diff options
51 files changed, 2581 insertions, 2533 deletions
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 0d5394920a3..74484e69640 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -32,9 +32,9 @@ Mailing list: linux-ext4@vger.kernel.org you will need to merge your changes with the version from e2fsprogs 1.41.x. - - Create a new filesystem using the ext4dev filesystem type: + - Create a new filesystem using the ext4 filesystem type: - # mke2fs -t ext4dev /dev/hda1 + # mke2fs -t ext4 /dev/hda1 Or configure an existing ext3 filesystem to support extents and set the test_fs flag to indicate that it's ok for an in-development @@ -47,13 +47,13 @@ Mailing list: linux-ext4@vger.kernel.org # tune2fs -I 256 /dev/hda1 - (Note: we currently do not have tools to convert an ext4dev + (Note: we currently do not have tools to convert an ext4 filesystem back to ext3; so please do not do try this on production filesystems.) - Mounting: - # mount -t ext4dev /dev/hda1 /wherever + # mount -t ext4 /dev/hda1 /wherever - When comparing performance with other filesystems, remember that ext3/4 by default offers higher data integrity guarantees than most. @@ -177,6 +177,11 @@ barrier=<0|1(*)> This enables/disables the use of write barriers in your disks are battery-backed in one way or another, disabling barriers may safely improve performance. +inode_readahead=n This tuning parameter controls the maximum + number of inode table blocks that ext4's inode + table readahead algorithm will pre-read into + the buffer cache. The default value is 32 blocks. + orlov (*) This enables the new Orlov block allocator. It is enabled by default. @@ -252,6 +257,7 @@ stripe=n Number of filesystem blocks that mballoc will try delalloc (*) Deferring block allocation until write-out time. nodelalloc Disable delayed allocation. Blocks are allocation when data is copied from user to page cache. + Data Mode ========= There are 3 different data modes: diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt new file mode 100644 index 00000000000..1e3defcfe50 --- /dev/null +++ b/Documentation/filesystems/fiemap.txt @@ -0,0 +1,228 @@ +============ +Fiemap Ioctl +============ + +The fiemap ioctl is an efficient method for userspace to get file +extent mappings. Instead of block-by-block mapping (such as bmap), fiemap +returns a list of extents. + + +Request Basics +-------------- + +A fiemap request is encoded within struct fiemap: + +struct fiemap { + __u64 fm_start; /* logical offset (inclusive) at + * which to start mapping (in) */ + __u64 fm_length; /* logical length of mapping which + * userspace cares about (in) */ + __u32 fm_flags; /* FIEMAP_FLAG_* flags for request (in/out) */ + __u32 fm_mapped_extents; /* number of extents that were + * mapped (out) */ + __u32 fm_extent_count; /* size of fm_extents array (in) */ + __u32 fm_reserved; + struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */ +}; + + +fm_start, and fm_length specify the logical range within the file +which the process would like mappings for. Extents returned mirror +those on disk - that is, the logical offset of the 1st returned extent +may start before fm_start, and the range covered by the last returned +extent may end after fm_length. All offsets and lengths are in bytes. + +Certain flags to modify the way in which mappings are looked up can be +set in fm_flags. If the kernel doesn't understand some particular +flags, it will return EBADR and the contents of fm_flags will contain +the set of flags which caused the error. If the kernel is compatible +with all flags passed, the contents of fm_flags will be unmodified. +It is up to userspace to determine whether rejection of a particular +flag is fatal to it's operation. This scheme is intended to allow the +fiemap interface to grow in the future but without losing +compatibility with old software. + +fm_extent_count specifies the number of elements in the fm_extents[] array +that can be used to return extents. If fm_extent_count is zero, then the +fm_extents[] array is ignored (no extents will be returned), and the +fm_mapped_extents count will hold the number of extents needed in +fm_extents[] to hold the file's current mapping. Note that there is +nothing to prevent the file from changing between calls to FIEMAP. + +The following flags can be set in fm_flags: + +* FIEMAP_FLAG_SYNC +If this flag is set, the kernel will sync the file before mapping extents. + +* FIEMAP_FLAG_XATTR +If this flag is set, the extents returned will describe the inodes +extended attribute lookup tree, instead of it's data tree. + + +Extent Mapping +-------------- + +Extent information is returned within the embedded fm_extents array +which userspace must allocate along with the fiemap structure. The +number of elements in the fiemap_extents[] array should be passed via +fm_extent_count. The number of extents mapped by kernel will be +returned via fm_mapped_extents. If the number of fiemap_extents +allocated is less than would be required to map the requested range, +the maximum number of extents that can be mapped in the fm_extent[] +array will be returned and fm_mapped_extents will be equal to +fm_extent_count. In that case, the last extent in the array will not +complete the requested range and will not have the FIEMAP_EXTENT_LAST +flag set (see the next section on extent flags). + +Each extent is described by a single fiemap_extent structure as +returned in fm_extents. + +struct fiemap_extent { + __u64 fe_logical; /* logical offset in bytes for the start of + * the extent */ + __u64 fe_physical; /* physical offset in bytes for the start + * of the extent */ + __u64 fe_length; /* length in bytes for the extent */ + __u64 fe_reserved64[2]; + __u32 fe_flags; /* FIEMAP_EXTENT_* flags for this extent */ + __u32 fe_reserved[3]; +}; + +All offsets and lengths are in bytes and mirror those on disk. It is valid +for an extents logical offset to start before the request or it's logical +length to extend past the request. Unless FIEMAP_EXTENT_NOT_ALIGNED is +returned, fe_logical, fe_physical, and fe_length will be aligned to the +block size of the file system. With the exception of extents flagged as +FIEMAP_EXTENT_MERGED, adjacent extents will not be merged. + +The fe_flags field contains flags which describe the extent returned. +A special flag, FIEMAP_EXTENT_LAST is always set on the last extent in +the file so that the process making fiemap calls can determine when no +more extents are available, without having to call the ioctl again. + +Some flags are intentionally vague and will always be set in the +presence of other more specific flags. This way a program looking for +a general property does not have to know all existing and future flags +which imply that property. + +For example, if FIEMAP_EXTENT_DATA_INLINE or FIEMAP_EXTENT_DATA_TAIL +are set, FIEMAP_EXTENT_NOT_ALIGNED will also be set. A program looking +for inline or tail-packed data can key on the specific flag. Software +which simply cares not to try operating on non-aligned extents +however, can just key on FIEMAP_EXTENT_NOT_ALIGNED, and not have to +worry about all present and future flags which might imply unaligned +data. Note that the opposite is not true - it would be valid for +FIEMAP_EXTENT_NOT_ALIGNED to appear alone. + +* FIEMAP_EXTENT_LAST +This is the last extent in the file. A mapping attempt past this +extent will return nothing. + +* FIEMAP_EXTENT_UNKNOWN +The location of this extent is currently unknown. This may indicate +the data is stored on an inaccessible volume or that no storage has +been allocated for the file yet. + +* FIEMAP_EXTENT_DELALLOC + - This will also set FIEMAP_EXTENT_UNKNOWN. +Delayed allocation - while there is data for this extent, it's +physical location has not been allocated yet. + +* FIEMAP_EXTENT_ENCODED +This extent does not consist of plain filesystem blocks but is +encoded (e.g. encrypted or compressed). Reading the data in this +extent via I/O to the block device will have undefined results. + +Note that it is *always* undefined to try to update the data +in-place by writing to the indicated location without the +assistance of the filesystem, or to access the data using the +information returned by the FIEMAP interface while the filesystem +is mounted. In other words, user applications may only read the +extent data via I/O to the block device while the filesystem is +unmounted, and then only if the FIEMAP_EXTENT_ENCODED flag is +clear; user applications must not try reading or writing to the +filesystem via the block device under any other circumstances. + +* FIEMAP_EXTENT_DATA_ENCRYPTED + - This will also set FIEMAP_EXTENT_ENCODED +The data in this extent has been encrypted by the file system. + +* FIEMAP_EXTENT_NOT_ALIGNED +Extent offsets and length are not guaranteed to be block aligned. + +* FIEMAP_EXTENT_DATA_INLINE + This will also set FIEMAP_EXTENT_NOT_ALIGNED +Data is located within a meta data block. + +* FIEMAP_EXTENT_DATA_TAIL + This will also set FIEMAP_EXTENT_NOT_ALIGNED +Data is packed into a block with data from other files. + +* FIEMAP_EXTENT_UNWRITTEN +Unwritten extent - the extent is allocated but it's data has not been +initialized. This indicates the extent's data will be all zero if read +through the filesystem but the contents are undefined if read directly from +the device. + +* FIEMAP_EXTENT_MERGED +This will be set when a file does not support extents, i.e., it uses a block +based addressing scheme. Since returning an extent for each block back to +userspace would be highly inefficient, the kernel will try to merge most +adjacent blocks into 'extents'. + + +VFS -> File System Implementation +--------------------------------- + +File systems wishing to support fiemap must implement a ->fiemap callback on +their inode_operations structure. The fs ->fiemap call is responsible for +defining it's set of supported fiemap flags, and calling a helper function on +each discovered extent: + +struct inode_operations { + ... + + int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, + u64 len); + +->fiemap is passed struct fiemap_extent_info which describes the +fiemap request: + +struct fiemap_extent_info { + unsigned int fi_flags; /* Flags as passed from user */ + unsigned int fi_extents_mapped; /* Number of mapped extents */ + unsigned int fi_extents_max; /* Size of fiemap_extent array */ + struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent array */ +}; + +It is intended that the file system should not need to access any of this +structure directly. + + +Flag checking should be done at the beginning of the ->fiemap callback via the +fiemap_check_flags() helper: + +int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); + +The struct fieinfo should be passed in as recieved from ioctl_fiemap(). The +set of fiemap flags which the fs understands should be passed via fs_flags. If +fiemap_check_flags finds invalid user flags, it will place the bad values in +fieinfo->fi_flags and return -EBADR. If the file system gets -EBADR, from +fiemap_check_flags(), it should immediately exit, returning that error back to +ioctl_fiemap(). + + +For each extent in the request range, the file system should call +the helper function, fiemap_fill_next_extent(): + +int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, + u64 phys, u64 len, u32 flags, u32 dev); + +fiemap_fill_next_extent() will use the passed values to populate the +next free extent in the fm_extents array. 'General' extent flags will +automatically be set from specific flags on behalf of the calling file +system so that the userspace API is not broken. + +fiemap_fill_next_extent() returns 0 on success, and 1 when the +user-supplied fm_extents array is full. If an error is encountered +while copying the extent to user memory, -EFAULT will be returned. diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index f566ad9bcb7..d831d24d2a6 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -923,45 +923,44 @@ CPUs. The "procs_blocked" line gives the number of processes currently blocked, waiting for I/O to complete. + 1.9 Ext4 file system parameters ------------------------------ -Ext4 file system have one directory per partition under /proc/fs/ext4/ -# ls /proc/fs/ext4/hdc/ -group_prealloc max_to_scan mb_groups mb_history min_to_scan order2_req -stats stream_req - -mb_groups: -This file gives the details of multiblock allocator buddy cache of free blocks - -mb_history: -Multiblock allocation history. - -stats: -This file indicate whether the multiblock allocator should start collecting -statistics. The statistics are shown during unmount - -group_prealloc: -The multiblock allocator normalize the block allocation request to -group_prealloc filesystem blocks if we don't have strip value set. -The stripe value can be specified at mount time or during mke2fs. - -max_to_scan: -How long multiblock allocator can look for a best extent (in found extents) - -min_to_scan: -How long multiblock allocator must look for a best extent - -order2_req: -Multiblock allocator use 2^N search using buddies only for requests greater -than or equal to order2_req. The request size is specfied in file system -blocks. A value of 2 indicate only if the requests are greater than or equal -to 4 blocks. - -stream_req: -Files smaller than stream_req are served by the stream allocator, whose -purpose is to pack requests as close each to other as possible to -produce smooth I/O traffic. Avalue of 16 indicate that file smaller than 16 -filesystem block size will use group based preallocation. + +Information about mounted ext4 file systems can be found in +/proc/fs/ext4. Each mounted filesystem will have a directory in +/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or +/proc/fs/ext4/dm-0). The files in each per-device directory are shown +in Table 1-10, below. + +Table 1-10: Files in /proc/fs/ext4/<devname> +.............................................................................. + File Content + mb_groups details of multiblock allocator buddy cache of free blocks + mb_history multiblock allocation history + stats controls whether the multiblock allocator should start + collecting statistics, which are shown during the unmount + group_prealloc the multiblock allocator will round up allocation + requests to a multiple of this tuning parameter if the + stripe size is not set in the ext4 superblock + max_to_scan The maximum number of extents the multiblock allocator + will search to find the best extent + min_to_scan The minimum number of extents the multiblock allocator + will search to find the best extent + order2_req Tuning parameter which controls the minimum size for + requests (as a power of 2) where the buddy cache is + used + stream_req Files which have fewer blocks than this tunable + parameter will have their blocks allocated out of a + block group specific preallocation pool, so that small + files are packed closely together. Each large file + will have its blocks allocated out of its own unique + preallocation pool. +inode_readahead Tuning parameter which controls the maximum number of + inode table blocks that ext4's inode table readahead + algorithm will pre-read into the buffer cache +.............................................................................. + ------------------------------------------------------------------------------ Summary diff --git a/MAINTAINERS b/MAINTAINERS index 68781ed2b73..587f418ed00 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1659,9 +1659,10 @@ L: linux-ext4@vger.kernel.org S: Maintained EXT4 FILE SYSTEM -P: Stephen Tweedie, Andrew Morton -M: sct@redhat.com, akpm@linux-foundation.org, adilger@sun.com +P: Theodore Ts'o +M: tytso@mit.edu, adilger@sun.com L: linux-ext4@vger.kernel.org +W: http://ext4.wiki.kernel.org S: Maintained F71805F HARDWARE MONITORING DRIVER diff --git a/fs/Kconfig b/fs/Kconfig index abccb5dab9a..40183d94b68 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -136,37 +136,51 @@ config EXT3_FS_SECURITY If you are not using a security module that requires using extended attributes for file security labels, say N. -config EXT4DEV_FS - tristate "Ext4dev/ext4 extended fs support development (EXPERIMENTAL)" - depends on EXPERIMENTAL +config EXT4_FS + tristate "The Extended 4 (ext4) filesystem" select JBD2 select CRC16 help - Ext4dev is a predecessor filesystem of the next generation - extended fs ext4, based on ext3 filesystem code. It will be - renamed ext4 fs later, once ext4dev is mature and stabilized. + This is the next generation of the ext3 filesystem. Unlike the change from ext2 filesystem to ext3 filesystem, - the on-disk format of ext4dev is not the same as ext3 any more: - it is based on extent maps and it supports 48-bit physical block - numbers. These combined on-disk format changes will allow - ext4dev/ext4 to handle more than 16 TB filesystem volumes -- - a hard limit that ext3 cannot overcome without changing the - on-disk format. - - Other than extent maps and 48-bit block numbers, ext4dev also is - likely to have other new features such as persistent preallocation, - high resolution time stamps, and larger file support etc. These - features will be added to ext4dev gradually. + the on-disk format of ext4 is not forwards compatible with + ext3; it is based on extent maps and it supports 48-bit + physical block numbers. The ext4 filesystem also supports delayed + allocation, persistent preallocation, high resolution time stamps, + and a number of other features to improve performance and speed + up fsck time. For more information, please see the web pages at + http://ext4.wiki.kernel.org. + + The ext4 filesystem will support mounting an ext3 + filesystem; while there will be some performance gains from + the delayed allocation and inode table readahead, the best + performance gains will require enabling ext4 features in the + filesystem, or formating a new filesystem as an ext4 + filesystem initially. To compile this file system support as a module, choose M here. The module will be called ext4dev. If unsure, say N. -config EXT4DEV_FS_XATTR - bool "Ext4dev extended attributes" - depends on EXT4DEV_FS +config EXT4DEV_COMPAT + bool "Enable ext4dev compatibility" + depends on EXT4_FS + help + Starting with 2.6.28, the name of the ext4 filesystem was + renamed from ext4dev to ext4. Unfortunately there are some + lagecy userspace programs (such as klibc's fstype) have + "ext4dev" hardcoded. + + To enable backwards compatibility so that systems that are + still expecting to mount ext4 filesystems using ext4dev, + chose Y here. This feature will go away by 2.6.31, so + please arrange to get your userspace programs fixed! + +config EXT4_FS_XATTR + bool "Ext4 extended attributes" + depends on EXT4_FS default y help Extended attributes are name:value pairs associated with inodes by @@ -175,11 +189,11 @@ config EXT4DEV_FS_XATTR If unsure, say N. - You need this for POSIX ACL support on ext4dev/ext4. + You need this for POSIX ACL support on ext4. -config EXT4DEV_FS_POSIX_ACL - bool "Ext4dev POSIX Access Control Lists" - depends on EXT4DEV_FS_XATTR +config EXT4_FS_POSIX_ACL + bool "Ext4 POSIX Access Control Lists" + depends on EXT4_FS_XATTR select FS_POSIX_ACL help POSIX Access Control Lists (ACLs) support permissions for users and @@ -190,14 +204,14 @@ config EXT4DEV_FS_POSIX_ACL If you don't know what Access Control Lists are, say N -config EXT4DEV_FS_SECURITY - bool "Ext4dev Security Labels" - depends on EXT4DEV_FS_XATTR +config EXT4_FS_SECURITY + bool "Ext4 Security Labels" + depends on EXT4_FS_XATTR help Security labels support alternative access control models implemented by security modules like SELinux. This option enables an extended attribute handler for file security - labels in the ext4dev/ext4 filesystem. + labels in the ext4 filesystem. If you are not using a security module that requires using extended attributes for file security labels, say N. @@ -240,22 +254,22 @@ config JBD2 help This is a generic journaling layer for block devices that support both 32-bit and 64-bit block numbers. It is currently used by - the ext4dev/ext4 filesystem, but it could also be used to add + the ext4 filesystem, but it could also be used to add journal support to other file systems or block devices such as RAID or LVM. - If you are using ext4dev/ext4, you need to say Y here. If you are not - using ext4dev/ext4 then you will probably want to say N. + If you are using ext4, you need to say Y here. If you are not + using ext4 then you will probably want to say N. To compile this device as a module, choose M here. The module will be - called jbd2. If you are compiling ext4dev/ext4 into the kernel, + called jbd2. If you are compiling ext4 into the kernel, you cannot compile this code as a module. config JBD2_DEBUG - bool "JBD2 (ext4dev/ext4) debugging support" + bool "JBD2 (ext4) debugging support" depends on JBD2 && DEBUG_FS help - If you are using the ext4dev/ext4 journaled file system (or + If you are using the ext4 journaled file system (or potentially any other filesystem/device using JBD2), this option allows you to enable debugging output while the system is running, in order to help track down any problems you are having. @@ -270,9 +284,9 @@ config JBD2_DEBUG config FS_MBCACHE # Meta block cache for Extended Attributes (ext2/ext3/ext4) tristate - depends on EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4DEV_FS_XATTR - default y if EXT2_FS=y || EXT3_FS=y || EXT4DEV_FS=y - default m if EXT2_FS=m || EXT3_FS=m || EXT4DEV_FS=m + depends on EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4_FS_XATTR + default y if EXT2_FS=y || EXT3_FS=y || EXT4_FS=y + default m if EXT2_FS=m || EXT3_FS=m || EXT4_FS=m config REISERFS_FS tristate "Reiserfs support" diff --git a/fs/Makefile b/fs/Makefile index a1482a5eff1..de404b00eb0 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -69,7 +69,7 @@ obj-$(CONFIG_DLM) += dlm/ # Do not add any filesystems before this line obj-$(CONFIG_REISERFS_FS) += reiserfs/ obj-$(CONFIG_EXT3_FS) += ext3/ # Before ext2 so root fs can be ext3 -obj-$(CONFIG_EXT4DEV_FS) += ext4/ # Before ext2 so root fs can be ext4dev +obj-$(CONFIG_EXT4_FS) += ext4/ # Before ext2 so root fs can be ext4dev obj-$(CONFIG_JBD) += jbd/ obj-$(CONFIG_JBD2) += jbd2/ obj-$(CONFIG_EXT2_FS) += ext2/ diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 47d88da2d33..bae998c1e44 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -133,6 +133,8 @@ extern void ext2_truncate (struct inode *); extern int ext2_setattr (struct dentry *, struct iattr *); extern void ext2_set_inode_flags(struct inode *inode); extern void ext2_get_inode_flags(struct ext2_inode_info *); +extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len); int __ext2_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 5f2fa9c3629..45ed0712218 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -86,4 +86,5 @@ const struct inode_operations ext2_file_inode_operations = { #endif .setattr = ext2_setattr, .permission = ext2_permission, + .fiemap = ext2_fiemap, }; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 991d6dfeb51..7658b33e265 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -31,6 +31,7 @@ #include <linux/writeback.h> #include <linux/buffer_head.h> #include <linux/mpage.h> +#include <linux/fiemap.h> #include "ext2.h" #include "acl.h" #include "xip.h" @@ -704,6 +705,13 @@ int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_ } +int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len) +{ + return generic_block_fiemap(inode, fieinfo, start, len, + ext2_get_block); +} + static int ext2_writepage(struct page *page, struct writeback_control *wbc) { return block_write_full_page(page, ext2_get_block, wbc); diff --git a/fs/ext3/file.c b/fs/ext3/file.c index acc4913d301..3be1e0689c9 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -134,5 +134,6 @@ const struct inode_operations ext3_file_inode_operations = { .removexattr = generic_removexattr, #endif .permission = ext3_permission, + .fiemap = ext3_fiemap, }; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 507d8689b11..ebfec4d0148 100644 --- a/fs/ext3/inode.c +++ b/ |