diff options
112 files changed, 17259 insertions, 1980 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-rbd b/Documentation/ABI/testing/sysfs-bus-rbd index 1cf2adf46b11..cd9213ccf3dc 100644 --- a/Documentation/ABI/testing/sysfs-bus-rbd +++ b/Documentation/ABI/testing/sysfs-bus-rbd @@ -70,6 +70,10 @@ snap_* A directory per each snapshot +parent + + Information identifying the pool, image, and snapshot id for + the parent image in a layered rbd image (format 2 only). Entries under /sys/bus/rbd/devices/<dev-id>/snap_<snap-name> ------------------------------------------------------------- diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt index a0b6250add79..4a4fb295ceef 100644 --- a/Documentation/DMA-API-HOWTO.txt +++ b/Documentation/DMA-API-HOWTO.txt @@ -468,11 +468,46 @@ To map a single region, you do: size_t size = buffer->len; dma_handle = dma_map_single(dev, addr, size, direction); + if (dma_mapping_error(dma_handle)) { + /* + * reduce current DMA mapping usage, + * delay and try again later or + * reset driver. + */ + goto map_error_handling; + } and to unmap it: dma_unmap_single(dev, dma_handle, size, direction); +You should call dma_mapping_error() as dma_map_single() could fail and return +error. Not all dma implementations support dma_mapping_error() interface. +However, it is a good practice to call dma_mapping_error() interface, which +will invoke the generic mapping error check interface. Doing so will ensure +that the mapping code will work correctly on all dma implementations without +any dependency on the specifics of the underlying implementation. Using the +returned address without checking for errors could result in failures ranging +from panics to silent data corruption. Couple of example of incorrect ways to +check for errors that make assumptions about the underlying dma implementation +are as follows and these are applicable to dma_map_page() as well. + +Incorrect example 1: + dma_addr_t dma_handle; + + dma_handle = dma_map_single(dev, addr, size, direction); + if ((dma_handle & 0xffff != 0) || (dma_handle >= 0x1000000)) { + goto map_error; + } + +Incorrect example 2: + dma_addr_t dma_handle; + + dma_handle = dma_map_single(dev, addr, size, direction); + if (dma_handle == DMA_ERROR_CODE) { + goto map_error; + } + You should call dma_unmap_single when the DMA activity is finished, e.g. from the interrupt which told you that the DMA transfer is done. @@ -489,6 +524,14 @@ Specifically: size_t size = buffer->len; dma_handle = dma_map_page(dev, page, offset, size, direction); + if (dma_mapping_error(dma_handle)) { + /* + * reduce current DMA mapping usage, + * delay and try again later or + * reset driver. + */ + goto map_error_handling; + } ... @@ -496,6 +539,12 @@ Specifically: Here, "offset" means byte offset within the given page. +You should call dma_mapping_error() as dma_map_page() could fail and return +error as outlined under the dma_map_single() discussion. + +You should call dma_unmap_page when the DMA activity is finished, e.g. +from the interrupt which told you that the DMA transfer is done. + With scatterlists, you map a region gathered from several regions by: int i, count = dma_map_sg(dev, sglist, nents, direction); @@ -578,6 +627,14 @@ to use the dma_sync_*() interfaces. dma_addr_t mapping; mapping = dma_map_single(cp->dev, buffer, len, DMA_FROM_DEVICE); + if (dma_mapping_error(dma_handle)) { + /* + * reduce current DMA mapping usage, + * delay and try again later or + * reset driver. + */ + goto map_error_handling; + } cp->rx_buf = buffer; cp->rx_len = len; @@ -658,6 +715,75 @@ failure can be determined by: * delay and try again later or * reset driver. */ + goto map_error_handling; + } + +- unmap pages that are already mapped, when mapping error occurs in the middle + of a multiple page mapping attempt. These example are applicable to + dma_map_page() as well. + +Example 1: + dma_addr_t dma_handle1; + dma_addr_t dma_handle2; + + dma_handle1 = dma_map_single(dev, addr, size, direction); + if (dma_mapping_error(dev, dma_handle1)) { + /* + * reduce current DMA mapping usage, + * delay and try again later or + * reset driver. + */ + goto map_error_handling1; + } + dma_handle2 = dma_map_single(dev, addr, size, direction); + if (dma_mapping_error(dev, dma_handle2)) { + /* + * reduce current DMA mapping usage, + * delay and try again later or + * reset driver. + */ + goto map_error_handling2; + } + + ... + + map_error_handling2: + dma_unmap_single(dma_handle1); + map_error_handling1: + +Example 2: (if buffers are allocated a loop, unmap all mapped buffers when + mapping error is detected in the middle) + + dma_addr_t dma_addr; + dma_addr_t array[DMA_BUFFERS]; + int save_index = 0; + + for (i = 0; i < DMA_BUFFERS; i++) { + + ... + + dma_addr = dma_map_single(dev, addr, size, direction); + if (dma_mapping_error(dev, dma_addr)) { + /* + * reduce current DMA mapping usage, + * delay and try again later or + * reset driver. + */ + goto map_error_handling; + } + array[i].dma_addr = dma_addr; + save_index++; + } + + ... + + map_error_handling: + + for (i = 0; i < save_index; i++) { + + ... + + dma_unmap_single(array[i].dma_addr); } Networking drivers must call dev_kfree_skb to free the socket buffer diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index 66bd97a95f10..78a6c569d204 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -678,3 +678,15 @@ out of dma_debug_entries. These entries are preallocated at boot. The number of preallocated entries is defined per architecture. If it is too low for you boot with 'dma_debug_entries=<your_desired_number>' to overwrite the architectural default. + +void debug_dmap_mapping_error(struct device *dev, dma_addr_t dma_addr); + +dma-debug interface debug_dma_mapping_error() to debug drivers that fail +to check dma mapping errors on addresses returned by dma_map_single() and +dma_map_page() interfaces. This interface clears a flag set by +debug_dma_map_page() to indicate that dma_mapping_error() has been called by +the driver. When driver does unmap, debug_dma_unmap() checks the flag and if +this flag is still set, prints warning message that includes call trace that +leads up to the unmap. This interface can be called from dma_mapping_error() +routines to enable dma mapping error check debugging. + diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX index 7b52ba7bf32a..8042050eb265 100644 --- a/Documentation/filesystems/00-INDEX +++ b/Documentation/filesystems/00-INDEX @@ -50,6 +50,8 @@ 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 000000000000..8fbd8b46ee34 --- /dev/null +++ b/Documentation/filesystems/f2fs.txt @@ -0,0 +1,421 @@ +================================================================================ +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 file system formatting tool, "mkfs.f2fs", is available from the following +git tree: +>> 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_off Turn off cleaning operations, namely garbage collection, + triggered in background when I/O subsystem is idle. +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. + +================================================================================ +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. + +================================================================================ +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 + +Format options +-------------- +-l [label] : Give a volume label, up to 256 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" + +================================================================================ +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 + _________________________________________________________________________ + | | | Node | Segment | Segment | | + | Superblock | Checkpoint | Address | Info. | Summary | Main | + | (SB) | (CP) | Table (NAT) | Table (SIT) | 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. + +- Node Address Table (NAT) + : It is composed of a block address table for all the node blocks stored in + Main area. + +- Segment Information Table (SIT) + : It contains segment information such as valid block count and bitmap for the + validity of all the blocks. + +- 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 | NAT | SIT | + +--------+----------+---------+ + . . . . + . . . . + . . . . + +-------+-------+--------+--------+--------+--------+ + | CP #0 | CP #1 | NAT #0 | NAT #1 | SIT #0 | SIT #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/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt index 092fad92a3f0..01c2db769791 100644 --- a/Documentation/filesystems/nfs/nfs41-server.txt +++ b/Documentation/filesystems/nfs/nfs41-server.txt @@ -39,21 +39,10 @@ interoperability problems with future clients. Known issues: from a linux client are possible, but we aren't really conformant with the spec (for example, we don't use kerberos on the backchannel correctly). - - Incomplete backchannel support: incomplete backchannel gss - support and no support for BACKCHANNEL_CTL mean that - callbacks (hence delegations and layouts) may not be - available and clients confused by the incomplete - implementation may fail. - We do not support SSV, which provides security for shared client-server state (thus preventing unauthorized tampering with locks and opens, for example). It is mandatory for servers to support this, though no clients use it yet. - - Mandatory operations which we do not support, such as - DESTROY_CLIENTID, are not currently used by clients, but will be - (and the spec recommends their uses in common cases), and - clients should not be expected to know how to recover from the - case where they are not supported. This will eventually cause - interoperability failures. In addition, some limitations are inherited from the current NFSv4 implementation: @@ -89,7 +78,7 @@ Operations | | MNI | or OPT) | | +----------------------+------------+--------------+----------------+ | ACCESS | REQ | | Section 18.1 | -NS | BACKCHANNEL_CTL | REQ | | Section 18.33 | +I | BACKCHANNEL_CTL | REQ | | Section 18.33 | I | BIND_CONN_TO_SESSION | REQ | | Section 18.34 | | CLOSE | REQ | | Section 18.2 | | COMMIT | REQ | | Section 18.3 | @@ -99,7 +88,7 @@ NS*| DELEGPURGE | OPT | FDELG (REQ) | Section 18.5 | | DELEGRETURN | OPT | FDELG, | Section 18.6 | | | | DDELG, pNFS | | | | | (REQ) | | -NS | DESTROY_CLIENTID | REQ | | Section 18.50 | +I | DESTROY_CLIENTID | REQ | | Section 18.50 | I | DESTROY_SESSION | REQ | | Section 18.37 | I | EXCHANGE_ID | REQ | | Section 18.35 | I | FREE_STATEID | REQ | | Section 18.38 | @@ -192,7 +181,6 @@ EXCHANGE_ID: CREATE_SESSION: * backchannel attributes are ignored -* backchannel security parameters are ignored SEQUENCE: * no support for dynamic slot table renegotiation (optional) @@ -202,7 +190,7 @@ Nonstandard compound limitations: ca_maxrequestsize request and a ca_maxresponsesize reply, so we may fail to live up to the promise we made in CREATE_SESSION fore channel negotiation. -* No more than one IO operation (read, write, readdir) allowed per - compound. +* No more than one read-like operation allowed per compound; encoding + replies that cross page boundaries (except for read data) not handled. See also http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues. @@ -124,7 +124,7 @@ $(if $(KBUILD_OUTPUT),, \ PHONY += $(MAKECMDGOALS) sub-make $(filter-out _all sub-make $(CURDIR)/Makefile, $(MAKECMDGOALS)) _all: sub-make - $(Q)@: + @: sub-make: FORCE $(if $(KBUILD_VERBOSE:1=),@)$(MAKE) -C $(KBUILD_OUTPUT) \ @@ -1027,11 +1027,14 @@ clean: rm-dirs := $(CLEAN_DIRS) clean: rm-files := $(CLEAN_FILES) clean-dirs := $(addprefix _clean_, . $(vmlinux-alldirs) Documentation samples) -PHONY += $(clean-dirs) clean archclean +PHONY += $(clean-dirs) clean archclean vmlinuxclean $(clean-dirs): $(Q)$(MAKE) $(clean)=$(patsubst _clean_%,%,$@) -clean: archclean +vmlinuxclean: + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/link-vmlinux.sh clean + +clean: archclean vmlinuxclean # mrproper - Delete all generated files, including .config # @@ -1258,7 +1261,6 @@ scripts: ; endif # KBUILD_EXTMOD clean: $(clean-dirs) - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/link-vmlinux.sh clean $(call cmd,rmdirs) $(call cmd,rmfiles) @find $(if $(KBUILD_EXTMOD), $(KBUILD_EXTMOD), .) $(RCS_FIND_IGNORE) \ diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 67d06324e74a..5b579b951503 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -91,6 +91,7 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr) */ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { + debug_dma_mapping_error(dev, dma_addr); return dma_addr == DMA_ERROR_CODE; } diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c index 4abb8b5e9bc0..5e304d0719a2 100644 --- a/arch/arm/mach-omap2/devices.c +++ b/arch/arm/mach-omap2/devices.c @@ -226,7 +226,7 @@ static struct platform_device omap3isp_device = { }; static struct omap_iommu_arch_data omap3_isp_iommu = { - .name = "isp", + .name = "mmu_isp", }; int omap3_init_camera(struct isp_platform_data *pdata) diff --git a/arch/arm/mach-omap2/omap-iommu.c b/arch/arm/mach-omap2/omap-iommu.c index a6a4ff8744b7..6da4f7ae9d7f 100644 --- a/arch/arm/mach-omap2/omap-iommu.c +++ b/arch/arm/mach-omap2/omap-iommu.c @@ -12,153 +12,60 @@ #include <linux/module.h> #include <linux/platform_device.h> +#include <linux/err.h> +#include <linux/slab.h> #include <linux/platform_data/iommu-omap.h> +#include "omap_hwmod.h" +#include "omap_device.h" -#include "soc.h" -#include "common.h" - -struct iommu_device { - resource_size_t base; - int irq; - struct iommu_platform_data pdata; - struct resource res[2]; -}; -static struct iommu_device *devices; -static int num_iommu_devices; - -#ifdef CONFIG_ARCH_OMAP3 -static struct iommu_device omap3_devices[] = { - { - .base = 0x480bd400, - .irq = 24 + OMAP_INTC_START, - .pdata = { - .name = "isp", - .nr_tlb_entries = 8, - .clk_name = "cam_ick", - .da_start = 0x0, - .da_end = 0xFFFFF000, - }, - }, -#if defined(CONFIG_OMAP_IOMMU_IVA2) - { - .base = 0x5d000000, - .irq = 28 + OMAP_INTC_START, - .pdata = { - .name = "iva2", - .nr_tlb_entries = 32, - .clk_name = "iva2_ck", - .da_start = 0x11000000, - .da_end = 0xFFFFF000, - }, - }, -#endif -}; -#define NR_OMAP3_IOMMU_DEVICES ARRAY_SIZE(omap3_devices) -static struct platform_device *omap3_iommu_pdev[NR_OMAP3_IOMMU_DEVICES]; -#else -#define omap3_devices NULL -#define NR_OMAP3_IOMMU_DEVICES 0 -#define omap3_iommu_pdev NULL -#endif - -#ifdef CONFIG_ARCH_OMAP4 -static struct iommu_device omap4_devices[] = { - { - .base = OMAP4_MMU1_BASE, - .irq = 100 + OMAP44XX_IRQ_GIC_START, - .pdata = { - .name = "ducati", - .nr_tlb_entries = 32, - .clk_name = "ipu_fck", - .da_start = 0x0, - .da_end = 0xFFFFF000, - }, - }, - { - .base = OMAP4_MMU2_BASE, - .irq = 28 + OMAP44XX_IRQ_GIC_START, - .pdata = { - .name = "tesla", - .nr_tlb_entries = 32, - .clk_name = "dsp_fck", - .da_start = 0x0, - .da_end = 0xFFFFF000, - }, - }, -}; -#define NR_OMAP4_IOMMU_DEVICES ARRAY_SIZE(omap4_devices) -static struct platform_device *omap4_iommu_pdev[NR_OMAP4_IOMMU_DEVICES]; -#else -#define omap4_devices NULL -#define NR_OMAP4_IOMMU_DEVICES 0 -#define omap4_iommu_pdev NULL -#endif - -static struct platform_device **omap_iommu_pdev; - -static int __init omap_iommu_init(void) +static int __init omap_iommu_dev_init(struct omap_hwmod *oh, void *unused) { - int i, err; - struct resource res[] = { - { .flags = IORESOURCE_MEM }, - { .flags = IORESOURCE_IRQ }, - }; + struct platform_device *pdev; + struct iommu_platform_data *pdata; + struct omap_mmu_dev_attr *a = (struct omap_mmu_dev_attr *)oh->dev_attr; + static int i; + + pdata = kzalloc(sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return -ENOMEM; + + pdata->name = oh->name; + pdata->nr_tlb_entries = a->nr_tlb_entries; + pdata->da_start = a->da_start; + pdata->da_end = a->da_end; + + if (oh->rst_lines_cnt == 1) { + pdata->reset_name = oh->rst_lines->name; + pdata->assert_reset = omap_device_assert_hardreset; + pdata->deassert_reset = omap_device_deassert_hardreset; + } - if (cpu_is_omap34xx()) { - devices = omap3_devices; - omap_iommu_pdev = omap3_iommu_pdev; - num_iommu_devices = NR_OMAP3_IOMMU_DEVICES; - } else if (cpu_is_omap44xx()) { - devices = omap4_devices; - omap_iommu_pdev = omap4_iommu_pdev; - num_iommu_devices = NR_OMAP4_IOMMU_DEVICES; - } else - return -ENODEV; + pdev = omap_device_build("omap-iommu", i, oh, pdata, sizeof(*pdata), + NULL, 0, 0); - for (i = 0; i < num_iommu_devices; i++) { - struct platform_device *pdev; - const struct iommu_device *d = &devices[i]; + kfree(pdata); - pdev = platform_device_alloc("omap-iommu", i); - if (!pdev) { - err = -ENOMEM; - goto err_out; - } + if (IS_ERR(pdev)) { + pr_err("%s: device build err: %ld\n", __func__, PTR_ERR(pdev)); + return PTR_ERR(pdev); + } - res[0].start = d->base; - res[0].end = d->base + MMU_REG_SIZE - 1; - res[1].start = res[1].end = d->irq; + i++; - err = platform_device_add_resources(pdev, res, - ARRAY_SIZE(res)); - if (err) - goto err_out; - err = platform_device_add_data(pdev, &d->pdata, - sizeof(d->pdata)); - if (err) - goto err_out; - err = platform_device_add(pdev); - if (err) - goto err_out; - omap_iommu_pdev[i] = pdev; - } return 0; +} -err_out: - while (i--) - platform_device_put(omap_iommu_pdev[i]); - return err; +static int __init omap_iommu_init(void) +{ + return omap_hwmod_for_each_by_class("mmu", omap_iommu_dev_init, NULL); } /* must be ready before omap3isp is probed */ subsys_initcall(omap_iommu_init); static void __exit omap_iommu_exit(void) { - int i; - - for (i = 0; i < num_iommu_devices; i++) - platform_device_unregister(omap_iommu_pdev[i]); + /* Do nothing */ } module_exit(omap_iommu_exit); diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c index 272b0178dba6..f9fab942d5ba 100644 --- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c @@ -653,7 +653,7 @@ static struct omap_hwmod omap44xx_dsp_hwmod = { .mpu_irqs = omap44xx_dsp_irqs, .rst_lines = omap44xx_dsp_resets, .rst_lines_cnt = ARRAY_SIZE(omap44xx_dsp_resets), - .main_clk = "dsp_fck", + .main_clk = "dpll_iva_m4x2_ck", .prcm = { .omap4 = { .clkctrl_offs = OMAP4_CM_TESLA_TESLA_CLKCTRL_OFFSET, @@ -1679,7 +1679,7 @@ static struct omap_hwmod omap44xx_ipu_hwmod = { .mpu_irqs = omap44xx_ipu_irqs, .rst_lines = omap44xx_ipu_resets, .rst_lines_cnt = ARRAY_SIZE(omap44xx_ipu_resets), - .main_clk = "ipu_fck", + .main_clk = "ducati_clk_mux_ck", .prcm = { .omap4 = { .clkctrl_offs = OMAP4_CM_DUCATI_DUCATI_CLKCTRL_OFFSET, diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index 538f4b44db5d..994776894198 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -50,6 +50,7 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr) static inline int dma_mapping_error(struct device *dev, dma_addr_t dev_addr) { struct dma_map_ops *ops = get_dma_ops(dev); + debug_dma_mapping_error(dev, dev_addr); return ops->mapping_error(dev, dev_addr); } diff --git a/arch/c6x/include/asm/dma-mapping.h b/arch/c6x/include/asm/dma-mapping.h index 03579fd99dba..3c694065030f 100644 --- a/arch/c6x/include/asm/dma-mapping.h +++ b/arch/c6x/include/asm/dma-mapping.h @@ -32,6 +32,7 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask) */ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { + debug_dma_mapping_error(dev, dma_addr); return dma_addr == ~0; } diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h index 4f5e8148440d..cf3ab7e784b5 100644 --- a/arch/ia64/include/asm/dma-mapping.h +++ b/arch/ia64/include/asm/dma-mapping.h @@ -58,6 +58,7 @@ static inline void dma_free_attrs(struct device *dev, size_t size, static inline int dma_mapping_error(struct device *dev, dma_addr_t daddr) { struct dma_map_ops *ops = platform_dma_get_ops(dev); + debug_dma_mapping_error(dev, daddr); return ops->mapping_error(dev, daddr); } diff --git a/arch/microblaze/include/asm/dma-mapping.h b/arch/microblaze/include/asm/dma-mapping.h index 01d228286cb0..46460f1c49c4 100644 --- a/arch/microblaze/include/asm/dma-mapping.h +++ b/arch/microblaze/include/asm/dma-mapping.h @@ -114,6 +114,8 @@ static inline void __dma_sync(unsigned long paddr, static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { struct dma_map_ops *ops = get_dma_ops(dev); + + debug_dma_mapping_error(dev, dma_addr); if (ops->mapping_error) return ops->mapping_error(dev, dma_addr); diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h index be39a12901c6..006b43e38a9c 100644 --- a/arch/mips/include/asm/dma-mapping.h +++ b/arch/mips/include/asm/dma-mapping.h @@ -40,6 +40,8 @@ static inline int dma_supported(struct device *dev, u64 mask) static inline int dma_mapping_error(struct device *dev, u64 mask) { struct dma_map_ops *ops = get_dma_ops(dev); + + debug_dma_mapping_error(dev, mask); return ops->mapping_error(dev, mask); } diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index 78160874809a..e27e9ad6818e 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -172,6 +172,7 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { struct dma_map_ops *dma_ops = get_dma_ops(dev); + debug_dma_mapping_error(dev, dma_addr); if (dma_ops->mapping_error) return dma_ops->mapping_error(dev, dma_addr); diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h index 8bd965e00a15..b437f2c780b8 100644 --- a/arch/sh/include/asm/dma-mapping.h +++ b/arch/sh/include/asm/dma-mapping.h @@ -46,6 +46,7 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { struct dma_map_ops *ops = get_dma_ops(dev); + debug_dma_mapping_error(dev, dma_addr); if (ops->mapping_error) return ops->mapping_error(dev, dma_addr); diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h index 8493fd3c7ba5..05fe53f5346e 100644 --- a/arch/sparc/include/asm/dma-mapping.h +++ b/arch/sparc/include/asm/dma-mapping.h @@ -59,6 +59,7 @@ static inline void dma_free_attrs(struct device *dev, size_t size, static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { + debug_dma_mapping_error(dev, dma_addr); return (dma_addr == DMA_ERROR_CODE); } diff --git a/arch/tile/include/asm/dma-mapping.h b/arch/tile/include/asm/dma-mapping.h index 4b6247d1a315..f2ff191376b4 100644 --- a/arch/tile/include/asm/dma-mapping.h +++ b/arch/tile/include/asm/dma-mapping.h @@ -72,6 +72,7 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { + debug_dma_mapping_error(dev, dma_addr); return get_dma_ops(dev)->mapping_error(dev, dma_addr); } diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index f7b4c7903e7e..808dae63eeea 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -47,6 +47,7 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev) static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { struct dma_map_ops *ops = get_dma_ops(dev); + debug_dma_mapping_error(dev, dma_addr); if (ops->mapping_error) return ops->mapping_error(dev, dma_addr); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index bb3d9be3b1b4..89576a0b3f2e 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -61,15 +61,29 @@ #define RBD_MINORS_PER_MAJOR 256 /* max minors per blkdev */ -#define RBD_MAX_SNAP_NAME_LEN 32 +#define RBD_SNAP_DEV_NAME_PREFIX "snap_" +#define RBD_MAX_SNAP_NAME_LEN \ + (NAME_MAX - (sizeof (RBD_SNAP_DEV_NAME_PREFIX) - 1)) + #define RBD_MAX_SNAP_COUNT 510 /* allows max snapc to fit in 4KB */ #define RBD_MAX_OPT_LEN 1024 #define RBD_SNAP_HEAD_NAME "-" +/* This allows a single page to hold an image name sent by OSD */ +#define RBD_IMAGE_NAME_LEN_MAX (PAGE_SIZE - sizeof (__le32) - 1) #define RBD_IMAGE_ID_LEN_MAX 64 + #define RBD_OBJ_PREFIX_LEN_MAX 64 +/* Feature bits */ + +#define RBD_FEATURE_LAYERING 1 + +/* Features supported by this (client software) implementation. */ + +#define RBD_FEATURES_ALL (0) + /* * An RBD device name will be "rbd#", where the "rbd" comes from * RBD_DRV_NAME above, and # is a unique integer identifier. @@ -101,6 +115,27 @@ struct rbd_image_header { u64 obj_version; }; +/* + * An rbd image specification. + * + * The tuple (pool_id, image_id, snap_id) is sufficient to uniquely + * identify an image. + */ +struct rbd_spec { + u64 pool_id; + char *pool_name; + + char *image_id; + size_t image_id_len; + char *image_name; + size_t image_name_len; + + u64 snap_id; + char *snap_name; + + struct kref kref; +}; + struct rbd_options { bool read_only; }; @@ -155,11 +190,8 @@ struct rbd_snap { }; struct rbd_mapping { - char *snap_name; - u64 snap_id; u64 size; u64 features; - bool snap_exists; bool read_only; }; @@ -173,7 +205,6 @@ struct rbd_device { struct gendisk *disk; /* blkdev's gendisk and rq */ u32 image_format; /* Either 1 or 2 */ - struct rbd_options rbd_opts; struct rbd_client *rbd_client; char name[DEV_NAME_LEN]; /* blkdev name, e.g. rbd3 */ @@ -181,17 +212,17 @@ struct rbd_device { spinlock_t lock; /* queue lock */ struct rbd_image_header header; - char *image_id; - size_t image_id_len; - char *image_name; - size_t image_name_len; + bool exists; + struct rbd_spec *spec; + char *header_name; - char *pool_name; - int pool_id; struct ceph_osd_event *watch_event; struct ceph_osd_request *watch_request; + struct rbd_spec *parent_spec; + u64 parent_overlap; + /* protects updating the header */ struct rw_semaphore header_rwsem; @@ -204,6 +235,7 @@ struct rbd_device { /* sysfs related */ struct device dev; + unsigned long open_count; }; static DEFINE_MUTEX(ctl_mutex); /* Serialize open/close/setup/teardown */ @@ -218,7 +250,7 @@ static int rbd_dev_snaps_update(struct rbd_device *rbd_dev); static int rbd_dev_snaps_register(struct rbd_device *rbd_dev); static void rbd_dev_release(struct device *dev); -static void __rbd_remove_snap_dev(struct rbd_snap *snap); +static void rbd_remove_snap_dev(struct rbd_snap *snap); static ssize_t rbd_add(struct bus_type *bus, const char *buf, size_t count); @@ -258,17 +290,8 @@ static struct device rbd_root_dev = { # define rbd_assert(expr) ((void) 0) #endif /* !RBD_DEBUG */ -static struct device *rbd_get_dev(struct rbd_device *rbd_dev) -{ - return get_device(&rbd_dev->dev); -} - -static void rbd_put_dev(struct rbd_device *rbd_dev) -{ - put_device(&rbd_dev->dev); -} - -static int rbd_refresh_header(struct rbd_device *rbd_dev, u64 *hver); +static int rbd_dev_refresh(struct rbd_device *rbd_dev, u64 *hver); +static int rbd_dev_v2_refresh(struct rbd_device *rbd_dev, u64 *hver); static int rbd_open(struct block_device *bdev, fmode_t mode) { @@ -277,8 +300,11 @@ static int rbd_open(struct block_device *bdev, fmode_t mode) if ((mode & FMODE_WRITE) && rbd_dev->mapping.read_only) return -EROFS; - rbd_get_dev(rbd_dev); + mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); + (void) get_device(&rbd_dev->dev); set_device_ro(bdev, rbd_dev->mapping.read_only); + rbd_dev->open_count++; + mutex_unlock(&ctl_mutex); return 0; } @@ -287,7 +313,11 @@ static int rbd_release(struct gendisk *disk, fmode_t mode) { struct rbd_device *rbd_dev = disk->private_data; - rbd_put_dev(rbd_dev); + mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); + rbd_assert(rbd_dev->open_count > 0); + rbd_dev->open_count--; + put_device(&rbd_dev->dev); + mutex_unlock(&ctl_mutex); return 0; } @@ -388,7 +418,7 @@ enum { static match_table_t rbd_opts_tokens = { /* int args above */ /* string args above */ - {Opt_read_only, "mapping.read_only"}, + {Opt_read_only, "read_only"}, {Opt_read_only, "ro"}, /* Alternate spelling */ {Opt_read_write, "read_write"}, {Opt_read_write, "rw"}, /* Alternate spelling */ @@ -441,33 +471,17 @@ static int parse_rbd_opts_token(char *c, void *private) * Get a ceph client with specific addr and configuration, if one does * not exist create it. */ -static int rbd_get_client(struct rbd_device *rbd_dev, const char *mon_addr, - size_t mon_addr_len, char *options) +static struct rbd_client *rbd_get_client(struct ceph_options *ceph_opts) { - struct rbd_options *rbd_opts = &rbd_dev->rbd_opts; - struct ceph_options *ceph_opts; struct rbd_client *rbdc; - rbd_opts->read_only = RBD_READ_ONLY_DEFAULT; - - ceph_opts = ceph_parse_options(options, mon_addr, - mon_addr + mon_addr_len, - parse_rbd_opts_token, rbd_opts); - if (IS_ERR(ceph_opts)) - return PTR_ERR(ceph_opts); - rbdc = rbd_client_find(ceph_opts); - if (rbdc) { - /* using an existing client */ + if (rbdc) /* using an existing client */ ceph_destroy_options(ceph_opts); - } else { + else rbdc = rbd_client_create(ceph_opts); - if (IS_ERR(rbdc)) - return PTR_ERR(rbdc); - } - rbd_dev->rbd_client = rbdc; - return 0; + return rbdc; } /* @@ -492,10 +506,10 @@ static void rbd_client_release(struct kref *kref) * Drop reference to ceph client node. If it's not referenced anymore, release * it. */ -static void rbd_put_client(struct rbd_device *rbd_dev) +static void rbd_put_client(struct rbd_client *rbdc) { - kref_put(&rbd_dev->rbd_client->kref, rbd_client_release); - rbd_dev->rbd_client = NULL; + if (rbdc) + kref_put(&rbdc->kref, rbd_client_release); } /* @@ -524,6 +538,16 @@ static bool rbd_dev_ondisk_valid(struct rbd_image_header_ondisk *ondisk) if (memcmp(&ondisk->text, RBD_HEADER_TEXT, sizeof (RBD_HEADER_TEXT))) return false; + /* The bio layer requires at least sector-sized I/O */ + + if (ondisk->options.order < SECTOR_SHIFT) + return false; + + /* If we use u64 in a few spots we may be able to loosen this */ + + if (ondisk->options.order > 8 * sizeof (int) - 1) + return false; + /* * The size of a snapshot header has to fit in a size_t, and * that limits the number of snapshots. @@ -635,6 +659,20 @@ out_err: return -ENOMEM; } +static const char *rbd_snap_name(struct rbd_device *rbd_dev, u64 snap_id) +{ + struct rbd_snap *snap; + + if (snap_id == CEPH_NOSNAP) + return RBD_SNAP_HEAD_NAME; + + list_for_each_entry(snap, &rbd_dev->snaps, node) + if (snap_id == snap->id) + return snap->name; + + return NULL; +} + static int snap_by_name(struct rbd_device *rbd_dev, const char *snap_name) { @@ -642,7 +680,7 @@ static int snap_by_name(struct rbd_device *rbd_dev, const char *snap_name) list_for_each_entry(snap, &rbd_dev->snaps, node) { if (!strcmp(snap_name, snap->name)) { - rbd_dev->mapping.snap_id = snap->id; + rbd_dev->spec->snap_id = snap->id; rbd_dev->mapping.size = snap->size; rbd_dev->mapping.features = snap->features; @@ -653,26 +691,23 @@ static int snap_by_name(struct rbd_device *rbd_dev, const char *snap_name) return -ENOENT; } -static int rbd_dev_set_mapping(struct rbd_device *rbd_dev, char *snap_name) +static int rbd_dev_set_mapping(struct rbd_device *rbd_dev) { int ret; - if (!memcmp(snap_name, RBD_SNAP_HEAD_NAME, + if (!memcmp(rbd_dev->spec->snap_name, RBD_SNAP_HEAD_NAME, sizeof (RBD_SNAP_HEAD_NAME))) { - rbd_dev->mapping.snap_id = CEPH_NOSNAP; + rbd_dev->spec->snap_id = CEPH_NOSNAP; rbd_dev->mapping.size = rbd_dev->header.image_size; rbd_dev->mapping.features = rbd_dev->header.features; - rbd_dev->mapping.snap_exists = false; - rbd_dev->mapping.read_only = rbd_dev->rbd_opts.read_only; ret = 0; } else { - ret = snap_by_name(rbd_dev, snap_name); + ret = snap_by_name(rbd_dev, rbd_dev->spec->snap_name); if (ret < 0) goto done; - rbd_dev->mapping.snap_exists = true; rbd_dev->mapping.read_only = true; } - rbd_dev->mapping.snap_name = snap_name; + rbd_dev->exists = true; done: return ret; } @@ -695,13 +730,13 @@ static char *rbd_segment_name(struct rbd_device *rbd_dev, u64 offset) u64 segment; int ret; - name = kmalloc(RBD_MAX_SEG_NAME_LEN + 1, GFP_NOIO); + name = kmalloc(MAX_OBJ_NAME_SIZE + 1, GFP_NOIO); if (!name) return NULL; segment = offset >> rbd_dev->header.obj_order; - ret = snprintf(name, RBD_MAX_SEG_NAME_LEN, "%s.%012llx", + ret = snprintf(name, MAX_OBJ_NAME_SIZE + 1, "%s.%012llx", rbd_dev->header.object_prefix, segment); - if (ret < 0 || ret >= RBD_MAX_SEG_NAME_LEN) { + if (ret < 0 || ret > MAX_OBJ_NAME_SIZE) { pr_err("error formatting segment name for #%llu (%d)\n", segment, ret); kfree(name); @@ -800,77 +835,144 @@ static void zero_bio_chain(struct bio *chain, int start_ofs) } /* - * bio_chain_clone - clone a chain of bios up to a certain length. - * might return a bio_pair that will need to be released. + * Clone a portion of a bio, starting at the given byte offset + * and continuing for the number of bytes indicated. */ -static struct bio *bio_chain_clone(struct bio **old, struct bio **next, - struct bio_pair **bp, - int len, gfp_t gfpmask) -{ - struct bio *old_chain = *old; - struct bio *new_chain = NULL; - struct bio *tail; - int total = 0; - - if (*bp) { - bio_pair_release(*bp); - *bp = NULL; - } +static struct bio *bio_clone_range(struct bio *bio_src, + unsigned int offset, + unsigned int len, + gfp_t gfpmask) +{ + struct bio_vec *bv; + unsigned int resid; + unsigned short idx; + unsigned int voff; + unsigned short end_idx; + unsigned short vcnt; + struct bio *bio; - while (old_chain && (total < len)) { - struct bio *tmp; + /* Handle the easy case for the caller */ - tmp = bio_kmalloc(gfpmask, old_chain->bi_max_vecs); - if (!tmp) - goto err_out; - gfpmask &= ~__GFP_WAIT; /* can't wait after the first */ + if (!offset && len == bio_src->bi_size) + return bio_clone(bio_src, gfpmask); - if (total + old_chain->bi_size > len) { - struct bio_pair *bp; + if (WARN_ON_ONCE(!len)) + return NULL; + if (WARN_ON_ONCE(len > bio_src->bi_size)) + return NULL; + if (WARN_ON_ONCE(offset > bio_src->bi_size - len)) + return NULL; - /* - * this split can only happen with a single paged bio, - * split_bio will BUG_ON if this is not the case - */ - dout("bio_chain_clone split! total=%d remaining=%d" - "bi_size=%u\n", - total, len - total, old_chain->bi_size); + /* Find first affected segment... */ - /* split the bio. We'll release it either in the next - call, or it will have to be released outside */ - bp = bio_split(old_chain, (len - total) / SECTOR_SIZE); - if (!bp) - goto err_out; + resid = offset; + __bio_for_each_segment(bv, bio_src, idx, 0) { + if (resid < bv->bv_len) + break; + resid -= bv->bv_len; + } + voff = resid; - __bio_clone(tmp, &bp->bio1); + /* ...and the last affected segment */ - *next = &bp->bio2; - } else { - __bio_clone(tmp, old_chain); - *next = old_chain->bi_next; - } + resid += len; + __bio_for_each_segment(bv, bio_src, end_idx, idx) { + if (resid <= bv->bv_len) + break; + resid -= bv->bv_len; + } + vcnt = end_idx - idx + 1; + + /* Build the clone */ - tmp->bi_bdev = NULL; - tmp->bi_next = NULL; - if (new_chain) - tail->bi_next = tmp; - else - new_chain = tmp; - tail = tmp; - old_chain = old_chain->bi_next; + bio = bio_alloc(gfpmask, (unsigned int) vcnt); + if (!bio) + return NULL; /* ENOMEM */ - total += tmp->bi_size; + bio->bi_bdev = bio_src->bi_bdev; + bio->bi_sector = bio_src->bi_sector + (offset >> SECTOR_SHIFT); + bio->bi_rw = bio_src->bi_rw; + bio->bi_flags |= 1 << BIO_CLONED; + + /* + * Copy over our part of the bio_vec, then update the first + * and last (or only) entries. + */ + memcpy(&bio->bi_io_vec[0], &bio_src->bi_io_vec[idx], + vcnt * sizeof (struct bio_vec)); + bio->bi_io_vec[0].bv_offset += voff; + if (vcnt > 1) { + bio->bi_io_vec[0].bv_len -= voff; + bio->bi_io_vec[vcnt - 1].bv_len = resid; + } else { + bio->bi_io_vec[0].bv_len = len; } - rbd_assert(total == len); + bio->bi_vcnt = vcnt; + bio->bi_size = len; + bio->bi_idx = 0; + + return bio; +} + +/* + * Clone a portion of a bio chain, starting at the given byte offset + * into the first bio in the source chain and continuing for the + * number of bytes indicated. The result is another bio chain of + * exactly the given length, or a null pointer on error. + * + * The bio_src and offset parameters are both in-out. On entry they + * refer to the first source bio and the offset into that bio where + * the start of data to be cloned is located. + * + * On return, bio_src is updated to refer to the bio in the source + * chain that contains first un-cloned byte, and *offset will + * contain the offset of that byte within that bio. + */ +static struct bio *bio_chain_clone_range(struct bio **bio_src, + unsigned int *offset, + unsigned int len, + gfp_t gfpmask) +{ + struct bio *bi = *bio_src; + unsigned int off = *offset; + struct bio *chain = NULL; + struct bio **end; + + /* Build up a chain of clone bios up to the limit */ + + if (!bi || off >= bi->bi_size || !len) + return NULL; /* Nothing to clone */ - *old = old_chain; + end = &chain; + while (len) { + unsigned int bi_size; + struct bio *bio; + + if (!bi) + goto out_err; /* EINVAL; ran out of bio's */ + bi_size = min_t(unsigned int, bi->bi_size - off, len); + bio = bio_clone_range(bi, off, bi_size, gfpmask); + if (!bio) + goto out_err; /* ENOMEM */ + + *end = bio; + end = &bio->bi_next; + + off += bi_size; + if (off == bi->bi_size) { + bi = bi->bi_next; + off = 0; + } + len -= bi_size; + } + *bio_src = bi; + *offset = off; - return new_chain; + return chain; +out_err: + bio_chain_put(chain); -err_out: - dout("bio_chain_clone with err\n"); - bio_chain_put(new_chain); return NULL; } @@ -988,8 +1090,9 @@ static int rbd_do_request(struct request *rq, req_data->coll_index = coll_index; } - dout("rbd_do_request object_name=%s ofs=%llu len=%llu\n", object_name, - (unsigned long long) ofs, (unsigned long long) len); + dout("rbd_do_request object_name=%s ofs=%llu len=%llu coll=%p[%d]\n", + object_name, (unsigned long long) ofs, + (unsigned long long) len, coll, coll_index); osdc = &rbd_dev->rbd_client->client->osdc; req = ceph_osdc_alloc_request(osdc, flags, snapc, ops, @@ -1019,7 +1122,7 @@ static int rbd_do_request(struct request *rq, layout->fl_stripe_unit = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER); layout->fl_stripe_count = cpu_to_le32(1); layout->fl_object_size = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER); - layout->fl_pg_pool = cpu_to_le32(rbd_dev->pool_id); + layout->fl_pg_pool = cpu_to_le32((int) rbd_dev->spec->pool_id); ret = ceph_calc_raw_layout(osdc, layout, snapid, ofs, &len, &bno, req, ops); rbd_assert(ret == 0); @@ -1154,8 +1257,6 @@ done: static int rbd_do_op(struct request *rq, struct rbd_device *rbd_dev, struct ceph_snap_context *snapc, - u64 snapid, - int opcode, int flags, u64 ofs, u64 len, struct bio *bio, struct rbd_req_coll *coll, @@ -1167,6 +1268,9 @@ static int rbd_do_op(struct request *rq, int ret; struct ceph_osd_req_op *ops; u32 payload_len; + int opcode; + int flags; + u64 snapid; seg_name = rbd_segment_name(rbd_dev, ofs); if (!seg_name) @@ -1174,7 +1278,18 @@ static int rbd_do_op(struct request *rq, seg_len = rbd_segment_length(rbd_dev, ofs, len); seg_ofs = rbd_segment_offset(rbd_dev, ofs); - payload_len = (flags & CEPH_OSD_FLAG_WRITE ? seg_len : 0); + if (rq_data_dir(rq) == WRITE) { + opcode = CEPH_OSD_OP_WRITE; + flags = CEPH_OSD_FLAG_WRITE|CEPH_OSD_FLAG_ONDISK; + snapid = CEPH_NOSNAP; + payload_len = seg_len; + } else { + opcode = CEPH_OSD_OP_READ; + flags = CEPH_OSD_FLAG_READ; + snapc = NULL; + snapid = rbd_dev->spec->snap_id; + payload_len = 0; + } ret = -ENOMEM; ops = rbd_create_rw_ops(1, opcode, payload_len); @@ -1202,41 +1317,6 @@ done: } /* - * Request async osd write - */ -static int rbd_req_write(struct request *rq, - struct rbd_device *rbd_dev, - struct ceph_snap_context *snapc, - u64 ofs, u64 len, - struct bio *bio, - struct rbd_req_coll *coll, - int coll_index) -{ - return rbd_do_op(rq, rbd_dev, snapc, CEPH_NOSNAP, - CEPH_OSD_OP_WRITE, - CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK, - ofs, len, bio, coll, coll_index); -} - -/* - * Request async osd read - */ -static int rbd_req_read(struct request *rq, - struct rbd_device *rbd_dev, - u64 snapid, - u64 ofs, u64 len, - struct bio *bio, - struct rbd_req_coll *coll, - int coll_index) -{ - return rbd_do_op(rq, rbd_dev, NULL, - snapid, - CEPH_OSD_OP_READ, - CEPH_OSD_FLAG_READ, - ofs, len, bio, coll, coll_index); -} - -/* * Request sync osd read */ static int rbd_req_sync_read(struct rbd_device *rbd_dev, @@ -1304,7 +1384,7 @@ static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data) dout("rbd_watch_cb %s notify_id=%llu opcode=%u\n", rbd_dev->header_name, (unsigned long long) notify_id, (unsigned int) opcode); - rc = rbd_refresh_header(rbd_dev, &hver); + rc = rbd_dev_refresh(rbd_dev, &hver); if (rc) pr_warning(RBD_DRV_NAME "%d got notification but failed to " " update snaps: %d\n", rbd_dev->major, rc); @@ -1460,18 +1540,16 @@ static void rbd_rq_fn(struct request_queue *q) { struct rbd_device *rbd_dev = q->queuedata; struct request *rq; - struct bio_pair *bp = NULL; while ((rq = blk_fetch_request(q))) { struct bio *bio; - struct bio *rq_bio, *next_bio = NULL; bool do_write; unsigned int size; - u64 op_size = 0; u64 ofs; int num_segs, cur_seg = 0; struct rbd_req_coll *coll; struct ceph_snap_context *snapc; + unsigned int bio_offset; dout("fetched request\n"); @@ -1483,10 +1561,6 @@ static void rbd_rq_fn(struct request_queue *q) /* deduce our operation (read, write) */ do_write = (rq_data_dir(rq) == WRITE); - - size = blk_rq_bytes(rq); - ofs = blk_rq_pos(rq) * SECTOR_SIZE; - rq_bio = rq->bio; if (do_write && rbd_dev->mapping.read_only) { __blk_end_request_all(rq, -EROFS); continue; @@ -1496,8 +1570,8 @@ static void rbd_rq_fn(struct request_queue *q) down_read(&rbd_dev->header_rwsem); - if (rbd_dev->mapping.snap_id != CEPH_NOSNAP && - !rbd_dev->mapping.snap_exists) { + if (!rbd_dev->exists) { + rbd_assert(rbd_dev->spec->snap_id != CEPH_NOSNAP); up_read(&rbd_dev->header_rwsem); dout("request for non-existent snapshot"); spin_lock_irq(q->queue_lock); @@ -1509,6 +1583,10 @@ static void rbd_rq_fn(struct request_queue *q) up_read(&rbd_dev->header_rwsem); + size = blk_rq_bytes(rq); + ofs = blk_rq_pos(rq) * SECTOR_SIZE; + bio = rq->bio; + dout("%s 0x%x bytes at 0x%llx\n", do_write ? "write" : "read", size, (unsigned long long) blk_rq_pos(rq) * SECTOR_SIZE); @@ -1528,45 +1606,37 @@ static void rbd_rq_fn(struct request_queue *q) continue; } + bio_offset = 0; do { - /* a bio clone to be passed down to OSD req */ + u64 limit = rbd_segment_length(rbd_dev, ofs, size); + unsigned int chain_size; + struct bio *bio_chain; + + BUG_ON(limit > (u64) UINT_MAX); + chain_size = (unsigned int) limit; dout("rq->bio->bi_vcnt=%hu\n", rq->bio->bi_vcnt); - op_size = rbd_segment_length(rbd_dev, ofs, size); + kref_get(&coll->kref); - bio = bio_chain_clone(&rq_bio, &next_bio, &bp, - op_size, GFP_ATOMIC); - if (!bio) { - rbd_coll_end_req_index(rq, coll, cur_seg, - -ENOMEM, op_size); - goto next_seg; - } + /* Pass a cloned bio chain via an osd request */ - /* init OSD command: write or read */ - if (do_write) - rbd_req_write(rq, rbd_dev, - snapc, - ofs, - op_size, bio, - coll, cur_seg); + bio_chain = bio_chain_clone_range(&bio, + &bio_offset, chain_size, + GFP_ATOMIC); + if (bio_chain) + (void) rbd_do_op(rq, rbd_dev, snapc, + ofs, chain_size, + bio_chain, coll, cur_seg); else - rbd_req_read(rq, rbd_dev, - rbd_dev->mapping.snap_id, - ofs, - op_size, bio, - coll, cur_seg); - -next_seg: - size -= op_size; - ofs += op_size; + rbd_coll_end_req_index(rq, coll, cur_seg, + -ENOMEM, chain_size); + size -= chain_size; + ofs += chain_size; cur_seg++; - rq_bio = next_bio; } while (size > 0); kref_put(&coll->kref, rbd_coll_release); - if (bp) - bio_pair_release(bp); spin_lock_irq(q->queue_lock); ceph_put_snap_context(snapc); @@ -1576,28 +1646,47 @@ next_seg: /* * a queue callback. Makes sure that we don't create a bio that spans across * multiple osd objects. One exception would be with a single page bios, - * which we handle later at bio_chain_clone + * which we handle later at bio_chain_clone_range() */ static int rbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd, struct bio_vec *bvec) { struct rbd_device *rbd_dev = q->queuedata; - unsigned int chunk_sectors; - sector_t sector; - unsigned int bio_sectors; - int max; + sector_t sector_offset; + sector_t sectors_per_obj; + sector_t obj_sector_offset; + int ret; - chunk_sectors = 1 << (rbd_dev->header.obj_order - SECTOR_SHIFT); - sector = bmd->bi_sector + get_start_sect(bmd->bi_bdev); - bio_sectors = bmd->bi_size >> SECTOR_SHIFT; + /* + * Find how far into its rbd object the partition-relative + * bio start sector is to offset relative to the enclosing + * device. + */ + sector_offset = get_start_sect(bmd->bi_bdev) + bmd->bi_sector; + sectors_per_obj = 1 << (rbd_dev->header.obj_order - SECTOR_SHIFT); + obj_sector_offset = sector_offset & (sectors_per_obj - 1); + + /* + * Compute the number of bytes from that offset to the end + * of the object. Account for what's already used by the bio. + */ + ret = (int) (sectors_per_obj - obj_sector_offset) << SECTOR_SHIFT; + if (ret > bmd->bi_size) + ret -= bmd->bi_size; + else + ret = 0; - max = (chunk_sectors - ((sector & (chunk_sectors - 1)) - + bio_sectors)) << SECTOR_SHIFT; - if (max < 0) - max = 0; /* bio_add cannot handle a negative return */ - if (max <= bvec->bv_len && bio_sectors == 0) - return bvec->bv_len; - return max; + /* + * Don't send back more than was asked for. And if the bio + * was empty, let the whole thing through because: "Note + * that a block device *must* allow a single page to be + * added to an empty bio." + */ + rbd_assert(bvec->bv_len <= PAGE_SIZE); + if (ret > (int) bvec->bv_len || !bmd->bi_size) + ret = (int) bvec->bv_len; + + return ret; } static void rbd_free_disk(struct rbd_device *rbd_dev) @@ -1663,13 +1752,13 @@ rbd_dev_v1_header_read(struct rbd_device *rbd_dev, u64 *version) ret = -ENXIO; pr_warning("short header read for image %s" " (want %zd got %d)\n", - rbd_dev->image_name, size, ret); + rbd_dev->spec->image_name, size, ret); goto out_err; } if (!rbd_dev_ondisk_valid(ondisk)) { ret = -ENXIO; pr_warning("invalid header for image %s\n", - rbd_dev->image_name); + rbd_dev->spec->image_name); goto out_err; } @@ -1707,19 +1796,32 @@ static int rbd_read_header(struct rbd_device *rbd_dev, return ret; } -static void __rbd_remove_all_snaps(struct rbd_device *rbd_dev) +static void rbd_remove_all_snaps(struct rbd_device *rbd_dev) { struct rbd_snap *snap; struct rbd_snap *next; list_for_each_entry_safe(snap, next, &rbd_dev->snaps, node) - __rbd_remove_snap_dev(snap); + rbd_remove_snap_dev(snap); +} + +static void rbd_update_mapping_size(struct rbd_device *rbd_dev) +{ + sector_t size; + + if (rbd_dev->spec->snap_id != CEPH_NOSNAP) + return; + + size = (sector_t) rbd_dev->header.image_size / SECTOR_SIZE; + dout("setting size to %llu sectors", (unsigned long long) size); + rbd_dev->mapping.size = (u64) size; + set_capacity(rbd_dev->disk, size); } /* * only read the first part of the ondisk header, without the snaps info */ -static int __rbd_refresh_header(struct rbd_device *rbd_dev, u64 *hver) +static int rbd_dev_v1_refresh(struct rbd_device *rbd_dev, u64 *hver) { int ret; struct rbd_image_header h; @@ -1730,17 +1832,9 @@ static int __rbd_refresh_header(struct rbd_device *rbd_dev, u64 *hver) down_write(&rbd_dev->header_rwsem); - /* resized? */ - if (rbd_dev->mapping.snap_id == CEPH_NOSNAP) { - sector_t size = (sector_t) h.image_size / SECTOR_SIZE; - - if (size != (sector_t) rbd_dev->mapping.size) { - dout("setting size to %llu sectors", - (unsigned long long) size); - rbd_dev->mapping.size = (u64) size; - set_capacity(rbd_dev->disk, size); - } - } + /* Update image size, and check for resize of mapped image */ + rbd_dev->header.image_size = h.image_size; + rbd_update_mapping_size(rbd_dev); /* rbd_dev->header.object_prefix shouldn't change */ kfree(rbd_dev->header.snap_sizes); @@ -1768,12 +1862,16 @@ static int __rbd_refresh_header(struct rbd_device *rbd_dev, u64 *hver) return ret; } -static int rbd_refresh_header(struct rbd_device *rbd_dev, u64 *hver) +static int rbd_dev_refresh(struct rbd_device *rbd_dev, u64 *hver) { int ret; + rbd_assert(rbd_image_format_valid(rbd_dev->image_format)); mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); - ret = __rbd_refresh_header(rbd_dev, hver); + if (rbd_dev->image_format == 1) + ret = rbd_dev_v1_refresh(rbd_dev, hver); + else + ret = rbd_dev_v2_refresh(rbd_dev, hver); mutex_unlock(&ctl_mutex); return ret; @@ -1885,7 +1983,7 @@ static ssize_t rbd_pool_show(struct device *dev, { struct rbd_device *rbd_dev = dev_to_rbd_dev(dev); - return sprintf(buf, "%s\n", rbd_dev->pool_name); + return sprintf(buf, "%s\n", rbd_dev->spec->pool_name); } static ssize_t rbd_pool_id_show(struct device *dev, @@ -1893,7 +1991,8 @@ static ssize_t rbd_pool_id_show(struct device *dev, { struct rbd_device *rbd_dev = dev_to_rbd_dev(dev); - return sprintf(buf, "%d\n", rbd_dev->pool_id); + return sprintf(buf, "%llu\n", + (unsigned long long) rbd_dev->spec->pool_id); } static ssize_t rbd_name_show(struct device *dev, @@ -1901,7 +2000,10 @@ static ssize_t rbd_name_show(struct device *dev, { struct rbd_device *rbd_dev = dev_to_rbd_dev(dev); - return sprintf(buf, "%s\n", rbd_dev->image_name); + if (rbd_dev->spec->image_name) + return sprintf(buf, "%s\n", rbd_dev->spec->image_name); + + return sprintf(buf, "(unknown)\n"); } static ssize_t rbd_image_id_show(struct device *dev, @@ -1909,7 +2011,7 @@ static ssize_t rbd_image_id_show(struct device *dev, { struct rbd_device *rbd_dev = dev_to_rbd_dev(dev); - return sprintf(buf, "%s\n", rbd_dev->image_id); + return sprintf(buf, "%s\n", rbd_dev->spec->image_id); } /* @@ -1922,7 +2024,50 @@ static ssize_t rbd_snap_show(struct device *dev, { struct rbd_device *rbd_dev = dev_to_rbd_dev(dev); - return sprintf(buf, "%s\n", rbd_dev->mapping.snap_name); + return sprintf(buf, "%s\n", rbd_dev->spec->snap_name); +} + +/* + * For an rbd v2 image, shows the pool id, image id, and snapshot id + * for the parent image. If there is no parent, simply shows + * "(no parent image)". + */ +static ssize_t rbd_parent_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct rbd_device *rbd_dev = dev_to_rbd_dev(dev); + struct rbd_spec *spec = rbd_dev->parent_spec; + int count; + char *bufp = buf; + + if (!spec) + return sprintf(buf, "(no parent image)\n"); + + count = sprintf(bufp, "pool_id %llu\npool_name %s\n", + (unsigned long long) spec->pool_id, spec->pool_name); + if (count < 0) + return count; + bufp += count; + + count = sprintf(bufp, "image_id %s\nimage_name %s\n", spec->image_id, + spec->image_name ? spec->image_name : "(unknown)"); + if (count < 0) + return count; + bufp += count; + + count = sprintf(bufp, "snap_id %llu\nsnap_name %s\n", + (unsigned long long) spec->snap_id, spec->snap_name); + if (count < 0) + return count; + bufp += count; + + count = sprintf(bufp, "overlap %llu\n", rbd_dev->parent_overlap); + if (count < 0) + return count; + bufp += count; + + return (ssize_t) (bufp - buf); } static ssize_t rbd_image_refresh(struct device *dev, @@ -1933,7 +2078,7 @@ static ssize_t rbd_image_refresh(struct device *dev, struct rbd_device *rbd_dev = dev_to_rbd_dev(dev); int ret; - ret = rbd_refresh_header(rbd_dev, NULL); + ret = rbd_dev_refresh(rbd_dev, NULL); return ret < 0 ? ret : size; } @@ -1948,6 +2093,7 @@ static DEVICE_ATTR(name, S_IRUGO, rbd_name_show, NULL); static DEVICE_ATTR(image_id, S_IRUGO, rbd_image_id_show, NULL); static DEVICE_ATTR(refresh, S_IWUSR, NULL, rbd_image_refresh); static DEVICE_ATTR(current_snap, S_IRUGO, rbd_snap_show, NULL); +static DEVICE_ATTR(parent, S_IRUGO, rbd_parent_show, NULL); static struct attribute *rbd_attrs[] = { &dev_attr_size.attr, @@ -1959,6 +2105,7 @@ static struct attribute *rbd_attrs[] = { &dev_attr_name.attr, &dev_attr_image_id.attr, &dev_attr_current_snap.attr, + &dev_attr_parent.attr, &dev_attr_refresh.attr, NULL }; @@ -2047,6 +2194,74 @@ static struct device_type rbd_snap_device_type = { .release = rbd_snap_dev_release, }; +static struct rbd_spec *rbd_spec_get(struct rbd_spec *spec) +{ + kref_get(&spec->kref); + + return spec; +} + +static void rbd_spec_free(struct kref *kref); +static void rbd_spec_put(struct rbd_spec *spec) +{ + if (spec) + kref_put(&spec->kref, rbd_spec_free); +} + +static struct rbd_spec *rbd_spec_alloc(void) +{ + struct rbd_spec *spec; + + spec = kzalloc(sizeof (*spec), GFP_KERNEL); + if (!spec) + return NULL; + kref_init(&spec->kref); + + rbd_spec_put(rbd_spec_get(spec)); /* TEMPORARY */ + + return spec; +} + +static void rbd_spec_free(struct kref *kref) +{ + struct rbd_spec *spec = container_of(kref, struct rbd_spec, kref); + + kfree(spec->pool_name); + kfree(spec->image_id); + kfree(spec->image_name); + kfree(spec->snap_name); + kfree(spec); +} + +struct rbd_device *rbd_dev_create(struct rbd_client *rbdc, + struct rbd_spec *spec) +{ + struct rbd_device *rbd_dev; + + rbd_dev = kzalloc(sizeof (*rbd_dev), GFP_KERNEL); + if (!rbd_dev) + return NULL; + + spin_lock_init(&rbd_dev->lock); + INIT_LIST_HEAD(&rbd_dev->node); + INIT_LIST_HEAD(&rbd_dev->snaps); + init_rwsem(&rbd_dev->header_rwsem); + + rbd_dev->spec = spec; + rbd_dev->rbd_client = rbdc; + + return rbd_dev; +} + +static void rbd_dev_destroy(struct rbd_device *rbd_dev) +{ + rbd_spec_put(rbd_dev->parent_spec); + kfree(rbd_dev->header_name); + rbd_put_client(rbd_dev->rbd_client); + rbd_spec_put(rbd_dev->spec); + kfree(rbd_dev); +} + static bool rbd_snap_registered(struct rbd_snap *snap) { bool ret = snap->dev.type == &rbd_snap_device_type; @@ -2057,7 +2272,7 @@ static bool rbd_snap_registered(struct rbd_snap *snap) return ret; } -static void __rbd_remove_snap_dev(struct rbd_snap *snap) +static void rbd_remove_snap_dev(struct rbd_snap *snap) { list_del(&snap->node); if (device_is_registered(&snap->dev)) @@ -2073,7 +2288,7 @@ static int rbd_register_snap_dev(struct rbd_snap *snap, dev->type = &rbd_snap_device_type; dev->parent = parent; dev->release = rbd_snap_dev_release; - dev_set_name(dev, "snap_%s", snap->name); + dev_set_name(dev, "%s%s", RBD_SNAP_DEV_NAME_PREFIX, snap->name); dout("%s: registering device for snapshot %s\n", __func__, snap->name); ret = device_register(dev); @@ -2189,6 +2404,7 @@ static int rbd_dev_v2_object_prefix(struct rbd_device *rbd_dev) dout("%s: rbd_req_sync_exec returned %d\n", __func__, ret); if (ret < 0) goto out; + ret = 0; /* rbd_req_sync_exec() can return positive */ p = reply_buf; rbd_dev->header.object_prefix = ceph_extract_encoded_string(&p, @@ -2216,6 +2432,7 @@ static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id, __le64 features; __le64 incompat; } features_buf = { 0 }; + u64 incompat; int ret; ret = rbd_req_sync_exec(rbd_dev, rbd_dev->header_name, @@ -2226,6 +2443,11 @@ static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id, dout("%s: rbd_req_sync_exec returned %d\n", __func__, ret); if (ret < 0) return ret; + + incompat = le64_to_cpu(features_buf.incompat); + if (incompat & ~RBD_FEATURES_ALL) + return -ENXIO; + *snap_features = le64_to_cpu(features_buf.features); dout(" snap_id 0x%016llx features = 0x%016llx incompat = 0x%016llx\n", @@ -2242,6 +2464,183 @@ static int rbd_dev_v2_features(struct rbd_device *rbd_dev) &rbd_dev->header.features); } +static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) +{ + struct rbd_spec *parent_spec; + size_t size; + void *reply_buf = NULL; + __le64 snapid; + void *p; + void *end; + char *image_id; + u64 overlap; + size_t len = 0; + int ret; + + parent_spec = rbd_spec_alloc(); + if (!parent_spec) + return -ENOMEM; + + size = sizeof (__le64) + /* pool_id */ + sizeof (__le32) + RBD_IMAGE_ID_LEN_MAX + /* image_id */ + sizeof (__le64) + /* snap_id */ + sizeof (__le64); /* overlap */ + reply_buf = kmalloc(size, GFP_KERNEL); + if (!reply_buf) { + ret = -ENOMEM; + goto out_err; + } + + snapid = cpu_to_le64(CEPH_NOSNAP); + ret = rbd_req_sync_exec(rbd_dev, rbd_dev->header_name, + "rbd", "get_parent", + (char *) &snapid, sizeof (snapid), + (char *) reply_buf, size, + CEPH_OSD_FLAG_READ, NULL); + dout("%s: rbd_req_sync_exec returned %d\n", __func__, ret); + if (ret < 0) + goto out_err; + + ret = -ERANGE; + p = reply_buf; + end = (char *) reply_buf + size; + ceph_decode_64_safe(&p, end, parent_spec->pool_id, out_err); + if (parent_spec->pool_id == CEPH_NOPOOL) + goto out; /* No parent? No problem. */ + + image_id = ceph_extract_encoded_string(&p, end, &len, GFP_KERNEL); + if (IS_ERR(image_id)) { + ret = PTR_ERR(image_id); + goto out_err; + } + parent_spec->image_id = image_id; + parent_spec->image_id_len = len; + ceph_decode_64_safe(&p, end, parent_spec->snap_id, out_err); + ceph_decode_64_safe(&p, end, overlap, out_err); + + rbd_dev->parent_overlap = overlap; + rbd_dev->parent_spec = parent_spec; + parent_spec = NULL; /* rbd_dev now owns this */ +out: + ret = 0; +out_err: + kfree(reply_buf); + rbd_spec_put(parent_spec); + + return ret; +} + +static char *rbd_dev_image_name(struct rbd_device *rbd_dev) +{ + size_t image_id_size; + char *image_id; + void *p; + void *end; + size_t size; + void *reply_buf = NULL; + size_t len = 0; + char *image_name = NULL; + int ret; + + rbd_assert(!rbd_dev->spec->image_name); + + image_id_size = sizeof (__le32) + rbd_dev->spec->image_id_len; + image_id = kmalloc(image_id_size, GFP_KERNEL); + if (!image_id) + return NULL; + + p = image_id; + end = (char *) image_id + image_id_size; + ceph_encode_string(&p, end, rbd_dev->spec->image_id, + (u32) rbd_dev->spec->image_id_len); + + size = sizeof (__le32) + RBD_IMAGE_NAME_LEN_MAX; + reply_buf = kmalloc(size, GFP_KERNEL); + if (!reply_buf) + goto out; + + ret = rbd_req_sync_exec(rbd_dev, RBD_DIRECTORY, + "rbd", "dir_get_name", + image_id, image_id_size, + (char *) reply_buf, size, + CEPH_OSD_FLAG_READ, NULL); + if (ret < 0) + goto out; + p = reply_buf; + end = (char *) reply_buf + size; + image_name = ceph_extract_encoded_string(&p, end, &len, GFP_KERNEL); + if (IS_ERR(image_name)) + image_name = NULL; + else + dout("%s: name is %s len is %zd\n", __func__, image_name, len); +out: + kfree(reply_buf); + kfree(image_id); + + return image_name; +} + +/* + * When a parent image gets probed, we only have the pool, image, + * and snapshot ids but not the names of any of them. This call + * is made later to fill in those names. It has to be done after + * rbd_dev_snaps_update() has completed because some of the + * information (in particular, snapshot name) is not available + * until then. + */ +static int rbd_dev_probe_update_spec(struct rbd_device *rbd_dev) +{ + struct ceph_osd_client *osdc; + const char *name; + void *reply_buf = NULL; + int ret; + + if (rbd_dev->spec->pool_name) + return 0; /* Already have the names */ + + /* Look up the pool name */ + + osdc = &rbd_dev->rbd_client->client->osdc; + name = ceph_pg_pool_name_by_id(osdc->osdmap, rbd_dev->spec->pool_id); + if (!name) + return -EIO; /* pool id too large (>= 2^31) */ + + rbd_dev->spec->pool_name = kstrdup(name, GFP_KERNEL); + if (!rbd_dev->spec->pool_name) + return -ENOMEM; + + /* Fetch the image name; tolerate failure here */ + + name = rbd_dev_image_name(rbd_dev); + if (name) { + rbd_dev->spec->image_name_len = strlen(name); + rbd_dev->spec->image_name = (char *) name; + } else { + pr_warning(RBD_DRV_NAME "%d " + "unable to get image name for image id %s\n", + rbd_dev->major, rbd_dev->spec->image_id); + } + + /* Look up the snapshot name. */ + + name = rbd_snap_name(rbd_dev, rbd_dev->spec->snap_id); + if (!name) { + ret = -EIO; + goto out_err; + } + rbd_dev->spec->snap_name = kstrdup(name, GFP_KERNEL); + if(!rbd_dev->spec->snap_name) + goto out_err; + + return 0; +out_err: + kfree(reply_buf); + kfree(rbd_dev->spec->pool_name); + rbd_dev->spec->pool_name = NULL; + + return ret; +} + static int rbd_dev_v2_snap_context(struct rbd_device *rbd_dev, u64 *ver) { size_t size; @@ -2328,7 +2727,6 @@ static char *rbd_dev_v2_snap_name(struct rbd_device *rbd_dev, u32 which) int ret; void *p; void *end; - size_t snap_name_len; char *snap_name; size = sizeof (__le32) + RBD_MAX_SNAP_NAME_LEN; @@ -2348,9 +2746,7 @@ static char *rbd_dev_v2_snap_name(struct rbd_device *rbd_dev, u32 which) p = reply_buf; end = (char *) reply_buf + size; - snap_name_len = 0; - snap_name = ceph_extract_encoded_string(&p, end, &snap_name_len, - GFP_KERNEL); + snap_name = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL); if (IS_ERR(snap_name)) { ret = PTR_ERR(snap_name); goto out; @@ -2397,6 +2793,41 @@ static char *rbd_dev_snap_info(struct rbd_device *rbd_dev, u32 which, return ERR_PTR(-EINVAL); } +static int rbd_dev_v2_refresh(struct rbd_device *rbd_dev, u64 *hver) +{ + int ret; + __u8 obj_order; + + down_write(&rbd_dev->header_rwsem); + + /* Grab old order first, to see if it changes */ + + obj_order = rbd_dev->header.obj_order, + ret = rbd_dev_v2_image_size(rbd_dev); + if (ret) + goto out; + if (rbd_dev->header.obj_order != obj_order) { + ret = -EIO; + goto out; + } + rbd_update_mapping_size(rbd_dev); + + ret = rbd_dev_v2_snap_context(rbd_dev, hver); + dout("rbd_dev_v2_snap_context returned %d\n", ret); + if (ret) + goto out; + ret = rbd_dev_snaps_update(rbd_dev); + dout("rbd_dev_snaps_update returned %d\n", ret); + if (ret) + goto out; + ret = rbd_dev_snaps_register(rbd_dev); + dout("rbd_dev_snaps_register returned %d\n", ret); +out: + up_write(&rbd_dev->header_rwsem); + + return ret; +} + /* * Scan the rbd device's current snapshot list and compare it to the * newly-received snapshot context. Remove any existing snapshots @@ -2436,12 +2867,12 @@ static int rbd_dev_snaps_update(struct rbd_device *rbd_dev) /* Existing snapshot not in the new snap context */ - if (rbd_dev->mapping.snap_id == snap->id) - rbd_dev->mapping.snap_exists = false; - __rbd_remove_snap_dev(snap); + if (rbd_dev->spec->snap_id == snap->id) + rbd_dev->exists = false; + rbd_remove_snap_dev(snap); dout("%ssnap id %llu has been removed\n", - rbd_dev->mapping.snap_id == snap->id ? - "mapped " : "", + rbd_dev->spec->snap_id == snap->id ? + "mapped " : "", (unsigned long long) snap->id); /* Done with this list entry; advance */ @@ -2559,7 +2990,7 @@ static int rbd_init_watch_dev(struct rbd_device *rbd_dev) do { ret = rbd_req_sync_watch(rbd_dev); if (ret == -ERANGE) { - rc = rbd_refresh_header(rbd_dev, NULL); + rc = rbd_dev_refresh(rbd_dev, NULL); if (rc < 0) return rc; } @@ -2621,8 +3052,8 @@ static void rbd_dev_id_put(struct rbd_device *rbd_dev) struct rbd_device *rbd_dev; rbd_dev = list_entry(tmp, struct rbd_device, node); - if (rbd_id > max_id) - max_id = rbd_id; + if (rbd_dev->dev_id > max_id) + max_id = rbd_dev->dev_id; } spin_unlock(&rbd_dev_list_lock); @@ -2722,73 +3153,140 @@ static inline char *dup_token(const char **buf, size_t *lenp) } /* - * This fills in the pool_name, image_name, image_name_len, rbd_dev, - * rbd_md_name, and name fields of the given rbd_dev, based on the - * list of monitor addresses and other options provided via - * /sys/bus/rbd/add. Returns a pointer to a dynamically-allocated - * copy of the snapshot name to map if successful, or a - * pointer-coded error otherwise. + * Parse the options provided for an "rbd add" (i.e., rbd image + * mapping) request. These arrive via a write to /sys/bus/rbd/add, + * and the data written is passed here via a NUL-terminated buffer. + * Returns 0 if successful or an error code otherwise. + * + * The information extracted from these options is recorded in + * the other parameters which return dynamically-allocated + * structures: + * ceph_opts + * The address of a pointer that will refer to a ceph options + * structure. Caller must release the returned pointer using + * ceph_destroy_options() when it is no longer needed. + * rbd_opts + * Address of an rbd options pointer. Fully initialized by + * this function; caller must release with kfree(). + * spec + * Address of an rbd image specification pointer. Fully + * initialized by this function based on parsed options. + * Caller must release with rbd_spec_put(). * - * Note: rbd_dev is assumed to have been initially zero-filled. + * The options passed take this form: + * <mon_addrs> <options> <pool_name> <image_name> [<snap_id>] + * where: + * <mon_addrs> + * A comma-separated list of one or more monitor addresses. + * A monitor address is an ip address, optionally followed + * by a port number (separated by a colon). + * I.e.: ip1[:port1][,ip2[:port2]...] + * <options> + * A comma-separated list of ceph and/or rbd options. + * <pool_name> + * The name of the rados pool containing the rbd image. + * <image_name> + * The name of the image in that pool to map. + * <snap_id> + * An optional snapshot id. If provided, the mapping will + * present data from the image at the time that snapshot was + * created. The image head is used if no snapshot id is + * provided. Snapshot mappings are always read-only. */ -static char *rbd_add_parse_args(struct rbd_device *rbd_dev, - const char *buf, - const char **mon_addrs, - size_t *mon_addrs_size, - char *options, - size_t options_size) +static int rbd_add_parse_args(const char *buf, + struct ceph_options **ceph_opts, + struct rbd_options **opts, + struct rbd_spec **rbd_spec) { size_t len; - char *err_ptr = ERR_PTR(-EINVAL); - char *snap_name; + char *options; + const char *mon_addrs; + size_t mon_addrs_size; + struct rbd_spec *spec = NULL; + struct rbd_options *rbd_opts = NULL; + struct ceph_options *copts; + int ret; /* The first four tokens are required */ len = next_token(&buf); if (!len) - return err_ptr; - *mon_addrs_size = len + 1; - *mon_addrs = buf; - + return -EINVAL; /* Missing monitor address(es) */ + mon_addrs = buf; + mon_addrs_size = len + 1; buf += len; - len = copy_token(&buf, options, options_size); - if (!len || len >= options_size) - return err_ptr; + ret = -EINVAL; + options = dup_token(&buf, NULL); + if (!options) + return -ENOMEM; + if (!*options) + goto out_err; /* Missing options */ - err_ptr = ERR_PTR(-ENOMEM); - rbd_dev->pool_name = dup_token(&buf, NULL); - if (!rbd_dev->pool_name) - goto out_err; + spec = rbd_spec_alloc(); + if (!spec) + goto out_mem; - rbd_dev->image_name = dup_token(&buf, &rbd_dev->image_name_len); - if (!rbd_dev->image_name) - goto out_err; + spec->pool_name = dup_token(&buf, NULL); + if (!spec->pool_name) + goto out_mem; + if (!*spec->pool_name) + goto out_err; /* Missing pool name */ - /* Snapshot name is optional */ + spec->image_name = dup_token(&buf, &spec->image_name_len); + if (!spec->image_name) + goto out_mem; + if (!*spec->image_name) + goto out_err; /* Missing image name */ + + /* + * Snapshot name is optional; default is to use "-" + * (indicating the head/no snapshot). + */ len = next_token(&buf); if (!len) { buf = RBD_SNAP_HEAD_NAME; /* No snapshot supplied */ len = sizeof (RBD_SNAP_HEAD_NAME) - 1; - } - snap_name = kmalloc(len + 1, GFP_KERNEL); - if (!snap_name) + } else if (len > RBD_MAX_SNAP_NAME_LEN) { + ret = -ENAMETOOLONG; goto out_err; - memcpy(snap_name, buf, len); - *(snap_name + len) = '\0'; + } + spec->snap_name = kmalloc(len + 1, GFP_KERNEL); + if (!spec->snap_name) + goto out_mem; + memcpy(spec->snap_name, buf, len); + *(spec->snap_name + len) = '\0'; -dout(" SNAP_NAME is <%s>, len is %zd\n", snap_name, len); + /* Initialize all rbd options to the defaults */ - return snap_name; + rbd_opts = kzalloc(sizeof (*rbd_opts), GFP_KERNEL); + if (!rbd_opts) + goto out_mem; + + rbd_opts->read_only = RBD_READ_ONLY_DEFAULT; + + copts = ceph_parse_options(options, mon_addrs, + mon_addrs + mon_addrs_size - 1, + parse_rbd_opts_token, rbd_opts); + if (IS_ERR(copts)) { + ret = PTR_ERR(copts); + goto out_err; + } + kfree(options); + *ceph_opts = copts; + *opts = rbd_opts; + *rbd_spec = spec; + + return 0; +out_mem: + ret = -ENOMEM; out_err: - kfree(rbd_dev->image_name); - rbd_dev->image_name = NULL; - rbd_dev->image_name_len = 0; - kfree(rbd_dev->pool_name); - rbd_dev->pool_name = NULL; + kfree(rbd_opts); + rbd_spec_put(spec); + kfree(options); - return err_ptr; + return ret; } /* @@ -2814,14 +3312,22 @@ static int rbd_dev_image_id(struct rbd_device *rbd_dev) void *p; /* + * When probing a parent image, the image id is already + * known (and the image name likely is not). There's no + * need to fetch the image id again in this case. + */ + if (rbd_dev->spec->image_id) + return 0; + + /* * First, see if the format 2 image id file exists, and if * so, get the image's persistent id from it. */ - size = sizeof (RBD_ID_PREFIX) + rbd_dev->image_name_len; + size = sizeof (RBD_ID_PREFIX) + rbd_dev->spec->image_name_len; object_name = kmalloc(size, GFP_NOIO); if (!object_name) return -ENOMEM; - sprintf(object_name, "%s%s", RBD_ID_PREFIX, rbd_dev->image_name); + sprintf(object_name, "%s%s", RBD_ID_PREFIX, rbd_dev->spec->image_name); dout("rbd id object name is %s\n", object_name); /* Response will be an encoded string, which includes a length */ @@ -2841,17 +3347,18 @@ static int rbd_dev_image_id(struct rbd_device *rbd_dev) dout("%s: rbd_req_sync_exec returned %d\n", __func__, ret); if (ret < 0) goto out; + ret = 0; /* rbd_req_sync_exec() can return positive */ p = response; - rbd_dev->image_id = ceph_extract_encoded_string(&p, + rbd_dev->spec->image_id = ceph_extract_encoded_string(&p, p + RBD_IMAGE_ID_LEN_MAX, - &rbd_dev->image_id_len, + &rbd_dev->spec->image_id_len, GFP_NOIO); - if (IS_ERR(rbd_dev->image_id)) { - ret = PTR_ERR(rbd_dev->image_id); - rbd_dev->image_id = NULL; + if (IS_ERR(rbd_dev->spec->image_id)) { + ret = PTR_ERR(rbd_dev->spec->image_id); + rbd_dev->spec->image_id = NULL; } else { - dout("image_id is %s\n", rbd_dev->image_id); + dout("image_id is %s\n", rbd_dev->spec->image_id); } out: kfree(response); @@ -2867,26 +3374,33 @@ static int rbd_dev_v1_probe(struct rbd_device *rbd_dev) /* Version 1 images have no id; empty string is used */ - rbd_dev->image_id = kstrdup("", GFP_KERNEL); - if (!rbd_dev->image_id) + rbd_dev->spec->image_id = kstrdup("", GFP_KERNEL); + if (!rbd_dev->spec->image_id) return -ENOMEM; - rbd_dev->image_id_len = 0; + rbd_dev->spec->image_id_len = 0; /* Record the header object name for this rbd image. */ - size = rbd_dev->image_name_len + sizeof (RBD_SUFFIX); + size = rbd_dev->spec->image_name_len + sizeof (RBD_SUFFIX); rbd_dev->header_name = kmalloc(size, GFP_KERNEL); if (!rbd_dev->header_name) { ret = -ENOMEM; goto out_err; } - sprintf(rbd_dev->header_name, "%s%s", rbd_dev->image_name, RBD_SUFFIX); + sprintf(rbd_dev->header_name, "%s%s", + rbd_dev->spec->image_name, RBD_SUFFIX); /* Populate rbd image metadata */ ret = rbd_read_header(rbd_dev, &rbd_dev->header); if (ret < 0) goto out_err; + + /* Version 1 images have no parent (no layering) */ + + rbd_dev->parent_spec = NULL; + rbd_dev->parent_overlap = 0; + rbd_dev->image_format = 1; dout("discovered version 1 image, header name is %s\n", @@ -2897,8 +3411,8 @@ static int rbd_dev_v1_probe(struct rbd_device *rbd_dev) out_err: kfree(rbd_dev->header_name); rbd_dev->header_name = NULL; - kfree(rbd_dev->image_id); - rbd_dev->image_id = NULL; + kfree(rbd_dev->spec->image_id); + rbd_dev->spec->image_id = NULL; return ret; } @@ -2913,12 +3427,12 @@ static int rbd_dev_v2_probe(struct rbd_device *rbd_dev) * Image id was filled in by the caller. Record the header * object name for this rbd image. */ - size = sizeof (RBD_HEADER_PREFIX) + rbd_dev->image_id_len; + size = sizeof (RBD_HEADER_PREFIX) + rbd_dev->spec->image_id_len; rbd_dev->header_name = kmalloc(size, GFP_KERNEL); if (!rbd_dev->header_name) return -ENOMEM; sprintf(rbd_dev->header_name, "%s%s", - RBD_HEADER_PREFIX, rbd_dev->image_id); + RBD_HEADER_PREFIX, rbd_dev->spec->image_id); /* Get the size and object order for the image */ @@ -2932,12 +3446,20 @@ static int rbd_dev_v2_probe(struct rbd_device *rbd_dev) if (ret < 0) goto out_err; - /* Get the features for the image */ + /* Get the and check features for the image */ ret = rbd_dev_v2_features(rbd_dev); if (ret < 0) goto out_err; + /* If the image supports layering, get the parent info */ + + if (rbd_dev->header.features & RBD_FEATURE_LAYERING) { + ret = rbd_dev_v2_parent_info(rbd_dev); + if (ret < 0) + goto out_err; + } + /* crypto and compression type aren't (yet) supported for v2 images */ rbd_dev->header.crypt_type = 0; @@ -2955,8 +3477,11 @@ static int rbd_dev_v2_probe(struct rbd_device *rbd_dev) dout("discovered version 2 image, header name is %s\n", rbd_dev->header_name); - return -ENOTSUPP; + return 0; out_err: + rbd_dev->parent_overlap = 0; + rbd_spec_put(rbd_dev->parent_spec); + rbd_dev->parent_spec = NULL; kfree(rbd_dev->header_name); rbd_dev->header_name = NULL; kfree(rbd_dev->header.object_prefix); @@ -2965,91 +3490,22 @@ out_err: return ret; } -/* - * Probe for the existence of the header object for the given rbd - * device. For format 2 images this includes determining the image - * id. - */ -static int rbd_dev_probe(struct rbd_device *rbd_dev) +static int rbd_dev_probe_finish(struct rbd_device *rbd_dev) { int ret; - /* - * Get the id from the image id object. If it's not a - * format 2 image, we'll get ENOENT back, and we'll assume - * it's a format 1 image. - */ - ret = rbd_dev_image_id(rbd_dev); - if (ret) - ret = rbd_dev_v1_probe(rbd_dev); - else - ret = rbd_dev_v2_probe(rbd_dev); + /* no need to lock here, as rbd_dev is not registered yet */ + ret = rbd_dev_snaps_update(rbd_dev); if (ret) - dout("probe failed, returning %d\n", ret); - - return ret; -} - -static ssize_t rbd_add(struct bus_type *bus, - const char *buf, - size_t count) -{ - char *options; - struct rbd_device *rbd_dev = NULL; - const char *mon_addrs = NULL; - size_t mon_addrs_size = 0; - struct ceph_osd_client *osdc; - int rc = -ENOMEM; - char *snap_name; - - if (!try_module_get(THIS_MODULE)) - return -ENODEV; - - options = kmalloc(count, GFP_KERNEL); - if (!options) - goto err_out_mem; - rbd_dev = kzalloc(sizeof(*rbd_dev), GFP_KERNEL); - if (!rbd_dev) - goto err_out_mem; - - /* static rbd_device initialization */ - spin_lock_init(&rbd_dev->lock); - INIT_LIST_HEAD(&rbd_dev->node); - INIT_LIST_HEAD(&rbd_dev->snaps); - init_rwsem(&rbd_dev->header_rwsem); - - /* parse add command */ - snap_name = rbd_add_parse_args(rbd_dev, buf, - &mon_addrs, &mon_addrs_size, options, count); - if (IS_ERR(snap_name)) { - rc = PTR_ERR(snap_name); - goto err_out_mem; - } - - rc = rbd_get_client(rbd_dev, mon_addrs, mon_addrs_size - 1, options); - if (rc < 0) - goto err_out_args; - - /* pick the pool */ - osdc = &rbd_dev->rbd_client->client->osdc; - rc = ceph_pg_poolid_by_name(osdc->osdmap, rbd_dev->pool_name); - if (rc < 0) - goto err_out_client; - rbd_dev->pool_id = rc; - - rc = rbd_dev_probe(rbd_dev); - if (rc < 0) - goto err_out_client; - rbd_assert(rbd_image_format_valid(rbd_dev->image_format)); + return ret; - /* no need to lock here, as rbd_dev is not registered yet */ - rc = rbd_dev_snaps_update(rbd_dev); - if (rc) - goto err_out_header; + ret = rbd_dev_probe_update_spec(rbd_dev); + if (ret) + goto err_out_snaps; - rc = rbd_dev_set_mapping(rbd_dev, snap_name); - if (rc) - goto err_out_header; + ret = rbd_dev_set_mapping(rbd_dev); + if (ret) + goto err_out_snaps; /* generate unique id: find highest unique id, add one */ rbd_dev_id_get(rbd_dev); @@ -3061,34 +3517,33 @@ static ssize_t rbd_add(struct bus_type *bus, /* Get our block major device number. */ - rc = register_blkdev(0, rbd_dev->name); - if (rc < 0) + ret = register_blkdev(0, rbd_dev->name); + if (ret < 0) goto err_out_id; - rbd_dev->major = rc; + rbd_dev->major = ret; /* Set up the blkdev mapping. */ - rc = rbd_init_disk(rbd_dev); - if (rc) + ret = rbd_init_disk(rbd_dev); + if (ret) goto err_out_blkdev; - rc = rbd_bus_add_dev(rbd_dev); - if (rc) + ret = rbd_bus_add_dev(rbd_dev); + if (ret) goto err_out_disk; /* * At this point cleanup in the event of an error is the job * of the sysfs code (initiated by rbd_bus_del_dev()). */ - down_write(&rbd_dev->header_rwsem); - rc = rbd_dev_snaps_register(rbd_dev); + ret = rbd_dev_snaps_register(rbd_dev); up_write(&rbd_dev->header_rwsem); - if (rc) + if (ret) goto err_out_bus; - rc = rbd_init_watch_dev(rbd_dev); - if (rc) + ret = rbd_init_watch_dev(rbd_dev); + if (ret) goto err_out_bus; /* Everything's ready. Announce the disk to the world. */ @@ -3098,37 +3553,119 @@ static ssize_t rbd_add(struct bus_type *bus, pr_info("%s: added with size 0x%llx\n", rbd_dev->disk->disk_name, (unsigned long long) rbd_dev->mapping.size); - return count; - + return ret; err_out_bus: /* this will also clean up rest of rbd_dev stuff */ rbd_bus_del_dev(rbd_dev); - kfree(options); - return rc; + return ret; err_out_disk: rbd_free_disk(rbd_dev); err_out_blkdev: unregister_blkdev(rbd_dev->major, rbd_dev->name); err_out_id: rbd_dev_id_put(rbd_dev); -err_out_header: - rbd_header_free(&rbd_dev->header); +err_out_snaps: + rbd_remove_all_snaps(rbd_dev); + + return ret; +} + +/* + * Probe for the existence of the header object for the given rbd + * device. For format 2 images this includes determining the image + * id. + */ +static int rbd_dev_probe(struct rbd_device *rbd_dev) +{ + int ret; + + /* + * Get the id from the image id object. If it's not a + * format 2 image, we'll get ENOENT back, and we'll assume + * it's a format 1 image. + */ + ret = rbd_dev_image_id(rbd_dev); + if (ret) + ret = rbd_dev_v1_probe(rbd_dev); + else + ret = rbd_dev_v2_probe(rbd_dev); + if (ret) { + dout("probe failed, returning %d\n", ret); + + return ret; + } + + ret = rbd_dev_probe_finish(rbd_dev); + if (ret) + rbd_header_free(&rbd_dev->header); + + return ret; +} + +static ssize_t rbd_add(struct bus_type *bus, + const char *buf, + size_t count) +{ + struct rbd_device *rbd_dev = NULL; + struct ceph_options *ceph_opts = NULL; + struct rbd_options *rbd_opts = NULL; + struct rbd_spec *spec = NULL; + struct rbd_client *rbdc; + struct ceph_osd_client *osdc; + int rc = -ENOMEM; + + if (!try_module_get(THIS_MODULE)) + return -ENODEV; + + /* parse add command */ + rc = rbd_add_parse_args(buf, &ceph_opts, &rbd_opts, &spec); + if (rc < 0) + goto err_out_module; + + rbdc = rbd_get_client(ceph_opts); + if (IS_ERR(rbdc)) { + rc = PTR_ERR(rbdc); + goto err_out_args; + } + ceph_opts = NULL; /* rbd_dev client now owns this */ + + /* pick the pool */ + osdc = &rbdc->client->osdc; + rc = ceph_pg_poolid_by_name(osdc->osdmap, spec->pool_name); + if (rc < 0) + goto err_out_client; + spec->pool_id = (u64) rc; + + rbd_dev = rbd_dev_create(rbdc, spec); + if (!rbd_dev) + goto err_out_client; + rbdc = NULL; /* rbd_dev now owns this */ + spec = NULL; /* rbd_dev now owns this */ + + rbd_dev->mapping.read_only = rbd_opts->read_only; + kfree(rbd_opts); + rbd_opts = NULL; /* done with this */ + + rc = rbd_dev_probe(rbd_dev); + if (rc < 0) + goto err_out_rbd_dev; + + return count; +err_out_rbd_dev: + rbd_dev_destroy(rbd_dev); err_out_client: - kfree(rbd_dev->header_name); - rbd_put_client(rbd_dev); - kfree(rbd_dev->image_id); + rbd_put_client(rbdc); err_out_args: - kfree(rbd_dev->mapping.snap_name); - kfree(rbd_dev->image_name); - kfree(rbd_dev->pool_name); -err_out_mem: - kfree(rbd_dev); - kfree(options); + if (ceph_opts) + ceph_destroy_options(ceph_opts); + kfree(rbd_opts); + rbd_spec_put(spec); +err_out_module: + module_put(THIS_MODULE); dout("Error adding device %s\n", buf); - module_put(THIS_MODULE); return (ssize_t) rc; } @@ -3163,7 +3700,6 @@ static void rbd_dev_release(struct device *dev) if (rbd_dev->watch_event) rbd_req_sync_unwatch(rbd_dev); - rbd_put_client(rbd_dev); /* clean up and free blkdev */ rbd_free_disk(rbd_dev); @@ -3173,13 +3709,9 @@ static void rbd_dev_release(struct device *dev) rbd_header_free(&rbd_dev->header); /* done with the id, and with the rbd_dev */ - kfree(rbd_dev->mapping.snap_name); - kfree(rbd_dev->image_id); - kfree(rbd_dev->header_name); - kfree(rbd_dev->pool_name); - kfree(rbd_dev->image_name); rbd_dev_id_put(rbd_dev); - kfree(rbd_dev); + rbd_assert(rbd_dev->rbd_client != NULL); + rbd_dev_destroy(rbd_dev); /* release module ref */ module_put(THIS_MODULE); @@ -3211,7 +3743,12 @@ static ssize_t rbd_remove(struct bus_type *bus, goto done; } - __rbd_remove_all_snaps(rbd_dev); + if (rbd_dev->open_count) { + ret = -EBUSY; + goto done; + } + + rbd_remove_all_snaps(rbd_dev); rbd_bus_del_dev(rbd_dev); done: diff --git a/drivers/block/rbd_types.h b/drivers/block/rbd_types.h index cbe77fa105ba..49d77cbcf8bd 100644 --- a/drivers/block/rbd_types.h +++ b/drivers/block/rbd_types.h @@ -46,8 +46,6 @@ #define RBD_MIN_OBJ_ORDER 16 #define RBD_MAX_OBJ_ORDER 30 -#define RBD_MAX_SEG_NAME_LEN 128 - #define RBD_COMP_NONE 0 #define RBD_CRYPT_NONE 0 diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 55074cba20eb..c1c74e030a58 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -57,17 +57,9 @@ * physically contiguous memory regions it is mapping into page sizes * that we support. * - * Traditionally the IOMMU core just handed us the mappings directly, - * after making sure the size is an order of a 4KiB page and that the - * mapping has natural alignment. - * - * To retain this behavior, we currently advertise that we support - * all page sizes that are an order of 4KiB. - * - * If at some point we'd like to utilize the IOMMU core's new behavior, - * we could change this to advertise the real page sizes we support. + * 512GB Pages are not supported due to a hardware bug */ -#define AMD_IOMMU_PGSIZES (~0xFFFUL) +#define AMD_IOMMU_PGSIZES ((~0xFFFUL) & ~(2ULL << 38)) static DEFINE_RWLOCK(amd_iommu_devtable_lock); @@ -140,6 +132,9 @@ static void free_dev_data(struct iommu_dev_data *dev_data) list_del(&dev_data->dev_data_list); spin_unlock_irqrestore(&dev_data_list_lock, flags); + if (dev_data->group) + iommu_group_put(dev_data->group); + kfree(dev_data); } @@ -274,41 +269,23 @@ static void swap_pci_ref(struct pci_dev **from, struct pci_dev *to) *from = to; } -#define REQ_ACS_FLAGS (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF) - -static int iommu_init_device(struct device *dev) +static struct pci_bus *find_hosted_bus(struct pci_bus *bus) { - struct pci_dev *dma_pdev = NULL, *pdev = to_pci_dev(dev); - struct iommu_dev_data *dev_data; - struct iommu_group *group; - u16 alias; - int ret; - - if (dev->archdata.iommu) - return 0; - - dev_data = find_dev_data(get_device_id(dev)); - if (!dev_data) - return -ENOMEM; - - alias = amd_iommu_alias_table[dev_data->devid]; - if (alias != dev_data->devid) { - struct iommu_dev_data *alias_data; + while (!bus->self) { + if (!pci_is_root_bus(bus)) + bus = bus->parent; + else + return ERR_PTR(-ENODEV); + } - alias_data = find_dev_data(alias); - if (alias_data == NULL) { - pr_err("AMD-Vi: Warning: Unhandled device %s\n", - dev_name(dev)); - free_dev_data(dev_data); - return -ENOTSUPP; - } - dev_data->alias_data = alias_data; + return bus; +} - dma_pdev = pci_get_bus_and_slot(alias >> 8, alias & 0xff); - } +#define REQ_ACS_FLAGS (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF) - if (dma_pdev == NULL) - dma_pdev = pci_dev_get(pdev); +static struct pci_dev *get_isolation_root(struct pci_dev *pdev) +{ + struct pci_dev *dma_pdev = pdev; /* Account for quirked devices */ swap_pci_ref(&dma_pdev, pci_get_dma_source(dma_pdev)); @@ -330,14 +307,9 @@ static int iommu_init_device(struct device *dev) * Finding the next device may require skipping virtual buses. */ while (!pci_is_root_bus(dma_pdev->bus)) { - struct pci_bus *bus = dma_pdev->bus; - - while (!bus->self) { - if (!pci_is_root_bus(bus)) - bus = bus->parent; - else - goto root_bus; - } + struct pci_bus *bus = find_hosted_bus(dma_pdev->bus); + if (IS_ERR(bus)) + break; if (pci_acs_path_enabled(bus->self, NULL, REQ_ACS_FLAGS)) break; @@ -345,19 +317,137 @@ static int iommu_init_device(struct device *dev) swap_pci_ref(&dma_pdev, pci_dev_get(bus->self)); } -root_bus: - group = iommu_group_get(&dma_pdev->dev); - pci_dev_put(dma_pdev); + return dma_pdev; +} + +static int use_pdev_iommu_group(struct pci_dev *pdev, struct device *dev) +{ + struct iommu_group *group = iommu_group_get(&pdev->dev); + int ret; + if (!group) { group = iommu_group_alloc(); if (IS_ERR(group)) return PTR_ERR(group); + + WARN_ON(&pdev->dev != dev); } ret = iommu_group_add_device(group, dev); - iommu_group_put(group); + return ret; +} + +static int use_dev_data_iommu_group(struct iommu_dev_data *dev_data, + struct device *dev) +{ + if (!dev_data->group) { + struct iommu_group *group = iommu_group_alloc(); + if (IS_ERR(group)) + return PTR_ERR(group); + + dev_data->group = group; + } + + return iommu_group_add_device(dev_data->group, dev); +} + +static int init_iommu_group(struct device *dev) +{ + struct iommu_dev_data *dev_data; + struct iommu_group *group; + struct pci_dev *dma_pdev; + int ret; + + group = iommu_group_get(dev); + if (group) { + iommu_group_put(group); + return 0; + } + + dev_data = find_dev_data(get_device_id(dev)); + if (!dev_data) + return -ENOMEM; + + if (dev_data->alias_data) { + u16 alias; + struct pci_bus *bus; + + if (dev_data->alias_data->group) + goto use_group; + + /* + * If the alias device exists, it's effectively just a first + * level quirk for finding the DMA source. + */ + alias = amd_iommu_alias_table[dev_data->devid]; + dma_pdev = pci_get_bus_and_slot(alias >> 8, alias & 0xff); + if (dma_pdev) { + dma_pdev = get_isolation_root(dma_pdev); + goto use_pdev; + } + + /* + * If the alias is virtual, try to find a parent device + * and test whether the IOMMU group is actualy rooted above + * the alias. Be careful to also test the parent device if + * we think the alias is the root of the group. + */ + bus = pci_find_bus(0, alias >> 8); + if (!bus) + goto use_group; + + bus = find_hosted_bus(bus); + if (IS_ERR(bus) || !bus->self) + goto use_group; + + dma_pdev = get_isolation_root(pci_dev_get(bus->self)); + if (dma_pdev != bus->self || (dma_pdev->multifunction && + !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS))) + goto use_pdev; + + pci_dev_put(dma_pdev); + goto use_group; + } + + dma_pdev = get_isolation_root(pci_dev_get(to_pci_dev(dev))); +use_pdev: + ret = use_pdev_iommu_group(dma_pdev, dev); + pci_dev_put(dma_pdev); + return ret; +use_group: + return use_dev_data_iommu_group(dev_data->alias_data, dev); +} + +static int iommu_init_device(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct iommu_dev_data *dev_data; + u16 alias; + int ret; + + if (dev->archdata.iommu) + return 0; + + dev_data = find_dev_data(get_device_id(dev)); + if (!dev_data) + return -ENOMEM; + + alias = amd_iommu_alias_table[dev_data->devid]; + if (alias != dev_data->devid) { + struct iommu_dev_data *alias_data; + + alias_data = find_dev_data(alias); + if (alias_data == NULL) { + pr_err("AMD-Vi: Warning: Unhandled device %s\n", + dev_name(dev)); + free_dev_data(dev_data); + return -ENOTSUPP; + } + dev_data->alias_data = alias_data; + } + ret = init_iommu_group(dev); if (ret) return ret; diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index c9aa3d079ff0..e38ab438bb34 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -426,6 +426,7 @@ struct iommu_dev_data { struct iommu_dev_data *alias_data;/* The alias dev_data */ struct protection_domain *domain; /* Domain the device is bound to */ atomic_t bind; /* Domain attach reference count */ + struct iommu_group *group; /* IOMMU group for virtual aliases */ u16 devid; /* PCI Device ID */ bool iommu_v2; /* Device can make use of IOMMUv2 */ bool passthrough; /* Default for device is pt_domain */ diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 0badfa48b32b..c2c07a4a7f21 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1827,10 +1827,17 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, if (!pte) return -ENOMEM; /* It is large page*/ - if (largepage_lvl > 1) + if (largepage_lvl > 1) { pteval |= DMA_PTE_LARGE_PAGE; - else + /* Ensure that old small page tables are removed to make room + for superpage, if they exist. */ + dma_pte_clear_range(domain, iov_pfn, + iov_pfn + lvl_to_nr_pages(largepage_lvl) - 1); + dma_pte_free_pagetable(domain, iov_pfn, + iov_pfn + lvl_to_nr_pages(largepage_lvl) - 1); + } else { pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE; + } } /* We don't need lock here, nobody else @@ -2320,8 +2327,39 @@ static int domain_add_dev_info(struct dmar_domain *domain, return 0; } +static bool device_has_rmrr(struct pci_dev *dev) +{ + struct dmar_rmrr_unit *rmrr; + int i; + + for_each_rmrr_units(rmrr) { + for (i = 0; i < rmrr->devices_cnt; i++) { + /* + * Return TRUE if this RMRR contains the device that + * is passed in. + */ + if (rmrr->devices[i] == dev) + return true; + } + } + return false; +} + static int iommu_should_identity_map(struct pci_dev *pdev, int startup) { + + /* + * We want to prevent any device associated with an RMRR from + * getting placed into the SI Domain. This is done because + * problems exist when devices are moved in and out of domains + * and their respective RMRR info is lost. We exempt USB devices + * from this process due to their usage of RMRRs that are known + * to not be needed after BIOS hand-off to OS. + */ + if (device_has_rmrr(pdev) && + (pdev->class >> 8) != PCI_CLASS_SERIAL_USB) + return 0; + if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev)) return 1; diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index badc17c2bcb4..18108c1405e2 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -16,13 +16,13 @@ #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/ioport.h> -#include <linux/clk.h> #include <linux/platform_device.h> #include <linux/iommu.h> #include <linux/omap-iommu.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/io.h> +#include <linux/pm_runtime.h> #include <asm/cacheflush.h> @@ -143,31 +143,44 @@ EXPORT_SYMBOL_GPL(omap_iommu_arch_version); static int iommu_enable(struct omap_iommu *obj) { int err; + struct platform_device *pdev = to_platform_device(obj->dev); + struct iommu_platform_data *pdata = pdev->dev.platform_data; - if (!obj) + if (!obj || !pdata) return -EINVAL; if (!arch_iommu) return -ENODEV; - clk_enable(obj->clk); + if (pdata->deassert_reset) { + err = pdata->deassert_reset(pdev, pdata->reset_name); + if (err) { + dev_err(obj->dev, "deassert_reset failed: %d\n", err); + return err; + } + } + + pm_runtime_get_sync(obj->dev); err = arch_iommu->enable(obj); - clk_disable(obj->clk); return err; } static void iommu_disable(struct omap_iommu *obj) { - if (!obj) - return; + struct platform_device *pdev = to_platform_device(obj->dev); + struct iommu_platform_data *pdata = pdev->dev.platform_data; - clk_enable(obj->clk); + if (!obj || !pdata) + return; arch_iommu->disable(obj); - clk_disable(obj->clk); + pm_runtime_put_sync(obj->dev); + + if (pdata->assert_reset) + pdata->assert_reset(pdev, pdata->reset_name); } /* @@ -290,7 +303,7 @@ static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e) if (!obj || !obj->nr_tlb_entries || !e) return -EINVAL; - clk_enable(obj->clk); + pm_runtime_get_sync(obj->dev); iotlb_lock_get(obj, &l); if (l.base == obj->nr_tlb_entries) { @@ -320,7 +333,7 @@ static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e) cr = iotlb_alloc_cr(obj, e); if (IS_ERR(cr)) { - clk_disable(obj->clk); + pm_runtime_put_sync(obj->dev); return PTR_ERR(cr); } @@ -334,7 +347,7 @@ static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e) l.vict = l.base; iotlb_lock_set(obj, &l); out: - clk_disable(obj->clk); + pm_runtime_put_sync(obj->dev); return err; } @@ -364,7 +377,7 @@ static void flush_iotlb_page(struct omap_iommu *obj, u32 da) int i; struct cr_regs cr; - clk_enable(obj->clk); + pm_runtime_get_sync(obj->dev); for_each_iotlb_cr(obj, obj->nr_tlb_entries, i, cr) { u32 start; @@ -383,7 +396,7 @@ static void flush_iotlb_page(struct omap_iommu *obj, u32 da) iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY); } } - clk_disable(obj->clk); + pm_runtime_put_sync(obj->dev); if (i == obj->nr_tlb_entries) dev_dbg(obj->dev, "%s: no page for %08x\n", __func__, da); @@ -397,7 +410,7 @@ static void flush_iotlb_all(struct omap_iommu *obj) { struct iotlb_lock l; - clk_enable(obj->clk); + pm_runtime_get_sync(obj->dev); l.base = 0; l.vict = 0; @@ -405,7 +418,7 @@ static void flush_iotlb_all(struct omap_iommu *obj) iommu_write_reg(obj, 1, MMU_GFLUSH); - clk_disable(obj->clk); + pm_runtime_put_sync(obj->dev); } #if defined(CONFIG_OMAP_IOMMU_DEBUG) || defined(CONFIG_OMAP_IOMMU_DEBUG_MODULE) @@ -415,11 +428,11 @@ ssize_t omap_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t bytes) if (!obj || !buf) return -EINVAL; - clk_enable(obj->clk); + pm_runtime_get_sync(obj->dev); bytes = arch_iommu->dump_ctx(obj, buf, bytes); - clk_disable(obj->clk); + pm_runtime_put_sync(obj->dev); return bytes; } @@ -433,7 +446,7 @@ __dump_tlb_entries(struct omap_iommu *obj, struct cr_regs *crs, int num) struct cr_regs tmp; struct cr_regs *p = crs; - clk_enable(obj->clk); + pm_runtime_get_sync(obj->dev); iotlb_lock_get(obj, &saved); for_each_iotlb_cr(obj, num, i, tmp) { @@ -443,7 +456,7 @@ __dump_tlb_entries(struct omap_iommu *obj, struct cr_regs *crs, int num) } iotlb_lock_set(obj, &saved); - clk_disable(obj->clk); + pm_runtime_put_sync(obj->dev); return p - crs; } @@ -807,9 +820,7 @@ static irqreturn_t iommu_fault_handler(int irq, void *data) if (!obj->refcount) return IRQ_NONE; - clk_enable(obj->clk); errs = iommu_report_fault(obj, &da); - clk_disable(obj->clk); if (errs == 0) return IRQ_HANDLED; @@ -931,17 +942,10 @@ static int __devinit omap_iommu_probe(struct platform_device *pdev) struct resource *res; struct iommu_platform_data *pdata = pdev->dev.platform_data; - if (pdev->num_resources != 2) - return -EINVAL; - obj = kzalloc(sizeof(*obj) + MMU_REG_SIZE, GFP_KERNEL); if (!obj) return -ENOMEM; - obj->clk = clk_get(&pdev->dev, pdata->clk_name); - if (IS_ERR(obj->clk)) - goto err_clk; - obj->nr_tlb_entries = pdata->nr_tlb_entries; obj->name = pdata->name; obj->dev = &pdev->dev; @@ -984,6 +988,9 @@ static int __devinit omap_iommu_probe(struct platform_device *pdev) goto err_irq; platform_set_drvdata(pdev, obj); + pm_runtime_irq_safe(obj->dev); + pm_runtime_enable(obj->dev); + dev_info(&pdev->dev, "%s registered\n", obj->name); return 0; @@ -992,8 +999,6 @@ err_irq: err_ioremap: release_mem_region(res->start, resource_size(res)); err_mem: - clk_put(obj->clk); -err_clk: kfree(obj); return err; } @@ -1014,7 +1019,8 @@ static int __devexit omap_iommu_remove(struct platform_device *pdev) release_mem_region(res->start, resource_size(res)); iounmap(obj->regbase); - clk_put(obj->clk); + pm_runtime_disable(obj->dev); + dev_info(&pdev->dev, "%s removed\n", obj->name); kfree(obj); return 0; diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h index 2b5f3c04d167..120084206602 100644 --- a/drivers/iommu/omap-iommu.h +++ b/drivers/iommu/omap-iommu.h @@ -29,7 +29,6 @@ struct iotlb_entry { struct omap_iommu { const char *name; struct module *owner; - struct clk *clk; void __iomem *regbase; struct device *dev; void *isr_priv; @@ -116,8 +115,6 @@ static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev) * MMU Register offsets */ #define MMU_REVISION 0x00 -#define MMU_SYSCONFIG 0x10 -#define MMU_SYSSTATUS 0x14 #define MMU_IRQSTATUS 0x18 #define MMU_IRQENABLE 0x1c #define MMU_WALKING_ST 0x40 diff --git a/drivers/iommu/omap-iommu2.c b/drivers/iommu/omap-iommu2.c index c02020292377..d745094a69dd 100644 --- a/drivers/iommu/omap-iommu2.c +++ b/drivers/iommu/omap-iommu2.c @@ -28,19 +28,6 @@ */ #define IOMMU_ARCH_VERSION 0x00000011 -/* SYSCONF */ -#define MMU_SYS_IDLE_SHIFT 3 -#define MMU_SYS_IDLE_FORCE (0 << MMU_SYS_IDLE_SHIFT) -#define MMU_SYS_IDLE_NONE (1 << MMU_SYS_IDLE_SHIFT) -#define MMU_SYS_IDLE_SMART (2 << MMU_SYS_IDLE_SHIFT) -#define MMU_SYS_IDLE_MASK (3 << MMU_SYS_IDLE_SHIFT) - -#define MMU_SYS_SOFTRESET (1 << 1) -#define MMU_SYS_AUTOIDLE 1 - -/* SYSSTATUS */ -#define MMU_SYS_RESETDONE 1 - /* IRQSTATUS & IRQENABLE */ #define MMU_IRQ_MULTIHITFAULT (1 << 4) #define MMU_IRQ_TABLEWALKFAULT (1 << 3) @@ -97,7 +84,6 @@ static void __iommu_set_twl(struct omap_iommu *obj, bool on) static int omap2_iommu_enable(struct omap_iommu *obj) { u32 l, pa; - unsigned long timeout; if (!obj->iopgd || !IS_ALIGNED((u32)obj->iopgd, SZ_16K)) return -EINVAL; @@ -106,29 +92,10 @@ static int omap2_iommu_enable(struct omap_iommu *obj) if (!IS_ALIGNED(pa, SZ_16K)) return -EINVAL; - iommu_write_reg(obj, MMU_SYS_SOFTRESET, MMU_SYSCONFIG); - - timeout = jiffies + msecs_to_jiffies(20); - do { - l = iommu_read_reg(obj, MMU_SYSSTATUS); - if (l & MMU_SYS_RESETDONE) - break; - } while (!time_after(jiffies, timeout)); - - if (!(l & MMU_SYS_RESETDONE)) { - dev_err(obj->dev, "can't take mmu out of reset\n"); - return -ENODEV; - } - l = iommu_read_reg(obj, MMU_REVISION); dev_info(obj->dev, "%s: version %d.%d\n", obj->name, (l >> 4) & 0xf, l & 0xf); - l = iommu_read_reg(obj, MMU_SYSCONFIG); - l &= ~MMU_SYS_IDLE_MASK; - l |= (MMU_SYS_IDLE_SMART | MMU_SYS_AUTOIDLE); - iommu_write_reg(obj, l, MMU_SYSCONFIG); - iommu_write_reg(obj, pa, MMU_TTB); __iommu_set_twl(obj, true); @@ -142,7 +109,6 @@ static void omap2_iommu_disable(struct omap_iommu *obj) l &= ~MMU_CNTL_MASK; iommu_write_reg(obj, l, MMU_CNTL); - iommu_write_reg(obj, MMU_SYS_IDLE_FORCE, MMU_SYSCONFIG); dev_dbg(obj->dev, "%s is shutting down\n", obj->name); } @@ -271,8 +237,6 @@ omap2_iommu_dump_ctx(struct omap_iommu *obj, char *buf, ssize_t len) char *p = buf; pr_reg(REVISION); - pr_reg(SYSCONFIG); - pr_reg(SYSSTATUS); pr_reg(IRQSTATUS); pr_reg(IRQENABLE); pr_reg(WALKING_ST); diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index c16e8fc8a4bd..4c9db62814ff 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -398,6 +398,7 @@ static int tegra_gart_probe(struct platform_device *pdev) do_gart_setup(gart, NULL); gart_handle = gart; + bus_set_iommu(&platform_bus_type, &gart_iommu_ops); return 0; fail: @@ -450,7 +451,6 @@ static struct platform_driver tegra_gart_driver = { static int __devinit tegra_gart_init(void) { - bus_set_iommu(&platform_bus_type, &gart_iommu_ops); return platform_driver_register(&tegra_gart_driver); } diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 4252d743963d..25c1210c0832 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -694,10 +694,8 @@ static void __smmu_iommu_unmap(struct smmu_as *as, dma_addr_t iova) *pte = _PTE_VACANT(iova); FLUSH_CPU_DCACHE(pte, page, sizeof(*pte)); flush_ptc_and_tlb(as->smmu, as, iova, pte, page, 0); - if (!--(*count)) { + if (!--(*count)) free_ptbl(as, iova); - smmu_flush_regs(as->smmu, 0); - } } static void __smmu_iommu_map_pfn(struct smmu_as *as, dma_addr_t iova, @@ -1232,6 +1230,7 @@ static int tegra_smmu_probe(struct platform_device *pdev) smmu_debugfs_create(smmu); smmu_handle = smmu; + bus_set_iommu(&platform_bus_type, &smmu_iommu_ops); return 0; } @@ -1276,7 +1275,6 @@ static struct platform_driver tegra_smmu_driver = { static int __devinit tegra_smmu_init(void) { - bus_set_iommu(&platform_bus_type, &smmu_iommu_ops); return platform_driver_register(&tegra_smmu_driver); } diff --git a/fs/Kconfig b/fs/Kconfig index eaff24a19502..cfe512fd1caf 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -220,6 +220,7 @@ 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 1d7af79288a0..9d53192236fc 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -123,6 +123,7 @@ 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-y += exofs/ # Multiple modules obj-$(CONFIG_CEPH_FS) += ceph/ obj-$(CONFIG_PSTORE) += pstore/ diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index c7b67cf24bba..eea5da7a2b9a 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1138,13 +1138,13 @@ __tree_mod_log_rewind(struct extent_buffer *eb, u64 time_seq, switch (tm->op) { case MOD_LOG_KEY_REMOVE_WHILE_FREEING: BUG_ON(tm->slot < n); - case MOD_LOG_KEY_REMOVE: - n++; case MOD_LOG_KEY_REMOVE_WHILE_MOVING: + case MOD_LOG_KEY_REMOVE: btrfs_set_node_key(eb, &tm->key, tm->slot); btrfs_set_node_blockptr(eb, tm->slot, tm->blockptr); btrfs_set_node_ptr_generation(eb, tm->slot, tm->generation); + n++; break; case MOD_LOG_KEY_REPLACE: BUG_ON(tm->slot >= n); @@ -4611,12 +4611,6 @@ static void del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, u32 nritems; int ret; - if (level) { - ret = tree_mod_log_insert_key(root->fs_info, parent, slot, - MOD_LOG_KEY_REMOVE); - BUG_ON(ret < 0); - } - nritems = btrfs_header_nritems(parent); if (slot != nritems - 1) { if (level) @@ -4627,6 +4621,10 @@ static void del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, btrfs_node_key_ptr_offset(slot + 1), sizeof(struct btrfs_key_ptr) * (nritems - slot - 1)); + } else if (level) { + ret = tree_mod_log_insert_key(root->fs_info, parent, slot, + MOD_LOG_KEY_REMOVE); + BUG_ON(ret < 0); } nritems--; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 6690269f5dde..064d1a68d2c1 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -267,6 +267,14 @@ static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg) kfree(req->r_pages); } +static void ceph_unlock_page_vector(struct page **pages, int num_pages) +{ + int i; + + for (i = 0; i < num_pages; i++) + unlock_page(pages[i]); +} + /* * start an async read(ahead) operation. return nr_pages we submitted * a read for on success, or negative error code. @@ -347,6 +355,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) return nr_pages; out_pages: + ceph_unlock_page_vector(pages, nr_pages); ceph_release_page_vector(pages, nr_pages); out: ceph_osdc_put_request(req); @@ -1078,23 +1087,51 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { struct inode *inode = file->f_dentry->d_inode; + struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_file_info *fi = file->private_data; struct page *page; pgoff_t index = pos >> PAGE_CACHE_SHIFT; - int r; + int r, want, got = 0; + + if (fi->fmode & CEPH_FILE_MODE_LAZY) + want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO; + else + want = CEPH_CAP_FILE_BUFFER; + + dout("write_begin %p %llx.%llx %llu~%u getting caps. i_size %llu\n", + inode, ceph_vinop(inode), pos, len, inode->i_size); + r = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, pos+len); + if (r < 0) + return r; + dout("write_begin %p %llx.%llx %llu~%u got cap refs on %s\n", + inode, ceph_vinop(inode), pos, len, ceph_cap_string(got)); + if (!(got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO))) { + ceph_put_cap_refs(ci, got); + return -EAGAIN; + } do { /* get a page */ page = grab_cache_page_write_begin(mapping, index, 0); - if (!page) - return -ENOMEM; - *pagep = page; + if (!page) { + r = -ENOMEM; + break; + } dout("write_begin file %p inode %p page %p %d~%d\n", file, inode, page, (int)pos, (int)len); r = ceph_update_writeable_page(file, pos, len, page); + if (r) + page_cache_release(page); } while (r == -EAGAIN); + if (r) { + ceph_put_cap_refs(ci, got); + } else { + *pagep = page; + *(int *)fsdata = got; + } return r; } @@ -1108,10 +1145,12 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { struct inode *inode = file->f_dentry->d_inode; + struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_mds_client *mdsc = fsc->mdsc; unsigned from = pos & (PAGE_CACHE_SIZE - 1); int check_cap = 0; + int got = (unsigned long)fsdata; dout("write_end file %p inode %p page %p %d~%d (%d)\n", file, inode, page, (int)pos, (int)copied, (int)len); @@ -1134,6 +1173,19 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, up_read(&mdsc->snap_rwsem); page_cache_release(page); + if (copied > 0) { + int dirty; + spin_lock(&ci->i_ceph_lock); + dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR); + spin_unlock(&ci->i_ceph_lock); + if (dirty) + __mark_inode_dirty(inode, dirty); + } + + dout("write_end %p %llx.%llx %llu~%u dropping cap refs on %s\n", + inode, ceph_vinop(inode), pos, len, ceph_cap_string(got)); + ceph_put_cap_refs(ci, got); + if (check_cap) ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 3251e9cc6401..a1d9bb30c1bf 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -236,8 +236,10 @@ static struct ceph_cap *get_cap(struct ceph_mds_client *mdsc, if (!ctx) { cap = kmem_cache_alloc(ceph_cap_cachep, GFP_NOFS); if (cap) { + spin_lock(&mdsc->caps_list_lock); mdsc->caps_use_count++; mdsc->caps_total_count++; + spin_unlock(&mdsc->caps_list_lock); } return cap; } @@ -1349,11 +1351,15 @@ int __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask) if (!ci->i_head_snapc) ci->i_head_snapc = ceph_get_snap_context( ci->i_snap_realm->cached_context); - dout(" inode %p now dirty snapc %p\n", &ci->vfs_inode, - ci->i_head_snapc); + dout(" inode %p now dirty snapc %p auth cap %p\n", + &ci->vfs_inode, ci->i_head_snapc, ci->i_auth_cap); BUG_ON(!list_empty(&ci->i_dirty_item)); spin_lock(&mdsc->cap_dirty_lock); - list_add(&ci->i_dirty_item, &mdsc->cap_dirty); + if (ci->i_auth_cap) + list_add(&ci->i_dirty_item, &mdsc->cap_dirty); + else + list_add(&ci->i_dirty_item, + &mdsc->cap_dirty_migrating); spin_unlock(&mdsc->cap_dirty_lock); if (ci->i_flushing_caps == 0) { ihold(inode); @@ -2388,7 +2394,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, &atime); /* max size increase? */ - if (max_size != ci->i_max_size) { + if (ci->i_auth_cap == cap && max_size != ci->i_max_size) { dout("max_size %lld -> %llu\n", ci->i_max_size, max_size); ci->i_max_size = max_size; if (max_size >= ci->i_wanted_max_size) { @@ -2745,6 +2751,7 @@ static void handle_cap_import(struct ceph_mds_client *mdsc, /* make sure we re-request max_size, if necessary */ spin_lock(&ci->i_ceph_lock); + ci->i_wanted_max_size = 0; /* reset */ ci->i_requested_max_size = 0; spin_unlock(&ci->i_ceph_lock); } @@ -2840,8 +2847,6 @@ void ceph_handle_caps(struct ceph_mds_session *session, case CEPH_CAP_OP_IMPORT: handle_cap_import(mdsc, inode, h, session, snaptrace, snaptrace_len); - ceph_check_caps(ceph_inode(inode), 0, session); - goto done_unlocked; } /* the rest require a cap */ @@ -2858,6 +2863,7 @@ void ceph_handle_caps(struct ceph_mds_session *session, switch (op) { case CEPH_CAP_OP_REVOKE: case CEPH_CAP_OP_GRANT: + case CEPH_CAP_OP_IMPORT: handle_cap_grant(inode, h, session, cap, msg->middle); goto done_unlocked; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d4dfdcf76d7f..e51558fca3a3 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -712,63 +712,53 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov, struct ceph_osd_client *osdc = &ceph_sb_to_client(inode->i_sb)->client->osdc; loff_t endoff = pos + iov->iov_len; - int want, got = 0; - int ret, err; + int got = 0; + int ret, err, written; if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; retry_snap: + written = 0; if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) return -ENOSPC; __ceph_do_pending_vmtruncate(inode); - dout("aio_write %p %llx.%llx %llu~%u getting caps. i_size %llu\n", - inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len, - inode->i_size); - if (fi->fmode & CEPH_FILE_MODE_LAZY) - want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO; - else - want = CEPH_CAP_FILE_BUFFER; - ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, endoff); - if (ret < 0) - goto out_put; - - dout("aio_write %p %llx.%llx %llu~%u got cap refs on %s\n", - inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len, - ceph_cap_string(got)); - - if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 || - (iocb->ki_filp->f_flags & O_DIRECT) || - (inode->i_sb->s_flags & MS_SYNCHRONOUS) || - (fi->flags & CEPH_F_SYNC)) { - ret = ceph_sync_write(file, iov->iov_base, iov->iov_len, - &iocb->ki_pos); - } else { - /* - * buffered write; drop Fw early to avoid slow - * revocation if we get stuck on balance_dirty_pages - */ - int dirty; - - spin_lock(&ci->i_ceph_lock); - dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR); - spin_unlock(&ci->i_ceph_lock); - ceph_put_cap_refs(ci, got); + /* + * try to do a buffered write. if we don't have sufficient + * caps, we'll get -EAGAIN from generic_file_aio_write, or a + * short write if we only get caps for some pages. + */ + if (!(iocb->ki_filp->f_flags & O_DIRECT) && + !(inode->i_sb->s_flags & MS_SYNCHRONOUS) && + !(fi->flags & CEPH_F_SYNC)) { ret = generic_file_aio_write(iocb, iov, nr_segs, pos); + if (ret >= 0) + written = ret; + if ((ret >= 0 || ret == -EIOCBQUEUED) && ((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host) || ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) { - err = vfs_fsync_range(file, pos, pos + ret - 1, 1); + err = vfs_fsync_range(file, pos, pos + written - 1, 1); if (err < 0) ret = err; } + if ((ret < 0 && ret != -EAGAIN) || pos + written >= endoff) + goto out; + } - if (dirty) - __mark_inode_dirty(inode, dirty); + dout("aio_write %p %llx.%llx %llu~%u getting caps. i_size %llu\n", + inode, ceph_vinop(inode), pos + written, + (unsigned)iov->iov_len - written, inode->i_size); + ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, 0, &got, endoff); + if (ret < 0) goto out; - } + dout("aio_write %p %llx.%llx %llu~%u got cap refs on %s\n", + inode, ceph_vinop(inode), pos + written, + (unsigned)iov->iov_len - written, ceph_cap_string(got)); + ret = ceph_sync_write(file, iov->iov_base + written, + iov->iov_len - written, &iocb->ki_pos); if (ret >= 0) { int dirty; spin_lock(&ci->i_ceph_lock); @@ -777,13 +767,10 @@ retry_snap: if (dirty) __mark_inode_dirty(inode, dirty); } - -out_put: dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n", - inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len, - ceph_cap_string(got)); + inode, ceph_vinop(inode), pos + written, + (unsigned)iov->iov_len - written, ceph_cap_string(got)); ceph_put_cap_refs(ci, got); - out: if (ret == -EOLDSNAPC) { dout("aio_write %p %llx.%llx %llu~%u got EOLDSNAPC, retrying\n", diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index ba95eea201bf..2971eaa65cdc 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1466,7 +1466,7 @@ void __ceph_do_pending_vmtruncate(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); u64 to; - int wrbuffer_refs, wake = 0; + int wrbuffer_refs, finish = 0; retry: spin_lock(&ci->i_ceph_lock); @@ -1498,15 +1498,18 @@ retry: truncate_inode_pages(inode->i_mapping, to); spin_lock(&ci->i_ceph_lock); - ci->i_truncate_pending--; - if (ci->i_truncate_pending == 0) - wake = 1; + if (to == ci->i_truncate_size) { + ci->i_truncate_pending = 0; + finish = 1; + } spin_unlock(&ci->i_ceph_lock); + if (!finish) + goto retry; if (wrbuffer_refs == 0) ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL); - if (wake) - wake_up_all(&ci->i_cap_wq); + + wake_up_all(&ci->i_cap_wq); } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 1bcf712655d9..9165eb8309eb 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1590,7 +1590,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, } else if (rpath || rino) { *ino = rino; *ppath = rpath; - *pathlen = strlen(rpath); + *pathlen = rpath ? strlen(rpath) : 0; dout(" path %.*s\n", *pathlen, rpath); } @@ -1876,9 +1876,14 @@ finish: static void __wake_requests(struct ceph_mds_client *mdsc, struct list_head *head) { - struct ceph_mds_request *req, *nreq; + struct ceph_mds_request *req; + LIST_HEAD(tmp_list); + + list_splice_init(head, &tmp_list); - list_for_each_entry_safe(req, nreq, head, r_wait) { + while (!list_empty(&tmp_list)) { + req = list_entry(tmp_list.next, + struct ceph_mds_request, r_wait); list_del_init(&req->r_wait); __do_request(mdsc, req); } diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 2eb43f211325..e86aa9948124 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -403,8 +403,6 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_printf(m, ",mount_timeout=%d", opt->mount_timeout); if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT) seq_printf(m, ",osd_idle_ttl=%d", opt->osd_idle_ttl); - if (opt->osd_timeout != CEPH_OSD_TIMEOUT_DEFAULT) - seq_printf(m, ",osdtimeout=%d", opt->osd_timeout); if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT) seq_printf(m, ",osdkeepalivetimeout=%d", opt->osd_keepalive_timeout); @@ -849,7 +847,7 @@ static int ceph_register_bdi(struct super_block *sb, fsc->backing_dev_info.ra_pages = default_backing_dev_info.ra_pages; - err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%d", + err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld", atomic_long_inc_return(&bdi_seq)); if (!err) sb->s_bdi = &fsc->backing_dev_info; diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 606bb074c501..5df4bb4aab14 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -322,10 +322,10 @@ static int export_encode_fh(struct inode *inode, struct fid *fid, if (parent && (len < 4)) { *max_len = 4; - return 255; + return FILEID_INVALID; } else if (len < 2) { *max_len = 2; - return 255; + return FILEID_INVALID; } len = 2; diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig new file mode 100644 index 000000000000..fd27e7e6326e --- /dev/null +++ b/fs/f2fs/Kconfig @@ -0,0 +1,53 @@ +config F2FS_FS + tristate "F2FS filesystem support (EXPERIMENTAL)" + depends on BLOCK + help + F2FS is based on Log-structured File System (LFS), which supports + versatile "flash-friendly" features. The design has been focused on + addressing the fundamental issues in LFS, which are snowball effect + of wandering tree and high cleaning overhead. + + Since flash-based storages show different characteristics according to + the internal geometry or flash memory management schemes aka FTL, F2FS + and tools support various parameters not only for configuring on-disk + layout, but also for selecting allocation and cleaning algorithms. + + If unsure, say N. + +config F2FS_STAT_FS + bool "F2FS Status Information" + depends on F2FS_FS && DEBUG_FS + default y + help + /sys/kernel/debug/f2fs/ contains information about all the partitions + mounted as f2fs. Each file shows the whole f2fs information. + + /sys/kernel/debug/f2fs/status includes: + - major file system information managed by f2fs currently + - average SIT information about whole segments + - current memory footprint consumed by f2fs. + +config F2FS_FS_XATTR + bool "F2FS extended attributes" + depends on F2FS_FS + default y + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page, or visit + <http://acl.bestbits.at/> for details). + + If unsure, say N. + +config F2FS_FS_POSIX_ACL + bool "F2FS Access Control Lists" + depends on F2FS_FS_XATTR + select FS_POSIX_ACL + default y + help + Posix Access Control Lists (ACLs) support permissions for users and + gourps beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the POSIX ACLs for + Linux website <http://acl.bestbits.at/>. + + If you don't know what Access Control Lists are, say N diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile new file mode 100644 index 000000000000..27a0820340b9 --- /dev/null +++ b/fs/f2fs/Makefile @@ -0,0 +1,7 @@ +obj-$(CONFIG_F2FS_FS) += f2fs.o + +f2fs-y := dir.o file.o inode.o namei.o hash.o super.o +f2fs-y += checkpoint.o gc.o data.o node.o segment.o recovery.o +f2fs-$(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 000000000000..fed74d193ffb --- /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, <agruen@suse.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/f2fs_fs.h> +#include "f2fs.h" +#include "xattr.h" +#include "acl.h" + +#define get_inode_mode(i) ((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \ + (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) + +static inline size_t f2fs_acl_size(int count) +{ + if (count <= 4) { + return sizeof(struct f2fs_acl_header) + + count * sizeof(struct f2fs_acl_entry_short); + } else { + return sizeof(struct f2fs_acl_header) + + 4 * sizeof(struct f2fs_acl_entry_short) + + (count - 4) * sizeof(struct f2fs_acl_entry); + } +} + +static inline int f2fs_acl_count(size_t size) +{ + ssize_t s; + size -= sizeof(struct f2fs_acl_header); + s = size - 4 * sizeof(struct f2fs_acl_entry_short); + if (s < 0) { + if (size % sizeof(struct f2fs_acl_entry_short)) + return -1; + return size / sizeof(struct f2fs_acl_entry_short); + } else { + if (s % sizeof(struct f2fs_acl_entry)) + return -1; + return s / sizeof(struct f2fs_acl_entry) + 4; + } +} + +static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) +{ + int i, count; + struct posix_acl *acl; + struct f2fs_acl_header *hdr = (struct f2fs_acl_header *)value; + struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1); + const char *end = value + size; + + if (hdr->a_version != cpu_to_le32(F2FS_ACL_VERSION)) + return ERR_PTR(-EINVAL); + + count = f2fs_acl_count(size); + if (count < 0) + return ERR_PTR(-EINVAL); + if (count == 0) + return NULL; + + acl = posix_acl_alloc(count, GFP_KERNEL); + if (!acl) + return ERR_PTR(-ENOMEM); + + for (i = 0; i < count; i++) { + + if ((char *)entry > end) + goto fail; + + acl->a_entries[i].e_tag = le16_to_cpu(entry->e_tag); + acl->a_entries[i].e_perm = le16_to_cpu(entry->e_perm); + + switch (acl->a_entries[i].e_tag) { + case ACL_USER_OBJ: + case ACL_GROUP_OBJ: + case ACL_MASK: + case ACL_OTHER: + acl->a_entries[i].e_id = ACL_UNDEFINED_ID; + 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) { + if (retval == -ENODATA) + acl = NULL; + else + acl = ERR_PTR(retval); + } else { + acl = f2fs_acl_from_disk(value, retval); + } + kfree(value); + if (!IS_ERR(acl)) + set_cached_acl(inode, type, acl); + + return acl; +} + +static int f2fs_set_acl(struct inode *inode, int type, struct posix_acl *acl) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct f2fs_inode_info *fi = F2FS_I(inode); + int name_index; + void *value = NULL; + size_t size = 0; + int error; + + if (!test_opt(sbi, POSIX_ACL)) + return 0; + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + + switch (type) { + case ACL_TYPE_ACCESS: + name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; + if (acl) { + error = posix_acl_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); + + kfree(value); + if (!error) + set_cached_acl(inode, type, acl); + + cond_clear_inode_flag(fi, FI_ACL_MODE); + return error; +} + +int f2fs_init_acl(struct inode *inode, struct inode *dir) +{ + struct posix_acl *acl = NULL; + struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); + int error = 0; + + if (!S_ISLNK(inode->i_mode)) { + if (test_opt(sbi, POSIX_ACL)) { + acl = f2fs_get_acl(dir, ACL_TYPE_DEFAULT); + if (IS_ERR(acl)) + return PTR_ERR(acl); + } + if (!acl) + inode->i_mode &= ~current_umask(); + } + + if (test_opt(sbi, POSIX_ACL) && acl) { + + if (S_ISDIR(inode->i_mode)) { + error = f2fs_set_acl(inode, ACL_TYPE_DEFAULT, acl); + if (error) + goto cleanup; + } + error = posix_acl_create(&acl, GFP_KERNEL, &inode->i_mode); + if (error < 0) + return error; + if (error > 0) + error = f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl); + } +cleanup: + posix_acl_release(acl); + return error; +} + +int f2fs_acl_chmod(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct posix_acl *acl; + int error; + mode_t mode = get_inode_mode(inode); + + if (!test_opt(sbi, POSIX_ACL)) + return 0; + if (S_ISLNK(mode)) + return -EOPNOTSUPP; + + acl = f2fs_get_acl(inode, ACL_TYPE_ACCESS); + if (IS_ERR(acl) || !acl) + return PTR_ERR(acl); + + error = posix_acl_chmod(&acl, GFP_KERNEL, mode); + if (error) + return error; + error = f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl); + posix_acl_release(acl); + return error; +} + +static size_t f2fs_xattr_list_acl(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); + const char *xname = POSIX_ACL_XATTR_DEFAULT; + size_t size; + + if (!test_opt(sbi, POSIX_ACL)) + return 0; + + if (type == ACL_TYPE_ACCESS) + xname = POSIX_ACL_XATTR_ACCESS; + + size = strlen(xname) + 1; + if (list && size <= list_size) + memcpy(list, xname, size); + return size; +} + +static int f2fs_xattr_get_acl(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); + struct posix_acl *acl; + int error; + + if (strcmp(name, "") != 0) + return -EINVAL; + if (!test_opt(sbi, POSIX_ACL)) + return -EOPNOTSUPP; + + acl = f2fs_get_acl(dentry->d_inode, type); + if (IS_ERR(acl)) + return PTR_ERR(acl); + if (!acl) + return -ENODATA; + error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); + posix_acl_release(acl); + + return error; +} + +static int f2fs_xattr_set_acl(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); + struct inode *inode = dentry->d_inode; + struct posix_acl *acl = NULL; + int error; + + if (strcmp(name, "") != 0) + return -EINVAL; + if (!test_opt(sbi, POSIX_ACL)) + return -EOPNOTSUPP; + if (!inode_owner_or_capable(inode)) + return -EPERM; + + if (value) { + acl = posix_acl_from_xattr(&init_user_ns, value, size); + if (IS_ERR(acl)) + return PTR_ERR(acl); + if (acl) { + error = posix_acl_valid(acl); + if (error) + goto release_and_out; + } + } else { + acl = NULL; + } + + error = f2fs_set_acl(inode, type, acl); + +release_and_out: + posix_acl_release(acl); + return error; +} + +const struct xattr_handler f2fs_xattr_acl_default_handler = { + .prefix = POSIX_ACL_XATTR_DEFAULT, + .flags = ACL_TYPE_DEFAULT, + .list = f2fs_xattr_list_acl, + .get = f2fs_xattr_get_acl, + .set = f2fs_xattr_set_acl, +}; + +const struct xattr_handler f2fs_xattr_acl_access_handler = { + .prefix = POSIX_ACL_XATTR_ACCESS, + .flags = ACL_TYPE_ACCESS, + .list = f2fs_xattr_list_acl, + .get = f2fs_xattr_get_acl, + .set = f2fs_xattr_set_acl, +}; diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h new file mode 100644 index 000000000000..80f430674417 --- /dev/null +++ b/fs/f2fs/acl.h @@ -0,0 +1,57 @@ +/* + * fs/f2fs/acl.h + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * Portions of this code from linux/fs/ext2/acl.h + * + * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __F2FS_ACL_H__ +#define __F2FS_ACL_H__ + +#include <linux/posix_acl_xattr.h> + +#define F2FS_ACL_VERSION 0x0001 + +struct f2fs_acl_entry { + __le16 e_tag; + __le16 e_perm; + __le32 e_id; +}; + +struct f2fs_acl_entry_short { + __le16 e_tag; + __le16 e_perm; +}; + +struct f2fs_acl_header { + __le32 a_version; +}; + +#ifdef CONFIG_F2FS_FS_POSIX_ACL + +extern struct posix_acl *f2fs_get_acl(struct inode *inode, int type); +extern int f2fs_acl_chmod(struct inode *inode); +extern int f2fs_init_acl(struct inode *inode, struct inode *dir); +#else +#define f2fs_check_acl NULL +#define f2fs_get_acl NULL +#define f2fs_set_acl NULL + +static inline int f2fs_acl_chmod(struct inode *inode) +{ + return 0; +} + +static inline int f2fs_init_acl(struct inode *inode, struct inode *dir) +{ + return 0; +} +#endif +#endif /* __F2FS_ACL_H__ */ diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c new file mode 100644 index 000000000000..6ef36c37e2be --- /dev/null +++ b/fs/f2fs/checkpoint.c @@ -0,0 +1,794 @@ +/* + * fs/f2fs/checkpoint.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/fs.h> +#include <linux/bio.h> +#include <linux/mpage.h> +#include <linux/writeback.h> +#include <linux/blkdev.h> +#include <linux/f2fs_fs.h> +#include <linux/pagevec.h> +#include <linux/swap.h> + +#include "f2fs.h" +#include "node.h" +#include "segment.h" + +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 (f2fs_readpage(sbi, page, index, READ_SYNC)) { + f2fs_put_page(page, 1); + goto repeat; + } + mark_page_accessed(page); + + /* We do not allow returning an errorneous 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); + int err; + + wait_on_page_writeback(page); + + err = write_meta_page(sbi, page, wbc); + if (err) { + wbc->pages_skipped++; + set_page_dirty(page); + } + + dec_page_count(sbi, F2FS_DIRTY_META); + + /* In this case, we should not unlock this page */ + if (err != AOP_WRITEPAGE_ACTIVATE) + unlock_page(page); + return err; +} + +static int f2fs_write_meta_pages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb); + struct block_device *bdev = sbi->sb->s_bdev; + long written; + + if (wbc->for_kupdate) + return 0; + + if (get_pages(sbi, F2FS_DIRTY_META) == 0) + return 0; + + /* if mounting is failed, skip writing node pages */ + mutex_lock(&sbi->cp_mutex); + written = sync_meta_pages(sbi, META, bio_get_nr_vecs(bdev)); + mutex_unlock(&sbi->cp_mutex); + wbc->nr_to_write -= written; + return 0; +} + +long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, + long nr_to_write) +{ + struct address_space *mapping = sbi->meta_inode->i_mapping; + pgoff_t index = 0, end = LONG_MAX; + struct pagevec pvec; + long nwritten = 0; + struct writeback_control wbc = { + .for_reclaim = 0, + }; + + pagevec_init(&pvec, 0); + + while (index <= end) { + int i, nr_pages; + nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_DIRTY, + min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); + if (nr_pages == 0) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + lock_page(page); + BUG_ON(page->mapping != mapping); + BUG_ON(!PageDirty(page)); + clear_page_dirty_for_io(page); + f2fs_write_meta_page(page, &wbc); + if (nwritten++ >= nr_to_write) + break; + } + pagevec_release(&pvec); + cond_resched(); + } + + if (nwritten) + f2fs_submit_bio(sbi, type, nr_to_write == LONG_MAX); + + return nwritten; +} + +static int f2fs_set_meta_page_dirty(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb); + + SetPageUptodate(page); + if (!PageDirty(page)) { + __set_page_dirty_nobuffers(page); + inc_page_count(sbi, F2FS_DIRTY_META); + F2FS_SET_SB_DIRT(sbi); + return 1; + } + return 0; +} + +const struct address_space_operations f2fs_meta_aops = { + .writepage = f2fs_write_meta_page, + .writepages = f2fs_write_meta_pages, + .set_page_dirty = f2fs_set_meta_page_dirty, +}; + +int check_orphan_space(struct f2fs_sb_info *sbi) +{ + unsigned int max_orphans; + int err = 0; + + /* + * considering 512 blocks in a segment 5 blocks are needed for cp + * and log segment summaries. Remaining blocks are used to keep + * orphan entries with the limitation one reserved segment + * for cp pack we can have max 1020*507 orphan entries + */ + max_orphans = (sbi->blocks_per_seg - 5) * F2FS_ORPHANS_PER_BLOCK; + mutex_lock(&sbi->orphan_inode_mutex); + if (sbi->n_orphans >= max_orphans) + err = -ENOSPC; + mutex_unlock(&sbi->orphan_inode_mutex); + return err; +} + +void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct list_head *head, *this; + struct orphan_inode_entry *new = NULL, *orphan = NULL; + + mutex_lock(&sbi->orphan_inode_mutex); + head = &sbi->orphan_inode_list; + list_for_each(this, head) { + orphan = list_entry(this, struct orphan_inode_entry, list); + if (orphan->ino == ino) + goto out; + if (orphan->ino > ino) + break; + orphan = NULL; + } +retry: + new = kmem_cache_alloc(orphan_entry_slab, GFP_ATOMIC); + if (!new) { + cond_resched(); + goto retry; + } + new->ino = ino; + INIT_LIST_HEAD(&new->list); + + /* add new_oentry into list which is sorted by inode number */ + if (orphan) { + struct orphan_inode_entry *prev; + + /* get previous entry */ + prev = list_entry(orphan->list.prev, typeof(*prev), list); + if (&prev->list != head) + /* insert new orphan inode entry */ + list_add(&new->list, &prev->list); + else + list_add(&new->list, head); + } else { + list_add_tail(&new->list, head); + } + sbi->n_orphans++; +out: + mutex_unlock(&sbi->orphan_inode_mutex); +} + +void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct list_head *this, *next, *head; + struct orphan_inode_entry *orphan; + + mutex_lock(&sbi->orphan_inode_mutex); + head = &sbi->orphan_inode_list; + list_for_each_safe(this, next, head) { + orphan = list_entry(this, struct orphan_inode_entry, list); + if (orphan->ino == ino) { + list_del(&orphan->list); + kmem_cache_free(orphan_entry_slab, orphan); + sbi->n_orphans--; + break; + } + } + mutex_unlock(&sbi->orphan_inode_mutex); +} + +static void recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +{ + struct inode *inode = f2fs_iget(sbi->sb, ino); + BUG_ON(IS_ERR(inode)); + clear_nlink(inode); + + /* truncate all the data during iput */ + iput(inode); +} + +int recover_orphan_inodes(struct f2fs_sb_info *sbi) +{ + block_t start_blk, orphan_blkaddr, i, j; + + if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG)) + return 0; + + sbi->por_doing = 1; + start_blk = __start_cp_addr(sbi) + 1; + orphan_blkaddr = __start_sum_addr(sbi) - 1; + + for (i = 0; i < orphan_blkaddr; i++) { + struct page *page = get_meta_page(sbi, start_blk + i); + struct f2fs_orphan_block *orphan_blk; + + orphan_blk = (struct f2fs_orphan_block *)page_address(page); + for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) { + nid_t ino = le32_to_cpu(orphan_blk->ino[j]); + recover_orphan_inode(sbi, ino); + } + f2fs_put_page(page, 1); + } + /* clear Orphan Flag */ + clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG); + sbi->por_doing = 0; + return 0; +} + +static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) +{ + struct list_head *head, *this, *next; + struct f2fs_orphan_block *orphan_blk = NULL; + struct page *page = NULL; + unsigned int nentries = 0; + unsigned short index = 1; + unsigned short orphan_blocks; + + orphan_blocks = (unsigned short)((sbi->n_orphans + + (F2FS_ORPHANS_PER_BLOCK - 1)) / F2FS_ORPHANS_PER_BLOCK); + + mutex_lock(&sbi->orphan_inode_mutex); + head = &sbi->orphan_inode_list; + + /* loop for each orphan inode entry and write them in Jornal block */ + list_for_each_safe(this, next, head) { + struct orphan_inode_entry *orphan; + + orphan = list_entry(this, struct orphan_inode_entry, list); + + if (nentries == F2FS_ORPHANS_PER_BLOCK) { + /* + * an orphan block is full of 1020 entries, + * then we need to flush current orphan blocks + * and bring another one in memory + */ + orphan_blk->blk_addr = cpu_to_le16(index); + orphan_blk->blk_count = cpu_to_le16(orphan_blocks); + orphan_blk->entry_count = cpu_to_le32(nentries); + set_page_dirty(page); + f2fs_put_page(page, 1); + index++; + start_blk++; + nentries = 0; + page = NULL; + } + if (page) + goto page_exist; + + page = grab_meta_page(sbi, start_blk); + orphan_blk = (struct f2fs_orphan_block *)page_address(page); + memset(orphan_blk, 0, sizeof(*orphan_blk)); +page_exist: + orphan_blk->ino[nentries++] = cpu_to_le32(orphan->ino); + } + if (!page) + goto end; + + orphan_blk->blk_addr = cpu_to_le16(index); + orphan_blk->blk_count = cpu_to_le16(orphan_blocks); + orphan_blk->entry_count = cpu_to_le32(nentries); + set_page_dirty(page); + f2fs_put_page(page, 1); +end: + mutex_unlock(&sbi->orphan_inode_mutex); +} + +static struct page *validate_checkpoint(struct f2fs_sb_info *sbi, + block_t cp_addr, unsigned long long *version) +{ + struct page *cp_page_1, *cp_page_2 = NULL; + unsigned long blk_size = sbi->blocksize; + struct f2fs_checkpoint *cp_block; + unsigned long long cur_version = 0, pre_version = 0; + unsigned int crc = 0; + size_t crc_offset; + + /* Read the 1st cp block in this CP pack */ + cp_page_1 = get_meta_page(sbi, cp_addr); + + /* get the version number */ + cp_block = (struct f2fs_checkpoint *)page_address(cp_page_1); + crc_offset = le32_to_cpu(cp_block->checksum_offset); + if (crc_offset >= blk_size) + goto invalid_cp1; + + crc = *(unsigned int *)((unsigned char *)cp_block + crc_offset); + if (!f2fs_crc_valid(crc, cp_block, crc_offset)) + goto invalid_cp1; + + pre_version = le64_to_cpu(cp_block->checkpoint_ver); + + /* Read the 2nd cp block in this CP pack */ + cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1; + cp_page_2 = get_meta_page(sbi, cp_addr); + + cp_block = (struct f2fs_checkpoint *)page_address(cp_page_2); + crc_offset = le32_to_cpu(cp_block->checksum_offset); + if (crc_offset >= blk_size) + goto invalid_cp2; + + crc = *(unsigned int *)((unsigned char *)cp_block + crc_offset); + if (!f2fs_crc_valid(crc, cp_block, crc_offset)) + goto invalid_cp2; + + cur_version = le64_to_cpu(cp_block->checkpoint_ver); + + if (cur_version == pre_version) { + *version = cur_version; + f2fs_put_page(cp_page_2, 1); + return cp_page_1; + } +invalid_cp2: + f2fs_put_page(cp_page_2, 1); +invalid_cp1: + f2fs_put_page(cp_page_1, 1); + return NULL; +} + +int get_valid_checkpoint(struct f2fs_sb_info *sbi) +{ + struct f2fs_checkpoint *cp_block; + struct f2fs_super_block *fsb = sbi->raw_super; + struct page *cp1, *cp2, *cur_page; + unsigned long blk_size = sbi->blocksize; + unsigned long long cp1_version = 0, cp2_version = 0; + unsigned long long cp_start_blk_no; + + sbi->ckpt = kzalloc(blk_size, GFP_KERNEL); + if (!sbi->ckpt) + return -ENOMEM; + /* + * Finding out valid cp block involves read both + * sets( cp pack1 and cp pack 2) + */ + cp_start_blk_no = le32_to_cpu(fsb->cp_blkaddr); + cp1 = validate_checkpoint(sbi, cp_start_blk_no, &cp1_version); + + /* The second checkpoint pack should start at the next segment */ + cp_start_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg); + cp2 = validate_checkpoint(sbi, cp_start_blk_no, &cp2_version); + + if (cp1 && cp2) { + if (ver_after(cp2_version, cp1_version)) + cur_page = cp2; + else + cur_page = cp1; + } else if (cp1) { + cur_page = cp1; + } else if (cp2) { + cur_page = cp2; + } else { + goto fail_no_cp; + } + + cp_block = (struct f2fs_checkpoint *)page_address(cur_page); + memcpy(sbi->ckpt, cp_block, blk_size); + + f2fs_put_page(cp1, 1); + f2fs_put_page(cp2, 1); + return 0; + +fail_no_cp: + kfree(sbi->ckpt); + return -EINVAL; +} + +void set_dirty_dir_page(struct inode *inode, struct page *page) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct list_head *head = &sbi->dir_inode_list; + struct dir_inode_entry *new; + struct list_head *this; + + if (!S_ISDIR(inode->i_mode)) + return; +retry: + new = kmem_cache_alloc(inode_entry_slab, GFP_NOFS); + if (!new) { + cond_resched(); + goto retry; + } + new->inode = inode; + INIT_LIST_HEAD(&new->list); + + spin_lock(&sbi->dir_inode_lock); + list_for_each(this, head) { + struct dir_inode_entry *entry; + entry = list_entry(this, struct dir_inode_entry, list); + if (entry->inode == inode) { + kmem_cache_free(inode_entry_slab, new); + goto out; + } + } + list_add_tail(&new->list, head); + sbi->n_dirty_dirs++; + + BUG_ON(!S_ISDIR(inode->i_mode)); +out: + inc_page_count(sbi, F2FS_DIRTY_DENTS); + inode_inc_dirty_dents(inode); + SetPagePrivate(page); + + spin_unlock(&sbi->dir_inode_lock); +} + +void remove_dirty_dir_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct list_head *head = &sbi->dir_inode_list; + struct list_head *this; + + if (!S_ISDIR(inode->i_mode)) + return; + + spin_lock(&sbi->dir_inode_lock); + if (atomic_read(&F2FS_I(inode)->dirty_dents)) + goto out; + + list_for_each(this, head) { + struct dir_inode_entry *entry; + entry = list_entry(this, struct dir_inode_entry, list); + if (entry->inode == inode) { + list_del(&entry->list); + kmem_cache_free(inode_entry_slab, entry); + sbi->n_dirty_dirs--; + break; + } + } +out: + spin_unlock(&sbi->dir_inode_lock); +} + +void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi) +{ + struct list_head *head = &sbi->dir_inode_list; + struct dir_inode_entry *entry; + struct inode *inode; +retry: + spin_lock(&sbi->dir_inode_lock); + if (list_empty(head)) { + spin_unlock(&sbi->dir_inode_lock); + return; + } + entry = list_entry(head->next, struct dir_inode_entry, list); + inode = igrab(entry->inode); + spin_unlock(&sbi->dir_inode_lock); + if (inode) { + filemap_flush(inode->i_mapping); + iput(inode); + } else { + /* + * We should submit bio, since it exists several + * wribacking dentry pages in the freeing inode. + */ + f2fs_submit_bio(sbi, DATA, true); + } + goto retry; +} + +/* + * Freeze all the FS-operations for checkpoint. + */ +void block_operations(struct f2fs_sb_info *sbi) +{ + int t; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = LONG_MAX, + .for_reclaim = 0, + }; + + /* Stop renaming operation */ + mutex_lock_op(sbi, RENAME); + mutex_lock_op(sbi, DENTRY_OPS); + +retry_dents: + /* write all the dirty dentry pages */ + sync_dirty_dir_inodes(sbi); + + mutex_lock_op(sbi, DATA_WRITE); + if (get_pages(sbi, F2FS_DIRTY_DENTS)) { + mutex_unlock_op(sbi, DATA_WRITE); + goto retry_dents; + } + + /* block all the operations */ + for (t = DATA_NEW; t <= NODE_TRUNC; t++) + mutex_lock_op(sbi, t); + + mutex_lock(&sbi->write_inode); + + /* + * POR: we should ensure that there is no dirty node pages + * until finishing nat/sit flush. + */ +retry: + sync_node_pages(sbi, 0, &wbc); + + mutex_lock_op(sbi, NODE_WRITE); + + if (get_pages(sbi, F2FS_DIRTY_NODES)) { + mutex_unlock_op(sbi, NODE_WRITE); + goto retry; + } + mutex_unlock(&sbi->write_inode); +} + +static void unblock_operations(struct f2fs_sb_info *sbi) +{ + int t; + for (t = NODE_WRITE; t >= RENAME; t--) + mutex_unlock_op(sbi, t); +} + +static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + nid_t last_nid = 0; + block_t start_blk; + struct page *cp_page; + unsigned int data_sum_blocks, orphan_blocks; + unsigned int crc32 = 0; + void *kaddr; + int i; + + /* Flush all the NAT/SIT pages */ + while (get_pages(sbi, F2FS_DIRTY_META)) + sync_meta_pages(sbi, META, LONG_MAX); + + next_free_nid(sbi, &last_nid); + + /* + * modify checkpoint + * version number is already updated + */ + ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi)); + ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi)); + ckpt->free_segment_count = cpu_to_le32(free_segments(sbi)); + for (i = 0; i < 3; i++) { + ckpt->cur_node_segno[i] = + cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_NODE)); + ckpt->cur_node_blkoff[i] = + cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_NODE)); + ckpt->alloc_type[i + CURSEG_HOT_NODE] = + curseg_alloc_type(sbi, i + CURSEG_HOT_NODE); + } + for (i = 0; i < 3; i++) { + ckpt->cur_data_segno[i] = + cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_DATA)); + ckpt->cur_data_blkoff[i] = + cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_DATA)); + ckpt->alloc_type[i + CURSEG_HOT_DATA] = + curseg_alloc_type(sbi, i + CURSEG_HOT_DATA); + } + + ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi)); + ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi)); + ckpt->next_free_nid = cpu_to_le32(last_nid); + + /* 2 cp + n data seg summary + orphan inode blocks */ + data_sum_blocks = npages_for_summary_flush(sbi); + if (data_sum_blocks < 3) + set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); + else + clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); + + orphan_blocks = (sbi->n_orphans + F2FS_ORPHANS_PER_BLOCK - 1) + / F2FS_ORPHANS_PER_BLOCK; + ckpt->cp_pack_start_sum = cpu_to_le32(1 + orphan_blocks); + + if (is_umount) { + set_ckpt_flags(ckpt, CP_UMOUNT_FLAG); + ckpt->cp_pack_total_block_count = cpu_to_le32(2 + + data_sum_blocks + orphan_blocks + NR_CURSEG_NODE_TYPE); + } else { + clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG); + ckpt->cp_pack_total_block_count = cpu_to_le32(2 + + data_sum_blocks + orphan_blocks); + } + + if (sbi->n_orphans) + set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); + else + clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG); + + /* update SIT/NAT bitmap */ + get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP)); + get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP)); + + crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset)); + *(__le32 *)((unsigned char *)ckpt + + le32_to_cpu(ckpt->checksum_offset)) + = cpu_to_le32(crc32); + + start_blk = __start_cp_addr(sbi); + + /* write out checkpoint buffer at block 0 */ + cp_page = grab_meta_page(sbi, start_blk++); + kaddr = page_address(cp_page); + memcpy(kaddr, ckpt, (1 << sbi->log_blocksize)); + set_page_dirty(cp_page); + f2fs_put_page(cp_page, 1); + + if (sbi->n_orphans) { + write_orphan_inodes(sbi, start_blk); + start_blk += orphan_blocks; + } + + write_data_summaries(sbi, start_blk); + start_blk += data_sum_blocks; + if (is_umount) { + write_node_summaries(sbi, start_blk); + start_blk += NR_CURSEG_NODE_TYPE; + } + + /* writeout checkpoint block */ + cp_page = grab_meta_page(sbi, start_blk); + kaddr = page_address(cp_page); + memcpy(kaddr, ckpt, (1 << sbi->log_blocksize)); + set_page_dirty(cp_page); + f2fs_put_page(cp_page, 1); + + /* wait for previous submitted node/meta pages writeback */ + while (get_pages(sbi, F2FS_WRITEBACK)) + congestion_wait(BLK_RW_ASYNC, HZ / 50); + + filemap_fdatawait_range(sbi->node_inode->i_mapping, 0, LONG_MAX); + filemap_fdatawait_range(sbi->meta_inode->i_mapping, 0, LONG_MAX); + + /* update user_block_counts */ + sbi->last_valid_block_count = sbi->total_valid_block_count; + sbi->alloc_valid_block_count = 0; + + /* Here, we only have one bio having CP pack */ + if (is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) + sbi->sb->s_flags |= MS_RDONLY; + else + sync_meta_pages(sbi, META_FLUSH, LONG_MAX); + + 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 blocked, bool is_umount) +{ + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + unsigned long long ckpt_ver; + + if (!blocked) { + mutex_lock(&sbi->cp_mutex); + block_operations(sbi); + } + + f2fs_submit_bio(sbi, DATA, true); + f2fs_submit_bio(sbi, NODE, true); + f2fs_submit_bio(sbi, META, true); + + /* + * update checkpoint pack index + * Increase the version number so that + * SIT entries and seg summaries are written at correct place + */ + ckpt_ver = le64_to_cpu(ckpt->checkpoint_ver); + ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver); + + /* write cached NAT/SIT entries to NAT/SIT area */ + flush_nat_entries(sbi); + flush_sit_entries(sbi); + + reset_victim_segmap(sbi); + + /* unlock all the fs_lock[] in do_checkpoint() */ + do_checkpoint(sbi, is_umount); + + unblock_operations(sbi); + mutex_unlock(&sbi->cp_mutex); +} + +void init_orphan_info(struct f2fs_sb_info *sbi) +{ + mutex_init(&sbi->orphan_inode_mutex); + INIT_LIST_HEAD(&sbi->orphan_inode_list); + sbi->n_orphans = 0; +} + +int create_checkpoint_caches(void) +{ + orphan_entry_slab = f2fs_kmem_cache_create("f2fs_orphan_entry", + sizeof(struct orphan_inode_entry), NULL); + if (unlikely(!orphan_entry_slab)) + return -ENOMEM; + inode_entry_slab = f2fs_kmem_cache_create("f2fs_dirty_dir_entry", + sizeof(struct dir_inode_entry), NULL); + if (unlikely(!inode_entry_slab)) { + kmem_cache_destroy(orphan_entry_slab); + return -ENOMEM; + } + return 0; +} + +void destroy_checkpoint_caches(void) +{ + kmem_cache_destroy(orphan_entry_slab); + kmem_cache_destroy(inode_entry_slab); +} diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c new file mode 100644 index 000000000000..655aeabc1dd4 --- /dev/null +++ b/fs/f2fs/data.c @@ -0,0 +1,702 @@ +/* + * fs/f2fs/data.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/fs.h> +#include <linux/f2fs_fs.h> +#include <linux/buffer_head.h> +#include <linux/mpage.h> +#include <linux/writeback.h> +#include <linux/backing-dev.h> +#include <linux/blkdev.h> +#include <linux/bio.h> + +#include "f2fs.h" +#include "node.h" +#include "segment.h" + +/* + * Lock ordering for the change of data block address: + * ->data_page + * ->node_page + * update block addresses in the node page + */ +static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr) +{ + struct f2fs_node *rn; + __le32 *addr_array; + struct page *node_page = dn->node_page; + unsigned int ofs_in_node = dn->ofs_in_node; + + wait_on_page_writeback(node_page); + + rn = (struct f2fs_node *)page_address(node_page); + + /* Get physical address of data block */ + addr_array = blkaddr_in_node(rn); + addr_array[ofs_in_node] = cpu_to_le32(new_addr); + set_page_dirty(node_page); +} + +int reserve_new_block(struct dnode_of_data *dn) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb); + + if (is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)) + return -EPERM; + if (!inc_valid_block_count(sbi, dn->inode, 1)) + return -ENOSPC; + + __set_data_blkaddr(dn, NEW_ADDR); + dn->data_blkaddr = NEW_ADDR; + sync_inode_page(dn); + return 0; +} + +static int check_extent_cache(struct inode *inode, pgoff_t pgofs, + struct buffer_head *bh_result) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + pgoff_t start_fofs, end_fofs; + block_t start_blkaddr; + + read_lock(&fi->ext.ext_lock); + if (fi->ext.len == 0) { + read_unlock(&fi->ext.ext_lock); + return 0; + } + + sbi->total_hit_ext++; + start_fofs = fi->ext.fofs; + end_fofs = fi->ext.fofs + fi->ext.len - 1; + start_blkaddr = fi->ext.blk_addr; + + if (pgofs >= start_fofs && pgofs <= end_fofs) { + unsigned int blkbits = inode->i_sb->s_blocksize_bits; + size_t count; + + clear_buffer_new(bh_result); + map_bh(bh_result, inode->i_sb, + start_blkaddr + pgofs - start_fofs); + count = end_fofs - pgofs + 1; + if (count < (UINT_MAX >> blkbits)) + bh_result->b_size = (count << blkbits); + else + bh_result->b_size = UINT_MAX; + + sbi->read_hit_ext++; + read_unlock(&fi->ext.ext_lock); + return 1; + } + read_unlock(&fi->ext.ext_lock); + return 0; +} + +void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn) +{ + struct f2fs_inode_info *fi = F2FS_I(dn->inode); + pgoff_t fofs, start_fofs, end_fofs; + block_t start_blkaddr, end_blkaddr; + + BUG_ON(blk_addr == NEW_ADDR); + fofs = start_bidx_of_node(ofs_of_node(dn->node_page)) + dn->ofs_in_node; + + /* Update the page address in the parent node */ + __set_data_blkaddr(dn, blk_addr); + + write_lock(&fi->ext.ext_lock); + + start_fofs = fi->ext.fofs; + end_fofs = fi->ext.fofs + fi->ext.len - 1; + start_blkaddr = fi->ext.blk_addr; + end_blkaddr = fi->ext.blk_addr + fi->ext.len - 1; + + /* Drop and initialize the matched extent */ + if (fi->ext.len == 1 && fofs == start_fofs) + fi->ext.len = 0; + + /* Initial extent */ + if (fi->ext.len == 0) { + if (blk_addr != NULL_ADDR) { + fi->ext.fofs = fofs; + fi->ext.blk_addr = blk_addr; + fi->ext.len = 1; + } + goto end_update; + } + + /* Frone merge */ + if (fofs == start_fofs - 1 && blk_addr == start_blkaddr - 1) { + fi->ext.fofs--; + fi->ext.blk_addr--; + fi->ext.len++; + goto end_update; + } + + /* Back merge */ + if (fofs == end_fofs + 1 && blk_addr == end_blkaddr + 1) { + fi->ext.len++; + goto end_update; + } + + /* Split the existing extent */ + if (fi->ext.len > 1 && + fofs >= start_fofs && fofs <= end_fofs) { + if ((end_fofs - fofs) < (fi->ext.len >> 1)) { + fi->ext.len = fofs - start_fofs; + } else { + fi->ext.fofs = fofs + 1; + fi->ext.blk_addr = start_blkaddr + + fofs - start_fofs + 1; + fi->ext.len -= fofs - start_fofs + 1; + } + goto end_update; + } + write_unlock(&fi->ext.ext_lock); + return; + +end_update: + write_unlock(&fi->ext.ext_lock); + sync_inode_page(dn); + return; +} + +struct page *find_data_page(struct inode *inode, pgoff_t index) +{ + 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, RDONLY_NODE); + if (err) + return ERR_PTR(err); + f2fs_put_dnode(&dn); + + if (dn.data_blkaddr == NULL_ADDR) + return ERR_PTR(-ENOENT); + + /* By fallocate(), there is no cached page, but with NEW_ADDR */ + if (dn.data_blkaddr == NEW_ADDR) + return ERR_PTR(-EINVAL); + + page = grab_cache_page(mapping, index); + if (!page) + return ERR_PTR(-ENOMEM); + + err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC); + if (err) { + f2fs_put_page(page, 1); + return ERR_PTR(err); + } + unlock_page(page); + return page; +} + +/* + * If it tries to access a hole, return an error. + * Because, the callers, functions in dir.c and GC, should be able to know + * whether this page exists or not. + */ +struct page *get_lock_data_page(struct inode *inode, pgoff_t index) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct address_space *mapping = inode->i_mapping; + struct dnode_of_data dn; + struct page *page; + int err; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, index, RDONLY_NODE); + if (err) + return ERR_PTR(err); + f2fs_put_dnode(&dn); + + if (dn.data_blkaddr == NULL_ADDR) + return ERR_PTR(-ENOENT); + + page = grab_cache_page(mapping, index); + if (!page) + return ERR_PTR(-ENOMEM); + + if (PageUptodate(page)) + return page; + + BUG_ON(dn.data_blkaddr == NEW_ADDR); + BUG_ON(dn.data_blkaddr == NULL_ADDR); + + err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC); + if (err) { + f2fs_put_page(page, 1); + return ERR_PTR(err); + } + return page; +} + +/* + * Caller ensures that this data page is never allocated. + * A new zero-filled data page is allocated in the page cache. + */ +struct page *get_new_data_page(struct inode *inode, pgoff_t index, + bool new_i_size) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct address_space *mapping = inode->i_mapping; + struct page *page; + struct dnode_of_data dn; + int err; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, index, 0); + if (err) + return ERR_PTR(err); + + if (dn.data_blkaddr == NULL_ADDR) { + if (reserve_new_block(&dn)) { + f2fs_put_dnode(&dn); + return ERR_PTR(-ENOSPC); + } + } + f2fs_put_dnode(&dn); + + page = grab_cache_page(mapping, index); + if (!page) + return ERR_PTR(-ENOMEM); + + if (PageUptodate(page)) + return page; + + if (dn.data_blkaddr == NEW_ADDR) { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + } else { + err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC); + if (err) { + f2fs_put_page(page, 1); + return ERR_PTR(err); + } + } + SetPageUptodate(page); + + if (new_i_size && + i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) { + i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT)); + mark_inode_dirty_sync(inode); + } + return page; +} + +static void read_end_io(struct bio *bio, int err) +{ + const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); + struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; + + do { + struct page *page = bvec->bv_page; + + if (--bvec >= bio->bi_io_vec) + prefetchw(&bvec->bv_page->flags); + + if (uptodate) { + SetPageUptodate(page); + } else { + ClearPageUptodate(page); + SetPageError(page); + } + unlock_page(page); + } while (bvec >= bio->bi_io_vec); + kfree(bio->bi_private); + bio_put(bio); +} + +/* + * Fill the locked page with data located in the block address. + * Read operation is synchronous, and caller must unlock the page. + */ +int f2fs_readpage(struct f2fs_sb_info *sbi, struct page *page, + block_t blk_addr, int type) +{ + struct block_device *bdev = sbi->sb->s_bdev; + bool sync = (type == READ_SYNC); + struct bio *bio; + + /* This page can be already read by other threads */ + if (PageUptodate(page)) { + if (!sync) + unlock_page(page); + return 0; + } + + down_read(&sbi->bio_sem); + + /* Allocate a new bio */ + bio = f2fs_bio_alloc(bdev, 1); + + /* Initialize the bio */ + bio->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr); + bio->bi_end_io = read_end_io; + + if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { + kfree(bio->bi_private); + bio_put(bio); + up_read(&sbi->bio_sem); + return -EFAULT; + } + + submit_bio(type, bio); + up_read(&sbi->bio_sem); + + /* wait for read completion if sync */ + if (sync) { + lock_page(page); + if (PageError(page)) + return -EIO; + } + return 0; +} + +/* + * This function should be used by the data read flow only where it + * does not check the "create" flag that indicates block allocation. + * The reason for this special functionality is to exploit VFS readahead + * mechanism. + */ +static int get_data_block_ro(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + unsigned int blkbits = inode->i_sb->s_blocksize_bits; + unsigned maxblocks = bh_result->b_size >> blkbits; + struct dnode_of_data dn; + pgoff_t pgofs; + int err; + + /* Get the page offset from the block offset(iblock) */ + pgofs = (pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits)); + + if (check_extent_cache(inode, pgofs, bh_result)) + return 0; + + /* When reading holes, we need its node page */ + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, pgofs, RDONLY_NODE); + if (err) + return (err == -ENOENT) ? 0 : err; + + /* It does not support data allocation */ + BUG_ON(create); + + if (dn.data_blkaddr != NEW_ADDR && dn.data_blkaddr != NULL_ADDR) { + int i; + unsigned int end_offset; + + end_offset = IS_INODE(dn.node_page) ? + ADDRS_PER_INODE : + ADDRS_PER_BLOCK; + + clear_buffer_new(bh_result); + + /* Give more consecutive addresses for the read ahead */ + for (i = 0; i < end_offset - dn.ofs_in_node; i++) + if (((datablock_addr(dn.node_page, + dn.ofs_in_node + i)) + != (dn.data_blkaddr + i)) || maxblocks == i) + break; + map_bh(bh_result, inode->i_sb, dn.data_blkaddr); + bh_result->b_size = (i << blkbits); + } + f2fs_put_dnode(&dn); + return 0; +} + +static int f2fs_read_data_page(struct file *file, struct page *page) +{ + return mpage_readpage(page, get_data_block_ro); +} + +static int f2fs_read_data_pages(struct file *file, + struct address_space *mapping, + struct list_head *pages, unsigned nr_pages) +{ + return mpage_readpages(mapping, pages, nr_pages, get_data_block_ro); +} + +int do_write_data_page(struct page *page) +{ + struct inode *inode = page->mapping->host; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + block_t old_blk_addr, new_blk_addr; + struct dnode_of_data dn; + int err = 0; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, page->index, RDONLY_NODE); + if (err) + return err; + + old_blk_addr = dn.data_blkaddr; + + /* This page is already truncated */ + if (old_blk_addr == NULL_ADDR) + goto out_writepage; + + set_page_writeback(page); + + /* + * If current allocation needs SSR, + * it had better in-place writes for updated data. + */ + if (old_blk_addr != NEW_ADDR && !is_cold_data(page) && + need_inplace_update(inode)) { + rewrite_data_page(F2FS_SB(inode->i_sb), page, + old_blk_addr); + } else { + write_data_page(inode, page, &dn, + old_blk_addr, &new_blk_addr); + update_extent_cache(new_blk_addr, &dn); + F2FS_I(inode)->data_version = + le64_to_cpu(F2FS_CKPT(sbi)->checkpoint_ver); + } +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; + int err = 0; + + if (page->index < end_index) + goto out; + + /* + * 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 unlock_out; + } + + zero_user_segment(page, offset, PAGE_CACHE_SIZE); +out: + if (sbi->por_doing) + goto redirty_out; + + if (wbc->for_reclaim && !S_ISDIR(inode->i_mode) && !is_cold_data(page)) + goto redirty_out; + + mutex_lock_op(sbi, DATA_WRITE); + if (S_ISDIR(inode->i_mode)) { + dec_page_count(sbi, F2FS_DIRTY_DENTS); + inode_dec_dirty_dents(inode); + } + err = do_write_data_page(page); + if (err && err != -ENOENT) { + wbc->pages_skipped++; + set_page_dirty(page); + } + mutex_unlock_op(sbi, DATA_WRITE); + + if (wbc->for_reclaim) + f2fs_submit_bio(sbi, DATA, true); + + if (err == -ENOENT) + goto unlock_out; + + clear_cold_data(page); + unlock_page(page); + + if (!wbc->for_reclaim && !S_ISDIR(inode->i_mode)) + f2fs_balance_fs(sbi); + return 0; + +unlock_out: + unlock_page(page); + return (err == -ENOENT) ? 0 : err; + +redirty_out: + wbc->pages_skipped++; + set_page_dirty(page); + return AOP_WRITEPAGE_ACTIVATE; +} + +#define MAX_DESIRED_PAGES_WP 4096 + +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); + int ret; + long excess_nrtw = 0, desired_nrtw; + + 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); + ret = generic_writepages(mapping, wbc); + if (!S_ISDIR(inode->i_mode)) + mutex_unlock(&sbi->writepages); + f2fs_submit_bio(sbi, DATA, (wbc->sync_mode == WB_SYNC_ALL)); + + remove_dirty_dir_inode(inode); + + wbc->nr_to_write -= excess_nrtw; + return ret; +} + +static int f2fs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) +{ + struct inode *inode = mapping->host; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct page *page; + pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT; + struct dnode_of_data dn; + int err = 0; + + /* for nobh_write_end */ + *fsdata = NULL; + + f2fs_balance_fs(sbi); + + page = grab_cache_page_write_begin(mapping, index, flags); + if (!page) + return -ENOMEM; + *pagep = page; + + mutex_lock_op(sbi, DATA_NEW); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, index, 0); + if (err) { + mutex_unlock_op(sbi, DATA_NEW); + f2fs_put_page(page, 1); + return err; + } + + if (dn.data_blkaddr == NULL_ADDR) { + err = reserve_new_block(&dn); + if (err) { + f2fs_put_dnode(&dn); + mutex_unlock_op(sbi, DATA_NEW); + f2fs_put_page(page, 1); + return err; + } + } + f2fs_put_dnode(&dn); + + mutex_unlock_op(sbi, DATA_NEW); + + 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); + return 0; + } + + if (dn.data_blkaddr == NEW_ADDR) { + zero_user_segment(page, 0, PAGE_CACHE_SIZE); + } else { + err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC); + if (err) { + f2fs_put_page(page, 1); + return err; + } + } + SetPageUptodate(page); + clear_cold_data(page); + 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; + + if (rw == WRITE) + return 0; + + /* Needs synchronization with the cleaner */ + return blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + get_data_block_ro); +} + +static void f2fs_invalidate_data_page(struct page *page, unsigned long offset) +{ + struct inode *inode = page->mapping->host; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + if (S_ISDIR(inode->i_mode) && PageDirty(page)) { + dec_page_count(sbi, F2FS_DIRTY_DENTS); + inode_dec_dirty_dents(inode); + } + ClearPagePrivate(page); +} + +static int f2fs_release_data_page(struct page *page, gfp_t wait) +{ + ClearPagePrivate(page); + return 0; +} + +static int f2fs_set_data_page_dirty(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct inode *inode = mapping->host; + + SetPageUptodate(page); + if (!PageDirty(page)) { + __set_page_dirty_nobuffers(page); + set_dirty_dir_page(inode, page); + return 1; + } + return 0; +} + +const struct address_space_operations f2fs_dblock_aops = { + .readpage = f2fs_read_data_page, + .readpages = f2fs_read_data_pages, + .writepage = f2fs_write_data_page, + .writepages = f2fs_write_data_pages, + .write_begin = f2fs_write_begin, + .write_end = nobh_write_end, + .set_page_dirty = f2fs_set_data_page_dirty, + .invalidatepage = f2fs_invalidate_data_page, + .releasepage = f2fs_release_data_page, + .direct_IO = f2fs_direct_IO, +}; diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c new file mode 100644 index 000000000000..0e0380a588ad --- /dev/null +++ b/fs/f2fs/debug.c @@ -0,0 +1,361 @@ +/* + * f2fs debugging statistics + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * Copyright (c) 2012 Linux Foundation + * Copyright (c) 2012 Greg Kroah-Hartman <gregkh@linuxfoundation.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/backing-dev.h> +#include <linux/proc_fs.h> +#include <linux/f2fs_fs.h> +#include <linux/blkdev.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include "gc.h" + +static LIST_HEAD(f2fs_stat_list); +static struct dentry *debugfs_root; + +static void update_general_status(struct f2fs_sb_info *sbi) +{ + struct f2fs_stat_info *si = sbi->stat_info; + int i; + + /* valid check of the segment numbers */ + si->hit_ext = sbi->read_hit_ext; + si->total_ext = sbi->total_hit_ext; + si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES); + si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS); + si->ndirty_dirs = sbi->n_dirty_dirs; + si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META); + si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg; + si->rsvd_segs = reserved_segments(sbi); + si->overp_segs = overprovision_segments(sbi); + si->valid_count = valid_user_blocks(sbi); + si->valid_node_count = valid_node_count(sbi); + si->valid_inode_count = valid_inode_count(sbi); + si->utilization = utilization(sbi); + + si->free_segs = free_segments(sbi); + si->free_secs = free_sections(sbi); + si->prefree_count = prefree_segments(sbi); + si->dirty_count = dirty_segments(sbi); + si->node_pages = sbi->node_inode->i_mapping->nrpages; + si->meta_pages = sbi->meta_inode->i_mapping->nrpages; + si->nats = NM_I(sbi)->nat_cnt; + si->sits = SIT_I(sbi)->dirty_sentries; + si->fnids = NM_I(sbi)->fcnt; + si->bg_gc = sbi->bg_gc; + si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg) + * 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg) + / 2; + si->util_valid = (int)(written_block_count(sbi) >> + sbi->log_blocks_per_seg) + * 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg) + / 2; + si->util_invalid = 50 - si->util_free - si->util_valid; + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_NODE; i++) { + struct curseg_info *curseg = CURSEG_I(sbi, i); + si->curseg[i] = curseg->segno; + si->cursec[i] = curseg->segno / sbi->segs_per_sec; + si->curzone[i] = si->cursec[i] / sbi->secs_per_zone; + } + + for (i = 0; i < 2; i++) { + si->segment_count[i] = sbi->segment_count[i]; + si->block_count[i] = sbi->block_count[i]; + } +} + +/* + * This function calculates BDF of every segments + */ +static void update_sit_info(struct f2fs_sb_info *sbi) +{ + struct f2fs_stat_info *si = sbi->stat_info; + unsigned int blks_per_sec, hblks_per_sec, total_vblocks, bimodal, dist; + struct sit_info *sit_i = SIT_I(sbi); + unsigned int segno, vblocks; + int ndirty = 0; + + bimodal = 0; + total_vblocks = 0; + blks_per_sec = sbi->segs_per_sec * (1 << sbi->log_blocks_per_seg); + hblks_per_sec = blks_per_sec / 2; + mutex_lock(&sit_i->sentry_lock); + for (segno = 0; segno < TOTAL_SEGS(sbi); segno += sbi->segs_per_sec) { + vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec); + dist = abs(vblocks - hblks_per_sec); + bimodal += dist * dist; + + if (vblocks > 0 && vblocks < blks_per_sec) { + total_vblocks += vblocks; + ndirty++; + } + } + mutex_unlock(&sit_i->sentry_lock); + dist = sbi->total_sections * hblks_per_sec * hblks_per_sec / 100; + si->bimodal = bimodal / dist; + if (si->dirty_count) + si->avg_vblocks = total_vblocks / ndirty; + else + si->avg_vblocks = 0; +} + +/* + * This function calculates memory footprint. + */ +static void update_mem_info(struct f2fs_sb_info *sbi) +{ + struct f2fs_stat_info *si = sbi->stat_info; + unsigned npages; + + if (si->base_mem) + goto get_cache; + + si->base_mem = sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize; + si->base_mem += 2 * sizeof(struct f2fs_inode_info); + si->base_mem += sizeof(*sbi->ckpt); + + /* build sm */ + si->base_mem += sizeof(struct f2fs_sm_info); + + /* build sit */ + si->base_mem += sizeof(struct sit_info); + si->base_mem += TOTAL_SEGS(sbi) * sizeof(struct seg_entry); + si->base_mem += f2fs_bitmap_size(TOTAL_SEGS(sbi)); + si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * TOTAL_SEGS(sbi); + if (sbi->segs_per_sec > 1) + si->base_mem += sbi->total_sections * + 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(sbi->total_sections); + + /* 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 += 2 * f2fs_bitmap_size(TOTAL_SEGS(sbi)); + + /* buld nm */ + si->base_mem += sizeof(struct f2fs_nm_info); + si->base_mem += __bitmap_size(sbi, NAT_BITMAP); + + /* build gc */ + si->base_mem += sizeof(struct f2fs_gc_kthread); + +get_cache: + /* free nids */ + si->cache_mem = NM_I(sbi)->fcnt; + si->cache_mem += NM_I(sbi)->nat_cnt; + npages = sbi->node_inode->i_mapping->nrpages; + si->cache_mem += npages << PAGE_CACHE_SHIFT; + npages = sbi->meta_inode->i_mapping->nrpages; + si->cache_mem += npages << PAGE_CACHE_SHIFT; + si->cache_mem += sbi->n_orphans * sizeof(struct orphan_inode_entry); + si->cache_mem += sbi->n_dirty_dirs * sizeof(struct dir_inode_entry); +} + +static int stat_show(struct seq_file *s, void *v) +{ + struct f2fs_stat_info *si, *next; + int i = 0; + int j; + + list_for_each_entry_safe(si, next, &f2fs_stat_list, stat_list) { + + mutex_lock(&si->stat_lock); + if (!si->sbi) { + mutex_unlock(&si->stat_lock); + continue; + } + update_general_status(si->sbi); + + seq_printf(s, "\n=====[ partition info. #%d ]=====\n", i++); + seq_printf(s, "[SB: 1] [CP: 2] [NAT: %d] [SIT: %d] ", + si->nat_area_segs, si->sit_area_segs); + seq_printf(s, "[SSA: %d] [MAIN: %d", + si->ssa_area_segs, si->main_area_segs); + seq_printf(s, "(OverProv:%d Resv:%d)]\n\n", + si->overp_segs, si->rsvd_segs); + seq_printf(s, "Utilization: %d%% (%d valid blocks)\n", + si->utilization, si->valid_count); + seq_printf(s, " - Node: %u (Inode: %u, ", + si->valid_node_count, si->valid_inode_count); + seq_printf(s, "Other: %u)\n - Data: %u\n", + si->valid_node_count - si->valid_inode_count, + si->valid_count - si->valid_node_count); + seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n", + si->main_area_segs, si->main_area_sections, + si->main_area_zones); + seq_printf(s, " - COLD data: %d, %d, %d\n", + si->curseg[CURSEG_COLD_DATA], + si->cursec[CURSEG_COLD_DATA], + si->curzone[CURSEG_COLD_DATA]); + seq_printf(s, " - WARM data: %d, %d, %d\n", + si->curseg[CURSEG_WARM_DATA], + si->cursec[CURSEG_WARM_DATA], + si->curzone[CURSEG_WARM_DATA]); + seq_printf(s, " - HOT data: %d, %d, %d\n", + si->curseg[CURSEG_HOT_DATA], + si->cursec[CURSEG_HOT_DATA], + si->curzone[CURSEG_HOT_DATA]); + seq_printf(s, " - Dir dnode: %d, %d, %d\n", + si->curseg[CURSEG_HOT_NODE], + si->cursec[CURSEG_HOT_NODE], + si->curzone[CURSEG_HOT_NODE]); + seq_printf(s, " - File dnode: %d, %d, %d\n", + si->curseg[CURSEG_WARM_NODE], + si->cursec[CURSEG_WARM_NODE], + si->curzone[CURSEG_WARM_NODE]); + seq_printf(s, " - Indir nodes: %d, %d, %d\n", + si->curseg[CURSEG_COLD_NODE], + si->cursec[CURSEG_COLD_NODE], + si->curzone[CURSEG_COLD_NODE]); + seq_printf(s, "\n - Valid: %d\n - Dirty: %d\n", + si->main_area_segs - si->dirty_count - + si->prefree_count - si->free_segs, + si->dirty_count); + seq_printf(s, " - Prefree: %d\n - Free: %d (%d)\n\n", + si->prefree_count, si->free_segs, si->free_secs); + seq_printf(s, "GC calls: %d (BG: %d)\n", + si->call_count, si->bg_gc); + seq_printf(s, " - data segments : %d\n", si->data_segs); + seq_printf(s, " - node segments : %d\n", si->node_segs); + seq_printf(s, "Try to move %d blocks\n", si->tot_blks); + seq_printf(s, " - data blocks : %d\n", si->data_blks); + seq_printf(s, " - node blocks : %d\n", si->node_blks); + seq_printf(s, "\nExtent Hit Ratio: %d / %d\n", + si->hit_ext, si->total_ext); + seq_printf(s, "\nBalancing F2FS Async:\n"); + seq_printf(s, " - nodes %4d in %4d\n", + si->ndirty_node, si->node_pages); + seq_printf(s, " - dents %4d in dirs:%4d\n", + si->ndirty_dent, si->ndirty_dirs); + seq_printf(s, " - meta %4d in %4d\n", + si->ndirty_meta, si->meta_pages); + seq_printf(s, " - NATs %5d > %lu\n", + si->nats, NM_WOUT_THRESHOLD); + seq_printf(s, " - SITs: %5d\n - free_nids: %5d\n", + si->sits, si->fnids); + seq_printf(s, "\nDistribution of User Blocks:"); + seq_printf(s, " [ valid | invalid | free ]\n"); + seq_printf(s, " ["); + + for (j = 0; j < si->util_valid; j++) + seq_printf(s, "-"); + seq_printf(s, "|"); + + for (j = 0; j < si->util_invalid; j++) + seq_printf(s, "-"); + seq_printf(s, "|"); + + for (j = 0; j < si->util_free; j++) + seq_printf(s, "-"); + seq_printf(s, "]\n\n"); + seq_printf(s, "SSR: %u blocks in %u segments\n", + si->block_count[SSR], si->segment_count[SSR]); + seq_printf(s, "LFS: %u blocks in %u segments\n", + si->block_count[LFS], si->segment_count[LFS]); + + /* segment usage info */ + update_sit_info(si->sbi); + seq_printf(s, "\nBDF: %u, avg. vblocks: %u\n", + si->bimodal, si->avg_vblocks); + + /* memory footprint */ + update_mem_info(si->sbi); + seq_printf(s, "\nMemory: %u KB = static: %u + cached: %u\n", + (si->base_mem + si->cache_mem) >> 10, + si->base_mem >> 10, si->cache_mem >> 10); + mutex_unlock(&si->stat_lock); + } + 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, +}; + +static int init_stats(struct f2fs_sb_info *sbi) +{ + struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); + struct f2fs_stat_info *si; + + sbi->stat_info = kzalloc(sizeof(struct f2fs_stat_info), GFP_KERNEL); + if (!sbi->stat_info) + return -ENOMEM; + + si = sbi->stat_info; + mutex_init(&si->stat_lock); + list_add_tail(&si->stat_list, &f2fs_stat_list); + + 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; + return 0; +} + +int f2fs_build_stats(struct f2fs_sb_info *sbi) +{ + int retval; + + retval = init_stats(sbi); + if (retval) + return retval; + + if (!debugfs_root) + debugfs_root = debugfs_create_dir("f2fs", NULL); + + debugfs_create_file("status", S_IRUGO, debugfs_root, NULL, &stat_fops); + return 0; +} + +void f2fs_destroy_stats(struct f2fs_sb_info *sbi) +{ + struct f2fs_stat_info *si = sbi->stat_info; + + list_del(&si->stat_list); + mutex_lock(&si->stat_lock); + si->sbi = NULL; + mutex_unlock(&si->stat_lock); + kfree(sbi->stat_info); +} + +void destroy_root_stats(void) +{ + debugfs_remove_recursive(debugfs_root); + debugfs_root = NULL; +} diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c new file mode 100644 index 000000000000..b4e24f32b54e --- /dev/null +++ b/fs/f2fs/dir.c @@ -0,0 +1,672 @@ +/* + * fs/f2fs/dir.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/fs.h> +#include <linux/f2fs_fs.h> +#include "f2fs.h" +#include "acl.h" + +static unsigned long dir_blocks(struct inode *inode) +{ + return ((unsigned long long) (i_size_read(inode) + PAGE_CACHE_SIZE - 1)) + >> PAGE_CACHE_SHIFT; +} + +static unsigned int dir_buckets(unsigned int level) +{ + if (level < MAX_DIR_HASH_DEPTH / 2) + return 1 << level; + else + return 1 << ((MAX_DIR_HASH_DEPTH / 2) - 1); +} + +static unsigned int bucket_blocks(unsigned int level) +{ + if (level < MAX_DIR_HASH_DEPTH / 2) + return 2; + else + return 4; +} + +static unsigned char f2fs_filetype_table[F2FS_FT_MAX] = { + [F2FS_FT_UNKNOWN] = DT_UNKNOWN, + [F2FS_FT_REG_FILE] = DT_REG, + [F2FS_FT_DIR] = DT_DIR, + [F2FS_FT_CHRDEV] = DT_CHR, + [F2FS_FT_BLKDEV] = DT_BLK, + [F2FS_FT_FIFO] = DT_FIFO, + [F2FS_FT_SOCK] = DT_SOCK, + [F2FS_FT_SYMLINK] = DT_LNK, +}; + +#define S_SHIFT 12 +static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = { + [S_IFREG >> S_SHIFT] = F2FS_FT_REG_FILE, + [S_IFDIR >> S_SHIFT] = F2FS_FT_DIR, + [S_IFCHR >> S_SHIFT] = F2FS_FT_CHRDEV, + [S_IFBLK >> S_SHIFT] = F2FS_FT_BLKDEV, + [S_IFIFO >> S_SHIFT] = F2FS_FT_FIFO, + [S_IFSOCK >> S_SHIFT] = F2FS_FT_SOCK, + [S_IFLNK >> S_SHIFT] = F2FS_FT_SYMLINK, +}; + +static void set_de_type(struct f2fs_dir_entry *de, struct inode *inode) +{ + mode_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, int 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, int 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, int namelen, + f2fs_hash_t namehash, struct page **res_page) +{ + int s = GET_DENTRY_SLOTS(namelen); + unsigned int nbucket, nblock; + unsigned int bidx, end_block; + struct page *dentry_page; + struct f2fs_dir_entry *de = NULL; + bool room = false; + int max_slots = 0; + + BUG_ON(level > MAX_DIR_HASH_DEPTH); + + nbucket = dir_buckets(level); + nblock = bucket_blocks(level); + + bidx = dir_block_index(level, le32_to_cpu(namehash) % nbucket); + end_block = bidx + nblock; + + for (; bidx < end_block; bidx++) { + /* no need to allocate new dentry pages to all the indices */ + dentry_page = find_data_page(dir, bidx); + 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; + int 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 = NULL; + struct f2fs_dir_entry *de = NULL; + struct f2fs_dentry_block *dentry_blk = NULL; + + page = get_lock_data_page(dir, 0); + if (IS_ERR(page)) + return NULL; + + dentry_blk = kmap(page); + de = &dentry_blk->dentry[1]; + *p = page; + unlock_page(page); + return de; +} + +ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr) +{ + ino_t res = 0; + struct f2fs_dir_entry *de; + struct page *page; + + de = f2fs_find_entry(dir, qstr, &page); + if (de) { + res = le32_to_cpu(de->ino); + kunmap(page); + f2fs_put_page(page, 0); + } + + return res; +} + +void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de, + struct page *page, struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); + + mutex_lock_op(sbi, DENTRY_OPS); + lock_page(page); + wait_on_page_writeback(page); + de->ino = cpu_to_le32(inode->i_ino); + set_de_type(de, inode); + kunmap(page); + set_page_dirty(page); + dir->i_mtime = dir->i_ctime = CURRENT_TIME; + mark_inode_dirty(dir); + + /* update parent inode number before releasing dentry page */ + F2FS_I(inode)->i_pino = dir->i_ino; + + f2fs_put_page(page, 1); + mutex_unlock_op(sbi, DENTRY_OPS); +} + +void init_dent_inode(struct dentry *dentry, struct page *ipage) +{ + struct f2fs_node *rn; + + if (IS_ERR(ipage)) + return; + + wait_on_page_writeback(ipage); + + /* copy dentry info. to this inode page */ + rn = (struct f2fs_node *)page_address(ipage); + rn->i.i_namelen = cpu_to_le32(dentry->d_name.len); + memcpy(rn->i.i_name, dentry->d_name.name, dentry->d_name.len); + set_page_dirty(ipage); +} + +static int init_inode_metadata(struct inode *inode, struct dentry *dentry) +{ + struct inode *dir = dentry->d_parent->d_inode; + + if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) { + int err; + err = new_inode_page(inode, dentry); + if (err) + return err; + + if (S_ISDIR(inode->i_mode)) { + err = f2fs_make_empty(inode, dir); + if (err) { + remove_inode_page(inode); + return err; + } + } + + err = f2fs_init_acl(inode, dir); + if (err) { + remove_inode_page(inode); + return err; + } + } else { + struct page *ipage; + ipage = get_node_page(F2FS_SB(dir->i_sb), inode->i_ino); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); + init_dent_inode(dentry, ipage); + f2fs_put_page(ipage, 1); + } + if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) { + inc_nlink(inode); + f2fs_write_inode(inode, NULL); + } + return 0; +} + +static void update_parent_metadata(struct inode *dir, struct inode *inode, + unsigned int current_depth) +{ + bool need_dir_update = false; + + if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) { + if (S_ISDIR(inode->i_mode)) { + inc_nlink(dir); + need_dir_update = true; + } + clear_inode_flag(F2FS_I(inode), FI_NEW_INODE); + } + dir->i_mtime = dir->i_ctime = CURRENT_TIME; + if (F2FS_I(dir)->i_current_depth != current_depth) { + F2FS_I(dir)->i_current_depth = current_depth; + need_dir_update = true; + } + + if (need_dir_update) + f2fs_write_inode(dir, NULL); + 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; +} + +int f2fs_add_link(struct dentry *dentry, 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; + struct inode *dir = dentry->d_parent->d_inode; + struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); + const char *name = dentry->d_name.name; + int namelen = dentry->d_name.len; + struct page *dentry_page = NULL; + struct f2fs_dentry_block *dentry_blk = NULL; + int slots = GET_DENTRY_SLOTS(namelen); + int err = 0; + int i; + + dentry_hash = f2fs_dentry_hash(name, dentry->d_name.len); + level = 0; + current_depth = F2FS_I(dir)->i_current_depth; + if (F2FS_I(dir)->chash == dentry_hash) { + level = F2FS_I(dir)->clevel; + F2FS_I(dir)->chash = 0; + } + +start: + if (current_depth == MAX_DIR_HASH_DEPTH) + return -ENOSPC; + + /* Increase the depth, if required */ + if (level == current_depth) + ++current_depth; + + nbucket = dir_buckets(level); + nblock = bucket_blocks(level); + + bidx = dir_block_index(level, (le32_to_cpu(dentry_hash) % nbucket)); + + for (block = bidx; block <= (bidx + nblock - 1); block++) { + mutex_lock_op(sbi, DENTRY_OPS); + dentry_page = get_new_data_page(dir, block, true); + if (IS_ERR(dentry_page)) { + mutex_unlock_op(sbi, DENTRY_OPS); + 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); + mutex_unlock_op(sbi, DENTRY_OPS); + } + + /* Move to next level to find the empty slot for new dentry */ + ++level; + goto start; +add_dentry: + err = init_inode_metadata(inode, dentry); + if (err) + goto fail; + + wait_on_page_writeback(dentry_page); + + de = &dentry_blk->dentry[bit_pos]; + de->hash_code = dentry_hash; + de->name_len = cpu_to_le16(namelen); + memcpy(dentry_blk->filename[bit_pos], name, namelen); + de->ino = cpu_to_le32(inode->i_ino); + set_de_type(de, inode); + for (i = 0; i < slots; i++) + test_and_set_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap); + set_page_dirty(dentry_page); + + update_parent_metadata(dir, inode, current_depth); + + /* update parent inode number before releasing dentry page */ + F2FS_I(inode)->i_pino = dir->i_ino; +fail: + kunmap(dentry_page); + f2fs_put_page(dentry_page, 1); + mutex_unlock_op(sbi, DENTRY_OPS); + 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; + + mutex_lock_op(sbi, DENTRY_OPS); + + 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); + f2fs_write_inode(dir, NULL); + } else { + mark_inode_dirty(dir); + } + + if (inode) { + inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; + drop_nlink(inode); + if (S_ISDIR(inode->i_mode)) { + drop_nlink(inode); + i_size_write(inode, 0); + } + f2fs_write_inode(inode, NULL); + if (inode->i_nlink == 0) + add_orphan_inode(sbi, inode->i_ino); + } + + if (bit_pos == NR_DENTRY_IN_BLOCK) { + truncate_hole(dir, page->index, page->index + 1); + clear_page_dirty_for_io(page); + ClearPageUptodate(page); + dec_page_count(sbi, F2FS_DIRTY_DENTS); + inode_dec_dirty_dents(dir); + } + f2fs_put_page(page, 1); + + mutex_unlock_op(sbi, DENTRY_OPS); +} + +int f2fs_make_empty(struct inode *inode, struct inode *parent) +{ + struct page *dentry_page; + struct f2fs_dentry_block *dentry_blk; + struct f2fs_dir_entry *de; + void *kaddr; + + dentry_page = get_new_data_page(inode, 0, true); + if (IS_ERR(dentry_page)) + return PTR_ERR(dentry_page); + + kaddr = kmap_atomic(dentry_page); + dentry_blk = (struct f2fs_dentry_block *)kaddr; + + de = &dentry_blk->dentry[0]; + de->name_len = cpu_to_le16(1); + de->hash_code = 0; + de->ino = cpu_to_le32(inode->i_ino); + memcpy(dentry_blk->filename[0], ".", 1); + set_de_type(de, inode); + + de = &dentry_blk->dentry[1]; + de->hash_code = 0; + de->name_len = cpu_to_le16(2); + de->ino = cpu_to_le32(parent->i_ino); + memcpy(dentry_blk->filename[1], "..", 2); + set_de_type(de, inode); + + test_and_set_bit_le(0, &dentry_blk->dentry_bitmap); + test_and_set_bit_le(1, &dentry_blk->dentry_bitmap); + kunmap_atomic(kaddr); + + set_page_dirty(dentry_page); + f2fs_put_page(dentry_page, 1); + return 0; +} + +bool f2fs_empty_dir(struct inode *dir) +{ + unsigned long bidx; + struct page *dentry_page; + unsigned int bit_pos; + struct f2fs_dentry_block *dentry_blk; + unsigned long nblock = dir_blocks(dir); + + for (bidx = 0; bidx < nblock; bidx++) { + void *kaddr; + dentry_page = get_lock_data_page(dir, bidx); + if (IS_ERR(dentry_page)) { + if (PTR_ERR(dentry_page) == -ENOENT) + continue; + else + return false; + } + + kaddr = kmap_atomic(dentry_page); + dentry_blk = (struct f2fs_dentry_block *)kaddr; + if (bidx == 0) + bit_pos = 2; + else + bit_pos = 0; + bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, + NR_DENTRY_IN_BLOCK, + bit_pos); + kunmap_atomic(kaddr); + + f2fs_put_page(dentry_page, 1); + + if (bit_pos < NR_DENTRY_IN_BLOCK) + return false; + } + return true; +} + +static int f2fs_readdir(struct file *file, void *dirent, filldir_t filldir) +{ + unsigned long pos = file->f_pos; + struct inode *inode = file->f_dentry->d_inode; + unsigned long npages = dir_blocks(inode); + unsigned char *types = NULL; + unsigned int bit_pos = 0, start_bit_pos = 0; + int over = 0; + struct f2fs_dentry_block *dentry_blk = NULL; + struct f2fs_dir_entry *de = NULL; + struct page *dentry_page = NULL; + unsigned int n = 0; + unsigned char d_type = DT_UNKNOWN; + int slots; + + types = f2fs_filetype_table; + bit_pos = (pos % NR_DENTRY_IN_BLOCK); + n = (pos / NR_DENTRY_IN_BLOCK); + + for ( ; n < npages; n++) { + dentry_page = get_lock_data_page(inode, n); + if (IS_ERR(dentry_page)) + continue; + + start_bit_pos = bit_pos; + dentry_blk = kmap(dentry_page); + while (bit_pos < NR_DENTRY_IN_BLOCK) { + d_type = DT_UNKNOWN; + bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, + NR_DENTRY_IN_BLOCK, + bit_pos); + if (bit_pos >= NR_DENTRY_IN_BLOCK) + break; + + de = &dentry_blk->dentry[bit_pos]; + if (types && de->file_type < F2FS_FT_MAX) + d_type = types[de->file_type]; + + over = filldir(dirent, + dentry_blk->filename[bit_pos], + le16_to_cpu(de->name_len), + (n * NR_DENTRY_IN_BLOCK) + bit_pos, + le32_to_cpu(de->ino), d_type); + if (over) { + file->f_pos += bit_pos - start_bit_pos; + goto success; + } + slots = GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); + bit_pos += slots; + } + bit_pos = 0; + file->f_pos = (n + 1) * NR_DENTRY_IN_BLOCK; + kunmap(dentry_page); + f2fs_put_page(dentry_page, 1); + dentry_page = NULL; + } +success: + if (dentry_page && !IS_ERR(dentry_page)) { + kunmap(dentry_page); + f2fs_put_page(dentry_page, 1); + } + + return 0; +} + +const struct file_operations f2fs_dir_operations = { + .llseek = generic_file_llseek, + .read = generic_read_dir, + .readdir = f2fs_readdir, + .fsync = f2fs_sync_file, + .unlocked_ioctl = f2fs_ioctl, +}; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h new file mode 100644 index 000000000000..a18d63db2fb6 --- /dev/null +++ b/fs/f2fs/f2fs.h @@ -0,0 +1,1083 @@ +/* + * fs/f2fs/f2fs.h + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef _LINUX_F2FS_H +#define _LINUX_F2FS_H + +#include <linux/types.h> +#include <linux/page-flags.h> +#include <linux/buffer_head.h> +#include <linux/slab.h> +#include <linux/crc32.h> +#include <linux/magic.h> + +/* + * 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 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 u64 block_t; +typedef u32 nid_t; + +struct f2fs_mount_info { + unsigned int opt; +}; + +static inline __u32 f2fs_crc32(void *buff, size_t len) +{ + return crc32_le(F2FS_SUPER_MAGIC, buff, len); +} + +static inline bool f2fs_crc_valid(__u32 blk_crc, void *buff, size_t buff_size) +{ + return f2fs_crc32(buff, buff_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 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; +} + +/* + * For INODE and NODE manager + */ +#define XATTR_NODE_OFFSET (-1) /* + * store xattrs to one node block per + * file keeping -1 as its node offset to + * distinguish from index node blocks. + */ +#define RDONLY_NODE 1 /* + * specify a read-only mode when getting + * a node block. 0 is read-write mode. + * used by get_dnode_of_data(). + */ +#define F2FS_LINK_MAX 32000 /* maximum link count per file */ + +/* for in-memory extent cache entry */ +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; /* lenth of the extent */ +}; + +/* + * i_advise uses FADVISE_XXX_BIT. We can add additional hints later. + */ +#define FADVISE_COLD_BIT 0x01 + +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 */ + unsigned long long data_version;/* lastes version of data for fsync */ + 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 */ + 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 init_scan_nid; /* the first nid to be scanned */ + 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) +{ + dn->inode = inode; + dn->inode_page = ipage; + dn->node_page = npage; + dn->nid = nid; + dn->inode_page_locked = 0; +} + +/* + * 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 */ +}; + +/* + * For directory operation + */ +#define NODE_DIR1_BLOCK (ADDRS_PER_INODE + 1) +#define NODE_DIR2_BLOCK (ADDRS_PER_INODE + 2) +#define NODE_IND1_BLOCK (ADDRS_PER_INODE + 3) +#define NODE_IND2_BLOCK (ADDRS_PER_INODE + 4) +#define NODE_DIND_BLOCK (ADDRS_PER_INODE + 5) + +/* + * 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, +}; + +/* + * FS_LOCK nesting subclasses for the lock validator: + * + * The locking order between these classes is + * RENAME -> DENTRY_OPS -> DATA_WRITE -> DATA_NEW + * -> DATA_TRUNC -> NODE_WRITE -> NODE_NEW -> NODE_TRUNC + */ +enum lock_type { + RENAME, /* for renaming operations */ + DENTRY_OPS, /* for directory operations */ + DATA_WRITE, /* for data write */ + DATA_NEW, /* for data allocation */ + DATA_TRUNC, /* for data truncate */ + NODE_NEW, /* for node allocation */ + NODE_TRUNC, /* for node truncate */ + NODE_WRITE, /* for node write */ + NR_LOCK_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. + */ +enum page_type { + DATA, + NODE, + META, + NR_PAGE_TYPE, + META_FLUSH, +}; + +struct f2fs_sb_info { + struct super_block *sb; /* pointer to VFS super block */ + 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 */ + struct bio *bio[NR_PAGE_TYPE]; /* bios to merge */ + sector_t last_block_in_bio[NR_PAGE_TYPE]; /* last block number */ + struct rw_semaphore bio_sem; /* IO semaphore */ + + /* for checkpoint */ + struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */ + struct inode *meta_inode; /* cache meta blocks */ + struct mutex cp_mutex; /* for checkpoint procedure */ + struct mutex fs_lock[NR_LOCK_TYPE]; /* for blocking FS operations */ + struct mutex write_inode; /* mutex for write inode */ + struct mutex writepages; /* mutex for writepages() */ + int por_doing; /* recovery is doing or not */ + + /* 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 */ + + /* for directory inode management */ + struct list_head dir_inode_list; /* dir inode list */ + spinlock_t dir_inode_lock; /* for dir inode list lock */ + unsigned int n_dirty_dirs; /* # of dir inodes */ + + /* 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 */ + + /* + * for stat information. + * one is for the LFS mode, and the other is for the SSR mode. + */ + 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 */ + unsigned int last_victim[2]; /* last victim segment # */ + int total_hit_ext, read_hit_ext; /* extent cache hit ratio */ + int bg_gc; /* background gc calls */ + spinlock_t stat_lock; /* lock for stat operations */ +}; + +/* + * 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_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 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 mutex_lock_op(struct f2fs_sb_info *sbi, enum lock_type t) +{ + mutex_lock_nested(&sbi->fs_lock[t], t); +} + +static inline void mutex_unlock_op(struct f2fs_sb_info *sbi, enum lock_type t) +{ + mutex_unlock(&sbi->fs_lock[t]); +} + +/* + * Check whether the given nid is within node id range. + */ +static inline void check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) +{ + BUG_ON((nid >= NM_I(sbi)->max_nid)); +} + +#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 (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 int dec_valid_block_count(struct f2fs_sb_info *sbi, + struct inode *inode, + blkcnt_t count) +{ + spin_lock(&sbi->stat_lock); + BUG_ON(sbi->total_valid_block_count < (block_t) count); + BUG_ON(inode->i_blocks < count); + inode->i_blocks -= count; + sbi->total_valid_block_count -= (block_t)count; + spin_unlock(&sbi->stat_lock); + return 0; +} + +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 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 = le64_to_cpu(ckpt->checkpoint_ver); + + 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, + unsigned int count) +{ + block_t valid_block_count; + unsigned int valid_node_count; + + spin_lock(&sbi->stat_lock); + + valid_block_count = sbi->total_valid_block_count + (block_t)count; + sbi->alloc_valid_block_count += (block_t)count; + valid_node_count = sbi->total_valid_node_count + count; + + if (valid_block_count > sbi->user_block_count) { + spin_unlock(&sbi->stat_lock); + return false; + } + + if (valid_node_count > sbi->total_node_count) { + spin_unlock(&sbi->stat_lock); + return false; + } + + if (inode) + inode->i_blocks += count; + sbi->total_valid_node_count = valid_node_count; + sbi->total_valid_block_count = 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, + unsigned int count) +{ + spin_lock(&sbi->stat_lock); + + BUG_ON(sbi->total_valid_block_count < count); + BUG_ON(sbi->total_valid_node_count < count); + BUG_ON(inode->i_blocks < count); + + inode->i_blocks -= count; + sbi->total_valid_node_count -= count; + sbi->total_valid_block_count -= (block_t)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); + BUG_ON(sbi->total_valid_inode_count == sbi->total_node_count); + sbi->total_valid_inode_count++; + spin_unlock(&sbi->stat_lock); +} + +static inline int dec_valid_inode_count(struct f2fs_sb_info *sbi) +{ + spin_lock(&sbi->stat_lock); + BUG_ON(!sbi->total_valid_inode_count); + sbi->total_valid_inode_count--; + spin_unlock(&sbi->stat_lock); + return 0; +} + +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 || IS_ERR(page)) + return; + + if (unlock) { + 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); +} + +#define RAW_IS_INODE(p) ((p)->footer.nid == (p)->footer.ino) + +static inline bool IS_INODE(struct page *page) +{ + struct f2fs_node *p = (struct f2fs_node *)page_address(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 = (struct f2fs_node *)page_address(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_NEED_CP, /* need to do checkpoint during fsync */ + FI_INC_LINK, /* need to increment i_nlink */ + FI_ACL_MODE, /* indicate acl mode */ + FI_NO_ALLOC, /* should not allocate any blocks */ +}; + +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; +} + +/* + * file.c + */ +int f2fs_sync_file(struct file *, loff_t, loff_t, int); +void truncate_data_blocks(struct dnode_of_data *); +void f2fs_truncate(struct inode *); +int f2fs_setattr(struct dentry *, struct iattr *); +int truncate_hole(struct inode *, pgoff_t, pgoff_t); +long f2fs_ioctl(struct file *, unsigned int, unsigned long); + +/* + * inode.c + */ +void f2fs_set_inode_flags(struct inode *); +struct inode *f2fs_iget_nowait(struct super_block *, unsigned long); +struct inode *f2fs_iget(struct super_block *, unsigned long); +void update_inode(struct inode *, struct page *); +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 *); +void init_dent_inode(struct dentry *, struct page *); +int f2fs_add_link(struct dentry *, 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 *); + +/* + * super.c + */ +int f2fs_sync_fs(struct super_block *, int); + +/* + * hash.c + */ +f2fs_hash_t f2fs_dentry_hash(const char *, int); + +/* + * 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 remove_inode_page(struct inode *); +int new_inode_page(struct inode *, struct dentry *); +struct page *new_node_page(struct dnode_of_data *, unsigned int); +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 create_node_manager_caches(void); +void destroy_node_manager_caches(void); + +/* + * segment.c + */ +void f2fs_balance_fs(struct f2fs_sb_info *); +void invalidate_blocks(struct f2fs_sb_info *, block_t); +void locate_dirty_segment(struct f2fs_sb_info *, unsigned int); +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); +struct bio *f2fs_bio_alloc(struct block_device *, int); +void f2fs_submit_bio(struct f2fs_sb_info *, enum page_type, bool sync); +int write_meta_page(struct f2fs_sb_info *, struct page *, + struct writeback_control *); +void write_node_page(struct f2fs_sb_info *, struct page *, unsigned int, + block_t, block_t *); +void write_data_page(struct inode *, struct page *, struct dnode_of_data*, + block_t, block_t *); +void rewrite_data_page(struct f2fs_sb_info *, struct page *, block_t); +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 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 reset_victim_segmap(struct f2fs_sb_info *); +void destroy_segment_manager(struct f2fs_sb_info *); + +/* + * 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 check_orphan_space(struct f2fs_sb_info *); +void add_orphan_inode(struct f2fs_sb_info *, nid_t); +void remove_orphan_inode(struct f2fs_sb_info *, nid_t); +int recover_orphan_inodes(struct f2fs_sb_info *); +int get_valid_checkpoint(struct f2fs_sb_info *); +void set_dirty_dir_page(struct inode *, struct page *); +void remove_dirty_dir_inode(struct inode *); +void sync_dirty_dir_inodes(struct f2fs_sb_info *); +void block_operations(struct f2fs_sb_info *); +void write_checkpoint(struct f2fs_sb_info *, bool, bool); +void init_orphan_info(struct f2fs_sb_info *); +int create_checkpoint_caches(void); +void destroy_checkpoint_caches(void); + +/* + * data.c + */ +int reserve_new_block(struct dnode_of_data *); +void update_extent_cache(block_t, struct dnode_of_data *); +struct page *find_data_page(struct inode *, pgoff_t); +struct page *get_lock_data_page(struct inode *, pgoff_t); +struct page *get_new_data_page(struct inode *, pgoff_t, bool); +int f2fs_readpage(struct f2fs_sb_info *, struct page *, block_t, int); +int do_write_data_page(struct page *); + +/* + * 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); +int f2fs_gc(struct f2fs_sb_info *, int); +void build_gc_manager(struct f2fs_sb_info *); +int create_gc_caches(void); +void destroy_gc_caches(void); + +/* + * recovery.c + */ +void 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; + 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; +}; + +#define stat_inc_call_count(si) ((si)->call_count++) + +#define stat_inc_seg_count(sbi, type) \ + do { \ + struct f2fs_stat_info *si = sbi->stat_info; \ + (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 = sbi->stat_info; \ + 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 = sbi->stat_info; \ + 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 destroy_root_stats(void); +#else +#define stat_inc_call_count(si) +#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 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; +#endif diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c new file mode 100644 index 000000000000..f9e085dfb1f0 --- /dev/null +++ b/fs/f2fs/file.c @@ -0,0 +1,636 @@ +/* + * fs/f2fs/file.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/fs.h> +#include <linux/f2fs_fs.h> +#include <linux/stat.h> +#include <linux/buffer_head.h> +#include <linux/writeback.h> +#include <linux/falloc.h> +#include <linux/types.h> +#include <linux/uaccess.h> +#include <linux/mount.h> + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include "xattr.h" +#include "acl.h" + +static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, + struct vm_fault *vmf) +{ + struct page *page = vmf->page; + struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + block_t old_blk_addr; + struct dnode_of_data dn; + int err; + + f2fs_balance_fs(sbi); + + sb_start_pagefault(inode->i_sb); + + mutex_lock_op(sbi, DATA_NEW); + + /* block allocation */ + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, page->index, 0); + if (err) { + mutex_unlock_op(sbi, DATA_NEW); + goto out; + } + + old_blk_addr = dn.data_blkaddr; + + if (old_blk_addr == NULL_ADDR) { + err = reserve_new_block(&dn); + if (err) { + f2fs_put_dnode(&dn); + mutex_unlock_op(sbi, DATA_NEW); + goto out; + } + } + f2fs_put_dnode(&dn); + + mutex_unlock_op(sbi, DATA_NEW); + + lock_page(page); + if (page->mapping != inode->i_mapping || + page_offset(page) >= i_size_read(inode) || + !PageUptodate(page)) { + unlock_page(page); + err = -EFAULT; + goto out; + } + + /* + * check to see if the page is mapped already (no holes) + */ + if (PageMappedToDisk(page)) + goto out; + + /* fill the page */ + wait_on_page_writeback(page); + + /* page is wholly or partially inside EOF */ + if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) { + unsigned offset; + offset = i_size_read(inode) & ~PAGE_CACHE_MASK; + zero_user_segment(page, offset, PAGE_CACHE_SIZE); + } + set_page_dirty(page); + SetPageUptodate(page); + + file_update_time(vma->vm_file); +out: + sb_end_pagefault(inode->i_sb); + return block_page_mkwrite_return(err); +} + +static const struct vm_operations_struct f2fs_file_vm_ops = { + .fault = filemap_fault, + .page_mkwrite = f2fs_vm_page_mkwrite, +}; + +static int need_to_sync_dir(struct f2fs_sb_info *sbi, struct inode *inode) +{ + struct dentry *dentry; + nid_t pino; + + inode = igrab(inode); + dentry = d_find_any_alias(inode); + if (!dentry) { + iput(inode); + return 0; + } + pino = dentry->d_parent->d_inode->i_ino; + dput(dentry); + iput(inode); + return !is_checkpointed_node(sbi, pino); +} + +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); + unsigned long long cur_version; + int ret = 0; + bool need_cp = false; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = LONG_MAX, + .for_reclaim = 0, + }; + + if (inode->i_sb->s_flags & MS_RDONLY) + return 0; + + ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (ret) + return ret; + + mutex_lock(&inode->i_mutex); + + if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) + goto out; + + mutex_lock(&sbi->cp_mutex); + cur_version = le64_to_cpu(F2FS_CKPT(sbi)->checkpoint_ver); + mutex_unlock(&sbi->cp_mutex); + + if (F2FS_I(inode)->data_version != cur_version && + !(inode->i_state & I_DIRTY)) + goto out; + F2FS_I(inode)->data_version--; + + if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1) + need_cp = true; + if (is_inode_flag_set(F2FS_I(inode), FI_NEED_CP)) + need_cp = true; + if (!space_for_roll_forward(sbi)) + need_cp = true; + if (need_to_sync_dir(sbi, inode)) + need_cp = true; + + f2fs_write_inode(inode, NULL); + + if (need_cp) { + /* all the dirty node pages should be flushed for POR */ + ret = f2fs_sync_fs(inode->i_sb, 1); + clear_inode_flag(F2FS_I(inode), FI_NEED_CP); + } else { + while (sync_node_pages(sbi, inode->i_ino, &wbc) == 0) + f2fs_write_inode(inode, NULL); + filemap_fdatawait_range(sbi->node_inode->i_mapping, + 0, LONG_MAX); + } +out: + mutex_unlock(&inode->i_mutex); + return ret; +} + +static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) +{ + file_accessed(file); + vma->vm_ops = &f2fs_file_vm_ops; + return 0; +} + +static int truncate_data_blocks_range(struct dnode_of_data *dn, int count) +{ + int nr_free = 0, ofs = dn->ofs_in_node; + struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb); + struct f2fs_node *raw_node; + __le32 *addr; + + raw_node = page_address(dn->node_page); + addr = blkaddr_in_node(raw_node) + ofs; + + for ( ; count > 0; count--, addr++, dn->ofs_in_node++) { + block_t blkaddr = le32_to_cpu(*addr); + if (blkaddr == NULL_ADDR) + continue; + + update_extent_cache(NULL_ADDR, dn); + invalidate_blocks(sbi, blkaddr); + dec_valid_block_count(sbi, dn->inode, 1); + nr_free++; + } + if (nr_free) { + set_page_dirty(dn->node_page); + sync_inode_page(dn); + } + dn->ofs_in_node = ofs; + 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); + if (IS_ERR(page)) + return; + + lock_page(page); + wait_on_page_writeback(page); + zero_user(page, offset, PAGE_CACHE_SIZE - offset); + set_page_dirty(page); + f2fs_put_page(page, 1); +} + +static int truncate_blocks(struct inode *inode, u64 from) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + unsigned int blocksize = inode->i_sb->s_blocksize; + struct dnode_of_data dn; + pgoff_t free_from; + int count = 0; + int err; + + free_from = (pgoff_t) + ((from + blocksize - 1) >> (sbi->log_blocksize)); + + mutex_lock_op(sbi, DATA_TRUNC); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, free_from, RDONLY_NODE); + if (err) { + if (err == -ENOENT) + goto free_next; + mutex_unlock_op(sbi, DATA_TRUNC); + return err; + } + + if (IS_INODE(dn.node_page)) + count = ADDRS_PER_INODE; + else + count = ADDRS_PER_BLOCK; + + count -= dn.ofs_in_node; + BUG_ON(count < 0); + if (dn.ofs_in_node || IS_INODE(dn.node_page)) { + truncate_data_blocks_range(&dn, count); + free_from += count; + } + + f2fs_put_dnode(&dn); +free_next: + err = truncate_inode_blocks(inode, free_from); + mutex_unlock_op(sbi, DATA_TRUNC); + + /* lastly zero out the first data page */ + truncate_partial_data_page(inode, from); + + 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; + + if (!truncate_blocks(inode, i_size_read(inode))) { + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(inode); + } + + f2fs_balance_fs(F2FS_SB(inode->i_sb)); +} + +static int f2fs_getattr(struct vfsmount *mnt, + struct dentry *dentry, struct kstat *stat) +{ + struct inode *inode = dentry->d_inode; + generic_fillattr(inode, stat); + stat->blocks <<= 3; + return 0; +} + +#ifdef CONFIG_F2FS_FS_POSIX_ACL +static void __setattr_copy(struct inode *inode, const struct iattr *attr) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + unsigned int ia_valid = attr->ia_valid; + + if (ia_valid & ATTR_UID) + inode->i_uid = attr->ia_uid; + if (ia_valid & ATTR_GID) + inode->i_gid = attr->ia_gid; + if (ia_valid & ATTR_ATIME) + inode->i_atime = timespec_trunc(attr->ia_atime, + inode->i_sb->s_time_gran); + if (ia_valid & ATTR_MTIME) + inode->i_mtime = timespec_trunc(attr->ia_mtime, + inode->i_sb->s_time_gran); + if (ia_valid & ATTR_CTIME) + inode->i_ctime = timespec_trunc(attr->ia_ctime, + inode->i_sb->s_time_gran); + if (ia_valid & ATTR_MODE) { + umode_t mode = attr->ia_mode; + + if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) + mode &= ~S_ISGID; + set_acl_inode(fi, mode); + } +} +#else +#define __setattr_copy setattr_copy +#endif + +int f2fs_setattr(struct dentry *dentry, struct iattr *attr) +{ + struct inode *inode = dentry->d_inode; + struct f2fs_inode_info *fi = F2FS_I(inode); + int err; + + err = inode_change_ok(inode, attr); + if (err) + return err; + + if ((attr->ia_valid & ATTR_SIZE) && + attr->ia_size != i_size_read(inode)) { + truncate_setsize(inode, attr->ia_size); + f2fs_truncate(inode); + } + + __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 page *page; + + if (!len) + return; + + page = get_new_data_page(inode, index, false); + + 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; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + + mutex_lock_op(sbi, DATA_TRUNC); + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = get_dnode_of_data(&dn, index, RDONLY_NODE); + if (err) { + mutex_unlock_op(sbi, DATA_TRUNC); + if (err == -ENOENT) + continue; + return err; + } + + if (dn.data_blkaddr != NULL_ADDR) + truncate_data_blocks_range(&dn, 1); + f2fs_put_dnode(&dn); + mutex_unlock_op(sbi, DATA_TRUNC); + } + return 0; +} + +static int punch_hole(struct inode *inode, loff_t offset, loff_t len, int mode) +{ + pgoff_t pg_start, pg_end; + loff_t off_start, off_end; + int ret = 0; + + pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; + pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; + + off_start = offset & (PAGE_CACHE_SIZE - 1); + off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + + if (pg_start == pg_end) { + fill_zero(inode, pg_start, off_start, + off_end - off_start); + } else { + if (off_start) + fill_zero(inode, pg_start++, off_start, + PAGE_CACHE_SIZE - off_start); + if (off_end) + fill_zero(inode, pg_end, 0, off_end); + + if (pg_start < pg_end) { + struct address_space *mapping = inode->i_mapping; + loff_t blk_start, blk_end; + + blk_start = pg_start << PAGE_CACHE_SHIFT; + blk_end = pg_end << PAGE_CACHE_SHIFT; + truncate_inode_pages_range(mapping, blk_start, + blk_end - 1); + ret = truncate_hole(inode, pg_start, pg_end); + } + } + + if (!(mode & FALLOC_FL_KEEP_SIZE) && + i_size_read(inode) <= (offset + len)) { + i_size_write(inode, offset); + mark_inode_dirty(inode); + } + + return ret; +} + +static int expand_inode_data(struct inode *inode, loff_t offset, + loff_t len, int mode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + pgoff_t index, pg_start, pg_end; + loff_t new_size = i_size_read(inode); + loff_t off_start, off_end; + int ret = 0; + + ret = inode_newsize_ok(inode, (len + offset)); + if (ret) + return ret; + + pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT; + pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT; + + off_start = offset & (PAGE_CACHE_SIZE - 1); + off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + + for (index = pg_start; index <= pg_end; index++) { + struct dnode_of_data dn; + + mutex_lock_op(sbi, DATA_NEW); + + set_new_dnode(&dn, inode, NULL, NULL, 0); + ret = get_dnode_of_data(&dn, index, 0); + if (ret) { + mutex_unlock_op(sbi, DATA_NEW); + break; + } + + if (dn.data_blkaddr == NULL_ADDR) { + ret = reserve_new_block(&dn); + if (ret) { + f2fs_put_dnode(&dn); + mutex_unlock_op(sbi, DATA_NEW); + break; + } + } + f2fs_put_dnode(&dn); + + mutex_unlock_op(sbi, DATA_NEW); + + 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->f_path.dentry->d_inode; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + long ret; + + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + return -EOPNOTSUPP; + + if (mode & FALLOC_FL_PUNCH_HOLE) + ret = punch_hole(inode, offset, len, mode); + else + ret = expand_inode_data(inode, offset, len, mode); + + f2fs_balance_fs(sbi); + 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 = filp->f_dentry->d_inode; + struct f2fs_inode_info *fi = F2FS_I(inode); + unsigned int flags; + int ret; + + switch (cmd) { + case FS_IOC_GETFLAGS: + flags = fi->i_flags & FS_FL_USER_VISIBLE; + return put_user(flags, (int __user *) arg); + case FS_IOC_SETFLAGS: + { + unsigned int oldflags; + + ret = mnt_want_write(filp->f_path.mnt); + 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(filp->f_path.mnt); + return ret; + } + default: + return -ENOTTY; + } +} + +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, + .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 000000000000..644aa3808273 --- /dev/null +++ b/fs/f2fs/gc.c @@ -0,0 +1,742 @@ +/* + * fs/f2fs/gc.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/fs.h> +#include <linux/module.h> +#include <linux/backing-dev.h> +#include <linux/proc_fs.h> +#include <linux/init.h> +#include <linux/f2fs_fs.h> +#include <linux/kthread.h> +#include <linux/delay.h> +#include <linux/freezer.h> +#include <linux/blkdev.h> + +#include "f2fs.h" +#include "node.h" +#include "segment.h" +#include "gc.h" + +static struct kmem_cache *winode_slab; + +static int gc_thread_func(void *data) +{ + struct f2fs_sb_info *sbi = data; + wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head; + long wait_ms; + + wait_ms = GC_THREAD_MIN_SLEEP_TIME; + + do { + if (try_to_freeze()) + continue; + else + wait_event_interruptible_timeout(*wq, + kthread_should_stop(), + msecs_to_jiffies(wait_ms)); + if (kthread_should_stop()) + break; + + f2fs_balance_fs(sbi); + + if (!test_opt(sbi, BG_GC)) + continue; + + /* + * [GC triggering condition] + * 0. GC is not conducted currently. + * 1. There are enough dirty segments. + * 2. IO subsystem is idle by checking the # of writeback pages. + * 3. IO subsystem is idle by checking the # of requests in + * bdev's request list. + * + * Note) We have to avoid triggering GCs too much frequently. + * Because it is possible that some segments can be + * invalidated soon after by user update or deletion. + * So, I'd like to wait some time to collect dirty segments. + */ + if (!mutex_trylock(&sbi->gc_mutex)) + continue; + + if (!is_idle(sbi)) { + wait_ms = increase_sleep_time(wait_ms); + mutex_unlock(&sbi->gc_mutex); + continue; + } + + if (has_enough_invalid_blocks(sbi)) + wait_ms = decrease_sleep_time(wait_ms); + else + wait_ms = increase_sleep_time(wait_ms); + + sbi->bg_gc++; + + if (f2fs_gc(sbi, 1) == GC_NONE) + wait_ms = GC_THREAD_NOGC_SLEEP_TIME; + else if (wait_ms == GC_THREAD_NOGC_SLEEP_TIME) + wait_ms = GC_THREAD_MAX_SLEEP_TIME; + + } while (!kthread_should_stop()); + return 0; +} + +int start_gc_thread(struct f2fs_sb_info *sbi) +{ + struct f2fs_gc_kthread *gc_th; + + gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL); + if (!gc_th) + return -ENOMEM; + + sbi->gc_thread = gc_th; + init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head); + sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi, + GC_THREAD_NAME); + if (IS_ERR(gc_th->f2fs_gc_task)) { + kfree(gc_th); + return -ENOMEM; + } + return 0; +} + +void stop_gc_thread(struct f2fs_sb_info *sbi) +{ + struct f2fs_gc_kthread *gc_th = sbi->gc_thread; + if (!gc_th) + return; + kthread_stop(gc_th->f2fs_gc_task); + kfree(gc_th); + sbi->gc_thread = NULL; +} + +static int select_gc_type(int gc_type) +{ + return (gc_type == BG_GC) ? GC_CB : GC_GREEDY; +} + +static void select_policy(struct f2fs_sb_info *sbi, int gc_type, + int type, struct victim_sel_policy *p) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + + if (p->alloc_mode) { + p->gc_mode = GC_GREEDY; + p->dirty_segmap = dirty_i->dirty_segmap[type]; + p->ofs_unit = 1; + } else { + p->gc_mode = select_gc_type(gc_type); + p->dirty_segmap = dirty_i->dirty_segmap[DIRTY]; + p->ofs_unit = sbi->segs_per_sec; + } + p->offset = sbi->last_victim[p->gc_mode]; +} + +static unsigned int get_max_cost(struct f2fs_sb_info *sbi, + struct victim_sel_policy *p) +{ + 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 segno; + + /* + * 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. + */ + segno = find_next_bit(dirty_i->victim_segmap[BG_GC], + TOTAL_SEGS(sbi), 0); + if (segno < TOTAL_SEGS(sbi)) { + clear_bit(segno, dirty_i->victim_segmap[BG_GC]); + return segno; + } + return NULL_SEGNO; +} + +static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno) +{ + struct sit_info *sit_i = SIT_I(sbi); + unsigned int secno = GET_SECNO(sbi, segno); + unsigned int start = secno * sbi->segs_per_sec; + unsigned long long mtime = 0; + unsigned int vblocks; + unsigned char age = 0; + unsigned char u; + unsigned int i; + + for (i = 0; i < sbi->segs_per_sec; i++) + mtime += get_seg_entry(sbi, start + i)->mtime; + vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec); + + mtime = div_u64(mtime, sbi->segs_per_sec); + vblocks = div_u64(vblocks, sbi->segs_per_sec); + + u = (vblocks * 100) >> sbi->log_blocks_per_seg; + + /* Handle if the system time is changed by user */ + if (mtime < sit_i->min_mtime) + sit_i->min_mtime = mtime; + if (mtime > sit_i->max_mtime) + sit_i->max_mtime = mtime; + if (sit_i->max_mtime != sit_i->min_mtime) + age = 100 - div64_u64(100 * (mtime - sit_i->min_mtime), + sit_i->max_mtime - sit_i->min_mtime); + + return UINT_MAX - ((100 * (100 - u) * age) / (100 + u)); +} + +static unsigned int get_gc_cost(struct f2fs_sb_info *sbi, unsigned int segno, + struct victim_sel_policy *p) +{ + if (p->alloc_mode == SSR) + return get_seg_entry(sbi, segno)->ckpt_valid_blocks; + + /* alloc_mode == LFS */ + if (p->gc_mode == GC_GREEDY) + return get_valid_blocks(sbi, segno, sbi->segs_per_sec); + else + return get_cb_cost(sbi, segno); +} + +/* + * This function is called from two pathes. + * 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 segno; + int nsearched = 0; + + p.alloc_mode = alloc_mode; + select_policy(sbi, gc_type, type, &p); + + p.min_segno = NULL_SEGNO; + p.min_cost = get_max_cost(sbi, &p); + + mutex_lock(&dirty_i->seglist_lock); + + if (p.alloc_mode == LFS && gc_type == FG_GC) { + p.min_segno = check_bg_victims(sbi); + if (p.min_segno != NULL_SEGNO) + goto got_it; + } + + while (1) { + unsigned long cost; + + segno = find_next_bit(p.dirty_segmap, + TOTAL_SEGS(sbi), p.offset); + if (segno >= TOTAL_SEGS(sbi)) { + if (sbi->last_victim[p.gc_mode]) { + sbi->last_victim[p.gc_mode] = 0; + p.offset = 0; + continue; + } + break; + } + p.offset = ((segno / p.ofs_unit) * p.ofs_unit) + p.ofs_unit; + + if (test_bit(segno, dirty_i->victim_segmap[FG_GC])) + continue; + if (gc_type == BG_GC && + test_bit(segno, dirty_i->victim_segmap[BG_GC])) + continue; + if (IS_CURSEC(sbi, GET_SECNO(sbi, segno))) + continue; + + cost = get_gc_cost(sbi, segno, &p); + + if (p.min_cost > cost) { + p.min_segno = segno; + p.min_cost = cost; + } + + if (cost == get_max_cost(sbi, &p)) + continue; + + if (nsearched++ >= MAX_VICTIM_SEARCH) { + sbi->last_victim[p.gc_mode] = segno; + break; + } + } +got_it: + if (p.min_segno != NULL_SEGNO) { + *result = (p.min_segno / p.ofs_unit) * p.ofs_unit; + if (p.alloc_mode == LFS) { + int i; + for (i = 0; i < p.ofs_unit; i++) + set_bit(*result + i, + dirty_i->victim_segmap[gc_type]); + } + } + mutex_unlock(&dirty_i->seglist_lock); + + return (p.min_segno == NULL_SEGNO) ? 0 : 1; +} + +static const struct victim_selection default_v_ops = { + .get_victim = get_victim_by_default, +}; + +static struct inode *find_gc_inode(nid_t ino, struct list_head *ilist) +{ + struct list_head *this; + struct inode_entry *ie; + + list_for_each(this, ilist) { + ie = list_entry(this, struct inode_entry, list); + if (ie->inode->i_ino == ino) + return ie->inode; + } + return NULL; +} + +static void add_gc_inode(struct inode *inode, struct list_head *ilist) +{ + struct list_head *this; + struct inode_entry *new_ie, *ie; + + list_for_each(this, ilist) { + ie = list_entry(this, struct inode_entry, list); + if (ie->inode == inode) { + iput(inode); + return; + } + } +repeat: + new_ie = kmem_cache_alloc(winode_slab, GFP_NOFS); + if (!new_ie) { + cond_resched(); + goto repeat; + } + new_ie->inode = inode; + list_add_tail(&new_ie->list, ilist); +} + +static void put_gc_inode(struct list_head *ilist) +{ + struct inode_entry *ie, *next_ie; + list_for_each_entry_safe(ie, next_ie, ilist, list) { + iput(ie->inode); + list_del(&ie->list); + kmem_cache_free(winode_slab, ie); + } +} + +static int check_valid_map(struct f2fs_sb_info *sbi, + unsigned int segno, int offset) +{ + struct sit_info *sit_i = SIT_I(sbi); + struct seg_entry *sentry; + int ret; + + mutex_lock(&sit_i->sentry_lock); + sentry = get_seg_entry(sbi, segno); + ret = f2fs_test_bit(offset, sentry->cur_valid_map); + mutex_unlock(&sit_i->sentry_lock); + return ret ? GC_OK : GC_NEXT; +} + +/* + * This function compares node address got in summary with that in NAT. + * On validity, copy that node with cold status, otherwise (invalid node) + * ignore that. + */ +static int gc_node_segment(struct f2fs_sb_info *sbi, + struct f2fs_summary *sum, unsigned int segno, int gc_type) +{ + bool initial = true; + struct f2fs_summary *entry; + 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; + int err; + + /* + * It makes sure that free segments are able to write + * all the dirty node pages before CP after this CP. + * So let's check the space of dirty node pages. + */ + if (should_do_checkpoint(sbi)) { + mutex_lock(&sbi->cp_mutex); + block_operations(sbi); + return GC_BLOCKED; + } + + err = check_valid_map(sbi, segno, off); + if (err == GC_ERROR) + return err; + else if (err == GC_NEXT) + 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 (!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); + } + return GC_DONE; +} + +/* + * Calculate start block index that this node page contains + */ +block_t start_bidx_of_node(unsigned int node_ofs) +{ + block_t start_bidx; + unsigned int bidx, indirect_blks; + int dec; + + indirect_blks = 2 * NIDS_PER_BLOCK + 4; + + start_bidx = 1; + if (node_ofs == 0) { + start_bidx = 0; + } else if (node_ofs <= 2) { + bidx = node_ofs - 1; + } else if (node_ofs <= indirect_blks) { + dec = (node_ofs - 4) / (NIDS_PER_BLOCK + 1); + bidx = node_ofs - 2 - dec; + } else { + dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1); + bidx = node_ofs - 5 - dec; + } + + if (start_bidx) + start_bidx = bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE; + return start_bidx; +} + +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 GC_NEXT; + + get_node_info(sbi, nid, dni); + + if (sum->version != dni->version) { + f2fs_put_page(node_page, 1); + return GC_NEXT; + } + + *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 GC_NEXT; + return GC_OK; +} + +static void move_data_page(struct inode *inode, struct page *page, int gc_type) +{ + if (page->mapping != inode->i_mapping) + goto out; + + if (inode != page->mapping->host) + goto out; + + if (PageWriteback(page)) + goto out; + + if (gc_type == BG_GC) { + set_page_dirty(page); + set_cold_data(page); + } else { + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + mutex_lock_op(sbi, DATA_WRITE); + 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); + mutex_unlock_op(sbi, DATA_WRITE); + clear_cold_data(page); + } +out: + f2fs_put_page(page, 1); +} + +/* + * This function tries to get parent node of victim data block, and identifies + * data block validity. If the block is valid, copy that with cold status and + * modify parent node. + * If the parent node is not valid or the data block address is different, + * the victim data block is ignored. + */ +static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, + struct list_head *ilist, unsigned int segno, int gc_type) +{ + struct super_block *sb = sbi->sb; + struct f2fs_summary *entry; + block_t start_addr; + int err, 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; + + /* + * It makes sure that free segments are able to write + * all the dirty node pages before CP after this CP. + * So let's check the space of dirty node pages. + */ + if (should_do_checkpoint(sbi)) { + mutex_lock(&sbi->cp_mutex); + block_operations(sbi); + err = GC_BLOCKED; + goto stop; + } + + err = check_valid_map(sbi, segno, off); + if (err == GC_ERROR) + goto stop; + else if (err == GC_NEXT) + continue; + + if (phase == 0) { + ra_node_page(sbi, le32_to_cpu(entry->nid)); + continue; + } + + /* Get an inode by ino with checking validity */ + err = check_dnode(sbi, entry, &dni, start_addr + off, &nofs); + if (err == GC_ERROR) + goto stop; + else if (err == GC_NEXT) + continue; + + if (phase == 1) { + ra_node_page(sbi, dni.ino); + continue; + } + + start_bidx = start_bidx_of_node(nofs); + ofs_in_node = le16_to_cpu(entry->ofs_in_node); + + if (phase == 2) { + inode = f2fs_iget_nowait(sb, dni.ino); + if (IS_ERR(inode)) + continue; + + data_page = find_data_page(inode, + start_bidx + ofs_in_node); + if (IS_ERR(data_page)) + goto next_iput; + + f2fs_put_page(data_page, 0); + add_gc_inode(inode, ilist); + } else { + inode = find_gc_inode(dni.ino, ilist); + if (inode) { + data_page = get_lock_data_page(inode, + start_bidx + ofs_in_node); + if (IS_ERR(data_page)) + continue; + move_data_page(inode, data_page, gc_type); + stat_inc_data_blk_count(sbi, 1); + } + } + continue; +next_iput: + iput(inode); + } + if (++phase < 4) + goto next_step; + err = GC_DONE; +stop: + if (gc_type == FG_GC) + f2fs_submit_bio(sbi, DATA, true); + return err; +} + +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 int 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; + int ret = GC_DONE; + + /* read segment summary of victim */ + sum_page = get_sum_page(sbi, segno); + if (IS_ERR(sum_page)) + return GC_ERROR; + + /* + * CP needs to lock sum_page. In this time, we don't need + * to lock this page, because this summary page is not gone anywhere. + * Also, this page is not gonna be updated before GC is done. + */ + unlock_page(sum_page); + sum = page_address(sum_page); + + switch (GET_SUM_TYPE((&sum->footer))) { + case SUM_TYPE_NODE: + ret = gc_node_segment(sbi, sum->entries, segno, gc_type); + break; + case SUM_TYPE_DATA: + ret = gc_data_segment(sbi, sum->entries, ilist, segno, gc_type); + break; + } + stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer))); + stat_inc_call_count(sbi->stat_info); + + f2fs_put_page(sum_page, 0); + return ret; +} + +int f2fs_gc(struct f2fs_sb_info *sbi, int nGC) +{ + unsigned int segno; + int old_free_secs, cur_free_secs; + int gc_status, nfree; + struct list_head ilist; + int gc_type = BG_GC; + + INIT_LIST_HEAD(&ilist); +gc_more: + nfree = 0; + gc_status = GC_NONE; + + if (has_not_enough_free_secs(sbi)) + old_free_secs = reserved_sections(sbi); + else + old_free_secs = free_sections(sbi); + + while (sbi->sb->s_flags & MS_ACTIVE) { + int i; + if (has_not_enough_free_secs(sbi)) + gc_type = FG_GC; + + cur_free_secs = free_sections(sbi) + nfree; + + /* We got free space successfully. */ + if (nGC < cur_free_secs - old_free_secs) + break; + + if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE)) + break; + + for (i = 0; i < sbi->segs_per_sec; i++) { + /* + * do_garbage_collect will give us three gc_status: + * GC_ERROR, GC_DONE, and GC_BLOCKED. + * If GC is finished uncleanly, we have to return + * the victim to dirty segment list. + */ + gc_status = do_garbage_collect(sbi, segno + i, + &ilist, gc_type); + if (gc_status != GC_DONE) + goto stop; + nfree++; + } + } +stop: + if (has_not_enough_free_secs(sbi) || gc_status == GC_BLOCKED) { + write_checkpoint(sbi, (gc_status == GC_BLOCKED), false); + if (nfree) + goto gc_more; + } + mutex_unlock(&sbi->gc_mutex); + + put_gc_inode(&ilist); + BUG_ON(!list_empty(&ilist)); + return gc_status; +} + +void build_gc_manager(struct f2fs_sb_info *sbi) +{ + DIRTY_I(sbi)->v_ops = &default_v_ops; +} + +int 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 000000000000..b026d9354ccd --- /dev/null +++ b/fs/f2fs/gc.h @@ -0,0 +1,117 @@ +/* + * 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_NAME "f2fs_gc_task" +#define GC_THREAD_MIN_WB_PAGES 1 /* + * a threshold to determine + * whether IO subsystem is idle + * or not + */ +#define GC_THREAD_MIN_SLEEP_TIME 10000 /* milliseconds */ +#define GC_THREAD_MAX_SLEEP_TIME 30000 +#define GC_THREAD_NOGC_SLEEP_TIME 10000 +#define LIMIT_INVALID_BLOCK 40 /* percentage over total user space */ +#define LIMIT_FREE_BLOCK 40 /* percentage over invalid + free space */ + +/* Search max. number of dirty segments to select a victim segment */ +#define MAX_VICTIM_SEARCH 20 + +enum { + GC_NONE = 0, + GC_ERROR, + GC_OK, + GC_NEXT, + GC_BLOCKED, + GC_DONE, +}; + +struct f2fs_gc_kthread { + struct task_struct *f2fs_gc_task; + wait_queue_head_t gc_wait_queue_head; +}; + +struct inode_entry { + struct list_head list; + struct inode *inode; +}; + +/* + * inline functions + */ +static inline block_t free_user_blocks(struct f2fs_sb_info *sbi) +{ + if (free_segments(sbi) < overprovision_segments(sbi)) + return 0; + else + return (free_segments(sbi) - overprovision_segments(sbi)) + << sbi->log_blocks_per_seg; +} + +static inline block_t limit_invalid_user_blocks(struct f2fs_sb_info *sbi) +{ + return (long)(sbi->user_block_count * LIMIT_INVALID_BLOCK) / 100; +} + +static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi) +{ + block_t reclaimable_user_blocks = sbi->user_block_count - + written_block_count(sbi); + return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100; +} + +static inline long increase_sleep_time(long wait) +{ + wait += GC_THREAD_MIN_SLEEP_TIME; + if (wait > GC_THREAD_MAX_SLEEP_TIME) + wait = GC_THREAD_MAX_SLEEP_TIME; + return wait; +} + +static inline long decrease_sleep_time(long wait) +{ + wait -= GC_THREAD_MIN_SLEEP_TIME; + if (wait <= GC_THREAD_MIN_SLEEP_TIME) + wait = GC_THREAD_MIN_SLEEP_TIME; + return wait; +} + +static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi) +{ + block_t invalid_user_blocks = sbi->user_block_count - + written_block_count(sbi); + /* + * Background GC is triggered with the following condition. + * 1. There are a number of invalid blocks. + * 2. There is not enough free space. + */ + if (invalid_user_blocks > limit_invalid_user_blocks(sbi) && + free_user_blocks(sbi) < limit_free_user_blocks(sbi)) + return true; + return false; +} + +static inline int is_idle(struct f2fs_sb_info *sbi) +{ + struct block_device *bdev = sbi->sb->s_bdev; + struct request_queue *q = bdev_get_queue(bdev); + struct request_list *rl = &q->root_rl; + return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]); +} + +static inline bool should_do_checkpoint(struct f2fs_sb_info *sbi) +{ + unsigned int pages_per_sec = sbi->segs_per_sec * + (1 << sbi->log_blocks_per_seg); + int node_secs = ((get_pages(sbi, F2FS_DIRTY_NODES) + pages_per_sec - 1) + >> sbi->log_blocks_per_seg) / sbi->segs_per_sec; + int dent_secs = ((get_pages(sbi, F2FS_DIRTY_DENTS) + pages_per_sec - 1) + >> sbi->log_blocks_per_seg) / sbi->segs_per_sec; + return free_sections(sbi) <= (node_secs + 2 * dent_secs + 2); +} diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c new file mode 100644 index 000000000000..a60f04200f8b --- /dev/null +++ b/fs/f2fs/hash.c @@ -0,0 +1,97 @@ +/* + * fs/f2fs/hash.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * Portions of this code from linux/fs/ext3/hash.c + * + * Copyright (C) 2002 by Theodore Ts'o + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/types.h> +#include <linux/fs.h> +#include <linux/f2fs_fs.h> +#include <linux/cryptohash.h> +#include <linux/pagemap.h> + +#include "f2fs.h" + +/* + * Hashing code copied from ext3 + */ +#define DELTA 0x9E3779B9 + +static void TEA_transform(unsigned int buf[4], unsigned int const in[]) +{ + __u32 sum = 0; + __u32 b0 = buf[0], b1 = buf[1]; + __u32 a = in[0], b = in[1], c = in[2], d = in[3]; + int n = 16; + + do { + sum += DELTA; + b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b); + b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d); + } while (--n); + + buf[0] += b0; + buf[1] += b1; +} + +static void str2hashbuf(const char *msg, int 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, int len) +{ + __u32 hash, minor_hash; + f2fs_hash_t f2fs_hash; + const char *p; + __u32 in[8], buf[4]; + + /* Initialize the default seed for the hash checksum functions */ + buf[0] = 0x67452301; + buf[1] = 0xefcdab89; + buf[2] = 0x98badcfe; + buf[3] = 0x10325476; + + p = name; + while (len > 0) { + str2hashbuf(p, len, in, 4); + TEA_transform(buf, in); + len -= 16; + p += 16; + } + hash = buf[0]; + minor_hash = buf[1]; + + f2fs_hash = cpu_to_le32(hash & ~F2FS_HASH_COL_BIT); + return f2fs_hash; +} diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c new file mode 100644 index 000000000000..df5fb381ebf1 --- /dev/null +++ b/fs/f2fs/inode.c @@ -0,0 +1,268 @@ +/* + * fs/f2fs/inode.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/fs.h> +#include <linux/f2fs_fs.h> +#include <linux/buffer_head.h> +#include <linux/writeback.h> + +#include "f2fs.h" +#include "node.h" + +struct f2fs_iget_args { + u64 ino; + int on_free; +}; + +void f2fs_set_inode_flags(struct inode *inode) +{ + unsigned int flags = F2FS_I(inode)->i_flags; + + inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | + S_NOATIME | S_DIRSYNC); + + if (flags & FS_SYNC_FL) + inode->i_flags |= S_SYNC; + if (flags & FS_APPEND_FL) + inode->i_flags |= S_APPEND; + if (flags & FS_IMMUTABLE_FL) + inode->i_flags |= S_IMMUTABLE; + if (flags & FS_NOATIME_FL) + inode->i_flags |= S_NOATIME; + if (flags & FS_DIRSYNC_FL) + inode->i_flags |= S_DIRSYNC; +} + +static int f2fs_iget_test(struct inode *inode, void *data) +{ + struct f2fs_iget_args *args = data; + + if (inode->i_ino != args->ino) + return 0; + if (inode->i_state & (I_FREEING | I_WILL_FREE)) { + args->on_free = 1; + return 0; + } + return 1; +} + +struct inode *f2fs_iget_nowait(struct super_block *sb, unsigned long ino) +{ + struct f2fs_iget_args args = { + .ino = ino, + .on_free = 0 + }; + struct inode *inode = ilookup5(sb, ino, f2fs_iget_test, &args); + + if (inode) + return inode; + if (!args.on_free) + return f2fs_iget(sb, ino); + return ERR_PTR(-ENOENT); +} + +static int do_read_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct page *node_page; + struct f2fs_node *rn; + struct f2fs_inode *ri; + + /* Check if ino is within scope */ + check_nid_range(sbi, inode->i_ino); + + node_page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(node_page)) + return PTR_ERR(node_page); + + rn = page_address(node_page); + ri = &(rn->i); + + inode->i_mode = le16_to_cpu(ri->i_mode); + i_uid_write(inode, le32_to_cpu(ri->i_uid)); + i_gid_write(inode, le32_to_cpu(ri->i_gid)); + set_nlink(inode, le32_to_cpu(ri->i_links)); + inode->i_size = le64_to_cpu(ri->i_size); + inode->i_blocks = le64_to_cpu(ri->i_blocks); + + inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime); + inode->i_ctime.tv_sec = le64_to_cpu(ri->i_ctime); + inode->i_mtime.tv_sec = le64_to_cpu(ri->i_mtime); + inode->i_atime.tv_nsec = le32_to_cpu(ri->i_atime_nsec); + inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec); + inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec); + inode->i_generation = le32_to_cpu(ri->i_generation); + + 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->data_version = le64_to_cpu(F2FS_CKPT(sbi)->checkpoint_ver) - 1; + fi->i_advise = ri->i_advise; + fi->i_pino = le32_to_cpu(ri->i_pino); + get_extent_info(&fi->ext, ri->i_ext); + f2fs_put_page(node_page, 1); + return 0; +} + +struct inode *f2fs_iget(struct super_block *sb, unsigned long ino) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct inode *inode; + int ret; + + inode = iget_locked(sb, ino); + if (!inode) + return ERR_PTR(-ENOMEM); + if (!(inode->i_state & I_NEW)) + return inode; + if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi)) + goto make_now; + + ret = do_read_inode(inode); + if (ret) + goto bad_inode; + + if (!sbi->por_doing && inode->i_nlink == 0) { + ret = -ENOENT; + goto bad_inode; + } + +make_now: + if (ino == F2FS_NODE_INO(sbi)) { + inode->i_mapping->a_ops = &f2fs_node_aops; + mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO); + } else if (ino == F2FS_META_INO(sbi)) { + inode->i_mapping->a_ops = &f2fs_meta_aops; + mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO); + } else if (S_ISREG(inode->i_mode)) { + inode->i_op = &f2fs_file_inode_operations; + inode->i_fop = &f2fs_file_operations; + inode->i_mapping->a_ops = &f2fs_dblock_aops; + } else if (S_ISDIR(inode->i_mode)) { + inode->i_op = &f2fs_dir_inode_operations; + inode->i_fop = &f2fs_dir_operations; + inode->i_mapping->a_ops = &f2fs_dblock_aops; + mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER_MOVABLE | + __GFP_ZERO); + } else if (S_ISLNK(inode->i_mode)) { + inode->i_op = &f2fs_symlink_inode_operations; + inode->i_mapping->a_ops = &f2fs_dblock_aops; + } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || + S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { + inode->i_op = &f2fs_special_inode_operations; + init_special_inode(inode, inode->i_mode, inode->i_rdev); + } else { + ret = -EIO; + goto bad_inode; + } + unlock_new_inode(inode); + + return inode; + +bad_inode: + iget_failed(inode); + return ERR_PTR(ret); +} + +void update_inode(struct inode *inode, struct page *node_page) +{ + struct f2fs_node *rn; + struct f2fs_inode *ri; + + wait_on_page_writeback(node_page); + + rn = page_address(node_page); + ri = &(rn->i); + + ri->i_mode = cpu_to_le16(inode->i_mode); + ri->i_advise = F2FS_I(inode)->i_advise; + ri->i_uid = cpu_to_le32(i_uid_read(inode)); + ri->i_gid = cpu_to_le32(i_gid_read(inode)); + ri->i_links = cpu_to_le32(inode->i_nlink); + ri->i_size = cpu_to_le64(i_size_read(inode)); + ri->i_blocks = cpu_to_le64(inode->i_blocks); + set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext); + + ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec); + ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec); + ri->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec); + ri->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec); + ri->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec); + ri->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); + ri->i_current_depth = cpu_to_le32(F2FS_I(inode)->i_current_depth); + ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid); + ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags); + ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino); + ri->i_generation = cpu_to_le32(inode->i_generation); + set_page_dirty(node_page); +} + +int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct page *node_page; + bool need_lock = false; + + if (inode->i_ino == F2FS_NODE_INO(sbi) || + inode->i_ino == F2FS_META_INO(sbi)) + return 0; + + node_page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(node_page)) + return PTR_ERR(node_page); + + if (!PageDirty(node_page)) { + need_lock = true; + f2fs_put_page(node_page, 1); + mutex_lock(&sbi->write_inode); + node_page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(node_page)) { + mutex_unlock(&sbi->write_inode); + return PTR_ERR(node_page); + } + } + update_inode(inode, node_page); + f2fs_put_page(node_page, 1); + if (need_lock) + mutex_unlock(&sbi->write_inode); + return 0; +} + +/* + * Called at the last iput() if i_nlink is zero + */ +void f2fs_evict_inode(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + + truncate_inode_pages(&inode->i_data, 0); + + if (inode->i_ino == F2FS_NODE_INO(sbi) || + inode->i_ino == F2FS_META_INO(sbi)) + goto no_delete; + + BUG_ON(atomic_read(&F2FS_I(inode)->dirty_dents)); + remove_dirty_dir_inode(inode); + + if (inode->i_nlink || is_bad_inode(inode)) + goto no_delete; + + set_inode_flag(F2FS_I(inode), FI_NO_ALLOC); + i_size_write(inode, 0); + + if (F2FS_HAS_BLOCKS(inode)) + f2fs_truncate(inode); + + remove_inode_page(inode); +no_delete: + clear_inode(inode); +} diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c new file mode 100644 index 000000000000..89b7675dc377 --- /dev/null +++ b/fs/f2fs/namei.c @@ -0,0 +1,503 @@ +/* + * fs/f2fs/namei.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/fs.h> +#include <linux/f2fs_fs.h> +#include <linux/pagemap.h> +#include <linux/sched.h> +#include <linux/ctype.h> + +#include "f2fs.h" +#include "xattr.h" +#include "acl.h" + +static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) +{ + struct super_block *sb = dir->i_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + nid_t ino; + struct inode *inode; + bool nid_free = false; + int err; + + inode = new_inode(sb); + if (!inode) + return ERR_PTR(-ENOMEM); + + mutex_lock_op(sbi, NODE_NEW); + if (!alloc_nid(sbi, &ino)) { + mutex_unlock_op(sbi, NODE_NEW); + err = -ENOSPC; + goto fail; + } + mutex_unlock_op(sbi, NODE_NEW); + + 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; + } + + mark_inode_dirty(inode); + return inode; + +out: + clear_nlink(inode); + unlock_new_inode(inode); +fail: + 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) +{ + int slen = strlen(s); + int sublen = strlen(sub); + int ret; + + if (sublen > slen) + return 1; + + ret = memcmp(s + slen - sublen, sub, sublen); + if (ret) { /* compare upper case */ + int i; + char upper_sub[8]; + for (i = 0; i < sublen && i < sizeof(upper_sub); i++) + upper_sub[i] = toupper(sub[i]); + return memcmp(s + slen - sublen, upper_sub, sublen); + } + + return ret; +} + +/* + * Set multimedia files as cold files for hot/cold data separation + */ +static inline void set_cold_file(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])) { + F2FS_I(inode)->i_advise |= FADVISE_COLD_BIT; + 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; + + inode = f2fs_new_inode(dir, mode); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + if (!test_opt(sbi, DISABLE_EXT_IDENTIFY)) + set_cold_file(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; + + err = f2fs_add_link(dentry, inode); + if (err) + goto out; + + alloc_nid_done(sbi, ino); + + if (!sbi->por_doing) + d_instantiate(dentry, inode); + unlock_new_inode(inode); + + f2fs_balance_fs(sbi); + return 0; +out: + clear_nlink(inode); + unlock_new_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; + + inode->i_ctime = CURRENT_TIME; + atomic_inc(&inode->i_count); + + set_inode_flag(F2FS_I(inode), FI_INC_LINK); + err = f2fs_add_link(dentry, inode); + if (err) + goto out; + + d_instantiate(dentry, inode); + + f2fs_balance_fs(sbi); + 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_MAX_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; + + de = f2fs_find_entry(dir, &dentry->d_name, &page); + if (!de) + goto fail; + + err = check_orphan_space(sbi); + if (err) { + kunmap(page); + f2fs_put_page(page, 0); + goto fail; + } + + f2fs_delete_entry(de, page, inode); + + /* In order to evict this inode, we set it dirty */ + mark_inode_dirty(inode); + f2fs_balance_fs(sbi); +fail: + 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; + unsigned symlen = strlen(symname) + 1; + int err; + + 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; + + err = f2fs_add_link(dentry, inode); + 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); + + f2fs_balance_fs(sbi); + + return err; +out: + clear_nlink(inode); + unlock_new_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; + + 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); + err = f2fs_add_link(dentry, inode); + if (err) + goto out_fail; + + alloc_nid_done(sbi, inode->i_ino); + + d_instantiate(dentry, inode); + unlock_new_inode(inode); + + f2fs_balance_fs(sbi); + return 0; + +out_fail: + clear_inode_flag(F2FS_I(inode), FI_INC_LINK); + clear_nlink(inode); + unlock_new_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; + + 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; + + err = f2fs_add_link(dentry, inode); + if (err) + goto out; + + alloc_nid_done(sbi, inode->i_ino); + d_instantiate(dentry, inode); + unlock_new_inode(inode); + + f2fs_balance_fs(sbi); + + return 0; +out: + clear_nlink(inode); + unlock_new_inode(inode); + iput(inode); + alloc_nid_failed(sbi, inode->i_ino); + return err; +} + +static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + struct super_block *sb = old_dir->i_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct inode *old_inode = old_dentry->d_inode; + struct inode *new_inode = new_dentry->d_inode; + struct page *old_dir_page; + struct page *old_page; + struct f2fs_dir_entry *old_dir_entry = NULL; + struct f2fs_dir_entry *old_entry; + struct f2fs_dir_entry *new_entry; + int err = -ENOENT; + + 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; + } + + mutex_lock_op(sbi, RENAME); + + if (new_inode) { + struct page *new_page; + + err = -ENOTEMPTY; + if (old_dir_entry && !f2fs_empty_dir(new_inode)) + goto out_dir; + + err = -ENOENT; + new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, + &new_page); + if (!new_entry) + goto out_dir; + + f2fs_set_link(new_dir, new_entry, new_page, old_inode); + + new_inode->i_ctime = CURRENT_TIME; + if (old_dir_entry) + drop_nlink(new_inode); + drop_nlink(new_inode); + if (!new_inode->i_nlink) + add_orphan_inode(sbi, new_inode->i_ino); + f2fs_write_inode(new_inode, NULL); + } else { + err = f2fs_add_link(new_dentry, old_inode); + if (err) + goto out_dir; + + if (old_dir_entry) { + inc_nlink(new_dir); + f2fs_write_inode(new_dir, NULL); + } + } + + old_inode->i_ctime = CURRENT_TIME; + set_inode_flag(F2FS_I(old_inode), FI_NEED_CP); + mark_inode_dirty(old_inode); + + f2fs_delete_entry(old_entry, old_page, NULL); + + if (old_dir_entry) { + if (old_dir != new_dir) { + f2fs_set_link(old_inode, old_dir_entry, + old_dir_page, new_dir); + } else { + kunmap(old_dir_page); + f2fs_put_page(old_dir_page, 0); + } + drop_nlink(old_dir); + f2fs_write_inode(old_dir, NULL); + } + + mutex_unlock_op(sbi, RENAME); + + f2fs_balance_fs(sbi); + return 0; + +out_dir: + if (old_dir_entry) { + kunmap(old_dir_page); + f2fs_put_page(old_dir_page, 0); + } + mutex_unlock_op(sbi, RENAME); +out_old: + kunmap(old_page); + f2fs_put_page(old_page, 0); +out: + return err; +} + +const struct inode_operations f2fs_dir_inode_operations = { + .create = f2fs_create, + .lookup = f2fs_lookup, + .link = f2fs_link, + .unlink = f2fs_unlink, + .symlink = f2fs_symlink, + .mkdir = f2fs_mkdir, + .rmdir = f2fs_rmdir, + .mknod = f2fs_mknod, + .rename = f2fs_rename, + .setattr = f2fs_setattr, + .get_acl = f2fs_get_acl, +#ifdef CONFIG_F2FS_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = f2fs_listxattr, + .removexattr = generic_removexattr, +#endif +}; + +const struct inode_operations f2fs_symlink_inode_operations = { + .readlink = generic_readlink, + .follow_link = page_follow_link_light, + .put_link = page_put_link, + .setattr = f2fs_setattr, +#ifdef CONFIG_F2FS_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = f2fs_listxattr, + .removexattr = generic_removexattr, +#endif +}; + +const struct inode_operations f2fs_special_inode_operations = { + .setattr = f2fs_setattr, + .get_acl = f2fs_get_acl, +#ifdef CONFIG_F2FS_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = f2fs_listxattr, + .removexattr = generic_removexattr, +#endif +}; diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c new file mode 100644 index 000000000000..19870361497e --- /dev/null +++ b/fs/f2fs/node.c @@ -0,0 +1,1764 @@ +/* + * fs/f2fs/node.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/fs.h> +#include <linux/f2fs_fs.h> +#include <linux/mpage.h> +#include <linux/backing-dev.h> +#include <linux/blkdev.h> +#include <linux/pagevec.h> +#include <linux/swap.h> + +#include "f2fs.h" +#include "node.h" +#include "segment.h" + +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; + + for (i = 0; i < FREE_NID_PAGES; i++, nid += NAT_ENTRY_PER_BLOCK) { + if (nid >= nm_i->max_nid) + nid = 0; + index = current_nat_addr(sbi, nid); + + page = grab_cache_page(mapping, index); + if (!page) + continue; + if (f2fs_readpage(sbi, page, index, READ)) { + f2fs_put_page(page, 1); + continue; + } + page_cache_release(page); + } +} + +static struct nat_entry *__lookup_nat_cache(struct f2fs_nm_info *nm_i, nid_t n) +{ + return radix_tree_lookup(&nm_i->nat_root, n); +} + +static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i, + nid_t start, unsigned int nr, struct nat_entry **ep) +{ + return radix_tree_gang_lookup(&nm_i->nat_root, (void **)ep, start, nr); +} + +static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e) +{ + list_del(&e->list); + radix_tree_delete(&nm_i->nat_root, nat_get_nid(e)); + nm_i->nat_cnt--; + kmem_cache_free(nat_entry_slab, e); +} + +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; + 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; + BUG_ON(ni->blk_addr != NULL_ADDR); + } + + if (new_blkaddr == NEW_ADDR) + e->checkpointed = false; + + /* sanity check */ + BUG_ON(nat_get_blkaddr(e) != ni->blk_addr); + BUG_ON(nat_get_blkaddr(e) == NULL_ADDR && + new_blkaddr == NULL_ADDR); + BUG_ON(nat_get_blkaddr(e) == NEW_ADDR && + new_blkaddr == NEW_ADDR); + 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); +} + +static 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 < 2 * 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(long block, int offset[4], unsigned int noffset[4]) +{ + const long direct_index = ADDRS_PER_INODE; + 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; + level = 0; + 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). + */ +int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int ro) +{ + 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(index, offset, noffset); + + nids[0] = dn->inode->i_ino; + npage[0] = get_node_page(sbi, nids[0]); + if (IS_ERR(npage[0])) + return PTR_ERR(npage[0]); + + parent = npage[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] && !ro) { + mutex_lock_op(sbi, NODE_NEW); + + /* alloc new node */ + if (!alloc_nid(sbi, &(nids[i]))) { + mutex_unlock_op(sbi, NODE_NEW); + err = -ENOSPC; + goto release_pages; + } + + dn->nid = nids[i]; + npage[i] = new_node_page(dn, noffset[i]); + if (IS_ERR(npage[i])) { + alloc_nid_failed(sbi, nids[i]); + mutex_unlock_op(sbi, NODE_NEW); + err = PTR_ERR(npage[i]); + goto release_pages; + } + + set_nid(parent, offset[i - 1], nids[i], i == 1); + alloc_nid_done(sbi, nids[i]); + mutex_unlock_op(sbi, NODE_NEW); + done = true; + } else if (ro && 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); + BUG_ON(ni.blk_addr == NULL_ADDR); + + if (ni.blk_addr != NULL_ADDR) + invalidate_blocks(sbi, ni.blk_addr); + + /* Deallocate node address */ + dec_valid_node_count(sbi, dn->inode, 1); + 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); + } + + clear_node_page_dirty(dn->node_page); + F2FS_SET_SB_DIRT(sbi); + + f2fs_put_page(dn->node_page, 1); + dn->node_page = NULL; +} + +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; + + page = get_node_page(sbi, dn->nid); + if (IS_ERR(page)) + return PTR_ERR(page); + + rn = (struct f2fs_node *)page_address(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); + } + return freed; + +out_err: + f2fs_put_page(page, 1); + 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 < depth - 1; i++) { + /* refernece count'll be increased */ + pages[i] = get_node_page(sbi, nid[i]); + if (IS_ERR(pages[i])) { + depth = i + 1; + err = PTR_ERR(pages[i]); + 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[depth - 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[depth - 1] == 0) { + dn->node_page = pages[idx]; + dn->nid = nid[idx]; + truncate_node(dn); + } else { + f2fs_put_page(pages[idx], 1); + } + offset[idx]++; + offset[depth - 1] = 0; +fail: + for (i = depth - 3; i >= 0; i--) + f2fs_put_page(pages[i], 1); + 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); + int err = 0, cont = 1; + int level, offset[4], noffset[4]; + unsigned int nofs; + struct f2fs_node *rn; + struct dnode_of_data dn; + struct page *page; + + level = get_node_path(from, offset, noffset); + + page = get_node_page(sbi, inode->i_ino); + if (IS_ERR(page)) + return PTR_ERR(page); + + set_new_dnode(&dn, inode, page, NULL, 0); + unlock_page(page); + + rn = page_address(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, &rn->i, 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, &rn->i, offset, level); + if (err < 0 && err != -ENOENT) + goto fail; + break; + default: + BUG(); + } + +skip_partial: + while (cont) { + dn.nid = le32_to_cpu(rn->i.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 && + rn->i.i_nid[offset[0] - NODE_DIR1_BLOCK]) { + lock_page(page); + wait_on_page_writeback(page); + rn->i.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); + return err > 0 ? 0 : err; +} + +int 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; + + mutex_lock_op(sbi, NODE_TRUNC); + page = get_node_page(sbi, ino); + if (IS_ERR(page)) { + mutex_unlock_op(sbi, NODE_TRUNC); + return PTR_ERR(page); + } + + if (F2FS_I(inode)->i_xattr_nid) { + nid_t nid = F2FS_I(inode)->i_xattr_nid; + struct page *npage = get_node_page(sbi, nid); + + if (IS_ERR(npage)) { + mutex_unlock_op(sbi, NODE_TRUNC); + return PTR_ERR(npage); + } + + F2FS_I(inode)->i_xattr_nid = 0; + set_new_dnode(&dn, inode, page, npage, nid); + dn.inode_page_locked = 1; + truncate_node(&dn); + } + if (inode->i_blocks == 1) { + /* inernally call f2fs_put_page() */ + set_new_dnode(&dn, inode, page, page, ino); + truncate_node(&dn); + } else if (inode->i_blocks == 0) { + struct node_info ni; + get_node_info(sbi, inode->i_ino, &ni); + + /* called after f2fs_new_inode() is failed */ + BUG_ON(ni.blk_addr != NULL_ADDR); + f2fs_put_page(page, 1); + } else { + BUG(); + } + mutex_unlock_op(sbi, NODE_TRUNC); + return 0; +} + +int new_inode_page(struct inode *inode, struct dentry *dentry) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct page *page; + struct dnode_of_data dn; + + /* allocate inode page for new inode */ + set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); + mutex_lock_op(sbi, NODE_NEW); + page = new_node_page(&dn, 0); + init_dent_inode(dentry, page); + mutex_unlock_op(sbi, NODE_NEW); + if (IS_ERR(page)) + return PTR_ERR(page); + f2fs_put_page(page, 1); + return 0; +} + +struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) +{ + 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 (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); + + get_node_info(sbi, dn->nid, &old_ni); + + SetPageUptodate(page); + fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true); + + /* Reinitialize old_ni with new node page */ + BUG_ON(old_ni.blk_addr != NULL_ADDR); + new_ni = old_ni; + new_ni.ino = dn->inode->i_ino; + + if (!inc_valid_node_count(sbi, dn->inode, 1)) { + err = -ENOSPC; + goto fail; + } + set_node_addr(sbi, &new_ni, NEW_ADDR); + + dn->node_page = page; + sync_inode_page(dn); + set_page_dirty(page); + set_cold_node(dn->inode, page); + if (ofs == 0) + inc_valid_inode_count(sbi); + + return page; + +fail: + f2fs_put_page(page, 1); + return ERR_PTR(err); +} + +static int read_node_page(struct page *page, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb); + struct node_info ni; + + get_node_info(sbi, page->index, &ni); + + if (ni.blk_addr == NULL_ADDR) + return -ENOENT; + return f2fs_readpage(sbi, page, ni.blk_addr, type); +} + +/* + * 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; + + apage = find_get_page(mapping, nid); + if (apage && PageUptodate(apage)) + goto release_out; + f2fs_put_page(apage, 0); + + apage = grab_cache_page(mapping, nid); + if (!apage) + return; + + if (read_node_page(apage, READA)) + goto unlock_out; + + page_cache_release(apage); + return; + +unlock_out: + unlock_page(apage); +release_out: + page_cache_release(apage); +} + +struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) +{ + int err; + struct page *page; + struct address_space *mapping = sbi->node_inode->i_mapping; + + page = grab_cache_page(mapping, nid); + if (!page) + return ERR_PTR(-ENOMEM); + + err = read_node_page(page, READ_SYNC); + if (err) { + f2fs_put_page(page, 1); + return ERR_PTR(err); + } + + 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; + int i, end; + int err = 0; + nid_t nid; + struct page *page; + + /* First, try getting the desired direct node. */ + nid = get_nid(parent, start, false); + if (!nid) + return ERR_PTR(-ENOENT); + + page = find_get_page(mapping, nid); + if (page && PageUptodate(page)) + goto page_hit; + f2fs_put_page(page, 0); + +repeat: + page = grab_cache_page(mapping, nid); + if (!page) + return ERR_PTR(-ENOMEM); + + err = read_node_page(page, READA); + if (err) { + f2fs_put_page(page, 1); + return ERR_PTR(err); + } + + /* 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); + } + +page_hit: + lock_page(page); + if (PageError(page)) { + f2fs_put_page(page, 1); + return ERR_PTR(-EIO); + } + + /* Has the page been truncated? */ + if (page->mapping != mapping) { + f2fs_put_page(page, 1); + goto repeat; + } + 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 { + f2fs_write_inode(dn->inode, NULL); + } +} + +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_bio(sbi, NODE, wbc->sync_mode == WB_SYNC_ALL); + + return nwritten; +} + +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; + unsigned int nofs; + block_t new_addr; + struct node_info ni; + + if (wbc->for_reclaim) { + dec_page_count(sbi, F2FS_DIRTY_NODES); + wbc->pages_skipped++; + set_page_dirty(page); + return AOP_WRITEPAGE_ACTIVATE; + } + + wait_on_page_writeback(page); + + mutex_lock_op(sbi, NODE_WRITE); + + /* get old block addr of this node page */ + nid = nid_of_node(page); + nofs = ofs_of_node(page); + BUG_ON(page->index != nid); + + get_node_info(sbi, nid, &ni); + + /* This page is already truncated */ + if (ni.blk_addr == NULL_ADDR) + return 0; + + set_page_writeback(page); + + /* insert node offset */ + 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_op(sbi, NODE_WRITE); + unlock_page(page); + return 0; +} + +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); + struct block_device *bdev = sbi->sb->s_bdev; + long nr_to_write = wbc->nr_to_write; + + if (wbc->for_kupdate) + return 0; + + if (get_pages(sbi, F2FS_DIRTY_NODES) == 0) + return 0; + + if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK)) { + write_checkpoint(sbi, false, false); + return 0; + } + + /* if mounting is failed, skip writing node pages */ + wbc->nr_to_write = bio_get_nr_vecs(bdev); + sync_node_pages(sbi, 0, wbc); + wbc->nr_to_write = nr_to_write - + (bio_get_nr_vecs(bdev) - 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); + + 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 long offset) +{ + 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 0; +} + +/* + * Structure of the f2fs node operations + */ +const struct address_space_operations f2fs_node_aops = { + .writepage = f2fs_write_node_page, + .writepages = f2fs_write_node_pages, + .set_page_dirty = f2fs_set_node_page_dirty, + .invalidatepage = f2fs_invalidate_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 = NULL; + list_for_each(this, head) { + i = list_entry(this, struct free_nid, list); + if (i->nid == n) + break; + i = NULL; + } + return i; +} + +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) +{ + struct free_nid *i; + + if (nm_i->fcnt > 2 * MAX_FREE_NIDS) + return 0; +retry: + i = kmem_cache_alloc(free_nid_slab, GFP_NOFS); + if (!i) { + cond_resched(); + goto retry; + } + 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 int 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 fcnt = 0; + int i; + + /* 0 nid should not be used */ + if (start_nid == 0) + ++start_nid; + + i = start_nid % NAT_ENTRY_PER_BLOCK; + + for (; i < NAT_ENTRY_PER_BLOCK; i++, start_nid++) { + blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr); + BUG_ON(blk_addr == NEW_ADDR); + if (blk_addr == NULL_ADDR) + fcnt += add_free_nid(nm_i, start_nid); + } + return fcnt; +} + +static void build_free_nids(struct f2fs_sb_info *sbi) +{ + struct free_nid *fnid, *next_fnid; + 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 nid = 0; + bool is_cycled = false; + int fcnt = 0; + int i; + + nid = nm_i->next_scan_nid; + nm_i->init_scan_nid = nid; + + ra_nat_pages(sbi, nid); + + while (1) { + struct page *page = get_current_nat_page(sbi, nid); + + fcnt += scan_nat_page(nm_i, page, nid); + f2fs_put_page(page, 1); + + nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK)); + + if (nid >= nm_i->max_nid) { + nid = 0; + is_cycled = true; + } + if (fcnt > MAX_FREE_NIDS) + break; + if (is_cycled && nm_i->init_scan_nid <= nid) + break; + } + + 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); + else + remove_free_nid(nm_i, nid); + } + mutex_unlock(&curseg->curseg_mutex); + + /* remove the free nids from current allocated nids */ + list_for_each_entry_safe(fnid, next_fnid, &nm_i->free_nid_list, list) { + struct nat_entry *ne; + + read_lock(&nm_i->nat_tree_lock); + ne = __lookup_nat_cache(nm_i, fnid->nid); + if (ne && nat_get_blkaddr(ne) != NULL_ADDR) + remove_free_nid(nm_i, fnid->nid); + read_unlock(&nm_i->nat_tree_lock); + } +} + +/* + * 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: + mutex_lock(&nm_i->build_lock); + if (!nm_i->fcnt) { + /* scan NAT in order to build free nid list */ + build_free_nids(sbi); + if (!nm_i->fcnt) { + mutex_unlock(&nm_i->build_lock); + return false; + } + } + mutex_unlock(&nm_i->build_lock); + + /* + * We check fcnt again since previous check is racy as + * we didn't hold free_nid_list_lock. So other thread + * could consume all of free nids. + */ + spin_lock(&nm_i->free_nid_list_lock); + if (!nm_i->fcnt) { + spin_unlock(&nm_i->free_nid_list_lock); + goto retry; + } + + 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; + } + + 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; +} + +/* + * 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); + if (i) { + BUG_ON(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) +{ + alloc_nid_done(sbi, nid); + add_free_nid(NM_I(sbi), nid); +} + +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_node *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 = (struct f2fs_node *)page_address(page); + dst = (struct f2fs_node *)page_address(ipage); + + memcpy(dst, src, (unsigned long)&src->i.i_ext - (unsigned long)&src->i); + dst->i.i_size = 0; + dst->i.i_blocks = cpu_to_le64(1); + dst->i.i_links = cpu_to_le32(1); + dst->i.i_xattr_nid = 0; + + new_ni = old_ni; + new_ni.ino = ino; + + set_node_addr(sbi, &new_ni, NEW_ADDR); + inc_valid_inode_count(sbi); + + f2fs_put_page(ipage, 1); + return 0; +} + +int restore_node_summary(struct f2fs_sb_info *sbi, + unsigned int segno, struct f2fs_summary_block *sum) +{ + struct f2fs_node *rn; + struct f2fs_summary *sum_entry; + struct page *page; + block_t addr; + int i, last_offset; + + /* alloc temporal page for read node */ + page = alloc_page(GFP_NOFS | __GFP_ZERO); + if (IS_ERR(page)) + return PTR_ERR(page); + lock_page(page); + + /* 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++, sum_entry++) { + if (f2fs_readpage(sbi, page, addr, READ_SYNC)) + goto out; + + rn = (struct f2fs_node *)page_address(page); + sum_entry->nid = rn->footer.nid; + sum_entry->version = 0; + sum_entry->ofs_in_node = 0; + addr++; + + /* + * In order to read next node page, + * we must clear PageUptodate flag. + */ + ClearPageUptodate(page); + } +out: + unlock_page(page); + __free_pages(page, 0); + return 0; +} + +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 old_blkaddr, 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); + old_blkaddr = le32_to_cpu(raw_ne.block_addr); + 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); + } + + BUG_ON(!nat_blk); + raw_ne = nat_blk->entries[nid - start_nid]; + old_blkaddr = le32_to_cpu(raw_ne.block_addr); +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) { + write_lock(&nm_i->nat_tree_lock); + __del_from_nat_cache(nm_i, ne); + write_unlock(&nm_i->nat_tree_lock); + + /* We can reuse this freed nid at this point */ + add_free_nid(NM_I(sbi), nid); + } 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->bitmap_size = __bitmap_size(sbi, NAT_BITMAP); + nm_i->init_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid); + nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid); + + nm_i->nat_bitmap = kzalloc(nm_i->bitmap_size, GFP_KERNEL); + if (!nm_i->nat_bitmap) + return -ENOMEM; + version_bitmap = __bitmap_ptr(sbi, NAT_BITMAP); + if (!version_bitmap) + return -EFAULT; + + /* copy version bitmap */ + memcpy(nm_i->nat_bitmap, version_bitmap, nm_i->bitmap_size); + 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) { + BUG_ON(i->state == NID_ALLOC); + __del_from_free_nid_list(i); + nm_i->fcnt--; + } + 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); + } + } + 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 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 000000000000..afdb130f782e --- /dev/null +++ b/fs/f2fs/node.h @@ -0,0 +1,353 @@ +/* + * 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 + +/* + * For node information + */ +struct node_info { + nid_t nid; /* node id */ + nid_t ino; /* inode number of the node's owner */ + block_t blk_addr; /* block address of the node */ + unsigned char version; /* version of the node */ +}; + +struct nat_entry { + struct list_head list; /* for clean or dirty nat list */ + bool checkpointed; /* whether it is checkpointed or not */ + struct node_info ni; /* in-memory node information */ +}; + +#define nat_get_nid(nat) (nat->ni.nid) +#define nat_set_nid(nat, n) (nat->ni.nid = n) +#define nat_get_blkaddr(nat) (nat->ni.blk_addr) +#define nat_set_blkaddr(nat, b) (nat->ni.blk_addr = b) +#define nat_get_ino(nat) (nat->ni.ino) +#define nat_set_ino(nat, i) (nat->ni.ino = i) +#define nat_get_version(nat) (nat->ni.version) +#define nat_set_version(nat, v) (nat->ni.version = v) + +#define __set_nat_cache_dirty(nm_i, ne) \ + list_move_tail(&ne->list, &nm_i->dirty_nat_entries); +#define __clear_nat_cache_dirty(nm_i, ne) \ + list_move_tail(&ne->list, &nm_i->nat_entries); +#define inc_node_version(version) (++version) + +static inline void node_info_from_raw_nat(struct node_info *ni, + struct f2fs_nat_entry *raw_ne) +{ + ni->ino = le32_to_cpu(raw_ne->ino); + ni->blk_addr = le32_to_cpu(raw_ne->block_addr); + ni->version = raw_ne->version; +} + +/* + * For free nid mangement + */ +enum nid_state { + NID_NEW, /* newly added to free nid list */ + NID_ALLOC /* it is allocated */ +}; + +struct free_nid { + struct list_head list; /* for free node id list */ + nid_t nid; /* node id */ + int state; /* in use or not: NID_NEW or NID_ALLOC */ +}; + +static inline int next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + struct free_nid *fnid; + + if (nm_i->fcnt <= 0) + return -1; + spin_lock(&nm_i->free_nid_list_lock); + fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list); + *nid = fnid->nid; + spin_unlock(&nm_i->free_nid_list_lock); + return 0; +} + +/* + * inline functions + */ +static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + memcpy(addr, nm_i->nat_bitmap, nm_i->bitmap_size); +} + +static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + pgoff_t block_off; + pgoff_t block_addr; + int seg_off; + + block_off = NAT_BLOCK_OFFSET(start); + seg_off = block_off >> sbi->log_blocks_per_seg; + + block_addr = (pgoff_t)(nm_i->nat_blkaddr + + (seg_off << sbi->log_blocks_per_seg << 1) + + (block_off & ((1 << sbi->log_blocks_per_seg) - 1))); + + if (f2fs_test_bit(block_off, nm_i->nat_bitmap)) + block_addr += sbi->blocks_per_seg; + + return block_addr; +} + +static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi, + pgoff_t block_addr) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + + block_addr -= nm_i->nat_blkaddr; + if ((block_addr >> sbi->log_blocks_per_seg) % 2) + block_addr -= sbi->blocks_per_seg; + else + block_addr += sbi->blocks_per_seg; + + return block_addr + nm_i->nat_blkaddr; +} + +static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid) +{ + unsigned int block_off = NAT_BLOCK_OFFSET(start_nid); + + if (f2fs_test_bit(block_off, nm_i->nat_bitmap)) + f2fs_clear_bit(block_off, nm_i->nat_bitmap); + else + f2fs_set_bit(block_off, nm_i->nat_bitmap); +} + +static inline void fill_node_footer(struct page *page, nid_t nid, + nid_t ino, unsigned int ofs, bool reset) +{ + void *kaddr = page_address(page); + struct f2fs_node *rn = (struct f2fs_node *)kaddr; + if (reset) + memset(rn, 0, sizeof(*rn)); + rn->footer.nid = cpu_to_le32(nid); + rn->footer.ino = cpu_to_le32(ino); + rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT); +} + +static inline void copy_node_footer(struct page *dst, struct page *src) +{ + void *src_addr = page_address(src); + void *dst_addr = page_address(dst); + struct f2fs_node *src_rn = (struct f2fs_node *)src_addr; + struct f2fs_node *dst_rn = (struct f2fs_node *)dst_addr; + memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer)); +} + +static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr) +{ + struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb); + struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + void *kaddr = page_address(page); + struct f2fs_node *rn = (struct f2fs_node *)kaddr; + rn->footer.cp_ver = ckpt->checkpoint_ver; + rn->footer.next_blkaddr = cpu_to_le32(blkaddr); +} + +static inline nid_t ino_of_node(struct page *node_page) +{ + void *kaddr = page_address(node_page); + struct f2fs_node *rn = (struct f2fs_node *)kaddr; + return le32_to_cpu(rn->footer.ino); +} + +static inline nid_t nid_of_node(struct page *node_page) +{ + void *kaddr = page_address(node_page); + struct f2fs_node *rn = (struct f2fs_node *)kaddr; + return le32_to_cpu(rn->footer.nid); +} + +static inline unsigned int ofs_of_node(struct page *node_page) +{ + void *kaddr = page_address(node_page); + struct f2fs_node *rn = (struct f2fs_node *)kaddr; + unsigned flag = le32_to_cpu(rn->footer.flag); + return flag >> OFFSET_BIT_SHIFT; +} + +static inline unsigned long long cpver_of_node(struct page *node_page) +{ + void *kaddr = page_address(node_page); + struct f2fs_node *rn = (struct f2fs_node *)kaddr; + return le64_to_cpu(rn->footer.cp_ver); +} + +static inline block_t next_blkaddr_of_node(struct page *node_page) +{ + void *kaddr = page_address(node_page); + struct f2fs_node *rn = (struct f2fs_node *)kaddr; + return le32_to_cpu(rn->footer.next_blkaddr); +} + +/* + * f2fs assigns the following node offsets described as (num). + * N = NIDS_PER_BLOCK + * + * Inode block (0) + * |- direct node (1) + * |- direct node (2) + * |- indirect node (3) + * | `- direct node (4 => 4 + N - 1) + * |- indirect node (4 + N) + * | `- direct node (5 + N => 5 + 2N - 1) + * `- double indirect node (5 + 2N) + * `- indirect node (6 + 2N) + * `- direct node (x(N + 1)) + */ +static inline bool IS_DNODE(struct page *node_page) +{ + unsigned int ofs = ofs_of_node(node_page); + if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK || + ofs == 5 + 2 * NIDS_PER_BLOCK) + return false; + if (ofs >= 6 + 2 * NIDS_PER_BLOCK) { + ofs -= 6 + 2 * NIDS_PER_BLOCK; + if ((long int)ofs % (NIDS_PER_BLOCK + 1)) + return false; + } + return true; +} + +static inline void set_nid(struct page *p, int off, nid_t nid, bool i) +{ + struct f2fs_node *rn = (struct f2fs_node *)page_address(p); + + wait_on_page_writeback(p); + + if (i) + rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid); + else + rn->in.nid[off] = cpu_to_le32(nid); + set_page_dirty(p); +} + +static inline nid_t get_nid(struct page *p, int off, bool i) +{ + struct f2fs_node *rn = (struct f2fs_node *)page_address(p); + if (i) + return le32_to_cpu(rn->i.i_nid[off - NODE_DIR1_BLOCK]); + return le32_to_cpu(rn->in.nid[off]); +} + +/* + * Coldness identification: + * - Mark cold files in f2fs_inode_info + * - Mark cold node blocks in their node footer + * - Mark cold data pages in page cache + */ +static inline int is_cold_file(struct inode *inode) +{ + return F2FS_I(inode)->i_advise & FADVISE_COLD_BIT; +} + +static inline int is_cold_data(struct page *page) +{ + return PageChecked(page); +} + +static inline void set_cold_data(struct page *page) +{ + SetPageChecked(page); +} + +static inline void clear_cold_data(struct page *page) +{ + ClearPageChecked(page); +} + +static inline int is_cold_node(struct page *page) +{ + void *kaddr = page_address(page); + struct f2fs_node *rn = (struct f2fs_node *)kaddr; + unsigned int flag = le32_to_cpu(rn->footer.flag); + return flag & (0x1 << COLD_BIT_SHIFT); +} + +static inline unsigned char is_fsync_dnode(struct page *page) +{ + void *kaddr = page_address(page); + struct f2fs_node *rn = (struct f2fs_node *)kaddr; + unsigned int flag = le32_to_cpu(rn->footer.flag); + return flag & (0x1 << FSYNC_BIT_SHIFT); +} + +static inline unsigned char is_dent_dnode(struct page *page) +{ + void *kaddr = page_address(page); + struct f2fs_node *rn = (struct f2fs_node *)kaddr; + unsigned int flag = le32_to_cpu(rn->footer.flag); + return flag & (0x1 << DENT_BIT_SHIFT); +} + +static inline void set_cold_node(struct inode *inode, struct page *page) +{ + struct f2fs_node *rn = (struct f2fs_node *)page_address(page); + unsigned int flag = le32_to_cpu(rn->footer.flag); + + if (S_ISDIR(inode->i_mode)) + flag &= ~(0x1 << COLD_BIT_SHIFT); + else + flag |= (0x1 << COLD_BIT_SHIFT); + rn->footer.flag = cpu_to_le32(flag); +} + +static inline void set_fsync_mark(struct page *page, int mark) +{ + void *kaddr = page_address(page); + struct f2fs_node *rn = (struct f2fs_node *)kaddr; + unsigned int flag = le32_to_cpu(rn->footer.flag); + if (mark) + flag |= (0x1 << FSYNC_BIT_SHIFT); + else + flag &= ~(0x1 << FSYNC_BIT_SHIFT); + rn->footer.flag = cpu_to_le32(flag); +} + +static inline void set_dentry_mark(struct page *page, int mark) +{ + void *kaddr = page_address(page); + struct f2fs_node *rn = (struct f2fs_node *)kaddr; + unsigned int flag = le32_to_cpu(rn->footer.flag); + if (mark) + flag |= (0x1 << DENT_BIT_SHIFT); + else + flag &= ~(0x1 << DENT_BIT_SHIFT); + rn->footer.flag = cpu_to_le32(flag); +} diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c new file mode 100644 index 000000000000..b07e9b6ef376 --- /dev/null +++ b/fs/f2fs/recovery.c @@ -0,0 +1,375 @@ +/* + * fs/f2fs/recovery.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/fs.h> +#include <linux/f2fs_fs.h> +#include "f2fs.h" +#include "node.h" +#include "segment.h" + +static struct kmem_cache *fsync_entry_slab; + +bool space_for_roll_forward(struct f2fs_sb_info *sbi) +{ + if (sbi->last_valid_block_count + sbi->alloc_valid_block_count + > sbi->user_block_count) + return false; + return true; +} + +static struct fsync_inode_entry *get_fsync_inode(struct list_head *head, + nid_t ino) +{ + struct list_head *this; + struct fsync_inode_entry *entry; + + list_for_each(this, head) { + entry = list_entry(this, struct fsync_inode_entry, list); + if (entry->inode->i_ino == ino) + return entry; + } + return NULL; +} + +static int recover_dentry(struct page *ipage, struct inode *inode) +{ + struct f2fs_node *raw_node = (struct f2fs_node *)kmap(ipage); + struct f2fs_inode *raw_inode = &(raw_node->i); + struct dentry dent, parent; + struct f2fs_dir_entry *de; + struct page *page; + struct inode *dir; + int err = 0; + + if (!is_dent_dnode(ipage)) + goto out; + + dir = f2fs_iget(inode->i_sb, le32_to_cpu(raw_inode->i_pino)); + if (IS_ERR(dir)) { + err = -EINVAL; + goto out; + } + + parent.d_inode = dir; + dent.d_parent = &parent; + dent.d_name.len = le32_to_cpu(raw_inode->i_namelen); + dent.d_name.name = raw_inode->i_name; + + de = f2fs_find_entry(dir, &dent.d_name, &page); + if (de) { + kunmap(page); + f2fs_put_page(page, 0); + } else { + f2fs_add_link(&dent, inode); + } + iput(dir); +out: + kunmap(ipage); + return err; +} + +static int recover_inode(struct inode *inode, struct page *node_page) +{ + void *kaddr = page_address(node_page); + struct f2fs_node *raw_node = (struct f2fs_node *)kaddr; + struct f2fs_inode *raw_inode = &(raw_node->i); + + inode->i_mode = le16_to_cpu(raw_inode->i_mode); + i_size_write(inode, le64_to_cpu(raw_inode->i_size)); + inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime); + inode->i_ctime.tv_sec = le64_to_cpu(raw_inode->i_ctime); + inode->i_mtime.tv_sec = le64_to_cpu(raw_inode->i_mtime); + inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); + inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec); + inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec); + + return recover_dentry(node_page, inode); +} + +static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) +{ + unsigned long long cp_ver = le64_to_cpu(sbi->ckpt->checkpoint_ver); + struct curseg_info *curseg; + struct page *page; + block_t blkaddr; + int err = 0; + + /* get node pages in the current segment */ + curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); + blkaddr = START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff; + + /* read node page */ + page = alloc_page(GFP_F2FS_ZERO); + if (IS_ERR(page)) + return PTR_ERR(page); + lock_page(page); + + while (1) { + struct fsync_inode_entry *entry; + + if (f2fs_readpage(sbi, page, blkaddr, READ_SYNC)) + goto out; + + if (cp_ver != cpver_of_node(page)) + goto out; + + if (!is_fsync_dnode(page)) + goto next; + + entry = get_fsync_inode(head, ino_of_node(page)); + if (entry) { + entry->blkaddr = blkaddr; + if (IS_INODE(page) && is_dent_dnode(page)) + set_inode_flag(F2FS_I(entry->inode), + FI_INC_LINK); + } else { + if (IS_INODE(page) && is_dent_dnode(page)) { + if (recover_inode_page(sbi, page)) { + err = -ENOMEM; + goto out; + } + } + + /* add this fsync inode to the list */ + entry = kmem_cache_alloc(fsync_entry_slab, GFP_NOFS); + if (!entry) { + err = -ENOMEM; + goto out; + } + + INIT_LIST_HEAD(&entry->list); + list_add_tail(&entry->list, head); + + entry->inode = f2fs_iget(sbi->sb, ino_of_node(page)); + if (IS_ERR(entry->inode)) { + err = PTR_ERR(entry->inode); + goto out; + } + entry->blkaddr = blkaddr; + } + if (IS_INODE(page)) { + err = recover_inode(entry->inode, page); + if (err) + goto out; + } +next: + /* check next segment */ + blkaddr = next_blkaddr_of_node(page); + ClearPageUptodate(page); + } +out: + unlock_page(page); + __free_pages(page, 0); + return err; +} + +static void destroy_fsync_dnodes(struct f2fs_sb_info *sbi, + struct list_head *head) +{ + struct list_head *this; + struct fsync_inode_entry *entry; + list_for_each(this, head) { + entry = list_entry(this, struct fsync_inode_entry, list); + iput(entry->inode); + list_del(&entry->list); + kmem_cache_free(fsync_entry_slab, entry); + } +} + +static void check_index_in_prev_nodes(struct f2fs_sb_info *sbi, + block_t blkaddr) +{ + struct seg_entry *sentry; + unsigned int segno = GET_SEGNO(sbi, blkaddr); + unsigned short blkoff = GET_SEGOFF_FROM_SEG0(sbi, blkaddr) & + (sbi->blocks_per_seg - 1); + struct f2fs_summary sum; + nid_t ino; + void *kaddr; + struct inode *inode; + struct page *node_page; + block_t bidx; + int i; + + sentry = get_seg_entry(sbi, segno); + if (!f2fs_test_bit(blkoff, sentry->cur_valid_map)) + return; + + /* Get the previous summary */ + for (i = CURSEG_WARM_DATA; i <= CURSEG_COLD_DATA; i++) { + struct curseg_info *curseg = CURSEG_I(sbi, i); + if (curseg->segno == segno) { + sum = curseg->sum_blk->entries[blkoff]; + break; + } + } + if (i > CURSEG_COLD_DATA) { + struct page *sum_page = get_sum_page(sbi, segno); + struct f2fs_summary_block *sum_node; + kaddr = page_address(sum_page); + sum_node = (struct f2fs_summary_block *)kaddr; + sum = sum_node->entries[blkoff]; + f2fs_put_page(sum_page, 1); + } + + /* Get the node page */ + node_page = get_node_page(sbi, le32_to_cpu(sum.nid)); + bidx = start_bidx_of_node(ofs_of_node(node_page)) + + le16_to_cpu(sum.ofs_in_node); + ino = ino_of_node(node_page); + f2fs_put_page(node_page, 1); + + /* Deallocate previous index in the node page */ + inode = f2fs_iget_nowait(sbi->sb, ino); + truncate_hole(inode, bidx, bidx + 1); + iput(inode); +} + +static void do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, + struct page *page, block_t blkaddr) +{ + unsigned int start, end; + struct dnode_of_data dn; + struct f2fs_summary sum; + struct node_info ni; + + start = start_bidx_of_node(ofs_of_node(page)); + if (IS_INODE(page)) + end = start + ADDRS_PER_INODE; + else + end = start + ADDRS_PER_BLOCK; + + set_new_dnode(&dn, inode, NULL, NULL, 0); + if (get_dnode_of_data(&dn, start, 0)) + return; + + wait_on_page_writeback(dn.node_page); + + get_node_info(sbi, dn.nid, &ni); + BUG_ON(ni.ino != ino_of_node(page)); + BUG_ON(ofs_of_node(dn.node_page) != ofs_of_node(page)); + + for (; start < end; start++) { + block_t src, dest; + + src = datablock_addr(dn.node_page, dn.ofs_in_node); + dest = datablock_addr(page, dn.ofs_in_node); + + if (src != dest && dest != NEW_ADDR && dest != NULL_ADDR) { + if (src == NULL_ADDR) { + int err = reserve_new_block(&dn); + /* We should not get -ENOSPC */ + BUG_ON(err); + } + + /* Check the previous node page having this index */ + check_index_in_prev_nodes(sbi, dest); + + set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); + + /* write dummy data page */ + recover_data_page(sbi, NULL, &sum, src, dest); + update_extent_cache(dest, &dn); + } + dn.ofs_in_node++; + } + + /* write node page in place */ + set_summary(&sum, dn.nid, 0, 0); + if (IS_INODE(dn.node_page)) + sync_inode_page(&dn); + + copy_node_footer(dn.node_page, page); + fill_node_footer(dn.node_page, dn.nid, ni.ino, + ofs_of_node(page), false); + set_page_dirty(dn.node_page); + + recover_node_page(sbi, dn.node_page, &sum, &ni, blkaddr); + f2fs_put_dnode(&dn); +} + +static void recover_data(struct f2fs_sb_info *sbi, + struct list_head *head, int type) +{ + unsigned long long cp_ver = le64_to_cpu(sbi->ckpt->checkpoint_ver); + struct curseg_info *curseg; + struct page *page; + block_t blkaddr; + + /* get node pages in the current segment */ + curseg = CURSEG_I(sbi, type); + blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); + + /* read node page */ + page = alloc_page(GFP_NOFS | __GFP_ZERO); + if (IS_ERR(page)) + return; + lock_page(page); + + while (1) { + struct fsync_inode_entry *entry; + + if (f2fs_readpage(sbi, page, blkaddr, READ_SYNC)) + goto out; + + if (cp_ver != cpver_of_node(page)) + goto out; + + entry = get_fsync_inode(head, ino_of_node(page)); + if (!entry) + goto next; + + do_recover_data(sbi, entry->inode, page, blkaddr); + + 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); + ClearPageUptodate(page); + } +out: + unlock_page(page); + __free_pages(page, 0); + + allocate_new_segments(sbi); +} + +void recover_fsync_data(struct f2fs_sb_info *sbi) +{ + struct list_head inode_list; + + fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry", + sizeof(struct fsync_inode_entry), NULL); + if (unlikely(!fsync_entry_slab)) + return; + + INIT_LIST_HEAD(&inode_list); + + /* step #1: find fsynced inode numbers */ + if (find_fsync_dnodes(sbi, &inode_list)) + goto out; + + if (list_empty(&inode_list)) + goto out; + + /* step #2: recover data */ + sbi->por_doing = 1; + recover_data(sbi, &inode_list, CURSEG_WARM_NODE); + sbi->por_doing = 0; + BUG_ON(!list_empty(&inode_list)); +out: + destroy_fsync_dnodes(sbi, &inode_list); + kmem_cache_destroy(fsync_entry_slab); + write_checkpoint(sbi, false, false); +} diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c new file mode 100644 index 000000000000..1b26e4ea1016 --- /dev/null +++ b/fs/f2fs/segment.c @@ -0,0 +1,1791 @@ +/* + * fs/f2fs/segment.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/fs.h> +#include <linux/f2fs_fs.h> +#include <linux/bio.h> +#include <linux/blkdev.h> +#include <linux/vmalloc.h> + +#include "f2fs.h" +#include "segment.h" +#include "node.h" + +static int need_to_flush(struct f2fs_sb_info *sbi) +{ + unsigned int pages_per_sec = (1 << sbi->log_blocks_per_seg) * + sbi->segs_per_sec; + int node_secs = ((get_pages(sbi, F2FS_DIRTY_NODES) + pages_per_sec - 1) + >> sbi->log_blocks_per_seg) / sbi->segs_per_sec; + int dent_secs = ((get_pages(sbi, F2FS_DIRTY_DENTS) + pages_per_sec - 1) + >> sbi->log_blocks_per_seg) / sbi->segs_per_sec; + + if (sbi->por_doing) + return 0; + + if (free_sections(sbi) <= (node_secs + 2 * dent_secs + + reserved_sections(sbi))) + return 1; + return 0; +} + +/* + * This function balances dirty node and dentry pages. + * In addition, it controls garbage collection. + */ +void f2fs_balance_fs(struct f2fs_sb_info *sbi) +{ + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = LONG_MAX, + .for_reclaim = 0, + }; + + if (sbi->por_doing) + return; + + /* + * We should do checkpoint when there are so many dirty node pages + * with enough free segments. After then, we should do GC. + */ + if (need_to_flush(sbi)) { + sync_dirty_dir_inodes(sbi); + sync_node_pages(sbi, 0, &wbc); + } + + if (has_not_enough_free_secs(sbi)) { + mutex_lock(&sbi->gc_mutex); + f2fs_gc(sbi, 1); + } +} + +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); + dirty_type = sentry->type; + if (!test_and_set_bit(segno, dirty_i->dirty_segmap[dirty_type])) + dirty_i->nr_dirty[dirty_type]++; + } +} + +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); + dirty_type = sentry->type; + if (test_and_clear_bit(segno, + dirty_i->dirty_segmap[dirty_type])) + dirty_i->nr_dirty[dirty_type]--; + clear_bit(segno, dirty_i->victim_segmap[FG_GC]); + clear_bit(segno, dirty_i->victim_segmap[BG_GC]); + } +} + +/* + * 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. + */ +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); + return; +} + +/* + * 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, offset = 0; + 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, + offset); + if (segno >= total_segs) + break; + __set_test_and_free(sbi, segno); + offset = segno + 1; + } + mutex_unlock(&dirty_i->seglist_lock); +} + +void clear_prefree_segments(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int segno, offset = 0; + 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, + offset); + if (segno >= total_segs) + break; + + offset = segno + 1; + if (test_and_clear_bit(segno, dirty_i->dirty_segmap[PRE])) + dirty_i->nr_dirty[PRE]--; + + /* Let's use trim */ + if (test_opt(sbi, DISCARD)) + blkdev_issue_discard(sbi->sb->s_bdev, + START_BLOCK(sbi, segno) << + sbi->log_sectors_per_block, + 1 << (sbi->log_sectors_per_block + + sbi->log_blocks_per_seg), + GFP_NOFS, 0); + } + mutex_unlock(&dirty_i->seglist_lock); +} + +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); + + 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); + + 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, unsigned short offset) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + void *addr = curseg->sum_blk; + addr += offset * sizeof(struct f2fs_summary); + memcpy(addr, sum, sizeof(struct f2fs_summary)); + return; +} + +/* + * Calculate the number of current summary pages for writing + */ +int npages_for_summary_flush(struct f2fs_sb_info *sbi) +{ + int total_size_bytes = 0; + int valid_sum_count = 0; + int i, sum_space; + + 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); + } + + total_size_bytes = valid_sum_count * (SUMMARY_SIZE + 1) + + sizeof(struct nat_journal) + 2 + + sizeof(struct sit_journal) + 2; + sum_space = PAGE_CACHE_SIZE - SUM_FOOTER_SIZE; + if (total_size_bytes < sum_space) + return 1; + else if (total_size_bytes < 2 * sum_space) + 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 unsigned int check_prefree_segments(struct f2fs_sb_info *sbi, + int ofs_unit, int type) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned long *prefree_segmap = dirty_i->dirty_segmap[PRE]; + unsigned int segno, next_segno, i; + int ofs = 0; + + /* + * If there is not enough reserved sections, + * we should not reuse prefree segments. + */ + if (has_not_enough_free_secs(sbi)) + return NULL_SEGNO; + + /* + * NODE page should not reuse prefree segment, + * since those information is used for SPOR. + */ + if (IS_NODESEG(type)) + return NULL_SEGNO; +next: + segno = find_next_bit(prefree_segmap, TOTAL_SEGS(sbi), ofs++); + ofs = ((segno / ofs_unit) * ofs_unit) + ofs_unit; + if (segno < TOTAL_SEGS(sbi)) { + /* skip intermediate segments in a section */ + if (segno % ofs_unit) + goto next; + + /* skip if whole section is not prefree */ + next_segno = find_next_zero_bit(prefree_segmap, + TOTAL_SEGS(sbi), segno + 1); + if (next_segno - segno < ofs_unit) + goto next; + + /* skip if whole section was not free at the last checkpoint */ + for (i = 0; i < ofs_unit; i++) + if (get_seg_entry(sbi, segno)->ckpt_valid_blocks) + goto next; + return segno; + } + return NULL_SEGNO; +} + +/* + * 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 total_secs = sbi->total_sections; + unsigned int segno, secno, zoneno; + unsigned int total_zones = sbi->total_sections / 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 < TOTAL_SEGS(sbi)) + goto got_it; + } +find_other_zone: + secno = find_next_zero_bit(free_i->free_secmap, total_secs, hint); + if (secno >= total_secs) { + if (dir == ALLOC_RIGHT) { + secno = find_next_zero_bit(free_i->free_secmap, + total_secs, 0); + BUG_ON(secno >= total_secs); + } 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, 0); + BUG_ON(left_start >= total_secs); + 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 */ + 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, curseg->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); + block_t ofs; + for (ofs = start; ofs < sbi->blocks_per_seg; ofs++) { + if (!f2fs_test_bit(ofs, se->ckpt_valid_map) + && !f2fs_test_bit(ofs, se->cur_valid_map)) + break; + } + seg->next_blkoff = ofs; +} + +/* + * 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); + } +} + +/* + * 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); + unsigned int ofs_unit; + + if (force) { + new_curseg(sbi, type, true); + goto out; + } + + ofs_unit = need_SSR(sbi) ? 1 : sbi->segs_per_sec; + curseg->next_segno = check_prefree_segments(sbi, ofs_unit, type); + + if (curseg->next_segno != NULL_SEGNO) + change_curseg(sbi, type, false); + else if (type == CURSEG_WARM_NODE) + 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); +out: + sbi->segment_count[curseg->alloc_type]++; +} + +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 void f2fs_end_io_write(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 bio_private *p = bio->bi_private; + + do { + struct page *page = bvec->bv_page; + + if (--bvec >= bio->bi_io_vec) + prefetchw(&bvec->bv_page->flags); + if (!uptodate) { + SetPageError(page); + if (page->mapping) + set_bit(AS_EIO, &page->mapping->flags); + set_ckpt_flags(p->sbi->ckpt, CP_ERROR_FLAG); + set_page_dirty(page); + } + end_page_writeback(page); + dec_page_count(p->sbi, F2FS_WRITEBACK); + } while (bvec >= bio->bi_io_vec); + + if (p->is_sync) + complete(p->wait); + kfree(p); + bio_put(bio); +} + +struct bio *f2fs_bio_alloc(struct block_device *bdev, int npages) +{ + struct bio *bio; + struct bio_private *priv; +retry: + priv = kmalloc(sizeof(struct bio_private), GFP_NOFS); + if (!priv) { + cond_resched(); + goto retry; + } + + /* No failure on bio allocation */ + bio = bio_alloc(GFP_NOIO, npages); + bio->bi_bdev = bdev; + bio->bi_private = priv; + return bio; +} + +static void do_submit_bio(struct f2fs_sb_info *sbi, + enum page_type type, bool sync) +{ + int rw = sync ? WRITE_SYNC : WRITE; + enum page_type btype = type > META ? META : type; + + if (type >= META_FLUSH) + rw = WRITE_FLUSH_FUA; + + if (sbi->bio[btype]) { + struct bio_private *p = sbi->bio[btype]->bi_private; + p->sbi = sbi; + sbi->bio[btype]->bi_end_io = f2fs_end_io_write; + if (type == META_FLUSH) { + DECLARE_COMPLETION_ONSTACK(wait); + p->is_sync = true; + p->wait = &wait; + submit_bio(rw, sbi->bio[btype]); + wait_for_completion(&wait); + } else { + p->is_sync = false; + submit_bio(rw, sbi->bio[btype]); + } + sbi->bio[btype] = NULL; + } +} + +void f2fs_submit_bio(struct f2fs_sb_info *sbi, enum page_type type, bool sync) +{ + down_write(&sbi->bio_sem); + do_submit_bio(sbi, type, sync); + up_write(&sbi->bio_sem); +} + +static void submit_write_page(struct f2fs_sb_info *sbi, struct page *page, + block_t blk_addr, enum page_type type) +{ + struct block_device *bdev = sbi->sb->s_bdev; + + verify_block_addr(sbi, blk_addr); + + down_write(&sbi->bio_sem); + + inc_page_count(sbi, F2FS_WRITEBACK); + + if (sbi->bio[type] && sbi->last_block_in_bio[type] != blk_addr - 1) + do_submit_bio(sbi, type, false); +alloc_new: + if (sbi->bio[type] == NULL) { + sbi->bio[type] = f2fs_bio_alloc(bdev, bio_get_nr_vecs(bdev)); + sbi->bio[type]->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr); + /* + * The end_io will be assigned at the sumbission phase. + * Until then, let bio_add_page() merge consecutive IOs as much + * as possible. + */ + } + + if (bio_add_page(sbi->bio[type], page, PAGE_CACHE_SIZE, 0) < + PAGE_CACHE_SIZE) { + do_submit_bio(sbi, type, false); + goto alloc_new; + } + + sbi->last_block_in_bio[type] = blk_addr; + + up_write(&sbi->bio_sem); +} + +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) || is_cold_file(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); + case 6: + return __get_segment_type_6(page, p_type); + default: + BUG(); + } +} + +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, enum page_type p_type) +{ + struct sit_info *sit_i = SIT_I(sbi); + struct curseg_info *curseg; + unsigned int old_cursegno; + int type; + + type = __get_segment_type(page, p_type); + 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, curseg->next_blkoff); + + mutex_lock(&sit_i->sentry_lock); + __refresh_next_blkoff(sbi, curseg); + sbi->block_count[curseg->alloc_type]++; + + /* + * 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 (p_type == NODE) + fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg)); + + /* writeout dirty page into bdev */ + submit_write_page(sbi, page, *new_blkaddr, p_type); + + mutex_unlock(&curseg->curseg_mutex); +} + +int write_meta_page(struct f2fs_sb_info *sbi, struct page *page, + struct writeback_control *wbc) +{ + if (wbc->for_reclaim) + return AOP_WRITEPAGE_ACTIVATE; + + set_page_writeback(page); + submit_write_page(sbi, page, page->index, META); + return 0; +} + +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; + set_summary(&sum, nid, 0, 0); + do_write_page(sbi, page, old_blkaddr, new_blkaddr, &sum, NODE); +} + +void write_data_page(struct inode *inode, struct page *page, + struct dnode_of_data *dn, block_t old_blkaddr, + block_t *new_blkaddr) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct f2fs_summary sum; + struct node_info ni; + + BUG_ON(old_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, old_blkaddr, + new_blkaddr, &sum, DATA); +} + +void rewrite_data_page(struct f2fs_sb_info *sbi, struct page *page, + block_t old_blk_addr) +{ + submit_write_page(sbi, page, old_blk_addr, DATA); +} + +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, curseg->next_blkoff); + + 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); + + 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, curseg->next_blkoff); + + /* 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); + submit_write_page(sbi, page, new_blkaddr, NODE); + f2fs_submit_bio(sbi, NODE, true); + 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); +} + +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; + + set_page_dirty(page); + + /* 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; + set_page_dirty(page); + + if (written_size + SUMMARY_SIZE <= PAGE_CACHE_SIZE - + SUM_FOOTER_SIZE) + continue; + + f2fs_put_page(page, 1); + page = NULL; + } + } + if (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); + return; +} + +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); + 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 1; + } + return 0; +} + +/* + * 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); + + 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(sbi->total_sections * + 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 = kzalloc(bitmap_size, GFP_KERNEL); + if (!dst_bitmap) + return -ENOMEM; + memcpy(dst_bitmap, src_bitmap, bitmap_size); + + /* 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(sbi->total_sections); + 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 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; + unsigned int start; + + for (start = 0; 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; + int i; + + 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; + } + } +} + +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; + unsigned short valid_blocks; + + while (segno < TOTAL_SEGS(sbi)) { + /* find dirty segment based on free segmap */ + segno = find_next_inuse(free_i, TOTAL_SEGS(sbi), offset); + if (segno >= TOTAL_SEGS(sbi)) + 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_segmap(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi)); + + dirty_i->victim_segmap[FG_GC] = kzalloc(bitmap_size, GFP_KERNEL); + dirty_i->victim_segmap[BG_GC] = kzalloc(bitmap_size, GFP_KERNEL); + if (!dirty_i->victim_segmap[FG_GC] || !dirty_i->victim_segmap[BG_GC]) + 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); + dirty_i->nr_dirty[i] = 0; + if (!dirty_i->dirty_segmap[i]) + return -ENOMEM; + } + + init_dirty_segmap(sbi); + return init_victim_segmap(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); + + 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); +} + +void reset_victim_segmap(struct f2fs_sb_info *sbi) +{ + unsigned int bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi)); + memset(DIRTY_I(sbi)->victim_segmap[FG_GC], 0, bitmap_size); +} + +static void destroy_victim_segmap(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + + kfree(dirty_i->victim_segmap[FG_GC]); + kfree(dirty_i->victim_segmap[BG_GC]); +} + +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_segmap(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); + destroy_dirty_segmap(sbi); + destroy_curseg(sbi); + destroy_free_segmap(sbi); + destroy_sit_info(sbi); + sbi->sm_info = NULL; + kfree(sm_info); +} diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h new file mode 100644 index 000000000000..0948405af6f5 --- /dev/null +++ b/fs/f2fs/segment.h @@ -0,0 +1,618 @@ +/* + * 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. + */ +/* constant macro */ +#define NULL_SEGNO ((unsigned int)(~0)) + +/* V: Logical segment # in volume, R: Relative segment # in main area */ +#define GET_L2R_SEGNO(free_i, segno) (segno - free_i->start_segno) +#define GET_R2L_SEGNO(free_i, segno) (segno + free_i->start_segno) + +#define IS_DATASEG(t) \ + ((t == CURSEG_HOT_DATA) || (t == CURSEG_COLD_DATA) || \ + (t == CURSEG_WARM_DATA)) + +#define IS_NODESEG(t) \ + ((t == CURSEG_HOT_NODE) || (t == CURSEG_COLD_NODE) || \ + (t == CURSEG_WARM_NODE)) + +#define IS_CURSEG(sbi, segno) \ + ((segno == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) || \ + (segno == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) || \ + (segno == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) || \ + (segno == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) || \ + (segno == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) || \ + (segno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno)) + +#define IS_CURSEC(sbi, secno) \ + ((secno == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno / \ + sbi->segs_per_sec) || \ + (secno == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno / \ + sbi->segs_per_sec) || \ + (secno == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno / \ + sbi->segs_per_sec) || \ + (secno == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno / \ + sbi->segs_per_sec) || \ + (secno == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno / \ + sbi->segs_per_sec) || \ + (secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \ + sbi->segs_per_sec)) \ + +#define START_BLOCK(sbi, segno) \ + (SM_I(sbi)->seg0_blkaddr + \ + (GET_R2L_SEGNO(FREE_I(sbi), segno) << sbi->log_blocks_per_seg)) +#define NEXT_FREE_BLKADDR(sbi, curseg) \ + (START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff) + +#define MAIN_BASE_BLOCK(sbi) (SM_I(sbi)->main_blkaddr) + +#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr) \ + ((blk_addr) - SM_I(sbi)->seg0_blkaddr) +#define GET_SEGNO_FROM_SEG0(sbi, blk_addr) \ + (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> sbi->log_blocks_per_seg) +#define GET_SEGNO(sbi, blk_addr) \ + (((blk_addr == NULL_ADDR) || (blk_addr == NEW_ADDR)) ? \ + NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \ + GET_SEGNO_FROM_SEG0(sbi, blk_addr))) +#define GET_SECNO(sbi, segno) \ + ((segno) / sbi->segs_per_sec) +#define GET_ZONENO_FROM_SEGNO(sbi, segno) \ + ((segno / sbi->segs_per_sec) / sbi->secs_per_zone) + +#define GET_SUM_BLOCK(sbi, segno) \ + ((sbi->sm_info->ssa_blkaddr) + segno) + +#define GET_SUM_TYPE(footer) ((footer)->entry_type) +#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = type) + +#define SIT_ENTRY_OFFSET(sit_i, segno) \ + (segno % sit_i->sents_per_block) +#define SIT_BLOCK_OFFSET(sit_i, segno) \ + (segno / SIT_ENTRY_PER_BLOCK) +#define START_SEGNO(sit_i, segno) \ + (SIT_BLOCK_OFFSET(sit_i, segno) * SIT_ENTRY_PER_BLOCK) +#define f2fs_bitmap_size(nr) \ + (BITS_TO_LONGS(nr) * sizeof(unsigned long)) +#define TOTAL_SEGS(sbi) (SM_I(sbi)->main_segments) + +#define SECTOR_FROM_BLOCK(sbi, blk_addr) \ + (blk_addr << ((sbi)->log_blocksize - F2FS_LOG_SECTOR_SIZE)) + +/* during checkpoint, bio_private is used to synchronize the last bio */ +struct bio_private { + struct f2fs_sb_info *sbi; + bool is_sync; + void *wait; +}; + +/* + * indicate a block allocation direction: RIGHT and LEFT. + * RIGHT means allocating new sections towards the end of volume. + * LEFT means the opposite direction. + */ +enum { + ALLOC_RIGHT = 0, + ALLOC_LEFT +}; + +/* + * In the victim_sel_policy->alloc_mode, there are two block allocation modes. + * LFS writes data sequentially with cleaning operations. + * SSR (Slack Space Recycle) reuses obsolete space without cleaning operations. + */ +enum { + LFS = 0, + SSR +}; + +/* + * In the victim_sel_policy->gc_mode, there are two gc, aka cleaning, modes. + * GC_CB is based on cost-benefit algorithm. + * GC_GREEDY is based on greedy algorithm. + */ +enum { + GC_CB = 0, + GC_GREEDY +}; + +/* + * BG_GC means the background cleaning job. + * FG_GC means the on-demand cleaning job. + */ +enum { + BG_GC = 0, + FG_GC +}; + +/* for a function parameter to select a victim segment */ +struct victim_sel_policy { + int alloc_mode; /* LFS or SSR */ + int gc_mode; /* GC_CB or GC_GREEDY */ + unsigned long *dirty_segmap; /* dirty segment bitmap */ + unsigned int offset; /* last scanned bitmap offset */ + unsigned int ofs_unit; /* bitmap search unit */ + unsigned int min_cost; /* minimum cost */ + unsigned int min_segno; /* segment # having min. cost */ +}; + +struct seg_entry { + unsigned short valid_blocks; /* # of valid blocks */ + unsigned char *cur_valid_map; /* validity bitmap of blocks */ + /* + * # of valid blocks and the validity bitmap stored in the the last + * checkpoint pack. This information is used by the SSR mode. + */ + unsigned short ckpt_valid_blocks; + unsigned char *ckpt_valid_map; + unsigned char type; /* segment type like CURSEG_XXX_TYPE */ + unsigned long long mtime; /* modification time of the segment */ +}; + +struct sec_entry { + unsigned int valid_blocks; /* # of valid blocks in a section */ +}; + +struct segment_allocation { + void (*allocate_segment)(struct f2fs_sb_info *, int, bool); +}; + +struct sit_info { + const struct segment_allocation *s_ops; + + block_t sit_base_addr; /* start block address of SIT area */ + block_t sit_blocks; /* # of blocks used by SIT area */ + block_t written_valid_blocks; /* # of valid blocks in main area */ + char *sit_bitmap; /* SIT bitmap pointer */ + unsigned int bitmap_size; /* SIT bitmap size */ + + unsigned long *dirty_sentries_bitmap; /* bitmap for dirty sentries */ + unsigned int dirty_sentries; /* # of dirty sentries */ + unsigned int sents_per_block; /* # of SIT entries per block */ + struct mutex sentry_lock; /* to protect SIT cache */ + struct seg_entry *sentries; /* SIT segment-level cache */ + struct sec_entry *sec_entries; /* SIT section-level cache */ + + /* for cost-benefit algorithm in cleaning procedure */ + unsigned long long elapsed_time; /* elapsed time after mount */ + unsigned long long mounted_time; /* mount time */ + unsigned long long min_mtime; /* min. modification time */ + unsigned long long max_mtime; /* max. modification time */ +}; + +struct free_segmap_info { + unsigned int start_segno; /* start segment number logically */ + unsigned int free_segments; /* # of free segments */ + unsigned int free_sections; /* # of free sections */ + rwlock_t segmap_lock; /* free segmap lock */ + unsigned long *free_segmap; /* free segment bitmap */ + unsigned long *free_secmap; /* free section bitmap */ +}; + +/* Notice: The order of dirty type is same with CURSEG_XXX in f2fs.h */ +enum dirty_type { + DIRTY_HOT_DATA, /* dirty segments assigned as hot data logs */ + DIRTY_WARM_DATA, /* dirty segments assigned as warm data logs */ + DIRTY_COLD_DATA, /* dirty segments assigned as cold data logs */ + DIRTY_HOT_NODE, /* dirty segments assigned as hot node logs */ + DIRTY_WARM_NODE, /* dirty segments assigned as warm node logs */ + DIRTY_COLD_NODE, /* dirty segments assigned as cold node logs */ + DIRTY, /* to count # of dirty segments */ + PRE, /* to count # of entirely obsolete segments */ + NR_DIRTY_TYPE +}; + +struct dirty_seglist_info { + const struct victim_selection *v_ops; /* victim selction operation */ + unsigned long *dirty_segmap[NR_DIRTY_TYPE]; + struct mutex seglist_lock; /* lock for segment bitmaps */ + int nr_dirty[NR_DIRTY_TYPE]; /* # of dirty segments */ + unsigned long *victim_segmap[2]; /* BG_GC, FG_GC */ +}; + +/* victim selection function for cleaning and SSR */ +struct victim_selection { + int (*get_victim)(struct f2fs_sb_info *, unsigned int *, + int, int, char); +}; + +/* for active log information */ +struct curseg_info { + struct mutex curseg_mutex; /* lock for consistency */ + struct f2fs_summary_block *sum_blk; /* cached summary block */ + unsigned char alloc_type; /* current allocation type */ + unsigned int segno; /* current segment number */ + unsigned short next_blkoff; /* next block offset to write */ + unsigned int zone; /* current zone number */ + unsigned int next_segno; /* preallocated segment */ +}; + +/* + * inline functions + */ +static inline struct curseg_info *CURSEG_I(struct f2fs_sb_info *sbi, int type) +{ + return (struct curseg_info *)(SM_I(sbi)->curseg_array + type); +} + +static inline struct seg_entry *get_seg_entry(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + struct sit_info *sit_i = SIT_I(sbi); + return &sit_i->sentries[segno]; +} + +static inline struct sec_entry *get_sec_entry(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + struct sit_info *sit_i = SIT_I(sbi); + return &sit_i->sec_entries[GET_SECNO(sbi, segno)]; +} + +static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi, + unsigned int segno, int section) +{ + /* + * In order to get # of valid blocks in a section instantly from many + * segments, f2fs manages two counting structures separately. + */ + if (section > 1) + return get_sec_entry(sbi, segno)->valid_blocks; + else + return get_seg_entry(sbi, segno)->valid_blocks; +} + +static inline void seg_info_from_raw_sit(struct seg_entry *se, + struct f2fs_sit_entry *rs) +{ + se->valid_blocks = GET_SIT_VBLOCKS(rs); + se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs); + memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE); + memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE); + se->type = GET_SIT_TYPE(rs); + se->mtime = le64_to_cpu(rs->mtime); +} + +static inline void seg_info_to_raw_sit(struct seg_entry *se, + struct f2fs_sit_entry *rs) +{ + unsigned short raw_vblocks = (se->type << SIT_VBLOCKS_SHIFT) | + se->valid_blocks; + rs->vblocks = cpu_to_le16(raw_vblocks); + memcpy(rs->valid_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE); + memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE); + se->ckpt_valid_blocks = se->valid_blocks; + rs->mtime = cpu_to_le64(se->mtime); +} + +static inline unsigned int find_next_inuse(struct free_segmap_info *free_i, + unsigned int max, unsigned int segno) +{ + unsigned int ret; + read_lock(&free_i->segmap_lock); + ret = find_next_bit(free_i->free_segmap, max, segno); + read_unlock(&free_i->segmap_lock); + return ret; +} + +static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int secno = segno / sbi->segs_per_sec; + unsigned int start_segno = secno * sbi->segs_per_sec; + unsigned int next; + + write_lock(&free_i->segmap_lock); + clear_bit(segno, free_i->free_segmap); + free_i->free_segments++; + + next = find_next_bit(free_i->free_segmap, TOTAL_SEGS(sbi), start_segno); + if (next >= start_segno + sbi->segs_per_sec) { + clear_bit(secno, free_i->free_secmap); + free_i->free_sections++; + } + write_unlock(&free_i->segmap_lock); +} + +static inline void __set_inuse(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int secno = segno / sbi->segs_per_sec; + set_bit(segno, free_i->free_segmap); + free_i->free_segments--; + if (!test_and_set_bit(secno, free_i->free_secmap)) + free_i->free_sections--; +} + +static inline void __set_test_and_free(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int secno = segno / sbi->segs_per_sec; + unsigned int start_segno = secno * sbi->segs_per_sec; + unsigned int next; + + write_lock(&free_i->segmap_lock); + if (test_and_clear_bit(segno, free_i->free_segmap)) { + free_i->free_segments++; + + next = find_next_bit(free_i->free_segmap, TOTAL_SEGS(sbi), + start_segno); + if (next >= start_segno + sbi->segs_per_sec) { + if (test_and_clear_bit(secno, free_i->free_secmap)) + free_i->free_sections++; + } + } + write_unlock(&free_i->segmap_lock); +} + +static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int secno = segno / sbi->segs_per_sec; + write_lock(&free_i->segmap_lock); + if (!test_and_set_bit(segno, free_i->free_segmap)) { + free_i->free_segments--; + if (!test_and_set_bit(secno, free_i->free_secmap)) + free_i->free_sections--; + } + write_unlock(&free_i->segmap_lock); +} + +static inline void get_sit_bitmap(struct f2fs_sb_info *sbi, + void *dst_addr) +{ + struct sit_info *sit_i = SIT_I(sbi); + memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size); +} + +static inline block_t written_block_count(struct f2fs_sb_info *sbi) +{ + struct sit_info *sit_i = SIT_I(sbi); + block_t vblocks; + + mutex_lock(&sit_i->sentry_lock); + vblocks = sit_i->written_valid_blocks; + mutex_unlock(&sit_i->sentry_lock); + + return vblocks; +} + +static inline unsigned int free_segments(struct f2fs_sb_info *sbi) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int free_segs; + + read_lock(&free_i->segmap_lock); + free_segs = free_i->free_segments; + read_unlock(&free_i->segmap_lock); + + return free_segs; +} + +static inline int reserved_segments(struct f2fs_sb_info *sbi) +{ + return SM_I(sbi)->reserved_segments; +} + +static inline unsigned int free_sections(struct f2fs_sb_info *sbi) +{ + struct free_segmap_info *free_i = FREE_I(sbi); + unsigned int free_secs; + + read_lock(&free_i->segmap_lock); + free_secs = free_i->free_sections; + read_unlock(&free_i->segmap_lock); + + return free_secs; +} + +static inline unsigned int prefree_segments(struct f2fs_sb_info *sbi) +{ + return DIRTY_I(sbi)->nr_dirty[PRE]; +} + +static inline unsigned int dirty_segments(struct f2fs_sb_info *sbi) +{ + return DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_DATA] + + DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_DATA] + + DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_DATA] + + DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_NODE] + + DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_NODE] + + DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_NODE]; +} + +static inline int overprovision_segments(struct f2fs_sb_info *sbi) +{ + return SM_I(sbi)->ovp_segments; +} + +static inline int overprovision_sections(struct f2fs_sb_info *sbi) +{ + return ((unsigned int) overprovision_segments(sbi)) / sbi->segs_per_sec; +} + +static inline int reserved_sections(struct f2fs_sb_info *sbi) +{ + return ((unsigned int) reserved_segments(sbi)) / sbi->segs_per_sec; +} + +static inline bool need_SSR(struct f2fs_sb_info *sbi) +{ + return (free_sections(sbi) < overprovision_sections(sbi)); +} + +static inline int get_ssr_segment(struct f2fs_sb_info *sbi, int type) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + return DIRTY_I(sbi)->v_ops->get_victim(sbi, + &(curseg)->next_segno, BG_GC, type, SSR); +} + +static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi) +{ + return free_sections(sbi) <= reserved_sections(sbi); +} + +static inline int utilization(struct f2fs_sb_info *sbi) +{ + return (long int)valid_user_blocks(sbi) * 100 / + (long int)sbi->user_block_count; +} + +/* + * Sometimes f2fs may be better to drop out-of-place update policy. + * So, if fs utilization is over MIN_IPU_UTIL, then f2fs tries to write + * data in the original place likewise other traditional file systems. + * But, currently set 100 in percentage, which means it is disabled. + * See below need_inplace_update(). + */ +#define MIN_IPU_UTIL 100 +static inline bool need_inplace_update(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + if (S_ISDIR(inode->i_mode)) + return false; + if (need_SSR(sbi) && utilization(sbi) > MIN_IPU_UTIL) + return true; + return false; +} + +static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi, + int type) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + return curseg->segno; +} + +static inline unsigned char curseg_alloc_type(struct f2fs_sb_info *sbi, + int type) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + return curseg->alloc_type; +} + +static inline unsigned short curseg_blkoff(struct f2fs_sb_info *sbi, int type) +{ + struct curseg_info *curseg = CURSEG_I(sbi, type); + return curseg->next_blkoff; +} + +static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno) +{ + unsigned int end_segno = SM_I(sbi)->segment_count - 1; + BUG_ON(segno > end_segno); +} + +/* + * This function is used for only debugging. + * NOTE: In future, we have to remove this function. + */ +static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr) +{ + struct f2fs_sm_info *sm_info = SM_I(sbi); + block_t total_blks = sm_info->segment_count << sbi->log_blocks_per_seg; + block_t start_addr = sm_info->seg0_blkaddr; + block_t end_addr = start_addr + total_blks - 1; + BUG_ON(blk_addr < start_addr); + BUG_ON(blk_addr > end_addr); +} + +/* + * Summary block is always treated as invalid block + */ +static inline void check_block_count(struct f2fs_sb_info *sbi, + int segno, struct f2fs_sit_entry *raw_sit) +{ + struct f2fs_sm_info *sm_info = SM_I(sbi); + unsigned int end_segno = sm_info->segment_count - 1; + int valid_blocks = 0; + int i; + + /* check segment usage */ + BUG_ON(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg); + + /* check boundary of a given segment number */ + BUG_ON(segno > end_segno); + + /* check bitmap with valid block count */ + for (i = 0; i < sbi->blocks_per_seg; i++) + if (f2fs_test_bit(i, raw_sit->valid_map)) + valid_blocks++; + BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks); +} + +static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi, + unsigned int start) +{ + struct sit_info *sit_i = SIT_I(sbi); + unsigned int offset = SIT_BLOCK_OFFSET(sit_i, start); + block_t blk_addr = sit_i->sit_base_addr + offset; + + check_seg_range(sbi, start); + + /* calculate sit block address */ + if (f2fs_test_bit(offset, sit_i->sit_bitmap)) + blk_addr += sit_i->sit_blocks; + + return blk_addr; +} + +static inline pgoff_t next_sit_addr(struct f2fs_sb_info *sbi, + pgoff_t block_addr) +{ + struct sit_info *sit_i = SIT_I(sbi); + block_addr -= sit_i->sit_base_addr; + if (block_addr < sit_i->sit_blocks) + block_addr += sit_i->sit_blocks; + else + block_addr -= sit_i->sit_blocks; + + return block_addr + sit_i->sit_base_addr; +} + +static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start) +{ + unsigned int block_off = SIT_BLOCK_OFFSET(sit_i, start); + + if (f2fs_test_bit(block_off, sit_i->sit_bitmap)) + f2fs_clear_bit(block_off, sit_i->sit_bitmap); + else + f2fs_set_bit(block_off, sit_i->sit_bitmap); +} + +static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi) +{ + struct sit_info *sit_i = SIT_I(sbi); + return sit_i->elapsed_time + CURRENT_TIME_SEC.tv_sec - + sit_i->mounted_time; +} + +static inline void set_summary(struct f2fs_summary *sum, nid_t nid, + unsigned int ofs_in_node, unsigned char version) +{ + sum->nid = cpu_to_le32(nid); + sum->ofs_in_node = cpu_to_le16(ofs_in_node); + sum->version = version; +} + +static inline block_t start_sum_block(struct f2fs_sb_info *sbi) +{ + return __start_cp_addr(sbi) + + le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum); +} + +static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type) +{ + return __start_cp_addr(sbi) + + le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_total_block_count) + - (base + 1) + type; +} diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c new file mode 100644 index 000000000000..13867322cf5a --- /dev/null +++ b/fs/f2fs/super.c @@ -0,0 +1,657 @@ +/* + * fs/f2fs/super.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/module.h> +#include <linux/init.h> +#include <linux/fs.h> +#include <linux/statfs.h> +#include <linux/proc_fs.h> +#include <linux/buffer_head.h> +#include <linux/backing-dev.h> +#include <linux/kthread.h> +#include <linux/parser.h> +#include <linux/mount.h> +#include <linux/seq_file.h> +#include <linux/random.h> +#include <linux/exportfs.h> +#include <linux/f2fs_fs.h> + +#include "f2fs.h" +#include "node.h" +#include "xattr.h" + +static struct kmem_cache *f2fs_inode_cachep; + +enum { + Opt_gc_background_off, + Opt_disable_roll_forward, + Opt_discard, + Opt_noheap, + Opt_nouser_xattr, + Opt_noacl, + Opt_active_logs, + Opt_disable_ext_identify, + Opt_err, +}; + +static match_table_t f2fs_tokens = { + {Opt_gc_background_off, "background_gc_off"}, + {Opt_disable_roll_forward, "disable_roll_forward"}, + {Opt_discard, "discard"}, + {Opt_noheap, "no_heap"}, + {Opt_nouser_xattr, "nouser_xattr"}, + {Opt_noacl, "noacl"}, + {Opt_active_logs, "active_logs=%u"}, + {Opt_disable_ext_identify, "disable_ext_identify"}, + {Opt_err, NULL}, +}; + +static void init_once(void *foo) +{ + struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo; + + inode_init_once(&fi->vfs_inode); +} + +static struct inode *f2fs_alloc_inode(struct super_block *sb) +{ + struct f2fs_inode_info *fi; + + fi = kmem_cache_alloc(f2fs_inode_cachep, GFP_NOFS | __GFP_ZERO); + if (!fi) + return NULL; + + init_once((void *) fi); + + /* Initilize f2fs-specific inode info */ + fi->vfs_inode.i_version = 1; + atomic_set(&fi->dirty_dents, 0); + fi->i_current_depth = 1; + fi->i_advise = 0; + rwlock_init(&fi->ext.ext_lock); + + set_inode_flag(fi, FI_NEW_INODE); + + return &fi->vfs_inode; +} + +static void f2fs_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + kmem_cache_free(f2fs_inode_cachep, F2FS_I(inode)); +} + +static void f2fs_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, f2fs_i_callback); +} + +static void f2fs_put_super(struct super_block *sb) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + + f2fs_destroy_stats(sbi); + stop_gc_thread(sbi); + + write_checkpoint(sbi, false, true); + + iput(sbi->node_inode); + iput(sbi->meta_inode); + + /* destroy f2fs internal modules */ + destroy_node_manager(sbi); + destroy_segment_manager(sbi); + + kfree(sbi->ckpt); + + sb->s_fs_info = NULL; + brelse(sbi->raw_super_buf); + kfree(sbi); +} + +int f2fs_sync_fs(struct super_block *sb, int sync) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + int ret = 0; + + if (!sbi->s_dirty && !get_pages(sbi, F2FS_DIRTY_NODES)) + return 0; + + if (sync) + write_checkpoint(sbi, false, false); + + return ret; +} + +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 = valid_inode_count(sbi); + buf->f_ffree = sbi->total_node_count - valid_node_count(sbi); + + buf->f_namelen = F2FS_MAX_NAME_LEN; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); + + return 0; +} + +static int f2fs_show_options(struct seq_file *seq, struct dentry *root) +{ + struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb); + + if (test_opt(sbi, BG_GC)) + seq_puts(seq, ",background_gc_on"); + else + seq_puts(seq, ",background_gc_off"); + if (test_opt(sbi, DISABLE_ROLL_FORWARD)) + seq_puts(seq, ",disable_roll_forward"); + if (test_opt(sbi, DISCARD)) + seq_puts(seq, ",discard"); + if (test_opt(sbi, NOHEAP)) + seq_puts(seq, ",no_heap_alloc"); +#ifdef CONFIG_F2FS_FS_XATTR + if (test_opt(sbi, XATTR_USER)) + seq_puts(seq, ",user_xattr"); + else + seq_puts(seq, ",nouser_xattr"); +#endif +#ifdef CONFIG_F2FS_FS_POSIX_ACL + if (test_opt(sbi, POSIX_ACL)) + seq_puts(seq, ",acl"); + else + seq_puts(seq, ",noacl"); +#endif + if (test_opt(sbi, DISABLE_EXT_IDENTIFY)) + seq_puts(seq, ",disable_ext_indentify"); + + seq_printf(seq, ",active_logs=%u", sbi->active_logs); + + return 0; +} + +static struct super_operations f2fs_sops = { + .alloc_inode = f2fs_alloc_inode, + .destroy_inode = f2fs_destroy_inode, + .write_inode = f2fs_write_inode, + .show_options = f2fs_show_options, + .evict_inode = f2fs_evict_inode, + .put_super = f2fs_put_super, + .sync_fs = f2fs_sync_fs, + .statfs = f2fs_statfs, +}; + +static struct inode *f2fs_nfs_get_inode(struct super_block *sb, + u64 ino, u32 generation) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct inode *inode; + + if (ino < F2FS_ROOT_INO(sbi)) + return ERR_PTR(-ESTALE); + + /* + * f2fs_iget isn't quite right if the inode is currently unallocated! + * However f2fs_iget currently does appropriate checks to handle stale + * inodes so everything is OK. + */ + inode = f2fs_iget(sb, ino); + if (IS_ERR(inode)) + return ERR_CAST(inode); + if (generation && inode->i_generation != generation) { + /* we didn't find the right inode.. */ + iput(inode); + return ERR_PTR(-ESTALE); + } + return inode; +} + +static struct dentry *f2fs_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_dentry(sb, fid, fh_len, fh_type, + f2fs_nfs_get_inode); +} + +static struct dentry *f2fs_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_parent(sb, fid, fh_len, fh_type, + f2fs_nfs_get_inode); +} + +static const struct export_operations f2fs_export_ops = { + .fh_to_dentry = f2fs_fh_to_dentry, + .fh_to_parent = f2fs_fh_to_parent, + .get_parent = f2fs_get_parent, +}; + +static int parse_options(struct f2fs_sb_info *sbi, char *options) +{ + substring_t args[MAX_OPT_ARGS]; + char *p; + int arg = 0; + + if (!options) + return 0; + + while ((p = strsep(&options, ",")) != NULL) { + int token; + if (!*p) + continue; + /* + * Initialize args struct so we know whether arg was + * found; some options take optional arguments. + */ + args[0].to = args[0].from = NULL; + token = match_token(p, f2fs_tokens, args); + + switch (token) { + case Opt_gc_background_off: + clear_opt(sbi, BG_GC); + break; + case Opt_disable_roll_forward: + set_opt(sbi, DISABLE_ROLL_FORWARD); + break; + case Opt_discard: + set_opt(sbi, DISCARD); + break; + case Opt_noheap: + set_opt(sbi, NOHEAP); + break; +#ifdef CONFIG_F2FS_FS_XATTR + case Opt_nouser_xattr: + clear_opt(sbi, XATTR_USER); + break; +#else + case Opt_nouser_xattr: + pr_info("nouser_xattr options not supported\n"); + break; +#endif +#ifdef CONFIG_F2FS_FS_POSIX_ACL + case Opt_noacl: + clear_opt(sbi, POSIX_ACL); + break; +#else + case Opt_noacl: + pr_info("noacl options not supported\n"); + break; +#endif + case Opt_active_logs: + if (args->from && match_int(args, &arg)) + return -EINVAL; + if (arg != 2 && arg != 4 && arg != 6) + return -EINVAL; + sbi->active_logs = arg; + break; + case Opt_disable_ext_identify: + set_opt(sbi, DISABLE_EXT_IDENTIFY); + break; + default: + pr_err("Unrecognized mount option \"%s\" or missing value\n", + p); + return -EINVAL; + } + } + return 0; +} + +static loff_t max_file_size(unsigned bits) +{ + loff_t result = ADDRS_PER_INODE; + loff_t leaf_count = ADDRS_PER_BLOCK; + + /* two direct node blocks */ + result += (leaf_count * 2); + + /* two indirect node blocks */ + leaf_count *= NIDS_PER_BLOCK; + result += (leaf_count * 2); + + /* one double indirect node block */ + leaf_count *= NIDS_PER_BLOCK; + result += leaf_count; + + result <<= bits; + return result; +} + +static int sanity_check_raw_super(struct f2fs_super_block *raw_super) +{ + unsigned int blocksize; + + if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) + return 1; + + /* Currently, support only 4KB block size */ + blocksize = 1 << le32_to_cpu(raw_super->log_blocksize); + if (blocksize != PAGE_CACHE_SIZE) + return 1; + if (le32_to_cpu(raw_super->log_sectorsize) != + F2FS_LOG_SECTOR_SIZE) + return 1; + if (le32_to_cpu(raw_super->log_sectors_per_block) != + F2FS_LOG_SECTORS_PER_BLOCK) + return 1; + return 0; +} + +static int sanity_check_ckpt(struct f2fs_super_block *raw_super, + struct f2fs_checkpoint *ckpt) +{ + unsigned int total, fsmeta; + + total = le32_to_cpu(raw_super->segment_count); + fsmeta = le32_to_cpu(raw_super->segment_count_ckpt); + fsmeta += le32_to_cpu(raw_super->segment_count_sit); + fsmeta += le32_to_cpu(raw_super->segment_count_nat); + fsmeta += le32_to_cpu(ckpt->rsvd_segment_count); + fsmeta += le32_to_cpu(raw_super->segment_count_ssa); + + if (fsmeta >= total) + return 1; + 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); + + for (i = 0; i < NR_COUNT_TYPE; i++) + atomic_set(&sbi->nr_pages[i], 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 temporary block size */ + if (!sb_set_blocksize(sb, F2FS_BLKSIZE)) + goto free_sbi; + + /* read f2fs raw super block */ + raw_super_buf = sb_bread(sb, 0); + if (!raw_super_buf) { + err = -EIO; + goto free_sbi; + } + raw_super = (struct f2fs_super_block *) + ((char *)raw_super_buf->b_data + F2FS_SUPER_OFFSET); + + /* 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 */ + if (parse_options(sbi, (char *)data)) + goto free_sb_buf; + + /* sanity checking of raw super */ + if (sanity_check_raw_super(raw_super)) + goto free_sb_buf; + + sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize)); + sb->s_max_links = F2FS_LINK_MAX; + get_random_bytes(&sbi->s_next_generation, sizeof(u32)); + + sb->s_op = &f2fs_sops; + sb->s_xattr = f2fs_xattr_handlers; + sb->s_export_op = &f2fs_export_ops; + sb->s_magic = F2FS_SUPER_MAGIC; + sb->s_fs_info = sbi; + sb->s_time_gran = 1; + sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | + (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0); + memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid)); + + /* init f2fs-specific super block info */ + sbi->sb = sb; + sbi->raw_super = raw_super; + sbi->raw_super_buf = raw_super_buf; + mutex_init(&sbi->gc_mutex); + mutex_init(&sbi->write_inode); + mutex_init(&sbi->writepages); + mutex_init(&sbi->cp_mutex); + for (i = 0; i < NR_LOCK_TYPE; i++) + mutex_init(&sbi->fs_lock[i]); + sbi->por_doing = 0; + spin_lock_init(&sbi->stat_lock); + init_rwsem(&sbi->bio_sem); + init_sb_info(sbi); + + /* get an inode for meta space */ + sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi)); + if (IS_ERR(sbi->meta_inode)) { + err = PTR_ERR(sbi->meta_inode); + goto free_sb_buf; + } + + err = get_valid_checkpoint(sbi); + if (err) + goto free_meta_inode; + + /* sanity checking of checkpoint */ + err = -EINVAL; + if (sanity_check_ckpt(raw_super, sbi->ckpt)) + 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 super block */ + if (!sb_set_blocksize(sb, sbi->blocksize)) + goto free_cp; + + init_orphan_info(sbi); + + /* setup f2fs internal modules */ + err = build_segment_manager(sbi); + if (err) + goto free_sm; + err = build_node_manager(sbi); + if (err) + 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)) { + err = PTR_ERR(sbi->node_inode); + goto free_nm; + } + + /* if there are nt orphan nodes free them */ + err = -EINVAL; + if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) && + recover_orphan_inodes(sbi)) + goto free_node_inode; + + /* read root inode and dentry */ + root = f2fs_iget(sb, F2FS_ROOT_INO(sbi)); + if (IS_ERR(root)) { + err = PTR_ERR(root); + goto free_node_inode; + } + if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) + goto free_root_inode; + + sb->s_root = d_make_root(root); /* allocate root dentry */ + if (!sb->s_root) { + err = -ENOMEM; + goto free_root_inode; + } + + /* recover fsynced data */ + if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) && + !test_opt(sbi, DISABLE_ROLL_FORWARD)) + recover_fsync_data(sbi); + + /* After POR, we can run background GC thread */ + err = start_gc_thread(sbi); + if (err) + goto fail; + + err = f2fs_build_stats(sbi); + if (err) + goto fail; + + return 0; +fail: + stop_gc_thread(sbi); +free_root_inode: + dput(sb->s_root); + sb->s_root = NULL; +free_node_inode: + iput(sbi->node_inode); +free_nm: + destroy_node_manager(sbi); +free_sm: + destroy_segment_manager(sbi); +free_cp: + kfree(sbi->ckpt); +free_meta_inode: + make_bad_inode(sbi->meta_inode); + iput(sbi->meta_inode); +free_sb_buf: + brelse(raw_super_buf); +free_sbi: + kfree(sbi); + return err; +} + +static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) +{ + return mount_bdev(fs_type, flags, dev_name, data, f2fs_fill_super); +} + +static struct file_system_type f2fs_fs_type = { + .owner = THIS_MODULE, + .name = "f2fs", + .mount = f2fs_mount, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, +}; + +static int init_inodecache(void) +{ + f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache", + sizeof(struct f2fs_inode_info), NULL); + if (f2fs_inode_cachep == NULL) + return -ENOMEM; + return 0; +} + +static void destroy_inodecache(void) +{ + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); + kmem_cache_destroy(f2fs_inode_cachep); +} + +static int __init init_f2fs_fs(void) +{ + int err; + + err = init_inodecache(); + if (err) + goto fail; + err = create_node_manager_caches(); + if (err) + goto fail; + err = create_gc_caches(); + if (err) + goto fail; + err = create_checkpoint_caches(); + if (err) + goto fail; + return register_filesystem(&f2fs_fs_type); +fail: + return err; +} + +static void __exit exit_f2fs_fs(void) +{ + destroy_root_stats(); + unregister_filesystem(&f2fs_fs_type); + destroy_checkpoint_caches(); + destroy_gc_caches(); + destroy_node_manager_caches(); + destroy_inodecache(); +} + +module_init(init_f2fs_fs) +module_exit(exit_f2fs_fs) + +MODULE_AUTHOR("Samsung Electronics's Praesto Team"); +MODULE_DESCRIPTION("Flash Friendly File System"); +MODULE_LICENSE("GPL"); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c new file mode 100644 index 000000000000..7d52e8dc0c59 --- /dev/null +++ b/fs/f2fs/xattr.c @@ -0,0 +1,440 @@ +/* + * fs/f2fs/xattr.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * Portions of this code from linux/fs/ext2/xattr.c + * + * Copyright (C) 2001-2003 Andreas Gruenbacher <agruen@suse.de> + * + * Fix by Harrison Xing <harrison@mountainviewdata.com>. + * Extended attributes for symlinks and special files added per + * suggestion of Luka Renko <luka.renko@hermes.si>. + * xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>, + * Red Hat Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/rwsem.h> +#include <linux/f2fs_fs.h> +#include "f2fs.h" +#include "xattr.h" + +static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); + int total_len, prefix_len = 0; + const char *prefix = NULL; + + switch (type) { + case F2FS_XATTR_INDEX_USER: + if (!test_opt(sbi, XATTR_USER)) + return -EOPNOTSUPP; + prefix = XATTR_USER_PREFIX; + prefix_len = XATTR_USER_PREFIX_LEN; + break; + case F2FS_XATTR_INDEX_TRUSTED: + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + prefix = XATTR_TRUSTED_PREFIX; + prefix_len = XATTR_TRUSTED_PREFIX_LEN; + break; + default: + return -EINVAL; + } + + total_len = prefix_len + name_len + 1; + if (list && total_len <= list_size) { + memcpy(list, prefix, prefix_len); + memcpy(list+prefix_len, name, name_len); + list[prefix_len + name_len] = '\0'; + } + return total_len; +} + +static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); + + switch (type) { + case F2FS_XATTR_INDEX_USER: + if (!test_opt(sbi, XATTR_USER)) + return -EOPNOTSUPP; + break; + case F2FS_XATTR_INDEX_TRUSTED: + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + break; + default: + return -EINVAL; + } + if (strcmp(name, "") == 0) + return -EINVAL; + return f2fs_getxattr(dentry->d_inode, type, name, + buffer, size); +} + +static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); + + switch (type) { + case F2FS_XATTR_INDEX_USER: + if (!test_opt(sbi, XATTR_USER)) + return -EOPNOTSUPP; + break; + case F2FS_XATTR_INDEX_TRUSTED: + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + break; + default: + return -EINVAL; + } + if (strcmp(name, "") == 0) + return -EINVAL; + + return f2fs_setxattr(dentry->d_inode, type, name, value, size); +} + +static size_t f2fs_xattr_advise_list(struct dentry *dentry, char *list, + size_t list_size, const char *name, size_t name_len, int type) +{ + const char *xname = F2FS_SYSTEM_ADVISE_PREFIX; + size_t size; + + if (type != F2FS_XATTR_INDEX_ADVISE) + return 0; + + size = strlen(xname) + 1; + if (list && size <= list_size) + memcpy(list, xname, size); + return size; +} + +static int f2fs_xattr_advise_get(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + struct inode *inode = dentry->d_inode; + + if (strcmp(name, "") != 0) + return -EINVAL; + + *((char *)buffer) = F2FS_I(inode)->i_advise; + return sizeof(char); +} + +static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, int type) +{ + struct inode *inode = dentry->d_inode; + + if (strcmp(name, "") != 0) + return -EINVAL; + if (!inode_owner_or_capable(inode)) + return -EPERM; + if (value == NULL) + return -EINVAL; + + F2FS_I(inode)->i_advise |= *(char *)value; + return 0; +} + +const struct xattr_handler f2fs_xattr_user_handler = { + .prefix = XATTR_USER_PREFIX, + .flags = F2FS_XATTR_INDEX_USER, + .list = f2fs_xattr_generic_list, + .get = f2fs_xattr_generic_get, + .set = f2fs_xattr_generic_set, +}; + +const struct xattr_handler f2fs_xattr_trusted_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .flags = F2FS_XATTR_INDEX_TRUSTED, + .list = f2fs_xattr_generic_list, + .get = f2fs_xattr_generic_get, + .set = f2fs_xattr_generic_set, +}; + +const struct xattr_handler f2fs_xattr_advise_handler = { + .prefix = F2FS_SYSTEM_ADVISE_PREFIX, + .flags = F2FS_XATTR_INDEX_ADVISE, + .list = f2fs_xattr_advise_list, + .get = f2fs_xattr_advise_get, + .set = f2fs_xattr_advise_set, +}; + +static const struct xattr_handler *f2fs_xattr_handler_map[] = { + [F2FS_XATTR_INDEX_USER] = &f2fs_xattr_user_handler, +#ifdef CONFIG_F2FS_FS_POSIX_ACL + [F2FS_XATTR_INDEX_POSIX_ACL_ACCESS] = &f2fs_xattr_acl_access_handler, + [F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &f2fs_xattr_acl_default_handler, +#endif + [F2FS_XATTR_INDEX_TRUSTED] = &f2fs_xattr_trusted_handler, + [F2FS_XATTR_INDEX_ADVISE] = &f2fs_xattr_advise_handler, +}; + +const struct xattr_handler *f2fs_xattr_handlers[] = { + &f2fs_xattr_user_handler, +#ifdef CONFIG_F2FS_FS_POSIX_ACL + &f2fs_xattr_acl_access_handler, + &f2fs_xattr_acl_default_handler, +#endif + &f2fs_xattr_trusted_handler, + &f2fs_xattr_advise_handler, + NULL, +}; + +static inline const struct xattr_handler *f2fs_xattr_handler(int name_index) +{ + const struct xattr_handler *handler = NULL; + + if (name_index > 0 && name_index < ARRAY_SIZE(f2fs_xattr_handler_map)) + handler = f2fs_xattr_handler_map[name_index]; + return handler; +} + +int f2fs_getxattr(struct inode *inode, int name_index, const char *name, + void *buffer, size_t buffer_size) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_xattr_entry *entry; + struct page *page; + void *base_addr; + int error = 0, found = 0; + int value_len, name_len; + + if (name == NULL) + return -EINVAL; + name_len = strlen(name); + + if (!fi->i_xattr_nid) + return -ENODATA; + + page = get_node_page(sbi, fi->i_xattr_nid); + base_addr = page_address(page); + + list_for_each_xattr(entry, base_addr) { + if (entry->e_name_index != name_index) + continue; + if (entry->e_name_len != name_len) + continue; + if (!memcmp(entry->e_name, name, name_len)) { + found = 1; + break; + } + } + if (!found) { + error = -ENODATA; + goto cleanup; + } + + value_len = le16_to_cpu(entry->e_value_size); + + if (buffer && value_len > buffer_size) { + error = -ERANGE; + goto cleanup; + } + + if (buffer) { + char *pval = entry->e_name + entry->e_name_len; + memcpy(buffer, pval, value_len); + } + error = value_len; + +cleanup: + f2fs_put_page(page, 1); + return error; +} + +ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) +{ + struct inode *inode = dentry->d_inode; + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_xattr_entry *entry; + struct page *page; + void *base_addr; + int error = 0; + size_t rest = buffer_size; + + if (!fi->i_xattr_nid) + return 0; + + page = get_node_page(sbi, fi->i_xattr_nid); + base_addr = page_address(page); + + list_for_each_xattr(entry, base_addr) { + const struct xattr_handler *handler = + f2fs_xattr_handler(entry->e_name_index); + size_t size; + + if (!handler) + continue; + + size = handler->list(dentry, buffer, rest, entry->e_name, + entry->e_name_len, handler->flags); + if (buffer && size > rest) { + error = -ERANGE; + goto cleanup; + } + + if (buffer) + buffer += size; + rest -= size; + } + error = buffer_size - rest; +cleanup: + f2fs_put_page(page, 1); + return error; +} + +int f2fs_setxattr(struct inode *inode, int name_index, const char *name, + const void *value, size_t value_len) +{ + struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_xattr_header *header = NULL; + struct f2fs_xattr_entry *here, *last; + struct page *page; + void *base_addr; + int error, found, free, name_len, newsize; + char *pval; + + if (name == NULL) + return -EINVAL; + name_len = strlen(name); + + if (value == NULL) + value_len = 0; + + if (name_len > 255 || value_len > MAX_VALUE_LEN) + return -ERANGE; + + mutex_lock_op(sbi, NODE_NEW); + if (!fi->i_xattr_nid) { + /* Allocate new attribute block */ + struct dnode_of_data dn; + + if (!alloc_nid(sbi, &fi->i_xattr_nid)) { + mutex_unlock_op(sbi, NODE_NEW); + return -ENOSPC; + } + set_new_dnode(&dn, inode, NULL, NULL, fi->i_xattr_nid); + mark_inode_dirty(inode); + + page = new_node_page(&dn, XATTR_NODE_OFFSET); + if (IS_ERR(page)) { + alloc_nid_failed(sbi, fi->i_xattr_nid); + fi->i_xattr_nid = 0; + mutex_unlock_op(sbi, NODE_NEW); + return PTR_ERR(page); + } + + alloc_nid_done(sbi, fi->i_xattr_nid); + base_addr = page_address(page); + header = XATTR_HDR(base_addr); + header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC); + header->h_refcount = cpu_to_le32(1); + } else { + /* The inode already has an extended attribute block. */ + page = get_node_page(sbi, fi->i_xattr_nid); + if (IS_ERR(page)) { + mutex_unlock_op(sbi, NODE_NEW); + return PTR_ERR(page); + } + + base_addr = page_address(page); + header = XATTR_HDR(base_addr); + } + + if (le32_to_cpu(header->h_magic) != F2FS_XATTR_MAGIC) { + error = -EIO; + goto cleanup; + } + + /* find entry with wanted name. */ + found = 0; + list_for_each_xattr(here, base_addr) { + if (here->e_name_index != name_index) + continue; + if (here->e_name_len != name_len) + continue; + if (!memcmp(here->e_name, name, name_len)) { + found = 1; + break; + } + } + + last = here; + + while (!IS_XATTR_LAST_ENTRY(last)) + last = XATTR_NEXT_ENTRY(last); + + newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + + name_len + value_len); + + /* 1. Check space */ + if (value) { + /* If value is NULL, it is remove operation. + * In case of update operation, we caculate free. + */ + free = MIN_OFFSET - ((char *)last - (char *)header); + if (found) + free = free - ENTRY_SIZE(here); + + if (free < newsize) { + error = -ENOSPC; + goto cleanup; + } + } + + /* 2. Remove old entry */ + if (found) { + /* If entry is found, remove old entry. + * If not found, remove operation is not needed. + */ + struct f2fs_xattr_entry *next = XATTR_NEXT_ENTRY(here); + int oldsize = ENTRY_SIZE(here); + + memmove(here, next, (char *)last - (char *)next); + last = (struct f2fs_xattr_entry *)((char *)last - oldsize); + memset(last, 0, oldsize); + } + + /* 3. Write new entry */ + if (value) { + /* Before we come here, old entry is removed. + * We just write new entry. */ + memset(last, 0, newsize); + last->e_name_index = name_index; + last->e_name_len = name_len; + memcpy(last->e_name, name, name_len); + pval = last->e_name + name_len; + memcpy(pval, value, value_len); + last->e_value_size = cpu_to_le16(value_len); + } + + set_page_dirty(page); + f2fs_put_page(page, 1); + + if (is_inode_flag_set(fi, FI_ACL_MODE)) { + inode->i_mode = fi->i_acl_mode; + inode->i_ctime = CURRENT_TIME; + clear_inode_flag(fi, FI_ACL_MODE); + } + f2fs_write_inode(inode, NULL); + mutex_unlock_op(sbi, NODE_NEW); + + return 0; +cleanup: + f2fs_put_page(page, 1); + mutex_unlock_op(sbi, NODE_NEW); + return error; +} diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h new file mode 100644 index 000000000000..49c9558305e3 --- /dev/null +++ b/fs/f2fs/xattr.h @@ -0,0 +1,145 @@ +/* + * fs/f2fs/xattr.h + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * Portions of this code from linux/fs/ext2/xattr.h + * + * On-disk format of extended attributes for the ext2 filesystem. + * + * (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __F2FS_XATTR_H__ +#define __F2FS_XATTR_H__ + +#include <linux/init.h> +#include <linux/xattr.h> + +/* Magic value in attribute blocks */ +#define F2FS_XATTR_MAGIC 0xF2F52011 + +/* Maximum number of references to one attribute block */ +#define F2FS_XATTR_REFCOUNT_MAX 1024 + +/* Name indexes */ +#define F2FS_SYSTEM_ADVISE_PREFIX "system.advise" +#define F2FS_XATTR_INDEX_USER 1 +#define F2FS_XATTR_INDEX_POSIX_ACL_ACCESS 2 +#define F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT 3 +#define F2FS_XATTR_INDEX_TRUSTED 4 +#define F2FS_XATTR_INDEX_LUSTRE 5 +#define F2FS_XATTR_INDEX_SECURITY 6 +#define F2FS_XATTR_INDEX_ADVISE 7 + +struct f2fs_xattr_header { + __le32 h_magic; /* magic number for identification */ + __le32 h_refcount; /* reference count */ + __u32 h_reserved[4]; /* zero right now */ +}; + +struct f2fs_xattr_entry { + __u8 e_name_index; + __u8 e_name_len; + __le16 e_value_size; /* size of attribute value */ + char e_name[0]; /* attribute name */ +}; + +#define XATTR_HDR(ptr) ((struct f2fs_xattr_header *)(ptr)) +#define XATTR_ENTRY(ptr) ((struct f2fs_xattr_entry *)(ptr)) +#define XATTR_FIRST_ENTRY(ptr) (XATTR_ENTRY(XATTR_HDR(ptr)+1)) +#define XATTR_ROUND (3) + +#define XATTR_ALIGN(size) ((size + XATTR_ROUND) & ~XATTR_ROUND) + +#define ENTRY_SIZE(entry) (XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + \ + entry->e_name_len + le16_to_cpu(entry->e_value_size))) + +#define XATTR_NEXT_ENTRY(entry) ((struct f2fs_xattr_entry *)((char *)(entry) +\ + ENTRY_SIZE(entry))) + +#define IS_XATTR_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0) + +#define list_for_each_xattr(entry, addr) \ + for (entry = XATTR_FIRST_ENTRY(addr);\ + !IS_XATTR_LAST_ENTRY(entry);\ + entry = XATTR_NEXT_ENTRY(entry)) + + +#define MIN_OFFSET XATTR_ALIGN(PAGE_SIZE - \ + sizeof(struct node_footer) - \ + sizeof(__u32)) + +#define MAX_VALUE_LEN (MIN_OFFSET - sizeof(struct f2fs_xattr_header) - \ + sizeof(struct f2fs_xattr_entry)) + +/* + * On-disk structure of f2fs_xattr + * We use only 1 block for xattr. + * + * +--------------------+ + * | f2fs_xattr_header | + * | | + * +--------------------+ + * | f2fs_xattr_entry | + * | .e_name_index = 1 | + * | .e_name_len = 3 | + * | .e_value_size = 14 | + * | .e_name = "foo" | + * | "value_of_xattr" |<- value_offs = e_name + e_name_len + * +--------------------+ + * | f2fs_xattr_entry | + * | .e_name_index = 4 | + * | .e_name = "bar" | + * +--------------------+ + * | | + * | Free | + * | | + * +--------------------+<- MIN_OFFSET + * | node_footer | + * | (nid, ino, offset) | + * +--------------------+ + * + **/ + +#ifdef CONFIG_F2FS_FS_XATTR +extern const struct xattr_handler f2fs_xattr_user_handler; +extern const struct xattr_handler f2fs_xattr_trusted_handler; +extern const struct xattr_handler f2fs_xattr_acl_access_handler; +extern const struct xattr_handler f2fs_xattr_acl_default_handler; +extern const struct xattr_handler f2fs_xattr_advise_handler; + +extern const struct xattr_handler *f2fs_xattr_handlers[]; + +extern int f2fs_setxattr(struct inode *inode, int name_index, const char *name, + const void *value, size_t value_len); +extern int f2fs_getxattr(struct inode *inode, int name_index, const char *name, + void *buffer, size_t buffer_size); +extern ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, + size_t buffer_size); + +#else + +#define f2fs_xattr_handlers NULL +static inline int f2fs_setxattr(struct inode *inode, int name_index, + const char *name, const void *value, size_t value_len) +{ + return -EOPNOTSUPP; +} +static inline int f2fs_getxattr(struct inode *inode, int name_index, + const char *name, void *buffer, size_t buffer_size) +{ + return -EOPNOTSUPP; +} +static inline ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, + size_t buffer_size) +{ + return -EOPNOTSUPP; +} +#endif + +#endif /* __F2FS_XATTR_H__ */ diff --git a/fs/fhandle.c b/fs/fhandle.c index cccdc874bb55..999ff5c3cab0 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -52,7 +52,7 @@ static long do_sys_name_to_handle(struct path *path, handle_bytes = handle_dwords * sizeof(u32); handle->handle_bytes = handle_bytes; if ((handle->handle_bytes > f_handle.handle_bytes) || - (retval == 255) || (retval == -ENOSPC)) { + (retval == FILEID_INVALID) || (retval == -ENOSPC)) { /* As per old exportfs_encode_fh documentation * we could return ENOSPC to indicate overflow * But file system returned 255 always. So handle diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c index e6c38159622f..e761ee95617f 100644 --- a/fs/nfsd/fault_inject.c +++ b/fs/nfsd/fault_inject.c @@ -8,61 +8,144 @@ #include <linux/fs.h> #include <linux/debugfs.h> #include <linux/module.h> +#include <linux/nsproxy.h> +#include <linux/sunrpc/clnt.h> +#include <asm/uaccess.h> #include "state.h" -#include "fault_inject.h" +#include "netns.h" struct nfsd_fault_inject_op { char *file; - void (*func)(u64); + u64 (*forget)(struct nfs4_client *, u64); + u64 (*print)(struct nfs4_client *, u64); }; static struct nfsd_fault_inject_op inject_ops[] = { { .file = "forget_clients", - .func = nfsd_forget_clients, + .forget = nfsd_forget_client, + .print = nfsd_print_client, }, { .file = "forget_locks", - .func = nfsd_forget_locks, + .forget = nfsd_forget_client_locks, + .print = nfsd_print_client_locks, }, { .file = "forget_openowners", - .func = nfsd_forget_openowners, + .forget = nfsd_forget_client_openowners, + .print = nfsd_print_client_openowners, }, { .file = "forget_delegations", - .func = nfsd_forget_delegations, + .forget = nfsd_forget_client_delegations, + .print = nfsd_print_client_delegations, }, { .file = "recall_delegations", - .func = nfsd_recall_delegations, + .forget = nfsd_recall_client_delegations, + .print = nfsd_print_client_delegations, }, }; static long int NUM_INJECT_OPS = sizeof(inject_ops) / sizeof(struct nfsd_fault_inject_op); static struct dentry *debug_dir; -static int nfsd_inject_set(void *op_ptr, u64 val) +static void nfsd_inject_set(struct nfsd_fault_inject_op *op, u64 val) { - struct nfsd_fault_inject_op *op = op_ptr; + u64 count = 0; if (val == 0) printk(KERN_INFO "NFSD Fault Injection: %s (all)", op->file); else printk(KERN_INFO "NFSD Fault Injection: %s (n = %llu)", op->file, val); - op->func(val); - return 0; + nfs4_lock_state(); + count = nfsd_for_n_state(val, op->forget); + nfs4_unlock_state(); + printk(KERN_INFO "NFSD: %s: found %llu", op->file, count); } -static int nfsd_inject_get(void *data, u64 *val) +static void nfsd_inject_set_client(struct nfsd_fault_inject_op *op, + struct sockaddr_storage *addr, + size_t addr_size) { - *val = 0; - return 0; + char buf[INET6_ADDRSTRLEN]; + struct nfs4_client *clp; + u64 count; + + nfs4_lock_state(); + clp = nfsd_find_client(addr, addr_size); + if (clp) { + count = op->forget(clp, 0); + rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf)); + printk(KERN_INFO "NFSD [%s]: Client %s had %llu state object(s)\n", op->file, buf, count); + } + nfs4_unlock_state(); +} + +static void nfsd_inject_get(struct nfsd_fault_inject_op *op, u64 *val) +{ + nfs4_lock_state(); + *val = nfsd_for_n_state(0, op->print); + nfs4_unlock_state(); } -DEFINE_SIMPLE_ATTRIBUTE(fops_nfsd, nfsd_inject_get, nfsd_inject_set, "%llu\n"); +static ssize_t fault_inject_read(struct file *file, char __user *buf, + size_t len, loff_t *ppos) +{ + static u64 val; + char read_buf[25]; + size_t size, ret; + loff_t pos = *ppos; + + if (!pos) + nfsd_inject_get(file->f_dentry->d_inode->i_private, &val); + size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val); + + if (pos < 0) + return -EINVAL; + if (pos >= size || !len) + return 0; + if (len > size - pos) + len = size - pos; + ret = copy_to_user(buf, read_buf + pos, len); + if (ret == len) + return -EFAULT; + len -= ret; + *ppos = pos + len; + return len; +} + +static ssize_t fault_inject_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + char write_buf[INET6_ADDRSTRLEN]; + size_t size = min(sizeof(write_buf) - 1, len); + struct net *net = current->nsproxy->net_ns; + struct sockaddr_storage sa; + u64 val; + + if (copy_from_user(write_buf, buf, size)) + return -EFAULT; + write_buf[size] = '\0'; + + size = rpc_pton(net, write_buf, size, (struct sockaddr *)&sa, sizeof(sa)); + if (size > 0) + nfsd_inject_set_client(file->f_dentry->d_inode->i_private, &sa, size); + else { + val = simple_strtoll(write_buf, NULL, 0); + nfsd_inject_set(file->f_dentry->d_inode->i_private, val); + } + return len; /* on success, claim we got the whole input */ +} + +static const struct file_operations fops_nfsd = { + .owner = THIS_MODULE, + .read = fault_inject_read, + .write = fault_inject_write, +}; void nfsd_fault_inject_cleanup(void) { diff --git a/fs/nfsd/fault_inject.h b/fs/nfsd/fault_inject.h deleted file mode 100644 index 90bd0570956c..000000000000 --- a/fs/nfsd/fault_inject.h +++ /dev/null @@ -1,28 +0,0 @@ -/* - * Copyright (c) 2011 Bryan Schumaker <bjschuma@netapp.com> - * - * Function definitions for fault injection - */ - -#ifndef LINUX_NFSD_FAULT_INJECT_H -#define LINUX_NFSD_FAULT_INJECT_H - -#ifdef CONFIG_NFSD_FAULT_INJECTION -int nfsd_fault_inject_init(void); -void nfsd_fault_inject_cleanup(void); -void nfsd_forget_clients(u64); -void nfsd_forget_locks(u64); -void nfsd_forget_openowners(u64); -void nfsd_forget_delegations(u64); -void nfsd_recall_delegations(u64); -#else /* CONFIG_NFSD_FAULT_INJECTION */ -static inline int nfsd_fault_inject_init(void) { return 0; } -static inline void nfsd_fault_inject_cleanup(void) {} -static inline void nfsd_forget_clients(u64 num) {} -static inline void nfsd_forget_locks(u64 num) {} -static inline void nfsd_forget_openowners(u64 num) {} -static inline void nfsd_forget_delegations(u64 num) {} -static inline void nfsd_recall_delegations(u64 num) {} -#endif /* CONFIG_NFSD_FAULT_INJECTION */ - -#endif /* LINUX_NFSD_FAULT_INJECT_H */ diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 65c2431ea32f..1051bebff1b0 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -24,7 +24,18 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> +/* Hash tables for nfs4_clientid state */ +#define CLIENT_HASH_BITS 4 +#define CLIENT_HASH_SIZE (1 << CLIENT_HASH_BITS) +#define CLIENT_HASH_MASK (CLIENT_HASH_SIZE - 1) + +#define LOCKOWNER_INO_HASH_BITS 8 +#define LOCKOWNER_INO_HASH_SIZE (1 << LOCKOWNER_INO_HASH_BITS) + +#define SESSION_HASH_SIZE 512 + struct cld_net; +struct nfsd4_client_tracking_ops; struct nfsd_net { struct cld_net *cld_net; @@ -38,7 +49,62 @@ struct nfsd_net { struct lock_manager nfsd4_manager; bool grace_ended; time_t boot_time; + + /* + * reclaim_str_hashtbl[] holds known client info from previous reset/reboot + * used in reboot/reset lease grace period processing + * + * conf_id_hashtbl[], and conf_name_tree hold confirmed + * setclientid_confirmed info. + * + * unconf_str_hastbl[] and unconf_name_tree hold unconfirmed + * setclientid info. + */ + struct list_head *reclaim_str_hashtbl; + int reclaim_str_hashtbl_size; + struct list_head *conf_id_hashtbl; + struct rb_root conf_name_tree; + struct list_head *unconf_id_hashtbl; + struct rb_root unconf_name_tree; + struct list_head *ownerstr_hashtbl; + struct list_head *lockowner_ino_hashtbl; + struct list_head *sessionid_hashtbl; + /* + * client_lru holds client queue ordered by nfs4_client.cl_time + * for lease renewal. + * + * close_lru holds (open) stateowner queue ordered by nfs4_stateowner.so_time + * for last close replay. + * + * All of the above fields are protected by the client_mutex. + */ + struct list_head client_lru; + struct list_head close_lru; + + struct delayed_work laundromat_work; + + /* client_lock protects the client lru list and session hash table */ + spinlock_t client_lock; + + struct file *rec_file; + bool in_grace; + struct nfsd4_client_tracking_ops *client_tracking_ops; + + time_t nfsd4_lease; + time_t nfsd4_grace; + + bool nfsd_net_up; + + /* + * Time of server startup + */ + struct timeval nfssvc_boot; + + struct svc_serv *nfsd_serv; }; +/* Simple check to find out if a given net was properly initialized */ +#define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl) + extern int nfsd_net_id; #endif /* __NFSD_NETNS_H__ */ diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index b314888825d5..9170861c804a 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -253,7 +253,7 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, (resp->mask & NFS_ACL) ? resp->acl_access : NULL, (resp->mask & NFS_DFACL) ? resp->acl_default : NULL); while (w > 0) { - if (!rqstp->rq_respages[rqstp->rq_resused++]) + if (!*(rqstp->rq_next_page++)) return 0; w -= PAGE_SIZE; } diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index a596e9d987e4..9cbc1a841f87 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -184,7 +184,7 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, (resp->mask & NFS_ACL) ? resp->acl_access : NULL, (resp->mask & NFS_DFACL) ? resp->acl_default : NULL); while (w > 0) { - if (!rqstp->rq_respages[rqstp->rq_resused++]) + if (!*(rqstp->rq_next_page++)) return 0; w -= PAGE_SIZE; } diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 97d90d1c8608..1fc02dfdc5c4 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -460,7 +460,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, __be32 nfserr; int count = 0; loff_t offset; - int i; + struct page **p; caddr_t page_addr = NULL; dprintk("nfsd: READDIR+(3) %s %d bytes at %d\n", @@ -484,8 +484,8 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, &resp->common, nfs3svc_encode_entry_plus); memcpy(resp->verf, argp->verf, 8); - for (i=1; i<rqstp->rq_resused ; i++) { - page_addr = page_address(rqstp->rq_respages[i]); + for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) { + page_addr = page_address(*p); if (((caddr_t)resp->buffer >= page_addr) && ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) { diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 43f46cd9edea..324c0baf7cda 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -7,8 +7,10 @@ */ #include <linux/namei.h> +#include <linux/sunrpc/svc_xprt.h> #include "xdr3.h" #include "auth.h" +#include "netns.h" #define NFSDDBG_FACILITY NFSDDBG_XDR @@ -323,7 +325,7 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_readargs *args) { unsigned int len; - int v,pn; + int v; u32 max_blocksize = svc_max_payload(rqstp); if (!(p = decode_fh(p, &args->fh))) @@ -338,8 +340,9 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, /* set up the kvec */ v=0; while (len > 0) { - pn = rqstp->rq_resused++; - rqstp->rq_vec[v].iov_base = page_address(rqstp->rq_respages[pn]); + struct page *p = *(rqstp->rq_next_page++); + + rqstp->rq_vec[v].iov_base = page_address(p); rqstp->rq_vec[v].iov_len = len < PAGE_SIZE? len : PAGE_SIZE; len -= rqstp->rq_vec[v].iov_len; v++; @@ -461,8 +464,7 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, len = ntohl(*p++); if (len == 0 || len > NFS3_MAXPATHLEN || len >= PAGE_SIZE) return 0; - args->tname = new = - page_address(rqstp->rq_respages[rqstp->rq_resused++]); + args->tname = new = page_address(*(rqstp->rq_next_page++)); args->tlen = len; /* first copy and check from the first page */ old = (char*)p; @@ -533,8 +535,7 @@ nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, { if (!(p = decode_fh(p, &args->fh))) return 0; - args->buffer = - page_address(rqstp->rq_respages[rqstp->rq_resused++]); + args->buffer = page_address(*(rqstp->rq_next_page++)); return xdr_argsize_check(rqstp, p); } @@ -565,8 +566,7 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, if (args->count > PAGE_SIZE) args->count = PAGE_SIZE; - args->buffer = - page_address(rqstp->rq_respages[rqstp->rq_resused++]); + args->buffer = page_address(*(rqstp->rq_next_page++)); return xdr_argsize_check(rqstp, p); } @@ -575,7 +575,7 @@ int nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_readdirargs *args) { - int len, pn; + int len; u32 max_blocksize = svc_max_payload(rqstp); if (!(p = decode_fh(p, &args->fh))) @@ -590,9 +590,9 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p, args->count = len; while (len > 0) { - pn = rqstp->rq_resused++; + struct page *p = *(rqstp->rq_next_page++); if (!args->buffer) - args->buffer = page_address(rqstp->rq_respages[pn]); + args->buffer = page_address(p); len -= PAGE_SIZE; } @@ -720,12 +720,14 @@ int nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_writeres *resp) { + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + p = encode_wcc_data(rqstp, p, &resp->fh); if (resp->status == 0) { *p++ = htonl(resp->count); *p++ = htonl(resp->committed); - *p++ = htonl(nfssvc_boot.tv_sec); - *p++ = htonl(nfssvc_boot.tv_usec); + *p++ = htonl(nn->nfssvc_boot.tv_sec); + *p++ = htonl(nn->nfssvc_boot.tv_usec); } return xdr_ressize_check(rqstp, p); } @@ -876,7 +878,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen, common); __be32 *p = cd->buffer; caddr_t curr_page_addr = NULL; - int pn; /* current page number */ + struct page ** page; int slen; /* string (name) length */ int elen; /* estimated entry length in words */ int num_entry_words = 0; /* actual number of words */ @@ -913,8 +915,9 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen, } /* determine which page in rq_respages[] we are currently filling */ - for (pn=1; pn < cd->rqstp->rq_resused; pn++) { - curr_page_addr = page_address(cd->rqstp->rq_respages[pn]); + for (page = cd->rqstp->rq_respages + 1; + page < cd->rqstp->rq_next_page; page++) { + curr_page_addr = page_address(*page); if (((caddr_t)cd->buffer >= curr_page_addr) && ((caddr_t)cd->buffer < curr_page_addr + PAGE_SIZE)) @@ -929,14 +932,14 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen, if (plus) p = encode_entryplus_baggage(cd, p, name, namlen); num_entry_words = p - cd->buffer; - } else if (cd->rqstp->rq_respages[pn+1] != NULL) { + } else if (*(page+1) != NULL) { /* temporarily encode entry into next page, then move back to * current and next page in rq_respages[] */ __be32 *p1, *tmp; int len1, len2; /* grab next page for temporary storage of entry */ - p1 = tmp = page_address(cd->rqstp->rq_respages[pn+1]); + p1 = tmp = page_address(*(page+1)); p1 = encode_entry_baggage(cd, p1, name, namlen, ino); @@ -1082,11 +1085,13 @@ int nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p, struct nfsd3_commitres *resp) { + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + p = encode_wcc_data(rqstp, p, &resp->fh); /* Write verifier */ if (resp->status == 0) { - *p++ = htonl(nfssvc_boot.tv_sec); - *p++ = htonl(nfssvc_boot.tv_usec); + *p++ = htonl(nn->nfssvc_boot.tv_sec); + *p++ = htonl(nn->nfssvc_boot.tv_usec); } return xdr_ressize_check(rqstp, p); } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index bdf29c96e4cd..99bc85ff0217 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -36,6 +36,7 @@ #include <linux/slab.h> #include "nfsd.h" #include "state.h" +#include "netns.h" #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -625,20 +626,46 @@ static const struct rpc_program cb_program = { .pipe_dir_name = "nfsd4_cb", }; -static int max_cb_time(void) +static int max_cb_time(struct net *net) { - return max(nfsd4_lease/10, (time_t)1) * HZ; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + return max(nn->nfsd4_lease/10, (time_t)1) * HZ; } +static struct rpc_cred *callback_cred; + +int set_callback_cred(void) +{ + if (callback_cred) + return 0; + callback_cred = rpc_lookup_machine_cred("nfs"); + if (!callback_cred) + return -ENOMEM; + return 0; +} + +static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses) +{ + if (clp->cl_minorversion == 0) { + return get_rpccred(callback_cred); + } else { + struct rpc_auth *auth = client->cl_auth; + struct auth_cred acred = {}; + + acred.uid = ses->se_cb_sec.uid; + acred.gid = ses->se_cb_sec.gid; + return auth->au_ops->lookup_cred(client->cl_auth, &acred, 0); + } +} static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses) { struct rpc_timeout timeparms = { - .to_initval = max_cb_time(), + .to_initval = max_cb_time(clp->net), .to_retries = 0, }; struct rpc_create_args args = { - .net = &init_net, + .net = clp->net, .address = (struct sockaddr *) &conn->cb_addr, .addrsize = conn->cb_addrlen, .saddress = (struct sockaddr *) &conn->cb_saddr, @@ -648,6 +675,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c .flags = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET), }; struct rpc_clnt *client; + struct rpc_cred *cred; if (clp->cl_minorversion == 0) { if (!clp->cl_cred.cr_principal && @@ -666,7 +694,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c args.bc_xprt = conn->cb_xprt; args.prognumber = clp->cl_cb_session->se_cb_prog; args.protocol = XPRT_TRANSPORT_BC_TCP; - args.authflavor = RPC_AUTH_UNIX; + args.authflavor = ses->se_cb_sec.flavor; } /* Create RPC client */ client = rpc_create(&args); @@ -675,9 +703,14 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c PTR_ERR(client)); return PTR_ERR(client); } + cred = get_backchannel_cred(clp, client, ses); + if (IS_ERR(cred)) { + rpc_shutdown_client(client); + return PTR_ERR(cred); + } clp->cl_cb_client = client; + clp->cl_cb_cred = cred; return 0; - } static void warn_no_callback_path(struct nfs4_client *clp, int reason) @@ -714,18 +747,6 @@ static const struct rpc_call_ops nfsd4_cb_probe_ops = { .rpc_call_done = nfsd4_cb_probe_done, }; -static struct rpc_cred *callback_cred; - -int set_callback_cred(void) -{ - if (callback_cred) - return 0; - callback_cred = rpc_lookup_machine_cred("nfs"); - if (!callback_cred) - return -ENOMEM; - return 0; -} - static struct workqueue_struct *callback_wq; static void run_nfsd4_cb(struct nfsd4_callback *cb) @@ -743,7 +764,6 @@ static void do_probe_callback(struct nfs4_client *clp) cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL]; cb->cb_msg.rpc_argp = NULL; cb->cb_msg.rpc_resp = NULL; - cb->cb_msg.rpc_cred = callback_cred; cb->cb_ops = &nfsd4_cb_probe_ops; @@ -962,6 +982,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) if (clp->cl_cb_client) { rpc_shutdown_client(clp->cl_cb_client); clp->cl_cb_client = NULL; + put_rpccred(clp->cl_cb_cred); + clp->cl_cb_cred = NULL; } if (clp->cl_cb_conn.cb_xprt) { svc_xprt_put(clp->cl_cb_conn.cb_xprt); @@ -995,7 +1017,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) run_nfsd4_cb(cb); } -void nfsd4_do_callback_rpc(struct work_struct *w) +static void nfsd4_do_callback_rpc(struct work_struct *w) { struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback, cb_work); struct nfs4_client *clp = cb->cb_clp; @@ -1010,10 +1032,16 @@ void nfsd4_do_callback_rpc(struct work_struct *w) nfsd4_release_cb(cb); return; } + cb->cb_msg.rpc_cred = clp->cl_cb_cred; rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN, cb->cb_ops, cb); } +void nfsd4_init_callback(struct nfsd4_callback *cb) +{ + INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc); +} + void nfsd4_cb_recall(struct nfs4_delegation *dp) { struct nfsd4_callback *cb = &dp->dl_recall; @@ -1025,7 +1053,6 @@ void nfsd4_cb_recall(struct nfs4_delegation *dp) cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL]; cb->cb_msg.rpc_argp = cb; cb->cb_msg.rpc_resp = cb; - cb->cb_msg.rpc_cred = callback_cred; cb->cb_ops = &nfsd4_cb_recall_ops; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 6c9a4b291dba..9d1c5dba2bbb 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -40,6 +40,7 @@ #include "xdr4.h" #include "vfs.h" #include "current_stateid.h" +#include "netns.h" #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -194,6 +195,7 @@ static __be32 do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open) { struct svc_fh *resfh; + int accmode; __be32 status; resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL); @@ -253,9 +255,10 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o /* set reply cache */ fh_copy_shallow(&open->op_openowner->oo_owner.so_replay.rp_openfh, &resfh->fh_handle); - if (!open->op_created) - status = do_open_permission(rqstp, resfh, open, - NFSD_MAY_NOP); + accmode = NFSD_MAY_NOP; + if (open->op_created) + accmode |= NFSD_MAY_OWNER_OVERRIDE; + status = do_open_permission(rqstp, resfh, open, accmode); set_change_info(&open->op_cinfo, current_fh); fh_dup2(current_fh, resfh); out: @@ -304,6 +307,8 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { __be32 status; struct nfsd4_compoundres *resp; + struct net *net = SVC_NET(rqstp); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); dprintk("NFSD: nfsd4_open filename %.*s op_openowner %p\n", (int)open->op_fname.len, open->op_fname.data, @@ -331,7 +336,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* check seqid for replay. set nfs4_owner */ resp = rqstp->rq_resp; - status = nfsd4_process_open1(&resp->cstate, open); + status = nfsd4_process_open1(&resp->cstate, open, nn); if (status == nfserr_replay_me) { struct nfs4_replay *rp = &open->op_openowner->oo_owner.so_replay; fh_put(&cstate->current_fh); @@ -354,10 +359,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, /* Openowner is now set, so sequence id will get bumped. Now we need * these checks before we do any creates: */ status = nfserr_grace; - if (locks_in_grace(SVC_NET(rqstp)) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS) + if (locks_in_grace(net) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS) goto out; status = nfserr_no_grace; - if (!locks_in_grace(SVC_NET(rqstp)) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS) + if (!locks_in_grace(net) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS) goto out; switch (open->op_claim_type) { @@ -370,7 +375,9 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, break; case NFS4_OPEN_CLAIM_PREVIOUS: open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; - status = nfs4_check_open_reclaim(&open->op_clientid, cstate->minorversion); + status = nfs4_check_open_reclaim(&open->op_clientid, + cstate->minorversion, + nn); if (status) goto out; case NFS4_OPEN_CLAIM_FH: @@ -490,12 +497,13 @@ nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &access->ac_supported); } -static void gen_boot_verifier(nfs4_verifier *verifier) +static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net) { __be32 verf[2]; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); - verf[0] = (__be32)nfssvc_boot.tv_sec; - verf[1] = (__be32)nfssvc_boot.tv_usec; + verf[0] = (__be32)nn->nfssvc_boot.tv_sec; + verf[1] = (__be32)nn->nfssvc_boot.tv_usec; memcpy(verifier->data, verf, sizeof(verifier->data)); } @@ -503,7 +511,7 @@ static __be32 nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_commit *commit) { - gen_boot_verifier(&commit->co_verf); + gen_boot_verifier(&commit->co_verf, SVC_NET(rqstp)); return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset, commit->co_count); } @@ -684,6 +692,17 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (read->rd_offset >= OFFSET_MAX) return nfserr_inval; + /* + * If we do a zero copy read, then a client will see read data + * that reflects the state of the file *after* performing the + * following compound. + * + * To ensure proper ordering, we therefore turn off zero copy if + * the client wants us to do more in this compound: + */ + if (!nfsd4_last_compound_op(rqstp)) + rqstp->rq_splice_ok = false; + nfs4_lock_state(); /* check stateid */ if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), @@ -876,6 +895,24 @@ out: return status; } +static int fill_in_write_vector(struct kvec *vec, struct nfsd4_write *write) +{ + int i = 1; + int buflen = write->wr_buflen; + + vec[0].iov_base = write->wr_head.iov_base; + vec[0].iov_len = min_t(int, buflen, write->wr_head.iov_len); + buflen -= vec[0].iov_len; + + while (buflen) { + vec[i].iov_base = page_address(write->wr_pagelist[i - 1]); + vec[i].iov_len = min_t(int, PAGE_SIZE, buflen); + buflen -= vec[i].iov_len; + i++; + } + return i; +} + static __be32 nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_write *write) @@ -884,6 +921,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct file *filp = NULL; __be32 status = nfs_ok; unsigned long cnt; + int nvecs; /* no need to check permission - this will be done in nfsd_write() */ @@ -904,10 +942,13 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cnt = write->wr_buflen; write->wr_how_written = write->wr_stable_how; - gen_boot_verifier(&write->wr_verifier); + gen_boot_verifier(&write->wr_verifier, SVC_NET(rqstp)); + + nvecs = fill_in_write_vector(rqstp->rq_vec, write); + WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec)); status = nfsd_write(rqstp, &cstate->current_fh, filp, - write->wr_offset, rqstp->rq_vec, write->wr_vlen, + write->wr_offset, rqstp->rq_vec, nvecs, &cnt, &write->wr_how_written); if (filp) fput(filp); @@ -1666,6 +1707,12 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_name = "OP_EXCHANGE_ID", .op_rsize_bop = (nfsd4op_rsize)nfsd4_exchange_id_rsize, }, + [OP_BACKCHANNEL_CTL] = { + .op_func = (nfsd4op_func)nfsd4_backchannel_ctl, + .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, + .op_name = "OP_BACKCHANNEL_CTL", + .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + }, [OP_BIND_CONN_TO_SESSION] = { .op_func = (nfsd4op_func)nfsd4_bind_conn_to_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP @@ -1719,6 +1766,7 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_func = (nfsd4op_func)nfsd4_free_stateid, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_FREE_STATEID", + .op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid, .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, }; diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 43295d45cc2b..ba6fdd4a0455 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -58,13 +58,11 @@ struct nfsd4_client_tracking_ops { void (*create)(struct nfs4_client *); void (*remove)(struct nfs4_client *); int (*check)(struct nfs4_client *); - void (*grace_done)(struct net *, time_t); + void (*grace_done)(struct nfsd_net *, time_t); }; /* Globals */ -static struct file *rec_file; static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery"; -static struct nfsd4_client_tracking_ops *client_tracking_ops; static int nfs4_save_creds(const struct cred **original_creds) @@ -102,33 +100,39 @@ md5_to_hex(char *out, char *md5) *out = '\0'; } -__be32 -nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname) +static int +nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname) { struct xdr_netobj cksum; struct hash_desc desc; struct scatterlist sg; - __be32 status = nfserr_jukebox; + int status; dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n", clname->len, clname->data); desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP; desc.tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(desc.tfm)) + if (IS_ERR(desc.tfm)) { + status = PTR_ERR(desc.tfm); goto out_no_tfm; + } + cksum.len = crypto_hash_digestsize(desc.tfm); cksum.data = kmalloc(cksum.len, GFP_KERNEL); - if (cksum.data == NULL) + if (cksum.data == NULL) { + status = -ENOMEM; goto out; + } sg_init_one(&sg, clname->data, clname->len); - if (crypto_hash_digest(&desc, &sg, sg.length, cksum.data)) + status = crypto_hash_digest(&desc, &sg, sg.length, cksum.data); + if (status) goto out; md5_to_hex(dname, cksum.data); - status = nfs_ok; + status = 0; out: kfree(cksum.data); crypto_free_hash(desc.tfm); @@ -136,29 +140,61 @@ out_no_tfm: return status; } +/* + * If we had an error generating the recdir name for the legacy tracker + * then warn the admin. If the error doesn't appear to be transient, + * then disable recovery tracking. + */ +static void +legacy_recdir_name_error(int error) +{ + printk(KERN_ERR "NFSD: unable to generate recoverydir " + "name (%d).\n", error); + + /* + * if the algorithm just doesn't exist, then disable the recovery + * tracker altogether. The crypto libs will generally return this if + * FIPS is enabled as well. + */ + if (error == -ENOENT) { + printk(KERN_ERR "NFSD: disabling legacy clientid tracking. " + "Reboot recovery will not function correctly!\n"); + + /* the argument is ignored by the legacy exit function */ + nfsd4_client_tracking_exit(NULL); + } +} + static void nfsd4_create_clid_dir(struct nfs4_client *clp) { const struct cred *original_cred; - char *dname = clp->cl_recdir; + char dname[HEXDIR_LEN]; struct dentry *dir, *dentry; + struct nfs4_client_reclaim *crp; int status; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); dprintk("NFSD: nfsd4_create_clid_dir for \"%s\"\n", dname); if (test_and_set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) return; - if (!rec_file) + if (!nn->rec_file) return; + + status = nfs4_make_rec_clidname(dname, &clp->cl_name); + if (status) + return legacy_recdir_name_error(status); + status = nfs4_save_creds(&original_cred); if (status < 0) return; - status = mnt_want_write_file(rec_file); + status = mnt_want_write_file(nn->rec_file); if (status) return; - dir = rec_file->f_path.dentry; + dir = nn->rec_file->f_path.dentry; /* lock the parent */ mutex_lock(&dir->d_inode->i_mutex); @@ -182,18 +218,24 @@ out_put: dput(dentry); out_unlock: mutex_unlock(&dir->d_inode->i_mutex); - if (status == 0) - vfs_fsync(rec_file, 0); - else + if (status == 0) { + if (nn->in_grace) { + crp = nfs4_client_to_reclaim(dname, nn); + if (crp) + crp->cr_clp = clp; + } + vfs_fsync(nn->rec_file, 0); + } else { printk(KERN_ERR "NFSD: failed to write recovery record" " (err %d); please check that %s exists" " and is writeable", status, user_recovery_dirname); - mnt_drop_write_file(rec_file); + } + mnt_drop_write_file(nn->rec_file); nfs4_reset_creds(original_cred); } -typedef int (recdir_func)(struct dentry *, struct dentry *); +typedef int (recdir_func)(struct dentry *, struct dentry *, struct nfsd_net *); struct name_list { char name[HEXDIR_LEN]; @@ -219,10 +261,10 @@ nfsd4_build_namelist(void *arg, const char *name, int namlen, } static int -nfsd4_list_rec_dir(recdir_func *f) +nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn) { const struct cred *original_cred; - struct dentry *dir = rec_file->f_path.dentry; + struct dentry *dir = nn->rec_file->f_path.dentry; LIST_HEAD(names); int status; @@ -230,13 +272,13 @@ nfsd4_list_rec_dir(recdir_func *f) if (status < 0) return status; - status = vfs_llseek(rec_file, 0, SEEK_SET); + status = vfs_llseek(nn->rec_file, 0, SEEK_SET); if (status < 0) { nfs4_reset_creds(original_cred); return status; } - status = vfs_readdir(rec_file, nfsd4_build_namelist, &names); + status = vfs_readdir(nn->rec_file, nfsd4_build_namelist, &names); mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT); while (!list_empty(&names)) { struct name_list *entry; @@ -248,7 +290,7 @@ nfsd4_list_rec_dir(recdir_func *f) status = PTR_ERR(dentry); break; } - status = f(dir, dentry); + status = f(dir, dentry, nn); dput(dentry); } list_del(&entry->list); @@ -260,14 +302,14 @@ nfsd4_list_rec_dir(recdir_func *f) } static int -nfsd4_unlink_clid_dir(char *name, int namlen) +nfsd4_unlink_clid_dir(char *name, int namlen, struct nfsd_net *nn) { struct dentry *dir, *dentry; int status; dprintk("NFSD: nfsd4_unlink_clid_dir. name %.*s\n", namlen, name); - dir = rec_file->f_path.dentry; + dir = nn->rec_file->f_path.dentry; mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT); dentry = lookup_one_len(name, dir, namlen); if (IS_ERR(dentry)) { @@ -289,37 +331,52 @@ static void nfsd4_remove_clid_dir(struct nfs4_client *clp) { const struct cred *original_cred; + struct nfs4_client_reclaim *crp; + char dname[HEXDIR_LEN]; int status; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - if (!rec_file || !test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) + if (!nn->rec_file || !test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) return; - status = mnt_want_write_file(rec_file); + status = nfs4_make_rec_clidname(dname, &clp->cl_name); + if (status) + return legacy_recdir_name_error(status); + + status = mnt_want_write_file(nn->rec_file); if (status) goto out; clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags); status = nfs4_save_creds(&original_cred); if (status < 0) - goto out; + goto out_drop_write; - status = nfsd4_unlink_clid_dir(clp->cl_recdir, HEXDIR_LEN-1); + status = nfsd4_unlink_clid_dir(dname, HEXDIR_LEN-1, nn); nfs4_reset_creds(original_cred); - if (status == 0) - vfs_fsync(rec_file, 0); - mnt_drop_write_file(rec_file); + if (status == 0) { + vfs_fsync(nn->rec_file, 0); + if (nn->in_grace) { + /* remove reclaim record */ + crp = nfsd4_find_reclaim_client(dname, nn); + if (crp) + nfs4_remove_reclaim_record(crp, nn); + } + } +out_drop_write: + mnt_drop_write_file(nn->rec_file); out: if (status) printk("NFSD: Failed to remove expired client state directory" - " %.*s\n", HEXDIR_LEN, clp->cl_recdir); + " %.*s\n", HEXDIR_LEN, dname); } static int -purge_old(struct dentry *parent, struct dentry *child) +purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) { int status; - if (nfs4_has_reclaimed_state(child->d_name.name, false)) + if (nfs4_has_reclaimed_state(child->d_name.name, nn)) return 0; status = vfs_rmdir(parent->d_inode, child); @@ -331,27 +388,29 @@ purge_old(struct dentry *parent, struct dentry *child) } static void -nfsd4_recdir_purge_old(struct net *net, time_t boot_time) +nfsd4_recdir_purge_old(struct nfsd_net *nn, time_t boot_time) { int status; - if (!rec_file) + nn->in_grace = false; + if (!nn->rec_file) return; - status = mnt_want_write_file(rec_file); + status = mnt_want_write_file(nn->rec_file); if (status) goto out; - status = nfsd4_list_rec_dir(purge_old); + status = nfsd4_list_rec_dir(purge_old, nn); if (status == 0) - vfs_fsync(rec_file, 0); - mnt_drop_write_file(rec_file); + vfs_fsync(nn->rec_file, 0); + mnt_drop_write_file(nn->rec_file); out: + nfs4_release_reclaim(nn); if (status) printk("nfsd4: failed to purge old clients from recovery" - " directory %s\n", rec_file->f_path.dentry->d_name.name); + " directory %s\n", nn->rec_file->f_path.dentry->d_name.name); } static int -load_recdir(struct dentry *parent, struct dentry *child) +load_recdir(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) { if (child->d_name.len != HEXDIR_LEN - 1) { printk("nfsd4: illegal name %s in recovery directory\n", @@ -359,21 +418,22 @@ load_recdir(struct dentry *parent, struct dentry *child) /* Keep trying; maybe the others are OK: */ return 0; } - nfs4_client_to_reclaim(child->d_name.name); + nfs4_client_to_reclaim(child->d_name.name, nn); return 0; } static int -nfsd4_recdir_load(void) { +nfsd4_recdir_load(struct net *net) { int status; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); - if (!rec_file) + if (!nn->rec_file) return 0; - status = nfsd4_list_rec_dir(load_recdir); + status = nfsd4_list_rec_dir(load_recdir, nn); if (status) printk("nfsd4: failed loading clients from recovery" - " directory %s\n", rec_file->f_path.dentry->d_name.name); + " directory %s\n", nn->rec_file->f_path.dentry->d_name.name); return status; } @@ -382,15 +442,16 @@ nfsd4_recdir_load(void) { */ static int -nfsd4_init_recdir(void) +nfsd4_init_recdir(struct net *net) { + struct nfsd_net *nn = net_generic(net, nfsd_net_id); const struct cred *original_cred; int status; printk("NFSD: Using %s as the NFSv4 state recovery directory\n", user_recovery_dirname); - BUG_ON(rec_file); + BUG_ON(nn->rec_file); status = nfs4_save_creds(&original_cred); if (status < 0) { @@ -400,23 +461,65 @@ nfsd4_init_recdir(void) return status; } - rec_file = filp_open(user_recovery_dirname, O_RDONLY | O_DIRECTORY, 0); - if (IS_ERR(rec_file)) { + nn->rec_file = filp_open(user_recovery_dirname, O_RDONLY | O_DIRECTORY, 0); + if (IS_ERR(nn->rec_file)) { printk("NFSD: unable to find recovery directory %s\n", user_recovery_dirname); - status = PTR_ERR(rec_file); - rec_file = NULL; + status = PTR_ERR(nn->rec_file); + nn->rec_file = NULL; } nfs4_reset_creds(original_cred); + if (!status) + nn->in_grace = true; return status; } + +static int +nfs4_legacy_state_init(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + int i; + + nn->reclaim_str_hashtbl = kmalloc(sizeof(struct list_head) * + CLIENT_HASH_SIZE, GFP_KERNEL); + if (!nn->reclaim_str_hashtbl) + return -ENOMEM; + + for (i = 0; i < CLIENT_HASH_SIZE; i++) + INIT_LIST_HEAD(&nn->reclaim_str_hashtbl[i]); + nn->reclaim_str_hashtbl_size = 0; + + return 0; +} + +static void +nfs4_legacy_state_shutdown(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + kfree(nn->reclaim_str_hashtbl); +} + static int nfsd4_load_reboot_recovery_data(struct net *net) { int status; + status = nfsd4_init_recdir(net); + if (!status) + status = nfsd4_recdir_load(net); + if (status) + printk(KERN_ERR "NFSD: Failure reading reboot recovery data\n"); + return status; +} + +static int +nfsd4_legacy_tracking_init(struct net *net) +{ + int status; + /* XXX: The legacy code won't work in a container */ if (net != &init_net) { WARN(1, KERN_ERR "NFSD: attempt to initialize legacy client " @@ -424,30 +527,37 @@ nfsd4_load_reboot_recovery_data(struct net *net) return -EINVAL; } - nfs4_lock_state(); - status = nfsd4_init_recdir(); - if (!status) - status = nfsd4_recdir_load(); - nfs4_unlock_state(); + status = nfs4_legacy_state_init(net); if (status) - printk(KERN_ERR "NFSD: Failure reading reboot recovery data\n"); + return status; + + status = nfsd4_load_reboot_recovery_data(net); + if (status) + goto err; + return 0; + +err: + nfs4_legacy_state_shutdown(net); return status; } static void -nfsd4_shutdown_recdir(void) +nfsd4_shutdown_recdir(struct nfsd_net *nn) { - if (!rec_file) + if (!nn->rec_file) return; - fput(rec_file); - rec_file = NULL; + fput(nn->rec_file); + nn->rec_file = NULL; } static void nfsd4_legacy_tracking_exit(struct net *net) { - nfs4_release_reclaim(); - nfsd4_shutdown_recdir(); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nfs4_release_reclaim(nn); + nfsd4_shutdown_recdir(nn); + nfs4_legacy_state_shutdown(net); } /* @@ -480,13 +590,26 @@ nfs4_recoverydir(void) static int nfsd4_check_legacy_client(struct nfs4_client *clp) { + int status; + char dname[HEXDIR_LEN]; + struct nfs4_client_reclaim *crp; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + /* did we already find that this client is stable? */ if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) return 0; + status = nfs4_make_rec_clidname(dname, &clp->cl_name); + if (status) { + legacy_recdir_name_error(status); + return status; + } + /* look for it in the reclaim hashtable otherwise */ - if (nfsd4_find_reclaim_client(clp)) { + crp = nfsd4_find_reclaim_client(dname, nn); + if (crp) { set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags); + crp->cr_clp = clp; return 0; } @@ -494,7 +617,7 @@ nfsd4_check_legacy_client(struct nfs4_client *clp) } static struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = { - .init = nfsd4_load_reboot_recovery_data, + .init = nfsd4_legacy_tracking_init, .exit = nfsd4_legacy_tracking_exit, .create = nfsd4_create_clid_dir, .remove = nfsd4_remove_clid_dir, @@ -785,8 +908,7 @@ nfsd4_cld_create(struct nfs4_client *clp) { int ret; struct cld_upcall *cup; - /* FIXME: determine net from clp */ - struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); struct cld_net *cn = nn->cld_net; /* Don't upcall if it's already stored */ @@ -823,8 +945,7 @@ nfsd4_cld_remove(struct nfs4_client *clp) { int ret; struct cld_upcall *cup; - /* FIXME: determine net from clp */ - struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); struct cld_net *cn = nn->cld_net; /* Don't upcall if it's already removed */ @@ -861,8 +982,7 @@ nfsd4_cld_check(struct nfs4_client *clp) { int ret; struct cld_upcall *cup; - /* FIXME: determine net from clp */ - struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); struct cld_net *cn = nn->cld_net; /* Don't upcall if one was already stored during this grace pd */ @@ -892,11 +1012,10 @@ nfsd4_cld_check(struct nfs4_client *clp) } static void -nfsd4_cld_grace_done(struct net *net, time_t boot_time) +nfsd4_cld_grace_done(struct nfsd_net *nn, time_t boot_time) { int ret; struct cld_upcall *cup; - struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct cld_net *cn = nn->cld_net; cup = alloc_cld_upcall(cn); @@ -926,28 +1045,261 @@ static struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = { .grace_done = nfsd4_cld_grace_done, }; +/* upcall via usermodehelper */ +static char cltrack_prog[PATH_MAX] = "/sbin/nfsdcltrack"; +module_param_string(cltrack_prog, cltrack_prog, sizeof(cltrack_prog), + S_IRUGO|S_IWUSR); +MODULE_PARM_DESC(cltrack_prog, "Path to the nfsdcltrack upcall program"); + +static bool cltrack_legacy_disable; +module_param(cltrack_legacy_disable, bool, S_IRUGO|S_IWUSR); +MODULE_PARM_DESC(cltrack_legacy_disable, + "Disable legacy recoverydir conversion. Default: false"); + +#define LEGACY_TOPDIR_ENV_PREFIX "NFSDCLTRACK_LEGACY_TOPDIR=" +#define LEGACY_RECDIR_ENV_PREFIX "NFSDCLTRACK_LEGACY_RECDIR=" + +static char * +nfsd4_cltrack_legacy_topdir(void) +{ + int copied; + size_t len; + char *result; + + if (cltrack_legacy_disable) + return NULL; + + len = strlen(LEGACY_TOPDIR_ENV_PREFIX) + + strlen(nfs4_recoverydir()) + 1; + + result = kmalloc(len, GFP_KERNEL); + if (!result) + return result; + + copied = snprintf(result, len, LEGACY_TOPDIR_ENV_PREFIX "%s", + nfs4_recoverydir()); + if (copied >= len) { + /* just return nothing if output was truncated */ + kfree(result); + return NULL; + } + + return result; +} + +static char * +nfsd4_cltrack_legacy_recdir(const struct xdr_netobj *name) +{ + int copied; + size_t len; + char *result; + + if (cltrack_legacy_disable) + return NULL; + + /* +1 is for '/' between "topdir" and "recdir" */ + len = strlen(LEGACY_RECDIR_ENV_PREFIX) + + strlen(nfs4_recoverydir()) + 1 + HEXDIR_LEN; + + result = kmalloc(len, GFP_KERNEL); + if (!result) + return result; + + copied = snprintf(result, len, LEGACY_RECDIR_ENV_PREFIX "%s/", + nfs4_recoverydir()); + if (copied > (len - HEXDIR_LEN)) { + /* just return nothing if output will be truncated */ + kfree(result); + return NULL; + } + + copied = nfs4_make_rec_clidname(result + copied, name); + if (copied) { + kfree(result); + return NULL; + } + + return result; +} + +static int +nfsd4_umh_cltrack_upcall(char *cmd, char *arg, char *legacy) +{ + char *envp[2]; + char *argv[4]; + int ret; + + if (unlikely(!cltrack_prog[0])) { + dprintk("%s: cltrack_prog is disabled\n", __func__); + return -EACCES; + } + + dprintk("%s: cmd: %s\n", __func__, cmd); + dprintk("%s: arg: %s\n", __func__, arg ? arg : "(null)"); + dprintk("%s: legacy: %s\n", __func__, legacy ? legacy : "(null)"); + + envp[0] = legacy; + envp[1] = NULL; + + argv[0] = (char *)cltrack_prog; + argv[1] = cmd; + argv[2] = arg; + argv[3] = NULL; + + ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC); + /* + * Disable the upcall mechanism if we're getting an ENOENT or EACCES + * error. The admin can re-enable it on the fly by using sysfs + * once the problem has been fixed. + */ + if (ret == -ENOENT || ret == -EACCES) { + dprintk("NFSD: %s was not found or isn't executable (%d). " + "Setting cltrack_prog to blank string!", + cltrack_prog, ret); + cltrack_prog[0] = '\0'; + } + dprintk("%s: %s return value: %d\n", __func__, cltrack_prog, ret); + + return ret; +} + +static char * +bin_to_hex_dup(const unsigned char *src, int srclen) +{ + int i; + char *buf, *hex; + + /* +1 for terminating NULL */ + buf = kmalloc((srclen * 2) + 1, GFP_KERNEL); + if (!buf) + return buf; + + hex = buf; + for (i = 0; i < srclen; i++) { + sprintf(hex, "%2.2x", *src++); + hex += 2; + } + return buf; +} + +static int +nfsd4_umh_cltrack_init(struct net __attribute__((unused)) *net) +{ + return nfsd4_umh_cltrack_upcall("init", NULL, NULL); +} + +static void +nfsd4_umh_cltrack_create(struct nfs4_client *clp) +{ + char *hexid; + + hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len); + if (!hexid) { + dprintk("%s: can't allocate memory for upcall!\n", __func__); + return; + } + nfsd4_umh_cltrack_upcall("create", hexid, NULL); + kfree(hexid); +} + +static void +nfsd4_umh_cltrack_remove(struct nfs4_client *clp) +{ + char *hexid; + + hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len); + if (!hexid) { + dprintk("%s: can't allocate memory for upcall!\n", __func__); + return; + } + nfsd4_umh_cltrack_upcall("remove", hexid, NULL); + kfree(hexid); +} + +static int +nfsd4_umh_cltrack_check(struct nfs4_client *clp) +{ + int ret; + char *hexid, *legacy; + + hexid = bin_to_hex_dup(clp->cl_name.data, clp->cl_name.len); + if (!hexid) { + dprintk("%s: can't allocate memory for upcall!\n", __func__); + return -ENOMEM; + } + legacy = nfsd4_cltrack_legacy_recdir(&clp->cl_name); + ret = nfsd4_umh_cltrack_upcall("check", hexid, legacy); + kfree(legacy); + kfree(hexid); + return ret; +} + +static void +nfsd4_umh_cltrack_grace_done(struct nfsd_net __attribute__((unused)) *nn, + time_t boot_time) +{ + char *legacy; + char timestr[22]; /* FIXME: better way to determine max size? */ + + sprintf(timestr, "%ld", boot_time); + legacy = nfsd4_cltrack_legacy_topdir(); + nfsd4_umh_cltrack_upcall("gracedone", timestr, legacy); + kfree(legacy); +} + +static struct nfsd4_client_tracking_ops nfsd4_umh_tracking_ops = { + .init = nfsd4_umh_cltrack_init, + .exit = NULL, + .create = nfsd4_umh_cltrack_create, + .remove = nfsd4_umh_cltrack_remove, + .check = nfsd4_umh_cltrack_check, + .grace_done = nfsd4_umh_cltrack_grace_done, +}; + int nfsd4_client_tracking_init(struct net *net) { int status; struct path path; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); - if (!client_tracking_ops) { - client_tracking_ops = &nfsd4_cld_tracking_ops; - status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path); - if (!status) { - if (S_ISDIR(path.dentry->d_inode->i_mode)) - client_tracking_ops = - &nfsd4_legacy_tracking_ops; - path_put(&path); - } + /* just run the init if it the method is already decided */ + if (nn->client_tracking_ops) + goto do_init; + + /* + * First, try a UMH upcall. It should succeed or fail quickly, so + * there's little harm in trying that first. + */ + nn->client_tracking_ops = &nfsd4_umh_tracking_ops; + status = nn->client_tracking_ops->init(net); + if (!status) + return status; + + /* + * See if the recoverydir exists and is a directory. If it is, + * then use the legacy ops. + */ + nn->client_tracking_ops = &nfsd4_legacy_tracking_ops; + status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path); + if (!status) { + status = S_ISDIR(path.dentry->d_inode->i_mode); + path_put(&path); + if (status) + goto do_init; } - status = client_tracking_ops->init(net); + /* Finally, try to use nfsdcld */ + nn->client_tracking_ops = &nfsd4_cld_tracking_ops; + printk(KERN_WARNING "NFSD: the nfsdcld client tracking upcall will be " + "removed in 3.10. Please transition to using " + "nfsdcltrack.\n"); +do_init: + status = nn->client_tracking_ops->init(net); if (status) { printk(KERN_WARNING "NFSD: Unable to initialize client " "recovery tracking! (%d)\n", status); - client_tracking_ops = NULL; + nn->client_tracking_ops = NULL; } return status; } @@ -955,40 +1307,49 @@ nfsd4_client_tracking_init(struct net *net) void nfsd4_client_tracking_exit(struct net *net) { - if (client_tracking_ops) { - client_tracking_ops->exit(net); - client_tracking_ops = NULL; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + if (nn->client_tracking_ops) { + if (nn->client_tracking_ops->exit) + nn->client_tracking_ops->exit(net); + nn->client_tracking_ops = NULL; } } void nfsd4_client_record_create(struct nfs4_client *clp) { - if (client_tracking_ops) - client_tracking_ops->create(clp); + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + + if (nn->client_tracking_ops) + nn->client_tracking_ops->create(clp); } void nfsd4_client_record_remove(struct nfs4_client *clp) { - if (client_tracking_ops) - client_tracking_ops->remove(clp); + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + + if (nn->client_tracking_ops) + nn->client_tracking_ops->remove(clp); } int nfsd4_client_record_check(struct nfs4_client *clp) { - if (client_tracking_ops) - return client_tracking_ops->check(clp); + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + + if (nn->client_tracking_ops) + return nn->client_tracking_ops->check(clp); return -EOPNOTSUPP; } void -nfsd4_record_grace_done(struct net *net, time_t boot_time) +nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time) { - if (client_tracking_ops) - client_tracking_ops->grace_done(net, boot_time); + if (nn->client_tracking_ops) + nn->client_tracking_ops->grace_done(nn, boot_time); } static int diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index d0237f872cc4..ac8ed96c4199 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -44,16 +44,11 @@ #include "xdr4.h" #include "vfs.h" #include "current_stateid.h" -#include "fault_inject.h" #include "netns.h" #define NFSDDBG_FACILITY NFSDDBG_PROC -/* Globals */ -time_t nfsd4_lease = 90; /* default lease time */ -time_t nfsd4_grace = 90; - #define all_ones {{~0,~0},~0} static const stateid_t one_stateid = { .si_generation = ~0, @@ -176,8 +171,6 @@ static unsigned int ownerstr_hashval(u32 clientid, struct xdr_netobj *ownername) return ret & OWNER_HASH_MASK; } -static struct list_head ownerstr_hashtbl[OWNER_HASH_SIZE]; - /* hash table for nfs4_file */ #define FILE_HASH_BITS 8 #define FILE_HASH_SIZE (1 << FILE_HASH_BITS) @@ -192,7 +185,7 @@ static struct list_head file_hashtbl[FILE_HASH_SIZE]; static void __nfs4_file_get_access(struct nfs4_file *fp, int oflag) { - BUG_ON(!(fp->fi_fds[oflag] || fp->fi_fds[O_RDWR])); + WARN_ON_ONCE(!(fp->fi_fds[oflag] || fp->fi_fds[O_RDWR])); atomic_inc(&fp->fi_access[oflag]); } @@ -251,7 +244,7 @@ static inline int get_new_stid(struct nfs4_stid *stid) * preallocations that can exist at a time, but the state lock * prevents anyone from using ours before we get here: */ - BUG_ON(error); + WARN_ON_ONCE(error); /* * It shouldn't be a problem to reuse an opaque stateid value. * I don't think it is for 4.1. But with 4.0 I worry that, for @@ -340,7 +333,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle); dp->dl_time = 0; atomic_set(&dp->dl_count, 1); - INIT_WORK(&dp->dl_recall.cb_work, nfsd4_do_callback_rpc); + nfsd4_init_callback(&dp->dl_recall); return dp; } @@ -390,14 +383,6 @@ unhash_delegation(struct nfs4_delegation *dp) * SETCLIENTID state */ -/* client_lock protects the client lru list and session hash table */ -static DEFINE_SPINLOCK(client_lock); - -/* Hash tables for nfs4_clientid state */ -#define CLIENT_HASH_BITS 4 -#define CLIENT_HASH_SIZE (1 << CLIENT_HASH_BITS) -#define CLIENT_HASH_MASK (CLIENT_HASH_SIZE - 1) - static unsigned int clientid_hashval(u32 id) { return id & CLIENT_HASH_MASK; @@ -409,31 +394,6 @@ static unsigned int clientstr_hashval(const char *name) } /* - * reclaim_str_hashtbl[] holds known client info from previous reset/reboot - * used in reboot/reset lease grace period processing - * - * conf_id_hashtbl[], and conf_str_hashtbl[] hold confirmed - * setclientid_confirmed info. - * - * unconf_str_hastbl[] and unconf_id_hashtbl[] hold unconfirmed - * setclientid info. - * - * client_lru holds client queue ordered by nfs4_client.cl_time - * for lease renewal. - * - * close_lru holds (open) stateowner queue ordered by nfs4_stateowner.so_time - * for last close replay. - */ -static struct list_head reclaim_str_hashtbl[CLIENT_HASH_SIZE]; -static int reclaim_str_hashtbl_size = 0; -static struct list_head conf_id_hashtbl[CLIENT_HASH_SIZE]; -static struct list_head conf_str_hashtbl[CLIENT_HASH_SIZE]; -static struct list_head unconf_str_hashtbl[CLIENT_HASH_SIZE]; -static struct list_head unconf_id_hashtbl[CLIENT_HASH_SIZE]; -static struct list_head client_lru; -static struct list_head close_lru; - -/* * We store the NONE, READ, WRITE, and BOTH bits separately in the * st_{access,deny}_bmap field of the stateid, in order to track not * only what share bits are currently in force, but also what @@ -526,7 +486,8 @@ static int nfs4_access_to_omode(u32 access) case NFS4_SHARE_ACCESS_BOTH: return O_RDWR; } - BUG(); + WARN_ON_ONCE(1); + return O_RDONLY; } /* release all access and file references for a given stateid */ @@ -652,9 +613,6 @@ static void release_openowner(struct nfs4_openowner *oo) nfs4_free_openowner(oo); } -#define SESSION_HASH_SIZE 512 -static struct list_head sessionid_hashtbl[SESSION_HASH_SIZE]; - static inline int hash_sessionid(struct nfs4_sessionid *sessionid) { @@ -785,9 +743,12 @@ out_free: return NULL; } -static void init_forechannel_attrs(struct nfsd4_channel_attrs *new, struct nfsd4_channel_attrs *req, int numslots, int slotsize) +static void init_forechannel_attrs(struct nfsd4_channel_attrs *new, + struct nfsd4_channel_attrs *req, + int numslots, int slotsize, + struct nfsd_net *nn) { - u32 maxrpc = nfsd_serv->sv_max_mesg; + u32 maxrpc = nn->nfsd_serv->sv_max_mesg; new->maxreqs = numslots; new->maxresp_cached = min_t(u32, req->maxresp_cached, @@ -906,21 +867,27 @@ static void __free_session(struct nfsd4_session *ses) static void free_session(struct kref *kref) { struct nfsd4_session *ses; + struct nfsd_net *nn; - lockdep_assert_held(&client_lock); ses = container_of(kref, struct nfsd4_session, se_ref); + nn = net_generic(ses->se_client->net, nfsd_net_id); + + lockdep_assert_held(&nn->client_lock); nfsd4_del_conns(ses); __free_session(ses); } void nfsd4_put_session(struct nfsd4_session *ses) { - spin_lock(&client_lock); + struct nfsd_net *nn = net_generic(ses->se_client->net, nfsd_net_id); + + spin_lock(&nn->client_lock); nfsd4_put_session_locked(ses); - spin_unlock(&client_lock); + spin_unlock(&nn->client_lock); } -static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fchan) +static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fchan, + struct nfsd_net *nn) { struct nfsd4_session *new; int numslots, slotsize; @@ -941,13 +908,14 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fchan) nfsd4_put_drc_mem(slotsize, fchan->maxreqs); return NULL; } - init_forechannel_attrs(&new->se_fchannel, fchan, numslots, slotsize); + init_forechannel_attrs(&new->se_fchannel, fchan, numslots, slotsize, nn); return new; } -static struct nfsd4_session *init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses) +static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses) { int idx; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); new->se_client = clp; gen_sessionid(new); @@ -957,14 +925,15 @@ static struct nfsd4_session *init_session(struct svc_rqst *rqstp, struct nfsd4_s new->se_cb_seq_nr = 1; new->se_flags = cses->flags; new->se_cb_prog = cses->callback_prog; + new->se_cb_sec = cses->cb_sec; kref_init(&new->se_ref); idx = hash_sessionid(&new->se_sessionid); - spin_lock(&client_lock); - list_add(&new->se_hash, &sessionid_hashtbl[idx]); + spin_lock(&nn->client_lock); + list_add(&new->se_hash, &nn->sessionid_hashtbl[idx]); spin_lock(&clp->cl_lock); list_add(&new->se_perclnt, &clp->cl_sessions); spin_unlock(&clp->cl_lock); - spin_unlock(&client_lock); + spin_unlock(&nn->client_lock); if (cses->flags & SESSION4_BACK_CHAN) { struct sockaddr *sa = svc_addr(rqstp); @@ -978,20 +947,20 @@ static struct nfsd4_session *init_session(struct svc_rqst *rqstp, struct nfsd4_s rpc_copy_addr((struct sockaddr *)&clp->cl_cb_conn.cb_addr, sa); clp->cl_cb_conn.cb_addrlen = svc_addr_len(sa); } - return new; } /* caller must hold client_lock */ static struct nfsd4_session * -find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid) +find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net) { struct nfsd4_session *elem; int idx; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); dump_sessionid(__func__, sessionid); idx = hash_sessionid(sessionid); /* Search in the appropriate list */ - list_for_each_entry(elem, &sessionid_hashtbl[idx], se_hash) { + list_for_each_entry(elem, &nn->sessionid_hashtbl[idx], se_hash) { if (!memcmp(elem->se_sessionid.data, sessionid->data, NFS4_MAX_SESSIONID_LEN)) { return elem; @@ -1016,6 +985,8 @@ unhash_session(struct nfsd4_session *ses) static inline void renew_client_locked(struct nfs4_client *clp) { + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + if (is_client_expired(clp)) { WARN_ON(1); printk("%s: client (clientid %08x/%08x) already expired\n", @@ -1028,16 +999,18 @@ renew_client_locked(struct nfs4_client *clp) dprintk("renewing client (clientid %08x/%08x)\n", clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); - list_move_tail(&clp->cl_lru, &client_lru); + list_move_tail(&clp->cl_lru, &nn->client_lru); clp->cl_time = get_seconds(); } static inline void renew_client(struct nfs4_client *clp) { - spin_lock(&client_lock); + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + + spin_lock(&nn->client_lock); renew_client_locked(clp); - spin_unlock(&client_lock); + spin_unlock(&nn->client_lock); } /* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */ @@ -1075,7 +1048,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) static inline void free_client(struct nfs4_client *clp) { - lockdep_assert_held(&client_lock); + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + + lockdep_assert_held(&nn->client_lock); while (!list_empty(&clp->cl_sessions)) { struct nfsd4_session *ses; ses = list_entry(clp->cl_sessions.next, struct nfsd4_session, @@ -1092,15 +1067,16 @@ void release_session_client(struct nfsd4_session *session) { struct nfs4_client *clp = session->se_client; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - if (!atomic_dec_and_lock(&clp->cl_refcount, &client_lock)) + if (!atomic_dec_and_lock(&clp->cl_refcount, &nn->client_lock)) return; if (is_client_expired(clp)) { free_client(clp); session->se_client = NULL; } else renew_client_locked(clp); - spin_unlock(&client_lock); + spin_unlock(&nn->client_lock); } /* must be called under the client_lock */ @@ -1123,6 +1099,7 @@ destroy_client(struct nfs4_client *clp) struct nfs4_openowner *oo; struct nfs4_delegation *dp; struct list_head reaplist; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); INIT_LIST_HEAD(&reaplist); spin_lock(&recall_lock); @@ -1144,12 +1121,15 @@ destroy_client(struct nfs4_client *clp) if (clp->cl_cb_conn.cb_xprt) svc_xprt_put(clp->cl_cb_conn.cb_xprt); list_del(&clp->cl_idhash); - list_del(&clp->cl_strhash); - spin_lock(&client_lock); + if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags)) + rb_erase(&clp->cl_namenode, &nn->conf_name_tree); + else + rb_erase(&clp->cl_namenode, &nn->unconf_name_tree); + spin_lock(&nn->client_lock); unhash_client_locked(clp); if (atomic_read(&clp->cl_refcount) == 0) free_client(clp); - spin_unlock(&client_lock); + spin_unlock(&nn->client_lock); } static void expire_client(struct nfs4_client *clp) @@ -1187,6 +1167,17 @@ static int copy_cred(struct svc_cred *target, struct svc_cred *source) return 0; } +static long long +compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2) +{ + long long res; + + res = o1->len - o2->len; + if (res) + return res; + return (long long)memcmp(o1->data, o2->data, o1->len); +} + static int same_name(const char *n1, const char *n2) { return 0 == memcmp(n1, n2, HEXDIR_LEN); @@ -1247,10 +1238,9 @@ same_creds(struct svc_cred *cr1, struct svc_cred *cr2) return 0 == strcmp(cr1->cr_principal, cr2->cr_principal); } -static void gen_clid(struct nfs4_client *clp) +static void gen_clid(struct nfs4_client *clp, struct nfsd_net *nn) { static u32 current_clientid = 1; - struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); clp->cl_clientid.cl_boot = nn->boot_time; clp->cl_clientid.cl_id = current_clientid++; @@ -1283,12 +1273,14 @@ static struct nfs4_stid *find_stateid_by_type(struct nfs4_client *cl, stateid_t return NULL; } -static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir, +static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { struct nfs4_client *clp; struct sockaddr *sa = svc_addr(rqstp); int ret; + struct net *net = SVC_NET(rqstp); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); clp = alloc_client(name); if (clp == NULL) @@ -1297,23 +1289,21 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir, INIT_LIST_HEAD(&clp->cl_sessions); ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred); if (ret) { - spin_lock(&client_lock); + spin_lock(&nn->client_lock); free_client(clp); - spin_unlock(&client_lock); + spin_unlock(&nn->client_lock); return NULL; } idr_init(&clp->cl_stateids); - memcpy(clp->cl_recdir, recdir, HEXDIR_LEN); atomic_set(&clp->cl_refcount, 0); clp->cl_cb_state = NFSD4_CB_UNKNOWN; INIT_LIST_HEAD(&clp->cl_idhash); - INIT_LIST_HEAD(&clp->cl_strhash); INIT_LIST_HEAD(&clp->cl_openowners); INIT_LIST_HEAD(&clp->cl_delegations); INIT_LIST_HEAD(&clp->cl_lru); INIT_LIST_HEAD(&clp->cl_callbacks); spin_lock_init(&clp->cl_lock); - INIT_WORK(&clp->cl_cb_null.cb_work, nfsd4_do_callback_rpc); + nfsd4_init_callback(&clp->cl_cb_null); clp->cl_time = get_seconds(); clear_bit(0, &clp->cl_cb_slot_busy); rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); @@ -1321,17 +1311,60 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir, rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa); gen_confirm(clp); clp->cl_cb_session = NULL; + clp->net = net; return clp; } static void -add_to_unconfirmed(struct nfs4_client *clp, unsigned int strhashval) +add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root) +{ + struct rb_node **new = &(root->rb_node), *parent = NULL; + struct nfs4_client *clp; + + while (*new) { + clp = rb_entry(*new, struct nfs4_client, cl_namenode); + parent = *new; + + if (compare_blob(&clp->cl_name, &new_clp->cl_name) > 0) + new = &((*new)->rb_left); + else + new = &((*new)->rb_right); + } + + rb_link_node(&new_clp->cl_namenode, parent, new); + rb_insert_color(&new_clp->cl_namenode, root); +} + +static struct nfs4_client * +find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root) +{ + long long cmp; + struct rb_node *node = root->rb_node; + struct nfs4_client *clp; + + while (node) { + clp = rb_entry(node, struct nfs4_client, cl_namenode); + cmp = compare_blob(&clp->cl_name, name); + if (cmp > 0) + node = node->rb_left; + else if (cmp < 0) + node = node->rb_right; + else + return clp; + } + return NULL; +} + +static void +add_to_unconfirmed(struct nfs4_client *clp) { unsigned int idhashval; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - list_add(&clp->cl_strhash, &unconf_str_hashtbl[strhashval]); + clear_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags); + add_clp_to_name_tree(clp, &nn->unconf_name_tree); idhashval = clientid_hashval(clp->cl_clientid.cl_id); - list_add(&clp->cl_idhash, &unconf_id_hashtbl[idhashval]); + list_add(&clp->cl_idhash, &nn->unconf_id_hashtbl[idhashval]); renew_client(clp); } @@ -1339,22 +1372,23 @@ static void move_to_confirmed(struct nfs4_client *clp) { unsigned int idhashval = clientid_hashval(clp->cl_clientid.cl_id); - unsigned int strhashval; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); dprintk("NFSD: move_to_confirm nfs4_client %p\n", clp); - list_move(&clp->cl_idhash, &conf_id_hashtbl[idhashval]); - strhashval = clientstr_hashval(clp->cl_recdir); - list_move(&clp->cl_strhash, &conf_str_hashtbl[strhashval]); + list_move(&clp->cl_idhash, &nn->conf_id_hashtbl[idhashval]); + rb_erase(&clp->cl_namenode, &nn->unconf_name_tree); + add_clp_to_name_tree(clp, &nn->conf_name_tree); + set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags); renew_client(clp); } static struct nfs4_client * -find_confirmed_client(clientid_t *clid, bool sessions) +find_confirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn) { struct nfs4_client *clp; unsigned int idhashval = clientid_hashval(clid->cl_id); - list_for_each_entry(clp, &conf_id_hashtbl[idhashval], cl_idhash) { + list_for_each_entry(clp, &nn->conf_id_hashtbl[idhashval], cl_idhash) { if (same_clid(&clp->cl_clientid, clid)) { if ((bool)clp->cl_minorversion != sessions) return NULL; @@ -1366,12 +1400,12 @@ find_confirmed_client(clientid_t *clid, bool sessions) } static struct nfs4_client * -find_unconfirmed_client(clientid_t *clid, bool sessions) +find_unconfirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn) { struct nfs4_client *clp; unsigned int idhashval = clientid_hashval(clid->cl_id); - list_for_each_entry(clp, &unconf_id_hashtbl[idhashval], cl_idhash) { + list_for_each_entry(clp, &nn->unconf_id_hashtbl[idhashval], cl_idhash) { if (same_clid(&clp->cl_clientid, clid)) { if ((bool)clp->cl_minorversion != sessions) return NULL; @@ -1387,27 +1421,15 @@ static bool clp_used_exchangeid(struct nfs4_client *clp) } static struct nfs4_client * -find_confirmed_client_by_str(const char *dname, unsigned int hashval) +find_confirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn) { - struct nfs4_client *clp; - - list_for_each_entry(clp, &conf_str_hashtbl[hashval], cl_strhash) { - if (same_name(clp->cl_recdir, dname)) - return clp; - } - return NULL; + return find_clp_in_name_tree(name, &nn->conf_name_tree); } static struct nfs4_client * -find_unconfirmed_client_by_str(const char *dname, unsigned int hashval) +find_unconfirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn) { - struct nfs4_client *clp; - - list_for_each_entry(clp, &unconf_str_hashtbl[hashval], cl_strhash) { - if (same_name(clp->cl_recdir, dname)) - return clp; - } - return NULL; + return find_clp_in_name_tree(name, &nn->unconf_name_tree); } static void @@ -1428,7 +1450,7 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_r else goto out_err; - conn->cb_addrlen = rpc_uaddr2sockaddr(&init_net, se->se_callback_addr_val, + conn->cb_addrlen = rpc_uaddr2sockaddr(clp->net, se->se_callback_addr_val, se->se_callback_addr_len, (struct sockaddr *)&conn->cb_addr, sizeof(conn->cb_addr)); @@ -1572,12 +1594,11 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, { struct nfs4_client *unconf, *conf, *new; __be32 status; - unsigned int strhashval; - char dname[HEXDIR_LEN]; char addr_str[INET6_ADDRSTRLEN]; nfs4_verifier verf = exid->verifier; struct sockaddr *sa = svc_addr(rqstp); bool update = exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); rpc_ntop(sa, addr_str, sizeof(addr_str)); dprintk("%s rqstp=%p exid=%p clname.len=%u clname.data=%p " @@ -1592,24 +1613,16 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, switch (exid->spa_how) { case SP4_NONE: break; + default: /* checked by xdr code */ + WARN_ON_ONCE(1); case SP4_SSV: - return nfserr_serverfault; - default: - BUG(); /* checked by xdr code */ case SP4_MACH_CRED: return nfserr_serverfault; /* no excuse :-/ */ } - status = nfs4_make_rec_clidname(dname, &exid->clname); - - if (status) - return status; - - strhashval = clientstr_hashval(dname); - /* Cases below refer to rfc 5661 section 18.35.4: */ nfs4_lock_state(); - conf = find_confirmed_client_by_str(dname, strhashval); + conf = find_confirmed_client_by_name(&exid->clname, nn); if (conf) { bool creds_match = same_creds(&conf->cl_cred, &rqstp->rq_cred); bool verfs_match = same_verf(&verf, &conf->cl_verifier); @@ -1654,21 +1667,21 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, goto out; } - unconf = find_unconfirmed_client_by_str(dname, strhashval); + unconf = find_unconfirmed_client_by_name(&exid->clname, nn); if (unconf) /* case 4, possible retry or client restart */ expire_client(unconf); /* case 1 (normal case) */ out_new: - new = create_client(exid->clname, dname, rqstp, &verf); + new = create_client(exid->clname, rqstp, &verf); if (new == NULL) { status = nfserr_jukebox; goto out; } new->cl_minorversion = 1; - gen_clid(new); - add_to_unconfirmed(new, strhashval); + gen_clid(new, nn); + add_to_unconfirmed(new); out_copy: exid->clientid.cl_boot = new->cl_clientid.cl_boot; exid->clientid.cl_id = new->cl_clientid.cl_id; @@ -1761,12 +1774,13 @@ nfsd4_create_session(struct svc_rqst *rqstp, struct nfsd4_conn *conn; struct nfsd4_clid_slot *cs_slot = NULL; __be32 status = 0; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (cr_ses->flags & ~SESSION4_FLAG_MASK_A) return nfserr_inval; if (check_forechannel_attrs(cr_ses->fore_channel)) return nfserr_toosmall; - new = alloc_session(&cr_ses->fore_channel); + new = alloc_session(&cr_ses->fore_channel, nn); if (!new) return nfserr_jukebox; status = nfserr_jukebox; @@ -1775,8 +1789,8 @@ nfsd4_create_session(struct svc_rqst *rqstp, goto out_free_session; nfs4_lock_state(); - unconf = find_unconfirmed_client(&cr_ses->clientid, true); - conf = find_confirmed_client(&cr_ses->clientid, true); + unconf = find_unconfirmed_client(&cr_ses->clientid, true, nn); + conf = find_confirmed_client(&cr_ses->clientid, true, nn); if (conf) { cs_slot = &conf->cl_cs_slot; @@ -1789,7 +1803,6 @@ nfsd4_create_session(struct svc_rqst *rqstp, goto out_free_conn; } } else if (unconf) { - unsigned int hash; struct nfs4_client *old; if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) || !rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) { @@ -1803,8 +1816,7 @@ nfsd4_create_session(struct svc_rqst *rqstp, status = nfserr_seq_misordered; goto out_free_conn; } - hash = clientstr_hashval(unconf->cl_recdir); - old = find_confirmed_client_by_str(unconf->cl_recdir, hash); + old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) expire_client(old); move_to_confirmed(unconf); @@ -1843,14 +1855,6 @@ out_free_session: goto out; } -static bool nfsd4_last_compound_op(struct svc_rqst *rqstp) -{ - struct nfsd4_compoundres *resp = rqstp->rq_resp; - struct nfsd4_compoundargs *argp = rqstp->rq_argp; - - return argp->opcnt == resp->opcnt; -} - static __be32 nfsd4_map_bcts_dir(u32 *dir) { switch (*dir) { @@ -1865,24 +1869,40 @@ static __be32 nfsd4_map_bcts_dir(u32 *dir) return nfserr_inval; } +__be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_backchannel_ctl *bc) +{ + struct nfsd4_session *session = cstate->session; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + + spin_lock(&nn->client_lock); + session->se_cb_prog = bc->bc_cb_program; + session->se_cb_sec = bc->bc_cb_sec; + spin_unlock(&nn->client_lock); + + nfsd4_probe_callback(session->se_client); + + return nfs_ok; +} + __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_bind_conn_to_session *bcts) { __be32 status; struct nfsd4_conn *conn; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (!nfsd4_last_compound_op(rqstp)) return nfserr_not_only_op; - spin_lock(&client_lock); - cstate->session = find_in_sessionid_hashtbl(&bcts->sessionid); + spin_lock(&nn->client_lock); + cstate->session = find_in_sessionid_hashtbl(&bcts->sessionid, SVC_NET(rqstp)); /* Sorta weird: we only need the refcnt'ing because new_conn acquires * client_lock iself: */ if (cstate->session) { nfsd4_get_session(cstate->session); atomic_inc(&cstate->session->se_client->cl_refcount); } - spin_unlock(&client_lock); + spin_unlock(&nn->client_lock); if (!cstate->session) return nfserr_badsession; @@ -1910,6 +1930,7 @@ nfsd4_destroy_session(struct svc_rqst *r, { struct nfsd4_session *ses; __be32 status = nfserr_badsession; + struct nfsd_net *nn = net_generic(SVC_NET(r), nfsd_net_id); /* Notes: * - The confirmed nfs4_client->cl_sessionid holds destroyed sessinid @@ -1923,24 +1944,24 @@ nfsd4_destroy_session(struct svc_rqst *r, return nfserr_not_only_op; } dump_sessionid(__func__, &sessionid->sessionid); - spin_lock(&client_lock); - ses = find_in_sessionid_hashtbl(&sessionid->sessionid); + spin_lock(&nn->client_lock); + ses = find_in_sessionid_hashtbl(&sessionid->sessionid, SVC_NET(r)); if (!ses) { - spin_unlock(&client_lock); + spin_unlock(&nn->client_lock); goto out; } unhash_session(ses); - spin_unlock(&client_lock); + spin_unlock(&nn->client_lock); nfs4_lock_state(); nfsd4_probe_callback_sync(ses->se_client); nfs4_unlock_state(); - spin_lock(&client_lock); + spin_lock(&nn->client_lock); nfsd4_del_conns(ses); nfsd4_put_session_locked(ses); - spin_unlock(&client_lock); + spin_unlock(&nn->client_lock); status = nfs_ok; out: dprintk("%s returns %d\n", __func__, ntohl(status)); @@ -2006,6 +2027,7 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_slot *slot; struct nfsd4_conn *conn; __be32 status; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (resp->opcnt != 1) return nfserr_sequence_pos; @@ -2018,9 +2040,9 @@ nfsd4_sequence(struct svc_rqst *rqstp, if (!conn) return nfserr_jukebox; - spin_lock(&client_lock); + spin_lock(&nn->client_lock); status = nfserr_badsession; - session = find_in_sessionid_hashtbl(&seq->sessionid); + session = find_in_sessionid_hashtbl(&seq->sessionid, SVC_NET(rqstp)); if (!session) goto out; @@ -2094,7 +2116,7 @@ out: } } kfree(conn); - spin_unlock(&client_lock); + spin_unlock(&nn->client_lock); dprintk("%s: return %d\n", __func__, ntohl(status)); return status; } @@ -2104,10 +2126,11 @@ nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta { struct nfs4_client *conf, *unconf, *clp; __be32 status = 0; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); nfs4_lock_state(); - unconf = find_unconfirmed_client(&dc->clientid, true); - conf = find_confirmed_client(&dc->clientid, true); + unconf = find_unconfirmed_client(&dc->clientid, true, nn); + conf = find_confirmed_client(&dc->clientid, true, nn); if (conf) { clp = conf; @@ -2181,20 +2204,13 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { struct xdr_netobj clname = setclid->se_name; nfs4_verifier clverifier = setclid->se_verf; - unsigned int strhashval; struct nfs4_client *conf, *unconf, *new; __be32 status; - char dname[HEXDIR_LEN]; - - status = nfs4_make_rec_clidname(dname, &clname); - if (status) - return status; - - strhashval = clientstr_hashval(dname); + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); /* Cases below refer to rfc 3530 section 14.2.33: */ nfs4_lock_state(); - conf = find_confirmed_client_by_str(dname, strhashval); + conf = find_confirmed_client_by_name(&clname, nn); if (conf) { /* case 0: */ status = nfserr_clid_inuse; @@ -2209,21 +2225,21 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } } - unconf = find_unconfirmed_client_by_str(dname, strhashval); + unconf = find_unconfirmed_client_by_name(&clname, nn); if (unconf) expire_client(unconf); status = nfserr_jukebox; - new = create_client(clname, dname, rqstp, &clverifier); + new = create_client(clname, rqstp, &clverifier); if (new == NULL) goto out; if (conf && same_verf(&conf->cl_verifier, &clverifier)) /* case 1: probable callback update */ copy_clid(new, conf); else /* case 4 (new client) or cases 2, 3 (client reboot): */ - gen_clid(new); + gen_clid(new, nn); new->cl_minorversion = 0; gen_callback(new, setclid, rqstp); - add_to_unconfirmed(new, strhashval); + add_to_unconfirmed(new); setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot; setclid->se_clientid.cl_id = new->cl_clientid.cl_id; memcpy(setclid->se_confirm.data, new->cl_confirm.data, sizeof(setclid->se_confirm.data)); @@ -2243,14 +2259,14 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, nfs4_verifier confirm = setclientid_confirm->sc_confirm; clientid_t * clid = &setclientid_confirm->sc_clientid; __be32 status; - struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (STALE_CLIENTID(clid, nn)) return nfserr_stale_clientid; nfs4_lock_state(); - conf = find_confirmed_client(clid, false); - unconf = find_unconfirmed_client(clid, false); + conf = find_confirmed_client(clid, false, nn); + unconf = find_unconfirmed_client(clid, false, nn); /* * We try hard to give out unique clientid's, so if we get an * attempt to confirm the same clientid with a different cred, @@ -2276,9 +2292,7 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, nfsd4_probe_callback(conf); expire_client(unconf); } else { /* case 3: normal case; new or rebooted client */ - unsigned int hash = clientstr_hashval(unconf->cl_recdir); - - conf = find_confirmed_client_by_str(unconf->cl_recdir, hash); + conf = find_confirmed_client_by_name(&unconf->cl_name, nn); if (conf) expire_client(conf); move_to_confirmed(unconf); @@ -2340,7 +2354,7 @@ nfsd4_init_slabs(void) if (openowner_slab == NULL) goto out_nomem; lockowner_slab = kmem_cache_create("nfsd4_lockowners", - sizeof(struct nfs4_openowner), 0, 0, NULL); + sizeof(struct nfs4_lockowner), 0, 0, NULL); if (lockowner_slab == NULL) goto out_nomem; file_slab = kmem_cache_create("nfsd4_files", @@ -2404,7 +2418,9 @@ static inline void *alloc_stateowner(struct kmem_cache *slab, struct xdr_netobj static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, unsigned int strhashval) { - list_add(&oo->oo_owner.so_strhash, &ownerstr_hashtbl[strhashval]); + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + + list_add(&oo->oo_owner.so_strhash, &nn->ownerstr_hashtbl[strhashval]); list_add(&oo->oo_perclient, &clp->cl_openowners); } @@ -2444,11 +2460,13 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, } static void -move_to_close_lru(struct nfs4_openowner *oo) +move_to_close_lru(struct nfs4_openowner *oo, struct net *net) { + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + dprintk("NFSD: move_to_close_lru nfs4_openowner %p\n", oo); - list_move_tail(&oo->oo_close_lru, &close_lru); + list_move_tail(&oo->oo_close_lru, &nn->close_lru); oo->oo_time = get_seconds(); } @@ -2462,13 +2480,14 @@ same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner, } static struct nfs4_openowner * -find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open, bool sessions) +find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open, + bool sessions, struct nfsd_net *nn) { struct nfs4_stateowner *so; struct nfs4_openowner *oo; struct nfs4_client *clp; - list_for_each_entry(so, &ownerstr_hashtbl[hashval], so_strhash) { + list_for_each_entry(so, &nn->ownerstr_hashtbl[hashval], so_strhash) { if (!so->so_is_open_owner) continue; if (same_owner_str(so, &open->op_owner, &open->op_clientid)) { @@ -2555,9 +2574,14 @@ static void nfsd_break_deleg_cb(struct file_lock *fl) struct nfs4_file *fp = (struct nfs4_file *)fl->fl_owner; struct nfs4_delegation *dp; - BUG_ON(!fp); - /* We assume break_lease is only called once per lease: */ - BUG_ON(fp->fi_had_conflict); + if (!fp) { + WARN(1, "(%p)->fl_owner NULL\n", fl); + return; + } + if (fp->fi_had_conflict) { + WARN(1, "duplicate break on %p\n", fp); + return; + } /* * We don't want the locks code to timeout the lease for us; * we'll remove it ourself if a delegation isn't returned @@ -2599,14 +2623,13 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4 __be32 nfsd4_process_open1(struct nfsd4_compound_state *cstate, - struct nfsd4_open *open) + struct nfsd4_open *open, struct nfsd_net *nn) { clientid_t *clientid = &open->op_clientid; struct nfs4_client *clp = NULL; unsigned int strhashval; struct nfs4_openowner *oo = NULL; __be32 status; - struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); if (STALE_CLIENTID(&open->op_clientid, nn)) return nfserr_stale_clientid; @@ -2619,10 +2642,11 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate, return nfserr_jukebox; strhashval = ownerstr_hashval(clientid->cl_id, &open->op_owner); - oo = find_openstateowner_str(strhashval, open, cstate->minorversion); + oo = find_openstateowner_str(strhashval, open, cstate->minorversion, nn); open->op_openowner = oo; if (!oo) { - clp = find_confirmed_client(clientid, cstate->minorversion); + clp = find_confirmed_client(clientid, cstate->minorversion, + nn); if (clp == NULL) return nfserr_expired; goto new_owner; @@ -2891,7 +2915,7 @@ static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) open->op_why_no_deleg = WND4_CANCELLED; break; case NFS4_SHARE_WANT_NO_DELEG: - BUG(); /* not supposed to get here */ + WARN_ON_ONCE(1); } } } @@ -2959,6 +2983,7 @@ out: } return; out_free: + unhash_stid(&dp->dl_stid); nfs4_put_delegation(dp); out_no_deleg: flag = NFS4_OPEN_DELEGATE_NONE; @@ -3104,27 +3129,32 @@ void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status) free_generic_stateid(open->op_stp); } +static __be32 lookup_clientid(clientid_t *clid, bool session, struct nfsd_net *nn, struct nfs4_client **clp) +{ + struct nfs4_client *found; + + if (STALE_CLIENTID(clid, nn)) + return nfserr_stale_clientid; + found = find_confirmed_client(clid, session, nn); + if (clp) + *clp = found; + return found ? nfs_ok : nfserr_expired; +} + __be32 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, clientid_t *clid) { struct nfs4_client *clp; __be32 status; - struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); nfs4_lock_state(); dprintk("process_renew(%08x/%08x): starting\n", clid->cl_boot, clid->cl_id); - status = nfserr_stale_clientid; - if (STALE_CLIENTID(clid, nn)) - goto out; - clp = find_confirmed_client(clid, cstate->minorversion); - status = nfserr_expired; - if (clp == NULL) { - /* We assume the client took too long to RENEW. */ - dprintk("nfsd4_renew: clientid not found!\n"); + status = lookup_clientid(clid, cstate->minorversion, nn, &clp); + if (status) goto out; - } status = nfserr_cb_path_down; if (!list_empty(&clp->cl_delegations) && clp->cl_cb_state != NFSD4_CB_UP) @@ -3136,44 +3166,42 @@ out: } static void -nfsd4_end_grace(struct net *net) +nfsd4_end_grace(struct nfsd_net *nn) { - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - /* do nothing if grace period already ended */ if (nn->grace_ended) return; dprintk("NFSD: end of grace period\n"); nn->grace_ended = true; - nfsd4_record_grace_done(net, nn->boot_time); + nfsd4_record_grace_done(nn, nn->boot_time); locks_end_grace(&nn->nfsd4_manager); /* * Now that every NFSv4 client has had the chance to recover and * to see the (possibly new, possibly shorter) lease time, we * can safely set the next grace time to the current lease time: */ - nfsd4_grace = nfsd4_lease; + nn->nfsd4_grace = nn->nfsd4_lease; } static time_t -nfs4_laundromat(void) +nfs4_laundromat(struct nfsd_net *nn) { struct nfs4_client *clp; struct nfs4_openowner *oo; struct nfs4_delegation *dp; struct list_head *pos, *next, reaplist; - time_t cutoff = get_seconds() - nfsd4_lease; - time_t t, clientid_val = nfsd4_lease; - time_t u, test_val = nfsd4_lease; + time_t cutoff = get_seconds() - nn->nfsd4_lease; + time_t t, clientid_val = nn->nfsd4_lease; + time_t u, test_val = nn->nfsd4_lease; nfs4_lock_state(); dprintk("NFSD: laundromat service - starting\n"); - nfsd4_end_grace(&init_net); + nfsd4_end_grace(nn); INIT_LIST_HEAD(&reaplist); - spin_lock(&client_lock); - list_for_each_safe(pos, next, &client_lru) { + spin_lock(&nn->client_lock); + list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) { t = clp->cl_time - cutoff; @@ -3189,7 +3217,7 @@ nfs4_laundromat(void) unhash_client_locked(clp); list_add(&clp->cl_lru, &reaplist); } - spin_unlock(&client_lock); + spin_unlock(&nn->client_lock); list_for_each_safe(pos, next, &reaplist) { clp = list_entry(pos, struct nfs4_client, cl_lru); dprintk("NFSD: purging unused client (clientid %08x)\n", @@ -3199,6 +3227,8 @@ nfs4_laundromat(void) spin_lock(&recall_lock); list_for_each_safe(pos, next, &del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); + if (net_generic(dp->dl_stid.sc_client->net, nfsd_net_id) != nn) + continue; if (time_after((unsigned long)dp->dl_time, (unsigned long)cutoff)) { u = dp->dl_time - cutoff; if (test_val > u) @@ -3212,8 +3242,8 @@ nfs4_laundromat(void) dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); unhash_delegation(dp); } - test_val = nfsd4_lease; - list_for_each_safe(pos, next, &close_lru) { + test_val = nn->nfsd4_lease; + list_for_each_safe(pos, next, &nn->close_lru) { oo = container_of(pos, struct nfs4_openowner, oo_close_lru); if (time_after((unsigned long)oo->oo_time, (unsigned long)cutoff)) { u = oo->oo_time - cutoff; @@ -3231,16 +3261,19 @@ nfs4_laundromat(void) static struct workqueue_struct *laundry_wq; static void laundromat_main(struct work_struct *); -static DECLARE_DELAYED_WORK(laundromat_work, laundromat_main); static void -laundromat_main(struct work_struct *not_used) +laundromat_main(struct work_struct *laundry) { time_t t; + struct delayed_work *dwork = container_of(laundry, struct delayed_work, + work); + struct nfsd_net *nn = container_of(dwork, struct nfsd_net, + laundromat_work); - t = nfs4_laundromat(); + t = nfs4_laundromat(nn); dprintk("NFSD: laundromat_main - sleeping for %ld seconds\n", t); - queue_delayed_work(laundry_wq, &laundromat_work, t*HZ); + queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ); } static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp) @@ -3385,16 +3418,17 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) return nfs_ok; } -static __be32 nfsd4_lookup_stateid(stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s, bool sessions) +static __be32 nfsd4_lookup_stateid(stateid_t *stateid, unsigned char typemask, + struct nfs4_stid **s, bool sessions, + struct nfsd_net *nn) { struct nfs4_client *cl; - struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) return nfserr_bad_stateid; if (STALE_STATEID(stateid, nn)) return nfserr_stale_stateid; - cl = find_confirmed_client(&stateid->si_opaque.so_clid, sessions); + cl = find_confirmed_client(&stateid->si_opaque.so_clid, sessions, nn); if (!cl) return nfserr_expired; *s = find_stateid_by_type(cl, stateid, typemask); @@ -3416,6 +3450,7 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, struct nfs4_delegation *dp = NULL; struct svc_fh *current_fh = &cstate->current_fh; struct inode *ino = current_fh->fh_dentry->d_inode; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); __be32 status; if (filpp) @@ -3427,7 +3462,8 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) return check_special_stateids(net, current_fh, stateid, flags); - status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, &s, cstate->minorversion); + status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, + &s, cstate->minorversion, nn); if (status) return status; status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate)); @@ -3441,7 +3477,11 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, goto out; if (filpp) { *filpp = dp->dl_file->fi_deleg_file; - BUG_ON(!*filpp); + if (!*filpp) { + WARN_ON_ONCE(1); + status = nfserr_serverfault; + goto out; + } } break; case NFS4_OPEN_STID: @@ -3568,7 +3608,8 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ static __be32 nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, stateid_t *stateid, char typemask, - struct nfs4_ol_stateid **stpp) + struct nfs4_ol_stateid **stpp, + struct nfsd_net *nn) { __be32 status; struct nfs4_stid *s; @@ -3577,7 +3618,8 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, seqid, STATEID_VAL(stateid)); *stpp = NULL; - status = nfsd4_lookup_stateid(stateid, typemask, &s, cstate->minorversion); + status = nfsd4_lookup_stateid(stateid, typemask, &s, + cstate->minorversion, nn); if (status) return status; *stpp = openlockstateid(s); @@ -3586,13 +3628,14 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, return nfs4_seqid_op_checks(cstate, stateid, seqid, *stpp); } -static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, stateid_t *stateid, struct nfs4_ol_stateid **stpp) +static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, + stateid_t *stateid, struct nfs4_ol_stateid **stpp, struct nfsd_net *nn) { __be32 status; struct nfs4_openowner *oo; status = nfs4_preprocess_seqid_op(cstate, seqid, stateid, - NFS4_OPEN_STID, stpp); + NFS4_OPEN_STID, stpp, nn); if (status) return status; oo = openowner((*stpp)->st_stateowner); @@ -3608,6 +3651,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfs4_openowner *oo; struct nfs4_ol_stateid *stp; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); dprintk("NFSD: nfsd4_open_confirm on file %.*s\n", (int)cstate->current_fh.fh_dentry->d_name.len, @@ -3621,7 +3665,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_seqid_op(cstate, oc->oc_seqid, &oc->oc_req_stateid, - NFS4_OPEN_STID, &stp); + NFS4_OPEN_STID, &stp, nn); if (status) goto out; oo = openowner(stp->st_stateowner); @@ -3664,7 +3708,7 @@ static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_ac case NFS4_SHARE_ACCESS_BOTH: break; default: - BUG(); + WARN_ON_ONCE(1); } } @@ -3685,6 +3729,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, { __be32 status; struct nfs4_ol_stateid *stp; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); dprintk("NFSD: nfsd4_open_downgrade on file %.*s\n", (int)cstate->current_fh.fh_dentry->d_name.len, @@ -3697,7 +3742,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, nfs4_lock_state(); status = nfs4_preprocess_confirmed_seqid_op(cstate, od->od_seqid, - &od->od_stateid, &stp); + &od->od_stateid, &stp, nn); if (status) goto out; status = nfserr_inval; @@ -3760,6 +3805,8 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfs4_openowner *oo; struct nfs4_ol_stateid *stp; + struct net *net = SVC_NET(rqstp); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); dprintk("NFSD: nfsd4_close on file %.*s\n", (int)cstate->current_fh.fh_dentry->d_name.len, @@ -3769,7 +3816,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_seqid_op(cstate, close->cl_seqid, &close->cl_stateid, NFS4_OPEN_STID|NFS4_CLOSED_STID, - &stp); + &stp, nn); if (status) goto out; oo = openowner(stp->st_stateowner); @@ -3791,7 +3838,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, * little while to handle CLOSE replay. */ if (list_empty(&oo->oo_owner.so_stateids)) - move_to_close_lru(oo); + move_to_close_lru(oo, SVC_NET(rqstp)); } } out: @@ -3807,15 +3854,15 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfs4_delegation *dp; stateid_t *stateid = &dr->dr_stateid; struct nfs4_stid *s; - struct inode *inode; __be32 status; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) return status; - inode = cstate->current_fh.fh_dentry->d_inode; nfs4_lock_state(); - status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID, &s, cstate->minorversion); + status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID, &s, + cstate->minorversion, nn); if (status) goto out; dp = delegstateid(s); @@ -3833,8 +3880,6 @@ out: #define LOFF_OVERFLOW(start, len) ((u64)(len) > ~(u64)(start)) -#define LOCKOWNER_INO_HASH_BITS 8 -#define LOCKOWNER_INO_HASH_SIZE (1 << LOCKOWNER_INO_HASH_BITS) #define LOCKOWNER_INO_HASH_MASK (LOCKOWNER_INO_HASH_SIZE - 1) static inline u64 @@ -3852,7 +3897,7 @@ last_byte_offset(u64 start, u64 len) { u64 end; - BUG_ON(!len); + WARN_ON_ONCE(!len); end = start + len; return end > start ? end - 1: NFS4_MAX_UINT64; } @@ -3864,8 +3909,6 @@ static unsigned int lockowner_ino_hashval(struct inode *inode, u32 cl_id, struct & LOCKOWNER_INO_HASH_MASK; } -static struct list_head lockowner_ino_hashtbl[LOCKOWNER_INO_HASH_SIZE]; - /* * TODO: Linux file offsets are _signed_ 64-bit quantities, which means that * we can't properly handle lock requests that go beyond the (2^63 - 1)-th @@ -3931,12 +3974,12 @@ static bool same_lockowner_ino(struct nfs4_lockowner *lo, struct inode *inode, c static struct nfs4_lockowner * find_lockowner_str(struct inode *inode, clientid_t *clid, - struct xdr_netobj *owner) + struct xdr_netobj *owner, struct nfsd_net *nn) { unsigned int hashval = lockowner_ino_hashval(inode, clid->cl_id, owner); struct nfs4_lockowner *lo; - list_for_each_entry(lo, &lockowner_ino_hashtbl[hashval], lo_owner_ino_hash) { + list_for_each_entry(lo, &nn->lockowner_ino_hashtbl[hashval], lo_owner_ino_hash) { if (same_lockowner_ino(lo, inode, clid, owner)) return lo; } @@ -3948,9 +3991,10 @@ static void hash_lockowner(struct nfs4_lockowner *lo, unsigned int strhashval, s struct inode *inode = open_stp->st_file->fi_inode; unsigned int inohash = lockowner_ino_hashval(inode, clp->cl_clientid.cl_id, &lo->lo_owner.so_owner); + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - list_add(&lo->lo_owner.so_strhash, &ownerstr_hashtbl[strhashval]); - list_add(&lo->lo_owner_ino_hash, &lockowner_ino_hashtbl[inohash]); + list_add(&lo->lo_owner.so_strhash, &nn->ownerstr_hashtbl[strhashval]); + list_add(&lo->lo_owner_ino_hash, &nn->lockowner_ino_hashtbl[inohash]); list_add(&lo->lo_perstateid, &open_stp->st_lockowners); } @@ -4024,8 +4068,10 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, s struct nfs4_client *cl = oo->oo_owner.so_client; struct nfs4_lockowner *lo; unsigned int strhashval; + struct nfsd_net *nn = net_generic(cl->net, nfsd_net_id); - lo = find_lockowner_str(fi->fi_inode, &cl->cl_clientid, &lock->v.new.owner); + lo = find_lockowner_str(fi->fi_inode, &cl->cl_clientid, + &lock->v.new.owner, nn); if (lo) { if (!cstate->minorversion) return nfserr_bad_seqid; @@ -4065,7 +4111,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, bool new_state = false; int lkflg; int err; - struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); + struct net *net = SVC_NET(rqstp); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); dprintk("NFSD: nfsd4_lock: start=%Ld length=%Ld\n", (long long) lock->lk_offset, @@ -4099,7 +4146,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_confirmed_seqid_op(cstate, lock->lk_new_open_seqid, &lock->lk_new_open_stateid, - &open_stp); + &open_stp, nn); if (status) goto out; open_sop = openowner(open_stp->st_stateowner); @@ -4113,7 +4160,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, &lock->lk_old_lock_stateid, - NFS4_LOCK_STID, &lock_stp); + NFS4_LOCK_STID, &lock_stp, nn); if (status) goto out; lock_sop = lockowner(lock_stp->st_stateowner); @@ -4124,10 +4171,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; status = nfserr_grace; - if (locks_in_grace(SVC_NET(rqstp)) && !lock->lk_reclaim) + if (locks_in_grace(net) && !lock->lk_reclaim) goto out; status = nfserr_no_grace; - if (!locks_in_grace(SVC_NET(rqstp)) && lock->lk_reclaim) + if (!locks_in_grace(net) && lock->lk_reclaim) goto out; file_lock = locks_alloc_lock(); @@ -4238,7 +4285,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct file_lock *file_lock = NULL; struct nfs4_lockowner *lo; __be32 status; - struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (locks_in_grace(SVC_NET(rqstp))) return nfserr_grace; @@ -4248,9 +4295,11 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); - status = nfserr_stale_clientid; - if (!nfsd4_has_session(cstate) && STALE_CLIENTID(&lockt->lt_clientid, nn)) - goto out; + if (!nfsd4_has_session(cstate)) { + status = lookup_clientid(&lockt->lt_clientid, false, nn, NULL); + if (status) + goto out; + } if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) goto out; @@ -4278,7 +4327,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } - lo = find_lockowner_str(inode, &lockt->lt_clientid, &lockt->lt_owner); + lo = find_lockowner_str(inode, &lockt->lt_clientid, &lockt->lt_owner, nn); if (lo) file_lock->fl_owner = (fl_owner_t)lo; file_lock->fl_pid = current->tgid; @@ -4313,7 +4362,8 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct file_lock *file_lock = NULL; __be32 status; int err; - + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + dprintk("NFSD: nfsd4_locku: start=%Ld length=%Ld\n", (long long) locku->lu_offset, (long long) locku->lu_length); @@ -4324,7 +4374,8 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_lock_state(); status = nfs4_preprocess_seqid_op(cstate, locku->lu_seqid, - &locku->lu_stateid, NFS4_LOCK_STID, &stp); + &locku->lu_stateid, NFS4_LOCK_STID, + &stp, nn); if (status) goto out; filp = find_any_file(stp->st_file); @@ -4414,23 +4465,21 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, struct list_head matches; unsigned int hashval = ownerstr_hashval(clid->cl_id, owner); __be32 status; - struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n", clid->cl_boot, clid->cl_id); - /* XXX check for lease expiration */ - - status = nfserr_stale_clientid; - if (STALE_CLIENTID(clid, nn)) - return status; - nfs4_lock_state(); + status = lookup_clientid(clid, cstate->minorversion, nn, NULL); + if (status) + goto out; + status = nfserr_locks_held; INIT_LIST_HEAD(&matches); - list_for_each_entry(sop, &ownerstr_hashtbl[hashval], so_strhash) { + list_for_each_entry(sop, &nn->ownerstr_hashtbl[hashval], so_strhash) { if (sop->so_is_open_owner) continue; if (!same_owner_str(sop, owner, clid)) @@ -4466,73 +4515,74 @@ alloc_reclaim(void) return kmalloc(sizeof(struct nfs4_client_reclaim), GFP_KERNEL); } -int -nfs4_has_reclaimed_state(const char *name, bool use_exchange_id) +bool +nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn) { - unsigned int strhashval = clientstr_hashval(name); - struct nfs4_client *clp; + struct nfs4_client_reclaim *crp; - clp = find_confirmed_client_by_str(name, strhashval); - if (!clp) - return 0; - return test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags); + crp = nfsd4_find_reclaim_client(name, nn); + return (crp && crp->cr_clp); } /* * failure => all reset bets are off, nfserr_no_grace... */ -int -nfs4_client_to_reclaim(const char *name) +struct nfs4_client_reclaim * +nfs4_client_to_reclaim(const char *name, struct nfsd_net *nn) { unsigned int strhashval; - struct nfs4_client_reclaim *crp = NULL; + struct nfs4_client_reclaim *crp; dprintk("NFSD nfs4_client_to_reclaim NAME: %.*s\n", HEXDIR_LEN, name); crp = alloc_reclaim(); - if (!crp) - return 0; - strhashval = clientstr_hashval(name); - INIT_LIST_HEAD(&crp->cr_strhash); - list_add(&crp->cr_strhash, &reclaim_str_hashtbl[strhashval]); - memcpy(crp->cr_recdir, name, HEXDIR_LEN); - reclaim_str_hashtbl_size++; - return 1; + if (crp) { + strhashval = clientstr_hashval(name); + INIT_LIST_HEAD(&crp->cr_strhash); + list_add(&crp->cr_strhash, &nn->reclaim_str_hashtbl[strhashval]); + memcpy(crp->cr_recdir, name, HEXDIR_LEN); + crp->cr_clp = NULL; + nn->reclaim_str_hashtbl_size++; + } + return crp; +} + +void +nfs4_remove_reclaim_record(struct nfs4_client_reclaim *crp, struct nfsd_net *nn) +{ + list_del(&crp->cr_strhash); + kfree(crp); + nn->reclaim_str_hashtbl_size--; } void -nfs4_release_reclaim(void) +nfs4_release_reclaim(struct nfsd_net *nn) { struct nfs4_client_reclaim *crp = NULL; int i; for (i = 0; i < CLIENT_HASH_SIZE; i++) { - while (!list_empty(&reclaim_str_hashtbl[i])) { - crp = list_entry(reclaim_str_hashtbl[i].next, + while (!list_empty(&nn->reclaim_str_hashtbl[i])) { + crp = list_entry(nn->reclaim_str_hashtbl[i].next, struct nfs4_client_reclaim, cr_strhash); - list_del(&crp->cr_strhash); - kfree(crp); - reclaim_str_hashtbl_size--; + nfs4_remove_reclaim_record(crp, nn); } } - BUG_ON(reclaim_str_hashtbl_size); + WARN_ON_ONCE(nn->reclaim_str_hashtbl_size); } /* * called from OPEN, CLAIM_PREVIOUS with a new clientid. */ struct nfs4_client_reclaim * -nfsd4_find_reclaim_client(struct nfs4_client *clp) +nfsd4_find_reclaim_client(const char *recdir, struct nfsd_net *nn) { unsigned int strhashval; struct nfs4_client_reclaim *crp = NULL; - dprintk("NFSD: nfs4_find_reclaim_client for %.*s with recdir %s\n", - clp->cl_name.len, clp->cl_name.data, - clp->cl_recdir); + dprintk("NFSD: nfs4_find_reclaim_client for recdir %s\n", recdir); - /* find clp->cl_name in reclaim_str_hashtbl */ - strhashval = clientstr_hashval(clp->cl_recdir); - list_for_each_entry(crp, &reclaim_str_hashtbl[strhashval], cr_strhash) { - if (same_name(crp->cr_recdir, clp->cl_recdir)) { + strhashval = clientstr_hashval(recdir); + list_for_each_entry(crp, &nn->reclaim_str_hashtbl[strhashval], cr_strhash) { + if (same_name(crp->cr_recdir, recdir)) { return crp; } } @@ -4543,12 +4593,12 @@ nfsd4_find_reclaim_client(struct nfs4_client *clp) * Called from OPEN. Look for clientid in reclaim list. */ __be32 -nfs4_check_open_reclaim(clientid_t *clid, bool sessions) +nfs4_check_open_reclaim(clientid_t *clid, bool sessions, struct nfsd_net *nn) { struct nfs4_client *clp; /* find clientid in conf_id_hashtbl */ - clp = find_confirmed_client(clid, sessions); + clp = find_confirmed_client(clid, sessions, nn); if (clp == NULL) return nfserr_reclaim_bad; @@ -4557,124 +4607,177 @@ nfs4_check_open_reclaim(clientid_t *clid, bool sessions) #ifdef CONFIG_NFSD_FAULT_INJECTION -void nfsd_forget_clients(u64 num) +u64 nfsd_forget_client(struct nfs4_client *clp, u64 max) { - struct nfs4_client *clp, *next; - int count = 0; - - nfs4_lock_state(); - list_for_each_entry_safe(clp, next, &client_lru, cl_lru) { - expire_client(clp); - if (++count == num) - break; - } - nfs4_unlock_state(); - - printk(KERN_INFO "NFSD: Forgot %d clients", count); + expire_client(clp); + return 1; } -static void release_lockowner_sop(struct nfs4_stateowner *sop) +u64 nfsd_print_client(struct nfs4_client *clp, u64 num) { - release_lockowner(lockowner(sop)); + char buf[INET6_ADDRSTRLEN]; + rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf)); + printk(KERN_INFO "NFS Client: %s\n", buf); + return 1; } -static void release_openowner_sop(struct nfs4_stateowner *sop) +static void nfsd_print_count(struct nfs4_client *clp, unsigned int count, + const char *type) { - release_openowner(openowner(sop)); + char buf[INET6_ADDRSTRLEN]; + rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf)); + printk(KERN_INFO "NFS Client: %s has %u %s\n", buf, count, type); } -static int nfsd_release_n_owners(u64 num, bool is_open_owner, - void (*release_sop)(struct nfs4_stateowner *)) +static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max, void (*func)(struct nfs4_lockowner *)) { - int i, count = 0; - struct nfs4_stateowner *sop, *next; + struct nfs4_openowner *oop; + struct nfs4_lockowner *lop, *lo_next; + struct nfs4_ol_stateid *stp, *st_next; + u64 count = 0; - for (i = 0; i < OWNER_HASH_SIZE; i++) { - list_for_each_entry_safe(sop, next, &ownerstr_hashtbl[i], so_strhash) { - if (sop->so_is_open_owner != is_open_owner) - continue; - release_sop(sop); - if (++count == num) - return count; + list_for_each_entry(oop, &clp->cl_openowners, oo_perclient) { + list_for_each_entry_safe(stp, st_next, &oop->oo_owner.so_stateids, st_perstateowner) { + list_for_each_entry_safe(lop, lo_next, &stp->st_lockowners, lo_perstateid) { + if (func) + func(lop); + if (++count == max) + return count; + } } } + return count; } -void nfsd_forget_locks(u64 num) +u64 nfsd_forget_client_locks(struct nfs4_client *clp, u64 max) { - int count; - - nfs4_lock_state(); - count = nfsd_release_n_owners(num, false, release_lockowner_sop); - nfs4_unlock_state(); + return nfsd_foreach_client_lock(clp, max, release_lockowner); +} - printk(KERN_INFO "NFSD: Forgot %d locks", count); +u64 nfsd_print_client_locks(struct nfs4_client *clp, u64 max) +{ + u64 count = nfsd_foreach_client_lock(clp, max, NULL); + nfsd_print_count(clp, count, "locked files"); + return count; } -void nfsd_forget_openowners(u64 num) +static u64 nfsd_foreach_client_open(struct nfs4_client *clp, u64 max, void (*func)(struct nfs4_openowner *)) { - int count; + struct nfs4_openowner *oop, *next; + u64 count = 0; - nfs4_lock_state(); - count = nfsd_release_n_owners(num, true, release_openowner_sop); - nfs4_unlock_state(); + list_for_each_entry_safe(oop, next, &clp->cl_openowners, oo_perclient) { + if (func) + func(oop); + if (++count == max) + break; + } - printk(KERN_INFO "NFSD: Forgot %d open owners", count); + return count; } -static int nfsd_process_n_delegations(u64 num, struct list_head *list) +u64 nfsd_forget_client_openowners(struct nfs4_client *clp, u64 max) { - int i, count = 0; - struct nfs4_file *fp, *fnext; - struct nfs4_delegation *dp, *dnext; + return nfsd_foreach_client_open(clp, max, release_openowner); +} - for (i = 0; i < FILE_HASH_SIZE; i++) { - list_for_each_entry_safe(fp, fnext, &file_hashtbl[i], fi_hash) { - list_for_each_entry_safe(dp, dnext, &fp->fi_delegations, dl_perfile) { - list_move(&dp->dl_recall_lru, list); - if (++count == num) - return count; - } - } - } +u64 nfsd_print_client_openowners(struct nfs4_client *clp, u64 max) +{ + u64 count = nfsd_foreach_client_open(clp, max, NULL); + nfsd_print_count(clp, count, "open files"); + return count; +} + +static u64 nfsd_find_all_delegations(struct nfs4_client *clp, u64 max, + struct list_head *victims) +{ + struct nfs4_delegation *dp, *next; + u64 count = 0; + list_for_each_entry_safe(dp, next, &clp->cl_delegations, dl_perclnt) { + if (victims) + list_move(&dp->dl_recall_lru, victims); + if (++count == max) + break; + } return count; } -void nfsd_forget_delegations(u64 num) +u64 nfsd_forget_client_delegations(struct nfs4_client *clp, u64 max) { - unsigned int count; + struct nfs4_delegation *dp, *next; LIST_HEAD(victims); - struct nfs4_delegation *dp, *dnext; + u64 count; spin_lock(&recall_lock); - count = nfsd_process_n_delegations(num, &victims); + count = nfsd_find_all_delegations(clp, max, &victims); spin_unlock(&recall_lock); - nfs4_lock_state(); - list_for_each_entry_safe(dp, dnext, &victims, dl_recall_lru) + list_for_each_entry_safe(dp, next, &victims, dl_recall_lru) unhash_delegation(dp); - nfs4_unlock_state(); - printk(KERN_INFO "NFSD: Forgot %d delegations", count); + return count; } -void nfsd_recall_delegations(u64 num) +u64 nfsd_recall_client_delegations(struct nfs4_client *clp, u64 max) { - unsigned int count; + struct nfs4_delegation *dp, *next; LIST_HEAD(victims); - struct nfs4_delegation *dp, *dnext; + u64 count; spin_lock(&recall_lock); - count = nfsd_process_n_delegations(num, &victims); - list_for_each_entry_safe(dp, dnext, &victims, dl_recall_lru) { - list_del(&dp->dl_recall_lru); + count = nfsd_find_all_delegations(clp, max, &victims); + list_for_each_entry_safe(dp, next, &victims, dl_recall_lru) nfsd_break_one_deleg(dp); - } spin_unlock(&recall_lock); - printk(KERN_INFO "NFSD: Recalled %d delegations", count); + return count; +} + +u64 nfsd_print_client_delegations(struct nfs4_client *clp, u64 max) +{ + u64 count = 0; + + spin_lock(&recall_lock); + count = nfsd_find_all_delegations(clp, max, NULL); + spin_unlock(&recall_lock); + + nfsd_print_count(clp, count, "delegations"); + return count; +} + +u64 nfsd_for_n_state(u64 max, u64 (*func)(struct nfs4_client *, u64)) +{ + struct nfs4_client *clp, *next; + u64 count = 0; + struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, nfsd_net_id); + + if (!nfsd_netns_ready(nn)) + return 0; + + list_for_each_entry_safe(clp, next, &nn->client_lru, cl_lru) { + count += func(clp, max - count); + if ((max != 0) && (count >= max)) + break; + } + + return count; +} + +struct nfs4_client *nfsd_find_client(struct sockaddr_storage *addr, size_t addr_size) +{ + struct nfs4_client *clp; + struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, nfsd_net_id); + + if (!nfsd_netns_ready(nn)) + return NULL; + + list_for_each_entry(clp, &nn->client_lru, cl_lru) { + if (memcmp(&clp->cl_addr, addr, addr_size) == 0) + return clp; + } + return NULL; } #endif /* CONFIG_NFSD_FAULT_INJECTION */ @@ -4686,27 +4789,10 @@ nfs4_state_init(void) { int i; - for (i = 0; i < CLIENT_HASH_SIZE; i++) { - INIT_LIST_HEAD(&conf_id_hashtbl[i]); - INIT_LIST_HEAD(&conf_str_hashtbl[i]); - INIT_LIST_HEAD(&unconf_str_hashtbl[i]); - INIT_LIST_HEAD(&unconf_id_hashtbl[i]); - INIT_LIST_HEAD(&reclaim_str_hashtbl[i]); - } - for (i = 0; i < SESSION_HASH_SIZE; i++) - INIT_LIST_HEAD(&sessionid_hashtbl[i]); for (i = 0; i < FILE_HASH_SIZE; i++) { INIT_LIST_HEAD(&file_hashtbl[i]); } - for (i = 0; i < OWNER_HASH_SIZE; i++) { - INIT_LIST_HEAD(&ownerstr_hashtbl[i]); - } - for (i = 0; i < LOCKOWNER_INO_HASH_SIZE; i++) - INIT_LIST_HEAD(&lockowner_ino_hashtbl[i]); - INIT_LIST_HEAD(&close_lru); - INIT_LIST_HEAD(&client_lru); INIT_LIST_HEAD(&del_recall_lru); - reclaim_str_hashtbl_size = 0; } /* @@ -4730,12 +4816,100 @@ set_max_delegations(void) max_delegations = nr_free_buffer_pages() >> (20 - 2 - PAGE_SHIFT); } -/* initialization to perform when the nfsd service is started: */ +static int nfs4_state_create_net(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + int i; + + nn->conf_id_hashtbl = kmalloc(sizeof(struct list_head) * + CLIENT_HASH_SIZE, GFP_KERNEL); + if (!nn->conf_id_hashtbl) + goto err; + nn->unconf_id_hashtbl = kmalloc(sizeof(struct list_head) * + CLIENT_HASH_SIZE, GFP_KERNEL); + if (!nn->unconf_id_hashtbl) + goto err_unconf_id; + nn->ownerstr_hashtbl = kmalloc(sizeof(struct list_head) * + OWNER_HASH_SIZE, GFP_KERNEL); + if (!nn->ownerstr_hashtbl) + goto err_ownerstr; + nn->lockowner_ino_hashtbl = kmalloc(sizeof(struct list_head) * + LOCKOWNER_INO_HASH_SIZE, GFP_KERNEL); + if (!nn->lockowner_ino_hashtbl) + goto err_lockowner_ino; + nn->sessionid_hashtbl = kmalloc(sizeof(struct list_head) * + SESSION_HASH_SIZE, GFP_KERNEL); + if (!nn->sessionid_hashtbl) + goto err_sessionid; + + for (i = 0; i < CLIENT_HASH_SIZE; i++) { + INIT_LIST_HEAD(&nn->conf_id_hashtbl[i]); + INIT_LIST_HEAD(&nn->unconf_id_hashtbl[i]); + } + for (i = 0; i < OWNER_HASH_SIZE; i++) + INIT_LIST_HEAD(&nn->ownerstr_hashtbl[i]); + for (i = 0; i < LOCKOWNER_INO_HASH_SIZE; i++) + INIT_LIST_HEAD(&nn->lockowner_ino_hashtbl[i]); + for (i = 0; i < SESSION_HASH_SIZE; i++) + INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]); + nn->conf_name_tree = RB_ROOT; + nn->unconf_name_tree = RB_ROOT; + INIT_LIST_HEAD(&nn->client_lru); + INIT_LIST_HEAD(&nn->close_lru); + spin_lock_init(&nn->client_lock); + + INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); + get_net(net); + + return 0; + +err_sessionid: + kfree(nn->lockowner_ino_hashtbl); +err_lockowner_ino: + kfree(nn->ownerstr_hashtbl); +err_ownerstr: + kfree(nn->unconf_id_hashtbl); +err_unconf_id: + kfree(nn->conf_id_hashtbl); +err: + return -ENOMEM; +} + +static void +nfs4_state_destroy_net(struct net *net) +{ + int i; + struct nfs4_client *clp = NULL; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct rb_node *node, *tmp; + + for (i = 0; i < CLIENT_HASH_SIZE; i++) { + while (!list_empty(&nn->conf_id_hashtbl[i])) { + clp = list_entry(nn->conf_id_hashtbl[i].next, struct nfs4_client, cl_idhash); + destroy_client(clp); + } + } + + node = rb_first(&nn->unconf_name_tree); + while (node != NULL) { + tmp = node; + node = rb_next(tmp); + clp = rb_entry(tmp, struct nfs4_client, cl_namenode); + rb_erase(tmp, &nn->unconf_name_tree); + destroy_client(clp); + } + + kfree(nn->sessionid_hashtbl); + kfree(nn->lockowner_ino_hashtbl); + kfree(nn->ownerstr_hashtbl); + kfree(nn->unconf_id_hashtbl); + kfree(nn->conf_id_hashtbl); + put_net(net); +} int -nfs4_state_start(void) +nfs4_state_start_net(struct net *net) { - struct net *net = &init_net; struct nfsd_net *nn = net_generic(net, nfsd_net_id); int ret; @@ -4746,18 +4920,32 @@ nfs4_state_start(void) * to that instead and then do most of the rest of this on a per-net * basis. */ - get_net(net); + if (net != &init_net) + return -EINVAL; + + ret = nfs4_state_create_net(net); + if (ret) + return ret; nfsd4_client_tracking_init(net); nn->boot_time = get_seconds(); locks_start_grace(net, &nn->nfsd4_manager); nn->grace_ended = false; - printk(KERN_INFO "NFSD: starting %ld-second grace period\n", - nfsd4_grace); + printk(KERN_INFO "NFSD: starting %ld-second grace period (net %p)\n", + nn->nfsd4_grace, net); + queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ); + return 0; +} + +/* initialization to perform when the nfsd service is started: */ + +int +nfs4_state_start(void) +{ + int ret; + ret = set_callback_cred(); - if (ret) { - ret = -ENOMEM; - goto out_recovery; - } + if (ret) + return -ENOMEM; laundry_wq = create_singlethread_workqueue("nfsd4"); if (laundry_wq == NULL) { ret = -ENOMEM; @@ -4766,39 +4954,34 @@ nfs4_state_start(void) ret = nfsd4_create_callback_queue(); if (ret) goto out_free_laundry; - queue_delayed_work(laundry_wq, &laundromat_work, nfsd4_grace * HZ); + set_max_delegations(); + return 0; + out_free_laundry: destroy_workqueue(laundry_wq); out_recovery: - nfsd4_client_tracking_exit(net); - put_net(net); return ret; } -static void -__nfs4_state_shutdown(void) +/* should be called with the state lock held */ +void +nfs4_state_shutdown_net(struct net *net) { - int i; - struct nfs4_client *clp = NULL; struct nfs4_delegation *dp = NULL; struct list_head *pos, *next, reaplist; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + cancel_delayed_work_sync(&nn->laundromat_work); + locks_end_grace(&nn->nfsd4_manager); - for (i = 0; i < CLIENT_HASH_SIZE; i++) { - while (!list_empty(&conf_id_hashtbl[i])) { - clp = list_entry(conf_id_hashtbl[i].next, struct nfs4_client, cl_idhash); - destroy_client(clp); - } - while (!list_empty(&unconf_str_hashtbl[i])) { - clp = list_entry(unconf_str_hashtbl[i].next, struct nfs4_client, cl_strhash); - destroy_client(clp); - } - } INIT_LIST_HEAD(&reaplist); spin_lock(&recall_lock); list_for_each_safe(pos, next, &del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); + if (dp->dl_stid.sc_client->net != net) + continue; list_move(&dp->dl_recall_lru, &reaplist); } spin_unlock(&recall_lock); @@ -4807,22 +4990,14 @@ __nfs4_state_shutdown(void) unhash_delegation(dp); } - nfsd4_client_tracking_exit(&init_net); - put_net(&init_net); + nfsd4_client_tracking_exit(net); + nfs4_state_destroy_net(net); } void nfs4_state_shutdown(void) { - struct net *net = &init_net; - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - - cancel_delayed_work_sync(&laundromat_work); destroy_workqueue(laundry_wq); - locks_end_grace(&nn->nfsd4_manager); - nfs4_lock_state(); - __nfs4_state_shutdown(); - nfs4_unlock_state(); nfsd4_destroy_callback_queue(); } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index fd548d155088..0dc11586682f 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -53,6 +53,7 @@ #include "vfs.h" #include "state.h" #include "cache.h" +#include "netns.h" #define NFSDDBG_FACILITY NFSDDBG_XDR @@ -65,17 +66,17 @@ #define NFS4_REFERRAL_FSID_MINOR 0x8000000ULL static __be32 -check_filename(char *str, int len, __be32 err) +check_filename(char *str, int len) { int i; if (len == 0) return nfserr_inval; if (isdotent(str, len)) - return err; + return nfserr_badname; for (i = 0; i < len; i++) if (str[i] == '/') - return err; + return nfserr_badname; return 0; } @@ -422,6 +423,86 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access DECODE_TAIL; } +static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_cb_sec *cbs) +{ + DECODE_HEAD; + u32 dummy, uid, gid; + char *machine_name; + int i; + int nr_secflavs; + + /* callback_sec_params4 */ + READ_BUF(4); + READ32(nr_secflavs); + cbs->flavor = (u32)(-1); + for (i = 0; i < nr_secflavs; ++i) { + READ_BUF(4); + READ32(dummy); + switch (dummy) { + case RPC_AUTH_NULL: + /* Nothing to read */ + if (cbs->flavor == (u32)(-1)) + cbs->flavor = RPC_AUTH_NULL; + break; + case RPC_AUTH_UNIX: + READ_BUF(8); + /* stamp */ + READ32(dummy); + + /* machine name */ + READ32(dummy); + READ_BUF(dummy); + SAVEMEM(machine_name, dummy); + + /* uid, gid */ + READ_BUF(8); + READ32(uid); + READ32(gid); + + /* more gids */ + READ_BUF(4); + READ32(dummy); + READ_BUF(dummy * 4); + if (cbs->flavor == (u32)(-1)) { + cbs->uid = uid; + cbs->gid = gid; + cbs->flavor = RPC_AUTH_UNIX; + } + break; + case RPC_AUTH_GSS: + dprintk("RPC_AUTH_GSS callback secflavor " + "not supported!\n"); + READ_BUF(8); + /* gcbp_service */ + READ32(dummy); + /* gcbp_handle_from_server */ + READ32(dummy); + READ_BUF(dummy); + p += XDR_QUADLEN(dummy); + /* gcbp_handle_from_client */ + READ_BUF(4); + READ32(dummy); + READ_BUF(dummy); + break; + default: + dprintk("Illegal callback secflavor\n"); + return nfserr_inval; + } + } + DECODE_TAIL; +} + +static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, struct nfsd4_backchannel_ctl *bc) +{ + DECODE_HEAD; + + READ_BUF(4); + READ32(bc->bc_cb_program); + nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec); + + DECODE_TAIL; +} + static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, struct nfsd4_bind_conn_to_session *bcts) { DECODE_HEAD; @@ -490,7 +571,7 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create READ32(create->cr_namelen); READ_BUF(create->cr_namelen); SAVEMEM(create->cr_name, create->cr_namelen); - if ((status = check_filename(create->cr_name, create->cr_namelen, nfserr_inval))) + if ((status = check_filename(create->cr_name, create->cr_namelen))) return status; status = nfsd4_decode_fattr(argp, create->cr_bmval, &create->cr_iattr, @@ -522,7 +603,7 @@ nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link) READ32(link->li_namelen); READ_BUF(link->li_namelen); SAVEMEM(link->li_name, link->li_namelen); - if ((status = check_filename(link->li_name, link->li_namelen, nfserr_inval))) + if ((status = check_filename(link->li_name, link->li_namelen))) return status; DECODE_TAIL; @@ -616,7 +697,7 @@ nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup READ32(lookup->lo_len); READ_BUF(lookup->lo_len); SAVEMEM(lookup->lo_name, lookup->lo_len); - if ((status = check_filename(lookup->lo_name, lookup->lo_len, nfserr_noent))) + if ((status = check_filename(lookup->lo_name, lookup->lo_len))) return status; DECODE_TAIL; @@ -780,7 +861,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) READ32(open->op_fname.len); READ_BUF(open->op_fname.len); SAVEMEM(open->op_fname.data, open->op_fname.len); - if ((status = check_filename(open->op_fname.data, open->op_fname.len, nfserr_inval))) + if ((status = check_filename(open->op_fname.data, open->op_fname.len))) return status; break; case NFS4_OPEN_CLAIM_PREVIOUS: @@ -795,7 +876,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) READ32(open->op_fname.len); READ_BUF(open->op_fname.len); SAVEMEM(open->op_fname.data, open->op_fname.len); - if ((status = check_filename(open->op_fname.data, open->op_fname.len, nfserr_inval))) + if ((status = check_filename(open->op_fname.data, open->op_fname.len))) return status; break; case NFS4_OPEN_CLAIM_FH: @@ -907,7 +988,7 @@ nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove READ32(remove->rm_namelen); READ_BUF(remove->rm_namelen); SAVEMEM(remove->rm_name, remove->rm_namelen); - if ((status = check_filename(remove->rm_name, remove->rm_namelen, nfserr_noent))) + if ((status = check_filename(remove->rm_name, remove->rm_namelen))) return status; DECODE_TAIL; @@ -925,9 +1006,9 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename READ32(rename->rn_tnamelen); READ_BUF(rename->rn_tnamelen); SAVEMEM(rename->rn_tname, rename->rn_tnamelen); - if ((status = check_filename(rename->rn_sname, rename->rn_snamelen, nfserr_noent))) + if ((status = check_filename(rename->rn_sname, rename->rn_snamelen))) return status; - if ((status = check_filename(rename->rn_tname, rename->rn_tnamelen, nfserr_inval))) + if ((status = check_filename(rename->rn_tname, rename->rn_tnamelen))) return status; DECODE_TAIL; @@ -954,8 +1035,7 @@ nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp, READ32(secinfo->si_namelen); READ_BUF(secinfo->si_namelen); SAVEMEM(secinfo->si_name, secinfo->si_namelen); - status = check_filename(secinfo->si_name, secinfo->si_namelen, - nfserr_noent); + status = check_filename(secinfo->si_name, secinfo->si_namelen); if (status) return status; DECODE_TAIL; @@ -1026,31 +1106,14 @@ nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_s static __be32 nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify) { -#if 0 - struct nfsd4_compoundargs save = { - .p = argp->p, - .end = argp->end, - .rqstp = argp->rqstp, - }; - u32 ve_bmval[2]; - struct iattr ve_iattr; /* request */ - struct nfs4_acl *ve_acl; /* request */ -#endif DECODE_HEAD; if ((status = nfsd4_decode_bitmap(argp, verify->ve_bmval))) goto out; /* For convenience's sake, we compare raw xdr'd attributes in - * nfsd4_proc_verify; however we still decode here just to return - * correct error in case of bad xdr. */ -#if 0 - status = nfsd4_decode_fattr(ve_bmval, &ve_iattr, &ve_acl); - if (status == nfserr_inval) { - status = nfserrno(status); - goto out; - } -#endif + * nfsd4_proc_verify */ + READ_BUF(4); READ32(verify->ve_attrlen); READ_BUF(verify->ve_attrlen); @@ -1063,7 +1126,6 @@ static __be32 nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) { int avail; - int v; int len; DECODE_HEAD; @@ -1087,27 +1149,26 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) __FILE__, __LINE__); goto xdr_error; } - argp->rqstp->rq_vec[0].iov_base = p; - argp->rqstp->rq_vec[0].iov_len = avail; - v = 0; - len = write->wr_buflen; - while (len > argp->rqstp->rq_vec[v].iov_len) { - len -= argp->rqstp->rq_vec[v].iov_len; - v++; - argp->rqstp->rq_vec[v].iov_base = page_address(argp->pagelist[0]); - argp->pagelist++; - if (argp->pagelen >= PAGE_SIZE) { - argp->rqstp->rq_vec[v].iov_len = PAGE_SIZE; - argp->pagelen -= PAGE_SIZE; - } else { - argp->rqstp->rq_vec[v].iov_len = argp->pagelen; - argp->pagelen -= len; - } + write->wr_head.iov_base = p; + write->wr_head.iov_len = avail; + WARN_ON(avail != (XDR_QUADLEN(avail) << 2)); + write->wr_pagelist = argp->pagelist; + + len = XDR_QUADLEN(write->wr_buflen) << 2; + if (len >= avail) { + int pages; + + len -= avail; + + pages = len >> PAGE_SHIFT; + argp->pagelist += pages; + argp->pagelen -= pages * PAGE_SIZE; + len -= pages * PAGE_SIZE; + + argp->p = (__be32 *)page_address(argp->pagelist[0]); + argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE); } - argp->end = (__be32*) (argp->rqstp->rq_vec[v].iov_base + argp->rqstp->rq_vec[v].iov_len); - argp->p = (__be32*) (argp->rqstp->rq_vec[v].iov_base + (XDR_QUADLEN(len) << 2)); - argp->rqstp->rq_vec[v].iov_len = len; - write->wr_vlen = v+1; + argp->p += XDR_QUADLEN(len); DECODE_TAIL; } @@ -1237,11 +1298,7 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, struct nfsd4_create_session *sess) { DECODE_HEAD; - u32 dummy; - char *machine_name; - int i; - int nr_secflavs; READ_BUF(16); COPYMEM(&sess->clientid, 8); @@ -1282,58 +1339,9 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, goto xdr_error; } - READ_BUF(8); + READ_BUF(4); READ32(sess->callback_prog); - - /* callback_sec_params4 */ - READ32(nr_secflavs); - for (i = 0; i < nr_secflavs; ++i) { - READ_BUF(4); - READ32(dummy); - switch (dummy) { - case RPC_AUTH_NULL: - /* Nothing to read */ - break; - case RPC_AUTH_UNIX: - READ_BUF(8); - /* stamp */ - READ32(dummy); - - /* machine name */ - READ32(dummy); - READ_BUF(dummy); - SAVEMEM(machine_name, dummy); - - /* uid, gid */ - READ_BUF(8); - READ32(sess->uid); - READ32(sess->gid); - - /* more gids */ - READ_BUF(4); - READ32(dummy); - READ_BUF(dummy * 4); - break; - case RPC_AUTH_GSS: - dprintk("RPC_AUTH_GSS callback secflavor " - "not supported!\n"); - READ_BUF(8); - /* gcbp_service */ - READ32(dummy); - /* gcbp_handle_from_server */ - READ32(dummy); - READ_BUF(dummy); - p += XDR_QUADLEN(dummy); - /* gcbp_handle_from_client */ - READ_BUF(4); - READ32(dummy); - READ_BUF(dummy); - break; - default: - dprintk("Illegal callback secflavor\n"); - return nfserr_inval; - } - } + nfsd4_decode_cb_sec(argp, &sess->cb_sec); DECODE_TAIL; } @@ -1528,7 +1536,7 @@ static nfsd4_dec nfsd41_dec_ops[] = { [OP_RELEASE_LOCKOWNER] = (nfsd4_dec)nfsd4_decode_notsupp, /* new operations for NFSv4.1 */ - [OP_BACKCHANNEL_CTL] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_BACKCHANNEL_CTL] = (nfsd4_dec)nfsd4_decode_backchannel_ctl, [OP_BIND_CONN_TO_SESSION]= (nfsd4_dec)nfsd4_decode_bind_conn_to_session, [OP_EXCHANGE_ID] = (nfsd4_dec)nfsd4_decode_exchange_id, [OP_CREATE_SESSION] = (nfsd4_dec)nfsd4_decode_create_session, @@ -1568,12 +1576,6 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) bool cachethis = false; int i; - /* - * XXX: According to spec, we should check the tag - * for UTF-8 compliance. I'm postponing this for - * now because it seems that some clients do use - * binary tags. - */ READ_BUF(4); READ32(argp->taglen); READ_BUF(argp->taglen + 8); @@ -1603,38 +1605,8 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op = &argp->ops[i]; op->replay = NULL; - /* - * We can't use READ_BUF() here because we need to handle - * a missing opcode as an OP_WRITE + 1. So we need to check - * to see if we're truly at the end of our buffer or if there - * is another page we need to flip to. - */ - - if (argp->p == argp->end) { - if (argp->pagelen < 4) { - /* There isn't an opcode still on the wire */ - op->opnum = OP_WRITE + 1; - op->status = nfserr_bad_xdr; - argp->opcnt = i+1; - break; - } - - /* - * False alarm. We just hit a page boundary, but there - * is still data available. Move pointer across page - * boundary. *snip from READ_BUF* - */ - argp->p = page_address(argp->pagelist[0]); - argp->pagelist++; - if (argp->pagelen < PAGE_SIZE) { - argp->end = argp->p + (argp->pagelen>>2); - argp->pagelen = 0; - } else { - argp->end = argp->p + (PAGE_SIZE>>2); - argp->pagelen -= PAGE_SIZE; - } - } - op->opnum = ntohl(*argp->p++); + READ_BUF(4); + READ32(op->opnum); if (op->opnum >= FIRST_NFS4_OP && op->opnum <= LAST_NFS4_OP) op->status = ops->decoders[op->opnum](argp, &op->u); @@ -2014,6 +1986,22 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err) return 0; } + +static int get_parent_attributes(struct svc_export *exp, struct kstat *stat) +{ + struct path path = exp->ex_path; + int err; + + path_get(&path); + while (follow_up(&path)) { + if (path.dentry != path.mnt->mnt_root) + break; + } + err = vfs_getattr(path.mnt, path.dentry, stat); + path_put(&path); + return err; +} + /* * Note: @fhp can be NULL; in this case, we might have to compose the filehandle * ourselves. @@ -2048,6 +2036,7 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, .mnt = exp->ex_path.mnt, .dentry = dentry, }; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); BUG_ON(bmval1 & NFSD_WRITEONLY_ATTRS_WORD1); BUG_ON(bmval0 & ~nfsd_suppattrs0(minorversion)); @@ -2208,7 +2197,7 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, if (bmval0 & FATTR4_WORD0_LEASE_TIME) { if ((buflen -= 4) < 0) goto out_resource; - WRITE32(nfsd4_lease); + WRITE32(nn->nfsd4_lease); } if (bmval0 & FATTR4_WORD0_RDATTR_ERROR) { if ((buflen -= 4) < 0) @@ -2430,18 +2419,8 @@ out_acl: * and this is the root of a cross-mounted filesystem. */ if (ignore_crossmnt == 0 && - dentry == exp->ex_path.mnt->mnt_root) { - struct path path = exp->ex_path; - path_get(&path); - while (follow_up(&path)) { - if (path.dentry != path.mnt->mnt_root) - break; - } - err = vfs_getattr(path.mnt, path.dentry, &stat); - path_put(&path); - if (err) - goto out_nfserr; - } + dentry == exp->ex_path.mnt->mnt_root) + get_parent_attributes(exp, &stat); WRITE64(stat.ino); } if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) { @@ -2927,7 +2906,8 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_read *read) { u32 eof; - int v, pn; + int v; + struct page *page; unsigned long maxcount; long len; __be32 *p; @@ -2946,11 +2926,15 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, len = maxcount; v = 0; while (len > 0) { - pn = resp->rqstp->rq_resused++; - resp->rqstp->rq_vec[v].iov_base = - page_address(resp->rqstp->rq_respages[pn]); + page = *(resp->rqstp->rq_next_page); + if (!page) { /* ran out of pages */ + maxcount -= len; + break; + } + resp->rqstp->rq_vec[v].iov_base = page_address(page); resp->rqstp->rq_vec[v].iov_len = len < PAGE_SIZE ? len : PAGE_SIZE; + resp->rqstp->rq_next_page++; v++; len -= PAGE_SIZE; } @@ -2996,8 +2980,10 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd return nfserr; if (resp->xbuf->page_len) return nfserr_resource; + if (!*resp->rqstp->rq_next_page) + return nfserr_resource; - page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]); + page = page_address(*(resp->rqstp->rq_next_page++)); maxcount = PAGE_SIZE; RESERVE_SPACE(4); @@ -3045,6 +3031,8 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 return nfserr; if (resp->xbuf->page_len) return nfserr_resource; + if (!*resp->rqstp->rq_next_page) + return nfserr_resource; RESERVE_SPACE(NFS4_VERIFIER_SIZE); savep = p; @@ -3071,7 +3059,7 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 goto err_no_verf; } - page = page_address(resp->rqstp->rq_respages[resp->rqstp->rq_resused++]); + page = page_address(*(resp->rqstp->rq_next_page++)); readdir->common.err = 0; readdir->buflen = maxcount; readdir->buffer = page; @@ -3094,8 +3082,8 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 p = readdir->buffer; *p++ = 0; /* no more entries */ *p++ = htonl(readdir->common.err == nfserr_eof); - resp->xbuf->page_len = ((char*)p) - (char*)page_address( - resp->rqstp->rq_respages[resp->rqstp->rq_resused-1]); + resp->xbuf->page_len = ((char*)p) - + (char*)page_address(*(resp->rqstp->rq_next_page-1)); /* Use rest of head for padding and remaining ops: */ resp->xbuf->tail[0].iov_base = tailbase; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index dab350dfc376..74934284d9a7 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -19,7 +19,7 @@ #include "idmap.h" #include "nfsd.h" #include "cache.h" -#include "fault_inject.h" +#include "state.h" #include "netns.h" /* @@ -186,9 +186,6 @@ static struct file_operations supported_enctypes_ops = { }; #endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ -extern int nfsd_pool_stats_open(struct inode *inode, struct file *file); -extern int nfsd_pool_stats_release(struct inode *inode, struct file *file); - static const struct file_operations pool_stats_operations = { .open = nfsd_pool_stats_open, .read = seq_read, @@ -399,6 +396,8 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) { char *mesg = buf; int rv; + struct net *net = &init_net; + if (size > 0) { int newthreads; rv = get_int(&mesg, &newthreads); @@ -406,11 +405,11 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) return rv; if (newthreads < 0) return -EINVAL; - rv = nfsd_svc(newthreads); + rv = nfsd_svc(newthreads, net); if (rv < 0) return rv; } else - rv = nfsd_nrthreads(); + rv = nfsd_nrthreads(net); return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%d\n", rv); } @@ -448,9 +447,10 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size) int len; int npools; int *nthreads; + struct net *net = &init_net; mutex_lock(&nfsd_mutex); - npools = nfsd_nrpools(); + npools = nfsd_nrpools(net); if (npools == 0) { /* * NFS is shut down. The admin can start it by @@ -478,12 +478,12 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size) if (nthreads[i] < 0) goto out_free; } - rv = nfsd_set_nrthreads(i, nthreads); + rv = nfsd_set_nrthreads(i, nthreads, net); if (rv) goto out_free; } - rv = nfsd_get_nrthreads(npools, nthreads); + rv = nfsd_get_nrthreads(npools, nthreads, net); if (rv) goto out_free; @@ -510,11 +510,13 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) unsigned minor; ssize_t tlen = 0; char *sep; + struct net *net = &init_net; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (size>0) { - if (nfsd_serv) + if (nn->nfsd_serv) /* Cannot change versions without updating - * nfsd_serv->sv_xdrsize, and reallocing + * nn->nfsd_serv->sv_xdrsize, and reallocing * rq_argp and rq_resp */ return -EBUSY; @@ -645,11 +647,13 @@ static ssize_t write_versions(struct file *file, char *buf, size_t size) * Zero-length write. Return a list of NFSD's current listener * transports. */ -static ssize_t __write_ports_names(char *buf) +static ssize_t __write_ports_names(char *buf, struct net *net) { - if (nfsd_serv == NULL) + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + if (nn->nfsd_serv == NULL) return 0; - return svc_xprt_names(nfsd_serv, buf, SIMPLE_TRANSACTION_LIMIT); + return svc_xprt_names(nn->nfsd_serv, buf, SIMPLE_TRANSACTION_LIMIT); } /* @@ -657,28 +661,28 @@ static ssize_t __write_ports_names(char *buf) * a socket of a supported family/protocol, and we use it as an * nfsd listener. */ -static ssize_t __write_ports_addfd(char *buf) +static ssize_t __write_ports_addfd(char *buf, struct net *net) { char *mesg = buf; int fd, err; - struct net *net = &init_net; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); err = get_int(&mesg, &fd); if (err != 0 || fd < 0) return -EINVAL; - err = nfsd_create_serv(); + err = nfsd_create_serv(net); if (err != 0) return err; - err = svc_addsock(nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT); + err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT); if (err < 0) { nfsd_destroy(net); return err; } /* Decrease the count, but don't shut down the service */ - nfsd_serv->sv_nrthreads--; + nn->nfsd_serv->sv_nrthreads--; return err; } @@ -686,12 +690,12 @@ static ssize_t __write_ports_addfd(char *buf) * A transport listener is added by writing it's transport name and * a port number. */ -static ssize_t __write_ports_addxprt(char *buf) +static ssize_t __write_ports_addxprt(char *buf, struct net *net) { char transport[16]; struct svc_xprt *xprt; int port, err; - struct net *net = &init_net; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (sscanf(buf, "%15s %5u", transport, &port) != 2) return -EINVAL; @@ -699,25 +703,25 @@ static ssize_t __write_ports_addxprt(char *buf) if (port < 1 || port > USHRT_MAX) return -EINVAL; - err = nfsd_create_serv(); + err = nfsd_create_serv(net); if (err != 0) return err; - err = svc_create_xprt(nfsd_serv, transport, net, + err = svc_create_xprt(nn->nfsd_serv, transport, net, PF_INET, port, SVC_SOCK_ANONYMOUS); if (err < 0) goto out_err; - err = svc_create_xprt(nfsd_serv, transport, net, + err = svc_create_xprt(nn->nfsd_serv, transport, net, PF_INET6, port, SVC_SOCK_ANONYMOUS); if (err < 0 && err != -EAFNOSUPPORT) goto out_close; /* Decrease the count, but don't shut down the service */ - nfsd_serv->sv_nrthreads--; + nn->nfsd_serv->sv_nrthreads--; return 0; out_close: - xprt = svc_find_xprt(nfsd_serv, transport, net, PF_INET, port); + xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port); if (xprt != NULL) { svc_close_xprt(xprt); svc_xprt_put(xprt); @@ -727,16 +731,17 @@ out_err: return err; } -static ssize_t __write_ports(struct file *file, char *buf, size_t size) +static ssize_t __write_ports(struct file *file, char *buf, size_t size, + struct net *net) { if (size == 0) - return __write_ports_names(buf); + return __write_ports_names(buf, net); if (isdigit(buf[0])) - return __write_ports_addfd(buf); + return __write_ports_addfd(buf, net); if (isalpha(buf[0])) - return __write_ports_addxprt(buf); + return __write_ports_addxprt(buf, net); return -EINVAL; } @@ -787,9 +792,10 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size) static ssize_t write_ports(struct file *file, char *buf, size_t size) { ssize_t rv; + struct net *net = &init_net; mutex_lock(&nfsd_mutex); - rv = __write_ports(file, buf, size); + rv = __write_ports(file, buf, size, net); mutex_unlock(&nfsd_mutex); return rv; } @@ -821,6 +827,9 @@ int nfsd_max_blksize; static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) { char *mesg = buf; + struct net *net = &init_net; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + if (size > 0) { int bsize; int rv = get_int(&mesg, &bsize); @@ -835,7 +844,7 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) bsize = NFSSVC_MAXBLKSIZE; bsize &= ~(1024-1); mutex_lock(&nfsd_mutex); - if (nfsd_serv) { + if (nn->nfsd_serv) { mutex_unlock(&nfsd_mutex); return -EBUSY; } @@ -848,13 +857,14 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) } #ifdef CONFIG_NFSD_V4 -static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, time_t *time) +static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, + time_t *time, struct nfsd_net *nn) { char *mesg = buf; int rv, i; if (size > 0) { - if (nfsd_serv) + if (nn->nfsd_serv) return -EBUSY; rv = get_int(&mesg, &i); if (rv) @@ -879,12 +889,13 @@ static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size, tim return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%ld\n", *time); } -static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size, time_t *time) +static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size, + time_t *time, struct nfsd_net *nn) { ssize_t rv; mutex_lock(&nfsd_mutex); - rv = __nfsd4_write_time(file, buf, size, time); + rv = __nfsd4_write_time(file, buf, size, time, nn); mutex_unlock(&nfsd_mutex); return rv; } @@ -912,7 +923,8 @@ static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size, time_ */ static ssize_t write_leasetime(struct file *file, char *buf, size_t size) { - return nfsd4_write_time(file, buf, size, &nfsd4_lease); + struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); + return nfsd4_write_time(file, buf, size, &nn->nfsd4_lease, nn); } /** @@ -927,17 +939,19 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size) */ static ssize_t write_gracetime(struct file *file, char *buf, size_t size) { - return nfsd4_write_time(file, buf, size, &nfsd4_grace); + struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); + return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn); } -static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size) +static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size, + struct nfsd_net *nn) { char *mesg = buf; char *recdir; int len, status; if (size > 0) { - if (nfsd_serv) + if (nn->nfsd_serv) return -EBUSY; if (size > PATH_MAX || buf[size-1] != '\n') return -EINVAL; @@ -981,9 +995,10 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size) static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) { ssize_t rv; + struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); mutex_lock(&nfsd_mutex); - rv = __write_recoverydir(file, buf, size); + rv = __write_recoverydir(file, buf, size, nn); mutex_unlock(&nfsd_mutex); return rv; } @@ -1063,6 +1078,7 @@ int nfsd_net_id; static __net_init int nfsd_init_net(struct net *net) { int retval; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); retval = nfsd_export_init(net); if (retval) @@ -1070,6 +1086,8 @@ static __net_init int nfsd_init_net(struct net *net) retval = nfsd_idmap_init(net); if (retval) goto out_idmap_error; + nn->nfsd4_lease = 90; /* default lease time */ + nn->nfsd4_grace = 90; return 0; out_idmap_error: diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 80d5ce40aadb..de23db255c69 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -55,7 +55,6 @@ extern struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; extern u32 nfsd_supported_minorversion; extern struct mutex nfsd_mutex; -extern struct svc_serv *nfsd_serv; extern spinlock_t nfsd_drc_lock; extern unsigned int nfsd_drc_max_mem; extern unsigned int nfsd_drc_mem_used; @@ -65,26 +64,17 @@ extern const struct seq_operations nfs_exports_op; /* * Function prototypes. */ -int nfsd_svc(int nrservs); +int nfsd_svc(int nrservs, struct net *net); int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp); -int nfsd_nrthreads(void); -int nfsd_nrpools(void); -int nfsd_get_nrthreads(int n, int *); -int nfsd_set_nrthreads(int n, int *); +int nfsd_nrthreads(struct net *); +int nfsd_nrpools(struct net *); +int nfsd_get_nrthreads(int n, int *, struct net *); +int nfsd_set_nrthreads(int n, int *, struct net *); int nfsd_pool_stats_open(struct inode *, struct file *); int nfsd_pool_stats_release(struct inode *, struct file *); -static inline void nfsd_destroy(struct net *net) -{ - int destroy = (nfsd_serv->sv_nrthreads == 1); - - if (destroy) - svc_shutdown_net(nfsd_serv, net); - svc_destroy(nfsd_serv); - if (destroy) - nfsd_serv = NULL; -} +void nfsd_destroy(struct net *net); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) #ifdef CONFIG_NFSD_V2_ACL @@ -103,7 +93,7 @@ enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; int nfsd_vers(int vers, enum vers_op change); int nfsd_minorversion(u32 minorversion, enum vers_op change); void nfsd_reset_versions(void); -int nfsd_create_serv(void); +int nfsd_create_serv(struct net *net); extern int nfsd_max_blksize; @@ -121,7 +111,9 @@ void nfs4_state_init(void); int nfsd4_init_slabs(void); void nfsd4_free_slabs(void); int nfs4_state_start(void); +int nfs4_state_start_net(struct net *net); void nfs4_state_shutdown(void); +void nfs4_state_shutdown_net(struct net *net); void nfs4_reset_lease(time_t leasetime); int nfs4_reset_recoverydir(char *recdir); char * nfs4_recoverydir(void); @@ -130,7 +122,9 @@ static inline void nfs4_state_init(void) { } static inline int nfsd4_init_slabs(void) { return 0; } static inline void nfsd4_free_slabs(void) { } static inline int nfs4_state_start(void) { return 0; } +static inline int nfs4_state_start_net(struct net *net) { return 0; } static inline void nfs4_state_shutdown(void) { } +static inline void nfs4_state_shutdown_net(struct net *net) { } static inline void nfs4_reset_lease(time_t leasetime) { } static inline int nfs4_reset_recoverydir(char *recdir) { return 0; } static inline char * nfs4_recoverydir(void) {return NULL; } @@ -265,16 +259,8 @@ void nfsd_lockd_shutdown(void); /* Check for dir entries '.' and '..' */ #define isdotent(n, l) (l < 3 && n[0] == '.' && (l == 1 || n[1] == '.')) -/* - * Time of server startup - */ -extern struct timeval nfssvc_boot; - #ifdef CONFIG_NFSD_V4 -extern time_t nfsd4_lease; -extern time_t nfsd4_grace; - /* before processing a COMPOUND operation, we have to check that there * is enough space in the buffer for XDR encode to succeed. otherwise, * we might process an operation with side effects, and be unable to diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 032af381b3aa..814afaa4458a 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -572,7 +572,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry, if (inode) _fh_update(fhp, exp, dentry); - if (fhp->fh_handle.fh_fileid_type == 255) { + if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) { fh_put(fhp); return nfserr_opnotsupp; } @@ -603,7 +603,7 @@ fh_update(struct svc_fh *fhp) goto out; _fh_update(fhp, fhp->fh_export, dentry); - if (fhp->fh_handle.fh_fileid_type == 255) + if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) return nfserr_opnotsupp; } out: diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 2013aa001dab..cee62ab9d4a3 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -11,7 +11,6 @@ #include <linux/module.h> #include <linux/fs_struct.h> #include <linux/swap.h> -#include <linux/nsproxy.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svcsock.h> @@ -22,19 +21,19 @@ #include "nfsd.h" #include "cache.h" #include "vfs.h" +#include "netns.h" #define NFSDDBG_FACILITY NFSDDBG_SVC extern struct svc_program nfsd_program; static int nfsd(void *vrqstp); -struct timeval nfssvc_boot; /* - * nfsd_mutex protects nfsd_serv -- both the pointer itself and the members + * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and the members * of the svc_serv struct. In particular, ->sv_nrthreads but also to some * extent ->sv_temp_socks and ->sv_permsocks. It also protects nfsdstats.th_cnt * - * If (out side the lock) nfsd_serv is non-NULL, then it must point to a + * If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0. That number * of nfsd threads must exist and each must listed in ->sp_all_threads in each * entry of ->sv_pools[]. @@ -52,7 +51,6 @@ struct timeval nfssvc_boot; * nfsd_versions */ DEFINE_MUTEX(nfsd_mutex); -struct svc_serv *nfsd_serv; /* * nfsd_drc_lock protects nfsd_drc_max_pages and nfsd_drc_pages_used. @@ -173,28 +171,32 @@ int nfsd_minorversion(u32 minorversion, enum vers_op change) */ #define NFSD_MAXSERVS 8192 -int nfsd_nrthreads(void) +int nfsd_nrthreads(struct net *net) { int rv = 0; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + mutex_lock(&nfsd_mutex); - if (nfsd_serv) - rv = nfsd_serv->sv_nrthreads; + if (nn->nfsd_serv) + rv = nn->nfsd_serv->sv_nrthreads; mutex_unlock(&nfsd_mutex); return rv; } -static int nfsd_init_socks(void) +static int nfsd_init_socks(struct net *net) { int error; - if (!list_empty(&nfsd_serv->sv_permsocks)) + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + if (!list_empty(&nn->nfsd_serv->sv_permsocks)) return 0; - error = svc_create_xprt(nfsd_serv, "udp", &init_net, PF_INET, NFS_PORT, + error = svc_create_xprt(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT, SVC_SOCK_DEFAULTS); if (error < 0) return error; - error = svc_create_xprt(nfsd_serv, "tcp", &init_net, PF_INET, NFS_PORT, + error = svc_create_xprt(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT, SVC_SOCK_DEFAULTS); if (error < 0) return error; @@ -202,14 +204,15 @@ static int nfsd_init_socks(void) return 0; } -static bool nfsd_up = false; +static int nfsd_users = 0; -static int nfsd_startup(int nrservs) +static int nfsd_startup_generic(int nrservs) { int ret; - if (nfsd_up) + if (nfsd_users++) return 0; + /* * Readahead param cache - will no-op if it already exists. * (Note therefore results will be suboptimal if number of @@ -218,43 +221,79 @@ static int nfsd_startup(int nrservs) ret = nfsd_racache_init(2*nrservs); if (ret) return ret; - ret = nfsd_init_socks(); + ret = nfs4_state_start(); if (ret) goto out_racache; - ret = lockd_up(&init_net); + return 0; + +out_racache: + nfsd_racache_shutdown(); + return ret; +} + +static void nfsd_shutdown_generic(void) +{ + if (--nfsd_users) + return; + + nfs4_state_shutdown(); + nfsd_racache_shutdown(); +} + +static int nfsd_startup_net(int nrservs, struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + int ret; + + if (nn->nfsd_net_up) + return 0; + + ret = nfsd_startup_generic(nrservs); if (ret) - goto out_racache; - ret = nfs4_state_start(); + return ret; + ret = nfsd_init_socks(net); + if (ret) + goto out_socks; + ret = lockd_up(net); + if (ret) + goto out_socks; + ret = nfs4_state_start_net(net); if (ret) goto out_lockd; - nfsd_up = true; + + nn->nfsd_net_up = true; return 0; + out_lockd: - lockd_down(&init_net); -out_racache: - nfsd_racache_shutdown(); + lockd_down(net); +out_socks: + nfsd_shutdown_generic(); return ret; } -static void nfsd_shutdown(void) +static void nfsd_shutdown_net(struct net *net) { + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nfs4_state_shutdown_net(net); + lockd_down(net); + nn->nfsd_net_up = false; + nfsd_shutdown_generic(); +} + +static void nfsd_last_thread(struct svc_serv *serv, struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + /* * write_ports can create the server without actually starting * any threads--if we get shut down before any threads are * started, then nfsd_last_thread will be run before any of this * other initialization has been done. */ - if (!nfsd_up) + if (!nn->nfsd_net_up) return; - nfs4_state_shutdown(); - lockd_down(&init_net); - nfsd_racache_shutdown(); - nfsd_up = false; -} - -static void nfsd_last_thread(struct svc_serv *serv, struct net *net) -{ - nfsd_shutdown(); + nfsd_shutdown_net(net); svc_rpcb_cleanup(serv, net); @@ -327,69 +366,84 @@ static int nfsd_get_default_max_blksize(void) return ret; } -int nfsd_create_serv(void) +int nfsd_create_serv(struct net *net) { int error; - struct net *net = current->nsproxy->net_ns; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); WARN_ON(!mutex_is_locked(&nfsd_mutex)); - if (nfsd_serv) { - svc_get(nfsd_serv); + if (nn->nfsd_serv) { + svc_get(nn->nfsd_serv); return 0; } if (nfsd_max_blksize == 0) nfsd_max_blksize = nfsd_get_default_max_blksize(); nfsd_reset_versions(); - nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, + nn->nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, nfsd_last_thread, nfsd, THIS_MODULE); - if (nfsd_serv == NULL) + if (nn->nfsd_serv == NULL) return -ENOMEM; - error = svc_bind(nfsd_serv, net); + error = svc_bind(nn->nfsd_serv, net); if (error < 0) { - svc_destroy(nfsd_serv); + svc_destroy(nn->nfsd_serv); return error; } set_max_drc(); - do_gettimeofday(&nfssvc_boot); /* record boot time */ + do_gettimeofday(&nn->nfssvc_boot); /* record boot time */ return 0; } -int nfsd_nrpools(void) +int nfsd_nrpools(struct net *net) { - if (nfsd_serv == NULL) + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + if (nn->nfsd_serv == NULL) return 0; else - return nfsd_serv->sv_nrpools; + return nn->nfsd_serv->sv_nrpools; } -int nfsd_get_nrthreads(int n, int *nthreads) +int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) { int i = 0; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); - if (nfsd_serv != NULL) { - for (i = 0; i < nfsd_serv->sv_nrpools && i < n; i++) - nthreads[i] = nfsd_serv->sv_pools[i].sp_nrthreads; + if (nn->nfsd_serv != NULL) { + for (i = 0; i < nn->nfsd_serv->sv_nrpools && i < n; i++) + nthreads[i] = nn->nfsd_serv->sv_pools[i].sp_nrthreads; } return 0; } -int nfsd_set_nrthreads(int n, int *nthreads) +void nfsd_destroy(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + int destroy = (nn->nfsd_serv->sv_nrthreads == 1); + + if (destroy) + svc_shutdown_net(nn->nfsd_serv, net); + svc_destroy(nn->nfsd_serv); + if (destroy) + nn->nfsd_serv = NULL; +} + +int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) { int i = 0; int tot = 0; int err = 0; - struct net *net = &init_net; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); WARN_ON(!mutex_is_locked(&nfsd_mutex)); - if (nfsd_serv == NULL || n <= 0) + if (nn->nfsd_serv == NULL || n <= 0) return 0; - if (n > nfsd_serv->sv_nrpools) - n = nfsd_serv->sv_nrpools; + if (n > nn->nfsd_serv->sv_nrpools) + n = nn->nfsd_serv->sv_nrpools; /* enforce a global maximum number of threads */ tot = 0; @@ -419,9 +473,9 @@ int nfsd_set_nrthreads(int n, int *nthreads) nthreads[0] = 1; /* apply the new numbers */ - svc_get(nfsd_serv); + svc_get(nn->nfsd_serv); for (i = 0; i < n; i++) { - err = svc_set_num_threads(nfsd_serv, &nfsd_serv->sv_pools[i], + err = svc_set_num_threads(nn->nfsd_serv, &nn->nfsd_serv->sv_pools[i], nthreads[i]); if (err) break; @@ -436,11 +490,11 @@ int nfsd_set_nrthreads(int n, int *nthreads) * this is the first time nrservs is nonzero. */ int -nfsd_svc(int nrservs) +nfsd_svc(int nrservs, struct net *net) { int error; bool nfsd_up_before; - struct net *net = &init_net; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); mutex_lock(&nfsd_mutex); dprintk("nfsd: creating service\n"); @@ -449,29 +503,29 @@ nfsd_svc(int nrservs) if (nrservs > NFSD_MAXSERVS) nrservs = NFSD_MAXSERVS; error = 0; - if (nrservs == 0 && nfsd_serv == NULL) + if (nrservs == 0 && nn->nfsd_serv == NULL) goto out; - error = nfsd_create_serv(); + error = nfsd_create_serv(net); if (error) goto out; - nfsd_up_before = nfsd_up; + nfsd_up_before = nn->nfsd_net_up; - error = nfsd_startup(nrservs); + error = nfsd_startup_net(nrservs, net); if (error) goto out_destroy; - error = svc_set_num_threads(nfsd_serv, NULL, nrservs); + error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs); if (error) goto out_shutdown; - /* We are holding a reference to nfsd_serv which + /* We are holding a reference to nn->nfsd_serv which * we don't want to count in the return value, * so subtract 1 */ - error = nfsd_serv->sv_nrthreads - 1; + error = nn->nfsd_serv->sv_nrthreads - 1; out_shutdown: if (error < 0 && !nfsd_up_before) - nfsd_shutdown(); + nfsd_shutdown_net(net); out_destroy: nfsd_destroy(net); /* Release server */ out: @@ -487,6 +541,8 @@ static int nfsd(void *vrqstp) { struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp; + struct svc_xprt *perm_sock = list_entry(rqstp->rq_server->sv_permsocks.next, typeof(struct svc_xprt), xpt_list); + struct net *net = perm_sock->xpt_net; int err; /* Lock module and set up kernel thread */ @@ -551,7 +607,7 @@ out: /* Release the thread */ svc_exit_thread(rqstp); - nfsd_destroy(&init_net); + nfsd_destroy(net); /* Release module */ mutex_unlock(&nfsd_mutex); @@ -640,21 +696,24 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) } /* Store reply in cache. */ - nfsd_cache_update(rqstp, proc->pc_cachetype, statp + 1); + nfsd_cache_update(rqstp, rqstp->rq_cachetype, statp + 1); return 1; } int nfsd_pool_stats_open(struct inode *inode, struct file *file) { int ret; + struct net *net = &init_net; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + mutex_lock(&nfsd_mutex); - if (nfsd_serv == NULL) { + if (nn->nfsd_serv == NULL) { mutex_unlock(&nfsd_mutex); return -ENODEV; } /* bump up the psudo refcount while traversing */ - svc_get(nfsd_serv); - ret = svc_pool_stats_open(nfsd_serv, file); + svc_get(nn->nfsd_serv); + ret = svc_pool_stats_open(nn->nfsd_serv, file); mutex_unlock(&nfsd_mutex); return ret; } diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 65ec595e2226..979b42106979 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -246,7 +246,7 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readargs *args) { unsigned int len; - int v,pn; + int v; if (!(p = decode_fh(p, &args->fh))) return 0; @@ -262,8 +262,9 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, */ v=0; while (len > 0) { - pn = rqstp->rq_resused++; - rqstp->rq_vec[v].iov_base = page_address(rqstp->rq_respages[pn]); + struct page *p = *(rqstp->rq_next_page++); + + rqstp->rq_vec[v].iov_base = page_address(p); rqstp->rq_vec[v].iov_len = len < PAGE_SIZE?len:PAGE_SIZE; len -= rqstp->rq_vec[v].iov_len; v++; @@ -355,7 +356,7 @@ nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readli { if (!(p = decode_fh(p, &args->fh))) return 0; - args->buffer = page_address(rqstp->rq_respages[rqstp->rq_resused++]); + args->buffer = page_address(*(rqstp->rq_next_page++)); return xdr_argsize_check(rqstp, p); } @@ -396,7 +397,7 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, if (args->count > PAGE_SIZE) args->count = PAGE_SIZE; - args->buffer = page_address(rqstp->rq_respages[rqstp->rq_resused++]); + args->buffer = page_address(*(rqstp->rq_next_page++)); return xdr_argsize_check(rqstp, p); } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index e036894bce57..d1c229feed52 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -150,6 +150,12 @@ struct nfsd4_channel_attrs { u32 rdma_attrs; }; +struct nfsd4_cb_sec { + u32 flavor; /* (u32)(-1) used to mean "no valid flavor" */ + u32 uid; + u32 gid; +}; + struct nfsd4_create_session { clientid_t clientid; struct nfs4_sessionid sessionid; @@ -158,8 +164,12 @@ struct nfsd4_create_session { struct nfsd4_channel_attrs fore_channel; struct nfsd4_channel_attrs back_channel; u32 callback_prog; - u32 uid; - u32 gid; + struct nfsd4_cb_sec cb_sec; +}; + +struct nfsd4_backchannel_ctl { + u32 bc_cb_program; + struct nfsd4_cb_sec bc_cb_sec; }; struct nfsd4_bind_conn_to_session { @@ -192,6 +202,7 @@ struct nfsd4_session { struct nfs4_sessionid se_sessionid; struct nfsd4_channel_attrs se_fchannel; struct nfsd4_channel_attrs se_bchannel; + struct nfsd4_cb_sec se_cb_sec; struct list_head se_conns; u32 se_cb_prog; u32 se_cb_seq_nr; @@ -221,13 +232,12 @@ struct nfsd4_sessionid { */ struct nfs4_client { struct list_head cl_idhash; /* hash by cl_clientid.id */ - struct list_head cl_strhash; /* hash by cl_name */ + struct rb_node cl_namenode; /* link into by-name trees */ struct list_head cl_openowners; struct idr cl_stateids; /* stateid lookup */ struct list_head cl_delegations; struct list_head cl_lru; /* tail queue */ struct xdr_netobj cl_name; /* id generated by client */ - char cl_recdir[HEXDIR_LEN]; /* recovery dir */ nfs4_verifier cl_verifier; /* generated by client */ time_t cl_time; /* time of last lease renewal */ struct sockaddr_storage cl_addr; /* client ipaddress */ @@ -242,9 +252,11 @@ struct nfs4_client { #define NFSD4_CLIENT_CB_KILL (1) #define NFSD4_CLIENT_STABLE (2) /* client on stable storage */ #define NFSD4_CLIENT_RECLAIM_COMPLETE (3) /* reclaim_complete done */ +#define NFSD4_CLIENT_CONFIRMED (4) /* client is confirmed */ #define NFSD4_CLIENT_CB_FLAG_MASK (1 << NFSD4_CLIENT_CB_UPDATE | \ 1 << NFSD4_CLIENT_CB_KILL) unsigned long cl_flags; + struct rpc_cred *cl_cb_cred; struct rpc_clnt *cl_cb_client; u32 cl_cb_ident; #define NFSD4_CB_UP 0 @@ -271,6 +283,7 @@ struct nfs4_client { unsigned long cl_cb_slot_busy; struct rpc_wait_queue cl_cb_waitq; /* backchannel callers may */ /* wait here for slots */ + struct net *net; }; static inline void @@ -292,6 +305,7 @@ is_client_expired(struct nfs4_client *clp) */ struct nfs4_client_reclaim { struct list_head cr_strhash; /* hash by cr_name */ + struct nfs4_client *cr_clp; /* pointer to associated clp */ char cr_recdir[HEXDIR_LEN]; /* recover dir */ }; @@ -452,25 +466,26 @@ extern __be32 nfs4_preprocess_stateid_op(struct net *net, stateid_t *stateid, int flags, struct file **filp); extern void nfs4_lock_state(void); extern void nfs4_unlock_state(void); -extern int nfs4_in_grace(void); -extern void nfs4_release_reclaim(void); -extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(struct nfs4_client *crp); -extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions); +void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *); +extern void nfs4_release_reclaim(struct nfsd_net *); +extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir, + struct nfsd_net *nn); +extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions, struct nfsd_net *nn); extern void nfs4_free_openowner(struct nfs4_openowner *); extern void nfs4_free_lockowner(struct nfs4_lockowner *); extern int set_callback_cred(void); +extern void nfsd4_init_callback(struct nfsd4_callback *); extern void nfsd4_probe_callback(struct nfs4_client *clp); extern void nfsd4_probe_callback_sync(struct nfs4_client *clp); extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *); -extern void nfsd4_do_callback_rpc(struct work_struct *); extern void nfsd4_cb_recall(struct nfs4_delegation *dp); extern int nfsd4_create_callback_queue(void); extern void nfsd4_destroy_callback_queue(void); extern void nfsd4_shutdown_callback(struct nfs4_client *); extern void nfs4_put_delegation(struct nfs4_delegation *dp); -extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname); -extern int nfs4_client_to_reclaim(const char *name); -extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id); +extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name, + struct nfsd_net *nn); +extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn); extern void release_session_client(struct nfsd4_session *); extern void nfsd4_purge_closed_stateid(struct nfs4_stateowner *); @@ -480,5 +495,28 @@ extern void nfsd4_client_tracking_exit(struct net *net); extern void nfsd4_client_record_create(struct nfs4_client *clp); extern void nfsd4_client_record_remove(struct nfs4_client *clp); extern int nfsd4_client_record_check(struct nfs4_client *clp); -extern void nfsd4_record_grace_done(struct net *net, time_t boot_time); +extern void nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time); + +/* nfs fault injection functions */ +#ifdef CONFIG_NFSD_FAULT_INJECTION +int nfsd_fault_inject_init(void); +void nfsd_fault_inject_cleanup(void); +u64 nfsd_for_n_state(u64, u64 (*)(struct nfs4_client *, u64)); +struct nfs4_client *nfsd_find_client(struct sockaddr_storage *, size_t); + +u64 nfsd_forget_client(struct nfs4_client *, u64); +u64 nfsd_forget_client_locks(struct nfs4_client*, u64); +u64 nfsd_forget_client_openowners(struct nfs4_client *, u64); +u64 nfsd_forget_client_delegations(struct nfs4_client *, u64); +u64 nfsd_recall_client_delegations(struct nfs4_client *, u64); + +u64 nfsd_print_client(struct nfs4_client *, u64); +u64 nfsd_print_client_locks(struct nfs4_client *, u64); +u64 nfsd_print_client_openowners(struct nfs4_client *, u64); +u64 nfsd_print_client_delegations(struct nfs4_client *, u64); +#else /* CONFIG_NFSD_FAULT_INJECTION */ +static inline int nfsd_fault_inject_init(void) { return 0; } +static inline void nfsd_fault_inject_cleanup(void) {} +#endif /* CONFIG_NFSD_FAULT_INJECTION */ + #endif /* NFSD4_STATE_H */ diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index c120b48ec305..f0a6d88d7fff 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -886,7 +886,7 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { struct svc_rqst *rqstp = sd->u.data; - struct page **pp = rqstp->rq_respages + rqstp->rq_resused; + struct page **pp = rqstp->rq_next_page; struct page *page = buf->page; size_t size; @@ -894,17 +894,15 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, if (rqstp->rq_res.page_len == 0) { get_page(page); - put_page(*pp); - *pp = page; - rqstp->rq_resused++; + put_page(*rqstp->rq_next_page); + *(rqstp->rq_next_page++) = page; rqstp->rq_res.page_base = buf->offset; rqstp->rq_res.page_len = size; } else if (page != pp[-1]) { get_page(page); - if (*pp) - put_page(*pp); - *pp = page; - rqstp->rq_resused++; + if (*rqstp->rq_next_page) + put_page(*rqstp->rq_next_page); + *(rqstp->rq_next_page++) = page; rqstp->rq_res.page_len += size; } else rqstp->rq_res.page_len += size; @@ -936,7 +934,8 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, .u.data = rqstp, }; - rqstp->rq_resused = 1; + WARN_ON_ONCE(rqstp->rq_next_page != rqstp->rq_respages + 1); + rqstp->rq_next_page = rqstp->rq_respages + 1; host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor); } else { oldfs = get_fs(); @@ -1020,28 +1019,10 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, inode = dentry->d_inode; exp = fhp->fh_export; - /* - * Request sync writes if - * - the sync export option has been set, or - * - the client requested O_SYNC behavior (NFSv3 feature). - * - The file system doesn't support fsync(). - * When NFSv2 gathered writes have been configured for this volume, - * flushing the data to disk is handled separately below. - */ use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp); - if (!file->f_op->fsync) {/* COMMIT3 cannot work */ - stable = 2; - *stablep = 2; /* FILE_SYNC */ - } - if (!EX_ISSYNC(exp)) stable = 0; - if (stable && !use_wgather) { - spin_lock(&file->f_lock); - file->f_flags |= O_SYNC; - spin_unlock(&file->f_lock); - } /* Write the data. */ oldfs = get_fs(); set_fs(KERNEL_DS); @@ -1057,8 +1038,12 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (inode->i_mode & (S_ISUID | S_ISGID)) kill_suid(dentry); - if (stable && use_wgather) - host_err = wait_for_concurrent_writes(file); + if (stable) { + if (use_wgather) + host_err = wait_for_concurrent_writes(file); + else + host_err = vfs_fsync_range(file, offset, offset+*cnt, 0); + } out_nfserr: dprintk("nfsd: write complete host_err=%d\n", host_err); @@ -1485,13 +1470,19 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, case NFS3_CREATE_EXCLUSIVE: if ( dchild->d_inode->i_mtime.tv_sec == v_mtime && dchild->d_inode->i_atime.tv_sec == v_atime - && dchild->d_inode->i_size == 0 ) + && dchild->d_inode->i_size == 0 ) { + if (created) + *created = 1; break; + } case NFS4_CREATE_EXCLUSIVE4_1: if ( dchild->d_inode->i_mtime.tv_sec == v_mtime && dchild->d_inode->i_atime.tv_sec == v_atime - && dchild->d_inode->i_size == 0 ) + && dchild->d_inode->i_size == 0 ) { + if (created) + *created = 1; goto set_attr; + } /* fallthru */ case NFS3_CREATE_GUARDED: err = nfserr_exist; diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index acd127d4ee82..0889bfb43dc9 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -385,7 +385,8 @@ struct nfsd4_write { u64 wr_offset; /* request */ u32 wr_stable_how; /* request */ u32 wr_buflen; /* request */ - int wr_vlen; + struct kvec wr_head; + struct page ** wr_pagelist; /* request */ u32 wr_bytes_written; /* response */ u32 wr_how_written; /* response */ @@ -462,6 +463,7 @@ struct nfsd4_op { /* NFSv4.1 */ struct nfsd4_exchange_id exchange_id; + struct nfsd4_backchannel_ctl backchannel_ctl; struct nfsd4_bind_conn_to_session bind_conn_to_session; struct nfsd4_create_session create_session; struct nfsd4_destroy_session destroy_session; @@ -526,6 +528,14 @@ static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp) || nfsd4_is_solo_sequence(resp); } +static inline bool nfsd4_last_compound_op(struct svc_rqst *rqstp) +{ + struct nfsd4_compoundres *resp = rqstp->rq_resp; + struct nfsd4_compoundargs *argp = rqstp->rq_argp; + + return argp->opcnt == resp->opcnt; +} + #define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs) static inline void @@ -566,6 +576,7 @@ extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, struct nfsd4_sequence *seq); extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *, struct nfsd4_exchange_id *); +extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_backchannel_ctl *); extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_bind_conn_to_session *); extern __be32 nfsd4_create_session(struct svc_rqst *, struct nfsd4_compound_state *, @@ -579,7 +590,7 @@ extern __be32 nfsd4_destroy_session(struct svc_rqst *, extern __be32 nfsd4_destroy_clientid(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_destroy_clientid *); __be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_reclaim_complete *); extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *, - struct nfsd4_open *open); + struct nfsd4_open *open, struct nfsd_net *nn); extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open); extern void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 2a9a9abc9126..12731a19ef06 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -114,6 +114,7 @@ struct backing_dev_info { int bdi_init(struct backing_dev_info *bdi); void bdi_destroy(struct backing_dev_info *bdi); +__printf(3, 4) int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 6470792b13d3..084d3c622b12 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -43,7 +43,6 @@ struct ceph_options { struct ceph_entity_addr my_addr; int mount_timeout; int osd_idle_ttl; - int osd_timeout; int osd_keepalive_timeout; /* @@ -63,7 +62,6 @@ struct ceph_options { * defaults */ #define CEPH_MOUNT_TIMEOUT_DEFAULT 60 -#define CEPH_OSD_TIMEOUT_DEFAULT 60 /* seconds */ #define CEPH_OSD_KEEPALIVE_DEFAULT 5 #define CEPH_OSD_IDLE_TTL_DEFAULT 60 diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index e37acbe989a9..10a417f9f76f 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -123,6 +123,7 @@ extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid); +extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id); extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name); #endif diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index de91fbdf127e..2c04afeead1c 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -87,6 +87,8 @@ struct ceph_pg { * * lpgp_num -- as above. */ +#define CEPH_NOPOOL ((__u64) (-1)) /* pool id not defined */ + #define CEPH_PG_TYPE_REP 1 #define CEPH_PG_TYPE_RAID4 2 #define CEPH_PG_POOL_VERSION 2 diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index 171ad8aedc83..fc0e34ce038f 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -39,6 +39,8 @@ extern void debug_dma_map_page(struct device *dev, struct page *page, int direction, dma_addr_t dma_addr, bool map_single); +extern void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); + extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, size_t size, int direction, bool map_single); @@ -105,6 +107,11 @@ static inline void debug_dma_map_page(struct device *dev, struct page *page, { } +static inline void debug_dma_mapping_error(struct device *dev, + dma_addr_t dma_addr) +{ +} + static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, size_t size, int direction, bool map_single) diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index c7e6b6392ab8..5b9b5b317180 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -83,6 +83,11 @@ enum fid_type { * 64 bit parent inode number. */ FILEID_NILFS_WITH_PARENT = 0x62, + + /* + * Filesystems must not use 0xff file ID. + */ + FILEID_INVALID = 0xff, }; struct fid { diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h new file mode 100644 index 000000000000..f9a12f6243a5 --- /dev/null +++ b/include/linux/f2fs_fs.h @@ -0,0 +1,413 @@ +/** + * include/linux/f2fs_fs.h + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef _LINUX_F2FS_FS_H +#define _LINUX_F2FS_FS_H + +#include <linux/pagemap.h> +#include <linux/types.h> + +#define F2FS_SUPER_OFFSET 1024 /* byte-size offset */ +#define F2FS_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 0x0U +#define NEW_ADDR -1U + +#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_MAX_NAME_LEN 256 +#define ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ +#define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ +#define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */ + +struct f2fs_inode { + __le16 i_mode; /* file mode */ + __u8 i_advise; /* file hints */ + __u8 i_reserved; /* reserved */ + __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_MAX_NAME_LEN]; /* file name for SPOR */ + + struct f2fs_extent i_ext; /* caching a largest extent */ + + __le32 i_addr[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_NAME_LEN 8 +#define F2FS_NAME_LEN_BITS 3 + +#define GET_DENTRY_SLOTS(x) ((x + F2FS_NAME_LEN - 1) >> F2FS_NAME_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_NAME_LEN) * \ + NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP)) + +/* One directory entry slot representing F2FS_NAME_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_NAME_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/platform_data/iommu-omap.h b/include/linux/platform_data/iommu-omap.h index c677b9f2fefa..5b429c43a297 100644 --- a/include/linux/platform_data/iommu-omap.h +++ b/include/linux/platform_data/iommu-omap.h @@ -10,6 +10,8 @@ * published by the Free Software Foundation. */ +#include <linux/platform_device.h> + #define MMU_REG_SIZE 256 /** @@ -42,8 +44,11 @@ struct omap_mmu_dev_attr { struct iommu_platform_data { const char *name; - const char *clk_name; - const int nr_tlb_entries; + const char *reset_name; + int nr_tlb_entries; u32 da_start; u32 da_end; + + int (*assert_reset)(struct platform_device *pdev, const char *name); + int (*deassert_reset)(struct platform_device *pdev, const char *name); }; diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index f792794f6634..5dc9ee4d616e 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -217,6 +217,8 @@ extern int qword_get(char **bpp, char *dest, int bufsize); static inline int get_int(char **bpp, int *anint) { char buf[50]; + char *ep; + int rv; int len = qword_get(bpp, buf, sizeof(buf)); if (len < 0) @@ -224,9 +226,11 @@ static inline int get_int(char **bpp, int *anint) if (len == 0) return -ENOENT; - if (kstrtoint(buf, 0, anint)) + rv = simple_strtol(buf, &ep, 0); + if (*ep) return -EINVAL; + *anint = rv; return 0; } diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index d83db800fe02..676ddf53b3ee 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -243,6 +243,7 @@ struct svc_rqst { struct page * rq_pages[RPCSVC_MAXPAGES]; struct page * *rq_respages; /* points into rq_pages */ int rq_resused; /* number of pages used for result */ + struct page * *rq_next_page; /* next reply page to use */ struct kvec rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */ @@ -338,9 +339,8 @@ xdr_ressize_check(struct svc_rqst *rqstp, __be32 *p) static inline void svc_free_res_pages(struct svc_rqst *rqstp) { - while (rqstp->rq_resused) { - struct page **pp = (rqstp->rq_respages + - --rqstp->rq_resused); + while (rqstp->rq_next_page != rqstp->rq_respages) { + struct page **pp = --rqstp->rq_next_page; if (*pp) { put_page(*pp); *pp = NULL; diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 92ad02f0dcc0..62fd1b756e99 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -26,11 +26,28 @@ struct svc_sock { void (*sk_owspace)(struct sock *); /* private TCP part */ - u32 sk_reclen; /* length of record */ - u32 sk_tcplen; /* current read length */ + /* On-the-wire fragment header: */ + __be32 sk_reclen; + /* As we receive a record, this includes the length received so + * far (including the fragment header): */ + u32 sk_tcplen; + /* Total length of the data (not including fragment headers) + * received so far in the fragments making up this rpc: */ + u32 sk_datalen; + struct page * sk_pages[RPCSVC_MAXPAGES]; /* received data */ }; +static inline u32 svc_sock_reclen(struct svc_sock *svsk) +{ + return ntohl(svsk->sk_reclen) & RPC_FRAGMENT_SIZE_MASK; +} + +static inline u32 svc_sock_final_rec(struct svc_sock *svsk) +{ + return ntohl(svsk->sk_reclen) & RPC_LAST_STREAM_FRAGMENT; +} + /* * Function prototypes. */ diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 12f68c7ceba6..873e086ce3a1 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -23,6 +23,7 @@ #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/lib/atomic64.c b/lib/atomic64.c index 978537809d84..08a4f068e61e 100644 --- a/lib/atomic64.c +++ b/lib/atomic64.c @@ -31,7 +31,11 @@ static union { raw_spinlock_t lock; char pad[L1_CACHE_BYTES]; -} atomic64_lock[NR_LOCKS] __cacheline_aligned_in_smp; +} atomic64_lock[NR_LOCKS] __cacheline_aligned_in_smp = { + [0 ... (NR_LOCKS - 1)] = { + .lock = __RAW_SPIN_LOCK_UNLOCKED(atomic64_lock.lock), + }, +}; static inline raw_spinlock_t *lock_addr(const atomic64_t *v) { @@ -173,14 +177,3 @@ int atomic64_add_unless(atomic64_t *v, long long a, long long u) return ret; } EXPORT_SYMBOL(atomic64_add_unless); - -static int init_atomic64_lock(void) -{ - int i; - - for (i = 0; i < NR_LOCKS; ++i) - raw_spin_lock_init(&atomic64_lock[i].lock); - return 0; -} - -pure_initcall(init_atomic64_lock); diff --git a/lib/dma-debug.c b/lib/dma-debug.c index d84beb994f36..5e396accd3d0 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -45,6 +45,12 @@ enum { dma_debug_coherent, }; +enum map_err_types { + MAP_ERR_CHECK_NOT_APPLICABLE, + MAP_ERR_NOT_CHECKED, + MAP_ERR_CHECKED, +}; + #define DMA_DEBUG_STACKTRACE_ENTRIES 5 struct dma_debug_entry { @@ -57,6 +63,7 @@ struct dma_debug_entry { int direction; int sg_call_ents; int sg_mapped_ents; + enum map_err_types map_err_type; #ifdef CONFIG_STACKTRACE struct stack_trace stacktrace; unsigned long st_entries[DMA_DEBUG_STACKTRACE_ENTRIES]; @@ -114,6 +121,12 @@ static struct device_driver *current_driver __read_mostly; static DEFINE_RWLOCK(driver_name_lock); +static const char *const maperr2str[] = { + [MAP_ERR_CHECK_NOT_APPLICABLE] = "dma map error check not applicable", + [MAP_ERR_NOT_CHECKED] = "dma map error not checked", + [MAP_ERR_CHECKED] = "dma map error checked", +}; + static const char *type2name[4] = { "single", "page", "scather-gather", "coherent" }; @@ -376,11 +389,12 @@ void debug_dma_dump_mappings(struct device *dev) list_for_each_entry(entry, &bucket->list, list) { if (!dev || dev == entry->dev) { dev_info(entry->dev, - "%s idx %d P=%Lx D=%Lx L=%Lx %s\n", + "%s idx %d P=%Lx D=%Lx L=%Lx %s %s\n", type2name[entry->type], idx, (unsigned long long)entry->paddr, entry->dev_addr, entry->size, - dir2name[entry->direction]); + dir2name[entry->direction], + maperr2str[entry->map_err_type]); } } @@ -844,16 +858,16 @@ static void check_unmap(struct dma_debug_entry *ref) struct hash_bucket *bucket; unsigned long flags; - if (dma_mapping_error(ref->dev, ref->dev_addr)) { - err_printk(ref->dev, NULL, "DMA-API: device driver tries " - "to free an invalid DMA memory address\n"); - return; - } - bucket = get_hash_bucket(ref, &flags); entry = bucket_find_exact(bucket, ref); if (!entry) { + if (dma_mapping_error(ref->dev, ref->dev_addr)) { + err_printk(ref->dev, NULL, + "DMA-API: device driver tries " + "to free an invalid DMA memory address\n"); + return; + } err_printk(ref->dev, NULL, "DMA-API: device driver tries " "to free DMA memory it has not allocated " "[device address=0x%016llx] [size=%llu bytes]\n", @@ -910,6 +924,15 @@ static void check_unmap(struct dma_debug_entry *ref) dir2name[ref->direction]); } + if (entry->map_err_type == MAP_ERR_NOT_CHECKED) { + err_printk(ref->dev, entry, + "DMA-API: device driver failed to check map error" + "[device address=0x%016llx] [size=%llu bytes] " + "[mapped as %s]", + ref->dev_addr, ref->size, + type2name[entry->type]); + } + hash_bucket_del(entry); dma_entry_free(entry); @@ -1017,7 +1040,7 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, if (unlikely(global_disable)) return; - if (unlikely(dma_mapping_error(dev, dma_addr))) + if (dma_mapping_error(dev, dma_addr)) return; entry = dma_entry_alloc(); @@ -1030,6 +1053,7 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, entry->dev_addr = dma_addr; entry->size = size; entry->direction = direction; + entry->map_err_type = MAP_ERR_NOT_CHECKED; if (map_single) entry->type = dma_debug_single; @@ -1045,6 +1069,30 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, } EXPORT_SYMBOL(debug_dma_map_page); +void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + struct dma_debug_entry ref; + struct dma_debug_entry *entry; + struct hash_bucket *bucket; + unsigned long flags; + + if (unlikely(global_disable)) + return; + + ref.dev = dev; + ref.dev_addr = dma_addr; + bucket = get_hash_bucket(&ref, &flags); + entry = bucket_find_exact(bucket, &ref); + + if (!entry) + goto out; + + entry->map_err_type = MAP_ERR_CHECKED; +out: + put_hash_bucket(bucket, &flags); +} +EXPORT_SYMBOL(debug_dma_mapping_error); + void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, size_t size, int direction, bool map_single) { diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index a8020293f342..ee71ea26777a 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -305,7 +305,6 @@ ceph_parse_options(char *options, const char *dev_name, /* start with defaults */ opt->flags = CEPH_OPT_DEFAULT; - opt->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT; opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */ opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; /* seconds */ @@ -391,7 +390,7 @@ ceph_parse_options(char *options, const char *dev_name, /* misc */ case Opt_osdtimeout: - opt->osd_timeout = intval; + pr_warning("ignoring deprecated osdtimeout option\n"); break; case Opt_osdkeepalivetimeout: opt->osd_keepalive_timeout = intval; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 3ef1759403b4..4d111fd2b492 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2244,22 +2244,62 @@ bad_tag: /* - * Atomically queue work on a connection. Bump @con reference to - * avoid races with connection teardown. + * Atomically queue work on a connection after the specified delay. + * Bump @con reference to avoid races with connection teardown. + * Returns 0 if work was queued, or an error code otherwise. */ -static void queue_con(struct ceph_connection *con) +static int queue_con_delay(struct ceph_connection *con, unsigned long delay) { if (!con->ops->get(con)) { - dout("queue_con %p ref count 0\n", con); - return; + dout("%s %p ref count 0\n", __func__, con); + + return -ENOENT; } - if (!queue_delayed_work(ceph_msgr_wq, &con->work, 0)) { - dout("queue_con %p - already queued\n", con); + if (!queue_delayed_work(ceph_msgr_wq, &con->work, delay)) { + dout("%s %p - already queued\n", __func__, con); con->ops->put(con); - } else { - dout("queue_con %p\n", con); + + return -EBUSY; } + + dout("%s %p %lu\n", __func__, con, delay); + + return 0; +} + +static void queue_con(struct ceph_connection *con) +{ + (void) queue_con_delay(con, 0); +} + +static bool con_sock_closed(struct ceph_connection *con) +{ + if (!test_and_clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags)) + return false; + +#define CASE(x) \ + case CON_STATE_ ## x: \ + con->error_msg = "socket closed (con state " #x ")"; \ + break; + + switch (con->state) { + CASE(CLOSED); + CASE(PREOPEN); + CASE(CONNECTING); + CASE(NEGOTIATING); + CASE(OPEN); + CASE(STANDBY); + default: + pr_warning("%s con %p unrecognized state %lu\n", + __func__, con, con->state); + con->error_msg = "unrecognized con state"; + BUG(); + break; + } +#undef CASE + + return true; } /* @@ -2273,35 +2313,16 @@ static void con_work(struct work_struct *work) mutex_lock(&con->mutex); restart: - if (test_and_clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags)) { - switch (con->state) { - case CON_STATE_CONNECTING: - con->error_msg = "connection failed"; - break; - case CON_STATE_NEGOTIATING: - con->error_msg = "negotiation failed"; - break; - case CON_STATE_OPEN: - con->error_msg = "socket closed"; - break; - default: - dout("unrecognized con state %d\n", (int)con->state); - con->error_msg = "unrecognized con state"; - BUG(); - } + if (con_sock_closed(con)) goto fault; - } if (test_and_clear_bit(CON_FLAG_BACKOFF, &con->flags)) { dout("con_work %p backing off\n", con); - if (queue_delayed_work(ceph_msgr_wq, &con->work, - round_jiffies_relative(con->delay))) { - dout("con_work %p backoff %lu\n", con, con->delay); - mutex_unlock(&con->mutex); - return; - } else { + ret = queue_con_delay(con, round_jiffies_relative(con->delay)); + if (ret) { dout("con_work %p FAILED to back off %lu\n", con, con->delay); + BUG_ON(ret == -ENOENT); set_bit(CON_FLAG_BACKOFF, &con->flags); } goto done; @@ -2356,7 +2377,7 @@ fault: static void ceph_fault(struct ceph_connection *con) __releases(con->mutex) { - pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), + pr_warning("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg); dout("fault %p state %lu to peer %s\n", con, con->state, ceph_pr_addr(&con->peer_addr.in_addr)); @@ -2398,24 +2419,8 @@ static void ceph_fault(struct ceph_connection *con) con->delay = BASE_DELAY_INTERVAL; else if (con->delay < MAX_DELAY_INTERVAL) con->delay *= 2; - con->ops->get(con); - if (queue_delayed_work(ceph_msgr_wq, &con->work, - round_jiffies_relative(con->delay))) { - dout("fault queued %p delay %lu\n", con, con->delay); - } else { - con->ops->put(con); - dout("fault failed to queue %p delay %lu, backoff\n", - con, con->delay); - /* - * In many cases we see a socket state change - * while con_work is running and end up - * queuing (non-delayed) work, such that we - * can't backoff with a delay. Set a flag so - * that when con_work restarts we schedule the - * delay then. - */ - set_bit(CON_FLAG_BACKOFF, &con->flags); - } + set_bit(CON_FLAG_BACKOFF, &con->flags); + queue_con(con); } out_unlock: diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index c1d756cc7448..780caf6b0491 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -221,6 +221,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, kref_init(&req->r_kref); init_completion(&req->r_completion); init_completion(&req->r_safe_completion); + RB_CLEAR_NODE(&req->r_node); INIT_LIST_HEAD(&req->r_unsafe_item); INIT_LIST_HEAD(&req->r_linger_item); INIT_LIST_HEAD(&req->r_linger_osd); @@ -580,7 +581,7 @@ static void __kick_osd_requests(struct ceph_osd_client *osdc, dout("__kick_osd_requests osd%d\n", osd->o_osd); err = __reset_osd(osdc, osd); - if (err == -EAGAIN) + if (err) return; list_for_each_entry(req, &osd->o_requests, r_osd_item) { @@ -607,14 +608,6 @@ static void __kick_osd_requests(struct ceph_osd_client *osdc, } } -static void kick_osd_requests(struct ceph_osd_client *osdc, - struct ceph_osd *kickosd) -{ - mutex_lock(&osdc->request_mutex); - __kick_osd_requests(osdc, kickosd); - mutex_unlock(&osdc->request_mutex); -} - /* * If the osd connection drops, we need to resubmit all requests. */ @@ -628,7 +621,9 @@ static void osd_reset(struct ceph_connection *con) dout("osd_reset osd%d\n", osd->o_osd); osdc = osd->o_osdc; down_read(&osdc->map_sem); - kick_osd_requests(osdc, osd); + mutex_lock(&osdc->request_mutex); + __kick_osd_requests(osdc, osd); + mutex_unlock(&osdc->request_mutex); send_queued(osdc); up_read(&osdc->map_sem); } @@ -647,6 +642,7 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum) atomic_set(&osd->o_ref, 1); osd->o_osdc = osdc; osd->o_osd = onum; + RB_CLEAR_NODE(&osd->o_node); INIT_LIST_HEAD(&osd->o_requests); INIT_LIST_HEAD(&osd->o_linger_requests); INIT_LIST_HEAD(&osd->o_osd_lru); @@ -750,6 +746,7 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) if (list_empty(&osd->o_requests) && list_empty(&osd->o_linger_requests)) { __remove_osd(osdc, osd); + ret = -ENODEV; } else if (memcmp(&osdc->osdmap->osd_addr[osd->o_osd], &osd->o_con.peer_addr, sizeof(osd->o_con.peer_addr)) == 0 && @@ -876,9 +873,9 @@ static void __unregister_request(struct ceph_osd_client *osdc, req->r_osd = NULL; } + list_del_init(&req->r_req_lru_item); ceph_osdc_put_request(req); - list_del_init(&req->r_req_lru_item); if (osdc->num_requests == 0) { dout(" no requests, canceling timeout\n"); __cancel_osd_timeout(osdc); @@ -910,8 +907,8 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req) { dout("__unregister_linger_request %p\n", req); + list_del_init(&req->r_linger_item); if (req->r_osd) { - list_del_init(&req->r_linger_item); list_del_init(&req->r_linger_osd); if (list_empty(&req->r_osd->o_requests) && @@ -1090,12 +1087,10 @@ static void handle_timeout(struct work_struct *work) { struct ceph_osd_client *osdc = container_of(work, struct ceph_osd_client, timeout_work.work); - struct ceph_osd_request *req, *last_req = NULL; + struct ceph_osd_request *req; struct ceph_osd *osd; - unsigned long timeout = osdc->client->options->osd_timeout * HZ; unsigned long keepalive = osdc->client->options->osd_keepalive_timeout * HZ; - unsigned long last_stamp = 0; struct list_head slow_osds; dout("timeout\n"); down_read(&osdc->map_sem); @@ -1105,37 +1100,6 @@ static void handle_timeout(struct work_struct *work) mutex_lock(&osdc->request_mutex); /* - * reset osds that appear to be _really_ unresponsive. this - * is a failsafe measure.. we really shouldn't be getting to - * this point if the system is working properly. the monitors - * should mark the osd as failed and we should find out about - * it from an updated osd map. - */ - while (timeout && !list_empty(&osdc->req_lru)) { - req = list_entry(osdc->req_lru.next, struct ceph_osd_request, - r_req_lru_item); - - /* hasn't been long enough since we sent it? */ - if (time_before(jiffies, req->r_stamp + timeout)) - break; - - /* hasn't been long enough since it was acked? */ - if (req->r_request->ack_stamp == 0 || - time_before(jiffies, req->r_request->ack_stamp + timeout)) - break; - - BUG_ON(req == last_req && req->r_stamp == last_stamp); - last_req = req; - last_stamp = req->r_stamp; - - osd = req->r_osd; - BUG_ON(!osd); - pr_warning(" tid %llu timed out on osd%d, will reset osd\n", - req->r_tid, osd->o_osd); - __kick_osd_requests(osdc, osd); - } - - /* * ping osds that are a bit slow. this ensures that if there * is a break in the TCP connection we will notice, and reopen * a connection with that osd (from the fault callback). @@ -1364,8 +1328,8 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) dout("kicking lingering %p tid %llu osd%d\n", req, req->r_tid, req->r_osd ? req->r_osd->o_osd : -1); - __unregister_linger_request(osdc, req); __register_request(osdc, req); + __unregister_linger_request(osdc, req); } mutex_unlock(&osdc->request_mutex); @@ -1599,6 +1563,7 @@ int ceph_osdc_create_event(struct ceph_osd_client *osdc, event->data = data; event->osdc = osdc; INIT_LIST_HEAD(&event->osd_node); + RB_CLEAR_NODE(&event->node); kref_init(&event->kref); /* one ref for us */ kref_get(&event->kref); /* one ref for the caller */ init_completion(&event->completion); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 5433fb0eb3c6..de73214b5d26 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -469,6 +469,22 @@ static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id) return NULL; } +const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id) +{ + struct ceph_pg_pool_info *pi; + + if (id == CEPH_NOPOOL) + return NULL; + + if (WARN_ON_ONCE(id > (u64) INT_MAX)) + return NULL; + + pi = __lookup_pg_pool(&map->pg_pools, (int) id); + + return pi ? pi->name : NULL; +} +EXPORT_SYMBOL(ceph_pg_pool_name_by_id); + int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name) { struct rb_node *rbp; @@ -645,10 +661,12 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) ceph_decode_32_safe(p, end, max, bad); while (max--) { ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad); + err = -ENOMEM; pi = kzalloc(sizeof(*pi), GFP_NOFS); if (!pi) goto bad; pi->id = ceph_decode_32(p); + err = -EINVAL; ev = ceph_decode_8(p); /* encoding version */ if (ev > CEPH_PG_POOL_VERSION) { pr_warning("got unknown v %d > %d of ceph_pg_pool\n", @@ -664,8 +682,13 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) __insert_pg_pool(&map->pg_pools, pi); } - if (version >= 5 && __decode_pool_names(p, end, map) < 0) - goto bad; + if (version >= 5) { + err = __decode_pool_names(p, end, map); + if (err < 0) { + dout("fail to decode pool names"); + goto bad; + } + } ceph_decode_32_safe(p, end, map->pool_max, bad); @@ -745,7 +768,7 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) return map; bad: - dout("osdmap_decode fail\n"); + dout("osdmap_decode fail err %d\n", err); ceph_osdmap_destroy(map); return ERR_PTR(err); } @@ -839,6 +862,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, if (ev > CEPH_PG_POOL_VERSION) { pr_warning("got unknown v %d > %d of ceph_pg_pool\n", ev, CEPH_PG_POOL_VERSION); + err = -EINVAL; goto bad; } pi = __lookup_pg_pool(&map->pg_pools, pool); @@ -855,8 +879,11 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, if (err < 0) goto bad; } - if (version >= 5 && __decode_pool_names(p, end, map) < 0) - goto bad; + if (version >= 5) { + err = __decode_pool_names(p, end, map); + if (err < 0) + goto bad; + } /* old_pool */ ceph_decode_32_safe(p, end, len, bad); @@ -932,15 +959,13 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, (void) __remove_pg_mapping(&map->pg_temp, pgid); /* insert */ - if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) { - err = -EINVAL; + err = -EINVAL; + if (pglen > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) goto bad; - } + err = -ENOMEM; pg = kmalloc(sizeof(*pg) + sizeof(u32)*pglen, GFP_NOFS); - if (!pg) { - err = -ENOMEM; + if (!pg) goto bad; - } pg->pgid = pgid; pg->len = pglen; for (j = 0; j < pglen; j++) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 411f332de0b3..795a0f4e920b 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -23,7 +23,6 @@ #include <linux/errno.h> #include <linux/mutex.h> #include <linux/slab.h> -#include <linux/nsproxy.h> #include <net/ipv6.h> #include <linux/sunrpc/clnt.h> diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index dfa4ba69ff45..dbf12ac5ecb7 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -20,7 +20,6 @@ #include <linux/module.h> #include <linux/kthread.h> #include <linux/slab.h> -#include <linux/nsproxy.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/xdr.h> @@ -1041,7 +1040,7 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net) } /* - * Printk the given error with the address of the client that caused it. + * dprintk the given error with the address of the client that caused it. */ static __printf(2, 3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) @@ -1055,8 +1054,7 @@ void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) vaf.fmt = fmt; vaf.va = &args; - net_warn_ratelimited("svc: %s: %pV", - svc_print_addr(rqstp, buf, sizeof(buf)), &vaf); + dprintk("svc: %s: %pV", svc_print_addr(rqstp, buf, sizeof(buf)), &vaf); va_end(args); } @@ -1305,7 +1303,7 @@ svc_process(struct svc_rqst *rqstp) * Setup response xdr_buf. * Initially it has just one page */ - rqstp->rq_resused = 1; + rqstp->rq_next_page = &rqstp->rq_respages[1]; resv->iov_base = page_address(rqstp->rq_respages[0]); resv->iov_len = 0; rqstp->rq_res.pages = rqstp->rq_respages + 1; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index cc3020d16789..0a148c9d2a5c 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -605,6 +605,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) rqstp->rq_respages = rqstp->rq_pages + 1 + DIV_ROUND_UP(rqstp->rq_arg.page_len, PAGE_SIZE); } + rqstp->rq_next_page = rqstp->rq_respages+1; if (serv->sv_stats) serv->sv_stats->netudpcnt++; @@ -878,9 +879,9 @@ static unsigned int svc_tcp_restore_pages(struct svc_sock *svsk, struct svc_rqst { unsigned int i, len, npages; - if (svsk->sk_tcplen <= sizeof(rpc_fraghdr)) + if (svsk->sk_datalen == 0) return 0; - len = svsk->sk_tcplen - sizeof(rpc_fraghdr); + len = svsk->sk_datalen; npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < npages; i++) { if (rqstp->rq_pages[i] != NULL) @@ -897,9 +898,9 @@ static void svc_tcp_save_pages(struct svc_sock *svsk, struct svc_rqst *rqstp) { unsigned int i, len, npages; - if (svsk->sk_tcplen <= sizeof(rpc_fraghdr)) + if (svsk->sk_datalen == 0) return; - len = svsk->sk_tcplen - sizeof(rpc_fraghdr); + len = svsk->sk_datalen; npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < npages; i++) { svsk->sk_pages[i] = rqstp->rq_pages[i]; @@ -911,9 +912,9 @@ static void svc_tcp_clear_pages(struct svc_sock *svsk) { unsigned int i, len, npages; - if (svsk->sk_tcplen <= sizeof(rpc_fraghdr)) + if (svsk->sk_datalen == 0) goto out; - len = svsk->sk_tcplen - sizeof(rpc_fraghdr); + len = svsk->sk_datalen; npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < npages; i++) { BUG_ON(svsk->sk_pages[i] == NULL); @@ -922,13 +923,12 @@ static void svc_tcp_clear_pages(struct svc_sock *svsk) } out: svsk->sk_tcplen = 0; + svsk->sk_datalen = 0; } /* - * Receive data. + * Receive fragment record header. * If we haven't gotten the record length yet, get the next four bytes. - * Otherwise try to gobble up as much as possible up to the complete - * record length. */ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp) { @@ -954,32 +954,16 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp) return -EAGAIN; } - svsk->sk_reclen = ntohl(svsk->sk_reclen); - if (!(svsk->sk_reclen & RPC_LAST_STREAM_FRAGMENT)) { - /* FIXME: technically, a record can be fragmented, - * and non-terminal fragments will not have the top - * bit set in the fragment length header. - * But apparently no known nfs clients send fragmented - * records. */ - net_notice_ratelimited("RPC: multiple fragments per record not supported\n"); - goto err_delete; - } - - svsk->sk_reclen &= RPC_FRAGMENT_SIZE_MASK; - dprintk("svc: TCP record, %d bytes\n", svsk->sk_reclen); - if (svsk->sk_reclen > serv->sv_max_mesg) { - net_notice_ratelimited("RPC: fragment too large: 0x%08lx\n", - (unsigned long)svsk->sk_reclen); + dprintk("svc: TCP record, %d bytes\n", svc_sock_reclen(svsk)); + if (svc_sock_reclen(svsk) + svsk->sk_datalen > + serv->sv_max_mesg) { + net_notice_ratelimited("RPC: fragment too large: %d\n", + svc_sock_reclen(svsk)); goto err_delete; } } - if (svsk->sk_reclen < 8) - goto err_delete; /* client is nuts. */ - - len = svsk->sk_reclen; - - return len; + return svc_sock_reclen(svsk); error: dprintk("RPC: TCP recv_record got %d\n", len); return len; @@ -1023,7 +1007,7 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp) if (dst->iov_len < src->iov_len) return -EAGAIN; /* whatever; just giving up. */ memcpy(dst->iov_base, src->iov_base, src->iov_len); - xprt_complete_rqst(req->rq_task, svsk->sk_reclen); + xprt_complete_rqst(req->rq_task, rqstp->rq_arg.len); rqstp->rq_arg.len = 0; return 0; } @@ -1042,6 +1026,17 @@ static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len) return i; } +static void svc_tcp_fragment_received(struct svc_sock *svsk) +{ + /* If we have more data, signal svc_xprt_enqueue() to try again */ + if (svc_recv_available(svsk) > sizeof(rpc_fraghdr)) + set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); + dprintk("svc: TCP %s record (%d bytes)\n", + svc_sock_final_rec(svsk) ? "final" : "nonfinal", + svc_sock_reclen(svsk)); + svsk->sk_tcplen = 0; + svsk->sk_reclen = 0; +} /* * Receive data from a TCP socket. @@ -1068,29 +1063,39 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) goto error; base = svc_tcp_restore_pages(svsk, rqstp); - want = svsk->sk_reclen - base; + want = svc_sock_reclen(svsk) - (svsk->sk_tcplen - sizeof(rpc_fraghdr)); vec = rqstp->rq_vec; pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0], - svsk->sk_reclen); + svsk->sk_datalen + want); rqstp->rq_respages = &rqstp->rq_pages[pnum]; + rqstp->rq_next_page = rqstp->rq_respages + 1; /* Now receive data */ len = svc_partial_recvfrom(rqstp, vec, pnum, want, base); - if (len >= 0) + if (len >= 0) { svsk->sk_tcplen += len; - if (len != want) { + svsk->sk_datalen += len; + } + if (len != want || !svc_sock_final_rec(svsk)) { svc_tcp_save_pages(svsk, rqstp); if (len < 0 && len != -EAGAIN) - goto err_other; - dprintk("svc: incomplete TCP record (%d of %d)\n", - svsk->sk_tcplen, svsk->sk_reclen); + goto err_delete; + if (len == want) + svc_tcp_fragment_received(svsk); + else + dprintk("svc: incomplete TCP record (%d of %d)\n", + (int)(svsk->sk_tcplen - sizeof(rpc_fraghdr)), + svc_sock_reclen(svsk)); goto err_noclose; } - rqstp->rq_arg.len = svsk->sk_reclen; + if (svc_sock_reclen(svsk) < 8) + goto err_delete; /* client is nuts. */ + + rqstp->rq_arg.len = svsk->sk_datalen; rqstp->rq_arg.page_base = 0; if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) { rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len; @@ -1107,11 +1112,8 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) len = receive_cb_reply(svsk, rqstp); /* Reset TCP read info */ - svsk->sk_reclen = 0; - svsk->sk_tcplen = 0; - /* If we have more data, signal svc_xprt_enqueue() to try again */ - if (svc_recv_available(svsk) > sizeof(rpc_fraghdr)) - set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); + svsk->sk_datalen = 0; + svc_tcp_fragment_received(svsk); if (len < 0) goto error; @@ -1120,15 +1122,14 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) if (serv->sv_stats) serv->sv_stats->nettcpcnt++; - dprintk("svc: TCP complete record (%d bytes)\n", rqstp->rq_arg.len); return rqstp->rq_arg.len; error: if (len != -EAGAIN) - goto err_other; + goto err_delete; dprintk("RPC: TCP recvfrom got EAGAIN\n"); return 0; -err_other: +err_delete: printk(KERN_NOTICE "%s: recvfrom returned errno %d\n", svsk->sk_xprt.xpt_server->sv_name, -len); set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); @@ -1305,6 +1306,7 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) svsk->sk_reclen = 0; svsk->sk_tcplen = 0; + svsk->sk_datalen = 0; memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages)); tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 41cb63b623df..0ce75524ed21 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -521,11 +521,11 @@ next_sge: rqstp->rq_pages[ch_no] = NULL; /* - * Detach res pages. svc_release must see a resused count of - * zero or it will attempt to put them. + * Detach res pages. If svc_release sees any it will attempt to + * put them. */ - while (rqstp->rq_resused) - rqstp->rq_respages[--rqstp->rq_resused] = NULL; + while (rqstp->rq_next_page != rqstp->rq_respages) + *(--rqstp->rq_next_page) = NULL; return err; } @@ -550,7 +550,7 @@ static int rdma_read_complete(struct svc_rqst *rqstp, /* rq_respages starts after the last arg page */ rqstp->rq_respages = &rqstp->rq_arg.pages[page_no]; - rqstp->rq_resused = 0; + rqstp->rq_next_page = &rqstp->rq_arg.pages[page_no]; /* Rebuild rq_arg head and tail. */ rqstp->rq_arg.head[0] = head->arg.head[0]; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 42eb7ba0b903..c1d124dc772b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -548,6 +548,7 @@ static int send_reply(struct svcxprt_rdma *rdma, int sge_no; int sge_bytes; int page_no; + int pages; int ret; /* Post a recv buffer to handle another request. */ @@ -611,7 +612,8 @@ static int send_reply(struct svcxprt_rdma *rdma, * respages array. They are our pages until the I/O * completes. */ - for (page_no = 0; page_no < rqstp->rq_resused; page_no++) { + pages = rqstp->rq_next_page - rqstp->rq_respages; + for (page_no = 0; page_no < pages; page_no++) { ctxt->pages[page_no+1] = rqstp->rq_respages[page_no]; ctxt->count++; rqstp->rq_respages[page_no] = NULL; diff --git a/scripts/coccinelle/misc/warn.cocci b/scripts/coccinelle/misc/warn.cocci new file mode 100644 index 000000000000..fda8c3558e4f --- /dev/null +++ b/scripts/coccinelle/misc/warn.cocci @@ -0,0 +1,109 @@ +/// Use WARN(1,...) rather than printk followed by WARN_ON(1) +/// +// Confidence: High +// Copyright: (C) 2012 Julia Lawall, INRIA/LIP6. GPLv2. +// Copyright: (C) 2012 Gilles Muller, INRIA/LiP6. GPLv2. +// URL: http://coccinelle.lip6.fr/ +// Comments: +// Options: -no_includes -include_headers + +virtual patch +virtual context +virtual org +virtual report + +@bad1@ +position p; +@@ + +printk(...); +printk@p(...); +WARN_ON(1); + +@r1 depends on context || report || org@ +position p != bad1.p; +@@ + + printk@p(...); +*WARN_ON(1); + +@script:python depends on org@ +p << r1.p; +@@ + +cocci.print_main("printk + WARN_ON can be just WARN",p) + +@script:python depends on report@ +p << r1.p; +@@ + +msg = "SUGGESTION: printk + WARN_ON can be just WARN" +coccilib.report.print_report(p[0],msg) + +@ok1 depends on patch@ +expression list es; +position p != bad1.p; +@@ + +-printk@p( ++WARN(1, + es); +-WARN_ON(1); + +@depends on patch@ +expression list ok1.es; +@@ + +if (...) +- { + WARN(1,es); +- } + +// -------------------------------------------------------------------- + +@bad2@ +position p; +@@ + +printk(...); +printk@p(...); +WARN_ON_ONCE(1); + +@r2 depends on context || report || org@ +position p != bad1.p; +@@ + + printk@p(...); +*WARN_ON_ONCE(1); + +@script:python depends on org@ +p << r2.p; +@@ + +cocci.print_main("printk + WARN_ON_ONCE can be just WARN_ONCE",p) + +@script:python depends on report@ +p << r2.p; +@@ + +msg = "SUGGESTION: printk + WARN_ON_ONCE can be just WARN_ONCE" +coccilib.report.print_report(p[0],msg) + +@ok2 depends on patch@ +expression list es; +position p != bad2.p; +@@ + +-printk@p( ++WARN_ONCE(1, + es); +-WARN_ON_ONCE(1); + +@depends on patch@ +expression list ok2.es; +@@ + +if (...) +- { + WARN_ONCE(1,es); +- } diff --git a/scripts/config b/scripts/config index ee355394f4ef..bb4d3deb6d1c 100755 --- a/scripts/config +++ b/scripts/config @@ -101,7 +101,6 @@ while [ "$1" != "" ] ; do case "$CMD" in --keep-case|-k) MUNGE_CASE=no - shift continue ;; --refresh) diff --git a/scripts/pnmtologo.c b/scripts/pnmtologo.c index 5c113123ed9f..68bb4efc5af4 100644 --- a/scripts/pnmtologo.c +++ b/scripts/pnmtologo.c @@ -74,6 +74,7 @@ static unsigned int logo_height; static struct color **logo_data; static struct color logo_clut[MAX_LINUX_LOGO_COLORS]; static unsigned int logo_clutsize; +static int is_plain_pbm = 0; static void die(const char *fmt, ...) __attribute__ ((noreturn)) __attribute ((format (printf, 1, 2))); @@ -103,6 +104,11 @@ static unsigned int get_number(FILE *fp) val = 0; while (isdigit(c)) { val = 10*val+c-'0'; + /* some PBM are 'broken'; GiMP for example exports a PBM without space + * between the digits. This is Ok cause we know a PBM can only have a '1' + * or a '0' for the digit. */ + if (is_plain_pbm) + break; c = fgetc(fp); if (c == EOF) die("%s: end of file\n", filename); @@ -167,6 +173,7 @@ static void read_image(void) switch (magic) { case '1': /* Plain PBM */ + is_plain_pbm = 1; for (i = 0; i < logo_height; i++) for (j = 0; j < logo_width; j++) logo_data[i][j].red = logo_data[i][j].green = diff --git a/scripts/tags.sh b/scripts/tags.sh index 79fdafb0d263..08f06c00745e 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -48,13 +48,14 @@ find_arch_sources() for i in $archincludedir; do prune="$prune -wholename $i -prune -o" done - find ${tree}arch/$1 $ignore $prune -name "$2" -print; + find ${tree}arch/$1 $ignore $subarchprune $prune -name "$2" -print; } # find sources in arch/$1/include find_arch_include_sources() { - include=$(find ${tree}arch/$1/ -name include -type d); + include=$(find ${tree}arch/$1/ $subarchprune \ + -name include -type d -print); if [ -n "$include" ]; then archincludedir="$archincludedir $include" find $include $ignore -name "$2" -print; @@ -95,6 +96,32 @@ all_sources() find_other_sources '*.[chS]' } +all_compiled_sources() +{ + for i in $(all_sources); do + case "$i" in + *.[cS]) + j=${i/\.[cS]/\.o} + if [ -e $j ]; then + echo $i + fi + ;; + *) + echo $i + ;; + esac + done +} + +all_target_sources() +{ + if [ -n "$COMPILED_SOURCE" ]; then + all_compiled_sources + else + all_sources + fi +} + all_kconfigs() { for arch in $ALLSOURCE_ARCHS; do @@ -110,18 +137,18 @@ all_defconfigs() docscope() { - (echo \-k; echo \-q; all_sources) > cscope.files + (echo \-k; echo \-q; all_target_sources) > cscope.files cscope -b -f cscope.out } dogtags() { - all_sources | gtags -i -f - + all_target_sources | gtags -i -f - } exuberant() { - all_sources | xargs $1 -a \ + all_target_sources | xargs $1 -a \ -I __initdata,__exitdata,__acquires,__releases \ -I __read_mostly,____cacheline_aligned \ -I ____cacheline_aligned_in_smp \ @@ -173,7 +200,7 @@ exuberant() emacs() { - all_sources | xargs $1 -a \ + all_target_sources | xargs $1 -a \ --regex='/^(ENTRY|_GLOBAL)(\([^)]*\)).*/\2/' \ --regex='/^SYSCALL_DEFINE[0-9]?(\([^,)]*\).*/sys_\1/' \ --regex='/^TRACE_EVENT(\([^,)]*\).*/trace_\1/' \ @@ -220,11 +247,10 @@ xtags() elif $1 --version 2>&1 | grep -iq emacs; then emacs $1 else - all_sources | xargs $1 -a + all_target_sources | xargs $1 -a fi } - # Support um (which uses SUBARCH) if [ "${ARCH}" = "um" ]; then if [ "$SUBARCH" = "i386" ]; then @@ -234,6 +260,21 @@ if [ "${ARCH}" = "um" ]; then else archinclude=${SUBARCH} fi +elif [ "${SRCARCH}" = "arm" -a "${SUBARCH}" != "" ]; then + subarchdir=$(find ${tree}arch/$SRCARCH/ -name "mach-*" -type d -o \ + -name "plat-*" -type d); + for i in $subarchdir; do + case "$i" in + *"mach-"${SUBARCH}) + ;; + *"plat-"${SUBARCH}) + ;; + *) + subarchprune="$subarchprune \ + -wholename $i -prune -o" + ;; + esac + done fi remove_structs= |