy name info. to this inode page */ + ri = F2FS_INODE(ipage); + ri->i_namelen = cpu_to_le32(name->len); + memcpy(ri->i_name, name->name, name->len); + set_page_dirty(ipage); +} + +int update_dent_inode(struct inode *inode, const struct qstr *name) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct page *page; + + page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(page)) + return PTR_ERR(page); + + init_dent_inode(name, page); + f2fs_put_page(page, 1); + + return 0; +} + +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_dir_entry *de; + void *kaddr; + + dentry_page = get_new_data_page(inode, page, 0, true); + if (IS_ERR(dentry_page)) + return PTR_ERR(dentry_page); + + kaddr = kmap_atomic(dentry_page); + dentry_blk = (struct f2fs_dentry_block *)kaddr; + + de = &dentry_blk->dentry[0]; + de->name_len = cpu_to_le16(1); + de->hash_code = 0; + de->ino = cpu_to_le32(inode->i_ino); + memcpy(dentry_blk->filename[0], ".", 1); + set_de_type(de, inode); + + de = &dentry_blk->dentry[1]; + de->hash_code = 0; + de->name_len = cpu_to_le16(2); + de->ino = cpu_to_le32(parent->i_ino); + memcpy(dentry_blk->filename[1], "..", 2); + set_de_type(de, inode); + + test_and_set_bit_le(0, &dentry_blk->dentry_bitmap); + test_and_set_bit_le(1, &dentry_blk->dentry_bitmap); + kunmap_atomic(kaddr); + + set_page_dirty(dentry_page); + f2fs_put_page(dentry_page, 1); + return 0; +} + +static struct page *init_inode_metadata(struct inode *inode, + struct inode *dir, const struct qstr *name) +{ + struct page *page; + int err; + + if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) { + page = new_inode_page(inode, name); + 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); + if (err) + goto put_error; + + err = f2fs_init_security(inode, dir, name, page); + if (err) + goto put_error; + + wait_on_page_writeback(page); + } else { + page = get_node_page(F2FS_SB(dir->i_sb), inode->i_ino); + if (IS_ERR(page)) + return page; + + wait_on_page_writeback(page); + set_cold_node(inode, page); + } + + 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); + inc_nlink(inode); + } + return page; + +put_error: + f2fs_put_page(page, 1); +error: + remove_inode_page(inode); + return ERR_PTR(err); +} + +static void update_parent_metadata(struct inode *dir, struct inode *inode, + unsigned int current_depth) +{ + if (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; + 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 (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) + update_inode_page(dir); + else + mark_inode_dirty(dir); + + if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) + clear_inode_flag(F2FS_I(inode), FI_INC_LINK); +} + +static int room_for_filename(struct f2fs_dentry_block *dentry_blk, int slots) +{ + int bit_start = 0; + int zero_start, zero_end; +next: + zero_start = find_next_zero_bit_le(&dentry_blk->dentry_bitmap, + NR_DENTRY_IN_BLOCK, + bit_start); + if (zero_start >= NR_DENTRY_IN_BLOCK) + return NR_DENTRY_IN_BLOCK; + + zero_end = find_next_bit_le(&dentry_blk->dentry_bitmap, + NR_DENTRY_IN_BLOCK, + zero_start); + if (zero_end - zero_start >= slots) + return zero_start; + + bit_start = zero_end + 1; + + if (zero_end + 1 >= NR_DENTRY_IN_BLOCK) + return NR_DENTRY_IN_BLOCK; + goto next; +} + +/* + * Caller should grab and release a rwsem by calling f2fs_lock_op() and + * f2fs_unlock_op(). + */ +int __f2fs_add_link(struct inode *dir, const struct qstr *name, struct inode *inode) +{ + unsigned int bit_pos; + unsigned int level; + unsigned int current_depth; + unsigned long bidx, block; + f2fs_hash_t dentry_hash; + struct f2fs_dir_entry *de; + unsigned int nbucket, nblock; + size_t namelen = name->len; + struct page *dentry_page = NULL; + struct f2fs_dentry_block *dentry_blk = NULL; + int slots = GET_DENTRY_SLOTS(namelen); + struct page *page; + int err = 0; + int i; + + dentry_hash = f2fs_dentry_hash(name->name, name->len); + level = 0; + current_depth = F2FS_I(dir)->i_current_depth; + if (F2FS_I(dir)->chash == dentry_hash) { + level = F2FS_I(dir)->clevel; + F2FS_I(dir)->chash = 0; + } + +start: + if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) + return -ENOSPC; + + /* Increase the depth, if required */ + if (level == current_depth) + ++current_depth; + + nbucket = dir_buckets(level); + nblock = bucket_blocks(level); + + bidx = dir_block_index(level, (le32_to_cpu(dentry_hash) % nbucket)); + + for (block = bidx; block <= (bidx + nblock - 1); block++) { + dentry_page = get_new_data_page(dir, NULL, block, true); + if (IS_ERR(dentry_page)) + return PTR_ERR(dentry_page); + + dentry_blk = kmap(dentry_page); + bit_pos = room_for_filename(dentry_blk, slots); + if (bit_pos < NR_DENTRY_IN_BLOCK) + goto add_dentry; + + kunmap(dentry_page); + f2fs_put_page(dentry_page, 1); + } + + /* Move to next level to find the empty slot for new dentry */ + ++level; + goto start; +add_dentry: + wait_on_page_writeback(dentry_page); + + page = init_inode_metadata(inode, dir, name); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto fail; + } + de = &dentry_blk->dentry[bit_pos]; + de->hash_code = dentry_hash; + de->name_len = cpu_to_le16(namelen); + memcpy(dentry_blk->filename[bit_pos], name->name, name->len); + de->ino = cpu_to_le32(inode->i_ino); + set_de_type(de, inode); + for (i = 0; i < slots; i++) + test_and_set_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap); + set_page_dirty(dentry_page); + + /* 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: + clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR); + kunmap(dentry_page); + f2fs_put_page(dentry_page, 1); + return err; +} + +/* + * It only removes the dentry from the dentry page,corresponding name + * entry in name page does not need to be touched during deletion. + */ +void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, + struct inode *inode) +{ + struct f2fs_dentry_block *dentry_blk; + unsigned int bit_pos; + struct address_space *mapping = page->mapping; + struct inode *dir = mapping->host; + struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); + int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); + void *kaddr = page_address(page); + int i; + + lock_page(page); + wait_on_page_writeback(page); + + dentry_blk = (struct f2fs_dentry_block *)kaddr; + bit_pos = dentry - (struct f2fs_dir_entry *)dentry_blk->dentry; + for (i = 0; i < slots; i++) + test_and_clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap); + + /* Let's check and deallocate this dentry page */ + bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, + NR_DENTRY_IN_BLOCK, + 0); + kunmap(page); /* kunmap - pair of f2fs_find_entry */ + set_page_dirty(page); + + dir->i_ctime = dir->i_mtime = CURRENT_TIME; + + if (inode && S_ISDIR(inode->i_mode)) { + drop_nlink(dir); + update_inode_page(dir); + } else { + mark_inode_dirty(dir); + } + + if (inode) { + inode->i_ctime = CURRENT_TIME; + drop_nlink(inode); + if (S_ISDIR(inode->i_mode)) { + drop_nlink(inode); + i_size_write(inode, 0); + } + update_inode_page(inode); + + if (inode->i_nlink == 0) + add_orphan_inode(sbi, inode->i_ino); + else + release_orphan_inode(sbi); + } + + if (bit_pos == NR_DENTRY_IN_BLOCK) { + truncate_hole(dir, page->index, page->index + 1); + clear_page_dirty_for_io(page); + ClearPageUptodate(page); + dec_page_count(sbi, F2FS_DIRTY_DENTS); + inode_dec_dirty_dents(dir); + } + f2fs_put_page(page, 1); +} + +bool f2fs_empty_dir(struct inode *dir) +{ + unsigned long bidx; + struct page *dentry_page; + unsigned int bit_pos; + struct f2fs_dentry_block *dentry_blk; + unsigned long nblock = dir_blocks(dir); + + for (bidx = 0; bidx < nblock; bidx++) { + void *kaddr; + dentry_page = get_lock_data_page(dir, bidx); + if (IS_ERR(dentry_page)) { + if (PTR_ERR(dentry_page) == -ENOENT) + continue; + else + return false; + } + + kaddr = kmap_atomic(dentry_page); + dentry_blk = (struct f2fs_dentry_block *)kaddr; + if (bidx == 0) + bit_pos = 2; + else + bit_pos = 0; + bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, + NR_DENTRY_IN_BLOCK, + bit_pos); + kunmap_atomic(kaddr); + + f2fs_put_page(dentry_page, 1); + + if (bit_pos < NR_DENTRY_IN_BLOCK) + return false; + } + return true; +} + +static int f2fs_readdir(struct file *file, struct dir_context *ctx) +{ + struct inode *inode = file_inode(file); + unsigned long npages = dir_blocks(inode); + unsigned int bit_pos = 0; + struct f2fs_dentry_block *dentry_blk = NULL; + struct f2fs_dir_entry *de = NULL; + struct page *dentry_page = NULL; + unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK); + unsigned char d_type = DT_UNKNOWN; + + bit_pos = ((unsigned long)ctx->pos % NR_DENTRY_IN_BLOCK); + + for ( ; n < npages; n++) { + dentry_page = get_lock_data_page(inode, n); + if (IS_ERR(dentry_page)) + continue; + + dentry_blk = kmap(dentry_page); + while (bit_pos < NR_DENTRY_IN_BLOCK) { + bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, + NR_DENTRY_IN_BLOCK, + bit_pos); + if (bit_pos >= NR_DENTRY_IN_BLOCK) + break; + + de = &dentry_blk->dentry[bit_pos]; + if (de->file_type < F2FS_FT_MAX) + d_type = f2fs_filetype_table[de->file_type]; + else + d_type = DT_UNKNOWN; + if (!dir_emit(ctx, + dentry_blk->filename[bit_pos], + le16_to_cpu(de->name_len), + le32_to_cpu(de->ino), d_type)) + goto stop; + + bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); + ctx->pos = n * NR_DENTRY_IN_BLOCK + bit_pos; + } + bit_pos = 0; + ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK; + kunmap(dentry_page); + f2fs_put_page(dentry_page, 1); + dentry_page = NULL; + } +stop: + if (dentry_page && !IS_ERR(dentry_page)) { + kunmap(dentry_page); + f2fs_put_page(dentry_page, 1); + } + + return 0; +} + +const struct file_operations f2fs_dir_operations = { + .llseek = generic_file_llseek, + .read = generic_read_dir, + .iterate = f2fs_readdir, + .fsync = f2fs_sync_file, + .unlocked_ioctl = f2fs_ioctl, +}; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h new file mode 100644 index 0000000..07a7ae0 --- /dev/null +++ b/fs/f2fs/f2fs.h @@ -0,0 +1,1327 @@ +/* + * 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 +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_F2FS_CHECK_FS +#define f2fs_bug_on(condition) BUG_ON(condition) +#define f2fs_down_write(x, y) down_write_nest_lock(x, y) +#else +#define f2fs_bug_on(condition) +#define f2fs_down_write(x, y) down_write(x) +#endif + +/* + * For mount options + */ +#define F2FS_MOUNT_BG_GC 0x00000001 +#define F2FS_MOUNT_DISABLE_ROLL_FORWARD 0x00000002 +#define F2FS_MOUNT_DISCARD 0x00000004 +#define F2FS_MOUNT_NOHEAP 0x00000008 +#define F2FS_MOUNT_XATTR_USER 0x00000010 +#define F2FS_MOUNT_POSIX_ACL 0x00000020 +#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000040 +#define F2FS_MOUNT_INLINE_XATTR 0x00000080 +#define F2FS_MOUNT_INLINE_DATA 0x00000100 + +#define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option) +#define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option) +#define test_opt(sbi, option) (sbi->mount_opt.opt & F2FS_MOUNT_##option) + +#define ver_after(a, b) (typecheck(unsigned long long, a) && \ + typecheck(unsigned long long, b) && \ + ((long long)((a) - (b)) > 0)) + +typedef u32 block_t; /* + * should not change u32, since it is the on-disk block + * address format, __le32. + */ +typedef u32 nid_t; + +struct f2fs_mount_info { + unsigned int opt; +}; + +#define CRCPOLY_LE 0xedb88320 + +static inline __u32 f2fs_crc32(void *buf, size_t len) +{ + unsigned char *p = (unsigned char *)buf; + __u32 crc = F2FS_SUPER_MAGIC; + int i; + + while (len--) { + crc ^= *p++; + for (i = 0; i < 8; i++) + crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0); + } + return crc; +} + +static inline bool f2fs_crc_valid(__u32 blk_crc, void *buf, size_t buf_size) +{ + return f2fs_crc32(buf, buf_size) == blk_crc; +} + +/* + * For checkpoint manager + */ +enum { + NAT_BITMAP, + SIT_BITMAP +}; + +/* for the list of orphan inodes */ +struct orphan_inode_entry { + struct list_head list; /* list head */ + nid_t ino; /* inode number */ +}; + +/* for the list of directory inodes */ +struct dir_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 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) + +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; +} + +/* + * ioctl commands + */ +#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS +#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS + +#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 + */ +/* + * XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1 + * as its node offset to distinguish from index node blocks. + * But some bits are used to mark the node block. + */ +#define XATTR_NODE_OFFSET ((((unsigned int)-1) << OFFSET_BIT_SHIFT) \ + >> OFFSET_BIT_SHIFT) +enum { + ALLOC_NODE, /* allocate a new node page if needed */ + LOOKUP_NODE, /* look up a node without readahead */ + LOOKUP_NODE_RA, /* + * look up a node with readahead called + * by get_data_block. + */ +}; + +#define F2FS_LINK_MAX 32000 /* maximum link count per file */ + +/* for in-memory extent cache entry */ +#define F2FS_MIN_EXTENT_LEN 16 /* minimum extent length */ + +struct extent_info { + rwlock_t ext_lock; /* rwlock for consistency */ + unsigned int fofs; /* start offset in a file */ + u32 blk_addr; /* start block address of the extent */ + unsigned int len; /* length of the extent */ +}; + +/* + * i_advise uses FADVISE_XXX_BIT. We can add additional hints later. + */ +#define FADVISE_COLD_BIT 0x01 +#define FADVISE_LOST_PINO_BIT 0x02 + +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 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 */ + atomic_t dirty_dents; /* # of dirty dentry pages */ + f2fs_hash_t chash; /* hash value of given file name */ + unsigned int clevel; /* maximum level of given file name */ + nid_t i_xattr_nid; /* node id that contains xattrs */ + unsigned long long xattr_ver; /* cp version of xattr modification */ + struct extent_info ext; /* in-memory extent cache entry */ +}; + +static inline void get_extent_info(struct extent_info *ext, + struct f2fs_extent i_ext) +{ + write_lock(&ext->ext_lock); + ext->fofs = le32_to_cpu(i_ext.fofs); + ext->blk_addr = le32_to_cpu(i_ext.blk_addr); + ext->len = le32_to_cpu(i_ext.len); + write_unlock(&ext->ext_lock); +} + +static inline void set_raw_extent(struct extent_info *ext, + struct f2fs_extent *i_ext) +{ + read_lock(&ext->ext_lock); + i_ext->fofs = cpu_to_le32(ext->fofs); + i_ext->blk_addr = cpu_to_le32(ext->blk_addr); + i_ext->len = cpu_to_le32(ext->len); + read_unlock(&ext->ext_lock); +} + +struct f2fs_nm_info { + block_t nat_blkaddr; /* base disk address of NAT */ + nid_t max_nid; /* maximum possible node ids */ + nid_t next_scan_nid; /* the next nid to be scanned */ + + /* NAT cache management */ + struct radix_tree_root nat_root;/* root of the nat entry cache */ + rwlock_t nat_tree_lock; /* protect nat_tree_lock */ + unsigned int nat_cnt; /* the # of cached nat entries */ + struct list_head nat_entries; /* cached nat entry list (clean) */ + struct list_head dirty_nat_entries; /* cached nat entry list (dirty) */ + + /* free node ids management */ + 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 +}; + +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 */ + + struct list_head wblist_head; /* list of under-writeback pages */ + spinlock_t wblist_lock; /* lock for checkpoint */ + + 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 */ + + unsigned int ipu_policy; /* in-place-update policy */ + unsigned int min_ipu_util; /* in-place-update threshold */ +}; + +/* + * 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, + NR_COUNT_TYPE, +}; + +/* + * The below are the page types of bios used in submti_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, +}; + +struct f2fs_io_info { + enum page_type type; /* contains DATA/NODE/META/META_FLUSH */ + int rw; /* contains R/RS/W/WS with REQ_META/REQ_PRIO */ +}; + +#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 mutex io_mutex; /* mutex for bio */ +}; + +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_dirty; /* dirty flag for checkpoint */ + + /* 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 mutex node_write; /* locking node writes */ + struct mutex writepages; /* mutex for writepages() */ + bool por_doing; /* recovery is doing or not */ + bool on_build_free_nids; /* build_free_nids is doing */ + wait_queue_head_t cp_wait; + + /* for orphan inode management */ + struct list_head orphan_inode_list; /* orphan inode list */ + struct mutex orphan_inode_mutex; /* for orphan inode list */ + unsigned int n_orphans; /* # of orphan inodes */ + 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 */ + + /* basic file system 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 */ + + block_t user_block_count; /* # of user blocks */ + block_t total_valid_block_count; /* # of valid blocks */ + block_t alloc_valid_block_count; /* # of allocated blocks */ + block_t last_valid_block_count; /* for recovery */ + u32 s_next_generation; /* for NFS support */ + atomic_t nr_pages[NR_COUNT_TYPE]; /* # of pages, see count_type */ + + struct f2fs_mount_info mount_opt; /* mount options */ + + /* for cleaning operations */ + struct mutex gc_mutex; /* mutex for GC */ + struct f2fs_gc_kthread *gc_thread; /* GC thread */ + unsigned int cur_victim_sec; /* current victim section num */ + + /* + * 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 */ + int total_hit_ext, read_hit_ext; /* extent cache hit ratio */ + int inline_inode; /* # of inline_data inodes */ + int bg_gc; /* background gc calls */ + unsigned int n_dirty_dirs; /* # of dir inodes */ +#endif + unsigned int last_victim[2]; /* last victim segment # */ + spinlock_t stat_lock; /* lock for stat operations */ + + /* For sysfs suppport */ + struct kobject s_kobj; + struct completion s_kobj_unregister; +}; + +/* + * Inline functions + */ +static inline struct f2fs_inode_info *F2FS_I(struct inode *inode) +{ + return container_of(inode, struct f2fs_inode_info, vfs_inode); +} + +static inline struct f2fs_sb_info *F2FS_SB(struct super_block *sb) +{ + return sb->s_fs_info; +} + +static inline struct f2fs_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 void F2FS_SET_SB_DIRT(struct f2fs_sb_info *sbi) +{ + sbi->s_dirty = 1; +} + +static inline void F2FS_RESET_SB_DIRT(struct f2fs_sb_info *sbi) +{ + sbi->s_dirty = 0; +} + +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); +} + +/* + * Check whether the given nid is within node id range. + */ +static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) +{ + WARN_ON((nid >= NM_I(sbi)->max_nid)); + 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 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->total_valid_block_count < (block_t) count); + f2fs_bug_on(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]); + F2FS_SET_SB_DIRT(sbi); +} + +static inline void inode_inc_dirty_dents(struct inode *inode) +{ + atomic_inc(&F2FS_I(inode)->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_dents(struct inode *inode) +{ + atomic_dec(&F2FS_I(inode)->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_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) +{ + block_t ret; + spin_lock(&sbi->stat_lock); + ret = sbi->total_valid_block_count; + spin_unlock(&sbi->stat_lock); + return ret; +} + +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 void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + int 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 segent 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->total_valid_block_count); + f2fs_bug_on(!sbi->total_valid_node_count); + f2fs_bug_on(!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) +{ + unsigned int ret; + spin_lock(&sbi->stat_lock); + ret = sbi->total_valid_node_count; + spin_unlock(&sbi->stat_lock); + return ret; +} + +static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi) +{ + spin_lock(&sbi->stat_lock); + f2fs_bug_on(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->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) +{ + unsigned int ret; + spin_lock(&sbi->stat_lock); + ret = sbi->total_valid_inode_count; + spin_unlock(&sbi->stat_lock); + return ret; +} + +static inline void f2fs_put_page(struct page *page, int unlock) +{ + if (!page) + return; + + if (unlock) { + f2fs_bug_on(!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, void (*ctor)(void *)) +{ + return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, ctor); +} + +static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep, + gfp_t flags) +{ + void *entry; +retry: + entry = kmem_cache_alloc(cachep, flags); + if (!entry) { + cond_resched(); + goto retry; + } + + return entry; +} + +#define RAW_IS_INODE(p) ((p)->footer.nid == (p)->footer.ino) + +static inline bool IS_INODE(struct page *page) +{ + struct f2fs_node *p = F2FS_NODE(page); + return RAW_IS_INODE(p); +} + +static inline __le32 *blkaddr_in_node(struct f2fs_node *node) +{ + return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr; +} + +static inline block_t datablock_addr(struct page *node_page, + unsigned int offset) +{ + struct f2fs_node *raw_node; + __le32 *addr_array; + raw_node = F2FS_NODE(node_page); + addr_array = blkaddr_in_node(raw_node); + return le32_to_cpu(addr_array[offset]); +} + +static inline int f2fs_test_bit(unsigned int nr, char *addr) +{ + int mask; + + addr += (nr >> 3); + mask = 1 << (7 - (nr & 0x07)); + return mask & *addr; +} + +static inline int f2fs_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_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; +} + +/* used for f2fs_inode_info->flags */ +enum { + FI_NEW_INODE, /* indicate newly allocated inode */ + FI_DIRTY_INODE, /* indicate inode is dirty or not */ + FI_INC_LINK, /* need to increment i_nlink */ + FI_ACL_MODE, /* indicate acl mode */ + FI_NO_ALLOC, /* should not allocate any blocks */ + FI_UPDATE_DIR, /* should update inode block for consistency */ + FI_DELAY_IPUT, /* used for the recovery */ + FI_NO_EXTENT, /* not to use the extent cache */ + FI_INLINE_XATTR, /* used for inline xattr */ + FI_INLINE_DATA, /* used for inline data*/ +}; + +static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag) +{ + 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) +{ + 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 int cond_clear_inode_flag(struct f2fs_inode_info *fi, int flag) +{ + if (is_inode_flag_set(fi, FI_ACL_MODE)) { + clear_inode_flag(fi, FI_ACL_MODE); + return 1; + } + return 0; +} + +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); +} + +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; +} + +static inline unsigned int addrs_per_inode(struct f2fs_inode_info *fi) +{ + if (is_inode_flag_set(fi, FI_INLINE_XATTR)) + 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; + ri = (struct f2fs_inode *)page_address(page); + return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE - + F2FS_INLINE_XATTR_ADDRS]); +} + +static inline int inline_xattr_size(struct inode *inode) +{ + if (is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR)) + 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 *inline_data_addr(struct page *page) +{ + struct f2fs_inode *ri; + ri = (struct f2fs_inode *)page_address(page); + return (void *)&(ri->i_addr[1]); +} + +static inline int f2fs_readonly(struct super_block *sb) +{ + return sb->s_flags & MS_RDONLY; +} + +/* + * 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); +void f2fs_truncate(struct inode *); +int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *); +int f2fs_setattr(struct dentry *, struct iattr *); +int truncate_hole(struct inode *, pgoff_t, pgoff_t); +int truncate_data_blocks_range(struct dnode_of_data *, int); +long f2fs_ioctl(struct file *, unsigned int, unsigned long); +long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long); + +/* + * inode.c + */ +void f2fs_set_inode_flags(struct inode *); +struct inode *f2fs_iget(struct super_block *, unsigned long); +int try_to_free_nats(struct f2fs_sb_info *, int); +void update_inode(struct inode *, struct page *); +int update_inode_page(struct inode *); +int f2fs_write_inode(struct inode *, struct writeback_control *); +void f2fs_evict_inode(struct inode *); + +/* + * namei.c + */ +struct dentry *f2fs_get_parent(struct dentry *child); + +/* + * dir.c + */ +struct f2fs_dir_entry *f2fs_find_entry(struct inode *, struct qstr *, + struct page **); +struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **); +ino_t f2fs_inode_by_name(struct inode *, struct qstr *); +void f2fs_set_link(struct inode *, struct f2fs_dir_entry *, + struct page *, struct inode *); +int update_dent_inode(struct inode *, const struct qstr *); +int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *); +void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *); +int f2fs_make_empty(struct inode *, struct inode *); +bool f2fs_empty_dir(struct inode *); + +static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) +{ + return __f2fs_add_link(dentry->d_parent->d_inode, &dentry->d_name, + inode); +} + +/* + * super.c + */ +int f2fs_sync_fs(struct super_block *, int); +extern __printf(3, 4) +void f2fs_msg(struct super_block *, const char *, const char *, ...); + +/* + * hash.c + */ +f2fs_hash_t f2fs_dentry_hash(const char *, size_t); + +/* + * node.c + */ +struct dnode_of_data; +struct node_info; + +int is_checkpointed_node(struct f2fs_sb_info *, nid_t); +void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *); +int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int); +int truncate_inode_blocks(struct inode *, pgoff_t); +int truncate_xattr_node(struct inode *, struct page *); +int wait_on_node_pages_writeback(struct f2fs_sb_info *, nid_t); +void remove_inode_page(struct inode *); +struct page *new_inode_page(struct inode *, const struct qstr *); +struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *); +void ra_node_page(struct f2fs_sb_info *, nid_t); +struct page *get_node_page(struct f2fs_sb_info *, pgoff_t); +struct page *get_node_page_ra(struct page *, int); +void sync_inode_page(struct dnode_of_data *); +int sync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *); +bool alloc_nid(struct f2fs_sb_info *, nid_t *); +void alloc_nid_done(struct f2fs_sb_info *, nid_t); +void alloc_nid_failed(struct f2fs_sb_info *, nid_t); +void recover_node_page(struct f2fs_sb_info *, struct page *, + struct f2fs_summary *, struct node_info *, 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 f2fs_balance_fs(struct f2fs_sb_info *); +void f2fs_balance_fs_bg(struct f2fs_sb_info *); +void invalidate_blocks(struct f2fs_sb_info *, block_t); +void clear_prefree_segments(struct f2fs_sb_info *); +int npages_for_summary_flush(struct f2fs_sb_info *); +void allocate_new_segments(struct f2fs_sb_info *); +struct page *get_sum_page(struct f2fs_sb_info *, unsigned int); +void write_meta_page(struct f2fs_sb_info *, struct page *); +void write_node_page(struct f2fs_sb_info *, struct page *, unsigned int, + block_t, block_t *); +void write_data_page(struct page *, struct dnode_of_data *, block_t *, + struct f2fs_io_info *); +void rewrite_data_page(struct page *, block_t, struct f2fs_io_info *); +void recover_data_page(struct f2fs_sb_info *, struct page *, + struct f2fs_summary *, block_t, block_t); +void rewrite_node_page(struct f2fs_sb_info *, struct page *, + struct f2fs_summary *, block_t, block_t); +void allocate_data_block(struct f2fs_sb_info *, struct page *, + block_t, block_t *, struct f2fs_summary *, int); +void f2fs_wait_on_page_writeback(struct page *, enum page_type, bool); +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 *); +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); +long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long); +int acquire_orphan_inode(struct f2fs_sb_info *); +void release_orphan_inode(struct f2fs_sb_info *); +void add_orphan_inode(struct f2fs_sb_info *, nid_t); +void remove_orphan_inode(struct f2fs_sb_info *, nid_t); +void recover_orphan_inodes(struct f2fs_sb_info *); +int get_valid_checkpoint(struct f2fs_sb_info *); +void set_dirty_dir_page(struct inode *, struct page *); +void add_dirty_dir_inode(struct inode *); +void remove_dirty_dir_inode(struct inode *); +struct inode *check_dirty_dir_inode(struct f2fs_sb_info *, nid_t); +void sync_dirty_dir_inodes(struct f2fs_sb_info *); +void write_checkpoint(struct f2fs_sb_info *, bool); +void init_orphan_info(struct f2fs_sb_info *); +int __init create_checkpoint_caches(void); +void destroy_checkpoint_caches(void); + +/* + * data.c + */ +void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int); +int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *, block_t, int); +void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *, block_t, + struct f2fs_io_info *); +int reserve_new_block(struct dnode_of_data *); +int f2fs_reserve_block(struct dnode_of_data *, pgoff_t); +void update_extent_cache(block_t, struct dnode_of_data *); +struct page *find_data_page(struct inode *, pgoff_t, bool); +struct page *get_lock_data_page(struct inode *, pgoff_t); +struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool); +int do_write_data_page(struct page *, struct f2fs_io_info *); + +/* + * gc.c + */ +int start_gc_thread(struct f2fs_sb_info *); +void stop_gc_thread(struct f2fs_sb_info *); +block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *); +int f2fs_gc(struct f2fs_sb_info *); +void build_gc_manager(struct f2fs_sb_info *); +int __init create_gc_caches(void); +void destroy_gc_caches(void); + +/* + * 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; + struct mutex stat_lock; + int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs; + int main_area_segs, main_area_sections, main_area_zones; + int hit_ext, total_ext; + int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta; + int nats, sits, fnids; + int total_count, utilization; + int bg_gc, inline_inode; + 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; + int tot_segs, node_segs, data_segs, free_segs, free_secs; + int tot_blks, data_blks, 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 base_mem, cache_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_call_count(si) ((si)->call_count++) +#define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++) +#define stat_inc_dirty_dir(sbi) ((sbi)->n_dirty_dirs++) +#define stat_dec_dirty_dir(sbi) ((sbi)->n_dirty_dirs--) +#define stat_inc_total_hit(sb) ((F2FS_SB(sb))->total_hit_ext++) +#define stat_inc_read_hit(sb) ((F2FS_SB(sb))->read_hit_ext++) +#define stat_inc_inline_inode(inode) \ + do { \ + if (f2fs_has_inline_data(inode)) \ + ((F2FS_SB(inode->i_sb))->inline_inode++); \ + } while (0) +#define stat_dec_inline_inode(inode) \ + do { \ + if (f2fs_has_inline_data(inode)) \ + ((F2FS_SB(inode->i_sb))->inline_inode--); \ + } 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_seg_count(sbi, type) \ + do { \ + struct f2fs_stat_info *si = F2FS_STAT(sbi); \ + (si)->tot_segs++; \ + if (type == SUM_TYPE_DATA) \ + si->data_segs++; \ + else \ + si->node_segs++; \ + } while (0) + +#define stat_inc_tot_blk_count(si, blks) \ + (si->tot_blks += (blks)) + +#define stat_inc_data_blk_count(sbi, blks) \ + do { \ + struct f2fs_stat_info *si = F2FS_STAT(sbi); \ + stat_inc_tot_blk_count(si, blks); \ + si->data_blks += (blks); \ + } while (0) + +#define stat_inc_node_blk_count(sbi, blks) \ + do { \ + struct f2fs_stat_info *si = F2FS_STAT(sbi); \ + stat_inc_tot_blk_count(si, blks); \ + si->node_blks += (blks); \ + } 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_call_count(si) +#define stat_inc_bggc_count(si) +#define stat_inc_dirty_dir(sbi) +#define stat_dec_dirty_dir(sbi) +#define stat_inc_total_hit(sb) +#define stat_inc_read_hit(sb) +#define stat_inc_inline_inode(inode) +#define stat_dec_inline_inode(inode) +#define stat_inc_seg_type(sbi, curseg) +#define stat_inc_block_count(sbi, curseg) +#define stat_inc_seg_count(si, type) +#define stat_inc_tot_blk_count(si, blks) +#define stat_inc_data_blk_count(si, blks) +#define stat_inc_node_blk_count(sbi, blks) + +static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; } +static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { } +static inline void __init f2fs_create_root_stats(void) { } +static inline void f2fs_destroy_root_stats(void) { } +#endif + +extern const struct file_operations f2fs_dir_operations; +extern const struct file_operations f2fs_file_operations; +extern const struct inode_operations f2fs_file_inode_operations; +extern const struct address_space_operations f2fs_dblock_aops; +extern const struct address_space_operations f2fs_node_aops; +extern const struct address_space_operations f2fs_meta_aops; +extern const struct inode_operations f2fs_dir_inode_operations; +extern const struct inode_operations f2fs_symlink_inode_operations; +extern const struct inode_operations f2fs_special_inode_operations; + +/* + * inline.c + */ +bool f2fs_may_inline(struct inode *); +int f2fs_read_inline_data(struct inode *, struct page *); +int f2fs_convert_inline_data(struct inode *, pgoff_t); +int f2fs_write_inline_data(struct inode *, struct page *, unsigned int); +int recover_inline_data(struct inode *, struct page *); +#endif diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c new file mode 100644 index 0000000..c77ad4d --- /dev/null +++ b/fs/f2fs/file.c @@ -0,0 +1,681 @@ +/* + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include "xattr.h" +#include "acl.h" +#include + +static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + struct page *page = vmf->page; + struct inode *inode = file_inode(vma->vm_file); + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct dnode_of_data dn; + int err; + + f2fs_balance_fs(sbi); + + sb_start_pagefault(inode->i_sb); + + /* block allocation */ + f2fs_lock_op(sbi); + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = f2fs_reserve_block(&dn, page->index); + f2fs_unlock_op(sbi); + if (err) + goto out; + + file_update_time(vma->vm_file); + lock_page(page); + if (unlikely(page->mapping != inode->i_mapping || + page_offset(page) > i_size_read(inode) || + !PageUptodate(page))) { + unlock_page(page); + err = -EFAULT; + goto out; + } + + /* + * check to see if the page is mapped already (no holes) + */ + if (PageMappedToDisk(page)) + goto mapped; + + /* page is wholly or partially inside EOF */ + if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) { + unsigned offset; + offset = i_size_read(inode) & ~PAGE_CACHE_MASK; + zero_user_segment(page, offset, PAGE_CACHE_SIZE); + } + set_page_dirty(page); + SetPageUptodate(page); + + trace_f2fs_vm_page_mkwrite(page, DATA); +mapped: + /* fill the page */ + wait_on_page_writeback(page); +out: + sb_end_pagefault(inode->i_sb); + return block_page_mkwrite_return(err); +} + +static const struct vm_operations_struct f2fs_file_vm_ops = { + .fault = filemap_fault, + .page_mkwrite = f2fs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, +}; + +static int get_parent_ino(struct inode *inode, nid_t *pino) +{ + struct dentry *dentry; + + inode = igrab(inode); + dentry = d_find_any_alias(inode); + iput(inode); + if (!dentry) + return 0; + + if (update_dent_inode(inode, &dentry->d_name)) { + dput(dentry); + return 0; + } + + *pino = parent_ino(dentry); + dput(dentry); + return 1; +} + +int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) +{ + struct inode *inode = file->f_mapping->host; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + int ret = 0; + bool need_cp = false; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = LONG_MAX, + .for_reclaim = 0, + }; + + if (unlikely(f2fs_readonly(inode->i_sb))) + return 0; + + trace_f2fs_sync_file_enter(inode); + ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (ret) { + trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); + return ret; + } + + /* guarantee free sections for fsync */ + f2fs_balance_fs(sbi); + + mutex_lock(&inode->i_mutex); + + /* + * Both of fdatasync() and fsync() are able to be recovered from + * sudden-power-off. + */ + if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1) + need_cp = true; + else if (file_wrong_pino(inode)) + need_cp = true; + else if (!space_for_roll_forward(sbi)) + need_cp = true; + else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino)) + need_cp = true; + else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi))) + need_cp = true; + + if (need_cp) { + nid_t pino; + + F2FS_I(inode)->xattr_ver = 0; + + /* all the dirty node pages should be flushed for POR */ + ret = f2fs_sync_fs(inode->i_sb, 1); + if (file_wrong_pino(inode) && inode->i_nlink == 1 && + get_parent_ino(inode, &pino)) { + F2FS_I(inode)->i_pino = pino; + file_got_pino(inode); + mark_inode_dirty_sync(inode); + ret = f2fs_write_inode(inode, NULL); + if (ret) + goto out; + } + } else { + /* if there is no written node page, write its inode page */ + while (!sync_node_pages(sbi, inode->i_ino, &wbc)) { + mark_inode_dirty_sync(inode); + ret = f2fs_write_inode(inode, NULL); + if (ret) + goto out; + } + ret = wait_on_node_pages_writeback(sbi, inode->i_ino); + if (ret) + goto out; + ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); + } +out: + mutex_unlock(&inode->i_mutex); + trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); + return ret; +} + +static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) +{ + file_accessed(file); + vma->vm_ops = &f2fs_file_vm_ops; + return 0; +} + +int truncate_data_blocks_range(struct dnode_of_data *dn, int count) +{ + int nr_free = 0, ofs = dn->ofs_in_node; + struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb); + struct f2fs_node *raw_node; + __le32 *addr; + + raw_node = 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; + + update_extent_cache(NULL_ADDR, dn); + invalidate_blocks(sbi, blkaddr); + nr_free++; + } + if (nr_free) { + dec_valid_block_count(sbi, dn->inode, nr_free); + set_page_dirty(dn->node_page); + sync_inode_page(dn); + } + dn->ofs_in_node = ofs; + + trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid, + dn->ofs_in_node, nr_free); + return nr_free; +} + +void truncate_data_blocks(struct dnode_of_data *dn) +{ + truncate_data_blocks_range(dn, ADDRS_PER_BLOCK); +} + +static void truncate_partial_data_page(struct inode *inode, u64 from) +{ + unsigned offset = from & (PAGE_CACHE_SIZE - 1); + struct page *page; + + if (!offset) + return; + + page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, false); + if (IS_ERR(page)) + return; + + lock_page(page); + if (unlikely(page->mapping != inode->i_mapping)) { + f2fs_put_page(page, 1); + return; + } + wait_on_page_writeback(page); + zero_user(page, offset, PAGE_CACHE_SIZE - offset); + set_page_dirty(page); + f2fs_put_page(page, 1); +} + +int truncate_blocks(struct inode *inode, u64 from) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + unsigned int blocksize = inode->i_sb->s_blocksize; + struct dnode_of_data dn; + pgoff_t free_from; + int count = 0, err = 0; + + trace_f2fs_truncate_blocks_enter(inode, from); + + if (f2fs_has_inline_data(inode)) + goto done; + + free_from = (pgoff_t) + ((from + blocksize - 1) >> (sbi->log_blocksize)); + + f2fs_lock_op(sbi); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE); + if (err) { + if (err == -ENOENT) + goto free_next; + f2fs_unlock_op(sbi); + trace_f2fs_truncate_blocks_exit(inode, err); + return err; + } + + if (IS_INODE(dn.node_page)) + count = ADDRS_PER_INODE(F2FS_I(inode)); + else + count = ADDRS_PER_BLOCK; + + count -= dn.ofs_in_node; + f2fs_bug_on(count < 0); + + if (dn.ofs_in_node || IS_INODE(dn.node_page)) { + truncate_data_blocks_range(&dn, count); + free_from += count; + } + + f2fs_put_dnode(&dn); +free_next: + err = truncate_inode_blocks(inode, free_from); + f2fs_unlock_op(sbi); +done: + /* lastly zero out the first data page */ + truncate_partial_data_page(inode, from); + + trace_f2fs_truncate_blocks_exit(inode, err); + return err; +} + +void f2fs_truncate(struct inode *inode) +{ + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode))) + return; + + trace_f2fs_truncate(inode); + + if (!truncate_blocks(inode, i_size_read(inode))) { + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(inode); + } +} + +int f2fs_getattr(struct vfsmount *mnt, + struct dentry *dentry, struct kstat *stat) +{ + struct inode *inode = dentry->d_inode; + generic_fillattr(inode, stat); + stat->blocks <<= 3; + return 0; +} + +#ifdef CONFIG_F2FS_FS_POSIX_ACL +static void __setattr_copy(struct inode *inode, const struct iattr *attr) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + unsigned int ia_valid = attr->ia_valid; + + if (ia_valid & ATTR_UID) + inode->i_uid = attr->ia_uid; + if (ia_valid & ATTR_GID) + inode->i_gid = attr->ia_gid; + if (ia_valid & ATTR_ATIME) + inode->i_atime = timespec_trunc(attr->ia_atime, + inode->i_sb->s_time_gran); + if (ia_valid & ATTR_MTIME) + inode->i_mtime = timespec_trunc(attr->ia_mtime, + inode->i_sb->s_time_gran); + if (ia_valid & ATTR_CTIME) + inode->i_ctime = timespec_trunc(attr->ia_ctime, + inode->i_sb->s_time_gran); + if (ia_valid & ATTR_MODE) { + umode_t mode = attr->ia_mode; + + if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) + mode &= ~S_ISGID; + set_acl_inode(fi, mode); + } +} +#else +#define __setattr_copy setattr_copy +#endif + +int f2fs_setattr(struct dentry *dentry, struct iattr *attr) +{ + struct inode *inode = dentry->d_inode; + struct f2fs_inode_info *fi = F2FS_I(inode); + int err; + + err = inode_change_ok(inode, attr); + if (err) + return err; + + if ((attr->ia_valid & ATTR_SIZE) && + attr->ia_size != i_size_read(inode)) { + err = f2fs_convert_inline_data(inode, attr->ia_size); + if (err) + return err; + + truncate_setsize(inode, attr->ia_size); + f2fs_truncate(inode); + f2fs_balance_fs(F2FS_SB(inode->i_sb)); + } + + __setattr_copy(inode, attr); + + if (attr->ia_valid & ATTR_MODE) { + err = f2fs_acl_chmod(inode); + if (err || is_inode_flag_set(fi, FI_ACL_MODE)) { + inode->i_mode = fi->i_acl_mode; + clear_inode_flag(fi, FI_ACL_MODE); + } + } + + mark_inode_dirty(inode); + return err; +} + +const struct inode_operations f2fs_file_inode_operations = { + .getattr = f2fs_getattr, + .setattr = f2fs_setattr, + .get_acl = f2fs_get_acl, +#ifdef CONFIG_F2FS_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = f2fs_listxattr, + .removexattr = generic_removexattr, +#endif +}; + +static void fill_zero(struct inode *inode, pgoff_t index, + loff_t start, loff_t len) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct page *page; + + if (!len) + return; + + f2fs_balance_fs(sbi); + + f2fs_lock_op(sbi); + page = get_new_data_page(inode, NULL, index, false); + f2fs_unlock_op(sbi); + + if (!IS_ERR(page)) { + wait_on_page_writeback(page); + zero_user(page, start, len); + set_page_dirty(page); + f2fs_put_page(page, 1); + } +} + +int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) +{ + pgoff_t index; + int err; + + for (index = pg_start; index < pg_end; index++) { + struct dnode_of_data dn; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, index, LOOKUP_NODE); + if (err) { + if (err == -ENOENT) + continue; + return err; + } + + if (dn.data_blkaddr != NULL_ADDR) + truncate_data_blocks_range(&dn, 1); + f2fs_put_dnode(&dn); + } + return 0; +} + +static int punch_hole(struct inode *inode, loff_t offset, loff_t len) +{ + pgoff_t pg_start, pg_end; + loff_t off_start, off_end; + int ret = 0; + + ret = f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1); + if (ret) + return ret; + + pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; + pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; + + off_start = offset & (PAGE_CACHE_SIZE - 1); + off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + + if (pg_start == pg_end) { + fill_zero(inode, pg_start, off_start, + off_end - off_start); + } else { + if (off_start) + fill_zero(inode, pg_start++, off_start, + PAGE_CACHE_SIZE - off_start); + if (off_end) + fill_zero(inode, pg_end, 0, off_end); + + if (pg_start < pg_end) { + struct address_space *mapping = inode->i_mapping; + loff_t blk_start, blk_end; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + + f2fs_balance_fs(sbi); + + blk_start = pg_start << PAGE_CACHE_SHIFT; + blk_end = pg_end << PAGE_CACHE_SHIFT; + truncate_inode_pages_range(mapping, blk_start, + blk_end - 1); + + f2fs_lock_op(sbi); + ret = truncate_hole(inode, pg_start, pg_end); + f2fs_unlock_op(sbi); + } + } + + return ret; +} + +static int expand_inode_data(struct inode *inode, loff_t offset, + loff_t len, int mode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + pgoff_t index, pg_start, pg_end; + loff_t new_size = i_size_read(inode); + loff_t off_start, off_end; + int ret = 0; + + ret = inode_newsize_ok(inode, (len + offset)); + if (ret) + return ret; + + ret = f2fs_convert_inline_data(inode, offset + len); + if (ret) + return ret; + + pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; + pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; + + off_start = offset & (PAGE_CACHE_SIZE - 1); + off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + + for (index = pg_start; index <= pg_end; index++) { + struct dnode_of_data dn; + + f2fs_lock_op(sbi); + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = f2fs_reserve_block(&dn, index); + f2fs_unlock_op(sbi); + if (ret) + break; + + if (pg_start == pg_end) + new_size = offset + len; + else if (index == pg_start && off_start) + new_size = (index + 1) << PAGE_CACHE_SHIFT; + else if (index == pg_end) + new_size = (index << PAGE_CACHE_SHIFT) + off_end; + else + new_size += PAGE_CACHE_SIZE; + } + + if (!(mode & FALLOC_FL_KEEP_SIZE) && + i_size_read(inode) < new_size) { + i_size_write(inode, new_size); + mark_inode_dirty(inode); + } + + return ret; +} + +static long f2fs_fallocate(struct file *file, int mode, + loff_t offset, loff_t len) +{ + struct inode *inode = file_inode(file); + long ret; + + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + return -EOPNOTSUPP; + + if (mode & FALLOC_FL_PUNCH_HOLE) + ret = punch_hole(inode, offset, len); + else + ret = expand_inode_data(inode, offset, len, mode); + + if (!ret) { + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(inode); + } + trace_f2fs_fallocate(inode, mode, offset, len, ret); + return ret; +} + +#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL)) +#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL) + +static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags) +{ + if (S_ISDIR(mode)) + return flags; + else if (S_ISREG(mode)) + return flags & F2FS_REG_FLMASK; + else + return flags & F2FS_OTHER_FLMASK; +} + +long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); + unsigned int flags; + int ret; + + switch (cmd) { + case F2FS_IOC_GETFLAGS: + flags = fi->i_flags & FS_FL_USER_VISIBLE; + return put_user(flags, (int __user *) arg); + case F2FS_IOC_SETFLAGS: + { + unsigned int oldflags; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + if (!inode_owner_or_capable(inode)) { + ret = -EACCES; + goto out; + } + + if (get_user(flags, (int __user *) arg)) { + ret = -EFAULT; + goto out; + } + + flags = f2fs_mask_flags(inode->i_mode, flags); + + mutex_lock(&inode->i_mutex); + + oldflags = fi->i_flags; + + if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) { + if (!capable(CAP_LINUX_IMMUTABLE)) { + mutex_unlock(&inode->i_mutex); + ret = -EPERM; + goto out; + } + } + + flags = flags & FS_FL_USER_MODIFIABLE; + flags |= oldflags & ~FS_FL_USER_MODIFIABLE; + fi->i_flags = flags; + mutex_unlock(&inode->i_mutex); + + f2fs_set_inode_flags(inode); + inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(inode); +out: + mnt_drop_write_file(filp); + return ret; + } + default: + return -ENOTTY; + } +} + +#ifdef CONFIG_COMPAT +long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + case F2FS_IOC32_GETFLAGS: + cmd = F2FS_IOC_GETFLAGS; + break; + case F2FS_IOC32_SETFLAGS: + cmd = F2FS_IOC_SETFLAGS; + break; + default: + return -ENOIOCTLCMD; + } + return f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); +} +#endif + +const struct file_operations f2fs_file_operations = { + .llseek = generic_file_llseek, + .read = do_sync_read, + .write = do_sync_write, + .aio_read = generic_file_aio_read, + .aio_write = generic_file_aio_write, + .open = generic_file_open, + .mmap = f2fs_file_mmap, + .fsync = f2fs_sync_file, + .fallocate = f2fs_fallocate, + .unlocked_ioctl = f2fs_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = f2fs_compat_ioctl, +#endif + .splice_read = generic_file_splice_read, + .splice_write = generic_file_splice_write, +}; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c new file mode 100644 index 0000000..599f546 --- /dev/null +++ b/fs/f2fs/gc.c @@ -0,0 +1,752 @@ +/* + * 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 +#include +#include +#include +#include +#include +#include +#include +#include + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include "gc.h" +#include + +static struct kmem_cache *winode_slab; + +static int gc_thread_func(void *data) +{ + struct f2fs_sb_info *sbi = data; + struct f2fs_gc_kthread *gc_th = sbi->gc_thread; + wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head; + long wait_ms; + + wait_ms = gc_th->min_sleep_time; + + do { + if (try_to_freeze()) + continue; + else + wait_event_interruptible_timeout(*wq, + kthread_should_stop(), + msecs_to_jiffies(wait_ms)); + if (kthread_should_stop()) + break; + + if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) { + wait_ms = 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 too much frequently. + * Because it is possible that some segments can be + * invalidated soon after by user update or deletion. + * So, I'd like to wait some time to collect dirty segments. + */ + if (!mutex_trylock(&sbi->gc_mutex)) + continue; + + if (!is_idle(sbi)) { + wait_ms = increase_sleep_time(gc_th, wait_ms); + mutex_unlock(&sbi->gc_mutex); + continue; + } + + if (has_enough_invalid_blocks(sbi)) + wait_ms = decrease_sleep_time(gc_th, wait_ms); + else + wait_ms = increase_sleep_time(gc_th, wait_ms); + + stat_inc_bggc_count(sbi); + + /* if return value is not zero, no victim was selected */ + if (f2fs_gc(sbi)) + wait_ms = gc_th->no_gc_sleep_time; + + /* balancing f2fs's metadata periodically */ + f2fs_balance_fs_bg(sbi); + + } while (!kthread_should_stop()); + return 0; +} + +int start_gc_thread(struct f2fs_sb_info *sbi) +{ + struct f2fs_gc_kthread *gc_th; + dev_t dev = sbi->sb->s_bdev->bd_dev; + int err = 0; + + if (!test_opt(sbi, BG_GC)) + goto out; + 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 > MAX_VICTIM_SEARCH) + p->max_search = 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 hint = 0; + unsigned int secno; + + /* + * If the gc_type is FG_GC, we can select victim segments + * selected by background GC before. + * Those segments guarantee they have small valid blocks. + */ +next: + secno = find_next_bit(dirty_i->victim_secmap, TOTAL_SECS(sbi), hint++); + if (secno < TOTAL_SECS(sbi)) { + if (sec_usage_check(sbi, secno)) + goto next; + clear_bit(secno, dirty_i->victim_secmap); + return secno * sbi->segs_per_sec; + } + return NULL_SEGNO; +} + +static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno) +{ + struct sit_info *sit_i = SIT_I(sbi); + unsigned int secno = GET_SECNO(sbi, segno); + unsigned int start = secno * sbi->segs_per_sec; + unsigned long long mtime = 0; + unsigned int vblocks; + unsigned char age = 0; + unsigned char u; + unsigned int i; + + for (i = 0; i < sbi->segs_per_sec; i++) + mtime += get_seg_entry(sbi, start + i)->mtime; + vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec); + + mtime = div_u64(mtime, sbi->segs_per_sec); + vblocks = div_u64(vblocks, sbi->segs_per_sec); + + u = (vblocks * 100) >> sbi->log_blocks_per_seg; + + /* Handle if the system time is changed by user */ + if (mtime < sit_i->min_mtime) + sit_i->min_mtime = mtime; + if (mtime > sit_i->max_mtime) + sit_i->max_mtime = mtime; + if (sit_i->max_mtime != sit_i->min_mtime) + age = 100 - div64_u64(100 * (mtime - sit_i->min_mtime), + sit_i->max_mtime - sit_i->min_mtime); + + return UINT_MAX - ((100 * (100 - u) * age) / (100 + u)); +} + +static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi, + unsigned int segno, struct victim_sel_policy *p) +{ + if (p->alloc_mode == SSR) + return get_seg_entry(sbi, segno)->ckpt_valid_blocks; + + /* alloc_mode == LFS */ + if (p->gc_mode == GC_GREEDY) + return get_valid_blocks(sbi, segno, sbi->segs_per_sec); + else + return get_cb_cost(sbi, segno); +} + +/* + * This function is called from two paths. + * One is garbage collection and the other is SSR segment selection. + * When it is called during GC, it just gets a victim segment + * and it does not remove it from dirty seglist. + * When it is called from SSR segment selection, it finds a segment + * which has minimum valid blocks and removes it from dirty seglist. + */ +static int get_victim_by_default(struct f2fs_sb_info *sbi, + unsigned int *result, int gc_type, int type, char alloc_mode) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + struct victim_sel_policy p; + unsigned int secno, max_cost; + int nsearched = 0; + + 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); + + mutex_lock(&dirty_i->seglist_lock); + + if (p.alloc_mode == LFS && gc_type == FG_GC) { + p.min_segno = check_bg_victims(sbi); + if (p.min_segno != NULL_SEGNO) + goto got_it; + } + + while (1) { + unsigned long cost; + unsigned int segno; + + segno = find_next_bit(p.dirty_segmap, + TOTAL_SEGS(sbi), p.offset); + if (segno >= TOTAL_SEGS(sbi)) { + if (sbi->last_victim[p.gc_mode]) { + sbi->last_victim[p.gc_mode] = 0; + p.offset = 0; + continue; + } + break; + } + + p.offset = segno + p.ofs_unit; + if (p.ofs_unit > 1) + p.offset -= segno % p.ofs_unit; + + secno = GET_SECNO(sbi, segno); + + if (sec_usage_check(sbi, secno)) + continue; + if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap)) + continue; + + cost = get_gc_cost(sbi, segno, &p); + + if (p.min_cost > cost) { + p.min_segno = segno; + p.min_cost = cost; + } else if (unlikely(cost == max_cost)) { + continue; + } + + if (nsearched++ >= p.max_search) { + sbi->last_victim[p.gc_mode] = segno; + break; + } + } + if (p.min_segno != NULL_SEGNO) { +got_it: + if (p.alloc_mode == LFS) { + secno = GET_SECNO(sbi, p.min_segno); + if (gc_type == FG_GC) + sbi->cur_victim_sec = secno; + else + set_bit(secno, dirty_i->victim_secmap); + } + *result = (p.min_segno / p.ofs_unit) * p.ofs_unit; + + trace_f2fs_get_victim(sbi->sb, type, gc_type, &p, + sbi->cur_victim_sec, + prefree_segments(sbi), free_segments(sbi)); + } + mutex_unlock(&dirty_i->seglist_lock); + + return (p.min_segno == NULL_SEGNO) ? 0 : 1; +} + +static const struct victim_selection default_v_ops = { + .get_victim = get_victim_by_default, +}; + +static struct inode *find_gc_inode(nid_t ino, struct list_head *ilist) +{ + struct inode_entry *ie; + + list_for_each_entry(ie, ilist, list) + if (ie->inode->i_ino == ino) + return ie->inode; + return NULL; +} + +static void add_gc_inode(struct inode *inode, struct list_head *ilist) +{ + struct inode_entry *new_ie; + + if (inode == find_gc_inode(inode->i_ino, ilist)) { + iput(inode); + return; + } + + new_ie = f2fs_kmem_cache_alloc(winode_slab, GFP_NOFS); + new_ie->inode = inode; + list_add_tail(&new_ie->list, ilist); +} + +static void put_gc_inode(struct list_head *ilist) +{ + struct inode_entry *ie, *next_ie; + list_for_each_entry_safe(ie, next_ie, ilist, list) { + iput(ie->inode); + list_del(&ie->list); + kmem_cache_free(winode_slab, ie); + } +} + +static int check_valid_map(struct f2fs_sb_info *sbi, + unsigned int segno, int offset) +{ + struct sit_info *sit_i = SIT_I(sbi); + struct seg_entry *sentry; + int ret; + + mutex_lock(&sit_i->sentry_lock); + sentry = get_seg_entry(sbi, segno); + ret = f2fs_test_bit(offset, sentry->cur_valid_map); + mutex_unlock(&sit_i->sentry_lock); + return ret; +} + +/* + * This function compares node address got in summary with that in NAT. + * On validity, copy that node with cold status, otherwise (invalid node) + * ignore that. + */ +static void gc_node_segment(struct f2fs_sb_info *sbi, + struct f2fs_summary *sum, unsigned int segno, int gc_type) +{ + bool initial = true; + struct f2fs_summary *entry; + int off; + +next_step: + entry = sum; + + for (off = 0; off < sbi->blocks_per_seg; off++, entry++) { + nid_t nid = le32_to_cpu(entry->nid); + struct page *node_page; + + /* stop BG_GC if there is not enough free sections. */ + if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0)) + return; + + if (check_valid_map(sbi, segno, off) == 0) + continue; + + if (initial) { + ra_node_page(sbi, nid); + continue; + } + node_page = get_node_page(sbi, nid); + if (IS_ERR(node_page)) + continue; + + /* set page dirty and write it */ + if (gc_type == FG_GC) { + f2fs_wait_on_page_writeback(node_page, NODE, true); + set_page_dirty(node_page); + } else { + if (!PageWriteback(node_page)) + set_page_dirty(node_page); + } + f2fs_put_page(node_page, 1); + stat_inc_node_blk_count(sbi, 1); + } + + if (initial) { + initial = false; + goto next_step; + } + + if (gc_type == FG_GC) { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = LONG_MAX, + .for_reclaim = 0, + }; + sync_node_pages(sbi, 0, &wbc); + + /* + * In the case of FG_GC, it'd be better to reclaim this victim + * completely. + */ + if (get_valid_blocks(sbi, segno, 1) != 0) + goto next_step; + } +} + +/* + * Calculate start block index indicating the given node offset. + * Be careful, caller should give this node offset only indicating direct node + * blocks. If any node offsets, which point the other types of node blocks such + * as indirect or double indirect node blocks, are given, it must be a caller's + * bug. + */ +block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi) +{ + unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4; + unsigned int bidx; + + if (node_ofs == 0) + return 0; + + if (node_ofs <= 2) { + bidx = node_ofs - 1; + } else if (node_ofs <= indirect_blks) { + int dec = (node_ofs - 4) / (NIDS_PER_BLOCK + 1); + bidx = node_ofs - 2 - dec; + } else { + int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1); + bidx = node_ofs - 5 - dec; + } + return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi); +} + +static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, + struct node_info *dni, block_t blkaddr, unsigned int *nofs) +{ + struct page *node_page; + nid_t nid; + unsigned int ofs_in_node; + block_t source_blkaddr; + + nid = le32_to_cpu(sum->nid); + ofs_in_node = le16_to_cpu(sum->ofs_in_node); + + node_page = get_node_page(sbi, nid); + if (IS_ERR(node_page)) + return 0; + + get_node_info(sbi, nid, dni); + + if (sum->version != dni->version) { + f2fs_put_page(node_page, 1); + return 0; + } + + *nofs = ofs_of_node(node_page); + source_blkaddr = datablock_addr(node_page, ofs_in_node); + f2fs_put_page(node_page, 1); + + if (source_blkaddr != blkaddr) + return 0; + return 1; +} + +static void move_data_page(struct inode *inode, struct page *page, int gc_type) +{ + struct f2fs_io_info fio = { + .type = DATA, + .rw = WRITE_SYNC, + }; + + if (gc_type == BG_GC) { + if (PageWriteback(page)) + goto out; + set_page_dirty(page); + set_cold_data(page); + } else { + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + + f2fs_wait_on_page_writeback(page, DATA, true); + + if (clear_page_dirty_for_io(page) && + S_ISDIR(inode->i_mode)) { + dec_page_count(sbi, F2FS_DIRTY_DENTS); + inode_dec_dirty_dents(inode); + } + set_cold_data(page); + do_write_data_page(page, &fio); + clear_cold_data(page); + } +out: + f2fs_put_page(page, 1); +} + +/* + * This function tries to get parent node of victim data block, and identifies + * data block validity. If the block is valid, copy that with cold status and + * modify parent node. + * If the parent node is not valid or the data block address is different, + * the victim data block is ignored. + */ +static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, + struct list_head *ilist, unsigned int segno, int gc_type) +{ + struct super_block *sb = sbi->sb; + struct f2fs_summary *entry; + block_t start_addr; + int off; + int phase = 0; + + start_addr = START_BLOCK(sbi, segno); + +next_step: + entry = sum; + + for (off = 0; off < sbi->blocks_per_seg; off++, entry++) { + struct page *data_page; + struct inode *inode; + struct node_info dni; /* dnode info for the data */ + unsigned int ofs_in_node, nofs; + block_t start_bidx; + + /* stop BG_GC if there is not enough free sections. */ + if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0)) + return; + + if (check_valid_map(sbi, segno, off) == 0) + continue; + + if (phase == 0) { + ra_node_page(sbi, le32_to_cpu(entry->nid)); + continue; + } + + /* Get an inode by ino with checking validity */ + if (check_dnode(sbi, entry, &dni, start_addr + off, &nofs) == 0) + continue; + + if (phase == 1) { + ra_node_page(sbi, dni.ino); + continue; + } + + ofs_in_node = le16_to_cpu(entry->ofs_in_node); + + if (phase == 2) { + inode = f2fs_iget(sb, dni.ino); + if (IS_ERR(inode)) + continue; + + start_bidx = start_bidx_of_node(nofs, F2FS_I(inode)); + + data_page = find_data_page(inode, + start_bidx + ofs_in_node, false); + if (IS_ERR(data_page)) + goto next_iput; + + f2fs_put_page(data_page, 0); + add_gc_inode(inode, ilist); + } else { + inode = find_gc_inode(dni.ino, ilist); + if (inode) { + start_bidx = start_bidx_of_node(nofs, + F2FS_I(inode)); + data_page = get_lock_data_page(inode, + start_bidx + ofs_in_node); + if (IS_ERR(data_page)) + continue; + move_data_page(inode, data_page, gc_type); + stat_inc_data_blk_count(sbi, 1); + } + } + continue; +next_iput: + iput(inode); + } + + if (++phase < 4) + goto next_step; + + if (gc_type == FG_GC) { + f2fs_submit_merged_bio(sbi, DATA, WRITE); + + /* + * In the case of FG_GC, it'd be better to reclaim this victim + * completely. + */ + if (get_valid_blocks(sbi, segno, 1) != 0) { + phase = 2; + goto next_step; + } + } +} + +static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim, + int gc_type, int type) +{ + struct sit_info *sit_i = SIT_I(sbi); + int ret; + mutex_lock(&sit_i->sentry_lock); + ret = DIRTY_I(sbi)->v_ops->get_victim(sbi, victim, gc_type, type, LFS); + mutex_unlock(&sit_i->sentry_lock); + return ret; +} + +static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno, + struct list_head *ilist, int gc_type) +{ + struct page *sum_page; + struct f2fs_summary_block *sum; + struct blk_plug plug; + + /* read segment summary of victim */ + sum_page = get_sum_page(sbi, segno); + + blk_start_plug(&plug); + + sum = page_address(sum_page); + + switch (GET_SUM_TYPE((&sum->footer))) { + case SUM_TYPE_NODE: + gc_node_segment(sbi, sum->entries, segno, gc_type); + break; + case SUM_TYPE_DATA: + gc_data_segment(sbi, sum->entries, ilist, segno, gc_type); + break; + } + blk_finish_plug(&plug); + + stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer))); + stat_inc_call_count(sbi->stat_info); + + f2fs_put_page(sum_page, 1); +} + +int f2fs_gc(struct f2fs_sb_info *sbi) +{ + struct list_head ilist; + unsigned int segno, i; + int gc_type = BG_GC; + int nfree = 0; + int ret = -1; + + INIT_LIST_HEAD(&ilist); +gc_more: + if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) + goto stop; + + if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree)) { + gc_type = FG_GC; + write_checkpoint(sbi, false); + } + + if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE)) + goto stop; + ret = 0; + + for (i = 0; i < sbi->segs_per_sec; i++) + do_garbage_collect(sbi, segno + i, &ilist, gc_type); + + if (gc_type == FG_GC) { + sbi->cur_victim_sec = NULL_SEGNO; + nfree++; + WARN_ON(get_valid_blocks(sbi, segno, sbi->segs_per_sec)); + } + + if (has_not_enough_free_secs(sbi, nfree)) + goto gc_more; + + if (gc_type == FG_GC) + write_checkpoint(sbi, false); +stop: + mutex_unlock(&sbi->gc_mutex); + + put_gc_inode(&ilist); + return ret; +} + +void build_gc_manager(struct f2fs_sb_info *sbi) +{ + DIRTY_I(sbi)->v_ops = &default_v_ops; +} + +int __init create_gc_caches(void) +{ + winode_slab = f2fs_kmem_cache_create("f2fs_gc_inodes", + sizeof(struct inode_entry), NULL); + if (!winode_slab) + return -ENOMEM; + return 0; +} + +void destroy_gc_caches(void) +{ + kmem_cache_destroy(winode_slab); +} diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h new file mode 100644 index 0000000..507056d --- /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 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 inode_entry { + struct list_head list; + struct inode *inode; +}; + +/* + * inline functions + */ +static inline block_t free_user_blocks(struct f2fs_sb_info *sbi) +{ + if (free_segments(sbi) < overprovision_segments(sbi)) + return 0; + else + return (free_segments(sbi) - overprovision_segments(sbi)) + << sbi->log_blocks_per_seg; +} + +static inline block_t limit_invalid_user_blocks(struct f2fs_sb_info *sbi) +{ + return (long)(sbi->user_block_count * LIMIT_INVALID_BLOCK) / 100; +} + +static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi) +{ + block_t reclaimable_user_blocks = sbi->user_block_count - + written_block_count(sbi); + return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100; +} + +static inline long increase_sleep_time(struct f2fs_gc_kthread *gc_th, long wait) +{ + if (wait == gc_th->no_gc_sleep_time) + return wait; + + wait += gc_th->min_sleep_time; + if (wait > gc_th->max_sleep_time) + wait = gc_th->max_sleep_time; + return wait; +} + +static inline long 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; + return wait; +} + +static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi) +{ + block_t invalid_user_blocks = sbi->user_block_count - + written_block_count(sbi); + /* + * Background GC is triggered with the following condition. + * 1. There are a number of invalid blocks. + * 2. There is not enough free space. + */ + if (invalid_user_blocks > limit_invalid_user_blocks(sbi) && + free_user_blocks(sbi) < limit_free_user_blocks(sbi)) + return true; + return false; +} + +static inline int is_idle(struct f2fs_sb_info *sbi) +{ + struct block_device *bdev = sbi->sb->s_bdev; + struct request_queue *q = bdev_get_queue(bdev); + struct request_list *rl = &q->root_rl; + return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]); +} diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c new file mode 100644 index 0000000..6eb8d26 --- /dev/null +++ b/fs/f2fs/hash.c @@ -0,0 +1,101 @@ +/* + * fs/f2fs/hash.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * Portions of this code from linux/fs/ext3/hash.c + * + * Copyright (C) 2002 by Theodore Ts'o + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include + +#include "f2fs.h" + +/* + * Hashing code copied from ext3 + */ +#define DELTA 0x9E3779B9 + +static void TEA_transform(unsigned int buf[4], unsigned int const in[]) +{ + __u32 sum = 0; + __u32 b0 = buf[0], b1 = buf[1]; + __u32 a = in[0], b = in[1], c = in[2], d = in[3]; + int n = 16; + + do { + sum += DELTA; + b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b); + b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d); + } while (--n); + + buf[0] += b0; + buf[1] += b1; +} + +static void str2hashbuf(const char *msg, size_t len, unsigned int *buf, int num) +{ + unsigned pad, val; + int i; + + pad = (__u32)len | ((__u32)len << 8); + pad |= pad << 16; + + val = pad; + if (len > num * 4) + len = num * 4; + for (i = 0; i < len; i++) { + if ((i % 4) == 0) + val = pad; + val = msg[i] + (val << 8); + if ((i % 4) == 3) { + *buf++ = val; + val = pad; + num--; + } + } + if (--num >= 0) + *buf++ = val; + while (--num >= 0) + *buf++ = pad; +} + +f2fs_hash_t f2fs_dentry_hash(const char *name, size_t len) +{ + __u32 hash; + f2fs_hash_t f2fs_hash; + const char *p; + __u32 in[8], buf[4]; + + if ((len <= 2) && (name[0] == '.') && + (name[1] == '.' || name[1] == '\0')) + return 0; + + /* Initialize the default seed for the hash checksum functions */ + buf[0] = 0x67452301; + buf[1] = 0xefcdab89; + buf[2] = 0x98badcfe; + buf[3] = 0x10325476; + + p = name; + while (1) { + str2hashbuf(p, len, in, 4); + TEA_transform(buf, in); + p += 16; + if (len <= 16) + break; + len -= 16; + } + hash = buf[0]; + f2fs_hash = cpu_to_le32(hash & ~F2FS_HASH_COL_BIT); + return f2fs_hash; +} diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c new file mode 100644 index 0000000..e0d800a --- /dev/null +++ b/fs/f2fs/inline.c @@ -0,0 +1,222 @@ +/* + * fs/f2fs/inline.c + * Copyright (c) 2013, Intel Corporation + * Authors: Huajun Li + * Haicheng Li + * 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 +#include + +#include "f2fs.h" + +bool f2fs_may_inline(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + block_t nr_blocks; + loff_t i_size; + + if (!test_opt(sbi, INLINE_DATA)) + return false; + + nr_blocks = F2FS_I(inode)->i_xattr_nid ? 3 : 2; + if (inode->i_blocks > nr_blocks) + return false; + + i_size = i_size_read(inode); + if (i_size > MAX_INLINE_DATA) + return false; + + return true; +} + +int f2fs_read_inline_data(struct inode *inode, struct page *page) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct page *ipage; + void *src_addr, *dst_addr; + + if (page->index) { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + goto out; + } + + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); + + 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(page); + memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + kunmap(page); + f2fs_put_page(ipage, 1); + +out: + SetPageUptodate(page); + unlock_page(page); + + return 0; +} + +static int __f2fs_convert_inline_data(struct inode *inode, struct page *page) +{ + int err; + struct page *ipage; + struct dnode_of_data dn; + void *src_addr, *dst_addr; + block_t new_blk_addr; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct f2fs_io_info fio = { + .type = DATA, + .rw = WRITE_SYNC | REQ_PRIO, + }; + + f2fs_lock_op(sbi); + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); + + /* + * i_addr[0] is not used for inline data, + * so reserving new block will not destroy inline data + */ + set_new_dnode(&dn, inode, ipage, NULL, 0); + err = f2fs_reserve_block(&dn, 0); + if (err) { + f2fs_unlock_op(sbi); + return err; + } + + 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(page); + memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + kunmap(page); + SetPageUptodate(page); + + /* write data page to try to make data consistent */ + set_page_writeback(page); + write_data_page(page, &dn, &new_blk_addr, &fio); + update_extent_cache(new_blk_addr, &dn); + f2fs_wait_on_page_writeback(page, DATA, true); + + /* clear inline data and flag after data writeback */ + zero_user_segment(ipage, INLINE_DATA_OFFSET, + INLINE_DATA_OFFSET + MAX_INLINE_DATA); + clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + stat_dec_inline_inode(inode); + + sync_inode_page(&dn); + f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); + return err; +} + +int f2fs_convert_inline_data(struct inode *inode, pgoff_t to_size) +{ + struct page *page; + int err; + + if (!f2fs_has_inline_data(inode)) + return 0; + else if (to_size <= MAX_INLINE_DATA) + return 0; + + page = grab_cache_page_write_begin(inode->i_mapping, 0, AOP_FLAG_NOFS); + if (!page) + return -ENOMEM; + + err = __f2fs_convert_inline_data(inode, page); + f2fs_put_page(page, 1); + return err; +} + +int f2fs_write_inline_data(struct inode *inode, + struct page *page, unsigned size) +{ + void *src_addr, *dst_addr; + struct page *ipage; + 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; + ipage = dn.inode_page; + + zero_user_segment(ipage, INLINE_DATA_OFFSET, + INLINE_DATA_OFFSET + MAX_INLINE_DATA); + src_addr = kmap(page); + dst_addr = inline_data_addr(ipage); + memcpy(dst_addr, src_addr, size); + kunmap(page); + + /* Release the first data block if it is allocated */ + if (!f2fs_has_inline_data(inode)) { + truncate_data_blocks_range(&dn, 1); + set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + stat_inc_inline_inode(inode); + } + + sync_inode_page(&dn); + f2fs_put_dnode(&dn); + + return 0; +} + +int recover_inline_data(struct inode *inode, struct page *npage) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + 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(IS_ERR(ipage)); + + src_addr = inline_data_addr(npage); + dst_addr = inline_data_addr(ipage); + memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + update_inode(inode, ipage); + f2fs_put_page(ipage, 1); + return -1; + } + + if (f2fs_has_inline_data(inode)) { + ipage = get_node_page(sbi, inode->i_ino); + f2fs_bug_on(IS_ERR(ipage)); + zero_user_segment(ipage, INLINE_DATA_OFFSET, + INLINE_DATA_OFFSET + MAX_INLINE_DATA); + clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + update_inode(inode, ipage); + f2fs_put_page(ipage, 1); + } else if (ri && ri->i_inline & F2FS_INLINE_DATA) { + truncate_blocks(inode, 0); + set_inode_flag(F2FS_I(inode), FI_INLINE_DATA); + goto process_inline; + } + return 0; +} diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c new file mode 100644 index 0000000..915f9a8 --- /dev/null +++ b/fs/f2fs/inode.c @@ -0,0 +1,286 @@ +/* + * 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 +#include +#include +#include + +#include "f2fs.h" +#include "node.h" + +#include + +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 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 int do_read_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct page *node_page; + struct f2fs_inode *ri; + + /* Check if ino is within scope */ + if (check_nid_range(sbi, inode->i_ino)) { + f2fs_msg(inode->i_sb, KERN_ERR, "bad inode number: %lu", + (unsigned long) inode->i_ino); + return -EINVAL; + } + + node_page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(node_page)) + return PTR_ERR(node_page); + + ri = F2FS_INODE(node_page); + + inode->i_mode = le16_to_cpu(ri->i_mode); + i_uid_write(inode, le32_to_cpu(ri->i_uid)); + i_gid_write(inode, le32_to_cpu(ri->i_gid)); + set_nlink(inode, le32_to_cpu(ri->i_links)); + inode->i_size = le64_to_cpu(ri->i_size); + inode->i_blocks = le64_to_cpu(ri->i_blocks); + + inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime); + inode->i_ctime.tv_sec = le64_to_cpu(ri->i_ctime); + inode->i_mtime.tv_sec = le64_to_cpu(ri->i_mtime); + inode->i_atime.tv_nsec = le32_to_cpu(ri->i_atime_nsec); + inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec); + inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec); + inode->i_generation = le32_to_cpu(ri->i_generation); + + fi->i_current_depth = le32_to_cpu(ri->i_current_depth); + fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid); + fi->i_flags = le32_to_cpu(ri->i_flags); + fi->flags = 0; + fi->i_advise = ri->i_advise; + fi->i_pino = le32_to_cpu(ri->i_pino); + + get_extent_info(&fi->ext, ri->i_ext); + get_inline_info(fi, ri); + + /* get rdev by using inline_info */ + __get_inode_rdev(inode, ri); + + f2fs_put_page(node_page, 1); + return 0; +} + +struct inode *f2fs_iget(struct super_block *sb, unsigned long ino) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct inode *inode; + int ret = 0; + + inode = iget_locked(sb, ino); + if (!inode) + return ERR_PTR(-ENOMEM); + + if (!(inode->i_state & I_NEW)) { + trace_f2fs_iget(inode); + return inode; + } + if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi)) + goto make_now; + + ret = do_read_inode(inode); + if (ret) + goto bad_inode; +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_ZERO); + } else if (S_ISLNK(inode->i_mode)) { + inode->i_op = &f2fs_symlink_inode_operations; + inode->i_mapping->a_ops = &f2fs_dblock_aops; + } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || + S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { + inode->i_op = &f2fs_special_inode_operations; + init_special_inode(inode, inode->i_mode, inode->i_rdev); + } else { + ret = -EIO; + goto bad_inode; + } + unlock_new_inode(inode); + trace_f2fs_iget(inode); + return inode; + +bad_inode: + iget_failed(inode); + trace_f2fs_iget_exit(inode, ret); + return ERR_PTR(ret); +} + +void update_inode(struct inode *inode, struct page *node_page) +{ + struct f2fs_inode *ri; + + f2fs_wait_on_page_writeback(node_page, NODE, false); + + ri = F2FS_INODE(node_page); + + ri->i_mode = cpu_to_le16(inode->i_mode); + ri->i_advise = F2FS_I(inode)->i_advise; + ri->i_uid = cpu_to_le32(i_uid_read(inode)); + ri->i_gid = cpu_to_le32(i_gid_read(inode)); + ri->i_links = cpu_to_le32(inode->i_nlink); + ri->i_size = cpu_to_le64(i_size_read(inode)); + ri->i_blocks = cpu_to_le64(inode->i_blocks); + set_raw_extent(&F2FS_I(inode)->ext, &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); + + __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); +} + +int update_inode_page(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct page *node_page; + + node_page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(node_page)) + return PTR_ERR(node_page); + + update_inode(inode, node_page); + f2fs_put_page(node_page, 1); + return 0; +} + +int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + int ret; + + if (inode->i_ino == F2FS_NODE_INO(sbi) || + inode->i_ino == F2FS_META_INO(sbi)) + return 0; + + if (!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_INODE)) + return 0; + + /* + * We need to lock here to prevent from producing dirty node pages + * during the urgent cleaning time when runing out of free sections. + */ + f2fs_lock_op(sbi); + ret = update_inode_page(inode); + f2fs_unlock_op(sbi); + + if (wbc) + f2fs_balance_fs(sbi); + + return ret; +} + +/* + * Called at the last iput() if i_nlink is zero + */ +void f2fs_evict_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + + trace_f2fs_evict_inode(inode); + truncate_inode_pages(&inode->i_data, 0); + + if (inode->i_ino == F2FS_NODE_INO(sbi) || + inode->i_ino == F2FS_META_INO(sbi)) + goto no_delete; + + f2fs_bug_on(atomic_read(&F2FS_I(inode)->dirty_dents)); + remove_dirty_dir_inode(inode); + + if (inode->i_nlink || is_bad_inode(inode)) + goto no_delete; + + sb_start_intwrite(inode->i_sb); + set_inode_flag(F2FS_I(inode), FI_NO_ALLOC); + i_size_write(inode, 0); + + if (F2FS_HAS_BLOCKS(inode)) + f2fs_truncate(inode); + + f2fs_lock_op(sbi); + remove_inode_page(inode); + stat_dec_inline_inode(inode); + f2fs_unlock_op(sbi); + + sb_end_intwrite(inode->i_sb); +no_delete: + clear_inode(inode); +} diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c new file mode 100644 index 0000000..a68838d --- /dev/null +++ b/fs/f2fs/namei.c @@ -0,0 +1,533 @@ +/* + * fs/f2fs/namei.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include + +#include "f2fs.h" +#include "node.h" +#include "xattr.h" +#include "acl.h" +#include + +static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) +{ + struct super_block *sb = dir->i_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + nid_t ino; + struct inode *inode; + bool nid_free = false; + int err; + + inode = new_inode(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->i_uid = current_fsuid(); + + if (dir->i_mode & S_ISGID) { + inode->i_gid = dir->i_gid; + if (S_ISDIR(mode)) + mode |= S_ISGID; + } else { + inode->i_gid = current_fsgid(); + } + + inode->i_ino = ino; + inode->i_mode = mode; + inode->i_blocks = 0; + inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; + inode->i_generation = sbi->s_next_generation++; + + err = insert_inode_locked(inode); + if (err) { + err = -EINVAL; + nid_free = true; + goto out; + } + trace_f2fs_new_inode(inode, 0); + mark_inode_dirty(inode); + return inode; + +out: + clear_nlink(inode); + unlock_new_inode(inode); +fail: + trace_f2fs_new_inode(inode, err); + make_bad_inode(inode); + iput(inode); + if (nid_free) + alloc_nid_failed(sbi, ino); + return ERR_PTR(err); +} + +static int is_multimedia_file(const unsigned char *s, const char *sub) +{ + size_t slen = strlen(s); + size_t sublen = strlen(sub); + + if (sublen > slen) + return 0; + + return !strncasecmp(s + slen - sublen, sub, sublen); +} + +/* + * Set multimedia files as cold files for hot/cold data separation + */ +static inline void set_cold_files(struct f2fs_sb_info *sbi, struct inode *inode, + const unsigned char *name) +{ + int i; + __u8 (*extlist)[8] = sbi->raw_super->extension_list; + + int count = le32_to_cpu(sbi->raw_super->extension_count); + for (i = 0; i < count; i++) { + if (is_multimedia_file(name, extlist[i])) { + file_set_cold(inode); + break; + } + } +} + +static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool excl) +{ + struct super_block *sb = dir->i_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + 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); + f2fs_unlock_op(sbi); + if (err) + goto out; + + alloc_nid_done(sbi, ino); + + d_instantiate(dentry, inode); + unlock_new_inode(inode); + return 0; +out: + clear_nlink(inode); + unlock_new_inode(inode); + make_bad_inode(inode); + iput(inode); + alloc_nid_failed(sbi, ino); + return err; +} + +static int f2fs_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *dentry) +{ + struct inode *inode = old_dentry->d_inode; + struct super_block *sb = dir->i_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + int err; + + 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); + f2fs_unlock_op(sbi); + if (err) + goto out; + + d_instantiate(dentry, inode); + return 0; +out: + clear_inode_flag(F2FS_I(inode), FI_INC_LINK); + iput(inode); + return err; +} + +struct dentry *f2fs_get_parent(struct dentry *child) +{ + struct qstr dotdot = QSTR_INIT("..", 2); + unsigned long ino = f2fs_inode_by_name(child->d_inode, &dotdot); + if (!ino) + return ERR_PTR(-ENOENT); + return d_obtain_alias(f2fs_iget(child->d_inode->i_sb, ino)); +} + +static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct inode *inode = NULL; + struct f2fs_dir_entry *de; + struct page *page; + + if (dentry->d_name.len > F2FS_NAME_LEN) + return ERR_PTR(-ENAMETOOLONG); + + de = f2fs_find_entry(dir, &dentry->d_name, &page); + if (de) { + nid_t ino = le32_to_cpu(de->ino); + kunmap(page); + f2fs_put_page(page, 0); + + inode = f2fs_iget(dir->i_sb, ino); + if (IS_ERR(inode)) + return ERR_CAST(inode); + } + + return d_splice_alias(inode, dentry); +} + +static int f2fs_unlink(struct inode *dir, struct dentry *dentry) +{ + struct super_block *sb = dir->i_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct inode *inode = dentry->d_inode; + struct f2fs_dir_entry *de; + struct page *page; + int err = -ENOENT; + + 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); + kunmap(page); + f2fs_put_page(page, 0); + goto fail; + } + f2fs_delete_entry(de, page, inode); + f2fs_unlock_op(sbi); + + /* In order to evict this inode, we set it dirty */ + mark_inode_dirty(inode); +fail: + trace_f2fs_unlink_exit(inode, err); + return err; +} + +static int f2fs_symlink(struct inode *dir, struct dentry *dentry, + const char *symname) +{ + struct super_block *sb = dir->i_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct inode *inode; + size_t symlen = strlen(symname) + 1; + int err; + + f2fs_balance_fs(sbi); + + inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + inode->i_op = &f2fs_symlink_inode_operations; + inode->i_mapping->a_ops = &f2fs_dblock_aops; + + f2fs_lock_op(sbi); + err = f2fs_add_link(dentry, inode); + f2fs_unlock_op(sbi); + if (err) + goto out; + + err = page_symlink(inode, symname, symlen); + alloc_nid_done(sbi, inode->i_ino); + + d_instantiate(dentry, inode); + unlock_new_inode(inode); + return err; +out: + clear_nlink(inode); + unlock_new_inode(inode); + make_bad_inode(inode); + iput(inode); + alloc_nid_failed(sbi, inode->i_ino); + return err; +} + +static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); + struct inode *inode; + int err; + + f2fs_balance_fs(sbi); + + inode = f2fs_new_inode(dir, S_IFDIR | mode); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + inode->i_op = &f2fs_dir_inode_operations; + inode->i_fop = &f2fs_dir_operations; + inode->i_mapping->a_ops = &f2fs_dblock_aops; + mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO); + + set_inode_flag(F2FS_I(inode), FI_INC_LINK); + f2fs_lock_op(sbi); + err = f2fs_add_link(dentry, inode); + f2fs_unlock_op(sbi); + if (err) + goto out_fail; + + alloc_nid_done(sbi, inode->i_ino); + + d_instantiate(dentry, inode); + unlock_new_inode(inode); + + return 0; + +out_fail: + clear_inode_flag(F2FS_I(inode), FI_INC_LINK); + clear_nlink(inode); + unlock_new_inode(inode); + make_bad_inode(inode); + iput(inode); + alloc_nid_failed(sbi, inode->i_ino); + return err; +} + +static int f2fs_rmdir(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + if (f2fs_empty_dir(inode)) + return f2fs_unlink(dir, dentry); + return -ENOTEMPTY; +} + +static int f2fs_mknod(struct inode *dir, struct dentry *dentry, + umode_t mode, dev_t rdev) +{ + struct super_block *sb = dir->i_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct inode *inode; + int err = 0; + + 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); + f2fs_unlock_op(sbi); + if (err) + goto out; + + alloc_nid_done(sbi, inode->i_ino); + d_instantiate(dentry, inode); + unlock_new_inode(inode); + return 0; +out: + clear_nlink(inode); + unlock_new_inode(inode); + make_bad_inode(inode); + iput(inode); + alloc_nid_failed(sbi, inode->i_ino); + return err; +} + +static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + struct super_block *sb = old_dir->i_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct inode *old_inode = old_dentry->d_inode; + struct inode *new_inode = new_dentry->d_inode; + struct page *old_dir_page; + struct page *old_page, *new_page; + struct f2fs_dir_entry *old_dir_entry = NULL; + struct f2fs_dir_entry *old_entry; + struct f2fs_dir_entry *new_entry; + int err = -ENOENT; + + f2fs_balance_fs(sbi); + + old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); + if (!old_entry) + goto out; + + if (S_ISDIR(old_inode->i_mode)) { + err = -EIO; + old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_page); + if (!old_dir_entry) + goto out_old; + } + + f2fs_lock_op(sbi); + + 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; + + err = acquire_orphan_inode(sbi); + if (err) + goto put_out_dir; + + if (update_dent_inode(old_inode, &new_dentry->d_name)) { + release_orphan_inode(sbi); + goto put_out_dir; + } + + f2fs_set_link(new_dir, new_entry, new_page, old_inode); + F2FS_I(old_inode)->i_pino = new_dir->i_ino; + + new_inode->i_ctime = CURRENT_TIME; + if (old_dir_entry) + drop_nlink(new_inode); + drop_nlink(new_inode); + + if (!new_inode->i_nlink) + add_orphan_inode(sbi, new_inode->i_ino); + else + release_orphan_inode(sbi); + + update_inode_page(old_inode); + update_inode_page(new_inode); + } else { + err = f2fs_add_link(new_dentry, old_inode); + if (err) + goto out_dir; + + if (old_dir_entry) { + inc_nlink(new_dir); + update_inode_page(new_dir); + } + } + + old_inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(old_inode); + + f2fs_delete_entry(old_entry, old_page, NULL); + + if (old_dir_entry) { + if (old_dir != new_dir) { + f2fs_set_link(old_inode, old_dir_entry, + old_dir_page, new_dir); + F2FS_I(old_inode)->i_pino = new_dir->i_ino; + } else { + kunmap(old_dir_page); + f2fs_put_page(old_dir_page, 0); + } + drop_nlink(old_dir); + update_inode_page(old_dir); + } + + f2fs_unlock_op(sbi); + return 0; + +put_out_dir: + f2fs_put_page(new_page, 1); +out_dir: + if (old_dir_entry) { + kunmap(old_dir_page); + f2fs_put_page(old_dir_page, 0); + } + f2fs_unlock_op(sbi); +out_old: + kunmap(old_page); + f2fs_put_page(old_page, 0); +out: + return err; +} + +const struct inode_operations f2fs_dir_inode_operations = { + .create = f2fs_create, + .lookup = f2fs_lookup, + .link = f2fs_link, + .unlink = f2fs_unlink, + .symlink = f2fs_symlink, + .mkdir = f2fs_mkdir, + .rmdir = f2fs_rmdir, + .mknod = f2fs_mknod, + .rename = f2fs_rename, + .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 = page_follow_link_light, + .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..0230326 --- /dev/null +++ b/fs/f2fs/node.c @@ -0,0 +1,1909 @@ +/* + * 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 +#include +#include +#include +#include +#include +#include + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include + +static struct kmem_cache *nat_entry_slab; +static struct kmem_cache *free_nid_slab; + +static void clear_node_page_dirty(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb); + 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(sbi, 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); + + /* Dirty src_page means that it is already the new target NAT page. */ + if (PageDirty(src_page)) + return src_page; + + dst_page = grab_meta_page(sbi, dst_off); + + 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; +} + +/* + * Readahead NAT pages + */ +static void ra_nat_pages(struct f2fs_sb_info *sbi, int nid) +{ + struct address_space *mapping = sbi->meta_inode->i_mapping; + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct page *page; + pgoff_t index; + int i; + struct f2fs_io_info fio = { + .type = META, + .rw = READ_SYNC | REQ_META | REQ_PRIO + }; + + + for (i = 0; i < FREE_NID_PAGES; i++, nid += NAT_ENTRY_PER_BLOCK) { + if (unlikely(nid >= nm_i->max_nid)) + nid = 0; + index = current_nat_addr(sbi, nid); + + page = grab_cache_page(mapping, index); + if (!page) + continue; + if (PageUptodate(page)) { + mark_page_accessed(page); + f2fs_put_page(page, 1); + continue; + } + f2fs_submit_page_mbio(sbi, page, index, &fio); + mark_page_accessed(page); + f2fs_put_page(page, 0); + } + f2fs_submit_merged_bio(sbi, META, READ); +} + +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); +} + +int is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct nat_entry *e; + int is_cp = 1; + + read_lock(&nm_i->nat_tree_lock); + e = __lookup_nat_cache(nm_i, nid); + if (e && !e->checkpointed) + is_cp = 0; + read_unlock(&nm_i->nat_tree_lock); + return is_cp; +} + +static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid) +{ + struct nat_entry *new; + + new = kmem_cache_alloc(nat_entry_slab, GFP_ATOMIC); + if (!new) + return NULL; + if (radix_tree_insert(&nm_i->nat_root, nid, new)) { + kmem_cache_free(nat_entry_slab, new); + return NULL; + } + memset(new, 0, sizeof(struct nat_entry)); + nat_set_nid(new, nid); + 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; +retry: + write_lock(&nm_i->nat_tree_lock); + e = __lookup_nat_cache(nm_i, nid); + if (!e) { + e = grab_nat_entry(nm_i, nid); + if (!e) { + write_unlock(&nm_i->nat_tree_lock); + goto retry; + } + nat_set_blkaddr(e, le32_to_cpu(ne->block_addr)); + nat_set_ino(e, le32_to_cpu(ne->ino)); + nat_set_version(e, ne->version); + e->checkpointed = true; + } + write_unlock(&nm_i->nat_tree_lock); +} + +static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, + block_t new_blkaddr) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct nat_entry *e; +retry: + write_lock(&nm_i->nat_tree_lock); + e = __lookup_nat_cache(nm_i, ni->nid); + if (!e) { + e = grab_nat_entry(nm_i, ni->nid); + if (!e) { + write_unlock(&nm_i->nat_tree_lock); + goto retry; + } + e->ni = *ni; + e->checkpointed = true; + f2fs_bug_on(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. + */ + e->ni = *ni; + f2fs_bug_on(ni->blk_addr != NULL_ADDR); + } + + if (new_blkaddr == NEW_ADDR) + e->checkpointed = false; + + /* sanity check */ + f2fs_bug_on(nat_get_blkaddr(e) != ni->blk_addr); + f2fs_bug_on(nat_get_blkaddr(e) == NULL_ADDR && + new_blkaddr == NULL_ADDR); + f2fs_bug_on(nat_get_blkaddr(e) == NEW_ADDR && + new_blkaddr == NEW_ADDR); + f2fs_bug_on(nat_get_blkaddr(e) != NEW_ADDR && + nat_get_blkaddr(e) != NULL_ADDR && + new_blkaddr == NEW_ADDR); + + /* increament version no as node is removed */ + if (nat_get_blkaddr(e) != NEW_ADDR && new_blkaddr == NULL_ADDR) { + unsigned char version = nat_get_version(e); + nat_set_version(e, inc_node_version(version)); + } + + /* change address */ + nat_set_blkaddr(e, new_blkaddr); + __set_nat_cache_dirty(nm_i, e); + write_unlock(&nm_i->nat_tree_lock); +} + +int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + + if (nm_i->nat_cnt <= NM_WOUT_THRESHOLD) + return 0; + + write_lock(&nm_i->nat_tree_lock); + while (nr_shrink && !list_empty(&nm_i->nat_entries)) { + struct nat_entry *ne; + ne = list_first_entry(&nm_i->nat_entries, + struct nat_entry, list); + __del_from_nat_cache(nm_i, ne); + nr_shrink--; + } + write_unlock(&nm_i->nat_tree_lock); + return nr_shrink; +} + +/* + * This function returns always 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; + + memset(&ne, 0, sizeof(struct f2fs_nat_entry)); + ni->nid = nid; + + /* Check nat cache */ + read_lock(&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); + } + read_unlock(&nm_i->nat_tree_lock); + if (e) + return; + + /* 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_SB(dn->inode->i_sb); + struct page *npage[4]; + struct page *parent; + 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]); + } + 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_SB(dn->inode->i_sb); + struct node_info ni; + + get_node_info(sbi, dn->nid, &ni); + if (dn->inode->i_blocks == 0) { + f2fs_bug_on(ni.blk_addr != NULL_ADDR); + goto invalidate; + } + f2fs_bug_on(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); + + 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); + F2FS_SET_SB_DIRT(sbi); + + f2fs_put_page(dn->node_page, 1); + 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 f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb); + struct page *page; + + if (dn->nid == 0) + return 1; + + /* get direct node */ + page = get_node_page(sbi, 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 f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb); + 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(sbi, 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 f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb); + 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++) { + /* refernece count'll be increased */ + pages[i] = get_node_page(sbi, 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_SB(inode->i_sb); + struct address_space *node_mapping = sbi->node_inode->i_mapping; + 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)) { + f2fs_put_page(page, 1); + goto restart; + } + wait_on_page_writeback(page); + 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_SB(inode->i_sb); + nid_t nid = F2FS_I(inode)->i_xattr_nid; + struct dnode_of_data dn; + struct page *npage; + + if (!nid) + return 0; + + npage = get_node_page(sbi, nid); + if (IS_ERR(npage)) + return PTR_ERR(npage); + + F2FS_I(inode)->i_xattr_nid = 0; + + /* need to do checkpoint during fsync */ + F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi)); + + set_new_dnode(&dn, inode, page, npage, nid); + + if (page) + dn.inode_page_locked = true; + truncate_node(&dn); + return 0; +} + +/* + * Caller should grab and release a rwsem by calling f2fs_lock_op() and + * f2fs_unlock_op(). + */ +void remove_inode_page(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct page *page; + nid_t ino = inode->i_ino; + struct dnode_of_data dn; + + page = get_node_page(sbi, ino); + if (IS_ERR(page)) + return; + + if (truncate_xattr_node(inode, page)) { + f2fs_put_page(page, 1); + return; + } + /* 0 is possible, after f2fs_new_inode() is failed */ + f2fs_bug_on(inode->i_blocks != 0 && inode->i_blocks != 1); + set_new_dnode(&dn, inode, page, page, ino); + truncate_node(&dn); +} + +struct page *new_inode_page(struct inode *inode, const struct qstr *name) +{ + 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_SB(dn->inode->i_sb); + struct address_space *mapping = sbi->node_inode->i_mapping; + 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(mapping, 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(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); + + 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 (ofs == XATTR_NODE_OFFSET) + F2FS_I(dn->inode)->i_xattr_nid = dn->nid; + + dn->node_page = page; + if (ipage) + update_inode(dn->inode, ipage); + else + sync_inode_page(dn); + if (ofs == 0) + inc_valid_inode_count(sbi); + + return page; + +fail: + clear_node_page_dirty(page); + f2fs_put_page(page, 1); + return ERR_PTR(err); +} + +/* + * Caller should do after getting the following values. + * 0: f2fs_put_page(page, 0) + * LOCKED_PAGE: f2fs_put_page(page, 1) + * error: nothing + */ +static int read_node_page(struct page *page, int rw) +{ + struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb); + struct node_info ni; + + get_node_info(sbi, page->index, &ni); + + if (unlikely(ni.blk_addr == NULL_ADDR)) { + f2fs_put_page(page, 1); + return -ENOENT; + } + + if (PageUptodate(page)) + return LOCKED_PAGE; + + return f2fs_submit_page_bio(sbi, page, ni.blk_addr, rw); +} + +/* + * Readahead a node page + */ +void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) +{ + struct address_space *mapping = sbi->node_inode->i_mapping; + struct page *apage; + int err; + + apage = find_get_page(mapping, nid); + if (apage && PageUptodate(apage)) { + f2fs_put_page(apage, 0); + return; + } + f2fs_put_page(apage, 0); + + apage = grab_cache_page(mapping, nid); + if (!apage) + return; + + err = read_node_page(apage, READA); + if (err == 0) + f2fs_put_page(apage, 0); + else if (err == LOCKED_PAGE) + f2fs_put_page(apage, 1); +} + +struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) +{ + struct address_space *mapping = sbi->node_inode->i_mapping; + struct page *page; + int err; +repeat: + page = grab_cache_page(mapping, nid); + if (!page) + return ERR_PTR(-ENOMEM); + + err = read_node_page(page, READ_SYNC); + if (err < 0) + return ERR_PTR(err); + else if (err == LOCKED_PAGE) + goto got_it; + + 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; + } +got_it: + f2fs_bug_on(nid != nid_of_node(page)); + 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_SB(parent->mapping->host->i_sb); + struct address_space *mapping = sbi->node_inode->i_mapping; + 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(mapping, nid); + if (!page) + return ERR_PTR(-ENOMEM); + + err = read_node_page(page, READ_SYNC); + if (err < 0) + return ERR_PTR(err); + else if (err == LOCKED_PAGE) + goto page_hit; + + blk_start_plug(&plug); + + /* Then, try readahead for siblings of the desired node */ + end = start + MAX_RA_NODE; + end = min(end, NIDS_PER_BLOCK); + for (i = start + 1; i < end; i++) { + nid = get_nid(parent, i, false); + if (!nid) + continue; + ra_node_page(sbi, nid); + } + + blk_finish_plug(&plug); + + lock_page(page); + if (unlikely(page->mapping != mapping)) { + 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) +{ + struct address_space *mapping = sbi->node_inode->i_mapping; + 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, mapping, &index, + PAGECACHE_TAG_DIRTY, + min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); + if (nr_pages == 0) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + /* + * 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 != mapping)) { +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)) { + int mark = !is_checkpointed_node(sbi, ino); + set_fsync_mark(page, 1); + if (IS_INODE(page)) + set_dentry_mark(page, mark); + nwritten++; + } else { + set_fsync_mark(page, 0); + set_dentry_mark(page, 0); + } + mapping->a_ops->writepage(page, wbc); + 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) +{ + struct address_space *mapping = sbi->node_inode->i_mapping; + pgoff_t index = 0, end = LONG_MAX; + struct pagevec pvec; + int nr_pages; + int ret2 = 0, ret = 0; + + pagevec_init(&pvec, 0); + while ((index <= end) && + (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_WRITEBACK, + min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1)) != 0) { + unsigned i; + + 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) { + wait_on_page_writeback(page); + if (TestClearPageError(page)) + ret = -EIO; + } + } + pagevec_release(&pvec); + cond_resched(); + } + + if (unlikely(test_and_clear_bit(AS_ENOSPC, &mapping->flags))) + ret2 = -ENOSPC; + if (unlikely(test_and_clear_bit(AS_EIO, &mapping->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_SB(page->mapping->host->i_sb); + nid_t nid; + block_t new_addr; + struct node_info ni; + + if (unlikely(sbi->por_doing)) + goto redirty_out; + + wait_on_page_writeback(page); + + /* get old block addr of this node page */ + nid = nid_of_node(page); + f2fs_bug_on(page->index != nid); + + get_node_info(sbi, nid, &ni); + + /* This page is already truncated */ + if (unlikely(ni.blk_addr == NULL_ADDR)) { + dec_page_count(sbi, F2FS_DIRTY_NODES); + unlock_page(page); + return 0; + } + + if (wbc->for_reclaim) + goto redirty_out; + + mutex_lock(&sbi->node_write); + set_page_writeback(page); + write_node_page(sbi, page, nid, ni.blk_addr, &new_addr); + set_node_addr(sbi, &ni, new_addr); + dec_page_count(sbi, F2FS_DIRTY_NODES); + mutex_unlock(&sbi->node_write); + unlock_page(page); + return 0; + +redirty_out: + dec_page_count(sbi, F2FS_DIRTY_NODES); + wbc->pages_skipped++; + set_page_dirty(page); + return AOP_WRITEPAGE_ACTIVATE; +} + +/* + * 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. + * Be default, 512 pages (2MB) * 3 node types, is more reasonable. + */ +#define COLLECT_DIRTY_NODES 1536 +static int f2fs_write_node_pages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb); + long nr_to_write = wbc->nr_to_write; + + /* 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) < COLLECT_DIRTY_NODES) + return 0; + + /* if mounting is failed, skip writing node pages */ + wbc->nr_to_write = 3 * max_hw_blocks(sbi); + sync_node_pages(sbi, 0, wbc); + wbc->nr_to_write = nr_to_write - (3 * max_hw_blocks(sbi) - + wbc->nr_to_write); + return 0; +} + +static int f2fs_set_node_page_dirty(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb); + + trace_f2fs_set_page_dirty(page, NODE); + + SetPageUptodate(page); + if (!PageDirty(page)) { + __set_page_dirty_nobuffers(page); + inc_page_count(sbi, F2FS_DIRTY_NODES); + SetPagePrivate(page); + return 1; + } + return 0; +} + +static void f2fs_invalidate_node_page(struct page *page, unsigned int offset, + unsigned int length) +{ + struct inode *inode = page->mapping->host; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + if (PageDirty(page)) + dec_page_count(sbi, F2FS_DIRTY_NODES); + ClearPagePrivate(page); +} + +static int f2fs_release_node_page(struct page *page, gfp_t wait) +{ + ClearPagePrivate(page); + return 1; +} + +/* + * 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_node_page, + .releasepage = f2fs_release_node_page, +}; + +static struct free_nid *__lookup_free_nid_list(nid_t n, struct list_head *head) +{ + struct list_head *this; + struct free_nid *i; + list_for_each(this, head) { + i = list_entry(this, struct free_nid, list); + if (i->nid == n) + return i; + } + return NULL; +} + +static void __del_from_free_nid_list(struct free_nid *i) +{ + list_del(&i->list); + kmem_cache_free(free_nid_slab, i); +} + +static int add_free_nid(struct f2fs_nm_info *nm_i, nid_t nid, bool build) +{ + struct free_nid *i; + struct nat_entry *ne; + bool allocated = false; + + if (nm_i->fcnt > 2 * MAX_FREE_NIDS) + return -1; + + /* 0 nid should not be used */ + if (unlikely(nid == 0)) + return 0; + + if (build) { + /* do not add allocated nids */ + read_lock(&nm_i->nat_tree_lock); + ne = __lookup_nat_cache(nm_i, nid); + if (ne && nat_get_blkaddr(ne) != NULL_ADDR) + allocated = true; + read_unlock(&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; + + spin_lock(&nm_i->free_nid_list_lock); + if (__lookup_free_nid_list(nid, &nm_i->free_nid_list)) { + spin_unlock(&nm_i->free_nid_list_lock); + 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); + return 1; +} + +static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid) +{ + struct free_nid *i; + spin_lock(&nm_i->free_nid_list_lock); + i = __lookup_free_nid_list(nid, &nm_i->free_nid_list); + if (i && i->state == NID_NEW) { + __del_from_free_nid_list(i); + nm_i->fcnt--; + } + spin_unlock(&nm_i->free_nid_list_lock); +} + +static void scan_nat_page(struct f2fs_nm_info *nm_i, + struct page *nat_page, nid_t start_nid) +{ + 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(blk_addr == NEW_ADDR); + if (blk_addr == NULL_ADDR) { + if (add_free_nid(nm_i, 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_nat_pages(sbi, nid); + + while (1) { + struct page *page = get_current_nat_page(sbi, nid); + + scan_nat_page(nm_i, 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(nm_i, nid, true); + else + remove_free_nid(nm_i, nid); + } + mutex_unlock(&curseg->curseg_mutex); +} + +/* + * If this function returns success, caller can obtain a new nid + * from second parameter of this function. + * The returned nid could be used ino as well as nid when inode is created. + */ +bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct free_nid *i = NULL; + struct list_head *this; +retry: + if (unlikely(sbi->total_valid_node_count + 1 >= nm_i->max_nid)) + 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 && !sbi->on_build_free_nids) { + f2fs_bug_on(list_empty(&nm_i->free_nid_list)); + list_for_each(this, &nm_i->free_nid_list) { + i = list_entry(this, struct free_nid, list); + if (i->state == NID_NEW) + break; + } + + f2fs_bug_on(i->state != NID_NEW); + *nid = i->nid; + i->state = NID_ALLOC; + nm_i->fcnt--; + spin_unlock(&nm_i->free_nid_list_lock); + return true; + } + spin_unlock(&nm_i->free_nid_list_lock); + + /* Let's scan nat pages and its caches to get free nids */ + mutex_lock(&nm_i->build_lock); + sbi->on_build_free_nids = true; + build_free_nids(sbi); + sbi->on_build_free_nids = false; + 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(nid, &nm_i->free_nid_list); + f2fs_bug_on(!i || i->state != NID_ALLOC); + __del_from_free_nid_list(i); + spin_unlock(&nm_i->free_nid_list_lock); +} + +/* + * 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; + + if (!nid) + return; + + spin_lock(&nm_i->free_nid_list_lock); + i = __lookup_free_nid_list(nid, &nm_i->free_nid_list); + f2fs_bug_on(!i || i->state != NID_ALLOC); + if (nm_i->fcnt > 2 * MAX_FREE_NIDS) { + __del_from_free_nid_list(i); + } else { + i->state = NID_NEW; + nm_i->fcnt++; + } + spin_unlock(&nm_i->free_nid_list_lock); +} + +void recover_node_page(struct f2fs_sb_info *sbi, struct page *page, + struct f2fs_summary *sum, struct node_info *ni, + block_t new_blkaddr) +{ + rewrite_node_page(sbi, page, sum, ni->blk_addr, new_blkaddr); + set_node_addr(sbi, ni, new_blkaddr); + clear_node_page_dirty(page); +} + +int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) +{ + struct address_space *mapping = sbi->node_inode->i_mapping; + struct f2fs_inode *src, *dst; + nid_t ino = ino_of_node(page); + struct node_info old_ni, new_ni; + struct page *ipage; + + ipage = grab_cache_page(mapping, ino); + if (!ipage) + return -ENOMEM; + + /* Should not use this inode from free nid list */ + remove_free_nid(NM_I(sbi), ino); + + get_node_info(sbi, ino, &old_ni); + 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; + + 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); + inc_valid_inode_count(sbi); + f2fs_put_page(ipage, 1); + return 0; +} + +/* + * ra_sum_pages() merge contiguous pages into one bio and submit. + * these pre-readed pages are linked in pages list. + */ +static int ra_sum_pages(struct f2fs_sb_info *sbi, struct list_head *pages, + int start, int nrpages) +{ + struct page *page; + int page_idx = start; + struct f2fs_io_info fio = { + .type = META, + .rw = READ_SYNC | REQ_META | REQ_PRIO + }; + + for (; page_idx < start + nrpages; page_idx++) { + /* alloc temporal page for read node summary info*/ + page = alloc_page(GFP_F2FS_ZERO); + if (!page) { + struct page *tmp; + list_for_each_entry_safe(page, tmp, pages, lru) { + list_del(&page->lru); + unlock_page(page); + __free_pages(page, 0); + } + return -ENOMEM; + } + + lock_page(page); + page->index = page_idx; + list_add_tail(&page->lru, pages); + } + + list_for_each_entry(page, pages, lru) + f2fs_submit_page_mbio(sbi, page, page->index, &fio); + + f2fs_submit_merged_bio(sbi, META, READ); + 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; + struct page *page, *tmp; + block_t addr; + int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi)); + int i, last_offset, nrpages, err = 0; + LIST_HEAD(page_list); + + /* 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); + + /* read ahead node pages */ + err = ra_sum_pages(sbi, &page_list, addr, nrpages); + if (err) + return err; + + list_for_each_entry_safe(page, tmp, &page_list, lru) { + + lock_page(page); + if (unlikely(!PageUptodate(page))) { + err = -EIO; + } else { + rn = F2FS_NODE(page); + sum_entry->nid = rn->footer.nid; + sum_entry->version = 0; + sum_entry->ofs_in_node = 0; + sum_entry++; + } + + list_del(&page->lru); + unlock_page(page); + __free_pages(page, 0); + } + } + return err; +} + +static bool flush_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); + + if (nats_in_cursum(sum) < NAT_JOURNAL_ENTRIES) { + mutex_unlock(&curseg->curseg_mutex); + return false; + } + + 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); +retry: + write_lock(&nm_i->nat_tree_lock); + ne = __lookup_nat_cache(nm_i, nid); + if (ne) { + __set_nat_cache_dirty(nm_i, ne); + write_unlock(&nm_i->nat_tree_lock); + continue; + } + ne = grab_nat_entry(nm_i, nid); + if (!ne) { + write_unlock(&nm_i->nat_tree_lock); + goto retry; + } + nat_set_blkaddr(ne, le32_to_cpu(raw_ne.block_addr)); + nat_set_ino(ne, le32_to_cpu(raw_ne.ino)); + nat_set_version(ne, raw_ne.version); + __set_nat_cache_dirty(nm_i, ne); + write_unlock(&nm_i->nat_tree_lock); + } + update_nats_in_cursum(sum, -i); + mutex_unlock(&curseg->curseg_mutex); + return true; +} + +/* + * 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 list_head *cur, *n; + struct page *page = NULL; + struct f2fs_nat_block *nat_blk = NULL; + nid_t start_nid = 0, end_nid = 0; + bool flushed; + + flushed = flush_nats_in_journal(sbi); + + if (!flushed) + mutex_lock(&curseg->curseg_mutex); + + /* 1) flush dirty nat caches */ + list_for_each_safe(cur, n, &nm_i->dirty_nat_entries) { + struct nat_entry *ne; + nid_t nid; + struct f2fs_nat_entry raw_ne; + int offset = -1; + block_t new_blkaddr; + + ne = list_entry(cur, struct nat_entry, list); + nid = nat_get_nid(ne); + + if (nat_get_blkaddr(ne) == NEW_ADDR) + continue; + if (flushed) + goto to_nat_page; + + /* if there is room for nat enries in curseg->sumpage */ + offset = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 1); + if (offset >= 0) { + raw_ne = nat_in_journal(sum, offset); + goto flush_now; + } +to_nat_page: + if (!page || (start_nid > nid || nid > end_nid)) { + if (page) { + f2fs_put_page(page, 1); + page = NULL; + } + start_nid = START_NID(nid); + end_nid = start_nid + NAT_ENTRY_PER_BLOCK - 1; + + /* + * get nat block with dirty flag, increased reference + * count, mapped and lock + */ + page = get_next_nat_page(sbi, start_nid); + nat_blk = page_address(page); + } + + f2fs_bug_on(!nat_blk); + raw_ne = nat_blk->entries[nid - start_nid]; +flush_now: + new_blkaddr = nat_get_blkaddr(ne); + + raw_ne.ino = cpu_to_le32(nat_get_ino(ne)); + raw_ne.block_addr = cpu_to_le32(new_blkaddr); + raw_ne.version = nat_get_version(ne); + + if (offset < 0) { + nat_blk->entries[nid - start_nid] = raw_ne; + } else { + nat_in_journal(sum, offset) = raw_ne; + nid_in_journal(sum, offset) = cpu_to_le32(nid); + } + + if (nat_get_blkaddr(ne) == NULL_ADDR && + add_free_nid(NM_I(sbi), nid, false) <= 0) { + write_lock(&nm_i->nat_tree_lock); + __del_from_nat_cache(nm_i, ne); + write_unlock(&nm_i->nat_tree_lock); + } else { + write_lock(&nm_i->nat_tree_lock); + __clear_nat_cache_dirty(nm_i, ne); + ne->checkpointed = true; + write_unlock(&nm_i->nat_tree_lock); + } + } + if (!flushed) + mutex_unlock(&curseg->curseg_mutex); + f2fs_put_page(page, 1); + + /* 2) shrink nat caches if necessary */ + try_to_free_nats(sbi, nm_i->nat_cnt - NM_WOUT_THRESHOLD); +} + +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; + nm_i->fcnt = 0; + nm_i->nat_cnt = 0; + + INIT_LIST_HEAD(&nm_i->free_nid_list); + INIT_RADIX_TREE(&nm_i->nat_root, GFP_ATOMIC); + INIT_LIST_HEAD(&nm_i->nat_entries); + INIT_LIST_HEAD(&nm_i->dirty_nat_entries); + + mutex_init(&nm_i->build_lock); + spin_lock_init(&nm_i->free_nid_list_lock); + rwlock_init(&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]; + 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(i->state == NID_ALLOC); + __del_from_free_nid_list(i); + nm_i->fcnt--; + } + f2fs_bug_on(nm_i->fcnt); + spin_unlock(&nm_i->free_nid_list_lock); + + /* destroy nat cache */ + write_lock(&nm_i->nat_tree_lock); + while ((found = __gang_lookup_nat_cache(nm_i, + nid, NATVEC_SIZE, natvec))) { + unsigned idx; + for (idx = 0; idx < found; idx++) { + struct nat_entry *e = natvec[idx]; + nid = nat_get_nid(e) + 1; + __del_from_nat_cache(nm_i, e); + } + } + f2fs_bug_on(nm_i->nat_cnt); + write_unlock(&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), NULL); + if (!nat_entry_slab) + return -ENOMEM; + + free_nid_slab = f2fs_kmem_cache_create("free_nid", + sizeof(struct free_nid), NULL); + if (!free_nid_slab) { + kmem_cache_destroy(nat_entry_slab); + return -ENOMEM; + } + return 0; +} + +void destroy_node_manager_caches(void) +{ + 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..c4c7988 --- /dev/null +++ b/fs/f2fs/node.h @@ -0,0 +1,351 @@ +/* + * fs/f2fs/node.h + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +/* start node id of a node block dedicated to the given node id */ +#define START_NID(nid) ((nid / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK) + +/* node block offset on the NAT area dedicated to the given start node id */ +#define NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK) + +/* # of pages to perform readahead before building free nids */ +#define FREE_NID_PAGES 4 + +/* maximum # of free node ids to produce during build_free_nids */ +#define MAX_FREE_NIDS (NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES) + +/* maximum readahead size for node during getting data blocks */ +#define MAX_RA_NODE 128 + +/* maximum cached nat entries to manage memory footprint */ +#define NM_WOUT_THRESHOLD (64 * NAT_ENTRY_PER_BLOCK) + +/* vector size for gang look-up from nat cache that consists of radix tree */ +#define NATVEC_SIZE 64 + +/* return value for read_node_page */ +#define LOCKED_PAGE 1 + +/* + * For node information + */ +struct node_info { + nid_t nid; /* node id */ + nid_t ino; /* inode number of the node's owner */ + block_t blk_addr; /* block address of the node */ + unsigned char version; /* version of the node */ +}; + +struct nat_entry { + struct list_head list; /* for clean or dirty nat list */ + bool checkpointed; /* whether it is checkpointed or not */ + struct node_info ni; /* in-memory node information */ +}; + +#define nat_get_nid(nat) (nat->ni.nid) +#define nat_set_nid(nat, n) (nat->ni.nid = n) +#define nat_get_blkaddr(nat) (nat->ni.blk_addr) +#define nat_set_blkaddr(nat, b) (nat->ni.blk_addr = b) +#define nat_get_ino(nat) (nat->ni.ino) +#define nat_set_ino(nat, i) (nat->ni.ino = i) +#define nat_get_version(nat) (nat->ni.version) +#define nat_set_version(nat, v) (nat->ni.version = v) + +#define __set_nat_cache_dirty(nm_i, ne) \ + list_move_tail(&ne->list, &nm_i->dirty_nat_entries); +#define __clear_nat_cache_dirty(nm_i, ne) \ + list_move_tail(&ne->list, &nm_i->nat_entries); +#define inc_node_version(version) (++version) + +static inline void node_info_from_raw_nat(struct node_info *ni, + struct f2fs_nat_entry *raw_ne) +{ + ni->ino = le32_to_cpu(raw_ne->ino); + ni->blk_addr = le32_to_cpu(raw_ne->block_addr); + ni->version = raw_ne->version; +} + +/* + * For free nid mangement + */ +enum nid_state { + NID_NEW, /* newly added to free nid list */ + NID_ALLOC /* it is allocated */ +}; + +struct free_nid { + struct list_head list; /* for free node id list */ + nid_t nid; /* node id */ + int state; /* in use or not: NID_NEW or NID_ALLOC */ +}; + +static inline int next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct free_nid *fnid; + + if (nm_i->fcnt <= 0) + return -1; + spin_lock(&nm_i->free_nid_list_lock); + fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list); + *nid = fnid->nid; + spin_unlock(&nm_i->free_nid_list_lock); + return 0; +} + +/* + * inline functions + */ +static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + memcpy(addr, nm_i->nat_bitmap, nm_i->bitmap_size); +} + +static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + pgoff_t block_off; + pgoff_t block_addr; + int seg_off; + + block_off = NAT_BLOCK_OFFSET(start); + seg_off = block_off >> sbi->log_blocks_per_seg; + + block_addr = (pgoff_t)(nm_i->nat_blkaddr + + (seg_off << sbi->log_blocks_per_seg << 1) + + (block_off & ((1 << sbi->log_blocks_per_seg) - 1))); + + if (f2fs_test_bit(block_off, nm_i->nat_bitmap)) + block_addr += sbi->blocks_per_seg; + + return block_addr; +} + +static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi, + pgoff_t block_addr) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + + block_addr -= nm_i->nat_blkaddr; + if ((block_addr >> sbi->log_blocks_per_seg) % 2) + block_addr -= sbi->blocks_per_seg; + else + block_addr += sbi->blocks_per_seg; + + return block_addr + nm_i->nat_blkaddr; +} + +static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid) +{ + unsigned int block_off = NAT_BLOCK_OFFSET(start_nid); + + if (f2fs_test_bit(block_off, nm_i->nat_bitmap)) + f2fs_clear_bit(block_off, nm_i->nat_bitmap); + else + f2fs_set_bit(block_off, nm_i->nat_bitmap); +} + +static inline void fill_node_footer(struct page *page, nid_t nid, + nid_t ino, unsigned int ofs, bool reset) +{ + struct f2fs_node *rn = F2FS_NODE(page); + if (reset) + memset(rn, 0, sizeof(*rn)); + rn->footer.nid = cpu_to_le32(nid); + rn->footer.ino = cpu_to_le32(ino); + rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT); +} + +static inline void copy_node_footer(struct page *dst, struct page *src) +{ + 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_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb); + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + 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 (ofs == XATTR_NODE_OFFSET) + 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); + + wait_on_page_writeback(p); + + if (i) + rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid); + else + rn->in.nid[off] = cpu_to_le32(nid); + set_page_dirty(p); +} + +static inline nid_t get_nid(struct page *p, int off, bool i) +{ + struct f2fs_node *rn = F2FS_NODE(p); + + if (i) + return le32_to_cpu(rn->i.i_nid[off - NODE_DIR1_BLOCK]); + return le32_to_cpu(rn->in.nid[off]); +} + +/* + * Coldness identification: + * - Mark cold files in f2fs_inode_info + * - Mark cold node blocks in their node footer + * - Mark cold data pages in page cache + */ +static inline int is_file(struct inode *inode, int type) +{ + return F2FS_I(inode)->i_advise & type; +} + +static inline void set_file(struct inode *inode, int type) +{ + F2FS_I(inode)->i_advise |= type; +} + +static inline void clear_file(struct inode *inode, int type) +{ + F2FS_I(inode)->i_advise &= ~type; +} + +#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT) +#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT) +#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT) +#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT) +#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT) +#define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT) + +static inline int is_cold_data(struct page *page) +{ + return PageChecked(page); +} + +static inline void set_cold_data(struct page *page) +{ + SetPageChecked(page); +} + +static inline void clear_cold_data(struct page *page) +{ + ClearPageChecked(page); +} + +static inline int is_node(struct page *page, int type) +{ + struct f2fs_node *rn = F2FS_NODE(page); + return le32_to_cpu(rn->footer.flag) & (1 << type); +} + +#define is_cold_node(page) is_node(page, COLD_BIT_SHIFT) +#define is_fsync_dnode(page) is_node(page, FSYNC_BIT_SHIFT) +#define is_dent_dnode(page) is_node(page, DENT_BIT_SHIFT) + +static inline void set_cold_node(struct inode *inode, struct page *page) +{ + struct f2fs_node *rn = F2FS_NODE(page); + unsigned int flag = le32_to_cpu(rn->footer.flag); + + if (S_ISDIR(inode->i_mode)) + flag &= ~(0x1 << COLD_BIT_SHIFT); + else + flag |= (0x1 << COLD_BIT_SHIFT); + rn->footer.flag = cpu_to_le32(flag); +} + +static inline void set_mark(struct page *page, int mark, int type) +{ + struct f2fs_node *rn = F2FS_NODE(page); + unsigned int flag = le32_to_cpu(rn->footer.flag); + if (mark) + flag |= (0x1 << type); + else + flag &= ~(0x1 << type); + rn->footer.flag = cpu_to_le32(flag); +} +#define set_dentry_mark(page, mark) set_mark(page, mark, DENT_BIT_SHIFT) +#define set_fsync_mark(page, mark) set_mark(page, mark, FSYNC_BIT_SHIFT) diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c new file mode 100644 index 0000000..655791e --- /dev/null +++ b/fs/f2fs/recovery.c @@ -0,0 +1,467 @@ +/* + * 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 +#include +#include "f2fs.h" +#include "node.h" +#include "segment.h" + +static struct kmem_cache *fsync_entry_slab; + +bool space_for_roll_forward(struct f2fs_sb_info *sbi) +{ + if (sbi->last_valid_block_count + sbi->alloc_valid_block_count + > sbi->user_block_count) + return false; + return true; +} + +static struct fsync_inode_entry *get_fsync_inode(struct list_head *head, + nid_t ino) +{ + struct list_head *this; + struct fsync_inode_entry *entry; + + list_for_each(this, head) { + entry = list_entry(this, struct fsync_inode_entry, list); + if (entry->inode->i_ino == ino) + return entry; + } + return NULL; +} + +static int recover_dentry(struct page *ipage, struct inode *inode) +{ + struct f2fs_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 = check_dirty_dir_inode(F2FS_SB(inode->i_sb), pino); + if (!dir) { + dir = f2fs_iget(inode->i_sb, pino); + if (IS_ERR(dir)) { + err = PTR_ERR(dir); + goto out; + } + set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT); + add_dirty_dir_inode(dir); + } + + 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; + } +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); + if (PTR_ERR(einode) == -ENOENT) + err = -EEXIST; + goto out_unmap_put; + } + err = acquire_orphan_inode(F2FS_SB(inode->i_sb)); + if (err) { + iput(einode); + goto out_unmap_put; + } + f2fs_delete_entry(de, page, einode); + iput(einode); + goto retry; + } + err = __f2fs_add_link(dir, &name, inode); + goto out; + +out_unmap_put: + kunmap(page); + f2fs_put_page(page, 0); +out: + f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode and its dentry: " + "ino = %x, name = %s, dir = %lx, err = %d", + ino_of_node(ipage), raw_inode->i_name, + IS_ERR(dir) ? 0 : dir->i_ino, err); + return err; +} + +static int recover_inode(struct inode *inode, struct page *node_page) +{ + struct f2fs_inode *raw_inode = F2FS_INODE(node_page); + + if (!IS_INODE(node_page)) + return 0; + + inode->i_mode = le16_to_cpu(raw_inode->i_mode); + i_size_write(inode, le64_to_cpu(raw_inode->i_size)); + inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime); + inode->i_ctime.tv_sec = le64_to_cpu(raw_inode->i_ctime); + inode->i_mtime.tv_sec = le64_to_cpu(raw_inode->i_mtime); + inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); + inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec); + inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); + + if (is_dent_dnode(node_page)) + return recover_dentry(node_page, inode); + + f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s", + ino_of_node(node_page), raw_inode->i_name); + return 0; +} + +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; + block_t blkaddr; + int err = 0; + + /* get node pages in the current segment */ + curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); + blkaddr = START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff; + + /* read node page */ + page = alloc_page(GFP_F2FS_ZERO); + if (!page) + return -ENOMEM; + lock_page(page); + + while (1) { + struct fsync_inode_entry *entry; + + err = f2fs_submit_page_bio(sbi, page, blkaddr, READ_SYNC); + if (err) + return err; + + lock_page(page); + + 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)) + set_inode_flag(F2FS_I(entry->inode), + FI_INC_LINK); + } else { + if (IS_INODE(page) && is_dent_dnode(page)) { + err = recover_inode_page(sbi, page); + if (err) + break; + } + + /* add this fsync inode to the list */ + entry = kmem_cache_alloc(fsync_entry_slab, GFP_NOFS); + if (!entry) { + err = -ENOMEM; + break; + } + + 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); + break; + } + list_add_tail(&entry->list, head); + } + entry->blkaddr = blkaddr; + + err = recover_inode(entry->inode, page); + if (err && err != -ENOENT) + break; +next: + /* check next segment */ + blkaddr = next_blkaddr_of_node(page); + } + + unlock_page(page); + __free_pages(page, 0); + + 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_SEGOFF_FROM_SEG0(sbi, blkaddr) & + (sbi->blocks_per_seg - 1); + struct f2fs_summary sum; + nid_t ino, nid; + void *kaddr; + struct inode *inode; + struct page *node_page; + 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]; + break; + } + } + if (i > CURSEG_COLD_DATA) { + struct page *sum_page = get_sum_page(sbi, segno); + struct f2fs_summary_block *sum_node; + kaddr = page_address(sum_page); + sum_node = (struct f2fs_summary_block *)kaddr; + sum = sum_node->entries[blkoff]; + f2fs_put_page(sum_page, 1); + } + + /* Use the locked dnode page and inode */ + nid = le32_to_cpu(sum.nid); + if (dn->inode->i_ino == nid) { + struct dnode_of_data tdn = *dn; + tdn.nid = nid; + tdn.node_page = dn->inode_page; + tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node); + truncate_data_blocks_range(&tdn, 1); + return 0; + } else if (dn->nid == nid) { + struct dnode_of_data tdn = *dn; + tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node); + truncate_data_blocks_range(&tdn, 1); + return 0; + } + + /* 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); + + /* Deallocate previous index in the node page */ + inode = f2fs_iget(sbi->sb, ino); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + bidx = start_bidx_of_node(offset, F2FS_I(inode)) + + le16_to_cpu(sum.ofs_in_node); + + truncate_hole(inode, bidx, bidx + 1); + iput(inode); + return 0; +} + +static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, + struct page *page, block_t blkaddr) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + unsigned int start, end; + struct dnode_of_data dn; + struct f2fs_summary sum; + struct node_info ni; + int err = 0, recovered = 0; + + if (recover_inline_data(inode, page)) + goto out; + + start = start_bidx_of_node(ofs_of_node(page), fi); + if (IS_INODE(page)) + end = start + ADDRS_PER_INODE(fi); + else + end = start + ADDRS_PER_BLOCK; + + f2fs_lock_op(sbi); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + + err = get_dnode_of_data(&dn, start, ALLOC_NODE); + if (err) { + f2fs_unlock_op(sbi); + goto out; + } + + wait_on_page_writeback(dn.node_page); + + get_node_info(sbi, dn.nid, &ni); + f2fs_bug_on(ni.ino != ino_of_node(page)); + f2fs_bug_on(ofs_of_node(dn.node_page) != ofs_of_node(page)); + + for (; start < end; start++) { + block_t src, dest; + + src = datablock_addr(dn.node_page, dn.ofs_in_node); + dest = datablock_addr(page, dn.ofs_in_node); + + if (src != dest && dest != NEW_ADDR && dest != NULL_ADDR) { + if (src == NULL_ADDR) { + err = reserve_new_block(&dn); + /* We should not get -ENOSPC */ + f2fs_bug_on(err); + } + + /* Check the previous node page having this index */ + err = check_index_in_prev_nodes(sbi, dest, &dn); + if (err) + goto err; + + set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); + + /* write dummy data page */ + recover_data_page(sbi, NULL, &sum, src, dest); + update_extent_cache(dest, &dn); + recovered++; + } + dn.ofs_in_node++; + } + + /* write node page in place */ + set_summary(&sum, dn.nid, 0, 0); + if (IS_INODE(dn.node_page)) + sync_inode_page(&dn); + + copy_node_footer(dn.node_page, page); + fill_node_footer(dn.node_page, dn.nid, ni.ino, + ofs_of_node(page), false); + set_page_dirty(dn.node_page); + + recover_node_page(sbi, dn.node_page, &sum, &ni, blkaddr); +err: + f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); +out: + f2fs_msg(sbi->sb, KERN_NOTICE, "recover_data: ino = %lx, " + "recovered_data = %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; + int err = 0; + block_t blkaddr; + + /* get node pages in the current segment */ + curseg = CURSEG_I(sbi, type); + blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); + + /* read node page */ + page = alloc_page(GFP_F2FS_ZERO); + if (!page) + return -ENOMEM; + + lock_page(page); + + while (1) { + struct fsync_inode_entry *entry; + + err = f2fs_submit_page_bio(sbi, page, blkaddr, READ_SYNC); + if (err) + return err; + + lock_page(page); + + if (cp_ver != cpver_of_node(page)) + break; + + entry = get_fsync_inode(head, ino_of_node(page)); + if (!entry) + goto next; + + err = do_recover_data(sbi, entry->inode, page, blkaddr); + if (err) + 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); + } + + unlock_page(page); + __free_pages(page, 0); + + if (!err) + allocate_new_segments(sbi); + return err; +} + +int recover_fsync_data(struct f2fs_sb_info *sbi) +{ + struct list_head inode_list; + int err; + bool need_writecp = false; + + fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry", + sizeof(struct fsync_inode_entry), NULL); + if (!fsync_entry_slab) + return -ENOMEM; + + INIT_LIST_HEAD(&inode_list); + + /* step #1: find fsynced inode numbers */ + sbi->por_doing = true; + 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); + f2fs_bug_on(!list_empty(&inode_list)); +out: + destroy_fsync_dnodes(&inode_list); + kmem_cache_destroy(fsync_entry_slab); + sbi->por_doing = false; + if (!err && need_writecp) + write_checkpoint(sbi, false); + return err; +} diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c new file mode 100644 index 0000000..555ae76 --- /dev/null +++ b/fs/f2fs/segment.c @@ -0,0 +1,1940 @@ +/* + * 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 +#include +#include +#include +#include +#include +#include + +#include "f2fs.h" +#include "segment.h" +#include "node.h" +#include + +#define __reverse_ffz(x) __reverse_ffs(~(x)) + +static struct kmem_cache *discard_entry_slab; + +/* + * __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since + * MSB and LSB are reversed in a byte by f2fs_set_bit. + */ +static inline unsigned long __reverse_ffs(unsigned long word) +{ + int num = 0; + +#if BITS_PER_LONG == 64 + if ((word & 0xffffffff) == 0) { + num += 32; + word >>= 32; + } +#endif + if ((word & 0xffff) == 0) { + num += 16; + word >>= 16; + } + if ((word & 0xff) == 0) { + num += 8; + word >>= 8; + } + if ((word & 0xf0) == 0) + num += 4; + else + word >>= 4; + if ((word & 0xc) == 0) + num += 2; + else + word >>= 2; + if ((word & 0x2) == 0) + num += 1; + return num; +} + +/* + * __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c becasue + * f2fs_set_bit makes MSB and LSB reversed in a byte. + * Example: + * LSB <--> MSB + * f2fs_set_bit(0, bitmap) => 0000 0001 + * f2fs_set_bit(7, bitmap) => 1000 0000 + */ +static unsigned long __find_rev_next_bit(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + const unsigned long *p = addr + BIT_WORD(offset); + unsigned long result = offset & ~(BITS_PER_LONG - 1); + unsigned long tmp; + unsigned long mask, submask; + unsigned long quot, rest; + + if (offset >= size) + return size; + + size -= result; + offset %= BITS_PER_LONG; + if (!offset) + goto aligned; + + tmp = *(p++); + quot = (offset >> 3) << 3; + rest = offset & 0x7; + mask = ~0UL << quot; + submask = (unsigned char)(0xff << rest) >> rest; + submask <<= quot; + mask &= submask; + tmp &= mask; + if (size < BITS_PER_LONG) + goto found_first; + if (tmp) + goto found_middle; + + size -= BITS_PER_LONG; + result += BITS_PER_LONG; +aligned: + while (size & ~(BITS_PER_LONG-1)) { + tmp = *(p++); + if (tmp) + goto found_middle; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + tmp = *p; +found_first: + tmp &= (~0UL >> (BITS_PER_LONG - size)); + if (tmp == 0UL) /* Are any bits set? */ + return result + size; /* Nope. */ +found_middle: + return result + __reverse_ffs(tmp); +} + +static unsigned long __find_rev_next_zero_bit(const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + const unsigned long *p = addr + BIT_WORD(offset); + unsigned long result = offset & ~(BITS_PER_LONG - 1); + unsigned long tmp; + unsigned long mask, submask; + unsigned long quot, rest; + + if (offset >= size) + return size; + + size -= result; + offset %= BITS_PER_LONG; + if (!offset) + goto aligned; + + tmp = *(p++); + quot = (offset >> 3) << 3; + rest = offset & 0x7; + mask = ~(~0UL << quot); + submask = (unsigned char)~((unsigned char)(0xff << rest) >> rest); + submask <<= quot; + mask += submask; + tmp |= mask; + if (size < BITS_PER_LONG) + goto found_first; + if (~tmp) + goto found_middle; + + size -= BITS_PER_LONG; + result += BITS_PER_LONG; +aligned: + while (size & ~(BITS_PER_LONG - 1)) { + tmp = *(p++); + if (~tmp) + goto found_middle; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + tmp = *p; + +found_first: + tmp |= ~0UL << size; + if (tmp == ~0UL) /* Are any bits zero? */ + return result + size; /* Nope. */ +found_middle: + return result + __reverse_ffz(tmp); +} + +/* + * This function balances dirty node and dentry pages. + * In addition, it controls garbage collection. + */ +void f2fs_balance_fs(struct f2fs_sb_info *sbi) +{ + /* + * We should do GC or end up with checkpoint, if there are so many dirty + * dir/node pages without enough free segments. + */ + if (has_not_enough_free_secs(sbi, 0)) { + mutex_lock(&sbi->gc_mutex); + f2fs_gc(sbi); + } +} + +void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) +{ + /* check the # of cached NAT entries and prefree segments */ + if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) || + excess_prefree_segs(sbi)) + f2fs_sync_fs(sbi->sb, true); +} + +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 (!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 void f2fs_issue_discard(struct f2fs_sb_info *sbi, + block_t blkstart, block_t blklen) +{ + sector_t start = SECTOR_FROM_BLOCK(sbi, blkstart); + sector_t len = SECTOR_FROM_BLOCK(sbi, blklen); + blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0); + trace_f2fs_issue_discard(sbi->sb, blkstart, blklen); +} + +static void add_discard_addrs(struct f2fs_sb_info *sbi, + unsigned int segno, struct seg_entry *se) +{ + struct list_head *head = &SM_I(sbi)->discard_list; + struct discard_entry *new; + int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long); + int max_blocks = sbi->blocks_per_seg; + unsigned long *cur_map = (unsigned long *)se->cur_valid_map; + unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map; + unsigned long dmap[entries]; + unsigned int start = 0, end = -1; + int i; + + if (!test_opt(sbi, DISCARD)) + return; + + /* zero block will be discarded through the prefree list */ + if (!se->valid_blocks || se->valid_blocks == max_blocks) + return; + + /* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */ + for (i = 0; i < entries; i++) + dmap[i] = (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i]; + + while (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); + + new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS); + INIT_LIST_HEAD(&new->list); + new->blkaddr = START_BLOCK(sbi, segno) + start; + new->len = end - start; + + list_add_tail(&new->list, head); + SM_I(sbi)->nr_discards += end - start; + } +} + +/* + * 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 = -1; + unsigned int total_segs = TOTAL_SEGS(sbi); + + mutex_lock(&dirty_i->seglist_lock); + while (1) { + segno = find_next_bit(dirty_i->dirty_segmap[PRE], total_segs, + segno + 1); + if (segno >= total_segs) + break; + __set_test_and_free(sbi, segno); + } + mutex_unlock(&dirty_i->seglist_lock); +} + +void clear_prefree_segments(struct f2fs_sb_info *sbi) +{ + struct list_head *head = &(SM_I(sbi)->discard_list); + struct list_head *this, *next; + struct discard_entry *entry; + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned long *prefree_map = dirty_i->dirty_segmap[PRE]; + unsigned int total_segs = TOTAL_SEGS(sbi); + unsigned int start = 0, end = -1; + + mutex_lock(&dirty_i->seglist_lock); + + while (1) { + int i; + start = find_next_bit(prefree_map, total_segs, end + 1); + if (start >= total_segs) + break; + end = find_next_zero_bit(prefree_map, total_segs, 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_safe(this, next, head) { + entry = list_entry(this, struct discard_entry, list); + f2fs_issue_discard(sbi, entry->blkaddr, entry->len); + list_del(&entry->list); + SM_I(sbi)->nr_discards -= entry->len; + kmem_cache_free(discard_entry_slab, entry); + } +} + +static void __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++; +} + +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_SEGOFF_FROM_SEG0(sbi, blkaddr) & (sbi->blocks_per_seg - 1); + + f2fs_bug_on((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_set_bit(offset, se->cur_valid_map)) + BUG(); + } else { + if (!f2fs_clear_bit(offset, se->cur_valid_map)) + BUG(); + } + 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; +} + +static void refresh_sit_entry(struct f2fs_sb_info *sbi, + block_t old_blkaddr, block_t new_blkaddr) +{ + update_sit_entry(sbi, new_blkaddr, 1); + if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) + update_sit_entry(sbi, old_blkaddr, -1); +} + +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(addr == NULL_ADDR); + if (addr == NEW_ADDR) + return; + + /* add it into sit main buffer */ + mutex_lock(&sit_i->sentry_lock); + + update_sit_entry(sbi, addr, -1); + + /* add it into dirty seglist */ + locate_dirty_segment(sbi, segno); + + mutex_unlock(&sit_i->sentry_lock); +} + +/* + * This function should be resided under the curseg_mutex lock + */ +static void __add_sum_entry(struct f2fs_sb_info *sbi, int type, + struct f2fs_summary *sum) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + void *addr = curseg->sum_blk; + addr += curseg->next_blkoff * sizeof(struct f2fs_summary); + memcpy(addr, sum, sizeof(struct f2fs_summary)); +} + +/* + * Calculate the number of current summary pages for writing + */ +int npages_for_summary_flush(struct f2fs_sb_info *sbi) +{ + 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 + valid_sum_count += curseg_blkoff(sbi, i); + } + + sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE - + SUM_FOOTER_SIZE) / SUMMARY_SIZE; + if (valid_sum_count <= sum_in_page) + return 1; + else if ((valid_sum_count - sum_in_page) <= + (PAGE_CACHE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE) + return 2; + return 3; +} + +/* + * Caller should put this summary page + */ +struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno) +{ + return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno)); +} + +static void write_sum_page(struct f2fs_sb_info *sbi, + struct f2fs_summary_block *sum_blk, block_t blk_addr) +{ + struct page *page = grab_meta_page(sbi, blk_addr); + void *kaddr = page_address(page); + memcpy(kaddr, sum_blk, PAGE_CACHE_SIZE); + set_page_dirty(page); + f2fs_put_page(page, 1); +} + +static int is_next_segment_free(struct f2fs_sb_info *sbi, int type) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + unsigned int segno = curseg->segno + 1; + struct free_segmap_info *free_i = FREE_I(sbi); + + if (segno < TOTAL_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 = TOTAL_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; + + write_lock(&free_i->segmap_lock); + + if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) { + segno = find_next_zero_bit(free_i->free_segmap, + TOTAL_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, TOTAL_SECS(sbi), hint); + if (secno >= TOTAL_SECS(sbi)) { + if (dir == ALLOC_RIGHT) { + secno = find_next_zero_bit(free_i->free_secmap, + TOTAL_SECS(sbi), 0); + f2fs_bug_on(secno >= TOTAL_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, + TOTAL_SECS(sbi), 0); + f2fs_bug_on(left_start >= TOTAL_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(test_bit(segno, free_i->free_segmap)); + __set_inuse(sbi, segno); + *newseg = segno; + write_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[entries]; + 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); +} + +void allocate_new_segments(struct f2fs_sb_info *sbi) +{ + struct curseg_info *curseg; + unsigned int old_curseg; + int i; + + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { + curseg = CURSEG_I(sbi, i); + old_curseg = curseg->segno; + SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true); + locate_dirty_segment(sbi, old_curseg); + } +} + +static const struct segment_allocation default_salloc_ops = { + .allocate_segment = allocate_segment_by_default, +}; + +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_HOT_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) +{ + struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb); + switch (sbi->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(sbi->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; + unsigned int old_cursegno; + + curseg = CURSEG_I(sbi, type); + + mutex_lock(&curseg->curseg_mutex); + + *new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); + old_cursegno = curseg->segno; + + /* + * __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); + + mutex_lock(&sit_i->sentry_lock); + __refresh_next_blkoff(sbi, curseg); + + stat_inc_block_count(sbi, curseg); + + /* + * SIT information should be updated before segment allocation, + * since SSR needs latest valid block information. + */ + refresh_sit_entry(sbi, old_blkaddr, *new_blkaddr); + + if (!__has_curseg_space(sbi, type)) + sit_i->s_ops->allocate_segment(sbi, type, false); + + locate_dirty_segment(sbi, old_cursegno); + locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); + mutex_unlock(&sit_i->sentry_lock); + + if (page && IS_NODESEG(type)) + fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg)); + + mutex_unlock(&curseg->curseg_mutex); +} + +static void do_write_page(struct f2fs_sb_info *sbi, struct page *page, + block_t old_blkaddr, block_t *new_blkaddr, + struct f2fs_summary *sum, struct f2fs_io_info *fio) +{ + int type = __get_segment_type(page, fio->type); + + allocate_data_block(sbi, page, old_blkaddr, new_blkaddr, sum, type); + + /* writeout dirty page into bdev */ + f2fs_submit_page_mbio(sbi, page, *new_blkaddr, fio); +} + +void write_meta_page(struct f2fs_sb_info *sbi, struct page *page) +{ + struct f2fs_io_info fio = { + .type = META, + .rw = WRITE_SYNC | REQ_META | REQ_PRIO + }; + + set_page_writeback(page); + f2fs_submit_page_mbio(sbi, page, page->index, &fio); +} + +void write_node_page(struct f2fs_sb_info *sbi, struct page *page, + unsigned int nid, block_t old_blkaddr, block_t *new_blkaddr) +{ + struct f2fs_summary sum; + struct f2fs_io_info fio = { + .type = NODE, + .rw = WRITE_SYNC, + }; + + set_summary(&sum, nid, 0, 0); + do_write_page(sbi, page, old_blkaddr, new_blkaddr, &sum, &fio); +} + +void write_data_page(struct page *page, struct dnode_of_data *dn, + block_t *new_blkaddr, struct f2fs_io_info *fio) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb); + struct f2fs_summary sum; + struct node_info ni; + + f2fs_bug_on(dn->data_blkaddr == NULL_ADDR); + get_node_info(sbi, dn->nid, &ni); + set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); + + do_write_page(sbi, page, dn->data_blkaddr, new_blkaddr, &sum, fio); +} + +void rewrite_data_page(struct page *page, block_t old_blkaddr, struct f2fs_io_info *fio) +{ + struct inode *inode = page->mapping->host; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + f2fs_submit_page_mbio(sbi, page, old_blkaddr, fio); +} + +void recover_data_page(struct f2fs_sb_info *sbi, + struct page *page, struct f2fs_summary *sum, + block_t old_blkaddr, block_t new_blkaddr) +{ + struct sit_info *sit_i = SIT_I(sbi); + struct curseg_info *curseg; + unsigned int segno, old_cursegno; + struct seg_entry *se; + int type; + + segno = GET_SEGNO(sbi, new_blkaddr); + se = get_seg_entry(sbi, segno); + type = se->type; + + if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) { + if (old_blkaddr == NULL_ADDR) + type = CURSEG_COLD_DATA; + else + type = CURSEG_WARM_DATA; + } + curseg = CURSEG_I(sbi, type); + + mutex_lock(&curseg->curseg_mutex); + mutex_lock(&sit_i->sentry_lock); + + old_cursegno = curseg->segno; + + /* change the current segment */ + if (segno != curseg->segno) { + curseg->next_segno = segno; + change_curseg(sbi, type, true); + } + + curseg->next_blkoff = GET_SEGOFF_FROM_SEG0(sbi, new_blkaddr) & + (sbi->blocks_per_seg - 1); + __add_sum_entry(sbi, type, sum); + + refresh_sit_entry(sbi, old_blkaddr, new_blkaddr); + + locate_dirty_segment(sbi, old_cursegno); + locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); + + mutex_unlock(&sit_i->sentry_lock); + mutex_unlock(&curseg->curseg_mutex); +} + +void rewrite_node_page(struct f2fs_sb_info *sbi, + struct page *page, struct f2fs_summary *sum, + block_t old_blkaddr, block_t new_blkaddr) +{ + struct sit_info *sit_i = SIT_I(sbi); + int type = CURSEG_WARM_NODE; + struct curseg_info *curseg; + unsigned int segno, old_cursegno; + block_t next_blkaddr = next_blkaddr_of_node(page); + unsigned int next_segno = GET_SEGNO(sbi, next_blkaddr); + struct f2fs_io_info fio = { + .type = NODE, + .rw = WRITE_SYNC, + }; + + curseg = CURSEG_I(sbi, type); + + mutex_lock(&curseg->curseg_mutex); + mutex_lock(&sit_i->sentry_lock); + + segno = GET_SEGNO(sbi, new_blkaddr); + old_cursegno = curseg->segno; + + /* change the current segment */ + if (segno != curseg->segno) { + curseg->next_segno = segno; + change_curseg(sbi, type, true); + } + curseg->next_blkoff = GET_SEGOFF_FROM_SEG0(sbi, new_blkaddr) & + (sbi->blocks_per_seg - 1); + __add_sum_entry(sbi, type, sum); + + /* change the current log to the next block addr in advance */ + if (next_segno != segno) { + curseg->next_segno = next_segno; + change_curseg(sbi, type, true); + } + curseg->next_blkoff = GET_SEGOFF_FROM_SEG0(sbi, next_blkaddr) & + (sbi->blocks_per_seg - 1); + + /* rewrite node page */ + set_page_writeback(page); + f2fs_submit_page_mbio(sbi, page, new_blkaddr, &fio); + f2fs_submit_merged_bio(sbi, NODE, WRITE); + refresh_sit_entry(sbi, old_blkaddr, new_blkaddr); + + locate_dirty_segment(sbi, old_cursegno); + locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); + + mutex_unlock(&sit_i->sentry_lock); + mutex_unlock(&curseg->curseg_mutex); +} + +void f2fs_wait_on_page_writeback(struct page *page, + enum page_type type, bool sync) +{ + struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb); + if (PageWriteback(page)) { + f2fs_submit_merged_bio(sbi, type, WRITE); + wait_on_page_writeback(page); + } +} + +static int read_compacted_summaries(struct f2fs_sb_info *sbi) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + struct curseg_info *seg_i; + unsigned char *kaddr; + struct page *page; + block_t start; + int i, j, offset; + + start = start_sum_block(sbi); + + page = get_meta_page(sbi, start++); + kaddr = (unsigned char *)page_address(page); + + /* Step 1: restore nat cache */ + seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA); + memcpy(&seg_i->sum_blk->n_nats, kaddr, SUM_JOURNAL_SIZE); + + /* Step 2: restore sit cache */ + seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA); + memcpy(&seg_i->sum_blk->n_sits, kaddr + SUM_JOURNAL_SIZE, + SUM_JOURNAL_SIZE); + offset = 2 * SUM_JOURNAL_SIZE; + + /* Step 3: restore summary entries */ + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { + unsigned short blk_off; + unsigned int segno; + + seg_i = CURSEG_I(sbi, i); + segno = le32_to_cpu(ckpt->cur_data_segno[i]); + blk_off = le16_to_cpu(ckpt->cur_data_blkoff[i]); + seg_i->next_segno = segno; + reset_curseg(sbi, i, 0); + seg_i->alloc_type = ckpt->alloc_type[i]; + seg_i->next_blkoff = blk_off; + + if (seg_i->alloc_type == SSR) + blk_off = sbi->blocks_per_seg; + + for (j = 0; j < blk_off; j++) { + struct f2fs_summary *s; + s = (struct f2fs_summary *)(kaddr + offset); + seg_i->sum_blk->entries[j] = *s; + offset += SUMMARY_SIZE; + if (offset + SUMMARY_SIZE <= PAGE_CACHE_SIZE - + SUM_FOOTER_SIZE) + continue; + + f2fs_put_page(page, 1); + page = NULL; + + page = get_meta_page(sbi, start++); + kaddr = (unsigned char *)page_address(page); + offset = 0; + } + } + f2fs_put_page(page, 1); + return 0; +} + +static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + struct f2fs_summary_block *sum; + struct curseg_info *curseg; + struct page *new; + unsigned short blk_off; + unsigned int segno = 0; + block_t blk_addr = 0; + + /* get segment number and block addr */ + if (IS_DATASEG(type)) { + segno = le32_to_cpu(ckpt->cur_data_segno[type]); + blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type - + CURSEG_HOT_DATA]); + if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG)) + 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 (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG)) + 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 (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG)) { + 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 { + if (restore_node_summary(sbi, segno, sum)) { + f2fs_put_page(new, 1); + return -EINVAL; + } + } + } + + /* 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; + + if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) { + /* restore for compacted data summary */ + if (read_compacted_summaries(sbi)) + return -EINVAL; + type = CURSEG_HOT_NODE; + } + + for (; type <= CURSEG_COLD_NODE; type++) + if (read_normal_summaries(sbi, type)) + return -EINVAL; + 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) +{ + if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG)) + 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) +{ + struct sit_info *sit_i = SIT_I(sbi); + unsigned int offset = SIT_BLOCK_OFFSET(sit_i, segno); + block_t blk_addr = sit_i->sit_base_addr + offset; + + check_seg_range(sbi, segno); + + /* calculate sit block address */ + if (f2fs_test_bit(offset, sit_i->sit_bitmap)) + blk_addr += sit_i->sit_blocks; + + return get_meta_page(sbi, blk_addr); +} + +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(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 bool flush_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; + + /* + * If the journal area in the current summary is full of sit entries, + * all the sit entries will be flushed. Otherwise the sit entries + * are not able to replace with newly hot sit entries. + */ + if (sits_in_cursum(sum) >= SIT_JOURNAL_ENTRIES) { + for (i = sits_in_cursum(sum) - 1; i >= 0; i--) { + unsigned int segno; + segno = le32_to_cpu(segno_in_journal(sum, i)); + __mark_sit_entry_dirty(sbi, segno); + } + update_sits_in_cursum(sum, -sits_in_cursum(sum)); + return true; + } + return false; +} + +/* + * 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 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; + unsigned long nsegs = TOTAL_SEGS(sbi); + struct page *page = NULL; + struct f2fs_sit_block *raw_sit = NULL; + unsigned int start = 0, end = 0; + unsigned int segno = -1; + bool flushed; + + mutex_lock(&curseg->curseg_mutex); + mutex_lock(&sit_i->sentry_lock); + + /* + * "flushed" indicates whether sit entries in journal are flushed + * to the SIT area or not. + */ + flushed = flush_sits_in_journal(sbi); + + while ((segno = find_next_bit(bitmap, nsegs, segno + 1)) < nsegs) { + struct seg_entry *se = get_seg_entry(sbi, segno); + int sit_offset, offset; + + sit_offset = SIT_ENTRY_OFFSET(sit_i, segno); + + /* add discard candidates */ + if (SM_I(sbi)->nr_discards < SM_I(sbi)->max_discards) + add_discard_addrs(sbi, segno, se); + + if (flushed) + goto to_sit_page; + + offset = lookup_journal_in_cursum(sum, SIT_JOURNAL, segno, 1); + if (offset >= 0) { + segno_in_journal(sum, offset) = cpu_to_le32(segno); + seg_info_to_raw_sit(se, &sit_in_journal(sum, offset)); + goto flush_done; + } +to_sit_page: + if (!page || (start > segno) || (segno > end)) { + if (page) { + f2fs_put_page(page, 1); + page = NULL; + } + + start = START_SEGNO(sit_i, segno); + end = start + SIT_ENTRY_PER_BLOCK - 1; + + /* read sit block that will be updated */ + page = get_next_sit_page(sbi, start); + raw_sit = page_address(page); + } + + /* udpate entry in SIT block */ + seg_info_to_raw_sit(se, &raw_sit->entries[sit_offset]); +flush_done: + __clear_bit(segno, bitmap); + sit_i->dirty_sentries--; + } + mutex_unlock(&sit_i->sentry_lock); + mutex_unlock(&curseg->curseg_mutex); + + /* writeout last modified SIT block */ + f2fs_put_page(page, 1); + + set_prefree_as_free_segments(sbi); +} + +static int build_sit_info(struct f2fs_sb_info *sbi) +{ + struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + struct sit_info *sit_i; + unsigned int sit_segs, start; + char *src_bitmap, *dst_bitmap; + unsigned int bitmap_size; + + /* allocate memory for SIT information */ + sit_i = kzalloc(sizeof(struct sit_info), GFP_KERNEL); + if (!sit_i) + return -ENOMEM; + + SM_I(sbi)->sit_info = sit_i; + + sit_i->sentries = vzalloc(TOTAL_SEGS(sbi) * sizeof(struct seg_entry)); + if (!sit_i->sentries) + return -ENOMEM; + + bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi)); + sit_i->dirty_sentries_bitmap = kzalloc(bitmap_size, GFP_KERNEL); + if (!sit_i->dirty_sentries_bitmap) + return -ENOMEM; + + for (start = 0; start < TOTAL_SEGS(sbi); start++) { + sit_i->sentries[start].cur_valid_map + = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + sit_i->sentries[start].ckpt_valid_map + = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + if (!sit_i->sentries[start].cur_valid_map + || !sit_i->sentries[start].ckpt_valid_map) + return -ENOMEM; + } + + if (sbi->segs_per_sec > 1) { + sit_i->sec_entries = vzalloc(TOTAL_SECS(sbi) * + sizeof(struct sec_entry)); + if (!sit_i->sec_entries) + return -ENOMEM; + } + + /* get information related with SIT */ + sit_segs = le32_to_cpu(raw_super->segment_count_sit) >> 1; + + /* setup SIT bitmap from ckeckpoint pack */ + bitmap_size = __bitmap_size(sbi, SIT_BITMAP); + src_bitmap = __bitmap_ptr(sbi, SIT_BITMAP); + + dst_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL); + if (!dst_bitmap) + return -ENOMEM; + + /* init SIT information */ + sit_i->s_ops = &default_salloc_ops; + + sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr); + sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg; + sit_i->written_valid_blocks = le64_to_cpu(ckpt->valid_block_count); + sit_i->sit_bitmap = dst_bitmap; + sit_i->bitmap_size = bitmap_size; + sit_i->dirty_sentries = 0; + sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK; + sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time); + sit_i->mounted_time = CURRENT_TIME_SEC.tv_sec; + mutex_init(&sit_i->sentry_lock); + return 0; +} + +static int build_free_segmap(struct f2fs_sb_info *sbi) +{ + struct f2fs_sm_info *sm_info = SM_I(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(TOTAL_SEGS(sbi)); + free_i->free_segmap = kmalloc(bitmap_size, GFP_KERNEL); + if (!free_i->free_segmap) + return -ENOMEM; + + sec_bitmap_size = f2fs_bitmap_size(TOTAL_SECS(sbi)); + free_i->free_secmap = kmalloc(sec_bitmap_size, GFP_KERNEL); + if (!free_i->free_secmap) + return -ENOMEM; + + /* set all segments as dirty temporarily */ + memset(free_i->free_segmap, 0xff, bitmap_size); + memset(free_i->free_secmap, 0xff, sec_bitmap_size); + + /* init free segmap information */ + free_i->start_segno = + (unsigned int) GET_SEGNO_FROM_SEG0(sbi, sm_info->main_blkaddr); + free_i->free_segments = 0; + free_i->free_sections = 0; + rwlock_init(&free_i->segmap_lock); + return 0; +} + +static int build_curseg(struct f2fs_sb_info *sbi) +{ + struct curseg_info *array; + int i; + + array = kzalloc(sizeof(*array) * NR_CURSEG_TYPE, 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 int ra_sit_pages(struct f2fs_sb_info *sbi, int start, int nrpages) +{ + struct address_space *mapping = sbi->meta_inode->i_mapping; + struct page *page; + block_t blk_addr, prev_blk_addr = 0; + int sit_blk_cnt = SIT_BLK_CNT(sbi); + int blkno = start; + struct f2fs_io_info fio = { + .type = META, + .rw = READ_SYNC | REQ_META | REQ_PRIO + }; + + for (; blkno < start + nrpages && blkno < sit_blk_cnt; blkno++) { + + blk_addr = current_sit_addr(sbi, blkno * SIT_ENTRY_PER_BLOCK); + + if (blkno != start && prev_blk_addr + 1 != blk_addr) + break; + prev_blk_addr = blk_addr; +repeat: + page = grab_cache_page(mapping, blk_addr); + if (!page) { + cond_resched(); + goto repeat; + } + if (PageUptodate(page)) { + mark_page_accessed(page); + f2fs_put_page(page, 1); + continue; + } + + f2fs_submit_page_mbio(sbi, page, blk_addr, &fio); + + mark_page_accessed(page); + f2fs_put_page(page, 0); + } + + f2fs_submit_merged_bio(sbi, META, READ); + return blkno - start; +} + +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(max_hw_blocks(sbi)); + + do { + readed = ra_sit_pages(sbi, start_blk, nrpages); + + start = start_blk * sit_i->sents_per_block; + end = (start_blk + readed) * sit_i->sents_per_block; + + for (; start < end && start < TOTAL_SEGS(sbi); start++) { + struct seg_entry *se = &sit_i->sentries[start]; + struct f2fs_sit_block *sit_blk; + struct f2fs_sit_entry sit; + struct page *page; + + mutex_lock(&curseg->curseg_mutex); + for (i = 0; i < sits_in_cursum(sum); i++) { + if (le32_to_cpu(segno_in_journal(sum, i)) == start) { + sit = sit_in_journal(sum, i); + mutex_unlock(&curseg->curseg_mutex); + goto got_it; + } + } + mutex_unlock(&curseg->curseg_mutex); + + page = get_current_sit_page(sbi, start); + sit_blk = (struct f2fs_sit_block *)page_address(page); + sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)]; + f2fs_put_page(page, 1); +got_it: + check_block_count(sbi, start, &sit); + seg_info_from_raw_sit(se, &sit); + if (sbi->segs_per_sec > 1) { + struct sec_entry *e = get_sec_entry(sbi, start); + e->valid_blocks += se->valid_blocks; + } + } + start_blk += readed; + } while (start_blk < sit_blk_cnt); +} + +static void init_free_segmap(struct f2fs_sb_info *sbi) +{ + unsigned int start; + int type; + + for (start = 0; start < TOTAL_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, total_segs = TOTAL_SEGS(sbi); + unsigned short valid_blocks; + + while (1) { + /* find dirty segment based on free segmap */ + segno = find_next_inuse(free_i, total_segs, offset); + if (segno >= total_segs) + break; + offset = segno + 1; + valid_blocks = get_valid_blocks(sbi, segno, 0); + if (valid_blocks >= sbi->blocks_per_seg || !valid_blocks) + 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(TOTAL_SECS(sbi)); + + dirty_i->victim_secmap = kzalloc(bitmap_size, GFP_KERNEL); + if (!dirty_i->victim_secmap) + return -ENOMEM; + return 0; +} + +static int build_dirty_segmap(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i; + unsigned int bitmap_size, i; + + /* allocate memory for dirty segments list information */ + dirty_i = kzalloc(sizeof(struct dirty_seglist_info), GFP_KERNEL); + if (!dirty_i) + return -ENOMEM; + + SM_I(sbi)->dirty_info = dirty_i; + mutex_init(&dirty_i->seglist_lock); + + bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi)); + + for (i = 0; i < NR_DIRTY_TYPE; i++) { + dirty_i->dirty_segmap[i] = kzalloc(bitmap_size, GFP_KERNEL); + if (!dirty_i->dirty_segmap[i]) + return -ENOMEM; + } + + init_dirty_segmap(sbi); + return init_victim_secmap(sbi); +} + +/* + * Update min, max modified time for cost-benefit GC algorithm + */ +static void init_min_max_mtime(struct f2fs_sb_info *sbi) +{ + struct sit_info *sit_i = SIT_I(sbi); + unsigned int segno; + + mutex_lock(&sit_i->sentry_lock); + + sit_i->min_mtime = LLONG_MAX; + + for (segno = 0; segno < TOTAL_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; + INIT_LIST_HEAD(&sm_info->wblist_head); + spin_lock_init(&sm_info->wblist_lock); + 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 = DEF_RECLAIM_PREFREE_SEGMENTS; + sm_info->ipu_policy = F2FS_IPU_DISABLE; + sm_info->min_ipu_util = DEF_MIN_IPU_UTIL; + + INIT_LIST_HEAD(&sm_info->discard_list); + sm_info->nr_discards = 0; + sm_info->max_discards = 0; + + err = build_sit_info(sbi); + if (err) + return err; + err = build_free_segmap(sbi); + if (err) + return err; + err = build_curseg(sbi); + if (err) + return err; + + /* reinit free segmap based on SIT */ + build_sit_entries(sbi); + + init_free_segmap(sbi); + err = build_dirty_segmap(sbi); + if (err) + return err; + + init_min_max_mtime(sbi); + return 0; +} + +static void discard_dirty_segmap(struct f2fs_sb_info *sbi, + enum dirty_type dirty_type) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + + mutex_lock(&dirty_i->seglist_lock); + kfree(dirty_i->dirty_segmap[dirty_type]); + dirty_i->nr_dirty[dirty_type] = 0; + mutex_unlock(&dirty_i->seglist_lock); +} + +static void destroy_victim_secmap(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + kfree(dirty_i->victim_secmap); +} + +static void destroy_dirty_segmap(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + int i; + + if (!dirty_i) + return; + + /* discard pre-free/dirty segments list */ + for (i = 0; i < NR_DIRTY_TYPE; i++) + discard_dirty_segmap(sbi, i); + + destroy_victim_secmap(sbi); + SM_I(sbi)->dirty_info = NULL; + kfree(dirty_i); +} + +static void destroy_curseg(struct f2fs_sb_info *sbi) +{ + struct curseg_info *array = SM_I(sbi)->curseg_array; + int i; + + if (!array) + return; + SM_I(sbi)->curseg_array = NULL; + for (i = 0; i < NR_CURSEG_TYPE; i++) + kfree(array[i].sum_blk); + kfree(array); +} + +static void destroy_free_segmap(struct f2fs_sb_info *sbi) +{ + struct free_segmap_info *free_i = SM_I(sbi)->free_info; + if (!free_i) + return; + SM_I(sbi)->free_info = NULL; + kfree(free_i->free_segmap); + kfree(free_i->free_secmap); + kfree(free_i); +} + +static void destroy_sit_info(struct f2fs_sb_info *sbi) +{ + struct sit_info *sit_i = SIT_I(sbi); + unsigned int start; + + if (!sit_i) + return; + + if (sit_i->sentries) { + for (start = 0; start < TOTAL_SEGS(sbi); start++) { + kfree(sit_i->sentries[start].cur_valid_map); + kfree(sit_i->sentries[start].ckpt_valid_map); + } + } + vfree(sit_i->sentries); + vfree(sit_i->sec_entries); + kfree(sit_i->dirty_sentries_bitmap); + + SM_I(sbi)->sit_info = NULL; + kfree(sit_i->sit_bitmap); + kfree(sit_i); +} + +void destroy_segment_manager(struct f2fs_sb_info *sbi) +{ + struct f2fs_sm_info *sm_info = SM_I(sbi); + if (!sm_info) + return; + destroy_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), NULL); + if (!discard_entry_slab) + return -ENOMEM; + return 0; +} + +void destroy_segment_manager_caches(void) +{ + kmem_cache_destroy(discard_entry_slab); +} diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h new file mode 100644 index 0000000..e9a10bd --- /dev/null +++ b/fs/f2fs/segment.h @@ -0,0 +1,683 @@ +/* + * 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 + +/* constant macro */ +#define NULL_SEGNO ((unsigned int)(~0)) +#define NULL_SECNO ((unsigned int)(~0)) + +#define DEF_RECLAIM_PREFREE_SEGMENTS 100 /* 200MB of prefree 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 START_BLOCK(sbi, segno) \ + (SM_I(sbi)->seg0_blkaddr + \ + (GET_R2L_SEGNO(FREE_I(sbi), segno) << sbi->log_blocks_per_seg)) +#define NEXT_FREE_BLKADDR(sbi, curseg) \ + (START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff) + +#define MAIN_BASE_BLOCK(sbi) (SM_I(sbi)->main_blkaddr) + +#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr) \ + ((blk_addr) - SM_I(sbi)->seg0_blkaddr) +#define GET_SEGNO_FROM_SEG0(sbi, blk_addr) \ + (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> sbi->log_blocks_per_seg) +#define GET_SEGNO(sbi, blk_addr) \ + (((blk_addr == NULL_ADDR) || (blk_addr == NEW_ADDR)) ? \ + NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \ + GET_SEGNO_FROM_SEG0(sbi, blk_addr))) +#define GET_SECNO(sbi, segno) \ + ((segno) / sbi->segs_per_sec) +#define GET_ZONENO_FROM_SEGNO(sbi, segno) \ + ((segno / sbi->segs_per_sec) / sbi->secs_per_zone) + +#define GET_SUM_BLOCK(sbi, segno) \ + ((sbi->sm_info->ssa_blkaddr) + segno) + +#define GET_SUM_TYPE(footer) ((footer)->entry_type) +#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = type) + +#define SIT_ENTRY_OFFSET(sit_i, segno) \ + (segno % sit_i->sents_per_block) +#define SIT_BLOCK_OFFSET(sit_i, segno) \ + (segno / SIT_ENTRY_PER_BLOCK) +#define START_SEGNO(sit_i, segno) \ + (SIT_BLOCK_OFFSET(sit_i, segno) * SIT_ENTRY_PER_BLOCK) +#define SIT_BLK_CNT(sbi) \ + ((TOTAL_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK) +#define f2fs_bitmap_size(nr) \ + (BITS_TO_LONGS(nr) * sizeof(unsigned long)) +#define TOTAL_SEGS(sbi) (SM_I(sbi)->main_segments) +#define TOTAL_SECS(sbi) (sbi->total_sections) + +#define SECTOR_FROM_BLOCK(sbi, blk_addr) \ + (((sector_t)blk_addr) << (sbi)->log_sectors_per_block) +#define SECTOR_TO_BLOCK(sbi, sectors) \ + (sectors >> (sbi)->log_sectors_per_block) +#define MAX_BIO_BLOCKS(max_hw_blocks) \ + (min((int)max_hw_blocks, BIO_MAX_PAGES)) + +/* + * indicate a block allocation direction: RIGHT and LEFT. + * RIGHT means allocating new sections towards the end of volume. + * LEFT means the opposite direction. + */ +enum { + ALLOC_RIGHT = 0, + ALLOC_LEFT +}; + +/* + * In the victim_sel_policy->alloc_mode, there are two block allocation modes. + * LFS writes data sequentially with cleaning operations. + * SSR (Slack Space Recycle) reuses obsolete space without cleaning operations. + */ +enum { + LFS = 0, + SSR +}; + +/* + * In the victim_sel_policy->gc_mode, there are two gc, aka cleaning, modes. + * GC_CB is based on cost-benefit algorithm. + * GC_GREEDY is based on greedy algorithm. + */ +enum { + GC_CB = 0, + GC_GREEDY +}; + +/* + * BG_GC means the background cleaning job. + * FG_GC means the on-demand cleaning job. + */ +enum { + BG_GC = 0, + FG_GC +}; + +/* for a function parameter to select a victim segment */ +struct victim_sel_policy { + int alloc_mode; /* LFS or SSR */ + int gc_mode; /* GC_CB or GC_GREEDY */ + unsigned long *dirty_segmap; /* dirty segment bitmap */ + unsigned int max_search; /* maximum # of segments to search */ + unsigned int offset; /* last scanned bitmap offset */ + unsigned int ofs_unit; /* bitmap search unit */ + unsigned int min_cost; /* minimum cost */ + unsigned int min_segno; /* segment # having min. cost */ +}; + +struct seg_entry { + unsigned short valid_blocks; /* # of valid blocks */ + unsigned char *cur_valid_map; /* validity bitmap of blocks */ + /* + * # of valid blocks and the validity bitmap stored in the the last + * checkpoint pack. This information is used by the SSR mode. + */ + unsigned short ckpt_valid_blocks; + unsigned char *ckpt_valid_map; + unsigned char type; /* segment type like CURSEG_XXX_TYPE */ + unsigned long long mtime; /* modification time of the segment */ +}; + +struct sec_entry { + unsigned int valid_blocks; /* # of valid blocks in a section */ +}; + +struct segment_allocation { + void (*allocate_segment)(struct f2fs_sb_info *, int, bool); +}; + +struct sit_info { + const struct segment_allocation *s_ops; + + block_t sit_base_addr; /* start block address of SIT area */ + block_t sit_blocks; /* # of blocks used by SIT area */ + block_t written_valid_blocks; /* # of valid blocks in main area */ + char *sit_bitmap; /* SIT bitmap pointer */ + unsigned int bitmap_size; /* SIT bitmap size */ + + unsigned long *dirty_sentries_bitmap; /* bitmap for dirty sentries */ + unsigned int dirty_sentries; /* # of dirty sentries */ + unsigned int sents_per_block; /* # of SIT entries per block */ + struct mutex sentry_lock; /* to protect SIT cache */ + struct seg_entry *sentries; /* SIT segment-level cache */ + struct sec_entry *sec_entries; /* SIT section-level cache */ + + /* for cost-benefit algorithm in cleaning procedure */ + unsigned long long elapsed_time; /* elapsed time after mount */ + unsigned long long mounted_time; /* mount time */ + unsigned long long min_mtime; /* min. modification time */ + unsigned long long max_mtime; /* max. modification time */ +}; + +struct free_segmap_info { + unsigned int start_segno; /* start segment number logically */ + unsigned int free_segments; /* # of free segments */ + unsigned int free_sections; /* # of free sections */ + rwlock_t segmap_lock; /* free segmap lock */ + unsigned long *free_segmap; /* free segment bitmap */ + unsigned long *free_secmap; /* free section bitmap */ +}; + +/* Notice: The order of dirty type is same with CURSEG_XXX in f2fs.h */ +enum dirty_type { + DIRTY_HOT_DATA, /* dirty segments assigned as hot data logs */ + DIRTY_WARM_DATA, /* dirty segments assigned as warm data logs */ + DIRTY_COLD_DATA, /* dirty segments assigned as cold data logs */ + DIRTY_HOT_NODE, /* dirty segments assigned as hot node logs */ + DIRTY_WARM_NODE, /* dirty segments assigned as warm node logs */ + DIRTY_COLD_NODE, /* dirty segments assigned as cold node logs */ + DIRTY, /* to count # of dirty segments */ + PRE, /* to count # of entirely obsolete segments */ + NR_DIRTY_TYPE +}; + +struct dirty_seglist_info { + const struct victim_selection *v_ops; /* victim selction operation */ + unsigned long *dirty_segmap[NR_DIRTY_TYPE]; + struct mutex seglist_lock; /* lock for segment bitmaps */ + int nr_dirty[NR_DIRTY_TYPE]; /* # of dirty segments */ + unsigned long *victim_secmap; /* background GC victims */ +}; + +/* victim selection function for cleaning and SSR */ +struct victim_selection { + int (*get_victim)(struct f2fs_sb_info *, unsigned int *, + int, int, char); +}; + +/* for active log information */ +struct curseg_info { + struct mutex curseg_mutex; /* lock for consistency */ + struct f2fs_summary_block *sum_blk; /* cached summary block */ + unsigned char alloc_type; /* current allocation type */ + unsigned int segno; /* current segment number */ + unsigned short next_blkoff; /* next block offset to write */ + unsigned int zone; /* current zone number */ + unsigned int next_segno; /* preallocated segment */ +}; + +/* + * inline functions + */ +static inline struct curseg_info *CURSEG_I(struct f2fs_sb_info *sbi, int type) +{ + return (struct curseg_info *)(SM_I(sbi)->curseg_array + type); +} + +static inline struct seg_entry *get_seg_entry(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + struct sit_info *sit_i = SIT_I(sbi); + return &sit_i->sentries[segno]; +} + +static inline struct sec_entry *get_sec_entry(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + struct sit_info *sit_i = SIT_I(sbi); + return &sit_i->sec_entries[GET_SECNO(sbi, segno)]; +} + +static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi, + unsigned int segno, int section) +{ + /* + * In order to get # of valid blocks in a section instantly from many + * segments, f2fs manages two counting structures separately. + */ + if (section > 1) + return get_sec_entry(sbi, segno)->valid_blocks; + else + return get_seg_entry(sbi, segno)->valid_blocks; +} + +static inline void seg_info_from_raw_sit(struct seg_entry *se, + struct f2fs_sit_entry *rs) +{ + se->valid_blocks = GET_SIT_VBLOCKS(rs); + se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs); + memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE); + memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE); + se->type = GET_SIT_TYPE(rs); + se->mtime = le64_to_cpu(rs->mtime); +} + +static inline void seg_info_to_raw_sit(struct seg_entry *se, + struct f2fs_sit_entry *rs) +{ + unsigned short raw_vblocks = (se->type << SIT_VBLOCKS_SHIFT) | + se->valid_blocks; + rs->vblocks = cpu_to_le16(raw_vblocks); + memcpy(rs->valid_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE); + memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE); + se->ckpt_valid_blocks = se->valid_blocks; + rs->mtime = cpu_to_le64(se->mtime); +} + +static inline unsigned int find_next_inuse(struct free_segmap_info *free_i, + unsigned int max, unsigned int segno) +{ + unsigned int ret; + read_lock(&free_i->segmap_lock); + ret = find_next_bit(free_i->free_segmap, max, segno); + read_unlock(&free_i->segmap_lock); + return ret; +} + +static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int secno = segno / sbi->segs_per_sec; + unsigned int start_segno = secno * sbi->segs_per_sec; + unsigned int next; + + write_lock(&free_i->segmap_lock); + clear_bit(segno, free_i->free_segmap); + free_i->free_segments++; + + next = find_next_bit(free_i->free_segmap, TOTAL_SEGS(sbi), start_segno); + if (next >= start_segno + sbi->segs_per_sec) { + clear_bit(secno, free_i->free_secmap); + free_i->free_sections++; + } + write_unlock(&free_i->segmap_lock); +} + +static inline void __set_inuse(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int secno = segno / sbi->segs_per_sec; + set_bit(segno, free_i->free_segmap); + free_i->free_segments--; + if (!test_and_set_bit(secno, free_i->free_secmap)) + free_i->free_sections--; +} + +static inline void __set_test_and_free(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int secno = segno / sbi->segs_per_sec; + unsigned int start_segno = secno * sbi->segs_per_sec; + unsigned int next; + + write_lock(&free_i->segmap_lock); + if (test_and_clear_bit(segno, free_i->free_segmap)) { + free_i->free_segments++; + + next = find_next_bit(free_i->free_segmap, TOTAL_SEGS(sbi), + start_segno); + if (next >= start_segno + sbi->segs_per_sec) { + if (test_and_clear_bit(secno, free_i->free_secmap)) + free_i->free_sections++; + } + } + write_unlock(&free_i->segmap_lock); +} + +static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int secno = segno / sbi->segs_per_sec; + write_lock(&free_i->segmap_lock); + if (!test_and_set_bit(segno, free_i->free_segmap)) { + free_i->free_segments--; + if (!test_and_set_bit(secno, free_i->free_secmap)) + free_i->free_sections--; + } + write_unlock(&free_i->segmap_lock); +} + +static inline void get_sit_bitmap(struct f2fs_sb_info *sbi, + void *dst_addr) +{ + struct sit_info *sit_i = SIT_I(sbi); + memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size); +} + +static inline block_t written_block_count(struct f2fs_sb_info *sbi) +{ + struct sit_info *sit_i = SIT_I(sbi); + block_t vblocks; + + mutex_lock(&sit_i->sentry_lock); + vblocks = sit_i->written_valid_blocks; + mutex_unlock(&sit_i->sentry_lock); + + return vblocks; +} + +static inline unsigned int free_segments(struct f2fs_sb_info *sbi) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int free_segs; + + read_lock(&free_i->segmap_lock); + free_segs = free_i->free_segments; + read_unlock(&free_i->segmap_lock); + + return free_segs; +} + +static inline int reserved_segments(struct f2fs_sb_info *sbi) +{ + return SM_I(sbi)->reserved_segments; +} + +static inline unsigned int free_sections(struct f2fs_sb_info *sbi) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int free_secs; + + read_lock(&free_i->segmap_lock); + free_secs = free_i->free_sections; + read_unlock(&free_i->segmap_lock); + + return free_secs; +} + +static inline unsigned int prefree_segments(struct f2fs_sb_info *sbi) +{ + return DIRTY_I(sbi)->nr_dirty[PRE]; +} + +static inline unsigned int dirty_segments(struct f2fs_sb_info *sbi) +{ + return DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_DATA] + + DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_DATA] + + DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_DATA] + + DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_NODE] + + DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_NODE] + + DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_NODE]; +} + +static inline int overprovision_segments(struct f2fs_sb_info *sbi) +{ + return SM_I(sbi)->ovp_segments; +} + +static inline int overprovision_sections(struct f2fs_sb_info *sbi) +{ + return ((unsigned int) overprovision_segments(sbi)) / sbi->segs_per_sec; +} + +static inline int reserved_sections(struct f2fs_sb_info *sbi) +{ + return ((unsigned int) reserved_segments(sbi)) / sbi->segs_per_sec; +} + +static inline bool need_SSR(struct f2fs_sb_info *sbi) +{ + return ((prefree_segments(sbi) / sbi->segs_per_sec) + + free_sections(sbi) < overprovision_sections(sbi)); +} + +static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed) +{ + int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES); + int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS); + + if (unlikely(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_IPUT_DISABLE - disable IPU. (=default option) + */ +#define DEF_MIN_IPU_UTIL 70 + +enum { + F2FS_IPU_FORCE, + F2FS_IPU_SSR, + F2FS_IPU_UTIL, + F2FS_IPU_SSR_UTIL, + F2FS_IPU_DISABLE, +}; + +static inline bool need_inplace_update(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + + /* IPU can be done only for the user data */ + if (S_ISDIR(inode->i_mode)) + return false; + + switch (SM_I(sbi)->ipu_policy) { + case F2FS_IPU_FORCE: + return true; + case F2FS_IPU_SSR: + if (need_SSR(sbi)) + return true; + break; + case F2FS_IPU_UTIL: + if (utilization(sbi) > SM_I(sbi)->min_ipu_util) + return true; + break; + case F2FS_IPU_SSR_UTIL: + if (need_SSR(sbi) && utilization(sbi) > SM_I(sbi)->min_ipu_util) + return true; + break; + case F2FS_IPU_DISABLE: + break; + } + return false; +} + +static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi, + int type) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + return curseg->segno; +} + +static inline unsigned char curseg_alloc_type(struct f2fs_sb_info *sbi, + int type) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + return curseg->alloc_type; +} + +static inline unsigned short curseg_blkoff(struct f2fs_sb_info *sbi, int type) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + return curseg->next_blkoff; +} + +#ifdef CONFIG_F2FS_CHECK_FS +static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno) +{ + unsigned int end_segno = SM_I(sbi)->segment_count - 1; + BUG_ON(segno > end_segno); +} + +static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr) +{ + struct f2fs_sm_info *sm_info = SM_I(sbi); + block_t total_blks = sm_info->segment_count << sbi->log_blocks_per_seg; + block_t start_addr = sm_info->seg0_blkaddr; + block_t end_addr = start_addr + total_blks - 1; + BUG_ON(blk_addr < start_addr); + BUG_ON(blk_addr > end_addr); +} + +/* + * Summary block is always treated as invalid block + */ +static inline void check_block_count(struct f2fs_sb_info *sbi, + int segno, struct f2fs_sit_entry *raw_sit) +{ + struct f2fs_sm_info *sm_info = SM_I(sbi); + unsigned int end_segno = sm_info->segment_count - 1; + bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false; + int valid_blocks = 0; + int cur_pos = 0, next_pos; + + /* check segment usage */ + BUG_ON(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg); + + /* check boundary of a given segment number */ + BUG_ON(segno > end_segno); + + /* check bitmap with valid block count */ + do { + if (is_valid) { + next_pos = find_next_zero_bit_le(&raw_sit->valid_map, + sbi->blocks_per_seg, + cur_pos); + valid_blocks += next_pos - cur_pos; + } else + next_pos = find_next_bit_le(&raw_sit->valid_map, + sbi->blocks_per_seg, + cur_pos); + cur_pos = next_pos; + is_valid = !is_valid; + } while (cur_pos < sbi->blocks_per_seg); + BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks); +} +#else +#define check_seg_range(sbi, segno) +#define verify_block_addr(sbi, blk_addr) +#define check_block_count(sbi, segno, raw_sit) +#endif + +static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi, + unsigned int start) +{ + struct sit_info *sit_i = SIT_I(sbi); + unsigned int offset = SIT_BLOCK_OFFSET(sit_i, start); + block_t blk_addr = sit_i->sit_base_addr + offset; + + check_seg_range(sbi, start); + + /* calculate sit block address */ + if (f2fs_test_bit(offset, sit_i->sit_bitmap)) + blk_addr += sit_i->sit_blocks; + + return blk_addr; +} + +static inline pgoff_t next_sit_addr(struct f2fs_sb_info *sbi, + pgoff_t block_addr) +{ + struct sit_info *sit_i = SIT_I(sbi); + block_addr -= sit_i->sit_base_addr; + if (block_addr < sit_i->sit_blocks) + block_addr += sit_i->sit_blocks; + else + block_addr -= sit_i->sit_blocks; + + return block_addr + sit_i->sit_base_addr; +} + +static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start) +{ + unsigned int block_off = SIT_BLOCK_OFFSET(sit_i, start); + + if (f2fs_test_bit(block_off, sit_i->sit_bitmap)) + f2fs_clear_bit(block_off, sit_i->sit_bitmap); + else + f2fs_set_bit(block_off, sit_i->sit_bitmap); +} + +static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi) +{ + struct sit_info *sit_i = SIT_I(sbi); + return sit_i->elapsed_time + CURRENT_TIME_SEC.tv_sec - + sit_i->mounted_time; +} + +static inline void set_summary(struct f2fs_summary *sum, nid_t nid, + unsigned int ofs_in_node, unsigned char version) +{ + sum->nid = cpu_to_le32(nid); + sum->ofs_in_node = cpu_to_le16(ofs_in_node); + sum->version = version; +} + +static inline block_t start_sum_block(struct f2fs_sb_info *sbi) +{ + return __start_cp_addr(sbi) + + le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum); +} + +static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type) +{ + return __start_cp_addr(sbi) + + le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_total_block_count) + - (base + 1) + type; +} + +static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno) +{ + if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno)) + return true; + return false; +} + +static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi) +{ + struct block_device *bdev = sbi->sb->s_bdev; + struct request_queue *q = bdev_get_queue(bdev); + return SECTOR_TO_BLOCK(sbi, queue_max_sectors(q)); +} diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c new file mode 100644 index 0000000..f16da92 --- /dev/null +++ b/fs/f2fs/super.c @@ -0,0 +1,1158 @@ +/* + * 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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include "xattr.h" +#include "gc.h" + +#define CREATE_TRACE_POINTS +#include + +static struct proc_dir_entry *f2fs_proc_root; +static struct kmem_cache *f2fs_inode_cachep; +static struct kset *f2fs_kset; + +enum { + Opt_gc_background, + Opt_disable_roll_forward, + Opt_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_err, +}; + +static match_table_t f2fs_tokens = { + {Opt_gc_background, "background_gc=%s"}, + {Opt_disable_roll_forward, "disable_roll_forward"}, + {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_err, NULL}, +}; + +/* Sysfs support for f2fs */ +enum { + GC_THREAD, /* struct f2fs_gc_thread */ + SM_INFO, /* struct f2fs_sm_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); + 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, ipu_policy, ipu_policy); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util); + +#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(ipu_policy), + ATTR_LIST(min_ipu_util), + NULL, +}; + +static const struct sysfs_ops f2fs_attr_ops = { + .show = f2fs_attr_show, + .store = f2fs_attr_store, +}; + +static struct kobj_type f2fs_ktype = { + .default_attrs = f2fs_attrs, + .sysfs_ops = &f2fs_attr_ops, + .release = f2fs_sb_release, +}; + +void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf); + va_end(args); +} + +static void init_once(void *foo) +{ + struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo; + + inode_init_once(&fi->vfs_inode); +} + +static int parse_options(struct super_block *sb, char *options) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + substring_t args[MAX_OPT_ARGS]; + char *p, *name; + int arg = 0; + + if (!options) + return 0; + + while ((p = strsep(&options, ",")) != NULL) { + int token; + if (!*p) + continue; + /* + * Initialize args struct so we know whether arg was + * found; some options take optional arguments. + */ + args[0].to = args[0].from = NULL; + token = match_token(p, f2fs_tokens, args); + + switch (token) { + case Opt_gc_background: + name = match_strdup(&args[0]); + + if (!name) + return -ENOMEM; + if (!strncmp(name, "on", 2)) + set_opt(sbi, BG_GC); + else if (!strncmp(name, "off", 3)) + clear_opt(sbi, BG_GC); + else { + kfree(name); + return -EINVAL; + } + kfree(name); + break; + case Opt_disable_roll_forward: + set_opt(sbi, DISABLE_ROLL_FORWARD); + break; + case Opt_discard: + set_opt(sbi, DISCARD); + break; + case Opt_noheap: + set_opt(sbi, NOHEAP); + break; +#ifdef CONFIG_F2FS_FS_XATTR + case Opt_user_xattr: + set_opt(sbi, XATTR_USER); + break; + case Opt_nouser_xattr: + clear_opt(sbi, XATTR_USER); + break; + case Opt_inline_xattr: + set_opt(sbi, INLINE_XATTR); + break; +#else + case Opt_user_xattr: + f2fs_msg(sb, KERN_INFO, + "user_xattr options not supported"); + break; + case Opt_nouser_xattr: + f2fs_msg(sb, KERN_INFO, + "nouser_xattr options not supported"); + break; + case Opt_inline_xattr: + f2fs_msg(sb, KERN_INFO, + "inline_xattr options not supported"); + break; +#endif +#ifdef CONFIG_F2FS_FS_POSIX_ACL + case Opt_acl: + set_opt(sbi, POSIX_ACL); + break; + case Opt_noacl: + clear_opt(sbi, POSIX_ACL); + break; +#else + case Opt_acl: + f2fs_msg(sb, KERN_INFO, "acl options not supported"); + break; + case Opt_noacl: + f2fs_msg(sb, KERN_INFO, "noacl options not supported"); + break; +#endif + case Opt_active_logs: + if (args->from && match_int(args, &arg)) + return -EINVAL; + if (arg != 2 && arg != 4 && arg != NR_CURSEG_TYPE) + return -EINVAL; + sbi->active_logs = arg; + break; + case Opt_disable_ext_identify: + set_opt(sbi, DISABLE_EXT_IDENTIFY); + break; + case Opt_inline_data: + set_opt(sbi, INLINE_DATA); + break; + 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_dents, 0); + fi->i_current_depth = 1; + fi->i_advise = 0; + rwlock_init(&fi->ext.ext_lock); + + set_inode_flag(fi, FI_NEW_INODE); + + if (test_opt(F2FS_SB(sb), INLINE_XATTR)) + set_inode_flag(fi, FI_INLINE_XATTR); + + return &fi->vfs_inode; +} + +static int f2fs_drop_inode(struct inode *inode) +{ + /* + * This is to avoid a deadlock condition like below. + * writeback_single_inode(inode) + * - f2fs_write_data_page + * - f2fs_gc -> iput -> evict + * - inode_wait_for_writeback(inode) + */ + if (!inode_unhashed(inode) && inode->i_state & I_SYNC) + return 0; + return generic_drop_inode(inode); +} + +/* + * f2fs_dirty_inode() is called from __mark_inode_dirty() + * + * We should call set_dirty_inode to write the dirty inode through write_inode. + */ +static void f2fs_dirty_inode(struct inode *inode, int flags) +{ + set_inode_flag(F2FS_I(inode), FI_DIRTY_INODE); +} + +static void f2fs_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + kmem_cache_free(f2fs_inode_cachep, F2FS_I(inode)); +} + +static void f2fs_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, f2fs_i_callback); +} + +static void f2fs_put_super(struct super_block *sb) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + + if (sbi->s_proc) { + remove_proc_entry("segment_info", sbi->s_proc); + remove_proc_entry(sb->s_id, f2fs_proc_root); + } + kobject_del(&sbi->s_kobj); + + f2fs_destroy_stats(sbi); + stop_gc_thread(sbi); + + /* We don't need to do checkpoint when it's clean */ + if (sbi->s_dirty && get_pages(sbi, F2FS_DIRTY_NODES)) + write_checkpoint(sbi, true); + + iput(sbi->node_inode); + iput(sbi->meta_inode); + + /* destroy f2fs internal modules */ + destroy_node_manager(sbi); + destroy_segment_manager(sbi); + + kfree(sbi->ckpt); + 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 (!sbi->s_dirty && !get_pages(sbi, F2FS_DIRTY_NODES)) + return 0; + + if (sync) { + mutex_lock(&sbi->gc_mutex); + write_checkpoint(sbi, false); + mutex_unlock(&sbi->gc_mutex); + } else { + f2fs_balance_fs(sbi); + } + + return 0; +} + +static int f2fs_freeze(struct super_block *sb) +{ + int err; + + if (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; + buf->f_ffree = sbi->total_node_count - valid_inode_count(sbi); + + buf->f_namelen = F2FS_NAME_LEN; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); + + return 0; +} + +static int f2fs_show_options(struct seq_file *seq, struct dentry *root) +{ + struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb); + + if (!(root->d_sb->s_flags & MS_RDONLY) && test_opt(sbi, BG_GC)) + seq_printf(seq, ",background_gc=%s", "on"); + else + seq_printf(seq, ",background_gc=%s", "off"); + if (test_opt(sbi, DISABLE_ROLL_FORWARD)) + seq_puts(seq, ",disable_roll_forward"); + if (test_opt(sbi, DISCARD)) + seq_puts(seq, ",discard"); + if (test_opt(sbi, NOHEAP)) + seq_puts(seq, ",no_heap_alloc"); +#ifdef CONFIG_F2FS_FS_XATTR + if (test_opt(sbi, XATTR_USER)) + seq_puts(seq, ",user_xattr"); + else + seq_puts(seq, ",nouser_xattr"); + if (test_opt(sbi, INLINE_XATTR)) + seq_puts(seq, ",inline_xattr"); +#endif +#ifdef CONFIG_F2FS_FS_POSIX_ACL + if (test_opt(sbi, POSIX_ACL)) + seq_puts(seq, ",acl"); + else + seq_puts(seq, ",noacl"); +#endif + if (test_opt(sbi, DISABLE_EXT_IDENTIFY)) + seq_puts(seq, ",disable_ext_identify"); + if (test_opt(sbi, INLINE_DATA)) + seq_puts(seq, ",inline_data"); + 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; + + for (i = 0; i < total_segs; i++) { + seq_printf(seq, "%u", get_valid_blocks(sbi, i, 1)); + if (i != 0 && (i % 10) == 0) + seq_puts(seq, "\n"); + else + seq_puts(seq, " "); + } + return 0; +} + +static int segment_info_open_fs(struct inode *inode, struct file *file) +{ + return single_open(file, segment_info_seq_show, PDE_DATA(inode)); +} + +static const struct file_operations f2fs_seq_segment_info_fops = { + .owner = THIS_MODULE, + .open = segment_info_open_fs, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int f2fs_remount(struct super_block *sb, int *flags, char *data) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct f2fs_mount_info org_mount_opt; + int err, active_logs; + + /* + * Save the old mount options in case we + * need to restore them. + */ + org_mount_opt = sbi->mount_opt; + active_logs = sbi->active_logs; + + /* parse mount options */ + err = parse_options(sb, data); + if (err) + goto restore_opts; + + /* + * Previous and new state of filesystem is RO, + * so no point in checking GC conditions. + */ + if ((sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) + goto skip; + + /* + * We stop the GC thread if FS is mounted as RO + * or if background_gc = off is passed in mount + * option. Also sync the filesystem. + */ + if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) { + if (sbi->gc_thread) { + stop_gc_thread(sbi); + f2fs_sync_fs(sb, 1); + } + } else if (test_opt(sbi, BG_GC) && !sbi->gc_thread) { + err = start_gc_thread(sbi); + if (err) + goto restore_opts; + } +skip: + /* Update the POSIXACL Flag */ + sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | + (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0); + return 0; + +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 (unlikely(ino < F2FS_ROOT_INO(sbi))) + return ERR_PTR(-ESTALE); + + /* + * f2fs_iget isn't quite right if the inode is currently unallocated! + * However f2fs_iget currently does appropriate checks to handle stale + * inodes so everything is OK. + */ + inode = f2fs_iget(sb, ino); + if (IS_ERR(inode)) + return ERR_CAST(inode); + if (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; + } + + if (le32_to_cpu(raw_super->log_sectorsize) != + F2FS_LOG_SECTOR_SIZE) { + f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize"); + return 1; + } + if (le32_to_cpu(raw_super->log_sectors_per_block) != + F2FS_LOG_SECTORS_PER_BLOCK) { + f2fs_msg(sb, KERN_INFO, "Invalid log sectors per block"); + return 1; + } + 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(is_set_ckpt_flags(ckpt, CP_ERROR_FLAG))) { + f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck"); + return 1; + } + return 0; +} + +static void init_sb_info(struct f2fs_sb_info *sbi) +{ + struct f2fs_super_block *raw_super = sbi->raw_super; + int i; + + sbi->log_sectors_per_block = + le32_to_cpu(raw_super->log_sectors_per_block); + sbi->log_blocksize = le32_to_cpu(raw_super->log_blocksize); + sbi->blocksize = 1 << sbi->log_blocksize; + sbi->log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg); + sbi->blocks_per_seg = 1 << sbi->log_blocks_per_seg; + sbi->segs_per_sec = le32_to_cpu(raw_super->segs_per_sec); + sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone); + sbi->total_sections = le32_to_cpu(raw_super->section_count); + sbi->total_node_count = + (le32_to_cpu(raw_super->segment_count_nat) / 2) + * sbi->blocks_per_seg * NAT_ENTRY_PER_BLOCK; + sbi->root_ino_num = le32_to_cpu(raw_super->root_ino); + sbi->node_ino_num = le32_to_cpu(raw_super->node_ino); + sbi->meta_ino_num = le32_to_cpu(raw_super->meta_ino); + sbi->cur_victim_sec = NULL_SECNO; + + for (i = 0; i < NR_COUNT_TYPE; i++) + atomic_set(&sbi->nr_pages[i], 0); +} + +/* + * Read f2fs raw super block. + * Because we have two copies of super block, so read the first one at first, + * if the first one is invalid, move to read the second one. + */ +static int read_raw_super_block(struct super_block *sb, + struct f2fs_super_block **raw_super, + struct buffer_head **raw_super_buf) +{ + int block = 0; + +retry: + *raw_super_buf = sb_bread(sb, block); + if (!*raw_super_buf) { + f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock", + block + 1); + if (block == 0) { + block++; + goto retry; + } else { + return -EIO; + } + } + + *raw_super = (struct f2fs_super_block *) + ((char *)(*raw_super_buf)->b_data + F2FS_SUPER_OFFSET); + + /* sanity checking of raw super */ + if (sanity_check_raw_super(sb, *raw_super)) { + brelse(*raw_super_buf); + f2fs_msg(sb, KERN_ERR, "Can't find a valid F2FS filesystem " + "in %dth superblock", block + 1); + if (block == 0) { + block++; + goto retry; + } else { + return -EINVAL; + } + } + + return 0; +} + +static int f2fs_fill_super(struct super_block *sb, void *data, int silent) +{ + struct f2fs_sb_info *sbi; + struct f2fs_super_block *raw_super; + struct buffer_head *raw_super_buf; + struct inode *root; + long err = -EINVAL; + int i; + + /* allocate memory for f2fs-specific super block info */ + sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL); + if (!sbi) + return -ENOMEM; + + /* set a block size */ + if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) { + f2fs_msg(sb, KERN_ERR, "unable to set blocksize"); + goto free_sbi; + } + + err = read_raw_super_block(sb, &raw_super, &raw_super_buf); + if (err) + goto free_sbi; + + sb->s_fs_info = sbi; + /* init some FS parameters */ + sbi->active_logs = NR_CURSEG_TYPE; + + set_opt(sbi, BG_GC); + +#ifdef CONFIG_F2FS_FS_XATTR + set_opt(sbi, XATTR_USER); +#endif +#ifdef CONFIG_F2FS_FS_POSIX_ACL + set_opt(sbi, POSIX_ACL); +#endif + /* parse mount options */ + err = parse_options(sb, (char *)data); + if (err) + goto free_sb_buf; + + sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize)); + sb->s_max_links = F2FS_LINK_MAX; + get_random_bytes(&sbi->s_next_generation, sizeof(u32)); + + sb->s_op = &f2fs_sops; + sb->s_xattr = f2fs_xattr_handlers; + sb->s_export_op = &f2fs_export_ops; + sb->s_magic = F2FS_SUPER_MAGIC; + sb->s_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); + mutex_init(&sbi->node_write); + sbi->por_doing = false; + spin_lock_init(&sbi->stat_lock); + + mutex_init(&sbi->read_io.io_mutex); + sbi->read_io.sbi = sbi; + sbi->read_io.bio = NULL; + for (i = 0; i < NR_PAGE_TYPE; i++) { + mutex_init(&sbi->write_io[i].io_mutex); + 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_sb_buf; + } + + err = get_valid_checkpoint(sbi); + if (err) { + f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint"); + goto free_meta_inode; + } + + /* sanity checking of checkpoint */ + err = -EINVAL; + if (sanity_check_ckpt(sbi)) { + f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint"); + goto free_cp; + } + + sbi->total_valid_node_count = + le32_to_cpu(sbi->ckpt->valid_node_count); + sbi->total_valid_inode_count = + le32_to_cpu(sbi->ckpt->valid_inode_count); + sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count); + sbi->total_valid_block_count = + le64_to_cpu(sbi->ckpt->valid_block_count); + sbi->last_valid_block_count = sbi->total_valid_block_count; + sbi->alloc_valid_block_count = 0; + INIT_LIST_HEAD(&sbi->dir_inode_list); + spin_lock_init(&sbi->dir_inode_lock); + + init_orphan_info(sbi); + + /* setup f2fs internal modules */ + err = build_segment_manager(sbi); + if (err) { + f2fs_msg(sb, KERN_ERR, + "Failed to initialize F2FS segment manager"); + goto free_sm; + } + err = build_node_manager(sbi); + if (err) { + f2fs_msg(sb, KERN_ERR, + "Failed to initialize F2FS node manager"); + goto free_nm; + } + + build_gc_manager(sbi); + + /* get an inode for node space */ + sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi)); + if (IS_ERR(sbi->node_inode)) { + f2fs_msg(sb, KERN_ERR, "Failed to read node inode"); + err = PTR_ERR(sbi->node_inode); + goto free_nm; + } + + /* if there are nt orphan nodes free them */ + recover_orphan_inodes(sbi); + + /* read root inode and dentry */ + root = f2fs_iget(sb, F2FS_ROOT_INO(sbi)); + if (IS_ERR(root)) { + f2fs_msg(sb, KERN_ERR, "Failed to read root inode"); + err = PTR_ERR(root); + goto free_node_inode; + } + if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { + err = -EINVAL; + goto free_root_inode; + } + + sb->s_root = d_make_root(root); /* allocate root dentry */ + if (!sb->s_root) { + err = -ENOMEM; + goto free_root_inode; + } + + /* recover fsynced data */ + if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) { + err = recover_fsync_data(sbi); + if (err) + f2fs_msg(sb, KERN_ERR, + "Cannot recover all fsync data errno=%ld", err); + } + + /* + * If filesystem is not mounted as read-only then + * do start the gc_thread. + */ + if (!(sb->s_flags & MS_RDONLY)) { + /* After POR, we can run background GC thread.*/ + err = start_gc_thread(sbi); + if (err) + goto free_gc; + } + + err = f2fs_build_stats(sbi); + if (err) + goto free_gc; + + if (f2fs_proc_root) + sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root); + + if (sbi->s_proc) + proc_create_data("segment_info", S_IRUGO, sbi->s_proc, + &f2fs_seq_segment_info_fops, sb); + + if (test_opt(sbi, DISCARD)) { + struct request_queue *q = bdev_get_queue(sb->s_bdev); + if (!blk_queue_discard(q)) + f2fs_msg(sb, KERN_WARNING, + "mounting with \"discard\" option, but " + "the device does not support discard"); + } + + sbi->s_kobj.kset = f2fs_kset; + init_completion(&sbi->s_kobj_unregister); + err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL, + "%s", sb->s_id); + if (err) + goto fail; + + return 0; +fail: + 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_gc: + stop_gc_thread(sbi); +free_root_inode: + dput(sb->s_root); + sb->s_root = NULL; +free_node_inode: + iput(sbi->node_inode); +free_nm: + destroy_node_manager(sbi); +free_sm: + destroy_segment_manager(sbi); +free_cp: + kfree(sbi->ckpt); +free_meta_inode: + make_bad_inode(sbi->meta_inode); + iput(sbi->meta_inode); +free_sb_buf: + brelse(raw_super_buf); +free_sbi: + kfree(sbi); + return err; +} + +static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) +{ + return mount_bdev(fs_type, flags, dev_name, data, f2fs_fill_super); +} + +static struct file_system_type f2fs_fs_type = { + .owner = THIS_MODULE, + .name = "f2fs", + .mount = f2fs_mount, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, +}; +MODULE_ALIAS_FS("f2fs"); + +static int __init init_inodecache(void) +{ + f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache", + sizeof(struct f2fs_inode_info), NULL); + if (!f2fs_inode_cachep) + return -ENOMEM; + return 0; +} + +static void destroy_inodecache(void) +{ + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); + kmem_cache_destroy(f2fs_inode_cachep); +} + +static int __init init_f2fs_fs(void) +{ + int err; + + err = init_inodecache(); + if (err) + goto fail; + err = create_node_manager_caches(); + if (err) + goto free_inodecache; + err = create_segment_manager_caches(); + if (err) + goto free_node_manager_caches; + err = create_gc_caches(); + if (err) + goto free_segment_manager_caches; + err = create_checkpoint_caches(); + if (err) + goto free_gc_caches; + f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj); + if (!f2fs_kset) { + err = -ENOMEM; + goto free_checkpoint_caches; + } + err = register_filesystem(&f2fs_fs_type); + if (err) + goto free_kset; + f2fs_create_root_stats(); + f2fs_proc_root = proc_mkdir("fs/f2fs", NULL); + return 0; + +free_kset: + kset_unregister(f2fs_kset); +free_checkpoint_caches: + destroy_checkpoint_caches(); +free_gc_caches: + destroy_gc_caches(); +free_segment_manager_caches: + destroy_segment_manager_caches(); +free_node_manager_caches: + destroy_node_manager_caches(); +free_inodecache: + destroy_inodecache(); +fail: + return err; +} + +static void __exit exit_f2fs_fs(void) +{ + remove_proc_entry("fs/f2fs", NULL); + f2fs_destroy_root_stats(); + unregister_filesystem(&f2fs_fs_type); + destroy_checkpoint_caches(); + destroy_gc_caches(); + destroy_segment_manager_caches(); + destroy_node_manager_caches(); + destroy_inodecache(); + kset_unregister(f2fs_kset); +} + +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/xattr.c b/fs/f2fs/xattr.c new file mode 100644 index 0000000..b0fb8a2 --- /dev/null +++ b/fs/f2fs/xattr.c @@ -0,0 +1,596 @@ +/* + * 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 + * + * Fix by Harrison Xing . + * Extended attributes for symlinks and special files added per + * suggestion of Luka Renko . + * xattr consolidation Copyright (c) 2004 James Morris , + * 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 +#include +#include +#include "f2fs.h" +#include "xattr.h" + +static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); + int total_len, prefix_len = 0; + const char *prefix = NULL; + + switch (type) { + case F2FS_XATTR_INDEX_USER: + if (!test_opt(sbi, XATTR_USER)) + return -EOPNOTSUPP; + prefix = XATTR_USER_PREFIX; + prefix_len = XATTR_USER_PREFIX_LEN; + break; + case F2FS_XATTR_INDEX_TRUSTED: + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + prefix = XATTR_TRUSTED_PREFIX; + prefix_len = XATTR_TRUSTED_PREFIX_LEN; + break; + case F2FS_XATTR_INDEX_SECURITY: + prefix = XATTR_SECURITY_PREFIX; + prefix_len = XATTR_SECURITY_PREFIX_LEN; + break; + default: + return -EINVAL; + } + + total_len = prefix_len + name_len + 1; + if (list && total_len <= list_size) { + memcpy(list, prefix, prefix_len); + memcpy(list + prefix_len, name, name_len); + list[prefix_len + name_len] = '\0'; + } + return total_len; +} + +static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); + + switch (type) { + case F2FS_XATTR_INDEX_USER: + if (!test_opt(sbi, XATTR_USER)) + return -EOPNOTSUPP; + break; + case F2FS_XATTR_INDEX_TRUSTED: + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + break; + 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); +} + +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); +} + +static size_t f2fs_xattr_advise_list(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + const char *xname = F2FS_SYSTEM_ADVISE_PREFIX; + size_t size; + + if (type != F2FS_XATTR_INDEX_ADVISE) + return 0; + + size = strlen(xname) + 1; + if (list && size <= list_size) + memcpy(list, xname, size); + return size; +} + +static int f2fs_xattr_advise_get(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + struct inode *inode = dentry->d_inode; + + if (strcmp(name, "") != 0) + return -EINVAL; + + *((char *)buffer) = F2FS_I(inode)->i_advise; + return sizeof(char); +} + +static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, int type) +{ + struct inode *inode = dentry->d_inode; + + if (strcmp(name, "") != 0) + return -EINVAL; + if (!inode_owner_or_capable(inode)) + return -EPERM; + if (value == NULL) + return -EINVAL; + + F2FS_I(inode)->i_advise |= *(char *)value; + return 0; +} + +#ifdef CONFIG_F2FS_FS_SECURITY +static int __f2fs_setxattr(struct inode *inode, int name_index, + const char *name, const void *value, size_t value_len, + struct page *ipage); +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); + 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 name_index) +{ + const struct xattr_handler *handler = NULL; + + if (name_index > 0 && name_index < ARRAY_SIZE(f2fs_xattr_handler_map)) + handler = f2fs_xattr_handler_map[name_index]; + return handler; +} + +static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int name_index, + size_t name_len, const char *name) +{ + struct f2fs_xattr_entry *entry; + + list_for_each_xattr(entry, base_addr) { + if (entry->e_name_index != name_index) + continue; + if (entry->e_name_len != name_len) + continue; + if (!memcmp(entry->e_name, name, name_len)) + break; + } + return entry; +} + +static void *read_all_xattrs(struct inode *inode, struct page *ipage) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + 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_KERNEL); + 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_SB(inode->i_sb); + 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); + } 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); + } + 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(new_nid); + } 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 name_index, const char *name, + void *buffer, size_t buffer_size) +{ + struct f2fs_xattr_entry *entry; + void *base_addr; + int error = 0; + size_t value_len, name_len; + + if (name == NULL) + return -EINVAL; + name_len = strlen(name); + + base_addr = read_all_xattrs(inode, NULL); + if (!base_addr) + return -ENOMEM; + + entry = __find_xattr(base_addr, name_index, name_len, name); + if (IS_XATTR_LAST_ENTRY(entry)) { + error = -ENODATA; + goto cleanup; + } + + value_len = le16_to_cpu(entry->e_value_size); + + if (buffer && value_len > buffer_size) { + error = -ERANGE; + goto cleanup; + } + + if (buffer) { + char *pval = entry->e_name + entry->e_name_len; + memcpy(buffer, pval, value_len); + } + error = value_len; + +cleanup: + 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 name_index, + const char *name, const void *value, size_t value_len, + struct page *ipage) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_xattr_entry *here, *last; + void *base_addr; + int found, newsize; + size_t name_len; + __u32 new_hsize; + int error = -ENOMEM; + + if (name == NULL) + return -EINVAL; + + if (value == NULL) + value_len = 0; + + name_len = strlen(name); + + if (name_len > F2FS_NAME_LEN || value_len > MAX_VALUE_LEN(inode)) + return -ERANGE; + + base_addr = read_all_xattrs(inode, ipage); + if (!base_addr) + goto exit; + + /* find entry with wanted name. */ + here = __find_xattr(base_addr, name_index, name_len, name); + + found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1; + last = here; + + while (!IS_XATTR_LAST_ENTRY(last)) + last = XATTR_NEXT_ENTRY(last); + + newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + + name_len + value_len); + + /* 1. Check space */ + if (value) { + int free; + /* + * If value is NULL, it is remove operation. + * In case of update operation, we caculate 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 = name_index; + last->e_name_len = name_len; + memcpy(last->e_name, name, name_len); + pval = last->e_name + name_len; + memcpy(pval, value, value_len); + last->e_value_size = cpu_to_le16(value_len); + new_hsize += newsize; + } + + error = write_all_xattrs(inode, new_hsize, base_addr, ipage); + if (error) + goto exit; + + if (is_inode_flag_set(fi, FI_ACL_MODE)) { + inode->i_mode = fi->i_acl_mode; + inode->i_ctime = CURRENT_TIME; + clear_inode_flag(fi, FI_ACL_MODE); + } + + if (ipage) + update_inode(inode, ipage); + else + update_inode_page(inode); +exit: + kzfree(base_addr); + return error; +} + +int f2fs_setxattr(struct inode *inode, int name_index, const char *name, + const void *value, size_t value_len, struct page *ipage) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + int err; + + f2fs_balance_fs(sbi); + + f2fs_lock_op(sbi); + err = __f2fs_setxattr(inode, name_index, name, value, value_len, ipage); + f2fs_unlock_op(sbi); + + return err; +} diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h new file mode 100644 index 0000000..02a08fb --- /dev/null +++ b/fs/f2fs/xattr.h @@ -0,0 +1,152 @@ +/* + * fs/f2fs/xattr.h + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * Portions of this code from linux/fs/ext2/xattr.h + * + * On-disk format of extended attributes for the ext2 filesystem. + * + * (C) 2001 Andreas Gruenbacher, + * + * 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 +#include + +/* Magic value in attribute blocks */ +#define F2FS_XATTR_MAGIC 0xF2F52011 + +/* Maximum number of references to one attribute block */ +#define F2FS_XATTR_REFCOUNT_MAX 1024 + +/* Name indexes */ +#define F2FS_SYSTEM_ADVISE_PREFIX "system.advise" +#define F2FS_XATTR_INDEX_USER 1 +#define F2FS_XATTR_INDEX_POSIX_ACL_ACCESS 2 +#define F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT 3 +#define F2FS_XATTR_INDEX_TRUSTED 4 +#define F2FS_XATTR_INDEX_LUSTRE 5 +#define F2FS_XATTR_INDEX_SECURITY 6 +#define F2FS_XATTR_INDEX_ADVISE 7 + +struct f2fs_xattr_header { + __le32 h_magic; /* magic number for identification */ + __le32 h_refcount; /* reference count */ + __u32 h_reserved[4]; /* zero right now */ +}; + +struct f2fs_xattr_entry { + __u8 e_name_index; + __u8 e_name_len; + __le16 e_value_size; /* size of attribute value */ + char e_name[0]; /* attribute name */ +}; + +#define XATTR_HDR(ptr) ((struct f2fs_xattr_header *)(ptr)) +#define XATTR_ENTRY(ptr) ((struct f2fs_xattr_entry *)(ptr)) +#define XATTR_FIRST_ENTRY(ptr) (XATTR_ENTRY(XATTR_HDR(ptr) + 1)) +#define XATTR_ROUND (3) + +#define XATTR_ALIGN(size) ((size + XATTR_ROUND) & ~XATTR_ROUND) + +#define ENTRY_SIZE(entry) (XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + \ + entry->e_name_len + le16_to_cpu(entry->e_value_size))) + +#define XATTR_NEXT_ENTRY(entry) ((struct f2fs_xattr_entry *)((char *)(entry) +\ + ENTRY_SIZE(entry))) + +#define IS_XATTR_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0) + +#define list_for_each_xattr(entry, addr) \ + for (entry = XATTR_FIRST_ENTRY(addr);\ + !IS_XATTR_LAST_ENTRY(entry);\ + entry = XATTR_NEXT_ENTRY(entry)) + +#define MIN_OFFSET(i) XATTR_ALIGN(inline_xattr_size(i) + PAGE_SIZE - \ + sizeof(struct node_footer) - sizeof(__u32)) + +#define MAX_VALUE_LEN(i) (MIN_OFFSET(i) - \ + sizeof(struct f2fs_xattr_header) - \ + sizeof(struct f2fs_xattr_entry)) + +/* + * On-disk structure of f2fs_xattr + * We use inline xattrs space + 1 block for xattr. + * + * +--------------------+ + * | f2fs_xattr_header | + * | | + * +--------------------+ + * | f2fs_xattr_entry | + * | .e_name_index = 1 | + * | .e_name_len = 3 | + * | .e_value_size = 14 | + * | .e_name = "foo" | + * | "value_of_xattr" |<- value_offs = e_name + e_name_len + * +--------------------+ + * | f2fs_xattr_entry | + * | .e_name_index = 4 | + * | .e_name = "bar" | + * +--------------------+ + * | | + * | Free | + * | | + * +--------------------+<- MIN_OFFSET + * | node_footer | + * | (nid, ino, offset) | + * +--------------------+ + * + **/ + +#ifdef CONFIG_F2FS_FS_XATTR +extern const struct xattr_handler f2fs_xattr_user_handler; +extern const struct xattr_handler f2fs_xattr_trusted_handler; +extern const struct xattr_handler f2fs_xattr_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 *); +extern int f2fs_getxattr(struct inode *, int, const char *, void *, size_t); +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 name_index, + const char *name, const void *value, size_t value_len) +{ + return -EOPNOTSUPP; +} +static inline int f2fs_getxattr(struct inode *inode, int name_index, + const char *name, void *buffer, size_t buffer_size) +{ + return -EOPNOTSUPP; +} +static inline ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, + size_t buffer_size) +{ + return -EOPNOTSUPP; +} +#endif + +#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..da74d87 --- /dev/null +++ b/include/linux/f2fs_fs.h @@ -0,0 +1,431 @@ +/** + * 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 +#include + +#define F2FS_SUPER_OFFSET 1024 /* byte-size offset */ +#define F2FS_LOG_SECTOR_SIZE 9 /* 9 bits for 512 byte */ +#define F2FS_LOG_SECTORS_PER_BLOCK 3 /* 4KB: F2FS_BLKSIZE */ +#define F2FS_BLKSIZE 4096 /* support only 4KB block */ +#define F2FS_MAX_EXTENSION 64 /* # of extension entries */ + +#define NULL_ADDR ((block_t)0) /* used as block_t addresses */ +#define NEW_ADDR ((block_t)-1) /* used as block_t addresses */ + +#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) + +/* + * 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 + +/* + * 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 */ +} __packed; + +/* + * For checkpoint + */ +#define CP_ERROR_FLAG 0x00000008 +#define CP_COMPACT_SUM_FLAG 0x00000004 +#define CP_ORPHAN_PRESENT_FLAG 0x00000002 +#define CP_UMOUNT_FLAG 0x00000001 + +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 + +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_addr; /* 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 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 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 MAX_INLINE_DATA (sizeof(__le32) * (DEF_ADDRS_PER_INODE - \ + F2FS_INLINE_XATTR_ADDRS - 1)) + +#define INLINE_DATA_OFFSET (PAGE_CACHE_SIZE - sizeof(struct node_footer) \ + - sizeof(__le32) * (DEF_ADDRS_PER_INODE + 5 - 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_reserved2; /* for backward compatibility */ + + struct f2fs_extent i_ext; /* caching a largest extent */ + + __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ + + __le32 i_nid[5]; /* 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 +}; + +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) + +/* the number of dentry in a block */ +#define NR_DENTRY_IN_BLOCK 214 + +/* MAX level for dir lookup */ +#define MAX_DIR_HASH_DEPTH 63 + +#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; + +/* 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/linux/magic.h b/include/linux/magic.h index 1e5df2a..2616b54 100644 --- a/include/linux/magic.h +++ b/include/linux/magic.h @@ -24,6 +24,7 @@ #define EXT4_SUPER_MAGIC 0xEF53 #define BTRFS_SUPER_MAGIC 0x9123683E #define NILFS_SUPER_MAGIC 0x3434 +#define F2FS_SUPER_MAGIC 0xF2F52010 #define HPFS_SUPER_MAGIC 0xf995e849 #define ISOFS_SUPER_MAGIC 0x9660 #define JFFS2_SUPER_MAGIC 0x72b6 diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h new file mode 100644 index 0000000..3b9f28d --- /dev/null +++ b/include/trace/events/f2fs.h @@ -0,0 +1,790 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM f2fs + +#if !defined(_TRACE_F2FS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_F2FS_H + +#include + +#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" }) + +#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" }) + +struct victim_sel_policy; + +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, bool 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(bool, 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 = F2FS_SB(sb)->s_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_CONDITION(f2fs_submit_page_bio, + + TP_PROTO(struct page *page, sector_t blkaddr, int type), + + TP_ARGS(page, blkaddr, type), + + TP_CONDITION(page->mapping), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(pgoff_t, index) + __field(sector_t, blkaddr) + __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 = blkaddr; + __entry->type = type; + ), + + TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, " + "blkaddr = 0x%llx, bio_type = %s%s", + show_dev_ino(__entry), + (unsigned long)__entry->index, + (unsigned long long)__entry->blkaddr, + show_bio_type(__entry->type)) +); + +TRACE_EVENT(f2fs_get_data_block, + TP_PROTO(struct inode *inode, sector_t iblock, + struct buffer_head *bh, int ret), + + TP_ARGS(inode, iblock, bh, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(sector_t, iblock) + __field(sector_t, bh_start) + __field(size_t, bh_size) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->iblock = iblock; + __entry->bh_start = bh->b_blocknr; + __entry->bh_size = bh->b_size; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, " + "start blkaddr = 0x%llx, len = 0x%llx bytes, err = %d", + show_dev_ino(__entry), + (unsigned long long)__entry->iblock, + (unsigned long long)__entry->bh_start, + (unsigned long long)__entry->bh_size, + __entry->ret) +); + +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_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_bio, + + TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio), + + TP_ARGS(sb, rw, type, 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 = rw; + __entry->type = 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, int rw, int type, struct bio *bio), + + TP_ARGS(sb, rw, type, bio), + + TP_CONDITION(bio) +); + +DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_read_bio, + + TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio), + + TP_ARGS(sb, rw, type, bio), + + TP_CONDITION(bio) +); + +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) + ), + + 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); + ), + + TP_printk("dev = (%d,%d), ino = %lu, %s, %s, index = %lu, dirty = %d", + show_dev_ino(__entry), + show_block_type(__entry->type), + show_file_type(__entry->dir), + (unsigned long)__entry->index, + __entry->dirty) +); + +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) +); + +TRACE_EVENT(f2fs_submit_page_mbio, + + TP_PROTO(struct page *page, int rw, int type, block_t blk_addr), + + TP_ARGS(page, rw, type, blk_addr), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(int, rw) + __field(int, type) + __field(pgoff_t, index) + __field(block_t, block) + ), + + TP_fast_assign( + __entry->dev = page->mapping->host->i_sb->s_dev; + __entry->ino = page->mapping->host->i_ino; + __entry->rw = rw; + __entry->type = type; + __entry->index = page->index; + __entry->block = blk_addr; + ), + + TP_printk("dev = (%d,%d), ino = %lu, %s%s, %s, index = %lu, blkaddr = 0x%llx", + show_dev_ino(__entry), + show_bio_type(__entry->rw), + show_block_type(__entry->type), + (unsigned long)__entry->index, + (unsigned long long)__entry->block) +); + +TRACE_EVENT(f2fs_write_checkpoint, + + TP_PROTO(struct super_block *sb, bool is_umount, char *msg), + + TP_ARGS(sb, is_umount, msg), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(bool, is_umount) + __field(char *, msg) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->is_umount = is_umount; + __entry->msg = msg; + ), + + TP_printk("dev = (%d,%d), checkpoint for %s, state = %s", + show_dev(__entry), + __entry->is_umount ? "clean umount" : "consistency", + __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) +); +#endif /* _TRACE_F2FS_H */ + + /* This part must be outside protection */ +#include -- cgit v1.1