diff options
Diffstat (limited to 'Documentation')
19 files changed, 699 insertions, 67 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-rbd b/Documentation/ABI/testing/sysfs-bus-rbd index 1cf2adf46b1..cd9213ccf3d 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/ABI/testing/sysfs-devices-node b/Documentation/ABI/testing/sysfs-devices-node deleted file mode 100644 index 453a210c3ce..00000000000 --- a/Documentation/ABI/testing/sysfs-devices-node +++ /dev/null @@ -1,7 +0,0 @@ -What: /sys/devices/system/node/nodeX/compact -Date: February 2010 -Contact: Mel Gorman <mel@csn.ul.ie> -Description: - When this file is written to, all memory within that node - will be compacted. When it completes, memory will be freed - into blocks which have as many contiguous pages as possible diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt index a0b6250add7..4a4fb295cee 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 66bd97a95f1..78a6c569d20 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/devicetree/bindings/spi/nvidia,tegra20-sflash.txt b/Documentation/devicetree/bindings/spi/nvidia,tegra20-sflash.txt index 8cf24f6f0a9..7b53da5cb75 100644 --- a/Documentation/devicetree/bindings/spi/nvidia,tegra20-sflash.txt +++ b/Documentation/devicetree/bindings/spi/nvidia,tegra20-sflash.txt @@ -13,7 +13,7 @@ Recommended properties: Example: -spi@7000d600 { +spi@7000c380 { compatible = "nvidia,tegra20-sflash"; reg = <0x7000c380 0x80>; interrupts = <0 39 0x04>; diff --git a/Documentation/devicetree/bindings/spi/nvidia,tegra20-slink.txt b/Documentation/devicetree/bindings/spi/nvidia,tegra20-slink.txt index f5b1ad1a1ec..eefe15e3d95 100644 --- a/Documentation/devicetree/bindings/spi/nvidia,tegra20-slink.txt +++ b/Documentation/devicetree/bindings/spi/nvidia,tegra20-slink.txt @@ -13,7 +13,7 @@ Recommended properties: Example: -slink@7000d600 { +spi@7000d600 { compatible = "nvidia,tegra20-slink"; reg = <0x7000d600 0x200>; interrupts = <0 82 0x04>; diff --git a/Documentation/devicetree/bindings/spi/spi_atmel.txt b/Documentation/devicetree/bindings/spi/spi_atmel.txt new file mode 100644 index 00000000000..07e04cdc0c9 --- /dev/null +++ b/Documentation/devicetree/bindings/spi/spi_atmel.txt @@ -0,0 +1,26 @@ +Atmel SPI device + +Required properties: +- compatible : should be "atmel,at91rm9200-spi". +- reg: Address and length of the register set for the device +- interrupts: Should contain spi interrupt +- cs-gpios: chipselects + +Example: + +spi1: spi@fffcc000 { + compatible = "atmel,at91rm9200-spi"; + reg = <0xfffcc000 0x4000>; + interrupts = <13 4 5>; + #address-cells = <1>; + #size-cells = <0>; + cs-gpios = <&pioB 3 0>; + status = "okay"; + + mmc-slot@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + gpios = <&pioC 4 0>; /* CD */ + spi-max-frequency = <25000000>; + }; +}; diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX index 7b52ba7bf32..8042050eb26 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/Locking b/Documentation/filesystems/Locking index e540a24e5d0..f48e0c6b4c4 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -80,7 +80,6 @@ rename: yes (all) (see below) readlink: no follow_link: no put_link: no -truncate: yes (see below) setattr: yes permission: no (may not block if called in rcu-walk mode) get_acl: no @@ -96,11 +95,6 @@ atomic_open: yes Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on victim. cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem. - ->truncate() is never called directly - it's a callback, not a -method. It's called by vmtruncate() - deprecated library function used by -->setattr(). Locking information above applies to that call (i.e. is -inherited from ->setattr() - vmtruncate() is used when ATTR_SIZE had been -passed). See Documentation/filesystems/directory-locking for more detailed discussion of the locking scheme for directory operations. diff --git a/Documentation/filesystems/caching/backend-api.txt b/Documentation/filesystems/caching/backend-api.txt index 382d52cdaf2..d78bab9622c 100644 --- a/Documentation/filesystems/caching/backend-api.txt +++ b/Documentation/filesystems/caching/backend-api.txt @@ -308,6 +308,18 @@ performed on the denizens of the cache. These are held in a structure of type: obtained by calling object->cookie->def->get_aux()/get_attr(). + (*) Invalidate data object [mandatory]: + + int (*invalidate_object)(struct fscache_operation *op) + + This is called to invalidate a data object (as pointed to by op->object). + All the data stored for this object should be discarded and an + attr_changed operation should be performed. The caller will follow up + with an object update operation. + + fscache_op_complete() must be called on op before returning. + + (*) Discard object [mandatory]: void (*drop_object)(struct fscache_object *object) @@ -419,7 +431,10 @@ performed on the denizens of the cache. These are held in a structure of type: If an I/O error occurs, fscache_io_error() should be called and -ENOBUFS returned if possible or fscache_end_io() called with a suitable error - code.. + code. + + fscache_put_retrieval() should be called after a page or pages are dealt + with. This will complete the operation when all pages are dealt with. (*) Request pages be read from cache [mandatory]: @@ -526,6 +541,27 @@ FS-Cache provides some utilities that a cache backend may make use of: error value should be 0 if successful and an error otherwise. + (*) Record that one or more pages being retrieved or allocated have been dealt + with: + + void fscache_retrieval_complete(struct fscache_retrieval *op, + int n_pages); + + This is called to record the fact that one or more pages have been dealt + with and are no longer the concern of this operation. When the number of + pages remaining in the operation reaches 0, the operation will be + completed. + + + (*) Record operation completion: + + void fscache_op_complete(struct fscache_operation *op); + + This is called to record the completion of an operation. This deducts + this operation from the parent object's run state, potentially permitting + one or more pending operations to start running. + + (*) Set highest store limit: void fscache_set_store_limit(struct fscache_object *object, diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.txt index 7cc6bf2871e..97e6c0ecc5e 100644 --- a/Documentation/filesystems/caching/netfs-api.txt +++ b/Documentation/filesystems/caching/netfs-api.txt @@ -35,8 +35,9 @@ This document contains the following sections: (12) Index and data file update (13) Miscellaneous cookie operations (14) Cookie unregistration - (15) Index and data file invalidation - (16) FS-Cache specific page flags. + (15) Index invalidation + (16) Data file invalidation + (17) FS-Cache specific page flags. ============================= @@ -767,13 +768,42 @@ the cookies for "child" indices, objects and pages have been relinquished first. -================================ -INDEX AND DATA FILE INVALIDATION -================================ +================== +INDEX INVALIDATION +================== + +There is no direct way to invalidate an index subtree. To do this, the caller +should relinquish and retire the cookie they have, and then acquire a new one. + + +====================== +DATA FILE INVALIDATION +====================== + +Sometimes it will be necessary to invalidate an object that contains data. +Typically this will be necessary when the server tells the netfs of a foreign +change - at which point the netfs has to throw away all the state it had for an +inode and reload from the server. + +To indicate that a cache object should be invalidated, the following function +can be called: + + void fscache_invalidate(struct fscache_cookie *cookie); + +This can be called with spinlocks held as it defers the work to a thread pool. +All extant storage, retrieval and attribute change ops at this point are +cancelled and discarded. Some future operations will be rejected until the +cache has had a chance to insert a barrier in the operations queue. After +that, operations will be queued again behind the invalidation operation. + +The invalidation operation will perform an attribute change operation and an +auxiliary data update operation as it is very likely these will have changed. + +Using the following function, the netfs can wait for the invalidation operation +to have reached a point at which it can start submitting ordinary operations +once again: -There is no direct way to invalidate an index subtree or a data file. To do -this, the caller should relinquish and retire the cookie they have, and then -acquire a new one. + void fscache_wait_on_invalidate(struct fscache_cookie *cookie); =========================== diff --git a/Documentation/filesystems/caching/object.txt b/Documentation/filesystems/caching/object.txt index 58313348da8..100ff41127e 100644 --- a/Documentation/filesystems/caching/object.txt +++ b/Documentation/filesystems/caching/object.txt @@ -216,7 +216,14 @@ servicing netfs requests: The normal running state. In this state, requests the netfs makes will be passed on to the cache. - (6) State FSCACHE_OBJECT_UPDATING. + (6) State FSCACHE_OBJECT_INVALIDATING. + + The object is undergoing invalidation. When the state comes here, it + discards all pending read, write and attribute change operations as it is + going to clear out the cache entirely and reinitialise it. It will then + continue to the FSCACHE_OBJECT_UPDATING state. + + (7) State FSCACHE_OBJECT_UPDATING. The state machine comes here to update the object in the cache from the netfs's records. This involves updating the auxiliary data that is used @@ -225,13 +232,13 @@ servicing netfs requests: And there are terminal states in which an object cleans itself up, deallocates memory and potentially deletes stuff from disk: - (7) State FSCACHE_OBJECT_LC_DYING. + (8) State FSCACHE_OBJECT_LC_DYING. The object comes here if it is dying because of a lookup or creation error. This would be due to a disk error or system error of some sort. Temporary data is cleaned up, and the parent is released. - (8) State FSCACHE_OBJECT_DYING. + (9) State FSCACHE_OBJECT_DYING. The object comes here if it is dying due to an error, because its parent cookie has been relinquished by the netfs or because the cache is being @@ -241,27 +248,27 @@ memory and potentially deletes stuff from disk: can destroy themselves. This object waits for all its children to go away before advancing to the next state. - (9) State FSCACHE_OBJECT_ABORT_INIT. +(10) State FSCACHE_OBJECT_ABORT_INIT. The object comes to this state if it was waiting on its parent in FSCACHE_OBJECT_INIT, but its parent died. The object will destroy itself so that the parent may proceed from the FSCACHE_OBJECT_DYING state. -(10) State FSCACHE_OBJECT_RELEASING. -(11) State FSCACHE_OBJECT_RECYCLING. +(11) State FSCACHE_OBJECT_RELEASING. +(12) State FSCACHE_OBJECT_RECYCLING. The object comes to one of these two states when dying once it is rid of all its children, if it is dying because the netfs relinquished its cookie. In the first state, the cached data is expected to persist, and in the second it will be deleted. -(12) State FSCACHE_OBJECT_WITHDRAWING. +(13) State FSCACHE_OBJECT_WITHDRAWING. The object transits to this state if the cache decides it wants to withdraw the object from service, perhaps to make space, but also due to error or just because the whole cache is being withdrawn. -(13) State FSCACHE_OBJECT_DEAD. +(14) State FSCACHE_OBJECT_DEAD. The object transits to this state when the in-memory object record is ready to be deleted. The object processor shouldn't ever see an object in diff --git a/Documentation/filesystems/caching/operations.txt b/Documentation/filesystems/caching/operations.txt index b6b070c57cb..bee2a5f93d6 100644 --- a/Documentation/filesystems/caching/operations.txt +++ b/Documentation/filesystems/caching/operations.txt @@ -174,7 +174,7 @@ Operations are used through the following procedure: necessary (the object might have died whilst the thread was waiting). When it has finished doing its processing, it should call - fscache_put_operation() on it. + fscache_op_complete() and fscache_put_operation() on it. (4) The operation holds an effective lock upon the object, preventing other exclusive ops conflicting until it is released. The operation can be diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt new file mode 100644 index 00000000000..8fbd8b46ee3 --- /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 092fad92a3f..01c2db76979 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. diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index 0742feebc6e..0472c31c163 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -281,7 +281,7 @@ ext2_write_failed and callers for an example. [mandatory] - ->truncate is going away. The whole truncate sequence needs to be + ->truncate is gone. The whole truncate sequence needs to be implemented in ->setattr, which is now mandatory for filesystems implementing on-disk size changes. Start with a copy of the old inode_setattr and vmtruncate, and the reorder the vmtruncate + foofs_vmtruncate sequence to diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 2ee133e030c..e3869098163 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -350,7 +350,6 @@ struct inode_operations { int (*readlink) (struct dentry *, char __user *,int); void * (*follow_link) (struct dentry *, struct nameidata *); void (*put_link) (struct dentry *, struct nameidata *, void *); - void (*truncate) (struct inode *); int (*permission) (struct inode *, int); int (*get_acl)(struct inode *, int); int (*setattr) (struct dentry *, struct iattr *); @@ -431,16 +430,6 @@ otherwise noted. started might not be in the page cache at the end of the walk). - truncate: Deprecated. This will not be called if ->setsize is defined. - Called by the VFS to change the size of a file. The - i_size field of the inode is set to the desired size by the - VFS before this method is called. This method is called by - the truncate(2) system call and related functionality. - - Note: ->truncate and vmtruncate are deprecated. Do not add new - instances/calls of these. Filesystems should be converted to do their - truncate sequence via ->setattr(). - permission: called by the VFS to check for access rights on a POSIX-like filesystem. diff --git a/Documentation/hwmon/it87 b/Documentation/hwmon/it87 index 87850d86c55..8386aadc0a8 100644 --- a/Documentation/hwmon/it87 +++ b/Documentation/hwmon/it87 @@ -209,3 +209,13 @@ doesn't use CPU cycles. Trip points must be set properly before switching to automatic fan speed control mode. The driver will perform basic integrity checks before actually switching to automatic control mode. + + +Temperature offset attributes +----------------------------- + +The driver supports temp[1-3]_offset sysfs attributes to adjust the reported +temperature for thermal diodes or diode-connected thermal transistors. +If a temperature sensor is configured for thermistors, the attribute values +are ignored. If the thermal sensor type is Intel PECI, the temperature offset +must be programmed to the critical CPU temperature. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index ddd84d62718..363e348bff9 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -446,12 +446,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted. possible to determine what the correct size should be. This option provides an override for these situations. - capability.disable= - [SECURITY] Disable capabilities. This would normally - be used only if an alternative security model is to be - configured. Potentially dangerous and should only be - used if you are entirely sure of the consequences. - ccw_timeout_log [S390] See Documentation/s390/CommonIO for details. |