diff options
Diffstat (limited to 'fs')
152 files changed, 2932 insertions, 3221 deletions
diff --git a/fs/9p/Kconfig b/fs/9p/Kconfig new file mode 100644 index 00000000000..74e0723e90b --- /dev/null +++ b/fs/9p/Kconfig @@ -0,0 +1,10 @@ +config 9P_FS + tristate "Plan 9 Resource Sharing Support (9P2000) (Experimental)" + depends on INET && NET_9P && EXPERIMENTAL + help + If you say Y here, you will get experimental support for + Plan 9 resource sharing via the 9P2000 protocol. + + See <http://v9fs.sf.net> for more information. + + If unsure, say N. diff --git a/fs/Kconfig b/fs/Kconfig index 51307b0fdf0..93945dd0b1a 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -27,141 +27,8 @@ config FS_MBCACHE default y if EXT4_FS=y && EXT4_FS_XATTR default m if EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4_FS_XATTR -config REISERFS_FS - tristate "Reiserfs support" - help - Stores not just filenames but the files themselves in a balanced - tree. Uses journalling. - - Balanced trees are more efficient than traditional file system - architectural foundations. - - In general, ReiserFS is as fast as ext2, but is very efficient with - large directories and small files. Additional patches are needed - for NFS and quotas, please see <http://www.namesys.com/> for links. - - It is more easily extended to have features currently found in - database and keyword search systems than block allocation based file - systems are. The next version will be so extended, and will support - plugins consistent with our motto ``It takes more than a license to - make source code open.'' - - Read <http://www.namesys.com/> to learn more about reiserfs. - - Sponsored by Threshold Networks, Emusic.com, and Bigstorage.com. - - If you like it, you can pay us to add new features to it that you - need, buy a support contract, or pay us to port it to another OS. - -config REISERFS_CHECK - bool "Enable reiserfs debug mode" - depends on REISERFS_FS - help - If you set this to Y, then ReiserFS will perform every check it can - possibly imagine of its internal consistency throughout its - operation. It will also go substantially slower. More than once we - have forgotten that this was on, and then gone despondent over the - latest benchmarks.:-) Use of this option allows our team to go all - out in checking for consistency when debugging without fear of its - effect on end users. If you are on the verge of sending in a bug - report, say Y and you might get a useful error message. Almost - everyone should say N. - -config REISERFS_PROC_INFO - bool "Stats in /proc/fs/reiserfs" - depends on REISERFS_FS && PROC_FS - help - Create under /proc/fs/reiserfs a hierarchy of files, displaying - various ReiserFS statistics and internal data at the expense of - making your kernel or module slightly larger (+8 KB). This also - increases the amount of kernel memory required for each mount. - Almost everyone but ReiserFS developers and people fine-tuning - reiserfs or tracing problems should say N. - -config REISERFS_FS_XATTR - bool "ReiserFS extended attributes" - depends on REISERFS_FS - 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 REISERFS_FS_POSIX_ACL - bool "ReiserFS POSIX Access Control Lists" - depends on REISERFS_FS_XATTR - select FS_POSIX_ACL - help - Posix Access Control Lists (ACLs) support permissions for users and - groups beyond the owner/group/world scheme. - - To learn more about Access Control Lists, visit the Posix ACLs for - Linux website <http://acl.bestbits.at/>. - - If you don't know what Access Control Lists are, say N - -config REISERFS_FS_SECURITY - bool "ReiserFS Security Labels" - depends on REISERFS_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 ReiserFS filesystem. - - If you are not using a security module that requires using - extended attributes for file security labels, say N. - -config JFS_FS - tristate "JFS filesystem support" - select NLS - help - This is a port of IBM's Journaled Filesystem . More information is - available in the file <file:Documentation/filesystems/jfs.txt>. - - If you do not intend to use the JFS filesystem, say N. - -config JFS_POSIX_ACL - bool "JFS POSIX Access Control Lists" - depends on JFS_FS - select FS_POSIX_ACL - help - Posix Access Control Lists (ACLs) support permissions for users and - groups beyond the owner/group/world scheme. - - To learn more about Access Control Lists, visit the Posix ACLs for - Linux website <http://acl.bestbits.at/>. - - If you don't know what Access Control Lists are, say N - -config JFS_SECURITY - bool "JFS Security Labels" - depends on JFS_FS - 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 jfs filesystem. - - If you are not using a security module that requires using - extended attributes for file security labels, say N. - -config JFS_DEBUG - bool "JFS debugging" - depends on JFS_FS - help - If you are experiencing any problems with the JFS filesystem, say - Y here. This will result in additional debugging messages to be - written to the system log. Under normal circumstances, this - results in very little overhead. - -config JFS_STATISTICS - bool "JFS statistics" - depends on JFS_FS - help - Enabling this option will cause statistics from the JFS file system - to be made available to the user in the /proc/fs/jfs/ directory. +source "fs/reiserfs/Kconfig" +source "fs/jfs/Kconfig" config FS_POSIX_ACL # Posix ACL utility routines (for now, only ext2/ext3/jfs/reiserfs/nfs4) @@ -182,111 +49,8 @@ config FILE_LOCKING source "fs/xfs/Kconfig" source "fs/gfs2/Kconfig" - -config OCFS2_FS - tristate "OCFS2 file system support" - depends on NET && SYSFS - select CONFIGFS_FS - select JBD2 - select CRC32 - select QUOTA - select QUOTA_TREE - help - OCFS2 is a general purpose extent based shared disk cluster file - system with many similarities to ext3. It supports 64 bit inode - numbers, and has automatically extending metadata groups which may - also make it attractive for non-clustered use. - - You'll want to install the ocfs2-tools package in order to at least - get "mount.ocfs2". - - Project web page: http://oss.oracle.com/projects/ocfs2 - Tools web page: http://oss.oracle.com/projects/ocfs2-tools - OCFS2 mailing lists: http://oss.oracle.com/projects/ocfs2/mailman/ - - For more information on OCFS2, see the file - <file:Documentation/filesystems/ocfs2.txt>. - -config OCFS2_FS_O2CB - tristate "O2CB Kernelspace Clustering" - depends on OCFS2_FS - default y - help - OCFS2 includes a simple kernelspace clustering package, the OCFS2 - Cluster Base. It only requires a very small userspace component - to configure it. This comes with the standard ocfs2-tools package. - O2CB is limited to maintaining a cluster for OCFS2 file systems. - It cannot manage any other cluster applications. - - It is always safe to say Y here, as the clustering method is - run-time selectable. - -config OCFS2_FS_USERSPACE_CLUSTER - tristate "OCFS2 Userspace Clustering" - depends on OCFS2_FS && DLM - default y - help - This option will allow OCFS2 to use userspace clustering services - in conjunction with the DLM in fs/dlm. If you are using a - userspace cluster manager, say Y here. - - It is safe to say Y, as the clustering method is run-time - selectable. - -config OCFS2_FS_STATS - bool "OCFS2 statistics" - depends on OCFS2_FS - default y - help - This option allows some fs statistics to be captured. Enabling - this option may increase the memory consumption. - -config OCFS2_DEBUG_MASKLOG - bool "OCFS2 logging support" - depends on OCFS2_FS - default y - help - The ocfs2 filesystem has an extensive logging system. The system - allows selection of events to log via files in /sys/o2cb/logmask/. - This option will enlarge your kernel, but it allows debugging of - ocfs2 filesystem issues. - -config OCFS2_DEBUG_FS - bool "OCFS2 expensive checks" - depends on OCFS2_FS - default n - help - This option will enable expensive consistency checks. Enable - this option for debugging only as it is likely to decrease - performance of the filesystem. - -config OCFS2_FS_POSIX_ACL - bool "OCFS2 POSIX Access Control Lists" - depends on OCFS2_FS - select FS_POSIX_ACL - default n - help - Posix Access Control Lists (ACLs) support permissions for users and - groups beyond the owner/group/world scheme. - -config BTRFS_FS - tristate "Btrfs filesystem (EXPERIMENTAL) Unstable disk format" - depends on EXPERIMENTAL - select LIBCRC32C - select ZLIB_INFLATE - select ZLIB_DEFLATE - help - Btrfs is a new filesystem with extents, writable snapshotting, - support for multiple devices and many more features. - - Btrfs is highly experimental, and THE DISK FORMAT IS NOT YET - FINALIZED. You should say N here unless you are interested in - testing Btrfs with non-critical data. - - To compile this file system support as a module, choose M here. The - module will be called btrfs. - - If unsure, say N. +source "fs/ocfs2/Kconfig" +source "fs/btrfs/Kconfig" endif # BLOCK @@ -348,64 +112,9 @@ config QUOTACTL depends on XFS_QUOTA || QUOTA default y -config AUTOFS_FS - tristate "Kernel automounter support" - help - The automounter is a tool to automatically mount remote file systems - on demand. This implementation is partially kernel-based to reduce - overhead in the already-mounted case; this is unlike the BSD - automounter (amd), which is a pure user space daemon. - - To use the automounter you need the user-space tools from the autofs - package; you can find the location in <file:Documentation/Changes>. - You also want to answer Y to "NFS file system support", below. - - If you want to use the newer version of the automounter with more - features, say N here and say Y to "Kernel automounter v4 support", - below. - - To compile this support as a module, choose M here: the module will be - called autofs. - - If you are not a part of a fairly large, distributed network, you - probably do not need an automounter, and can say N here. - -config AUTOFS4_FS - tristate "Kernel automounter version 4 support (also supports v3)" - help - The automounter is a tool to automatically mount remote file systems - on demand. This implementation is partially kernel-based to reduce - overhead in the already-mounted case; this is unlike the BSD - automounter (amd), which is a pure user space daemon. - - To use the automounter you need the user-space tools from - <ftp://ftp.kernel.org/pub/linux/daemons/autofs/v4/>; you also - want to answer Y to "NFS file system support", below. - - To compile this support as a module, choose M here: the module will be - called autofs4. You will need to add "alias autofs autofs4" to your - modules configuration file. - - If you are not a part of a fairly large, distributed network or - don't have a laptop which needs to dynamically reconfigure to the - local network, you probably do not need an automounter, and can say - N here. - -config FUSE_FS - tristate "FUSE (Filesystem in Userspace) support" - help - With FUSE it is possible to implement a fully functional filesystem - in a userspace program. - - There's also companion library: libfuse. This library along with - utilities is available from the FUSE homepage: - <http://fuse.sourceforge.net/> - - See <file:Documentation/filesystems/fuse.txt> for more information. - See <file:Documentation/Changes> for needed library/utility version. - - If you want to develop a userspace FS, or if you want to use - a filesystem based on FUSE, answer Y or M. +source "fs/autofs/Kconfig" +source "fs/autofs4/Kconfig" +source "fs/fuse/Kconfig" config GENERIC_ACL bool @@ -414,64 +123,8 @@ config GENERIC_ACL if BLOCK menu "CD-ROM/DVD Filesystems" -config ISO9660_FS - tristate "ISO 9660 CDROM file system support" - help - This is the standard file system used on CD-ROMs. It was previously - known as "High Sierra File System" and is called "hsfs" on other - Unix systems. The so-called Rock-Ridge extensions which allow for - long Unix filenames and symbolic links are also supported by this - driver. If you have a CD-ROM drive and want to do more with it than - just listen to audio CDs and watch its LEDs, say Y (and read - <file:Documentation/filesystems/isofs.txt> and the CD-ROM-HOWTO, - available from <http://www.tldp.org/docs.html#howto>), thereby - enlarging your kernel by about 27 KB; otherwise say N. - - To compile this file system support as a module, choose M here: the - module will be called isofs. - -config JOLIET - bool "Microsoft Joliet CDROM extensions" - depends on ISO9660_FS - select NLS - help - Joliet is a Microsoft extension for the ISO 9660 CD-ROM file system - which allows for long filenames in unicode format (unicode is the - new 16 bit character code, successor to ASCII, which encodes the - characters of almost all languages of the world; see - <http://www.unicode.org/> for more information). Say Y here if you - want to be able to read Joliet CD-ROMs under Linux. - -config ZISOFS - bool "Transparent decompression extension" - depends on ISO9660_FS - select ZLIB_INFLATE - help - This is a Linux-specific extension to RockRidge which lets you store - data in compressed form on a CD-ROM and have it transparently - decompressed when the CD-ROM is accessed. See - <http://www.kernel.org/pub/linux/utils/fs/zisofs/> for the tools - necessary to create such a filesystem. Say Y here if you want to be - able to read such compressed CD-ROMs. - -config UDF_FS - tristate "UDF file system support" - select CRC_ITU_T - help - This is the new file system used on some CD-ROMs and DVDs. Say Y if - you intend to mount DVD discs or CDRW's written in packet mode, or - if written to by other UDF utilities, such as DirectCD. - Please read <file:Documentation/filesystems/udf.txt>. - - To compile this file system support as a module, choose M here: the - module will be called udf. - - If unsure, say N. - -config UDF_NLS - bool - default y - depends on (UDF_FS=m && NLS) || (UDF_FS=y && NLS=y) +source "fs/isofs/Kconfig" +source "fs/udf/Kconfig" endmenu endif # BLOCK @@ -479,182 +132,8 @@ endif # BLOCK if BLOCK menu "DOS/FAT/NT Filesystems" -config FAT_FS - tristate - select NLS - help - If you want to use one of the FAT-based file systems (the MS-DOS and - VFAT (Windows 95) file systems), then you must say Y or M here - to include FAT support. You will then be able to mount partitions or - diskettes with FAT-based file systems and transparently access the - files on them, i.e. MSDOS files will look and behave just like all - other Unix files. - - This FAT support is not a file system in itself, it only provides - the foundation for the other file systems. You will have to say Y or - M to at least one of "MSDOS fs support" or "VFAT fs support" in - order to make use of it. - - Another way to read and write MSDOS floppies and hard drive - partitions from within Linux (but not transparently) is with the - mtools ("man mtools") program suite. You don't need to say Y here in - order to do that. - - If you need to move large files on floppies between a DOS and a - Linux box, say Y here, mount the floppy under Linux with an MSDOS - file system and use GNU tar's M option. GNU tar is a program - available for Unix and DOS ("man tar" or "info tar"). - - The FAT support will enlarge your kernel by about 37 KB. If unsure, - say Y. - - To compile this as a module, choose M here: the module will be called - fat. Note that if you compile the FAT support as a module, you - cannot compile any of the FAT-based file systems into the kernel - -- they will have to be modules as well. - -config MSDOS_FS - tristate "MSDOS fs support" - select FAT_FS - help - This allows you to mount MSDOS partitions of your hard drive (unless - they are compressed; to access compressed MSDOS partitions under - Linux, you can either use the DOS emulator DOSEMU, described in the - DOSEMU-HOWTO, available from - <http://www.tldp.org/docs.html#howto>, or try dmsdosfs in - <ftp://ibiblio.org/pub/Linux/system/filesystems/dosfs/>. If you - intend to use dosemu with a non-compressed MSDOS partition, say Y - here) and MSDOS floppies. This means that file access becomes - transparent, i.e. the MSDOS files look and behave just like all - other Unix files. - - If you have Windows 95 or Windows NT installed on your MSDOS - partitions, you should use the VFAT file system (say Y to "VFAT fs - support" below), or you will not be able to see the long filenames - generated by Windows 95 / Windows NT. - - This option will enlarge your kernel by about 7 KB. If unsure, - answer Y. This will only work if you said Y to "DOS FAT fs support" - as well. To compile this as a module, choose M here: the module will - be called msdos. - -config VFAT_FS - tristate "VFAT (Windows-95) fs support" - select FAT_FS - help - This option provides support for normal Windows file systems with - long filenames. That includes non-compressed FAT-based file systems - used by Windows 95, Windows 98, Windows NT 4.0, and the Unix - programs from the mtools package. - - The VFAT support enlarges your kernel by about 10 KB and it only - works if you said Y to the "DOS FAT fs support" above. Please read - the file <file:Documentation/filesystems/vfat.txt> for details. If - unsure, say Y. - - To compile this as a module, choose M here: the module will be called - vfat. - -config FAT_DEFAULT_CODEPAGE - int "Default codepage for FAT" - depends on MSDOS_FS || VFAT_FS - default 437 - help - This option should be set to the codepage of your FAT filesystems. - It can be overridden with the "codepage" mount option. - See <file:Documentation/filesystems/vfat.txt> for more information. - -config FAT_DEFAULT_IOCHARSET - string "Default iocharset for FAT" - depends on VFAT_FS - default "iso8859-1" - help - Set this to the default input/output character set you'd - like FAT to use. It should probably match the character set - that most of your FAT filesystems use, and can be overridden - with the "iocharset" mount option for FAT filesystems. - Note that "utf8" is not recommended for FAT filesystems. - If unsure, you shouldn't set "utf8" here. - See <file:Documentation/filesystems/vfat.txt> for more information. - -config NTFS_FS - tristate "NTFS file system support" - select NLS - help - NTFS is the file system of Microsoft Windows NT, 2000, XP and 2003. - - Saying Y or M here enables read support. There is partial, but - safe, write support available. For write support you must also - say Y to "NTFS write support" below. - - There are also a number of user-space tools available, called - ntfsprogs. These include ntfsundelete and ntfsresize, that work - without NTFS support enabled in the kernel. - - This is a rewrite from scratch of Linux NTFS support and replaced - the old NTFS code starting with Linux 2.5.11. A backport to - the Linux 2.4 kernel series is separately available as a patch - from the project web site. - - For more information see <file:Documentation/filesystems/ntfs.txt> - and <http://www.linux-ntfs.org/>. - - To compile this file system support as a module, choose M here: the - module will be called ntfs. - - If you are not using Windows NT, 2000, XP or 2003 in addition to - Linux on your computer it is safe to say N. - -config NTFS_DEBUG - bool "NTFS debugging support" - depends on NTFS_FS - help - If you are experiencing any problems with the NTFS file system, say - Y here. This will result in additional consistency checks to be - performed by the driver as well as additional debugging messages to - be written to the system log. Note that debugging messages are - disabled by default. To enable them, supply the option debug_msgs=1 - at the kernel command line when booting the kernel or as an option - to insmod when loading the ntfs module. Once the driver is active, - you can enable debugging messages by doing (as root): - echo 1 > /proc/sys/fs/ntfs-debug - Replacing the "1" with "0" would disable debug messages. - - If you leave debugging messages disabled, this results in little - overhead, but enabling debug messages results in very significant - slowdown of the system. - - When reporting bugs, please try to have available a full dump of - debugging messages while the misbehaviour was occurring. - -config NTFS_RW - bool "NTFS write support" - depends on NTFS_FS - help - This enables the partial, but safe, write support in the NTFS driver. - - The only supported operation is overwriting existing files, without - changing the file length. No file or directory creation, deletion or - renaming is possible. Note only non-resident files can be written to - so you may find that some very small files (<500 bytes or so) cannot - be written to. - - While we cannot guarantee that it will not damage any data, we have - so far not received a single report where the driver would have - damaged someones data so we assume it is perfectly safe to use. - - Note: While write support is safe in this version (a rewrite from - scratch of the NTFS support), it should be noted that the old NTFS - write support, included in Linux 2.5.10 and before (since 1997), - is not safe. - - This is currently useful with TopologiLinux. TopologiLinux is run - on top of any DOS/Microsoft Windows system without partitioning your - hard disk. Unlike other Linux distributions TopologiLinux does not - need its own partition. For more information see - <http://topologi-linux.sourceforge.net/> - - It is perfectly safe to say N here. +source "fs/fat/Kconfig" +source "fs/ntfs/Kconfig" endmenu endif # BLOCK @@ -662,30 +141,7 @@ endif # BLOCK menu "Pseudo filesystems" source "fs/proc/Kconfig" - -config SYSFS - bool "sysfs file system support" if EMBEDDED - default y - help - The sysfs filesystem is a virtual filesystem that the kernel uses to - export internal kernel objects, their attributes, and their - relationships to one another. - - Users can use sysfs to ascertain useful information about the running - kernel, such as the devices the kernel has discovered on each bus and - which driver each is bound to. sysfs can also be used to tune devices - and other kernel subsystems. - - Some system agents rely on the information in sysfs to operate. - /sbin/hotplug uses device and object attributes in sysfs to assist in - delegating policy decisions, like persistently naming devices. - - sysfs is currently used by the block subsystem to mount the root - partition. If sysfs is disabled you must specify the boot device on - the kernel boot command line via its major and minor numbers. For - example, "root=03:01" for /dev/hda1. - - Designers of embedded systems may wish to say N here to conserve space. +source "fs/sysfs/Kconfig" config TMPFS bool "Virtual memory file system support (former shm fs)" @@ -726,17 +182,7 @@ config HUGETLBFS config HUGETLB_PAGE def_bool HUGETLBFS -config CONFIGFS_FS - tristate "Userspace-driven configuration filesystem" - depends on SYSFS - help - configfs is a ram-based filesystem that provides the converse - of sysfs's functionality. Where sysfs is a filesystem-based - view of kernel objects, configfs is a filesystem-based manager - of kernel objects, or config_items. - - Both sysfs and configfs can and should exist together on the - same system. One is not a replacement for the other. +source "fs/configfs/Kconfig" endmenu @@ -755,425 +201,27 @@ menuconfig MISC_FILESYSTEMS if MISC_FILESYSTEMS -config ADFS_FS - tristate "ADFS file system support (EXPERIMENTAL)" - depends on BLOCK && EXPERIMENTAL - help - The Acorn Disc Filing System is the standard file system of the - RiscOS operating system which runs on Acorn's ARM-based Risc PC - systems and the Acorn Archimedes range of machines. If you say Y - here, Linux will be able to read from ADFS partitions on hard drives - and from ADFS-formatted floppy discs. If you also want to be able to - write to those devices, say Y to "ADFS write support" below. - - The ADFS partition should be the first partition (i.e., - /dev/[hs]d?1) on each of your drives. Please read the file - <file:Documentation/filesystems/adfs.txt> for further details. - - To compile this code as a module, choose M here: the module will be - called adfs. - - If unsure, say N. - -config ADFS_FS_RW - bool "ADFS write support (DANGEROUS)" - depends on ADFS_FS - help - If you say Y here, you will be able to write to ADFS partitions on - hard drives and ADFS-formatted floppy disks. This is experimental - codes, so if you're unsure, say N. - -config AFFS_FS - tristate "Amiga FFS file system support (EXPERIMENTAL)" - depends on BLOCK && EXPERIMENTAL - help - The Fast File System (FFS) is the common file system used on hard - disks by Amiga(tm) systems since AmigaOS Version 1.3 (34.20). Say Y - if you want to be able to read and write files from and to an Amiga - FFS partition on your hard drive. Amiga floppies however cannot be - read with this driver due to an incompatibility of the floppy - controller used in an Amiga and the standard floppy controller in - PCs and workstations. Read <file:Documentation/filesystems/affs.txt> - and <file:fs/affs/Changes>. - - With this driver you can also mount disk files used by Bernd - Schmidt's Un*X Amiga Emulator - (<http://www.freiburg.linux.de/~uae/>). - If you want to do this, you will also need to say Y or M to "Loop - device support", above. - - To compile this file system support as a module, choose M here: the - module will be called affs. If unsure, say N. - -config ECRYPT_FS - tristate "eCrypt filesystem layer support (EXPERIMENTAL)" - depends on EXPERIMENTAL && KEYS && CRYPTO && NET - help - Encrypted filesystem that operates on the VFS layer. See - <file:Documentation/filesystems/ecryptfs.txt> to learn more about - eCryptfs. Userspace components are required and can be - obtained from <http://ecryptfs.sf.net>. - - To compile this file system support as a module, choose M here: the - module will be called ecryptfs. - -config HFS_FS - tristate "Apple Macintosh file system support (EXPERIMENTAL)" - depends on BLOCK && EXPERIMENTAL - select NLS - help - If you say Y here, you will be able to mount Macintosh-formatted - floppy disks and hard drive partitions with full read-write access. - Please read <file:Documentation/filesystems/hfs.txt> to learn about - the available mount options. - - To compile this file system support as a module, choose M here: the - module will be called hfs. - -config HFSPLUS_FS - tristate "Apple Extended HFS file system support" - depends on BLOCK - select NLS - select NLS_UTF8 - help - If you say Y here, you will be able to mount extended format - Macintosh-formatted hard drive partitions with full read-write access. - - This file system is often called HFS+ and was introduced with - MacOS 8. It includes all Mac specific filesystem data such as - data forks and creator codes, but it also has several UNIX - style features such as file ownership and permissions. - -config BEFS_FS - tristate "BeOS file system (BeFS) support (read only) (EXPERIMENTAL)" - depends on BLOCK && EXPERIMENTAL - select NLS - help - The BeOS File System (BeFS) is the native file system of Be, Inc's - BeOS. Notable features include support for arbitrary attributes - on files and directories, and database-like indices on selected - attributes. (Also note that this driver doesn't make those features - available at this time). It is a 64 bit filesystem, so it supports - extremely large volumes and files. - - If you use this filesystem, you should also say Y to at least one - of the NLS (native language support) options below. - - If you don't know what this is about, say N. - - To compile this as a module, choose M here: the module will be - called befs. - -config BEFS_DEBUG - bool "Debug BeFS" - depends on BEFS_FS - help - If you say Y here, you can use the 'debug' mount option to enable - debugging output from the driver. - -config BFS_FS - tristate "BFS file system support (EXPERIMENTAL)" - depends on BLOCK && EXPERIMENTAL - help - Boot File System (BFS) is a file system used under SCO UnixWare to - allow the bootloader access to the kernel image and other important - files during the boot process. It is usually mounted under /stand - and corresponds to the slice marked as "STAND" in the UnixWare - partition. You should say Y if you want to read or write the files - on your /stand slice from within Linux. You then also need to say Y - to "UnixWare slices support", below. More information about the BFS - file system is contained in the file - <file:Documentation/filesystems/bfs.txt>. - - If you don't know what this is about, say N. - - To compile this as a module, choose M here: the module will be called - bfs. Note that the file system of your root partition (the one - containing the directory /) cannot be compiled as a module. - - - -config EFS_FS - tristate "EFS file system support (read only) (EXPERIMENTAL)" - depends on BLOCK && EXPERIMENTAL - help - EFS is an older file system used for non-ISO9660 CD-ROMs and hard - disk partitions by SGI's IRIX operating system (IRIX 6.0 and newer - uses the XFS file system for hard disk partitions however). - - This implementation only offers read-only access. If you don't know - what all this is about, it's safe to say N. For more information - about EFS see its home page at <http://aeschi.ch.eu.org/efs/>. - - To compile the EFS file system support as a module, choose M here: the - module will be called efs. - +source "fs/adfs/Kconfig" +source "fs/affs/Kconfig" +source "fs/ecryptfs/Kconfig" +source "fs/hfs/Kconfig" +source "fs/hfsplus/Kconfig" +source "fs/befs/Kconfig" +source "fs/bfs/Kconfig" +source "fs/efs/Kconfig" source "fs/jffs2/Kconfig" # UBIFS File system configuration source "fs/ubifs/Kconfig" - -config CRAMFS - tristate "Compressed ROM file system support (cramfs)" - depends on BLOCK - select ZLIB_INFLATE - help - Saying Y here includes support for CramFs (Compressed ROM File - System). CramFs is designed to be a simple, small, and compressed - file system for ROM based embedded systems. CramFs is read-only, - limited to 256MB file systems (with 16MB files), and doesn't support - 16/32 bits uid/gid, hard links and timestamps. - - See <file:Documentation/filesystems/cramfs.txt> and - <file:fs/cramfs/README> for further information. - - To compile this as a module, choose M here: the module will be called - cramfs. Note that the root file system (the one containing the - directory /) cannot be compiled as a module. - - If unsure, say N. - -config SQUASHFS - tristate "SquashFS 4.0 - Squashed file system support" - depends on BLOCK - select ZLIB_INFLATE - help - Saying Y here includes support for SquashFS 4.0 (a Compressed - Read-Only File System). Squashfs is a highly compressed read-only - filesystem for Linux. It uses zlib compression to compress both - files, inodes and directories. Inodes in the system are very small - and all blocks are packed to minimise data overhead. Block sizes - greater than 4K are supported up to a maximum of 1 Mbytes (default - block size 128K). SquashFS 4.0 supports 64 bit filesystems and files - (larger than 4GB), full uid/gid information, hard links and - timestamps. - - Squashfs is intended for general read-only filesystem use, for - archival use (i.e. in cases where a .tar.gz file may be used), and in - embedded systems where low overhead is needed. Further information - and tools are available from http://squashfs.sourceforge.net. - - If you want to compile this as a module ( = code which can be - inserted in and removed from the running kernel whenever you want), - say M here and read <file:Documentation/modules.txt>. The module - will be called squashfs. Note that the root file system (the one - containing the directory /) cannot be compiled as a module. - - If unsure, say N. - -config SQUASHFS_EMBEDDED - - bool "Additional option for memory-constrained systems" - depends on SQUASHFS - default n - help - Saying Y here allows you to specify cache size. - - If unsure, say N. - -config SQUASHFS_FRAGMENT_CACHE_SIZE - int "Number of fragments cached" if SQUASHFS_EMBEDDED - depends on SQUASHFS - default "3" - help - By default SquashFS caches the last 3 fragments read from - the filesystem. Increasing this amount may mean SquashFS - has to re-read fragments less often from disk, at the expense - of extra system memory. Decreasing this amount will mean - SquashFS uses less memory at the expense of extra reads from disk. - - Note there must be at least one cached fragment. Anything - much more than three will probably not make much difference. - -config VXFS_FS - tristate "FreeVxFS file system support (VERITAS VxFS(TM) compatible)" - depends on BLOCK - help - FreeVxFS is a file system driver that support the VERITAS VxFS(TM) - file system format. VERITAS VxFS(TM) is the standard file system - of SCO UnixWare (and possibly others) and optionally available - for Sunsoft Solaris, HP-UX and many other operating systems. - Currently only readonly access is supported. - - NOTE: the file system type as used by mount(1), mount(2) and - fstab(5) is 'vxfs' as it describes the file system format, not - the actual driver. - - To compile this as a module, choose M here: the module will be - called freevxfs. If unsure, say N. - -config MINIX_FS - tristate "Minix file system support" - depends on BLOCK - help - Minix is a simple operating system used in many classes about OS's. - The minix file system (method to organize files on a hard disk - partition or a floppy disk) was the original file system for Linux, - but has been superseded by the second extended file system ext2fs. - You don't want to use the minix file system on your hard disk - because of certain built-in restrictions, but it is sometimes found - on older Linux floppy disks. This option will enlarge your kernel - by about 28 KB. If unsure, say N. - - To compile this file system support as a module, choose M here: the - module will be called minix. Note that the file system of your root - partition (the one containing the directory /) cannot be compiled as - a module. - -config OMFS_FS - tristate "SonicBlue Optimized MPEG File System support" - depends on BLOCK - select CRC_ITU_T - help - This is the proprietary file system used by the Rio Karma music - player and ReplayTV DVR. Despite the name, this filesystem is not - more efficient than a standard FS for MPEG files, in fact likely - the opposite is true. Say Y if you have either of these devices - and wish to mount its disk. - - To compile this file system support as a module, choose M here: the - module will be called omfs. If unsure, say N. - -config HPFS_FS - tristate "OS/2 HPFS file system support" - depends on BLOCK - help - OS/2 is IBM's operating system for PC's, the same as Warp, and HPFS - is the file system used for organizing files on OS/2 hard disk - partitions. Say Y if you want to be able to read files from and - write files to an OS/2 HPFS partition on your hard drive. OS/2 - floppies however are in regular MSDOS format, so you don't need this - option in order to be able to read them. Read - <file:Documentation/filesystems/hpfs.txt>. - - To compile this file system support as a module, choose M here: the - module will be called hpfs. If unsure, say N. - - -config QNX4FS_FS - tristate "QNX4 file system support (read only)" - depends on BLOCK - help - This is the file system used by the real-time operating systems - QNX 4 and QNX 6 (the latter is also called QNX RTP). - Further information is available at <http://www.qnx.com/>. - Say Y if you intend to mount QNX hard disks or floppies. - Unless you say Y to "QNX4FS read-write support" below, you will - only be able to read these file systems. - - To compile this file system support as a module, choose M here: the - module will be called qnx4. - - If you don't know whether you need it, then you don't need it: - answer N. - -config QNX4FS_RW - bool "QNX4FS write support (DANGEROUS)" - depends on QNX4FS_FS && EXPERIMENTAL && BROKEN - help - Say Y if you want to test write support for QNX4 file systems. - - It's currently broken, so for now: - answer N. - -config ROMFS_FS - tristate "ROM file system support" - depends on BLOCK - ---help--- - This is a very small read-only file system mainly intended for - initial ram disks of installation disks, but it could be used for - other read-only media as well. Read - <file:Documentation/filesystems/romfs.txt> for details. - - To compile this file system support as a module, choose M here: the - module will be called romfs. Note that the file system of your - root partition (the one containing the directory /) cannot be a - module. - - If you don't know whether you need it, then you don't need it: - answer N. - - -config SYSV_FS - tristate "System V/Xenix/V7/Coherent file system support" - depends on BLOCK - help - SCO, Xenix and Coherent are commercial Unix systems for Intel - machines, and Version 7 was used on the DEC PDP-11. Saying Y - here would allow you to read from their floppies and hard disk - partitions. - - If you have floppies or hard disk partitions like that, it is likely - that they contain binaries from those other Unix systems; in order - to run these binaries, you will want to install linux-abi which is - a set of kernel modules that lets you run SCO, Xenix, Wyse, - UnixWare, Dell Unix and System V programs under Linux. It is - available via FTP (user: ftp) from - <ftp://ftp.openlinux.org/pub/people/hch/linux-abi/>). - NOTE: that will work only for binaries from Intel-based systems; - PDP ones will have to wait until somebody ports Linux to -11 ;-) - - If you only intend to mount files from some other Unix over the - network using NFS, you don't need the System V file system support - (but you need NFS file system support obviously). - - Note that this option is generally not needed for floppies, since a - good portable way to transport files and directories between unixes - (and even other operating systems) is given by the tar program ("man - tar" or preferably "info tar"). Note also that this option has - nothing whatsoever to do with the option "System V IPC". Read about - the System V file system in - <file:Documentation/filesystems/sysv-fs.txt>. - Saying Y here will enlarge your kernel by about 27 KB. - - To compile this as a module, choose M here: the module will be called - sysv. - - If you haven't heard about all of this before, it's safe to say N. - - -config UFS_FS - tristate "UFS file system support (read only)" - depends on BLOCK - help - BSD and derivate versions of Unix (such as SunOS, FreeBSD, NetBSD, - OpenBSD and NeXTstep) use a file system called UFS. Some System V - Unixes can create and mount hard disk partitions and diskettes using - this file system as well. Saying Y here will allow you to read from - these partitions; if you also want to write to them, say Y to the - experimental "UFS file system write support", below. Please read the - file <file:Documentation/filesystems/ufs.txt> for more information. - - The recently released UFS2 variant (used in FreeBSD 5.x) is - READ-ONLY supported. - - Note that this option is generally not needed for floppies, since a - good portable way to transport files and directories between unixes - (and even other operating systems) is given by the tar program ("man - tar" or preferably "info tar"). - - When accessing NeXTstep files, you may need to convert them from the - NeXT character set to the Latin1 character set; use the program - recode ("info recode") for this purpose. - - To compile the UFS file system support as a module, choose M here: the - module will be called ufs. - - If you haven't heard about all of this before, it's safe to say N. - -config UFS_FS_WRITE - bool "UFS file system write support (DANGEROUS)" - depends on UFS_FS && EXPERIMENTAL - help - Say Y here if you want to try writing to UFS partitions. This is - experimental, so you should back up your UFS partitions beforehand. - -config UFS_DEBUG - bool "UFS debugging" - depends on UFS_FS - help - If you are experiencing any problems with the UFS filesystem, say - Y here. This will result in _many_ additional debugging messages to be - written to the system log. +source "fs/cramfs/Kconfig" +source "fs/squashfs/Kconfig" +source "fs/freevxfs/Kconfig" +source "fs/minix/Kconfig" +source "fs/omfs/Kconfig" +source "fs/hpfs/Kconfig" +source "fs/qnx4/Kconfig" +source "fs/romfs/Kconfig" +source "fs/sysv/Kconfig" +source "fs/ufs/Kconfig" endif # MISC_FILESYSTEMS @@ -1193,173 +241,8 @@ menuconfig NETWORK_FILESYSTEMS if NETWORK_FILESYSTEMS -config NFS_FS - tristate "NFS client support" - depends on INET - select LOCKD - select SUNRPC - select NFS_ACL_SUPPORT if NFS_V3_ACL - help - Choose Y here if you want to access files residing on other - computers using Sun's Network File System protocol. To compile - this file system support as a module, choose M here: the module - will be called nfs. - - To mount file systems exported by NFS servers, you also need to - install the user space mount.nfs command which can be found in - the Linux nfs-utils package, available from http://linux-nfs.org/. - Information about using the mount command is available in the - mount(8) man page. More detail about the Linux NFS client - implementation is available via the nfs(5) man page. - - Below you can choose which versions of the NFS protocol are - available in the kernel to mount NFS servers. Support for NFS - version 2 (RFC 1094) is always available when NFS_FS is selected. - - To configure a system which mounts its root file system via NFS - at boot time, say Y here, select "Kernel level IP - autoconfiguration" in the NETWORK menu, and select "Root file - system on NFS" below. You cannot compile this file system as a - module in this case. - - If unsure, say N. - -config NFS_V3 - bool "NFS client support for NFS version 3" - depends on NFS_FS - help - This option enables support for version 3 of the NFS protocol - (RFC 1813) in the kernel's NFS client. - - If unsure, say Y. - -config NFS_V3_ACL - bool "NFS client support for the NFSv3 ACL protocol extension" - depends on NFS_V3 - help - Some NFS servers support an auxiliary NFSv3 ACL protocol that - Sun added to Solaris but never became an official part of the - NFS version 3 protocol. This protocol extension allows - applications on NFS clients to manipulate POSIX Access Control - Lists on files residing on NFS servers. NFS servers enforce - ACLs on local files whether this protocol is available or not. - - Choose Y here if your NFS server supports the Solaris NFSv3 ACL - protocol extension and you want your NFS client to allow - applications to access and modify ACLs on files on the server. - - Most NFS servers don't support the Solaris NFSv3 ACL protocol - extension. You can choose N here or specify the "noacl" mount - option to prevent your NFS client from trying to use the NFSv3 - ACL protocol. - - If unsure, say N. - -config NFS_V4 - bool "NFS client support for NFS version 4 (EXPERIMENTAL)" - depends on NFS_FS && EXPERIMENTAL - select RPCSEC_GSS_KRB5 - help - This option enables support for version 4 of the NFS protocol - (RFC 3530) in the kernel's NFS client. - - To mount NFS servers using NFSv4, you also need to install user - space programs which can be found in the Linux nfs-utils package, - available from http://linux-nfs.org/. - - If unsure, say N. - -config ROOT_NFS - bool "Root file system on NFS" - depends on NFS_FS=y && IP_PNP - help - If you want your system to mount its root file system via NFS, - choose Y here. This is common practice for managing systems - without local permanent storage. For details, read - <file:Documentation/filesystems/nfsroot.txt>. - - Most people say N here. - -config NFSD - tristate "NFS server support" - depends on INET - select LOCKD - select SUNRPC - select EXPORTFS - select NFS_ACL_SUPPORT if NFSD_V2_ACL - help - Choose Y here if you want to allow other computers to access - files residing on this system using Sun's Network File System - protocol. To compile the NFS server support as a module, - choose M here: the module will be called nfsd. - - You may choose to use a user-space NFS server instead, in which - case you can choose N here. - - To export local file systems using NFS, you also need to install - user space programs which can be found in the Linux nfs-utils - package, available from http://linux-nfs.org/. More detail about - the Linux NFS server implementation is available via the - exports(5) man page. - - Below you can choose which versions of the NFS protocol are - available to clients mounting the NFS server on this system. - Support for NFS version 2 (RFC 1094) is always available when - CONFIG_NFSD is selected. - - If unsure, say N. - -config NFSD_V2_ACL - bool - depends on NFSD - -config NFSD_V3 - bool "NFS server support for NFS version 3" - depends on NFSD - help - This option enables support in your system's NFS server for - version 3 of the NFS protocol (RFC 1813). - - If unsure, say Y. - -config NFSD_V3_ACL - bool "NFS server support for the NFSv3 ACL protocol extension" - depends on NFSD_V3 - select NFSD_V2_ACL - help - Solaris NFS servers support an auxiliary NFSv3 ACL protocol that - never became an official part of the NFS version 3 protocol. - This protocol extension allows applications on NFS clients to - manipulate POSIX Access Control Lists on files residing on NFS - servers. NFS servers enforce POSIX ACLs on local files whether - this protocol is available or not. - - This option enables support in your system's NFS server for the - NFSv3 ACL protocol extension allowing NFS clients to manipulate - POSIX ACLs on files exported by your system's NFS server. NFS - clients which support the Solaris NFSv3 ACL protocol can then - access and modify ACLs on your NFS server. - - To store ACLs on your NFS server, you also need to enable ACL- - related CONFIG options for your local file systems of choice. - - If unsure, say N. - -config NFSD_V4 - bool "NFS server support for NFS version 4 (EXPERIMENTAL)" - depends on NFSD && PROC_FS && EXPERIMENTAL - select NFSD_V3 - select FS_POSIX_ACL - select RPCSEC_GSS_KRB5 - help - This option enables support in your system's NFS server for - version 4 of the NFS protocol (RFC 3530). - - To export files using NFSv4, you need to install additional user - space programs which can be found in the Linux nfs-utils package, - available from http://linux-nfs.org/. - - If unsure, say N. +source "fs/nfs/Kconfig" +source "fs/nfsd/Kconfig" config LOCKD tristate @@ -1381,221 +264,13 @@ config NFS_COMMON depends on NFSD || NFS_FS default y -config SUNRPC - tristate - -config SUNRPC_GSS - tristate - -config SUNRPC_XPRT_RDMA - tristate - depends on SUNRPC && INFINIBAND && EXPERIMENTAL - default SUNRPC && INFINIBAND - help - This option enables an RPC client transport capability that - allows the NFS client to mount servers via an RDMA-enabled - transport. - - To compile RPC client RDMA transport support as a module, - choose M here: the module will be called xprtrdma. - - If unsure, say N. - -config SUNRPC_REGISTER_V4 - bool "Register local RPC services via rpcbind v4 (EXPERIMENTAL)" - depends on SUNRPC && EXPERIMENTAL - default n - help - Sun added support for registering RPC services at an IPv6 - address by creating two new versions of the rpcbind protocol - (RFC 1833). - - This option enables support in the kernel RPC server for - registering kernel RPC services via version 4 of the rpcbind - protocol. If you enable this option, you must run a portmapper - daemon that supports rpcbind protocol version 4. - - Serving NFS over IPv6 from knfsd (the kernel's NFS server) - requires that you enable this option and use a portmapper that - supports rpcbind version 4. - - If unsure, say N to get traditional behavior (register kernel - RPC services using only rpcbind version 2). Distributions - using the legacy Linux portmapper daemon must say N here. - -config RPCSEC_GSS_KRB5 - tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)" - depends on SUNRPC && EXPERIMENTAL - select SUNRPC_GSS - select CRYPTO - select CRYPTO_MD5 - select CRYPTO_DES - select CRYPTO_CBC - help - Choose Y here to enable Secure RPC using the Kerberos version 5 - GSS-API mechanism (RFC 1964). - - Secure RPC calls with Kerberos require an auxiliary user-space - daemon which may be found in the Linux nfs-utils package - available from http://linux-nfs.org/. In addition, user-space - Kerberos support should be installed. - - If unsure, say N. - -config RPCSEC_GSS_SPKM3 - tristate "Secure RPC: SPKM3 mechanism (EXPERIMENTAL)" - depends on SUNRPC && EXPERIMENTAL - select SUNRPC_GSS - select CRYPTO - select CRYPTO_MD5 - select CRYPTO_DES - select CRYPTO_CAST5 - select CRYPTO_CBC - help - Choose Y here to enable Secure RPC using the SPKM3 public key - GSS-API mechansim (RFC 2025). - - Secure RPC calls with SPKM3 require an auxiliary userspace - daemon which may be found in the Linux nfs-utils package - available from http://linux-nfs.org/. - - If unsure, say N. - -config SMB_FS - tristate "SMB file system support (OBSOLETE, please use CIFS)" - depends on INET - select NLS - help - SMB (Server Message Block) is the protocol Windows for Workgroups - (WfW), Windows 95/98, Windows NT and OS/2 Lan Manager use to share - files and printers over local networks. Saying Y here allows you to - mount their file systems (often called "shares" in this context) and - access them just like any other Unix directory. Currently, this - works only if the Windows machines use TCP/IP as the underlying - transport protocol, and not NetBEUI. For details, read - <file:Documentation/filesystems/smbfs.txt> and the SMB-HOWTO, - available from <http://www.tldp.org/docs.html#howto>. - - Note: if you just want your box to act as an SMB *server* and make - files and printing services available to Windows clients (which need - to have a TCP/IP stack), you don't need to say Y here; you can use - the program SAMBA (available from <ftp://ftp.samba.org/pub/samba/>) - for that. - - General information about how to connect Linux, Windows machines and - Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. - - To compile the SMB support as a module, choose M here: - the module will be called smbfs. Most people say N, however. - -config SMB_NLS_DEFAULT - bool "Use a default NLS" - depends on SMB_FS - help - Enabling this will make smbfs use nls translations by default. You - need to specify the local charset (CONFIG_NLS_DEFAULT) in the nls - settings and you need to give the default nls for the SMB server as - CONFIG_SMB_NLS_REMOTE. - - The nls settings can be changed at mount time, if your smbmount - supports that, using the codepage and iocharset parameters. - - smbmount from samba 2.2.0 or later supports this. - -config SMB_NLS_REMOTE - string "Default Remote NLS Option" - depends on SMB_NLS_DEFAULT - default "cp437" - help - This setting allows you to specify a default value for which - codepage the server uses. If this field is left blank no - translations will be done by default. The local codepage/charset - default to CONFIG_NLS_DEFAULT. - - The nls settings can be changed at mount time, if your smbmount - supports that, using the codepage and iocharset parameters. - - smbmount from samba 2.2.0 or later supports this. - +source "net/sunrpc/Kconfig" +source "fs/smbfs/Kconfig" source "fs/cifs/Kconfig" - -config NCP_FS - tristate "NCP file system support (to mount NetWare volumes)" - depends on IPX!=n || INET - help - NCP (NetWare Core Protocol) is a protocol that runs over IPX and is - used by Novell NetWare clients to talk to file servers. It is to - IPX what NFS is to TCP/IP, if that helps. Saying Y here allows you - to mount NetWare file server volumes and to access them just like - any other Unix directory. For details, please read the file - <file:Documentation/filesystems/ncpfs.txt> in the kernel source and - the IPX-HOWTO from <http://www.tldp.org/docs.html#howto>. - - You do not have to say Y here if you want your Linux box to act as a - file *server* for Novell NetWare clients. - - General information about how to connect Linux, Windows machines and - Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. - - To compile this as a module, choose M here: the module will be called - ncpfs. Say N unless you are connected to a Novell network. - source "fs/ncpfs/Kconfig" - -config CODA_FS - tristate "Coda file system support (advanced network fs)" - depends on INET - help - Coda is an advanced network file system, similar to NFS in that it - enables you to mount file systems of a remote server and access them - with regular Unix commands as if they were sitting on your hard - disk. Coda has several advantages over NFS: support for - disconnected operation (e.g. for laptops), read/write server - replication, security model for authentication and encryption, - persistent client caches and write back caching. - - If you say Y here, your Linux box will be able to act as a Coda - *client*. You will need user level code as well, both for the - client and server. Servers are currently user level, i.e. they need - no kernel support. Please read - <file:Documentation/filesystems/coda.txt> and check out the Coda - home page <http://www.coda.cs.cmu.edu/>. - - To compile the coda client support as a module, choose M here: the - module will be called coda. - -config AFS_FS - tristate "Andrew File System support (AFS) (EXPERIMENTAL)" - depends on INET && EXPERIMENTAL - select AF_RXRPC - help - If you say Y here, you will get an experimental Andrew File System - driver. It currently only supports unsecured read-only AFS access. - - See <file:Documentation/filesystems/afs.txt> for more information. - - If unsure, say N. - -config AFS_DEBUG - bool "AFS dynamic debugging" - depends on AFS_FS - help - Say Y here to make runtime controllable debugging messages appear. - - See <file:Documentation/filesystems/afs.txt> for more information. - - If unsure, say N. - -config 9P_FS - tristate "Plan 9 Resource Sharing Support (9P2000) (Experimental)" - depends on INET && NET_9P && EXPERIMENTAL - help - If you say Y here, you will get experimental support for - Plan 9 resource sharing via the 9P2000 protocol. - - See <http://v9fs.sf.net> for more information. - - If unsure, say N. +source "fs/coda/Kconfig" +source "fs/afs/Kconfig" +source "fs/9p/Kconfig" endif # NETWORK_FILESYSTEMS diff --git a/fs/adfs/Kconfig b/fs/adfs/Kconfig new file mode 100644 index 00000000000..e55182a7460 --- /dev/null +++ b/fs/adfs/Kconfig @@ -0,0 +1,27 @@ +config ADFS_FS + tristate "ADFS file system support (EXPERIMENTAL)" + depends on BLOCK && EXPERIMENTAL + help + The Acorn Disc Filing System is the standard file system of the + RiscOS operating system which runs on Acorn's ARM-based Risc PC + systems and the Acorn Archimedes range of machines. If you say Y + here, Linux will be able to read from ADFS partitions on hard drives + and from ADFS-formatted floppy discs. If you also want to be able to + write to those devices, say Y to "ADFS write support" below. + + The ADFS partition should be the first partition (i.e., + /dev/[hs]d?1) on each of your drives. Please read the file + <file:Documentation/filesystems/adfs.txt> for further details. + + To compile this code as a module, choose M here: the module will be + called adfs. + + If unsure, say N. + +config ADFS_FS_RW + bool "ADFS write support (DANGEROUS)" + depends on ADFS_FS + help + If you say Y here, you will be able to write to ADFS partitions on + hard drives and ADFS-formatted floppy disks. This is experimental + codes, so if you're unsure, say N. diff --git a/fs/affs/Kconfig b/fs/affs/Kconfig new file mode 100644 index 00000000000..cfad9afb476 --- /dev/null +++ b/fs/affs/Kconfig @@ -0,0 +1,21 @@ +config AFFS_FS + tristate "Amiga FFS file system support (EXPERIMENTAL)" + depends on BLOCK && EXPERIMENTAL + help + The Fast File System (FFS) is the common file system used on hard + disks by Amiga(tm) systems since AmigaOS Version 1.3 (34.20). Say Y + if you want to be able to read and write files from and to an Amiga + FFS partition on your hard drive. Amiga floppies however cannot be + read with this driver due to an incompatibility of the floppy + controller used in an Amiga and the standard floppy controller in + PCs and workstations. Read <file:Documentation/filesystems/affs.txt> + and <file:fs/affs/Changes>. + + With this driver you can also mount disk files used by Bernd + Schmidt's Un*X Amiga Emulator + (<http://www.freiburg.linux.de/~uae/>). + If you want to do this, you will also need to say Y or M to "Loop + device support", above. + + To compile this file system support as a module, choose M here: the + module will be called affs. If unsure, say N. diff --git a/fs/afs/Kconfig b/fs/afs/Kconfig new file mode 100644 index 00000000000..e7b522fe15e --- /dev/null +++ b/fs/afs/Kconfig @@ -0,0 +1,21 @@ +config AFS_FS + tristate "Andrew File System support (AFS) (EXPERIMENTAL)" + depends on INET && EXPERIMENTAL + select AF_RXRPC + help + If you say Y here, you will get an experimental Andrew File System + driver. It currently only supports unsecured read-only AFS access. + + See <file:Documentation/filesystems/afs.txt> for more information. + + If unsure, say N. + +config AFS_DEBUG + bool "AFS dynamic debugging" + depends on AFS_FS + help + Say Y here to make runtime controllable debugging messages appear. + + See <file:Documentation/filesystems/afs.txt> for more information. + + If unsure, say N. @@ -1270,7 +1270,7 @@ static void io_destroy(struct kioctx *ioctx) * pointer is passed for ctxp. Will fail with -ENOSYS if not * implemented. */ -asmlinkage long sys_io_setup(unsigned nr_events, aio_context_t __user *ctxp) +SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp) { struct kioctx *ioctx = NULL; unsigned long ctx; @@ -1308,7 +1308,7 @@ out: * implemented. May fail with -EFAULT if the context pointed to * is invalid. */ -asmlinkage long sys_io_destroy(aio_context_t ctx) +SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) { struct kioctx *ioctx = lookup_ioctx(ctx); if (likely(NULL != ioctx)) { @@ -1662,8 +1662,8 @@ out_put_req: * are available to queue any iocbs. Will return 0 if nr is 0. Will * fail with -ENOSYS if not implemented. */ -asmlinkage long sys_io_submit(aio_context_t ctx_id, long nr, - struct iocb __user * __user *iocbpp) +SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr, + struct iocb __user * __user *, iocbpp) { struct kioctx *ctx; long ret = 0; @@ -1737,8 +1737,8 @@ static struct kiocb *lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb, * invalid. May fail with -EAGAIN if the iocb specified was not * cancelled. Will fail with -ENOSYS if not implemented. */ -asmlinkage long sys_io_cancel(aio_context_t ctx_id, struct iocb __user *iocb, - struct io_event __user *result) +SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, + struct io_event __user *, result) { int (*cancel)(struct kiocb *iocb, struct io_event *res); struct kioctx *ctx; @@ -1799,11 +1799,11 @@ asmlinkage long sys_io_cancel(aio_context_t ctx_id, struct iocb __user *iocb, * will be updated if not NULL and the operation blocks. Will fail * with -ENOSYS if not implemented. */ -asmlinkage long sys_io_getevents(aio_context_t ctx_id, - long min_nr, - long nr, - struct io_event __user *events, - struct timespec __user *timeout) +SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id, + long, min_nr, + long, nr, + struct io_event __user *, events, + struct timespec __user *, timeout) { struct kioctx *ioctx = lookup_ioctx(ctx_id); long ret = -EINVAL; diff --git a/fs/autofs/Kconfig b/fs/autofs/Kconfig new file mode 100644 index 00000000000..5f3bea90911 --- /dev/null +++ b/fs/autofs/Kconfig @@ -0,0 +1,21 @@ +config AUTOFS_FS + tristate "Kernel automounter support" + help + The automounter is a tool to automatically mount remote file systems + on demand. This implementation is partially kernel-based to reduce + overhead in the already-mounted case; this is unlike the BSD + automounter (amd), which is a pure user space daemon. + + To use the automounter you need the user-space tools from the autofs + package; you can find the location in <file:Documentation/Changes>. + You also want to answer Y to "NFS file system support", below. + + If you want to use the newer version of the automounter with more + features, say N here and say Y to "Kernel automounter v4 support", + below. + + To compile this support as a module, choose M here: the module will be + called autofs. + + If you are not a part of a fairly large, distributed network, you + probably do not need an automounter, and can say N here. diff --git a/fs/autofs4/Kconfig b/fs/autofs4/Kconfig new file mode 100644 index 00000000000..1204d6384d3 --- /dev/null +++ b/fs/autofs4/Kconfig @@ -0,0 +1,20 @@ +config AUTOFS4_FS + tristate "Kernel automounter version 4 support (also supports v3)" + help + The automounter is a tool to automatically mount remote file systems + on demand. This implementation is partially kernel-based to reduce + overhead in the already-mounted case; this is unlike the BSD + automounter (amd), which is a pure user space daemon. + + To use the automounter you need the user-space tools from + <ftp://ftp.kernel.org/pub/linux/daemons/autofs/v4/>; you also + want to answer Y to "NFS file system support", below. + + To compile this support as a module, choose M here: the module will be + called autofs4. You will need to add "alias autofs autofs4" to your + modules configuration file. + + If you are not a part of a fairly large, distributed network or + don't have a laptop which needs to dynamically reconfigure to the + local network, you probably do not need an automounter, and can say + N here. diff --git a/fs/befs/Kconfig b/fs/befs/Kconfig new file mode 100644 index 00000000000..7835d30f211 --- /dev/null +++ b/fs/befs/Kconfig @@ -0,0 +1,26 @@ +config BEFS_FS + tristate "BeOS file system (BeFS) support (read only) (EXPERIMENTAL)" + depends on BLOCK && EXPERIMENTAL + select NLS + help + The BeOS File System (BeFS) is the native file system of Be, Inc's + BeOS. Notable features include support for arbitrary attributes + on files and directories, and database-like indices on selected + attributes. (Also note that this driver doesn't make those features + available at this time). It is a 64 bit filesystem, so it supports + extremely large volumes and files. + + If you use this filesystem, you should also say Y to at least one + of the NLS (native language support) options below. + + If you don't know what this is about, say N. + + To compile this as a module, choose M here: the module will be + called befs. + +config BEFS_DEBUG + bool "Debug BeFS" + depends on BEFS_FS + help + If you say Y here, you can use the 'debug' mount option to enable + debugging output from the driver. diff --git a/fs/bfs/Kconfig b/fs/bfs/Kconfig new file mode 100644 index 00000000000..c2336c62024 --- /dev/null +++ b/fs/bfs/Kconfig @@ -0,0 +1,19 @@ +config BFS_FS + tristate "BFS file system support (EXPERIMENTAL)" + depends on BLOCK && EXPERIMENTAL + help + Boot File System (BFS) is a file system used under SCO UnixWare to + allow the bootloader access to the kernel image and other important + files during the boot process. It is usually mounted under /stand + and corresponds to the slice marked as "STAND" in the UnixWare + partition. You should say Y if you want to read or write the files + on your /stand slice from within Linux. You then also need to say Y + to "UnixWare slices support", below. More information about the BFS + file system is contained in the file + <file:Documentation/filesystems/bfs.txt>. + + If you don't know what this is about, say N. + + To compile this as a module, choose M here: the module will be called + bfs. Note that the file system of your root partition (the one + containing the directory /) cannot be compiled as a module. diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index 77ebc3c263d..549b0144da1 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -140,7 +140,6 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, iv = bip_vec_idx(bip, bip->bip_vcnt); BUG_ON(iv == NULL); - BUG_ON(iv->bv_page != NULL); iv->bv_page = page; iv->bv_len = len; @@ -465,7 +464,7 @@ static int bio_integrity_verify(struct bio *bio) if (ret) { kunmap_atomic(kaddr, KM_USER0); - break; + return ret; } sectors = bv->bv_len / bi->sector_size; @@ -493,18 +492,13 @@ static void bio_integrity_verify_fn(struct work_struct *work) struct bio_integrity_payload *bip = container_of(work, struct bio_integrity_payload, bip_work); struct bio *bio = bip->bip_bio; - int error = bip->bip_error; + int error; - if (bio_integrity_verify(bio)) { - clear_bit(BIO_UPTODATE, &bio->bi_flags); - error = -EIO; - } + error = bio_integrity_verify(bio); /* Restore original bio completion handler */ bio->bi_end_io = bip->bip_end_io; - - if (bio->bi_end_io) - bio->bi_end_io(bio, error); + bio_endio(bio, error); } /** @@ -525,7 +519,17 @@ void bio_integrity_endio(struct bio *bio, int error) BUG_ON(bip->bip_bio != bio); - bip->bip_error = error; + /* In case of an I/O error there is no point in verifying the + * integrity metadata. Restore original bio end_io handler + * and run it. + */ + if (error) { + bio->bi_end_io = bip->bip_end_io; + bio_endio(bio, error); + + return; + } + INIT_WORK(&bip->bip_work, bio_integrity_verify_fn); queue_work(kintegrityd_wq, &bip->bip_work); } diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig new file mode 100644 index 00000000000..f8fcf999ea1 --- /dev/null +++ b/fs/btrfs/Kconfig @@ -0,0 +1,18 @@ +config BTRFS_FS + tristate "Btrfs filesystem (EXPERIMENTAL) Unstable disk format" + depends on EXPERIMENTAL + select LIBCRC32C + select ZLIB_INFLATE + select ZLIB_DEFLATE + help + Btrfs is a new filesystem with extents, writable snapshotting, + support for multiple devices and many more features. + + Btrfs is highly experimental, and THE DISK FORMAT IS NOT YET + FINALIZED. You should say N here unless you are interested in + testing Btrfs with non-critical data. + + To compile this file system support as a module, choose M here. The + module will be called btrfs. + + If unsure, say N. diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 78049ea208d..b320b103fa1 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -22,13 +22,20 @@ #define BTRFS_IOCTL_MAGIC 0x94 #define BTRFS_VOL_NAME_MAX 255 -#define BTRFS_PATH_NAME_MAX 3072 +#define BTRFS_PATH_NAME_MAX 4087 +/* this should be 4k */ struct btrfs_ioctl_vol_args { __s64 fd; char name[BTRFS_PATH_NAME_MAX + 1]; }; +struct btrfs_ioctl_clone_range_args { + __s64 src_fd; + __u64 src_offset, src_length; + __u64 dest_offset; +}; + #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \ struct btrfs_ioctl_vol_args) #define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \ @@ -52,11 +59,6 @@ struct btrfs_ioctl_vol_args { struct btrfs_ioctl_vol_args) #define BTRFS_IOC_BALANCE _IOW(BTRFS_IOCTL_MAGIC, 12, \ struct btrfs_ioctl_vol_args) -struct btrfs_ioctl_clone_range_args { - __s64 src_fd; - __u64 src_offset, src_length; - __u64 dest_offset; -}; #define BTRFS_IOC_CLONE_RANGE _IOW(BTRFS_IOCTL_MAGIC, 13, \ struct btrfs_ioctl_clone_range_args) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0a14b495532..db9fb3bc1e3 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -38,6 +38,7 @@ #include <linux/namei.h> #include <linux/miscdevice.h> #include <linux/version.h> +#include <linux/magic.h> #include "compat.h" #include "ctree.h" #include "disk-io.h" @@ -51,7 +52,6 @@ #include "export.h" #include "compression.h" -#define BTRFS_SUPER_MAGIC 0x9123683E static struct super_operations btrfs_super_ops; @@ -582,7 +582,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, { struct btrfs_ioctl_vol_args *vol; struct btrfs_fs_devices *fs_devices; - int ret = 0; + int ret = -ENOTTY; int len; if (!capable(CAP_SYS_ADMIN)) @@ -594,6 +594,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, goto out; } len = strnlen(vol->name, BTRFS_PATH_NAME_MAX); + switch (cmd) { case BTRFS_IOC_SCAN_DEV: ret = btrfs_scan_one_device(vol->name, FMODE_READ, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b187b537888..3451e1cca2b 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -220,6 +220,7 @@ loop: tail->bi_next = old_head; else device->pending_bio_tail = tail; + device->running_pending = 0; spin_unlock(&device->io_lock); btrfs_requeue_work(&device->work); diff --git a/fs/buffer.c b/fs/buffer.c index b6e8b8632e2..b58208f1640 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3243,7 +3243,7 @@ void block_sync_page(struct page *page) * Use of bdflush() is deprecated and will be removed in a future kernel. * The `pdflush' kernel threads fully replace bdflush daemons and this call. */ -asmlinkage long sys_bdflush(int func, long data) +SYSCALL_DEFINE2(bdflush, int, func, long, data) { static int msg_count; diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index 080703a15f4..73ac7ebd1df 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -5,7 +5,9 @@ rather than posix (advisory) byte range locks, even though server would support posix byte range locks. Fix query of root inode when prefixpath specified and user does not have access to query information about the top of the share. Fix problem in 2.6.28 resolving DFS paths to -Samba servers (worked to Windows). +Samba servers (worked to Windows). Fix rmdir so that pending search +(readdir) requests do not get invalid results which include the now +removed directory. Version 1.55 ------------ diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index d4839cf0cb2..7c9809523f4 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -48,11 +48,11 @@ static int cifs_calculate_signature(const struct smb_hdr *cifs_pdu, if ((cifs_pdu == NULL) || (signature == NULL) || (key == NULL)) return -EINVAL; - MD5Init(&context); - MD5Update(&context, (char *)&key->data, key->len); - MD5Update(&context, cifs_pdu->Protocol, cifs_pdu->smb_buf_length); + cifs_MD5_init(&context); + cifs_MD5_update(&context, (char *)&key->data, key->len); + cifs_MD5_update(&context, cifs_pdu->Protocol, cifs_pdu->smb_buf_length); - MD5Final(signature, &context); + cifs_MD5_final(signature, &context); return 0; } @@ -96,8 +96,8 @@ static int cifs_calc_signature2(const struct kvec *iov, int n_vec, if ((iov == NULL) || (signature == NULL) || (key == NULL)) return -EINVAL; - MD5Init(&context); - MD5Update(&context, (char *)&key->data, key->len); + cifs_MD5_init(&context); + cifs_MD5_update(&context, (char *)&key->data, key->len); for (i = 0; i < n_vec; i++) { if (iov[i].iov_len == 0) continue; @@ -110,13 +110,13 @@ static int cifs_calc_signature2(const struct kvec *iov, int n_vec, if (i == 0) { if (iov[0].iov_len <= 8) /* cmd field at offset 9 */ break; /* nothing to sign or corrupt header */ - MD5Update(&context, iov[0].iov_base+4, + cifs_MD5_update(&context, iov[0].iov_base+4, iov[0].iov_len-4); } else - MD5Update(&context, iov[i].iov_base, iov[i].iov_len); + cifs_MD5_update(&context, iov[i].iov_base, iov[i].iov_len); } - MD5Final(signature, &context); + cifs_MD5_final(signature, &context); return 0; } diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 06f6779988b..382ba629880 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -35,8 +35,8 @@ extern struct smb_hdr *cifs_buf_get(void); extern void cifs_buf_release(void *); extern struct smb_hdr *cifs_small_buf_get(void); extern void cifs_small_buf_release(void *); -extern int smb_send(struct socket *, struct smb_hdr *, - unsigned int /* length */ , struct sockaddr *, bool); +extern int smb_send(struct TCP_Server_Info *, struct smb_hdr *, + unsigned int /* length */); extern unsigned int _GetXid(void); extern void _FreeXid(unsigned int); #define GetXid() (int)_GetXid(); cFYI(1,("CIFS VFS: in %s as Xid: %d with uid: %d",__func__, xid,current_fsuid())); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index e9ea394ee07..2209be94305 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1354,7 +1354,7 @@ cifs_parse_mount_options(char *options, const char *devname, } static struct TCP_Server_Info * -cifs_find_tcp_session(struct sockaddr *addr) +cifs_find_tcp_session(struct sockaddr_storage *addr) { struct list_head *tmp; struct TCP_Server_Info *server; @@ -1374,11 +1374,11 @@ cifs_find_tcp_session(struct sockaddr *addr) if (server->tcpStatus == CifsNew) continue; - if (addr->sa_family == AF_INET && + if (addr->ss_family == AF_INET && (addr4->sin_addr.s_addr != server->addr.sockAddr.sin_addr.s_addr)) continue; - else if (addr->sa_family == AF_INET6 && + else if (addr->ss_family == AF_INET6 && memcmp(&server->addr.sockAddr6.sin6_addr, &addr6->sin6_addr, sizeof(addr6->sin6_addr))) continue; @@ -1419,12 +1419,12 @@ static struct TCP_Server_Info * cifs_get_tcp_session(struct smb_vol *volume_info) { struct TCP_Server_Info *tcp_ses = NULL; - struct sockaddr addr; + struct sockaddr_storage addr; struct sockaddr_in *sin_server = (struct sockaddr_in *) &addr; struct sockaddr_in6 *sin_server6 = (struct sockaddr_in6 *) &addr; int rc; - memset(&addr, 0, sizeof(struct sockaddr)); + memset(&addr, 0, sizeof(struct sockaddr_storage)); if (volume_info->UNCip && volume_info->UNC) { rc = cifs_inet_pton(AF_INET, volume_info->UNCip, @@ -1435,9 +1435,9 @@ cifs_get_tcp_session(struct smb_vol *volume_info) rc = cifs_inet_pton(AF_INET6, volume_info->UNCip, &sin_server6->sin6_addr.in6_u); if (rc > 0) - addr.sa_family = AF_INET6; + addr.ss_family = AF_INET6; } else { - addr.sa_family = AF_INET; + addr.ss_family = AF_INET; } if (rc <= 0) { @@ -1502,7 +1502,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info) tcp_ses->tcpStatus = CifsNew; ++tcp_ses->srv_count; - if (addr.sa_family == AF_INET6) { + if (addr.ss_family == AF_INET6) { cFYI(1, ("attempting ipv6 connect")); /* BB should we allow ipv6 on port 139? */ /* other OS never observed in Wild doing 139 with v6 */ @@ -1802,7 +1802,7 @@ ipv4_connect(struct TCP_Server_Info *server) * user space buffer */ socket->sk->sk_rcvtimeo = 7 * HZ; - socket->sk->sk_sndtimeo = 3 * HZ; + socket->sk->sk_sndtimeo = 5 * HZ; /* make the bufsizes depend on wsize/rsize and max requests */ if (server->noautotune) { @@ -1860,9 +1860,7 @@ ipv4_connect(struct TCP_Server_Info *server) smb_buf = (struct smb_hdr *)ses_init_buf; /* sizeof RFC1002_SESSION_REQUEST with no scope */ smb_buf->smb_buf_length = 0x81000044; - rc = smb_send(socket, smb_buf, 0x44, - (struct sockaddr *) &server->addr.sockAddr, - server->noblocksnd); + rc = smb_send(server, smb_buf, 0x44); kfree(ses_init_buf); msleep(1); /* RFC1001 layer in at least one server requires very short break before negprot @@ -1955,7 +1953,7 @@ ipv6_connect(struct TCP_Server_Info *server) * user space buffer */ socket->sk->sk_rcvtimeo = 7 * HZ; - socket->sk->sk_sndtimeo = 3 * HZ; + socket->sk->sk_sndtimeo = 5 * HZ; server->ssocket = socket; return rc; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 838d9c720a5..964aad03c5a 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -129,6 +129,17 @@ cifs_bp_rename_retry: return full_path; } +static void setup_cifs_dentry(struct cifsTconInfo *tcon, + struct dentry *direntry, + struct inode *newinode) +{ + if (tcon->nocase) + direntry->d_op = &cifs_ci_dentry_ops; + else + direntry->d_op = &cifs_dentry_ops; + d_instantiate(direntry, newinode); +} + /* Inode operations in similar order to how they appear in Linux file fs.h */ int @@ -139,14 +150,14 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, int xid; int create_options = CREATE_NOT_DIR; int oplock = 0; + /* BB below access is too much for the mknod to request */ int desiredAccess = GENERIC_READ | GENERIC_WRITE; __u16 fileHandle; struct cifs_sb_info *cifs_sb; - struct cifsTconInfo *pTcon; + struct cifsTconInfo *tcon; char *full_path = NULL; FILE_ALL_INFO *buf = NULL; struct inode *newinode = NULL; - struct cifsFileInfo *pCifsFile = NULL; struct cifsInodeInfo *pCifsInode; int disposition = FILE_OVERWRITE_IF; bool write_only = false; @@ -154,7 +165,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, xid = GetXid(); cifs_sb = CIFS_SB(inode->i_sb); - pTcon = cifs_sb->tcon; + tcon = cifs_sb->tcon; full_path = build_path_from_dentry(direntry); if (full_path == NULL) { @@ -162,6 +173,8 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, return -ENOMEM; } + mode &= ~current->fs->umask; + if (nd && (nd->flags & LOOKUP_OPEN)) { int oflags = nd->intent.open.flags; @@ -196,17 +209,15 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, return -ENOMEM; } - mode &= ~current->fs->umask; - /* * if we're not using unix extensions, see if we need to set * ATTR_READONLY on the create call */ - if (!pTcon->unix_ext && (mode & S_IWUGO) == 0) + if (!tcon->unix_ext && (mode & S_IWUGO) == 0) create_options |= CREATE_OPTION_READONLY; if (cifs_sb->tcon->ses->capabilities & CAP_NT_SMBS) - rc = CIFSSMBOpen(xid, pTcon, full_path, disposition, + rc = CIFSSMBOpen(xid, tcon, full_path, disposition, desiredAccess, create_options, &fileHandle, &oplock, buf, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); @@ -215,7 +226,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, if (rc == -EIO) { /* old server, retry the open legacy style */ - rc = SMBLegacyOpen(xid, pTcon, full_path, disposition, + rc = SMBLegacyOpen(xid, tcon, full_path, disposition, desiredAccess, create_options, &fileHandle, &oplock, buf, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); @@ -225,7 +236,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, } else { /* If Open reported that we actually created a file then we now have to set the mode if possible */ - if ((pTcon->unix_ext) && (oplock & CIFS_CREATE_ACTION)) { + if ((tcon->unix_ext) && (oplock & CIFS_CREATE_ACTION)) { struct cifs_unix_set_info_args args = { .mode = mode, .ctime = NO_CHANGE_64, @@ -244,20 +255,20 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, args.uid = NO_CHANGE_64; args.gid = NO_CHANGE_64; } - CIFSSMBUnixSetInfo(xid, pTcon, full_path, &args, + CIFSSMBUnixSetInfo(xid, tcon, full_path, &args, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); } else { /* BB implement mode setting via Windows security descriptors e.g. */ - /* CIFSSMBWinSetPerms(xid,pTcon,path,mode,-1,-1,nls);*/ + /* CIFSSMBWinSetPerms(xid,tcon,path,mode,-1,-1,nls);*/ /* Could set r/o dos attribute if mode & 0222 == 0 */ } /* server might mask mode so we have to query for it */ - if (pTcon->unix_ext) + if (tcon->unix_ext) rc = cifs_get_inode_info_unix(&newinode, full_path, inode->i_sb, xid); else { @@ -283,22 +294,17 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, } if (rc != 0) { - cFYI(1, - ("Create worked but get_inode_info failed rc = %d", - rc)); - } else { - if (pTcon->nocase) - direntry->d_op = &cifs_ci_dentry_ops; - else - direntry->d_op = &cifs_dentry_ops; - d_instantiate(direntry, newinode); - } + cFYI(1, ("Create worked, get_inode_info failed rc = %d", + rc)); + } else + setup_cifs_dentry(tcon, direntry, newinode); + if ((nd == NULL /* nfsd case - nfs srv does not set nd */) || (!(nd->flags & LOOKUP_OPEN))) { /* mknod case - do not leave file open */ - CIFSSMBClose(xid, pTcon, fileHandle); + CIFSSMBClose(xid, tcon, fileHandle); } else if (newinode) { - pCifsFile = + struct cifsFileInfo *pCifsFile = kzalloc(sizeof(struct cifsFileInfo), GFP_KERNEL); if (pCifsFile == NULL) @@ -316,7 +322,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, /* set the following in open now pCifsFile->pfile = file; */ write_lock(&GlobalSMBSeslock); - list_add(&pCifsFile->tlist, &pTcon->openFileList); + list_add(&pCifsFile->tlist, &tcon->openFileList); pCifsInode = CIFS_I(newinode); if (pCifsInode) { /* if readable file instance put first in list*/ diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 5ab9896fdcb..bcf7b518466 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1285,6 +1285,11 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) cifsInode = CIFS_I(direntry->d_inode); cifsInode->time = 0; /* force revalidate to go get info when needed */ + + cifsInode = CIFS_I(inode); + cifsInode->time = 0; /* force revalidate to get parent dir info + since cached search results now invalid */ + direntry->d_inode->i_ctime = inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb); diff --git a/fs/cifs/md5.c b/fs/cifs/md5.c index 462bbfefd4b..98b66a54c31 100644 --- a/fs/cifs/md5.c +++ b/fs/cifs/md5.c @@ -10,8 +10,8 @@ * with every copy. * * To compute the message digest of a chunk of bytes, declare an - * MD5Context structure, pass it to MD5Init, call MD5Update as - * needed on buffers full of bytes, and then call MD5Final, which + * MD5Context structure, pass it to cifs_MD5_init, call cifs_MD5_update as + * needed on buffers full of bytes, and then call cifs_MD5_final, which * will fill a supplied 16-byte array with the digest. */ @@ -45,7 +45,7 @@ byteReverse(unsigned char *buf, unsigned longs) * initialization constants. */ void -MD5Init(struct MD5Context *ctx) +cifs_MD5_init(struct MD5Context *ctx) { ctx->buf[0] = 0x67452301; ctx->buf[1] = 0xefcdab89; @@ -61,7 +61,7 @@ MD5Init(struct MD5Context *ctx) * of bytes. */ void -MD5Update(struct MD5Context *ctx, unsigned char const *buf, unsigned len) +cifs_MD5_update(struct MD5Context *ctx, unsigned char const *buf, unsigned len) { register __u32 t; @@ -110,7 +110,7 @@ MD5Update(struct MD5Context *ctx, unsigned char const *buf, unsigned len) * 1 0* (64-bit count of bits processed, MSB-first) */ void -MD5Final(unsigned char digest[16], struct MD5Context *ctx) +cifs_MD5_final(unsigned char digest[16], struct MD5Context *ctx) { unsigned int count; unsigned char *p; @@ -165,7 +165,7 @@ MD5Final(unsigned char digest[16], struct MD5Context *ctx) /* * The core of the MD5 algorithm, this alters an existing MD5 hash to - * reflect the addition of 16 longwords of new data. MD5Update blocks + * reflect the addition of 16 longwords of new data. cifs_MD5_update blocks * the data and converts bytes into longwords for this routine. */ static void @@ -267,9 +267,9 @@ hmac_md5_init_rfc2104(unsigned char *key, int key_len, unsigned char tk[16]; struct MD5Context tctx; - MD5Init(&tctx); - MD5Update(&tctx, key, key_len); - MD5Final(tk, &tctx); + cifs_MD5_init(&tctx); + cifs_MD5_update(&tctx, key, key_len); + cifs_MD5_final(tk, &tctx); key = tk; key_len = 16; @@ -287,8 +287,8 @@ hmac_md5_init_rfc2104(unsigned char *key, int key_len, ctx->k_opad[i] ^= 0x5c; } - MD5Init(&ctx->ctx); - MD5Update(&ctx->ctx, ctx->k_ipad, 64); + cifs_MD5_init(&ctx->ctx); + cifs_MD5_update(&ctx->ctx, ctx->k_ipad, 64); } #endif @@ -317,8 +317,8 @@ hmac_md5_init_limK_to_64(const unsigned char *key, int key_len, ctx->k_opad[i] ^= 0x5c; } - MD5Init(&ctx->ctx); - MD5Update(&ctx->ctx, ctx->k_ipad, 64); + cifs_MD5_init(&ctx->ctx); + cifs_MD5_update(&ctx->ctx, ctx->k_ipad, 64); } /*********************************************************************** @@ -328,7 +328,7 @@ void hmac_md5_update(const unsigned char *text, int text_len, struct HMACMD5Context *ctx) { - MD5Update(&ctx->ctx, text, text_len); /* then text of datagram */ + cifs_MD5_update(&ctx->ctx, text, text_len); /* then text of datagram */ } /*********************************************************************** @@ -339,12 +339,12 @@ hmac_md5_final(unsigned char *digest, struct HMACMD5Context *ctx) { struct MD5Context ctx_o; - MD5Final(digest, &ctx->ctx); + cifs_MD5_final(digest, &ctx->ctx); - MD5Init(&ctx_o); - MD5Update(&ctx_o, ctx->k_opad, 64); - MD5Update(&ctx_o, digest, 16); - MD5Final(digest, &ctx_o); + cifs_MD5_init(&ctx_o); + cifs_MD5_update(&ctx_o, ctx->k_opad, 64); + cifs_MD5_update(&ctx_o, digest, 16); + cifs_MD5_final(digest, &ctx_o); } /*********************************************************** diff --git a/fs/cifs/md5.h b/fs/cifs/md5.h index f7d4f4197ba..6fba8cb402f 100644 --- a/fs/cifs/md5.h +++ b/fs/cifs/md5.h @@ -20,10 +20,10 @@ struct HMACMD5Context { }; #endif /* _HMAC_MD5_H */ -void MD5Init(struct MD5Context *context); -void MD5Update(struct MD5Context *context, unsigned char const *buf, +void cifs_MD5_init(struct MD5Context *context); +void cifs_MD5_update(struct MD5Context *context, unsigned char const *buf, unsigned len); -void MD5Final(unsigned char digest[16], struct MD5Context *context); +void cifs_MD5_final(unsigned char digest[16], struct MD5Context *context); /* The following definitions come from lib/hmacmd5.c */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 7ebe6599ed3..0ad3e2d116a 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -154,81 +154,8 @@ void DeleteTconOplockQEntries(struct cifsTconInfo *tcon) spin_unlock(&GlobalMid_Lock); } -int -smb_send(struct socket *ssocket, struct smb_hdr *smb_buffer, - unsigned int smb_buf_length, struct sockaddr *sin, bool noblocksnd) -{ - int rc = 0; - int i = 0; - struct msghdr smb_msg; - struct kvec iov; - unsigned len = smb_buf_length + 4; - - if (ssocket == NULL) - return -ENOTSOCK; /* BB eventually add reconnect code here */ - iov.iov_base = smb_buffer; - iov.iov_len = len; - - smb_msg.msg_name = sin; - smb_msg.msg_namelen = sizeof(struct sockaddr); - smb_msg.msg_control = NULL; - smb_msg.msg_controllen = 0; - if (noblocksnd) - smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL; - else - smb_msg.msg_flags = MSG_NOSIGNAL; - - /* smb header is converted in header_assemble. bcc and rest of SMB word - area, and byte area if necessary, is converted to littleendian in - cifssmb.c and RFC1001 len is converted to bigendian in smb_send - Flags2 is converted in SendReceive */ - - smb_buffer->smb_buf_length = cpu_to_be32(smb_buffer->smb_buf_length); - cFYI(1, ("Sending smb of length %d", smb_buf_length)); - dump_smb(smb_buffer, len); - - while (len > 0) { - rc = kernel_sendmsg(ssocket, &smb_msg, &iov, 1, len); - if ((rc == -ENOSPC) || (rc == -EAGAIN)) { - i++; - /* smaller timeout here than send2 since smaller size */ - /* Although it may not be required, this also is smaller - oplock break time */ - if (i > 12) { - cERROR(1, - ("sends on sock %p stuck for 7 seconds", - ssocket)); - rc = -EAGAIN; - break; - } - msleep(1 << i); - continue; - } - if (rc < 0) - break; - else - i = 0; /* reset i after each successful send */ - iov.iov_base += rc; - iov.iov_len -= rc; - len -= rc; - } - - if (rc < 0) { - cERROR(1, ("Error %d sending data on socket to server", rc)); - } else { - rc = 0; - } - - /* Don't want to modify the buffer as a - side effect of this call. */ - smb_buffer->smb_buf_length = smb_buf_length; - - return rc; -} - static int -smb_send2(struct TCP_Server_Info *server, struct kvec *iov, int n_vec, - struct sockaddr *sin, bool noblocksnd) +smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec) { int rc = 0; int i = 0; @@ -243,11 +170,11 @@ smb_send2(struct TCP_Server_Info *server, struct kvec *iov, int n_vec, if (ssocket == NULL) return -ENOTSOCK; /* BB eventually add reconnect code here */ - smb_msg.msg_name = sin; + smb_msg.msg_name = (struct sockaddr *) &server->addr.sockAddr; smb_msg.msg_namelen = sizeof(struct sockaddr); smb_msg.msg_control = NULL; smb_msg.msg_controllen = 0; - if (noblocksnd) + if (server->noblocksnd) smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL; else smb_msg.msg_flags = MSG_NOSIGNAL; @@ -272,7 +199,25 @@ smb_send2(struct TCP_Server_Info *server, struct kvec *iov, int n_vec, n_vec - first_vec, total_len); if ((rc == -ENOSPC) || (rc == -EAGAIN)) { i++; - if (i >= 14) { + /* if blocking send we try 3 times, since each can block + for 5 seconds. For nonblocking we have to try more + but wait increasing amounts of time allowing time for + socket to clear. The overall time we wait in either + case to send on the socket is about 15 seconds. + Similarly we wait for 15 seconds for + a response from the server in SendReceive[2] + for the server to send a response back for + most types of requests (except SMB Write + past end of file which can be slow, and + blocking lock operations). NFS waits slightly longer + than CIFS, but this can make it take longer for + nonresponsive servers to be detected and 15 seconds + is more than enough time for modern networks to + send a packet. In most cases if we fail to send + after the retries we will kill the socket and + reconnect which may clear the network problem. + */ + if ((i >= 14) || (!server->noblocksnd && (i > 2))) { cERROR(1, ("sends on sock %p stuck for 15 seconds", ssocket)); @@ -339,6 +284,18 @@ smb_send2(struct TCP_Server_Info *server, struct kvec *iov, int n_vec, return rc; } +int +smb_send(struct TCP_Server_Info *server, struct smb_hdr *smb_buffer, + unsigned int smb_buf_length) +{ + struct kvec iov; + + iov.iov_base = smb_buffer; + iov.iov_len = smb_buf_length + 4; + + return smb_sendv(server, &iov, 1); +} + static int wait_for_free_request(struct cifsSesInfo *ses, const int long_op) { if (long_op == CIFS_ASYNC_OP) { @@ -540,9 +497,7 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses, #ifdef CONFIG_CIFS_STATS2 atomic_inc(&ses->server->inSend); #endif - rc = smb_send2(ses->server, iov, n_vec, - (struct sockaddr *) &(ses->server->addr.sockAddr), - ses->server->noblocksnd); + rc = smb_sendv(ses->server, iov, n_vec); #ifdef CONFIG_CIFS_STATS2 atomic_dec(&ses->server->inSend); midQ->when_sent = jiffies; @@ -736,9 +691,7 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses, #ifdef CONFIG_CIFS_STATS2 atomic_inc(&ses->server->inSend); #endif - rc = smb_send(ses->server->ssocket, in_buf, in_buf->smb_buf_length, - (struct sockaddr *) &(ses->server->addr.sockAddr), - ses->server->noblocksnd); + rc = smb_send(ses->server, in_buf, in_buf->smb_buf_length); #ifdef CONFIG_CIFS_STATS2 atomic_dec(&ses->server->inSend); midQ->when_sent = jiffies; @@ -879,9 +832,7 @@ send_nt_cancel(struct cifsTconInfo *tcon, struct smb_hdr *in_buf, mutex_unlock(&ses->server->srv_mutex); return rc; } - rc = smb_send(ses->server->ssocket, in_buf, in_buf->smb_buf_length, - (struct sockaddr *) &(ses->server->addr.sockAddr), - ses->server->noblocksnd); + rc = smb_send(ses->server, in_buf, in_buf->smb_buf_length); mutex_unlock(&ses->server->srv_mutex); return rc; } @@ -973,9 +924,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon, #ifdef CONFIG_CIFS_STATS2 atomic_inc(&ses->server->inSend); #endif - rc = smb_send(ses->server->ssocket, in_buf, in_buf->smb_buf_length, - (struct sockaddr *) &(ses->server->addr.sockAddr), - ses->server->noblocksnd); + rc = smb_send(ses->server, in_buf, in_buf->smb_buf_length); #ifdef CONFIG_CIFS_STATS2 atomic_dec(&ses->server->inSend); midQ->when_sent = jiffies; diff --git a/fs/coda/Kconfig b/fs/coda/Kconfig new file mode 100644 index 00000000000..c0e5a7fad06 --- /dev/null +++ b/fs/coda/Kconfig @@ -0,0 +1,21 @@ +config CODA_FS + tristate "Coda file system support (advanced network fs)" + depends on INET + help + Coda is an advanced network file system, similar to NFS in that it + enables you to mount file systems of a remote server and access them + with regular Unix commands as if they were sitting on your hard + disk. Coda has several advantages over NFS: support for + disconnected operation (e.g. for laptops), read/write server + replication, security model for authentication and encryption, + persistent client caches and write back caching. + + If you say Y here, your Linux box will be able to act as a Coda + *client*. You will need user level code as well, both for the + client and server. Servers are currently user level, i.e. they need + no kernel support. Please read + <file:Documentation/filesystems/coda.txt> and check out the Coda + home page <http://www.coda.cs.cmu.edu/>. + + To compile the coda client support as a module, choose M here: the + module will be called coda. diff --git a/fs/compat.c b/fs/compat.c index 30f2faa22f5..65a070e705a 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1709,7 +1709,7 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, } #ifdef HAVE_SET_RESTORE_SIGMASK -asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp, +static long do_compat_pselect(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask, compat_size_t sigsetsize) @@ -1775,8 +1775,8 @@ asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp, (compat_size_t __user *)(sig+sizeof(up)))) return -EFAULT; } - return compat_sys_pselect7(n, inp, outp, exp, tsp, compat_ptr(up), - sigsetsize); + return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(up), + sigsetsize); } asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 5235c67e759..c8f8d5904f5 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -538,6 +538,7 @@ static int dev_ifsioc(unsigned int fd, unsigned int cmd, unsigned long arg) * cannot be fixed without breaking all existing apps. */ case TUNSETIFF: + case TUNGETIFF: case SIOCGIFFLAGS: case SIOCGIFMETRIC: case SIOCGIFMTU: @@ -1982,6 +1983,11 @@ COMPATIBLE_IOCTL(TUNSETNOCSUM) COMPATIBLE_IOCTL(TUNSETDEBUG) COMPATIBLE_IOCTL(TUNSETPERSIST) COMPATIBLE_IOCTL(TUNSETOWNER) +COMPATIBLE_IOCTL(TUNSETLINK) +COMPATIBLE_IOCTL(TUNSETGROUP) +COMPATIBLE_IOCTL(TUNGETFEATURES) +COMPATIBLE_IOCTL(TUNSETOFFLOAD) +COMPATIBLE_IOCTL(TUNSETTXFILTER) /* Big V */ COMPATIBLE_IOCTL(VT_SETMODE) COMPATIBLE_IOCTL(VT_GETMODE) @@ -2573,6 +2579,7 @@ HANDLE_IOCTL(SIOCGIFPFLAGS, dev_ifsioc) HANDLE_IOCTL(SIOCGIFTXQLEN, dev_ifsioc) HANDLE_IOCTL(SIOCSIFTXQLEN, dev_ifsioc) HANDLE_IOCTL(TUNSETIFF, dev_ifsioc) +HANDLE_IOCTL(TUNGETIFF, dev_ifsioc) HANDLE_IOCTL(SIOCETHTOOL, ethtool_ioctl) HANDLE_IOCTL(SIOCBONDENSLAVE, bond_ioctl) HANDLE_IOCTL(SIOCBONDRELEASE, bond_ioctl) diff --git a/fs/configfs/Kconfig b/fs/configfs/Kconfig new file mode 100644 index 00000000000..13587cc97a0 --- /dev/null +++ b/fs/configfs/Kconfig @@ -0,0 +1,11 @@ +config CONFIGFS_FS + tristate "Userspace-driven configuration filesystem" + depends on SYSFS + help + configfs is a ram-based filesystem that provides the converse + of sysfs's functionality. Where sysfs is a filesystem-based + view of kernel objects, configfs is a filesystem-based manager + of kernel objects, or config_items. + + Both sysfs and configfs can and should exist together on the + same system. One is not a replacement for the other. diff --git a/fs/cramfs/Kconfig b/fs/cramfs/Kconfig new file mode 100644 index 00000000000..cd06466f365 --- /dev/null +++ b/fs/cramfs/Kconfig @@ -0,0 +1,19 @@ +config CRAMFS + tristate "Compressed ROM file system support (cramfs)" + depends on BLOCK + select ZLIB_INFLATE + help + Saying Y here includes support for CramFs (Compressed ROM File + System). CramFs is designed to be a simple, small, and compressed + file system for ROM based embedded systems. CramFs is read-only, + limited to 256MB file systems (with 16MB files), and doesn't support + 16/32 bits uid/gid, hard links and timestamps. + + See <file:Documentation/filesystems/cramfs.txt> and + <file:fs/cramfs/README> for further information. + + To compile this as a module, choose M here: the module will be called + cramfs. Note that the root file system (the one containing the + directory /) cannot be compiled as a module. + + If unsure, say N. diff --git a/fs/dcache.c b/fs/dcache.c index 4547f66884a..937df0fb0da 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2092,7 +2092,7 @@ Elong: * return NULL; * } */ -asmlinkage long sys_getcwd(char __user *buf, unsigned long size) +SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size) { int error; struct path pwd, root; diff --git a/fs/dcookies.c b/fs/dcookies.c index 180e9fec4ad..a21cabdbd87 100644 --- a/fs/dcookies.c +++ b/fs/dcookies.c @@ -145,7 +145,7 @@ out: /* And here is where the userspace process can look up the cookie value * to retrieve the path. */ -asmlinkage long sys_lookup_dcookie(u64 cookie64, char __user * buf, size_t len) +SYSCALL_DEFINE(lookup_dcookie)(u64 cookie64, char __user * buf, size_t len) { unsigned long cookie = (unsigned long)cookie64; int err = -EINVAL; @@ -198,7 +198,13 @@ out: mutex_unlock(&dcookie_mutex); return err; } - +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_lookup_dcookie(u64 cookie64, long buf, long len) +{ + return SYSC_lookup_dcookie(cookie64, (char __user *) buf, (size_t) len); +} +SYSCALL_ALIAS(sys_lookup_dcookie, SyS_lookup_dcookie); +#endif static int dcookie_init(void) { diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index 2f107d1a6a4..1d1d2744223 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -1,7 +1,7 @@ /****************************************************************************** ******************************************************************************* ** -** Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved. +** Copyright (C) 2005-2009 Red Hat, Inc. All rights reserved. ** ** This copyrighted material is made available to anyone wishing to use, ** modify, copy, or redistribute it subject to the terms and conditions @@ -25,19 +25,6 @@ static struct mutex debug_buf_lock; static struct dentry *dlm_root; -struct rsb_iter { - int entry; - int format; - int header; - struct dlm_ls *ls; - struct list_head *next; - struct dlm_rsb *rsb; -}; - -/* - * dump all rsb's in the lockspace hash table - */ - static char *print_lockmode(int mode) { switch (mode) { @@ -60,13 +47,13 @@ static char *print_lockmode(int mode) } } -static void print_format1_lock(struct seq_file *s, struct dlm_lkb *lkb, - struct dlm_rsb *res) +static int print_format1_lock(struct seq_file *s, struct dlm_lkb *lkb, + struct dlm_rsb *res) { seq_printf(s, "%08x %s", lkb->lkb_id, print_lockmode(lkb->lkb_grmode)); - if (lkb->lkb_status == DLM_LKSTS_CONVERT - || lkb->lkb_status == DLM_LKSTS_WAITING) + if (lkb->lkb_status == DLM_LKSTS_CONVERT || + lkb->lkb_status == DLM_LKSTS_WAITING) seq_printf(s, " (%s)", print_lockmode(lkb->lkb_rqmode)); if (lkb->lkb_nodeid) { @@ -80,33 +67,42 @@ static void print_format1_lock(struct seq_file *s, struct dlm_lkb *lkb, if (lkb->lkb_wait_type) seq_printf(s, " wait_type: %d", lkb->lkb_wait_type); - seq_printf(s, "\n"); + return seq_printf(s, "\n"); } static int print_format1(struct dlm_rsb *res, struct seq_file *s) { struct dlm_lkb *lkb; int i, lvblen = res->res_ls->ls_lvblen, recover_list, root_list; + int rv; lock_rsb(res); - seq_printf(s, "\nResource %p Name (len=%d) \"", res, res->res_length); + rv = seq_printf(s, "\nResource %p Name (len=%d) \"", + res, res->res_length); + if (rv) + goto out; + for (i = 0; i < res->res_length; i++) { if (isprint(res->res_name[i])) seq_printf(s, "%c", res->res_name[i]); else seq_printf(s, "%c", '.'); } + if (res->res_nodeid > 0) - seq_printf(s, "\" \nLocal Copy, Master is node %d\n", - res->res_nodeid); + rv = seq_printf(s, "\" \nLocal Copy, Master is node %d\n", + res->res_nodeid); else if (res->res_nodeid == 0) - seq_printf(s, "\" \nMaster Copy\n"); + rv = seq_printf(s, "\" \nMaster Copy\n"); else if (res->res_nodeid == -1) - seq_printf(s, "\" \nLooking up master (lkid %x)\n", - res->res_first_lkid); + rv = seq_printf(s, "\" \nLooking up master (lkid %x)\n", + res->res_first_lkid); else - seq_printf(s, "\" \nInvalid master %d\n", res->res_nodeid); + rv = seq_printf(s, "\" \nInvalid master %d\n", + res->res_nodeid); + if (rv) + goto out; /* Print the LVB: */ if (res->res_lvbptr) { @@ -119,52 +115,66 @@ static int print_format1(struct dlm_rsb *res, struct seq_file *s) } if (rsb_flag(res, RSB_VALNOTVALID)) seq_printf(s, " (INVALID)"); - seq_printf(s, "\n"); + rv = seq_printf(s, "\n"); + if (rv) + goto out; } root_list = !list_empty(&res->res_root_list); recover_list = !list_empty(&res->res_recover_list); if (root_list || recover_list) { - seq_printf(s, "Recovery: root %d recover %d flags %lx " - "count %d\n", root_list, recover_list, - res->res_flags, res->res_recover_locks_count); + rv = seq_printf(s, "Recovery: root %d recover %d flags %lx " + "count %d\n", root_list, recover_list, + res->res_flags, res->res_recover_locks_count); + if (rv) + goto out; } /* Print the locks attached to this resource */ seq_printf(s, "Granted Queue\n"); - list_for_each_entry(lkb, &res->res_grantqueue, lkb_statequeue) - print_format1_lock(s, lkb, res); + list_for_each_entry(lkb, &res->res_grantqueue, lkb_statequeue) { + rv = print_format1_lock(s, lkb, res); + if (rv) + goto out; + } seq_printf(s, "Conversion Queue\n"); - list_for_each_entry(lkb, &res->res_convertqueue, lkb_statequeue) - print_format1_lock(s, lkb, res); + list_for_each_entry(lkb, &res->res_convertqueue, lkb_statequeue) { + rv = print_format1_lock(s, lkb, res); + if (rv) + goto out; + } seq_printf(s, "Waiting Queue\n"); - list_for_each_entry(lkb, &res->res_waitqueue, lkb_statequeue) - print_format1_lock(s, lkb, res); + list_for_each_entry(lkb, &res->res_waitqueue, lkb_statequeue) { + rv = print_format1_lock(s, lkb, res); + if (rv) + goto out; + } if (list_empty(&res->res_lookup)) goto out; seq_printf(s, "Lookup Queue\n"); list_for_each_entry(lkb, &res->res_lookup, lkb_rsb_lookup) { - seq_printf(s, "%08x %s", lkb->lkb_id, - print_lockmode(lkb->lkb_rqmode)); + rv = seq_printf(s, "%08x %s", lkb->lkb_id, + print_lockmode(lkb->lkb_rqmode)); if (lkb->lkb_wait_type) seq_printf(s, " wait_type: %d", lkb->lkb_wait_type); - seq_printf(s, "\n"); + rv = seq_printf(s, "\n"); } out: unlock_rsb(res); - return 0; + return rv; } -static void print_format2_lock(struct seq_file *s, struct dlm_lkb *lkb, - struct dlm_rsb *r) +static int print_format2_lock(struct seq_file *s, struct dlm_lkb *lkb, + struct dlm_rsb *r) { u64 xid = 0; u64 us; + int rv; if (lkb->lkb_flags & DLM_IFL_USER) { if (lkb->lkb_ua) @@ -177,69 +187,82 @@ static void print_format2_lock(struct seq_file *s, struct dlm_lkb *lkb, /* id nodeid remid pid xid exflags flags sts grmode rqmode time_us r_nodeid r_len r_name */ - seq_printf(s, "%x %d %x %u %llu %x %x %d %d %d %llu %u %d \"%s\"\n", - lkb->lkb_id, - lkb->lkb_nodeid, - lkb->lkb_remid, - lkb->lkb_ownpid, - (unsigned long long)xid, - lkb->lkb_exflags, - lkb->lkb_flags, - lkb->lkb_status, - lkb->lkb_grmode, - lkb->lkb_rqmode, - (unsigned long long)us, - r->res_nodeid, - r->res_length, - r->res_name); + rv = seq_printf(s, "%x %d %x %u %llu %x %x %d %d %d %llu %u %d \"%s\"\n", + lkb->lkb_id, + lkb->lkb_nodeid, + lkb->lkb_remid, + lkb->lkb_ownpid, + (unsigned long long)xid, + lkb->lkb_exflags, + lkb->lkb_flags, + lkb->lkb_status, + lkb->lkb_grmode, + lkb->lkb_rqmode, + (unsigned long long)us, + r->res_nodeid, + r->res_length, + r->res_name); + return rv; } static int print_format2(struct dlm_rsb *r, struct seq_file *s) { struct dlm_lkb *lkb; + int rv = 0; lock_rsb(r); - list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) - print_format2_lock(s, lkb, r); - - list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) - print_format2_lock(s, lkb, r); + list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) { + rv = print_format2_lock(s, lkb, r); + if (rv) + goto out; + } - list_for_each_entry(lkb, &r->res_waitqueue, lkb_statequeue) - print_format2_lock(s, lkb, r); + list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) { + rv = print_format2_lock(s, lkb, r); + if (rv) + goto out; + } + list_for_each_entry(lkb, &r->res_waitqueue, lkb_statequeue) { + rv = print_format2_lock(s, lkb, r); + if (rv) + goto out; + } + out: unlock_rsb(r); - return 0; + return rv; } -static void print_format3_lock(struct seq_file *s, struct dlm_lkb *lkb, - int rsb_lookup) +static int print_format3_lock(struct seq_file *s, struct dlm_lkb *lkb, + int rsb_lookup) { u64 xid = 0; + int rv; if (lkb->lkb_flags & DLM_IFL_USER) { if (lkb->lkb_ua) xid = lkb->lkb_ua->xid; } - seq_printf(s, "lkb %x %d %x %u %llu %x %x %d %d %d %d %d %d %u %llu %llu\n", - lkb->lkb_id, - lkb->lkb_nodeid, - lkb->lkb_remid, - lkb->lkb_ownpid, - (unsigned long long)xid, - lkb->lkb_exflags, - lkb->lkb_flags, - lkb->lkb_status, - lkb->lkb_grmode, - lkb->lkb_rqmode, - lkb->lkb_highbast, - rsb_lookup, - lkb->lkb_wait_type, - lkb->lkb_lvbseq, - (unsigned long long)ktime_to_ns(lkb->lkb_timestamp), - (unsigned long long)ktime_to_ns(lkb->lkb_time_bast)); + rv = seq_printf(s, "lkb %x %d %x %u %llu %x %x %d %d %d %d %d %d %u %llu %llu\n", + lkb->lkb_id, + lkb->lkb_nodeid, + lkb->lkb_remid, + lkb->lkb_ownpid, + (unsigned long long)xid, + lkb->lkb_exflags, + lkb->lkb_flags, + lkb->lkb_status, + lkb->lkb_grmode, + lkb->lkb_rqmode, + lkb->lkb_highbast, + rsb_lookup, + lkb->lkb_wait_type, + lkb->lkb_lvbseq, + (unsigned long long)ktime_to_ns(lkb->lkb_timestamp), + (unsigned long long)ktime_to_ns(lkb->lkb_time_bast)); + return rv; } static int print_format3(struct dlm_rsb *r, struct seq_file *s) @@ -247,18 +270,21 @@ static int print_format3(struct dlm_rsb *r, struct seq_file *s) struct dlm_lkb *lkb; int i, lvblen = r->res_ls->ls_lvblen; int print_name = 1; + int rv; lock_rsb(r); - seq_printf(s, "rsb %p %d %x %lx %d %d %u %d ", - r, - r->res_nodeid, - r->res_first_lkid, - r->res_flags, - !list_empty(&r->res_root_list), - !list_empty(&r->res_recover_list), - r->res_recover_locks_count, - r->res_length); + rv = seq_printf(s, "rsb %p %d %x %lx %d %d %u %d ", + r, + r->res_nodeid, + r->res_first_lkid, + r->res_flags, + !list_empty(&r->res_root_list), + !list_empty(&r->res_recover_list), + r->res_recover_locks_count, + r->res_length); + if (rv) + goto out; for (i = 0; i < r->res_length; i++) { if (!isascii(r->res_name[i]) || !isprint(r->res_name[i])) @@ -273,7 +299,9 @@ static int print_format3(struct dlm_rsb *r, struct seq_file *s) else seq_printf(s, " %02x", (unsigned char)r->res_name[i]); } - seq_printf(s, "\n"); + rv = seq_printf(s, "\n"); + if (rv) + goto out; if (!r->res_lvbptr) goto do_locks; @@ -282,344 +310,294 @@ static int print_format3(struct dlm_rsb *r, struct seq_file *s) for (i = 0; i < lvblen; i++) seq_printf(s, " %02x", (unsigned char)r->res_lvbptr[i]); - seq_printf(s, "\n"); + rv = seq_printf(s, "\n"); + if (rv) + goto out; do_locks: - list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) - print_format3_lock(s, lkb, 0); - - list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) - print_format3_lock(s, lkb, 0); - - list_for_each_entry(lkb, &r->res_waitqueue, lkb_statequeue) - print_format3_lock(s, lkb, 0); - - list_for_each_entry(lkb, &r->res_lookup, lkb_rsb_lookup) - print_format3_lock(s, lkb, 1); - - unlock_rsb(r); - return 0; -} - -static int rsb_iter_next(struct rsb_iter *ri) -{ - struct dlm_ls *ls = ri->ls; - int i; - - if (!ri->next) { - top: - /* Find the next non-empty hash bucket */ - for (i = ri->entry; i < ls->ls_rsbtbl_size; i++) { - read_lock(&ls->ls_rsbtbl[i].lock); - if (!list_empty(&ls->ls_rsbtbl[i].list)) { - ri->next = ls->ls_rsbtbl[i].list.next; - ri->rsb = list_entry(ri->next, struct dlm_rsb, - res_hashchain); - dlm_hold_rsb(ri->rsb); - read_unlock(&ls->ls_rsbtbl[i].lock); - break; - } - read_unlock(&ls->ls_rsbtbl[i].lock); - } - ri->entry = i; - - if (ri->entry >= ls->ls_rsbtbl_size) - return 1; - } else { - struct dlm_rsb *old = ri->rsb; - i = ri->entry; - read_lock(&ls->ls_rsbtbl[i].lock); - ri->next = ri->next->next; - if (ri->next->next == ls->ls_rsbtbl[i].list.next) { - /* End of list - move to next bucket */ - ri->next = NULL; - ri->entry++; - read_unlock(&ls->ls_rsbtbl[i].lock); - dlm_put_rsb(old); - goto top; - } - ri->rsb = list_entry(ri->next, struct dlm_rsb, res_hashchain); - dlm_hold_rsb(ri->rsb); - read_unlock(&ls->ls_rsbtbl[i].lock); - dlm_put_rsb(old); + list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) { + rv = print_format3_lock(s, lkb, 0); + if (rv) + goto out; } - return 0; -} - -static void rsb_iter_free(struct rsb_iter *ri) -{ - kfree(ri); -} - -static struct rsb_iter *rsb_iter_init(struct dlm_ls *ls) -{ - struct rsb_iter *ri; - - ri = kzalloc(sizeof *ri, GFP_KERNEL); - if (!ri) - return NULL; - - ri->ls = ls; - ri->entry = 0; - ri->next = NULL; - ri->format = 1; - - if (rsb_iter_next(ri)) { - rsb_iter_free(ri); - return NULL; + list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) { + rv = print_format3_lock(s, lkb, 0); + if (rv) + goto out; } - return ri; -} - -static void *rsb_seq_start(struct seq_file *file, loff_t *pos) -{ - struct rsb_iter *ri; - loff_t n = *pos; - - ri = rsb_iter_init(file->private); - if (!ri) - return NULL; - - while (n--) { - if (rsb_iter_next(ri)) { - rsb_iter_free(ri); - return NULL; - } + list_for_each_entry(lkb, &r->res_waitqueue, lkb_statequeue) { + rv = print_format3_lock(s, lkb, 0); + if (rv) + goto out; } - return ri; -} - -static void *rsb_seq_next(struct seq_file *file, void *iter_ptr, loff_t *pos) -{ - struct rsb_iter *ri = iter_ptr; - - (*pos)++; - - if (rsb_iter_next(ri)) { - rsb_iter_free(ri); - return NULL; + list_for_each_entry(lkb, &r->res_lookup, lkb_rsb_lookup) { + rv = print_format3_lock(s, lkb, 1); + if (rv) + goto out; } - - return ri; + out: + unlock_rsb(r); + return rv; } -static void rsb_seq_stop(struct seq_file *file, void *iter_ptr) -{ - /* nothing for now */ -} +struct rsbtbl_iter { + struct dlm_rsb *rsb; + unsigned bucket; + int format; + int header; +}; -static int rsb_seq_show(struct seq_file *file, void *iter_ptr) +/* seq_printf returns -1 if the buffer is full, and 0 otherwise. + If the buffer is full, seq_printf can be called again, but it + does nothing and just returns -1. So, the these printing routines + periodically check the return value to avoid wasting too much time + trying to print to a full buffer. */ + +static int table_seq_show(struct seq_file *seq, void *iter_ptr) { - struct rsb_iter *ri = iter_ptr; + struct rsbtbl_iter *ri = iter_ptr; + int rv = 0; switch (ri->format) { case 1: - print_format1(ri->rsb, file); + rv = print_format1(ri->rsb, seq); break; case 2: if (ri->header) { - seq_printf(file, "id nodeid remid pid xid exflags " - "flags sts grmode rqmode time_ms " - "r_nodeid r_len r_name\n"); + seq_printf(seq, "id nodeid remid pid xid exflags " + "flags sts grmode rqmode time_ms " + "r_nodeid r_len r_name\n"); ri->header = 0; } - print_format2(ri->rsb, file); + rv = print_format2(ri->rsb, seq); break; case 3: if (ri->header) { - seq_printf(file, "version rsb 1.1 lvb 1.1 lkb 1.1\n"); + seq_printf(seq, "version rsb 1.1 lvb 1.1 lkb 1.1\n"); ri->header = 0; } - print_format3(ri->rsb, file); + rv = print_format3(ri->rsb, seq); break; } - return 0; + return rv; } -static struct seq_operations rsb_seq_ops = { - .start = rsb_seq_start, - .next = rsb_seq_next, - .stop = rsb_seq_stop, - .show = rsb_seq_show, -}; +static struct seq_operations format1_seq_ops; +static struct seq_operations format2_seq_ops; +static struct seq_operations format3_seq_ops; -static int rsb_open(struct inode *inode, struct file *file) +static void *table_seq_start(struct seq_file *seq, loff_t *pos) { - struct seq_file *seq; - int ret; - - ret = seq_open(file, &rsb_seq_ops); - if (ret) - return ret; - - seq = file->private_data; - seq->private = inode->i_private; - - return 0; -} - -static const struct file_operations rsb_fops = { - .owner = THIS_MODULE, - .open = rsb_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release -}; + struct dlm_ls *ls = seq->private; + struct rsbtbl_iter *ri; + struct dlm_rsb *r; + loff_t n = *pos; + unsigned bucket, entry; -/* - * Dump state in compact per-lock listing - */ + bucket = n >> 32; + entry = n & ((1LL << 32) - 1); -static struct rsb_iter *locks_iter_init(struct dlm_ls *ls, loff_t *pos) -{ - struct rsb_iter *ri; + if (bucket >= ls->ls_rsbtbl_size) + return NULL; - ri = kzalloc(sizeof *ri, GFP_KERNEL); + ri = kzalloc(sizeof(struct rsbtbl_iter), GFP_KERNEL); if (!ri) return NULL; - - ri->ls = ls; - ri->entry = 0; - ri->next = NULL; - ri->format = 2; - - if (*pos == 0) + if (n == 0) ri->header = 1; - - if (rsb_iter_next(ri)) { - rsb_iter_free(ri); - return NULL; + if (seq->op == &format1_seq_ops) + ri->format = 1; + if (seq->op == &format2_seq_ops) + ri->format = 2; + if (seq->op == &format3_seq_ops) + ri->format = 3; + + spin_lock(&ls->ls_rsbtbl[bucket].lock); + if (!list_empty(&ls->ls_rsbtbl[bucket].list)) { + list_for_each_entry(r, &ls->ls_rsbtbl[bucket].list, + res_hashchain) { + if (!entry--) { + dlm_hold_rsb(r); + ri->rsb = r; + ri->bucket = bucket; + spin_unlock(&ls->ls_rsbtbl[bucket].lock); + return ri; + } + } } + spin_unlock(&ls->ls_rsbtbl[bucket].lock); - return ri; -} + /* + * move to the first rsb in the next non-empty bucket + */ -static void *locks_seq_start(struct seq_file *file, loff_t *pos) -{ - struct rsb_iter *ri; - loff_t n = *pos; + /* zero the entry */ + n &= ~((1LL << 32) - 1); - ri = locks_iter_init(file->private, pos); - if (!ri) - return NULL; + while (1) { + bucket++; + n += 1LL << 32; - while (n--) { - if (rsb_iter_next(ri)) { - rsb_iter_free(ri); + if (bucket >= ls->ls_rsbtbl_size) { + kfree(ri); return NULL; } - } - return ri; + spin_lock(&ls->ls_rsbtbl[bucket].lock); + if (!list_empty(&ls->ls_rsbtbl[bucket].list)) { + r = list_first_entry(&ls->ls_rsbtbl[bucket].list, + struct dlm_rsb, res_hashchain); + dlm_hold_rsb(r); + ri->rsb = r; + ri->bucket = bucket; + spin_unlock(&ls->ls_rsbtbl[bucket].lock); + *pos = n; + return ri; + } + spin_unlock(&ls->ls_rsbtbl[bucket].lock); + } } -static struct seq_operations locks_seq_ops = { - .start = locks_seq_start, - .next = rsb_seq_next, - .stop = rsb_seq_stop, - .show = rsb_seq_show, -}; - -static int locks_open(struct inode *inode, struct file *file) +static void *table_seq_next(struct seq_file *seq, void *iter_ptr, loff_t *pos) { - struct seq_file *seq; - int ret; - - ret = seq_open(file, &locks_seq_ops); - if (ret) - return ret; - - seq = file->private_data; - seq->private = inode->i_private; - - return 0; -} - -static const struct file_operations locks_fops = { - .owner = THIS_MODULE, - .open = locks_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release -}; - -/* - * Dump all rsb/lvb/lkb state in compact listing, more complete than _locks - * This can replace both formats 1 and 2 eventually. - */ + struct dlm_ls *ls = seq->private; + struct rsbtbl_iter *ri = iter_ptr; + struct list_head *next; + struct dlm_rsb *r, *rp; + loff_t n = *pos; + unsigned bucket; + + bucket = n >> 32; + + /* + * move to the next rsb in the same bucket + */ + + spin_lock(&ls->ls_rsbtbl[bucket].lock); + rp = ri->rsb; + next = rp->res_hashchain.next; + + if (next != &ls->ls_rsbtbl[bucket].list) { + r = list_entry(next, struct dlm_rsb, res_hashchain); + dlm_hold_rsb(r); + ri->rsb = r; + spin_unlock(&ls->ls_rsbtbl[bucket].lock); + dlm_put_rsb(rp); + ++*pos; + return ri; + } + spin_unlock(&ls->ls_rsbtbl[bucket].lock); + dlm_put_rsb(rp); -static struct rsb_iter *all_iter_init(struct dlm_ls *ls, loff_t *pos) -{ - struct rsb_iter *ri; + /* + * move to the first rsb in the next non-empty bucket + */ - ri = kzalloc(sizeof *ri, GFP_KERNEL); - if (!ri) - return NULL; + /* zero the entry */ + n &= ~((1LL << 32) - 1); - ri->ls = ls; - ri->entry = 0; - ri->next = NULL; - ri->format = 3; + while (1) { + bucket++; + n += 1LL << 32; - if (*pos == 0) - ri->header = 1; + if (bucket >= ls->ls_rsbtbl_size) { + kfree(ri); + return NULL; + } - if (rsb_iter_next(ri)) { - rsb_iter_free(ri); - return NULL; + spin_lock(&ls->ls_rsbtbl[bucket].lock); + if (!list_empty(&ls->ls_rsbtbl[bucket].list)) { + r = list_first_entry(&ls->ls_rsbtbl[bucket].list, + struct dlm_rsb, res_hashchain); + dlm_hold_rsb(r); + ri->rsb = r; + ri->bucket = bucket; + spin_unlock(&ls->ls_rsbtbl[bucket].lock); + *pos = n; + return ri; + } + spin_unlock(&ls->ls_rsbtbl[bucket].lock); } - - return ri; } -static void *all_seq_start(struct seq_file *file, loff_t *pos) +static void table_seq_stop(struct seq_file *seq, void *iter_ptr) { - struct rsb_iter *ri; - loff_t n = *pos; - - ri = all_iter_init(file->private, pos); - if (!ri) - return NULL; + struct rsbtbl_iter *ri = iter_ptr; - while (n--) { - if (rsb_iter_next(ri)) { - rsb_iter_free(ri); - return NULL; - } + if (ri) { + dlm_put_rsb(ri->rsb); + kfree(ri); } - - return ri; } -static struct seq_operations all_seq_ops = { - .start = all_seq_start, - .next = rsb_seq_next, - .stop = rsb_seq_stop, - .show = rsb_seq_show, +static struct seq_operations format1_seq_ops = { + .start = table_seq_start, + .next = table_seq_next, + .stop = table_seq_stop, + .show = table_seq_show, }; -static int all_open(struct inode *inode, struct file *file) +static struct seq_operations format2_seq_ops = { + .start = table_seq_start, + .next = table_seq_next, + .stop = table_seq_stop, + .show = table_seq_show, +}; + +static struct seq_operations format3_seq_ops = { + .start = table_seq_start, + .next = table_seq_next, + .stop = table_seq_stop, + .show = table_seq_show, +}; + +static const struct file_operations format1_fops; +static const struct file_operations format2_fops; +static const struct file_operations format3_fops; + +static int table_open(struct inode *inode, struct file *file) { struct seq_file *seq; - int ret; + int ret = -1; + + if (file->f_op == &format1_fops) + ret = seq_open(file, &format1_seq_ops); + else if (file->f_op == &format2_fops) + ret = seq_open(file, &format2_seq_ops); + else if (file->f_op == &format3_fops) + ret = seq_open(file, &format3_seq_ops); - ret = seq_open(file, &all_seq_ops); if (ret) return ret; seq = file->private_data; - seq->private = inode->i_private; - + seq->private = inode->i_private; /* the dlm_ls */ return 0; } -static const struct file_operations all_fops = { +static const struct file_operations format1_fops = { + .owner = THIS_MODULE, + .open = table_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release +}; + +static const struct file_operations format2_fops = { + .owner = THIS_MODULE, + .open = table_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release +}; + +static const struct file_operations format3_fops = { .owner = THIS_MODULE, - .open = all_open, + .open = table_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -689,7 +667,7 @@ int dlm_create_debug_file(struct dlm_ls *ls) S_IFREG | S_IRUGO, dlm_root, ls, - &rsb_fops); + &format1_fops); if (!ls->ls_debug_rsb_dentry) goto fail; @@ -702,7 +680,7 @@ int dlm_create_debug_file(struct dlm_ls *ls) S_IFREG | S_IRUGO, dlm_root, ls, - &locks_fops); + &format2_fops); if (!ls->ls_debug_locks_dentry) goto fail; @@ -715,7 +693,7 @@ int dlm_create_debug_file(struct dlm_ls *ls) S_IFREG | S_IRUGO, dlm_root, ls, - &all_fops); + &format3_fops); if (!ls->ls_debug_all_dentry) goto fail; diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index ef2f1e35396..076e86f38bc 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -105,7 +105,7 @@ struct dlm_dirtable { struct dlm_rsbtable { struct list_head list; struct list_head toss; - rwlock_t lock; + spinlock_t lock; }; struct dlm_lkbtable { diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index 6cfe65bbf4a..01e7d39c5fb 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -412,9 +412,9 @@ static int search_rsb(struct dlm_ls *ls, char *name, int len, int b, unsigned int flags, struct dlm_rsb **r_ret) { int error; - write_lock(&ls->ls_rsbtbl[b].lock); + spin_lock(&ls->ls_rsbtbl[b].lock); error = _search_rsb(ls, name, len, b, flags, r_ret); - write_unlock(&ls->ls_rsbtbl[b].lock); + spin_unlock(&ls->ls_rsbtbl[b].lock); return error; } @@ -478,16 +478,16 @@ static int find_rsb(struct dlm_ls *ls, char *name, int namelen, r->res_nodeid = nodeid; } - write_lock(&ls->ls_rsbtbl[bucket].lock); + spin_lock(&ls->ls_rsbtbl[bucket].lock); error = _search_rsb(ls, name, namelen, bucket, 0, &tmp); if (!error) { - write_unlock(&ls->ls_rsbtbl[bucket].lock); + spin_unlock(&ls->ls_rsbtbl[bucket].lock); dlm_free_rsb(r); r = tmp; goto out; } list_add(&r->res_hashchain, &ls->ls_rsbtbl[bucket].list); - write_unlock(&ls->ls_rsbtbl[bucket].lock); + spin_unlock(&ls->ls_rsbtbl[bucket].lock); error = 0; out: *r_ret = r; @@ -530,9 +530,9 @@ static void put_rsb(struct dlm_rsb *r) struct dlm_ls *ls = r->res_ls; uint32_t bucket = r->res_bucket; - write_lock(&ls->ls_rsbtbl[bucket].lock); + spin_lock(&ls->ls_rsbtbl[bucket].lock); kref_put(&r->res_ref, toss_rsb); - write_unlock(&ls->ls_rsbtbl[bucket].lock); + spin_unlock(&ls->ls_rsbtbl[bucket].lock); } void dlm_put_rsb(struct dlm_rsb *r) @@ -967,7 +967,7 @@ static int shrink_bucket(struct dlm_ls *ls, int b) for (;;) { found = 0; - write_lock(&ls->ls_rsbtbl[b].lock); + spin_lock(&ls->ls_rsbtbl[b].lock); list_for_each_entry_reverse(r, &ls->ls_rsbtbl[b].toss, res_hashchain) { if (!time_after_eq(jiffies, r->res_toss_time + @@ -978,20 +978,20 @@ static int shrink_bucket(struct dlm_ls *ls, int b) } if (!found) { - write_unlock(&ls->ls_rsbtbl[b].lock); + spin_unlock(&ls->ls_rsbtbl[b].lock); break; } if (kref_put(&r->res_ref, kill_rsb)) { list_del(&r->res_hashchain); - write_unlock(&ls->ls_rsbtbl[b].lock); + spin_unlock(&ls->ls_rsbtbl[b].lock); if (is_master(r)) dir_remove(r); dlm_free_rsb(r); count++; } else { - write_unlock(&ls->ls_rsbtbl[b].lock); + spin_unlock(&ls->ls_rsbtbl[b].lock); log_error(ls, "tossed rsb in use %s", r->res_name); } } @@ -4224,7 +4224,7 @@ static struct dlm_rsb *find_purged_rsb(struct dlm_ls *ls, int bucket) { struct dlm_rsb *r, *r_ret = NULL; - read_lock(&ls->ls_rsbtbl[bucket].lock); + spin_lock(&ls->ls_rsbtbl[bucket].lock); list_for_each_entry(r, &ls->ls_rsbtbl[bucket].list, res_hashchain) { if (!rsb_flag(r, RSB_LOCKS_PURGED)) continue; @@ -4233,7 +4233,7 @@ static struct dlm_rsb *find_purged_rsb(struct dlm_ls *ls, int bucket) r_ret = r; break; } - read_unlock(&ls->ls_rsbtbl[bucket].lock); + spin_unlock(&ls->ls_rsbtbl[bucket].lock); return r_ret; } diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 8d86b7960f0..aa32e5f0249 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -464,7 +464,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace, for (i = 0; i < size; i++) { INIT_LIST_HEAD(&ls->ls_rsbtbl[i].list); INIT_LIST_HEAD(&ls->ls_rsbtbl[i].toss); - rwlock_init(&ls->ls_rsbtbl[i].lock); + spin_lock_init(&ls->ls_rsbtbl[i].lock); } size = dlm_config.ci_lkbtbl_size; diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index eba87ff3177..894a32d438d 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -168,7 +168,7 @@ static int dlm_plock_callback(struct plock_op *op) notify = xop->callback; if (op->info.rv) { - notify(flc, NULL, op->info.rv); + notify(fl, NULL, op->info.rv); goto out; } @@ -187,7 +187,7 @@ static int dlm_plock_callback(struct plock_op *op) (unsigned long long)op->info.number, file, fl); } - rv = notify(flc, NULL, 0); + rv = notify(fl, NULL, 0); if (rv) { /* XXX: We need to cancel the fs lock here: */ log_print("dlm_plock_callback: lock granted after lock request " @@ -304,7 +304,9 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file, if (rv == -ENOENT) rv = 0; else if (rv > 0) { + locks_init_lock(fl); fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK; + fl->fl_flags = FL_POSIX; fl->fl_pid = op->info.pid; fl->fl_start = op->info.start; fl->fl_end = op->info.end; diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c index 80aba5bdd4a..eda43f36261 100644 --- a/fs/dlm/recover.c +++ b/fs/dlm/recover.c @@ -726,7 +726,7 @@ int dlm_create_root_list(struct dlm_ls *ls) } for (i = 0; i < ls->ls_rsbtbl_size; i++) { - read_lock(&ls->ls_rsbtbl[i].lock); + spin_lock(&ls->ls_rsbtbl[i].lock); list_for_each_entry(r, &ls->ls_rsbtbl[i].list, res_hashchain) { list_add(&r->res_root_list, &ls->ls_root_list); dlm_hold_rsb(r); @@ -737,7 +737,7 @@ int dlm_create_root_list(struct dlm_ls *ls) but no other recovery steps should do anything with them. */ if (dlm_no_directory(ls)) { - read_unlock(&ls->ls_rsbtbl[i].lock); + spin_unlock(&ls->ls_rsbtbl[i].lock); continue; } @@ -745,7 +745,7 @@ int dlm_create_root_list(struct dlm_ls *ls) list_add(&r->res_root_list, &ls->ls_root_list); dlm_hold_rsb(r); } - read_unlock(&ls->ls_rsbtbl[i].lock); + spin_unlock(&ls->ls_rsbtbl[i].lock); } out: up_write(&ls->ls_root_sem); @@ -775,7 +775,7 @@ void dlm_clear_toss_list(struct dlm_ls *ls) int i; for (i = 0; i < ls->ls_rsbtbl_size; i++) { - write_lock(&ls->ls_rsbtbl[i].lock); + spin_lock(&ls->ls_rsbtbl[i].lock); list_for_each_entry_safe(r, safe, &ls->ls_rsbtbl[i].toss, res_hashchain) { if (dlm_no_directory(ls) || !is_master(r)) { @@ -783,7 +783,7 @@ void dlm_clear_toss_list(struct dlm_ls *ls) dlm_free_rsb(r); } } - write_unlock(&ls->ls_rsbtbl[i].lock); + spin_unlock(&ls->ls_rsbtbl[i].lock); } } diff --git a/fs/dquot.c b/fs/dquot.c index 48c0571f831..bca3cac4bee 100644 --- a/fs/dquot.c +++ b/fs/dquot.c @@ -87,14 +87,17 @@ #define __DQUOT_PARANOIA /* - * There are two quota SMP locks. dq_list_lock protects all lists with quotas - * and quota formats and also dqstats structure containing statistics about the - * lists. dq_data_lock protects data from dq_dqb and also mem_dqinfo structures - * and also guards consistency of dquot->dq_dqb with inode->i_blocks, i_bytes. + * There are three quota SMP locks. dq_list_lock protects all lists with quotas + * and quota formats, dqstats structure containing statistics about the lists + * dq_data_lock protects data from dq_dqb and also mem_dqinfo structures and + * also guards consistency of dquot->dq_dqb with inode->i_blocks, i_bytes. * i_blocks and i_bytes updates itself are guarded by i_lock acquired directly - * in inode_add_bytes() and inode_sub_bytes(). + * in inode_add_bytes() and inode_sub_bytes(). dq_state_lock protects + * modifications of quota state (on quotaon and quotaoff) and readers who care + * about latest values take it as well. * - * The spinlock ordering is hence: dq_data_lock > dq_list_lock > i_lock + * The spinlock ordering is hence: dq_data_lock > dq_list_lock > i_lock, + * dq_list_lock > dq_state_lock * * Note that some things (eg. sb pointer, type, id) doesn't change during * the life of the dquot structure and so needn't to be protected by a lock @@ -103,12 +106,7 @@ * operation is just reading pointers from inode (or not using them at all) the * read lock is enough. If pointers are altered function must hold write lock * (these locking rules also apply for S_NOQUOTA flag in the inode - note that - * for altering the flag i_mutex is also needed). If operation is holding - * reference to dquot in other way (e.g. quotactl ops) it must be guarded by - * dqonoff_mutex. - * This locking assures that: - * a) update/access to dquot pointers in inode is serialized - * b) everyone is guarded against invalidate_dquots() + * for altering the flag i_mutex is also needed). * * Each dquot has its dq_lock mutex. Locked dquots might not be referenced * from inodes (dquot_alloc_space() and such don't check the dq_lock). @@ -122,10 +120,17 @@ * Lock ordering (including related VFS locks) is the following: * i_mutex > dqonoff_sem > journal_lock > dqptr_sem > dquot->dq_lock > * dqio_mutex + * The lock ordering of dqptr_sem imposed by quota code is only dqonoff_sem > + * dqptr_sem. But filesystem has to count with the fact that functions such as + * dquot_alloc_space() acquire dqptr_sem and they usually have to be called + * from inside a transaction to keep filesystem consistency after a crash. Also + * filesystems usually want to do some IO on dquot from ->mark_dirty which is + * called with dqptr_sem held. * i_mutex on quota files is special (it's below dqio_mutex) */ static DEFINE_SPINLOCK(dq_list_lock); +static DEFINE_SPINLOCK(dq_state_lock); DEFINE_SPINLOCK(dq_data_lock); static char *quotatypes[] = INITQFNAMES; @@ -428,7 +433,7 @@ static inline void do_destroy_dquot(struct dquot *dquot) * quota is disabled and pointers from inodes removed so there cannot be new * quota users. There can still be some users of quotas due to inodes being * just deleted or pruned by prune_icache() (those are not attached to any - * list). We have to wait for such users. + * list) or parallel quotactl call. We have to wait for such users. */ static void invalidate_dquots(struct super_block *sb, int type) { @@ -600,7 +605,6 @@ static struct shrinker dqcache_shrinker = { /* * Put reference to dquot * NOTE: If you change this function please check whether dqput_blocks() works right... - * MUST be called with either dqptr_sem or dqonoff_mutex held */ void dqput(struct dquot *dquot) { @@ -697,36 +701,30 @@ static struct dquot *get_empty_dquot(struct super_block *sb, int type) } /* - * Check whether dquot is in memory. - * MUST be called with either dqptr_sem or dqonoff_mutex held - */ -int dquot_is_cached(struct super_block *sb, unsigned int id, int type) -{ - unsigned int hashent = hashfn(sb, id, type); - int ret = 0; - - if (!sb_has_quota_active(sb, type)) - return 0; - spin_lock(&dq_list_lock); - if (find_dquot(hashent, sb, id, type) != NODQUOT) - ret = 1; - spin_unlock(&dq_list_lock); - return ret; -} - -/* * Get reference to dquot - * MUST be called with either dqptr_sem or dqonoff_mutex held + * + * Locking is slightly tricky here. We are guarded from parallel quotaoff() + * destroying our dquot by: + * a) checking for quota flags under dq_list_lock and + * b) getting a reference to dquot before we release dq_list_lock */ struct dquot *dqget(struct super_block *sb, unsigned int id, int type) { unsigned int hashent = hashfn(sb, id, type); - struct dquot *dquot, *empty = NODQUOT; + struct dquot *dquot = NODQUOT, *empty = NODQUOT; if (!sb_has_quota_active(sb, type)) return NODQUOT; we_slept: spin_lock(&dq_list_lock); + spin_lock(&dq_state_lock); + if (!sb_has_quota_active(sb, type)) { + spin_unlock(&dq_state_lock); + spin_unlock(&dq_list_lock); + goto out; + } + spin_unlock(&dq_state_lock); + if ((dquot = find_dquot(hashent, sb, id, type)) == NODQUOT) { if (empty == NODQUOT) { spin_unlock(&dq_list_lock); @@ -735,6 +733,7 @@ we_slept: goto we_slept; } dquot = empty; + empty = NODQUOT; dquot->dq_id = id; /* all dquots go on the inuse_list */ put_inuse(dquot); @@ -749,8 +748,6 @@ we_slept: dqstats.cache_hits++; dqstats.lookups++; spin_unlock(&dq_list_lock); - if (empty) - do_destroy_dquot(empty); } /* Wait for dq_lock - after this we know that either dquot_release() is already * finished or it will be canceled due to dq_count > 1 test */ @@ -758,11 +755,15 @@ we_slept: /* Read the dquot and instantiate it (everything done only if needed) */ if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && sb->dq_op->acquire_dquot(dquot) < 0) { dqput(dquot); - return NODQUOT; + dquot = NODQUOT; + goto out; } #ifdef __DQUOT_PARANOIA BUG_ON(!dquot->dq_sb); /* Has somebody invalidated entry under us? */ #endif +out: + if (empty) + do_destroy_dquot(empty); return dquot; } @@ -1198,63 +1199,76 @@ static int info_bdq_free(struct dquot *dquot, qsize_t space) } /* * Initialize quota pointers in inode - * Transaction must be started at entry + * We do things in a bit complicated way but by that we avoid calling + * dqget() and thus filesystem callbacks under dqptr_sem. */ int dquot_initialize(struct inode *inode, int type) { unsigned int id = 0; int cnt, ret = 0; + struct dquot *got[MAXQUOTAS] = { NODQUOT, NODQUOT }; + struct super_block *sb = inode->i_sb; /* First test before acquiring mutex - solves deadlocks when we * re-enter the quota code and are already holding the mutex */ if (IS_NOQUOTA(inode)) return 0; - down_write(&sb_dqopt(inode->i_sb)->dqptr_sem); + + /* First get references to structures we might need. */ + for (cnt = 0; cnt < MAXQUOTAS; cnt++) { + if (type != -1 && cnt != type) + continue; + switch (cnt) { + case USRQUOTA: + id = inode->i_uid; + break; + case GRPQUOTA: + id = inode->i_gid; + break; + } + got[cnt] = dqget(sb, id, cnt); + } + + down_write(&sb_dqopt(sb)->dqptr_sem); /* Having dqptr_sem we know NOQUOTA flags can't be altered... */ if (IS_NOQUOTA(inode)) goto out_err; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; + /* Avoid races with quotaoff() */ + if (!sb_has_quota_active(sb, cnt)) + continue; if (inode->i_dquot[cnt] == NODQUOT) { - switch (cnt) { - case USRQUOTA: - id = inode->i_uid; - break; - case GRPQUOTA: - id = inode->i_gid; - break; - } - inode->i_dquot[cnt] = dqget(inode->i_sb, id, cnt); + inode->i_dquot[cnt] = got[cnt]; + got[cnt] = NODQUOT; } } out_err: - up_write(&sb_dqopt(inode->i_sb)->dqptr_sem); + up_write(&sb_dqopt(sb)->dqptr_sem); + /* Drop unused references */ + for (cnt = 0; cnt < MAXQUOTAS; cnt++) + dqput(got[cnt]); return ret; } /* * Release all quotas referenced by inode - * Transaction must be started at an entry */ -int dquot_drop_locked(struct inode *inode) +int dquot_drop(struct inode *inode) { int cnt; + struct dquot *put[MAXQUOTAS]; + down_write(&sb_dqopt(inode->i_sb)->dqptr_sem); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (inode->i_dquot[cnt] != NODQUOT) { - dqput(inode->i_dquot[cnt]); - inode->i_dquot[cnt] = NODQUOT; - } + put[cnt] = inode->i_dquot[cnt]; + inode->i_dquot[cnt] = NODQUOT; } - return 0; -} - -int dquot_drop(struct inode *inode) -{ - down_write(&sb_dqopt(inode->i_sb)->dqptr_sem); - dquot_drop_locked(inode); up_write(&sb_dqopt(inode->i_sb)->dqptr_sem); + + for (cnt = 0; cnt < MAXQUOTAS; cnt++) + dqput(put[cnt]); return 0; } @@ -1470,8 +1484,9 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr) qsize_t space; struct dquot *transfer_from[MAXQUOTAS]; struct dquot *transfer_to[MAXQUOTAS]; - int cnt, ret = NO_QUOTA, chuid = (iattr->ia_valid & ATTR_UID) && inode->i_uid != iattr->ia_uid, - chgid = (iattr->ia_valid & ATTR_GID) && inode->i_gid != iattr->ia_gid; + int cnt, ret = QUOTA_OK; + int chuid = iattr->ia_valid & ATTR_UID && inode->i_uid != iattr->ia_uid, + chgid = iattr->ia_valid & ATTR_GID && inode->i_gid != iattr->ia_gid; char warntype_to[MAXQUOTAS]; char warntype_from_inodes[MAXQUOTAS], warntype_from_space[MAXQUOTAS]; @@ -1479,21 +1494,11 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr) * re-enter the quota code and are already holding the mutex */ if (IS_NOQUOTA(inode)) return QUOTA_OK; - /* Clear the arrays */ + /* Initialize the arrays */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - transfer_to[cnt] = transfer_from[cnt] = NODQUOT; + transfer_from[cnt] = NODQUOT; + transfer_to[cnt] = NODQUOT; warntype_to[cnt] = QUOTA_NL_NOWARN; - } - down_write(&sb_dqopt(inode->i_sb)->dqptr_sem); - /* Now recheck reliably when holding dqptr_sem */ - if (IS_NOQUOTA(inode)) { /* File without quota accounting? */ - up_write(&sb_dqopt(inode->i_sb)->dqptr_sem); - return QUOTA_OK; - } - /* First build the transfer_to list - here we can block on - * reading/instantiating of dquots. We know that the transaction for - * us was already started so we don't violate lock ranking here */ - for (cnt = 0; cnt < MAXQUOTAS; cnt++) { switch (cnt) { case USRQUOTA: if (!chuid) @@ -1507,6 +1512,13 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr) break; } } + + down_write(&sb_dqopt(inode->i_sb)->dqptr_sem); + /* Now recheck reliably when holding dqptr_sem */ + if (IS_NOQUOTA(inode)) { /* File without quota accounting? */ + up_write(&sb_dqopt(inode->i_sb)->dqptr_sem); + goto put_all; + } spin_lock(&dq_data_lock); space = inode_get_bytes(inode); /* Build the transfer_from list and check the limits */ @@ -1517,7 +1529,7 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr) if (check_idq(transfer_to[cnt], 1, warntype_to + cnt) == NO_QUOTA || check_bdq(transfer_to[cnt], space, 0, warntype_to + cnt) == NO_QUOTA) - goto warn_put_all; + goto over_quota; } /* @@ -1545,28 +1557,37 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr) inode->i_dquot[cnt] = transfer_to[cnt]; } - ret = QUOTA_OK; -warn_put_all: spin_unlock(&dq_data_lock); + up_write(&sb_dqopt(inode->i_sb)->dqptr_sem); + /* Dirtify all the dquots - this can block when journalling */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (transfer_from[cnt]) mark_dquot_dirty(transfer_from[cnt]); - if (transfer_to[cnt]) + if (transfer_to[cnt]) { mark_dquot_dirty(transfer_to[cnt]); + /* The reference we got is transferred to the inode */ + transfer_to[cnt] = NODQUOT; + } } +warn_put_all: flush_warnings(transfer_to, warntype_to); flush_warnings(transfer_from, warntype_from_inodes); flush_warnings(transfer_from, warntype_from_space); - +put_all: for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (ret == QUOTA_OK && transfer_from[cnt] != NODQUOT) - dqput(transfer_from[cnt]); - if (ret == NO_QUOTA && transfer_to[cnt] != NODQUOT) - dqput(transfer_to[cnt]); + dqput(transfer_from[cnt]); + dqput(transfer_to[cnt]); } - up_write(&sb_dqopt(inode->i_sb)->dqptr_sem); return ret; +over_quota: + spin_unlock(&dq_data_lock); + up_write(&sb_dqopt(inode->i_sb)->dqptr_sem); + /* Clear dquot pointers we don't want to dqput() */ + for (cnt = 0; cnt < MAXQUOTAS; cnt++) + transfer_from[cnt] = NODQUOT; + ret = NO_QUOTA; + goto warn_put_all; } /* Wrapper for transferring ownership of an inode */ @@ -1651,19 +1672,24 @@ int vfs_quota_disable(struct super_block *sb, int type, unsigned int flags) continue; if (flags & DQUOT_SUSPENDED) { + spin_lock(&dq_state_lock); dqopt->flags |= dquot_state_flag(DQUOT_SUSPENDED, cnt); + spin_unlock(&dq_state_lock); } else { + spin_lock(&dq_state_lock); dqopt->flags &= ~dquot_state_flag(flags, cnt); /* Turning off suspended quotas? */ if (!sb_has_quota_loaded(sb, cnt) && sb_has_quota_suspended(sb, cnt)) { dqopt->flags &= ~dquot_state_flag( DQUOT_SUSPENDED, cnt); + spin_unlock(&dq_state_lock); iput(dqopt->files[cnt]); dqopt->files[cnt] = NULL; continue; } + spin_unlock(&dq_state_lock); } /* We still have to keep quota loaded? */ @@ -1830,7 +1856,9 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, } mutex_unlock(&dqopt->dqio_mutex); mutex_unlock(&inode->i_mutex); + spin_lock(&dq_state_lock); dqopt->flags |= dquot_state_flag(flags, type); + spin_unlock(&dq_state_lock); add_dquot_ref(sb, type); mutex_unlock(&dqopt->dqonoff_mutex); @@ -1872,9 +1900,11 @@ static int vfs_quota_on_remount(struct super_block *sb, int type) } inode = dqopt->files[type]; dqopt->files[type] = NULL; + spin_lock(&dq_state_lock); flags = dqopt->flags & dquot_state_flag(DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED, type); dqopt->flags &= ~dquot_state_flag(DQUOT_STATE_FLAGS, type); + spin_unlock(&dq_state_lock); mutex_unlock(&dqopt->dqonoff_mutex); flags = dquot_generic_flag(flags, type); @@ -1952,7 +1982,9 @@ int vfs_quota_enable(struct inode *inode, int type, int format_id, ret = -EBUSY; goto out_lock; } + spin_lock(&dq_state_lock); sb_dqopt(sb)->flags |= dquot_state_flag(flags, type); + spin_unlock(&dq_state_lock); out_lock: mutex_unlock(&dqopt->dqonoff_mutex); return ret; @@ -2039,14 +2071,12 @@ int vfs_get_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *d { struct dquot *dquot; - mutex_lock(&sb_dqopt(sb)->dqonoff_mutex); - if (!(dquot = dqget(sb, id, type))) { - mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex); + dquot = dqget(sb, id, type); + if (dquot == NODQUOT) return -ESRCH; - } do_get_dqblk(dquot, di); dqput(dquot); - mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex); + return 0; } @@ -2130,7 +2160,6 @@ int vfs_set_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *d struct dquot *dquot; int rc; - mutex_lock(&sb_dqopt(sb)->dqonoff_mutex); dquot = dqget(sb, id, type); if (!dquot) { rc = -ESRCH; @@ -2139,7 +2168,6 @@ int vfs_set_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *d rc = do_set_dqblk(dquot, di); dqput(dquot); out: - mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex); return rc; } @@ -2370,11 +2398,9 @@ EXPORT_SYMBOL(dquot_release); EXPORT_SYMBOL(dquot_mark_dquot_dirty); EXPORT_SYMBOL(dquot_initialize); EXPORT_SYMBOL(dquot_drop); -EXPORT_SYMBOL(dquot_drop_locked); EXPORT_SYMBOL(vfs_dq_drop); EXPORT_SYMBOL(dqget); EXPORT_SYMBOL(dqput); -EXPORT_SYMBOL(dquot_is_cached); EXPORT_SYMBOL(dquot_alloc_space); EXPORT_SYMBOL(dquot_alloc_inode); EXPORT_SYMBOL(dquot_free_space); diff --git a/fs/ecryptfs/Kconfig b/fs/ecryptfs/Kconfig new file mode 100644 index 00000000000..0c754e64232 --- /dev/null +++ b/fs/ecryptfs/Kconfig @@ -0,0 +1,11 @@ +config ECRYPT_FS + tristate "eCrypt filesystem layer support (EXPERIMENTAL)" + depends on EXPERIMENTAL && KEYS && CRYPTO && NET + help + Encrypted filesystem that operates on the VFS layer. See + <file:Documentation/filesystems/ecryptfs.txt> to learn more about + eCryptfs. Userspace components are required and can be + obtained from <http://ecryptfs.sf.net>. + + To compile this file system support as a module, choose M here: the + module will be called ecryptfs. diff --git a/fs/efs/Kconfig b/fs/efs/Kconfig new file mode 100644 index 00000000000..6ebfc1c207a --- /dev/null +++ b/fs/efs/Kconfig @@ -0,0 +1,14 @@ +config EFS_FS + tristate "EFS file system support (read only) (EXPERIMENTAL)" + depends on BLOCK && EXPERIMENTAL + help + EFS is an older file system used for non-ISO9660 CD-ROMs and hard + disk partitions by SGI's IRIX operating system (IRIX 6.0 and newer + uses the XFS file system for hard disk partitions however). + + This implementation only offers read-only access. If you don't know + what all this is about, it's safe to say N. For more information + about EFS see its home page at <http://aeschi.ch.eu.org/efs/>. + + To compile the EFS file system support as a module, choose M here: the + module will be called efs. diff --git a/fs/eventfd.c b/fs/eventfd.c index 08bf558d040..5de2c2db3aa 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -198,7 +198,7 @@ struct file *eventfd_fget(int fd) return file; } -asmlinkage long sys_eventfd2(unsigned int count, int flags) +SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags) { int fd; struct eventfd_ctx *ctx; @@ -228,8 +228,7 @@ asmlinkage long sys_eventfd2(unsigned int count, int flags) return fd; } -asmlinkage long sys_eventfd(unsigned int count) +SYSCALL_DEFINE1(eventfd, unsigned int, count) { return sys_eventfd2(count, 0); } - diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 96355d50534..011b9b8c90c 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -234,8 +234,6 @@ struct ep_pqueue { /* * Configuration options available inside /proc/sys/fs/epoll/ */ -/* Maximum number of epoll devices, per user */ -static int max_user_instances __read_mostly; /* Maximum number of epoll watched descriptors, per user */ static int max_user_watches __read_mostly; @@ -261,14 +259,6 @@ static int zero; ctl_table epoll_table[] = { { - .procname = "max_user_instances", - .data = &max_user_instances, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .extra1 = &zero, - }, - { .procname = "max_user_watches", .data = &max_user_watches, .maxlen = sizeof(int), @@ -491,7 +481,6 @@ static void ep_free(struct eventpoll *ep) mutex_unlock(&epmutex); mutex_destroy(&ep->mtx); - atomic_dec(&ep->user->epoll_devs); free_uid(ep->user); kfree(ep); } @@ -581,10 +570,6 @@ static int ep_alloc(struct eventpoll **pep) struct eventpoll *ep; user = get_current_user(); - error = -EMFILE; - if (unlikely(atomic_read(&user->epoll_devs) >= - max_user_instances)) - goto free_uid; error = -ENOMEM; ep = kzalloc(sizeof(*ep), GFP_KERNEL); if (unlikely(!ep)) @@ -1110,7 +1095,7 @@ retry: /* * Open an eventpoll file descriptor. */ -asmlinkage long sys_epoll_create1(int flags) +SYSCALL_DEFINE1(epoll_create1, int, flags) { int error, fd = -1; struct eventpoll *ep; @@ -1141,7 +1126,6 @@ asmlinkage long sys_epoll_create1(int flags) flags & O_CLOEXEC); if (fd < 0) ep_free(ep); - atomic_inc(&ep->user->epoll_devs); error_return: DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n", @@ -1150,7 +1134,7 @@ error_return: return fd; } -asmlinkage long sys_epoll_create(int size) +SYSCALL_DEFINE1(epoll_create, int, size) { if (size < 0) return -EINVAL; @@ -1163,8 +1147,8 @@ asmlinkage long sys_epoll_create(int size) * the eventpoll file that enables the insertion/removal/change of * file descriptors inside the interest set. */ -asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, - struct epoll_event __user *event) +SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, + struct epoll_event __user *, event) { int error; struct file *file, *tfile; @@ -1261,8 +1245,8 @@ error_return: * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_wait(2). */ -asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, - int maxevents, int timeout) +SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events, + int, maxevents, int, timeout) { int error; struct file *file; @@ -1319,9 +1303,9 @@ error_return: * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_pwait(2). */ -asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events, - int maxevents, int timeout, const sigset_t __user *sigmask, - size_t sigsetsize) +SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, + int, maxevents, int, timeout, const sigset_t __user *, sigmask, + size_t, sigsetsize) { int error; sigset_t ksigmask, sigsaved; @@ -1366,8 +1350,10 @@ static int __init eventpoll_init(void) struct sysinfo si; si_meminfo(&si); - max_user_instances = 128; - max_user_watches = (((si.totalram - si.totalhigh) / 32) << PAGE_SHIFT) / + /* + * Allows top 4% of lomem to be allocated for epoll watches (per user). + */ + max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) / EP_ITEM_COST; /* Initialize the structure used to perform safe poll wait head wake ups */ diff --git a/fs/exec.c b/fs/exec.c index 71a6efe5d8b..0dd60a01f1b 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -99,7 +99,7 @@ static inline void put_binfmt(struct linux_binfmt * fmt) * * Also note that we take the address to load from from the file itself. */ -asmlinkage long sys_uselib(const char __user * library) +SYSCALL_DEFINE1(uselib, const char __user *, library) { struct file *file; struct nameidata nd; diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 9a0fc400f91..2999d72153b 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -95,10 +95,13 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len) mark_inode_dirty(dir); } - if (IS_DIRSYNC(dir)) + if (IS_DIRSYNC(dir)) { err = write_one_page(page, 1); - else + if (!err) + err = ext2_sync_inode(dir); + } else { unlock_page(page); + } return err; } diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 69a3d19ca9f..4db4ffa1eda 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1358,7 +1358,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, struct fake_dirent *fde; blocksize = dir->i_sb->s_blocksize; - dxtrace(printk("Creating index\n")); + dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino)); retval = ext3_journal_get_write_access(handle, bh); if (retval) { ext3_std_error(dir->i_sb, retval); @@ -1367,6 +1367,19 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, } root = (struct dx_root *) bh->b_data; + /* The 0th block becomes the root, move the dirents out */ + fde = &root->dotdot; + de = (struct ext3_dir_entry_2 *)((char *)fde + + ext3_rec_len_from_disk(fde->rec_len)); + if ((char *) de >= (((char *) root) + blocksize)) { + ext3_error(dir->i_sb, __func__, + "invalid rec_len for '..' in inode %lu", + dir->i_ino); + brelse(bh); + return -EIO; + } + len = ((char *) root) + blocksize - (char *) de; + bh2 = ext3_append (handle, dir, &block, &retval); if (!(bh2)) { brelse(bh); @@ -1375,11 +1388,6 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, EXT3_I(dir)->i_flags |= EXT3_INDEX_FL; data1 = bh2->b_data; - /* The 0th block becomes the root, move the dirents out */ - fde = &root->dotdot; - de = (struct ext3_dir_entry_2 *)((char *)fde + - ext3_rec_len_from_disk(fde->rec_len)); - len = ((char *) root) + blocksize - (char *) de; memcpy (data1, de, len); de = (struct ext3_dir_entry_2 *) data1; top = data1 + len; diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 6bba06b09dd..9a50b8052dc 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -684,15 +684,15 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) gdp = ext4_get_group_desc(sb, i, NULL); if (!gdp) continue; - desc_count += le16_to_cpu(gdp->bg_free_blocks_count); + desc_count += ext4_free_blks_count(sb, gdp); brelse(bitmap_bh); bitmap_bh = ext4_read_block_bitmap(sb, i); if (bitmap_bh == NULL) continue; x = ext4_count_free(bitmap_bh, sb->s_blocksize); - printk(KERN_DEBUG "group %lu: stored = %d, counted = %u\n", - i, le16_to_cpu(gdp->bg_free_blocks_count), x); + printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n", + i, ext4_free_blks_count(sb, gdp), x); bitmap_count += x; } brelse(bitmap_bh); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index c668e4377d7..aafc9eba1c2 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1206,8 +1206,11 @@ static inline void ext4_r_blocks_count_set(struct ext4_super_block *es, static inline loff_t ext4_isize(struct ext4_inode *raw_inode) { - return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) | - le32_to_cpu(raw_inode->i_size_lo); + if (S_ISREG(le16_to_cpu(raw_inode->i_mode))) + return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) | + le32_to_cpu(raw_inode->i_size_lo); + else + return (loff_t) le32_to_cpu(raw_inode->i_size_lo); } static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 54bf0623a9a..e2eab196875 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3048,7 +3048,7 @@ retry: WARN_ON(ret <= 0); printk(KERN_ERR "%s: ext4_ext_get_blocks " "returned error inode#%lu, block=%u, " - "max_blocks=%lu", __func__, + "max_blocks=%u", __func__, inode->i_ino, block, max_blocks); #endif ext4_mark_inode_dirty(handle, inode); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a6444cee0c7..03ba20be132 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -360,9 +360,9 @@ static int ext4_block_to_path(struct inode *inode, final = ptrs; } else { ext4_warning(inode->i_sb, "ext4_block_to_path", - "block %lu > max", + "block %lu > max in inode %lu", i_block + direct_blocks + - indirect_blocks + double_blocks); + indirect_blocks + double_blocks, inode->i_ino); } if (boundary) *boundary = final - 1 - (i_block & (ptrs - 1)); @@ -2821,9 +2821,6 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) filemap_write_and_wait(mapping); } - BUG_ON(!EXT4_JOURNAL(inode) && - EXT4_I(inode)->i_state & EXT4_STATE_JDATA); - if (EXT4_JOURNAL(inode) && EXT4_I(inode)->i_state & EXT4_STATE_JDATA) { /* * This is a REALLY heavyweight approach, but the use of @@ -3622,7 +3619,7 @@ static void ext4_free_data(handle_t *handle, struct inode *inode, * block pointed to itself, it would have been detached when * the block was cleared. Check for this instead of OOPSing. */ - if (bh2jh(this_bh)) + if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh)) ext4_handle_dirty_metadata(handle, inode, this_bh); else ext4_error(inode->i_sb, __func__, diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 918aec0c8a1..deba54f6cbe 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3025,7 +3025,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, goto out_err; ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group, - gdp->bg_free_blocks_count); + ext4_free_blks_count(sb, gdp)); err = ext4_journal_get_write_access(handle, gdp_bh); if (err) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index fec0b4c2f5f..ba702bd7910 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1368,7 +1368,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, struct fake_dirent *fde; blocksize = dir->i_sb->s_blocksize; - dxtrace(printk(KERN_DEBUG "Creating index\n")); + dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino)); retval = ext4_journal_get_write_access(handle, bh); if (retval) { ext4_std_error(dir->i_sb, retval); @@ -1377,6 +1377,20 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, } root = (struct dx_root *) bh->b_data; + /* The 0th block becomes the root, move the dirents out */ + fde = &root->dotdot; + de = (struct ext4_dir_entry_2 *)((char *)fde + + ext4_rec_len_from_disk(fde->rec_len)); + if ((char *) de >= (((char *) root) + blocksize)) { + ext4_error(dir->i_sb, __func__, + "invalid rec_len for '..' in inode %lu", + dir->i_ino); + brelse(bh); + return -EIO; + } + len = ((char *) root) + blocksize - (char *) de; + + /* Allocate new block for the 0th block's dirents */ bh2 = ext4_append(handle, dir, &block, &retval); if (!(bh2)) { brelse(bh); @@ -1385,11 +1399,6 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, EXT4_I(dir)->i_flags |= EXT4_INDEX_FL; data1 = bh2->b_data; - /* The 0th block becomes the root, move the dirents out */ - fde = &root->dotdot; - de = (struct ext4_dir_entry_2 *)((char *)fde + - ext4_rec_len_from_disk(fde->rec_len)); - len = ((char *) root) + blocksize - (char *) de; memcpy (data1, de, len); de = (struct ext4_dir_entry_2 *) data1; top = data1 + len; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index c328be5d688..c06886abd65 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -861,12 +861,13 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) gdp = (struct ext4_group_desc *)((char *)primary->b_data + gdb_off * EXT4_DESC_SIZE(sb)); + memset(gdp, 0, EXT4_DESC_SIZE(sb)); ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */ ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */ ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */ ext4_free_blks_set(sb, gdp, input->free_blocks_count); ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb)); - gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED); + gdp->bg_flags = cpu_to_le16(EXT4_BG_INODE_ZEROED); gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp); /* diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig new file mode 100644 index 00000000000..d0a69ff2537 --- /dev/null +++ b/fs/fat/Kconfig @@ -0,0 +1,97 @@ +config FAT_FS + tristate + select NLS + help + If you want to use one of the FAT-based file systems (the MS-DOS and + VFAT (Windows 95) file systems), then you must say Y or M here + to include FAT support. You will then be able to mount partitions or + diskettes with FAT-based file systems and transparently access the + files on them, i.e. MSDOS files will look and behave just like all + other Unix files. + + This FAT support is not a file system in itself, it only provides + the foundation for the other file systems. You will have to say Y or + M to at least one of "MSDOS fs support" or "VFAT fs support" in + order to make use of it. + + Another way to read and write MSDOS floppies and hard drive + partitions from within Linux (but not transparently) is with the + mtools ("man mtools") program suite. You don't need to say Y here in + order to do that. + + If you need to move large files on floppies between a DOS and a + Linux box, say Y here, mount the floppy under Linux with an MSDOS + file system and use GNU tar's M option. GNU tar is a program + available for Unix and DOS ("man tar" or "info tar"). + + The FAT support will enlarge your kernel by about 37 KB. If unsure, + say Y. + + To compile this as a module, choose M here: the module will be called + fat. Note that if you compile the FAT support as a module, you + cannot compile any of the FAT-based file systems into the kernel + -- they will have to be modules as well. + +config MSDOS_FS + tristate "MSDOS fs support" + select FAT_FS + help + This allows you to mount MSDOS partitions of your hard drive (unless + they are compressed; to access compressed MSDOS partitions under + Linux, you can either use the DOS emulator DOSEMU, described in the + DOSEMU-HOWTO, available from + <http://www.tldp.org/docs.html#howto>, or try dmsdosfs in + <ftp://ibiblio.org/pub/Linux/system/filesystems/dosfs/>. If you + intend to use dosemu with a non-compressed MSDOS partition, say Y + here) and MSDOS floppies. This means that file access becomes + transparent, i.e. the MSDOS files look and behave just like all + other Unix files. + + If you have Windows 95 or Windows NT installed on your MSDOS + partitions, you should use the VFAT file system (say Y to "VFAT fs + support" below), or you will not be able to see the long filenames + generated by Windows 95 / Windows NT. + + This option will enlarge your kernel by about 7 KB. If unsure, + answer Y. This will only work if you said Y to "DOS FAT fs support" + as well. To compile this as a module, choose M here: the module will + be called msdos. + +config VFAT_FS + tristate "VFAT (Windows-95) fs support" + select FAT_FS + help + This option provides support for normal Windows file systems with + long filenames. That includes non-compressed FAT-based file systems + used by Windows 95, Windows 98, Windows NT 4.0, and the Unix + programs from the mtools package. + + The VFAT support enlarges your kernel by about 10 KB and it only + works if you said Y to the "DOS FAT fs support" above. Please read + the file <file:Documentation/filesystems/vfat.txt> for details. If + unsure, say Y. + + To compile this as a module, choose M here: the module will be called + vfat. + +config FAT_DEFAULT_CODEPAGE + int "Default codepage for FAT" + depends on MSDOS_FS || VFAT_FS + default 437 + help + This option should be set to the codepage of your FAT filesystems. + It can be overridden with the "codepage" mount option. + See <file:Documentation/filesystems/vfat.txt> for more information. + +config FAT_DEFAULT_IOCHARSET + string "Default iocharset for FAT" + depends on VFAT_FS + default "iso8859-1" + help + Set this to the default input/output character set you'd + like FAT to use. It should probably match the character set + that most of your FAT filesystems use, and can be overridden + with the "iocharset" mount option for FAT filesystems. + Note that "utf8" is not recommended for FAT filesystems. + If unsure, you shouldn't set "utf8" here. + See <file:Documentation/filesystems/vfat.txt> for more information. diff --git a/fs/fcntl.c b/fs/fcntl.c index cdc14194672..bd215cc791d 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -50,7 +50,7 @@ static int get_close_on_exec(unsigned int fd) return res; } -asmlinkage long sys_dup3(unsigned int oldfd, unsigned int newfd, int flags) +SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { int err = -EBADF; struct file * file, *tofree; @@ -113,7 +113,7 @@ out_unlock: return err; } -asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd) +SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; @@ -126,7 +126,7 @@ asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd) return sys_dup3(oldfd, newfd, 0); } -asmlinkage long sys_dup(unsigned int fildes) +SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget(fildes); @@ -335,7 +335,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, return err; } -asmlinkage long sys_fcntl(unsigned int fd, unsigned int cmd, unsigned long arg) +SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct file *filp; long err = -EBADF; @@ -358,7 +358,8 @@ out: } #if BITS_PER_LONG == 32 -asmlinkage long sys_fcntl64(unsigned int fd, unsigned int cmd, unsigned long arg) +SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, + unsigned long, arg) { struct file * filp; long err; diff --git a/fs/filesystems.c b/fs/filesystems.c index d488dcd7f2b..1aa70260e6d 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -179,7 +179,7 @@ static int fs_maxindex(void) /* * Whee.. Weird sysv syscall. */ -asmlinkage long sys_sysfs(int option, unsigned long arg1, unsigned long arg2) +SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2) { int retval = -EINVAL; diff --git a/fs/freevxfs/Kconfig b/fs/freevxfs/Kconfig new file mode 100644 index 00000000000..8dc1cd5c1ef --- /dev/null +++ b/fs/freevxfs/Kconfig @@ -0,0 +1,16 @@ +config VXFS_FS + tristate "FreeVxFS file system support (VERITAS VxFS(TM) compatible)" + depends on BLOCK + help + FreeVxFS is a file system driver that support the VERITAS VxFS(TM) + file system format. VERITAS VxFS(TM) is the standard file system + of SCO UnixWare (and possibly others) and optionally available + for Sunsoft Solaris, HP-UX and many other operating systems. + Currently only readonly access is supported. + + NOTE: the file system type as used by mount(1), mount(2) and + fstab(5) is 'vxfs' as it describes the file system format, not + the actual driver. + + To compile this as a module, choose M here: the module will be + called freevxfs. If unsure, say N. diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig new file mode 100644 index 00000000000..0cf160a94ed --- /dev/null +++ b/fs/fuse/Kconfig @@ -0,0 +1,15 @@ +config FUSE_FS + tristate "FUSE (Filesystem in Userspace) support" + help + With FUSE it is possible to implement a fully functional filesystem + in a userspace program. + + There's also companion library: libfuse. This library along with + utilities is available from the FUSE homepage: + <http://fuse.sourceforge.net/> + + See <file:Documentation/filesystems/fuse.txt> for more information. + See <file:Documentation/Changes> for needed library/utility version. + + If you want to develop a userspace FS, or if you want to use + a filesystem based on FUSE, answer Y or M. diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index e0c7ada08a1..ba76b68c52f 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -281,7 +281,8 @@ __releases(&fc->lock) fc->blocked = 0; wake_up_all(&fc->blocked_waitq); } - if (fc->num_background == FUSE_CONGESTION_THRESHOLD) { + if (fc->num_background == FUSE_CONGESTION_THRESHOLD && + fc->connected) { clear_bdi_congested(&fc->bdi, READ); clear_bdi_congested(&fc->bdi, WRITE); } @@ -825,16 +826,21 @@ static int fuse_notify_poll(struct fuse_conn *fc, unsigned int size, struct fuse_copy_state *cs) { struct fuse_notify_poll_wakeup_out outarg; - int err; + int err = -EINVAL; if (size != sizeof(outarg)) - return -EINVAL; + goto err; err = fuse_copy_one(cs, &outarg, sizeof(outarg)); if (err) - return err; + goto err; + fuse_copy_finish(cs); return fuse_notify_poll_wakeup(fc, &outarg); + +err: + fuse_copy_finish(cs); + return err; } static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, @@ -845,6 +851,7 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, return fuse_notify_poll(fc, size, cs); default: + fuse_copy_finish(cs); return -EINVAL; } } @@ -923,7 +930,6 @@ static ssize_t fuse_dev_write(struct kiocb *iocb, const struct iovec *iov, */ if (!oh.unique) { err = fuse_notify(fc, oh.error, nbytes - sizeof(oh), &cs); - fuse_copy_finish(&cs); return err ? err : nbytes; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index e8162646a9b..d9fdb7cec53 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -54,7 +54,7 @@ struct fuse_file *fuse_file_alloc(struct fuse_conn *fc) ff->reserved_req = fuse_request_alloc(); if (!ff->reserved_req) { kfree(ff); - ff = NULL; + return NULL; } else { INIT_LIST_HEAD(&ff->write_entry); atomic_set(&ff->count, 0); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 47c96fdca1a..459b73dd45e 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -292,6 +292,7 @@ static void fuse_put_super(struct super_block *sb) list_del(&fc->entry); fuse_ctl_remove_conn(fc); mutex_unlock(&fuse_mutex); + bdi_destroy(&fc->bdi); fuse_conn_put(fc); } @@ -532,7 +533,6 @@ void fuse_conn_put(struct fuse_conn *fc) if (fc->destroy_req) fuse_request_free(fc->destroy_req); mutex_destroy(&fc->inst_mutex); - bdi_destroy(&fc->bdi); fc->release(fc); } } @@ -805,16 +805,18 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) int err; int is_bdev = sb->s_bdev != NULL; + err = -EINVAL; if (sb->s_flags & MS_MANDLOCK) - return -EINVAL; + goto err; if (!parse_fuse_opt((char *) data, &d, is_bdev)) - return -EINVAL; + goto err; if (is_bdev) { #ifdef CONFIG_BLOCK + err = -EINVAL; if (!sb_set_blocksize(sb, d.blksize)) - return -EINVAL; + goto err; #endif } else { sb->s_blocksize = PAGE_CACHE_SIZE; @@ -826,20 +828,22 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) sb->s_export_op = &fuse_export_operations; file = fget(d.fd); + err = -EINVAL; if (!file) - return -EINVAL; + goto err; if (file->f_op != &fuse_dev_operations) - return -EINVAL; + goto err_fput; fc = kmalloc(sizeof(*fc), GFP_KERNEL); + err = -ENOMEM; if (!fc) - return -ENOMEM; + goto err_fput; err = fuse_conn_init(fc, sb); if (err) { kfree(fc); - return err; + goto err_fput; } fc->release = fuse_free_conn; @@ -854,12 +858,12 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) err = -ENOMEM; root = fuse_get_root_inode(sb, d.rootmode); if (!root) - goto err; + goto err_put_conn; root_dentry = d_alloc_root(root); if (!root_dentry) { iput(root); - goto err; + goto err_put_conn; } init_req = fuse_request_alloc(); @@ -903,9 +907,11 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fuse_request_free(init_req); err_put_root: dput(root_dentry); - err: - fput(file); + err_put_conn: fuse_conn_put(fc); + err_fput: + fput(file); + err: return err; } diff --git a/fs/hfs/Kconfig b/fs/hfs/Kconfig new file mode 100644 index 00000000000..b77c5bc20f8 --- /dev/null +++ b/fs/hfs/Kconfig @@ -0,0 +1,12 @@ +config HFS_FS + tristate "Apple Macintosh file system support (EXPERIMENTAL)" + depends on BLOCK && EXPERIMENTAL + select NLS + help + If you say Y here, you will be able to mount Macintosh-formatted + floppy disks and hard drive partitions with full read-write access. + Please read <file:Documentation/filesystems/hfs.txt> to learn about + the available mount options. + + To compile this file system support as a module, choose M here: the + module will be called hfs. diff --git a/fs/hfsplus/Kconfig b/fs/hfsplus/Kconfig new file mode 100644 index 00000000000..a63371815aa --- /dev/null +++ b/fs/hfsplus/Kconfig @@ -0,0 +1,13 @@ +config HFSPLUS_FS + tristate "Apple Extended HFS file system support" + depends on BLOCK + select NLS + select NLS_UTF8 + help + If you say Y here, you will be able to mount extended format + Macintosh-formatted hard drive partitions with full read-write access. + + This file system is often called HFS+ and was introduced with + MacOS 8. It includes all Mac specific filesystem data such as + data forks and creator codes, but it also has several UNIX + style features such as file ownership and permissions. diff --git a/fs/hpfs/Kconfig b/fs/hpfs/Kconfig new file mode 100644 index 00000000000..56bd15c5bf6 --- /dev/null +++ b/fs/hpfs/Kconfig @@ -0,0 +1,14 @@ +config HPFS_FS + tristate "OS/2 HPFS file system support" + depends on BLOCK + help + OS/2 is IBM's operating system for PC's, the same as Warp, and HPFS + is the file system used for organizing files on OS/2 hard disk + partitions. Say Y if you want to be able to read files from and + write files to an OS/2 HPFS partition on your hard drive. OS/2 + floppies however are in regular MSDOS format, so you don't need this + option in order to be able to read them. Read + <file:Documentation/filesystems/hpfs.txt>. + + To compile this file system support as a module, choose M here: the + module will be called hpfs. If unsure, say N. diff --git a/fs/ioctl.c b/fs/ioctl.c index 20b0a8a24c6..240ec63984c 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -542,7 +542,7 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, return error; } -asmlinkage long sys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg) +SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct file *filp; int error = -EBADF; diff --git a/fs/ioprio.c b/fs/ioprio.c index 1a39ac37094..c7c0b28d7d2 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -72,7 +72,7 @@ int set_task_ioprio(struct task_struct *task, int ioprio) } EXPORT_SYMBOL_GPL(set_task_ioprio); -asmlinkage long sys_ioprio_set(int which, int who, int ioprio) +SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio) { int class = IOPRIO_PRIO_CLASS(ioprio); int data = IOPRIO_PRIO_DATA(ioprio); @@ -188,7 +188,7 @@ int ioprio_best(unsigned short aprio, unsigned short bprio) return aprio; } -asmlinkage long sys_ioprio_get(int which, int who) +SYSCALL_DEFINE2(ioprio_get, int, which, int, who) { struct task_struct *g, *p; struct user_struct *user; @@ -252,4 +252,3 @@ asmlinkage long sys_ioprio_get(int which, int who) read_unlock(&tasklist_lock); return ret; } - diff --git a/fs/isofs/Kconfig b/fs/isofs/Kconfig new file mode 100644 index 00000000000..8ab9878e367 --- /dev/null +++ b/fs/isofs/Kconfig @@ -0,0 +1,39 @@ +config ISO9660_FS + tristate "ISO 9660 CDROM file system support" + help + This is the standard file system used on CD-ROMs. It was previously + known as "High Sierra File System" and is called "hsfs" on other + Unix systems. The so-called Rock-Ridge extensions which allow for + long Unix filenames and symbolic links are also supported by this + driver. If you have a CD-ROM drive and want to do more with it than + just listen to audio CDs and watch its LEDs, say Y (and read + <file:Documentation/filesystems/isofs.txt> and the CD-ROM-HOWTO, + available from <http://www.tldp.org/docs.html#howto>), thereby + enlarging your kernel by about 27 KB; otherwise say N. + + To compile this file system support as a module, choose M here: the + module will be called isofs. + +config JOLIET + bool "Microsoft Joliet CDROM extensions" + depends on ISO9660_FS + select NLS + help + Joliet is a Microsoft extension for the ISO 9660 CD-ROM file system + which allows for long filenames in unicode format (unicode is the + new 16 bit character code, successor to ASCII, which encodes the + characters of almost all languages of the world; see + <http://www.unicode.org/> for more information). Say Y here if you + want to be able to read Joliet CD-ROMs under Linux. + +config ZISOFS + bool "Transparent decompression extension" + depends on ISO9660_FS + select ZLIB_INFLATE + help + This is a Linux-specific extension to RockRidge which lets you store + data in compressed form on a CD-ROM and have it transparently + decompressed when the CD-ROM is accessed. See + <http://www.kernel.org/pub/linux/utils/fs/zisofs/> for the tools + necessary to create such a filesystem. Say Y here if you want to be + able to read such compressed CD-ROMs. diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 56675306ed8..eb343008ede 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -37,10 +37,10 @@ #include <linux/proc_fs.h> #include <linux/debugfs.h> #include <linux/seq_file.h> +#include <linux/math64.h> #include <asm/uaccess.h> #include <asm/page.h> -#include <asm/div64.h> EXPORT_SYMBOL(jbd2_journal_start); EXPORT_SYMBOL(jbd2_journal_restart); @@ -846,8 +846,8 @@ static int jbd2_seq_info_show(struct seq_file *seq, void *v) jiffies_to_msecs(s->stats->u.run.rs_flushing / s->stats->ts_tid)); seq_printf(seq, " %ums logging transaction\n", jiffies_to_msecs(s->stats->u.run.rs_logging / s->stats->ts_tid)); - seq_printf(seq, " %luus average transaction commit time\n", - do_div(s->journal->j_average_commit_time, 1000)); + seq_printf(seq, " %lluus average transaction commit time\n", + div_u64(s->journal->j_average_commit_time, 1000)); seq_printf(seq, " %lu handles per transaction\n", s->stats->u.run.rs_handle_count / s->stats->ts_tid); seq_printf(seq, " %lu blocks per transaction\n", diff --git a/fs/jfs/Kconfig b/fs/jfs/Kconfig new file mode 100644 index 00000000000..9ff619a6f9c --- /dev/null +++ b/fs/jfs/Kconfig @@ -0,0 +1,49 @@ +config JFS_FS + tristate "JFS filesystem support" + select NLS + help + This is a port of IBM's Journaled Filesystem . More information is + available in the file <file:Documentation/filesystems/jfs.txt>. + + If you do not intend to use the JFS filesystem, say N. + +config JFS_POSIX_ACL + bool "JFS POSIX Access Control Lists" + depends on JFS_FS + select FS_POSIX_ACL + help + Posix Access Control Lists (ACLs) support permissions for users and + groups beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the Posix ACLs for + Linux website <http://acl.bestbits.at/>. + + If you don't know what Access Control Lists are, say N + +config JFS_SECURITY + bool "JFS Security Labels" + depends on JFS_FS + 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 jfs filesystem. + + If you are not using a security module that requires using + extended attributes for file security labels, say N. + +config JFS_DEBUG + bool "JFS debugging" + depends on JFS_FS + help + If you are experiencing any problems with the JFS filesystem, say + Y here. This will result in additional debugging messages to be + written to the system log. Under normal circumstances, this + results in very little overhead. + +config JFS_STATISTICS + bool "JFS statistics" + depends on JFS_FS + help + Enabling this option will cause statistics from the JFS file system + to be made available to the user in the /proc/fs/jfs/ directory. diff --git a/fs/locks.c b/fs/locks.c index 46a2e12f7d4..ec3deea29e3 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1564,7 +1564,7 @@ EXPORT_SYMBOL(flock_lock_file_wait); * %LOCK_MAND can be combined with %LOCK_READ or %LOCK_WRITE to allow other * processes read and write access respectively. */ -asmlinkage long sys_flock(unsigned int fd, unsigned int cmd) +SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) { struct file *filp; struct file_lock *lock; diff --git a/fs/minix/Kconfig b/fs/minix/Kconfig new file mode 100644 index 00000000000..0fd7ca99426 --- /dev/null +++ b/fs/minix/Kconfig @@ -0,0 +1,17 @@ +config MINIX_FS + tristate "Minix file system support" + depends on BLOCK + help + Minix is a simple operating system used in many classes about OS's. + The minix file system (method to organize files on a hard disk + partition or a floppy disk) was the original file system for Linux, + but has been superseded by the second extended file system ext2fs. + You don't want to use the minix file system on your hard disk + because of certain built-in restrictions, but it is sometimes found + on older Linux floppy disks. This option will enlarge your kernel + by about 28 KB. If unsure, say N. + + To compile this file system support as a module, choose M here: the + module will be called minix. Note that the file system of your root + partition (the one containing the directory /) cannot be compiled as + a module. diff --git a/fs/namei.c b/fs/namei.c index f05bed24242..bbc15c23755 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1962,8 +1962,8 @@ static int may_mknod(mode_t mode) } } -asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode, - unsigned dev) +SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, int, mode, + unsigned, dev) { int error; char *tmp; @@ -2017,7 +2017,7 @@ out_unlock: return error; } -asmlinkage long sys_mknod(const char __user *filename, int mode, unsigned dev) +SYSCALL_DEFINE3(mknod, const char __user *, filename, int, mode, unsigned, dev) { return sys_mknodat(AT_FDCWD, filename, mode, dev); } @@ -2044,7 +2044,7 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) return error; } -asmlinkage long sys_mkdirat(int dfd, const char __user *pathname, int mode) +SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, int, mode) { int error = 0; char * tmp; @@ -2081,7 +2081,7 @@ out_err: return error; } -asmlinkage long sys_mkdir(const char __user *pathname, int mode) +SYSCALL_DEFINE2(mkdir, const char __user *, pathname, int, mode) { return sys_mkdirat(AT_FDCWD, pathname, mode); } @@ -2195,7 +2195,7 @@ exit1: return error; } -asmlinkage long sys_rmdir(const char __user *pathname) +SYSCALL_DEFINE1(rmdir, const char __user *, pathname) { return do_rmdir(AT_FDCWD, pathname); } @@ -2291,7 +2291,7 @@ slashes: goto exit2; } -asmlinkage long sys_unlinkat(int dfd, const char __user *pathname, int flag) +SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag) { if ((flag & ~AT_REMOVEDIR) != 0) return -EINVAL; @@ -2302,7 +2302,7 @@ asmlinkage long sys_unlinkat(int dfd, const char __user *pathname, int flag) return do_unlinkat(dfd, pathname); } -asmlinkage long sys_unlink(const char __user *pathname) +SYSCALL_DEFINE1(unlink, const char __user *, pathname) { return do_unlinkat(AT_FDCWD, pathname); } @@ -2328,8 +2328,8 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) return error; } -asmlinkage long sys_symlinkat(const char __user *oldname, - int newdfd, const char __user *newname) +SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, + int, newdfd, const char __user *, newname) { int error; char *from; @@ -2370,7 +2370,7 @@ out_putname: return error; } -asmlinkage long sys_symlink(const char __user *oldname, const char __user *newname) +SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname) { return sys_symlinkat(oldname, AT_FDCWD, newname); } @@ -2422,9 +2422,8 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de * with linux 2.0, and to avoid hard-linking to directories * and other special files. --ADM */ -asmlinkage long sys_linkat(int olddfd, const char __user *oldname, - int newdfd, const char __user *newname, - int flags) +SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, + int, newdfd, const char __user *, newname, int, flags) { struct dentry *new_dentry; struct nameidata nd; @@ -2473,7 +2472,7 @@ out: return error; } -asmlinkage long sys_link(const char __user *oldname, const char __user *newname) +SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname) { return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } @@ -2624,8 +2623,8 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, return error; } -asmlinkage long sys_renameat(int olddfd, const char __user *oldname, - int newdfd, const char __user *newname) +SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, + int, newdfd, const char __user *, newname) { struct dentry *old_dir, *new_dir; struct dentry *old_dentry, *new_dentry; @@ -2718,7 +2717,7 @@ exit: return error; } -asmlinkage long sys_rename(const char __user *oldname, const char __user *newname) +SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { return sys_renameat(AT_FDCWD, oldname, AT_FDCWD, newname); } diff --git a/fs/namespace.c b/fs/namespace.c index a40685d800a..228d8c4bfd1 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1128,7 +1128,7 @@ static int do_umount(struct vfsmount *mnt, int flags) * unixes. Our API is identical to OSF/1 to avoid making a mess of AMD */ -asmlinkage long sys_umount(char __user * name, int flags) +SYSCALL_DEFINE2(umount, char __user *, name, int, flags) { struct path path; int retval; @@ -1160,7 +1160,7 @@ out: /* * The 2.0 compatible umount. No flags. */ -asmlinkage long sys_oldumount(char __user * name) +SYSCALL_DEFINE1(oldumount, char __user *, name) { return sys_umount(name, 0); } @@ -2045,9 +2045,8 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, return new_ns; } -asmlinkage long sys_mount(char __user * dev_name, char __user * dir_name, - char __user * type, unsigned long flags, - void __user * data) +SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, + char __user *, type, unsigned long, flags, void __user *, data) { int retval; unsigned long data_page; @@ -2172,8 +2171,8 @@ static void chroot_fs_refs(struct path *old_root, struct path *new_root) * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root * first. */ -asmlinkage long sys_pivot_root(const char __user * new_root, - const char __user * put_old) +SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, + const char __user *, put_old) { struct vfsmount *tmp; struct path new, old, parent_path, root_parent, root; diff --git a/fs/ncpfs/Kconfig b/fs/ncpfs/Kconfig index 142808427b2..c931cf22a1f 100644 --- a/fs/ncpfs/Kconfig +++ b/fs/ncpfs/Kconfig @@ -1,6 +1,27 @@ # # NCP Filesystem configuration # +config NCP_FS + tristate "NCP file system support (to mount NetWare volumes)" + depends on IPX!=n || INET + help + NCP (NetWare Core Protocol) is a protocol that runs over IPX and is + used by Novell NetWare clients to talk to file servers. It is to + IPX what NFS is to TCP/IP, if that helps. Saying Y here allows you + to mount NetWare file server volumes and to access them just like + any other Unix directory. For details, please read the file + <file:Documentation/filesystems/ncpfs.txt> in the kernel source and + the IPX-HOWTO from <http://www.tldp.org/docs.html#howto>. + + You do not have to say Y here if you want your Linux box to act as a + file *server* for Novell NetWare clients. + + General information about how to connect Linux, Windows machines and + Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. + + To compile this as a module, choose M here: the module will be called + ncpfs. Say N unless you are connected to a Novell network. + config NCPFS_PACKET_SIGNING bool "Packet signatures" depends on NCP_FS diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig new file mode 100644 index 00000000000..36fe20d6eba --- /dev/null +++ b/fs/nfs/Kconfig @@ -0,0 +1,86 @@ +config NFS_FS + tristate "NFS client support" + depends on INET + select LOCKD + select SUNRPC + select NFS_ACL_SUPPORT if NFS_V3_ACL + help + Choose Y here if you want to access files residing on other + computers using Sun's Network File System protocol. To compile + this file system support as a module, choose M here: the module + will be called nfs. + + To mount file systems exported by NFS servers, you also need to + install the user space mount.nfs command which can be found in + the Linux nfs-utils package, available from http://linux-nfs.org/. + Information about using the mount command is available in the + mount(8) man page. More detail about the Linux NFS client + implementation is available via the nfs(5) man page. + + Below you can choose which versions of the NFS protocol are + available in the kernel to mount NFS servers. Support for NFS + version 2 (RFC 1094) is always available when NFS_FS is selected. + + To configure a system which mounts its root file system via NFS + at boot time, say Y here, select "Kernel level IP + autoconfiguration" in the NETWORK menu, and select "Root file + system on NFS" below. You cannot compile this file system as a + module in this case. + + If unsure, say N. + +config NFS_V3 + bool "NFS client support for NFS version 3" + depends on NFS_FS + help + This option enables support for version 3 of the NFS protocol + (RFC 1813) in the kernel's NFS client. + + If unsure, say Y. + +config NFS_V3_ACL + bool "NFS client support for the NFSv3 ACL protocol extension" + depends on NFS_V3 + help + Some NFS servers support an auxiliary NFSv3 ACL protocol that + Sun added to Solaris but never became an official part of the + NFS version 3 protocol. This protocol extension allows + applications on NFS clients to manipulate POSIX Access Control + Lists on files residing on NFS servers. NFS servers enforce + ACLs on local files whether this protocol is available or not. + + Choose Y here if your NFS server supports the Solaris NFSv3 ACL + protocol extension and you want your NFS client to allow + applications to access and modify ACLs on files on the server. + + Most NFS servers don't support the Solaris NFSv3 ACL protocol + extension. You can choose N here or specify the "noacl" mount + option to prevent your NFS client from trying to use the NFSv3 + ACL protocol. + + If unsure, say N. + +config NFS_V4 + bool "NFS client support for NFS version 4 (EXPERIMENTAL)" + depends on NFS_FS && EXPERIMENTAL + select RPCSEC_GSS_KRB5 + help + This option enables support for version 4 of the NFS protocol + (RFC 3530) in the kernel's NFS client. + + To mount NFS servers using NFSv4, you also need to install user + space programs which can be found in the Linux nfs-utils package, + available from http://linux-nfs.org/. + + If unsure, say N. + +config ROOT_NFS + bool "Root file system on NFS" + depends on NFS_FS=y && IP_PNP + help + If you want your system to mount its root file system via NFS, + choose Y here. This is common practice for managing systems + without local permanent storage. For details, read + <file:Documentation/filesystems/nfsroot.txt>. + + Most people say N here. diff --git a/fs/nfsctl.c b/fs/nfsctl.c index b27451909df..8f9a20556f7 100644 --- a/fs/nfsctl.c +++ b/fs/nfsctl.c @@ -86,8 +86,8 @@ static struct { }, }; -long -asmlinkage sys_nfsservctl(int cmd, struct nfsctl_arg __user *arg, void __user *res) +SYSCALL_DEFINE3(nfsservctl, int, cmd, struct nfsctl_arg __user *, arg, + void __user *, res) { struct file *file; void __user *p = &arg->u; diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig new file mode 100644 index 00000000000..44d7d04dab9 --- /dev/null +++ b/fs/nfsd/Kconfig @@ -0,0 +1,80 @@ +config NFSD + tristate "NFS server support" + depends on INET + select LOCKD + select SUNRPC + select EXPORTFS + select NFS_ACL_SUPPORT if NFSD_V2_ACL + help + Choose Y here if you want to allow other computers to access + files residing on this system using Sun's Network File System + protocol. To compile the NFS server support as a module, + choose M here: the module will be called nfsd. + + You may choose to use a user-space NFS server instead, in which + case you can choose N here. + + To export local file systems using NFS, you also need to install + user space programs which can be found in the Linux nfs-utils + package, available from http://linux-nfs.org/. More detail about + the Linux NFS server implementation is available via the + exports(5) man page. + + Below you can choose which versions of the NFS protocol are + available to clients mounting the NFS server on this system. + Support for NFS version 2 (RFC 1094) is always available when + CONFIG_NFSD is selected. + + If unsure, say N. + +config NFSD_V2_ACL + bool + depends on NFSD + +config NFSD_V3 + bool "NFS server support for NFS version 3" + depends on NFSD + help + This option enables support in your system's NFS server for + version 3 of the NFS protocol (RFC 1813). + + If unsure, say Y. + +config NFSD_V3_ACL + bool "NFS server support for the NFSv3 ACL protocol extension" + depends on NFSD_V3 + select NFSD_V2_ACL + help + Solaris NFS servers support an auxiliary NFSv3 ACL protocol that + never became an official part of the NFS version 3 protocol. + This protocol extension allows applications on NFS clients to + manipulate POSIX Access Control Lists on files residing on NFS + servers. NFS servers enforce POSIX ACLs on local files whether + this protocol is available or not. + + This option enables support in your system's NFS server for the + NFSv3 ACL protocol extension allowing NFS clients to manipulate + POSIX ACLs on files exported by your system's NFS server. NFS + clients which support the Solaris NFSv3 ACL protocol can then + access and modify ACLs on your NFS server. + + To store ACLs on your NFS server, you also need to enable ACL- + related CONFIG options for your local file systems of choice. + + If unsure, say N. + +config NFSD_V4 + bool "NFS server support for NFS version 4 (EXPERIMENTAL)" + depends on NFSD && PROC_FS && EXPERIMENTAL + select NFSD_V3 + select FS_POSIX_ACL + select RPCSEC_GSS_KRB5 + help + This option enables support in your system's NFS server for + version 4 of the NFS protocol (RFC 3530). + + To export files using NFSv4, you need to install additional user + space programs which can be found in the Linux nfs-utils package, + available from http://linux-nfs.org/. + + If unsure, say N. diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index c903e04aa21..5573508f707 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -49,6 +49,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) new->fsuid = exp->ex_anon_uid; new->fsgid = exp->ex_anon_gid; gi = groups_alloc(0); + if (!gi) + goto oom; } else if (flags & NFSEXP_ROOTSQUASH) { if (!new->fsuid) new->fsuid = exp->ex_anon_uid; @@ -85,6 +87,7 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) new->cap_effective = cap_raise_nfsd_set(new->cap_effective, new->cap_permitted); put_cred(override_creds(new)); + put_cred(new); return 0; oom: diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 88db7d3ec12..b6f60f48e94 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2871,7 +2871,6 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, file_lock.fl_owner = (fl_owner_t)lockt->lt_stateowner; file_lock.fl_pid = current->tgid; file_lock.fl_flags = FL_POSIX; - file_lock.fl_lmops = &nfsd_posix_mng_ops; file_lock.fl_start = lockt->lt_offset; file_lock.fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length); diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 81b8644b013..bed766e435b 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -427,10 +427,61 @@ static unsigned int inotify_poll(struct file *file, poll_table *wait) return ret; } +/* + * Get an inotify_kernel_event if one exists and is small + * enough to fit in "count". Return an error pointer if + * not large enough. + * + * Called with the device ev_mutex held. + */ +static struct inotify_kernel_event *get_one_event(struct inotify_device *dev, + size_t count) +{ + size_t event_size = sizeof(struct inotify_event); + struct inotify_kernel_event *kevent; + + if (list_empty(&dev->events)) + return NULL; + + kevent = inotify_dev_get_event(dev); + if (kevent->name) + event_size += kevent->event.len; + + if (event_size > count) + return ERR_PTR(-EINVAL); + + remove_kevent(dev, kevent); + return kevent; +} + +/* + * Copy an event to user space, returning how much we copied. + * + * We already checked that the event size is smaller than the + * buffer we had in "get_one_event()" above. + */ +static ssize_t copy_event_to_user(struct inotify_kernel_event *kevent, + char __user *buf) +{ + size_t event_size = sizeof(struct inotify_event); + + if (copy_to_user(buf, &kevent->event, event_size)) + return -EFAULT; + + if (kevent->name) { + buf += event_size; + + if (copy_to_user(buf, kevent->name, kevent->event.len)) + return -EFAULT; + + event_size += kevent->event.len; + } + return event_size; +} + static ssize_t inotify_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { - size_t event_size = sizeof (struct inotify_event); struct inotify_device *dev; char __user *start; int ret; @@ -440,81 +491,43 @@ static ssize_t inotify_read(struct file *file, char __user *buf, dev = file->private_data; while (1) { + struct inotify_kernel_event *kevent; prepare_to_wait(&dev->wq, &wait, TASK_INTERRUPTIBLE); mutex_lock(&dev->ev_mutex); - if (!list_empty(&dev->events)) { - ret = 0; - break; - } + kevent = get_one_event(dev, count); mutex_unlock(&dev->ev_mutex); - if (file->f_flags & O_NONBLOCK) { - ret = -EAGAIN; - break; - } - - if (signal_pending(current)) { - ret = -EINTR; - break; + if (kevent) { + ret = PTR_ERR(kevent); + if (IS_ERR(kevent)) + break; + ret = copy_event_to_user(kevent, buf); + free_kevent(kevent); + if (ret < 0) + break; + buf += ret; + count -= ret; + continue; } - schedule(); - } - - finish_wait(&dev->wq, &wait); - if (ret) - return ret; - - while (1) { - struct inotify_kernel_event *kevent; - - ret = buf - start; - if (list_empty(&dev->events)) + ret = -EAGAIN; + if (file->f_flags & O_NONBLOCK) break; - - kevent = inotify_dev_get_event(dev); - if (event_size + kevent->event.len > count) { - if (ret == 0 && count > 0) { - /* - * could not get a single event because we - * didn't have enough buffer space. - */ - ret = -EINVAL; - } + ret = -EINTR; + if (signal_pending(current)) break; - } - remove_kevent(dev, kevent); - /* - * Must perform the copy_to_user outside the mutex in order - * to avoid a lock order reversal with mmap_sem. - */ - mutex_unlock(&dev->ev_mutex); - - if (copy_to_user(buf, &kevent->event, event_size)) { - ret = -EFAULT; + if (start != buf) break; - } - buf += event_size; - count -= event_size; - - if (kevent->name) { - if (copy_to_user(buf, kevent->name, kevent->event.len)){ - ret = -EFAULT; - break; - } - buf += kevent->event.len; - count -= kevent->event.len; - } - - free_kevent(kevent); - mutex_lock(&dev->ev_mutex); + schedule(); } - mutex_unlock(&dev->ev_mutex); + finish_wait(&dev->wq, &wait); + if (start != buf && ret != -EFAULT) + ret = buf - start; return ret; } @@ -576,7 +589,7 @@ static const struct inotify_operations inotify_user_ops = { .destroy_watch = free_inotify_user_watch, }; -asmlinkage long sys_inotify_init1(int flags) +SYSCALL_DEFINE1(inotify_init1, int, flags) { struct inotify_device *dev; struct inotify_handle *ih; @@ -655,12 +668,13 @@ out_put_fd: return ret; } -asmlinkage long sys_inotify_init(void) +SYSCALL_DEFINE0(inotify_init) { return sys_inotify_init1(0); } -asmlinkage long sys_inotify_add_watch(int fd, const char __user *pathname, u32 mask) +SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, + u32, mask) { struct inode *inode; struct inotify_device *dev; @@ -704,7 +718,7 @@ fput_and_out: return ret; } -asmlinkage long sys_inotify_rm_watch(int fd, __s32 wd) +SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd) { struct file *filp; struct inotify_device *dev; diff --git a/fs/ntfs/Kconfig b/fs/ntfs/Kconfig new file mode 100644 index 00000000000..f5a868cc915 --- /dev/null +++ b/fs/ntfs/Kconfig @@ -0,0 +1,78 @@ +config NTFS_FS + tristate "NTFS file system support" + select NLS + help + NTFS is the file system of Microsoft Windows NT, 2000, XP and 2003. + + Saying Y or M here enables read support. There is partial, but + safe, write support available. For write support you must also + say Y to "NTFS write support" below. + + There are also a number of user-space tools available, called + ntfsprogs. These include ntfsundelete and ntfsresize, that work + without NTFS support enabled in the kernel. + + This is a rewrite from scratch of Linux NTFS support and replaced + the old NTFS code starting with Linux 2.5.11. A backport to + the Linux 2.4 kernel series is separately available as a patch + from the project web site. + + For more information see <file:Documentation/filesystems/ntfs.txt> + and <http://www.linux-ntfs.org/>. + + To compile this file system support as a module, choose M here: the + module will be called ntfs. + + If you are not using Windows NT, 2000, XP or 2003 in addition to + Linux on your computer it is safe to say N. + +config NTFS_DEBUG + bool "NTFS debugging support" + depends on NTFS_FS + help + If you are experiencing any problems with the NTFS file system, say + Y here. This will result in additional consistency checks to be + performed by the driver as well as additional debugging messages to + be written to the system log. Note that debugging messages are + disabled by default. To enable them, supply the option debug_msgs=1 + at the kernel command line when booting the kernel or as an option + to insmod when loading the ntfs module. Once the driver is active, + you can enable debugging messages by doing (as root): + echo 1 > /proc/sys/fs/ntfs-debug + Replacing the "1" with "0" would disable debug messages. + + If you leave debugging messages disabled, this results in little + overhead, but enabling debug messages results in very significant + slowdown of the system. + + When reporting bugs, please try to have available a full dump of + debugging messages while the misbehaviour was occurring. + +config NTFS_RW + bool "NTFS write support" + depends on NTFS_FS + help + This enables the partial, but safe, write support in the NTFS driver. + + The only supported operation is overwriting existing files, without + changing the file length. No file or directory creation, deletion or + renaming is possible. Note only non-resident files can be written to + so you may find that some very small files (<500 bytes or so) cannot + be written to. + + While we cannot guarantee that it will not damage any data, we have + so far not received a single report where the driver would have + damaged someones data so we assume it is perfectly safe to use. + + Note: While write support is safe in this version (a rewrite from + scratch of the NTFS support), it should be noted that the old NTFS + write support, included in Linux 2.5.10 and before (since 1997), + is not safe. + + This is currently useful with TopologiLinux. TopologiLinux is run + on top of any DOS/Microsoft Windows system without partitioning your + hard disk. Unlike other Linux distributions TopologiLinux does not + need its own partition. For more information see + <http://topologi-linux.sourceforge.net/> + + It is perfectly safe to say N here. diff --git a/fs/ocfs2/Kconfig b/fs/ocfs2/Kconfig new file mode 100644 index 00000000000..701b7a3a872 --- /dev/null +++ b/fs/ocfs2/Kconfig @@ -0,0 +1,85 @@ +config OCFS2_FS + tristate "OCFS2 file system support" + depends on NET && SYSFS + select CONFIGFS_FS + select JBD2 + select CRC32 + select QUOTA + select QUOTA_TREE + help + OCFS2 is a general purpose extent based shared disk cluster file + system with many similarities to ext3. It supports 64 bit inode + numbers, and has automatically extending metadata groups which may + also make it attractive for non-clustered use. + + You'll want to install the ocfs2-tools package in order to at least + get "mount.ocfs2". + + Project web page: http://oss.oracle.com/projects/ocfs2 + Tools web page: http://oss.oracle.com/projects/ocfs2-tools + OCFS2 mailing lists: http://oss.oracle.com/projects/ocfs2/mailman/ + + For more information on OCFS2, see the file + <file:Documentation/filesystems/ocfs2.txt>. + +config OCFS2_FS_O2CB + tristate "O2CB Kernelspace Clustering" + depends on OCFS2_FS + default y + help + OCFS2 includes a simple kernelspace clustering package, the OCFS2 + Cluster Base. It only requires a very small userspace component + to configure it. This comes with the standard ocfs2-tools package. + O2CB is limited to maintaining a cluster for OCFS2 file systems. + It cannot manage any other cluster applications. + + It is always safe to say Y here, as the clustering method is + run-time selectable. + +config OCFS2_FS_USERSPACE_CLUSTER + tristate "OCFS2 Userspace Clustering" + depends on OCFS2_FS && DLM + default y + help + This option will allow OCFS2 to use userspace clustering services + in conjunction with the DLM in fs/dlm. If you are using a + userspace cluster manager, say Y here. + + It is safe to say Y, as the clustering method is run-time + selectable. + +config OCFS2_FS_STATS + bool "OCFS2 statistics" + depends on OCFS2_FS + default y + help + This option allows some fs statistics to be captured. Enabling + this option may increase the memory consumption. + +config OCFS2_DEBUG_MASKLOG + bool "OCFS2 logging support" + depends on OCFS2_FS + default y + help + The ocfs2 filesystem has an extensive logging system. The system + allows selection of events to log via files in /sys/o2cb/logmask/. + This option will enlarge your kernel, but it allows debugging of + ocfs2 filesystem issues. + +config OCFS2_DEBUG_FS + bool "OCFS2 expensive checks" + depends on OCFS2_FS + default n + help + This option will enable expensive consistency checks. Enable + this option for debugging only as it is likely to decrease + performance of the filesystem. + +config OCFS2_FS_POSIX_ACL + bool "OCFS2 POSIX Access Control Lists" + depends on OCFS2_FS + select FS_POSIX_ACL + default n + help + Posix Access Control Lists (ACLs) support permissions for users and + groups beyond the owner/group/world scheme. diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 6aff8f2d3e4..f4efa89baee 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -810,171 +810,6 @@ out: return status; } -/* This is difficult. We have to lock quota inode and start transaction - * in this function but we don't want to take the penalty of exlusive - * quota file lock when we are just going to use cached structures. So - * we just take read lock check whether we have dquot cached and if so, - * we don't have to take the write lock... */ -static int ocfs2_dquot_initialize(struct inode *inode, int type) -{ - handle_t *handle = NULL; - int status = 0; - struct super_block *sb = inode->i_sb; - struct ocfs2_mem_dqinfo *oinfo; - int exclusive = 0; - int cnt; - qid_t id; - - mlog_entry_void(); - - for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (type != -1 && cnt != type) - continue; - if (!sb_has_quota_active(sb, cnt)) - continue; - oinfo = sb_dqinfo(sb, cnt)->dqi_priv; - status = ocfs2_lock_global_qf(oinfo, 0); - if (status < 0) - goto out; - /* This is just a performance optimization not a reliable test. - * Since we hold an inode lock, noone can actually release - * the structure until we are finished with initialization. */ - if (inode->i_dquot[cnt] != NODQUOT) { - ocfs2_unlock_global_qf(oinfo, 0); - continue; - } - /* When we have inode lock, we know that no dquot_release() can - * run and thus we can safely check whether we need to - * read+modify global file to get quota information or whether - * our node already has it. */ - if (cnt == USRQUOTA) - id = inode->i_uid; - else if (cnt == GRPQUOTA) - id = inode->i_gid; - else - BUG(); - /* Obtain exclusion from quota off... */ - down_write(&sb_dqopt(sb)->dqptr_sem); - exclusive = !dquot_is_cached(sb, id, cnt); - up_write(&sb_dqopt(sb)->dqptr_sem); - if (exclusive) { - status = ocfs2_lock_global_qf(oinfo, 1); - if (status < 0) { - exclusive = 0; - mlog_errno(status); - goto out_ilock; - } - handle = ocfs2_start_trans(OCFS2_SB(sb), - ocfs2_calc_qinit_credits(sb, cnt)); - if (IS_ERR(handle)) { - status = PTR_ERR(handle); - mlog_errno(status); - goto out_ilock; - } - } - dquot_initialize(inode, cnt); - if (exclusive) { - ocfs2_commit_trans(OCFS2_SB(sb), handle); - ocfs2_unlock_global_qf(oinfo, 1); - } - ocfs2_unlock_global_qf(oinfo, 0); - } - mlog_exit(0); - return 0; -out_ilock: - if (exclusive) - ocfs2_unlock_global_qf(oinfo, 1); - ocfs2_unlock_global_qf(oinfo, 0); -out: - mlog_exit(status); - return status; -} - -static int ocfs2_dquot_drop_slow(struct inode *inode) -{ - int status = 0; - int cnt; - int got_lock[MAXQUOTAS] = {0, 0}; - handle_t *handle; - struct super_block *sb = inode->i_sb; - struct ocfs2_mem_dqinfo *oinfo; - - for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!sb_has_quota_active(sb, cnt)) - continue; - oinfo = sb_dqinfo(sb, cnt)->dqi_priv; - status = ocfs2_lock_global_qf(oinfo, 1); - if (status < 0) - goto out; - got_lock[cnt] = 1; - } - handle = ocfs2_start_trans(OCFS2_SB(sb), - ocfs2_calc_qinit_credits(sb, USRQUOTA) + - ocfs2_calc_qinit_credits(sb, GRPQUOTA)); - if (IS_ERR(handle)) { - status = PTR_ERR(handle); - mlog_errno(status); - goto out; - } - dquot_drop(inode); - ocfs2_commit_trans(OCFS2_SB(sb), handle); -out: - for (cnt = 0; cnt < MAXQUOTAS; cnt++) - if (got_lock[cnt]) { - oinfo = sb_dqinfo(sb, cnt)->dqi_priv; - ocfs2_unlock_global_qf(oinfo, 1); - } - return status; -} - -/* See the comment before ocfs2_dquot_initialize. */ -static int ocfs2_dquot_drop(struct inode *inode) -{ - int status = 0; - struct super_block *sb = inode->i_sb; - struct ocfs2_mem_dqinfo *oinfo; - int exclusive = 0; - int cnt; - int got_lock[MAXQUOTAS] = {0, 0}; - - mlog_entry_void(); - for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!sb_has_quota_active(sb, cnt)) - continue; - oinfo = sb_dqinfo(sb, cnt)->dqi_priv; - status = ocfs2_lock_global_qf(oinfo, 0); - if (status < 0) - goto out; - got_lock[cnt] = 1; - } - /* Lock against anyone releasing references so that when when we check - * we know we are not going to be last ones to release dquot */ - down_write(&sb_dqopt(sb)->dqptr_sem); - /* Urgh, this is a terrible hack :( */ - for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (inode->i_dquot[cnt] != NODQUOT && - atomic_read(&inode->i_dquot[cnt]->dq_count) > 1) { - exclusive = 1; - break; - } - } - if (!exclusive) - dquot_drop_locked(inode); - up_write(&sb_dqopt(sb)->dqptr_sem); -out: - for (cnt = 0; cnt < MAXQUOTAS; cnt++) - if (got_lock[cnt]) { - oinfo = sb_dqinfo(sb, cnt)->dqi_priv; - ocfs2_unlock_global_qf(oinfo, 0); - } - /* In case we bailed out because we had to do expensive locking - * do it now... */ - if (exclusive) - status = ocfs2_dquot_drop_slow(inode); - mlog_exit(status); - return status; -} - static struct dquot *ocfs2_alloc_dquot(struct super_block *sb, int type) { struct ocfs2_dquot *dquot = @@ -991,8 +826,8 @@ static void ocfs2_destroy_dquot(struct dquot *dquot) } struct dquot_operations ocfs2_quota_operations = { - .initialize = ocfs2_dquot_initialize, - .drop = ocfs2_dquot_drop, + .initialize = dquot_initialize, + .drop = dquot_drop, .alloc_space = dquot_alloc_space, .alloc_inode = dquot_alloc_inode, .free_space = dquot_free_space, diff --git a/fs/omfs/Kconfig b/fs/omfs/Kconfig new file mode 100644 index 00000000000..b1b9a0aba6f --- /dev/null +++ b/fs/omfs/Kconfig @@ -0,0 +1,13 @@ +config OMFS_FS + tristate "SonicBlue Optimized MPEG File System support" + depends on BLOCK + select CRC_ITU_T + help + This is the proprietary file system used by the Rio Karma music + player and ReplayTV DVR. Despite the name, this filesystem is not + more efficient than a standard FS for MPEG files, in fact likely + the opposite is true. Say Y if you have either of these devices + and wish to mount its disk. + + To compile this file system support as a module, choose M here: the + module will be called omfs. If unsure, say N. diff --git a/fs/open.c b/fs/open.c index d882fd2351d..a3a78ceb2a2 100644 --- a/fs/open.c +++ b/fs/open.c @@ -122,7 +122,7 @@ static int vfs_statfs64(struct dentry *dentry, struct statfs64 *buf) return 0; } -asmlinkage long sys_statfs(const char __user *pathname, struct statfs __user * buf) +SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct statfs __user *, buf) { struct path path; int error; @@ -138,8 +138,7 @@ asmlinkage long sys_statfs(const char __user *pathname, struct statfs __user * b return error; } - -asmlinkage long sys_statfs64(const char __user *pathname, size_t sz, struct statfs64 __user *buf) +SYSCALL_DEFINE3(statfs64, const char __user *, pathname, size_t, sz, struct statfs64 __user *, buf) { struct path path; long error; @@ -157,8 +156,7 @@ asmlinkage long sys_statfs64(const char __user *pathname, size_t sz, struct stat return error; } - -asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user * buf) +SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct statfs __user *, buf) { struct file * file; struct statfs tmp; @@ -176,7 +174,7 @@ out: return error; } -asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz, struct statfs64 __user *buf) +SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user *, buf) { struct file * file; struct statfs64 tmp; @@ -289,7 +287,7 @@ out: return error; } -asmlinkage long sys_truncate(const char __user * path, unsigned long length) +SYSCALL_DEFINE2(truncate, const char __user *, path, unsigned long, length) { /* on 32-bit boxen it will cut the range 2^31--2^32-1 off */ return do_sys_truncate(path, (long)length); @@ -341,7 +339,7 @@ out: return error; } -asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length) +SYSCALL_DEFINE2(ftruncate, unsigned int, fd, unsigned long, length) { long ret = do_sys_ftruncate(fd, length, 1); /* avoid REGPARM breakage on x86: */ @@ -351,21 +349,35 @@ asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length) /* LFS versions of truncate are only needed on 32 bit machines */ #if BITS_PER_LONG == 32 -asmlinkage long sys_truncate64(const char __user * path, loff_t length) +SYSCALL_DEFINE(truncate64)(const char __user * path, loff_t length) { return do_sys_truncate(path, length); } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_truncate64(long path, loff_t length) +{ + return SYSC_truncate64((const char __user *) path, length); +} +SYSCALL_ALIAS(sys_truncate64, SyS_truncate64); +#endif -asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length) +SYSCALL_DEFINE(ftruncate64)(unsigned int fd, loff_t length) { long ret = do_sys_ftruncate(fd, length, 0); /* avoid REGPARM breakage on x86: */ asmlinkage_protect(2, ret, fd, length); return ret; } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_ftruncate64(long fd, loff_t length) +{ + return SYSC_ftruncate64((unsigned int) fd, length); +} +SYSCALL_ALIAS(sys_ftruncate64, SyS_ftruncate64); #endif +#endif /* BITS_PER_LONG == 32 */ -asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len) +SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len) { struct file *file; struct inode *inode; @@ -422,13 +434,20 @@ out_fput: out: return ret; } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_fallocate(long fd, long mode, loff_t offset, loff_t len) +{ + return SYSC_fallocate((int)fd, (int)mode, offset, len); +} +SYSCALL_ALIAS(sys_fallocate, SyS_fallocate); +#endif /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and * switching the fsuid/fsgid around to the real ones. */ -asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode) +SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) { const struct cred *old_cred; struct cred *override_cred; @@ -498,12 +517,12 @@ out: return res; } -asmlinkage long sys_access(const char __user *filename, int mode) +SYSCALL_DEFINE2(access, const char __user *, filename, int, mode) { return sys_faccessat(AT_FDCWD, filename, mode); } -asmlinkage long sys_chdir(const char __user * filename) +SYSCALL_DEFINE1(chdir, const char __user *, filename) { struct path path; int error; @@ -524,7 +543,7 @@ out: return error; } -asmlinkage long sys_fchdir(unsigned int fd) +SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct file *file; struct inode *inode; @@ -550,7 +569,7 @@ out: return error; } -asmlinkage long sys_chroot(const char __user * filename) +SYSCALL_DEFINE1(chroot, const char __user *, filename) { struct path path; int error; @@ -575,7 +594,7 @@ out: return error; } -asmlinkage long sys_fchmod(unsigned int fd, mode_t mode) +SYSCALL_DEFINE2(fchmod, unsigned int, fd, mode_t, mode) { struct inode * inode; struct dentry * dentry; @@ -609,8 +628,7 @@ out: return err; } -asmlinkage long sys_fchmodat(int dfd, const char __user *filename, - mode_t mode) +SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, mode_t, mode) { struct path path; struct inode *inode; @@ -639,7 +657,7 @@ out: return error; } -asmlinkage long sys_chmod(const char __user *filename, mode_t mode) +SYSCALL_DEFINE2(chmod, const char __user *, filename, mode_t, mode) { return sys_fchmodat(AT_FDCWD, filename, mode); } @@ -669,7 +687,7 @@ static int chown_common(struct dentry * dentry, uid_t user, gid_t group) return error; } -asmlinkage long sys_chown(const char __user * filename, uid_t user, gid_t group) +SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) { struct path path; int error; @@ -688,8 +706,8 @@ out: return error; } -asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user, - gid_t group, int flag) +SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, + gid_t, group, int, flag) { struct path path; int error = -EINVAL; @@ -713,7 +731,7 @@ out: return error; } -asmlinkage long sys_lchown(const char __user * filename, uid_t user, gid_t group) +SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) { struct path path; int error; @@ -732,8 +750,7 @@ out: return error; } - -asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group) +SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) { struct file * file; int error = -EBADF; @@ -1029,7 +1046,7 @@ long do_sys_open(int dfd, const char __user *filename, int flags, int mode) return fd; } -asmlinkage long sys_open(const char __user *filename, int flags, int mode) +SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, int, mode) { long ret; @@ -1042,8 +1059,8 @@ asmlinkage long sys_open(const char __user *filename, int flags, int mode) return ret; } -asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, - int mode) +SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, + int, mode) { long ret; @@ -1062,7 +1079,7 @@ asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, * For backward compatibility? Maybe this should be moved * into arch/i386 instead? */ -asmlinkage long sys_creat(const char __user * pathname, int mode) +SYSCALL_DEFINE2(creat, const char __user *, pathname, int, mode) { return sys_open(pathname, O_CREAT | O_WRONLY | O_TRUNC, mode); } @@ -1098,7 +1115,7 @@ EXPORT_SYMBOL(filp_close); * releasing the fd. This ensures that one clone task can't release * an fd while another clone is opening it. */ -asmlinkage long sys_close(unsigned int fd) +SYSCALL_DEFINE1(close, unsigned int, fd) { struct file * filp; struct files_struct *files = current->files; @@ -1131,14 +1148,13 @@ out_unlock: spin_unlock(&files->file_lock); return -EBADF; } - EXPORT_SYMBOL(sys_close); /* * This routine simulates a hangup on the tty, to arrange that users * are given clean terminals at login time. */ -asmlinkage long sys_vhangup(void) +SYSCALL_DEFINE0(vhangup) { if (capable(CAP_SYS_TTY_CONFIG)) { tty_vhangup_self(); diff --git a/fs/pipe.c b/fs/pipe.c index 891697112f6..3a48ba5179d 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1043,7 +1043,7 @@ int do_pipe(int *fd) * sys_pipe() is the normal C calling standard for creating * a pipe. It's not the way Unix traditionally does this, though. */ -asmlinkage long __weak sys_pipe2(int __user *fildes, int flags) +SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) { int fd[2]; int error; @@ -1059,7 +1059,7 @@ asmlinkage long __weak sys_pipe2(int __user *fildes, int flags) return error; } -asmlinkage long __weak sys_pipe(int __user *fildes) +SYSCALL_DEFINE1(pipe, int __user *, fildes) { return sys_pipe2(fildes, 0); } diff --git a/fs/qnx4/Kconfig b/fs/qnx4/Kconfig new file mode 100644 index 00000000000..be8e0e1445b --- /dev/null +++ b/fs/qnx4/Kconfig @@ -0,0 +1,25 @@ +config QNX4FS_FS + tristate "QNX4 file system support (read only)" + depends on BLOCK + help + This is the file system used by the real-time operating systems + QNX 4 and QNX 6 (the latter is also called QNX RTP). + Further information is available at <http://www.qnx.com/>. + Say Y if you intend to mount QNX hard disks or floppies. + Unless you say Y to "QNX4FS read-write support" below, you will + only be able to read these file systems. + + To compile this file system support as a module, choose M here: the + module will be called qnx4. + + If you don't know whether you need it, then you don't need it: + answer N. + +config QNX4FS_RW + bool "QNX4FS write support (DANGEROUS)" + depends on QNX4FS_FS && EXPERIMENTAL && BROKEN + help + Say Y if you want to test write support for QNX4 file systems. + + It's currently broken, so for now: + answer N. diff --git a/fs/quota.c b/fs/quota.c index 4a8c94f05f7..d76ada914f9 100644 --- a/fs/quota.c +++ b/fs/quota.c @@ -371,7 +371,8 @@ static inline struct super_block *quotactl_block(const char __user *special) * calls. Maybe we need to add the process quotas etc. in the future, * but we probably should use rlimits for that. */ -asmlinkage long sys_quotactl(unsigned int cmd, const char __user *special, qid_t id, void __user *addr) +SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special, + qid_t, id, void __user *, addr) { uint cmds, type; struct super_block *sb = NULL; diff --git a/fs/read_write.c b/fs/read_write.c index 5cc6924eb15..400fe81c973 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -147,7 +147,7 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int origin) } EXPORT_SYMBOL(vfs_llseek); -asmlinkage off_t sys_lseek(unsigned int fd, off_t offset, unsigned int origin) +SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, origin) { off_t retval; struct file * file; @@ -171,9 +171,9 @@ bad: } #ifdef __ARCH_WANT_SYS_LLSEEK -asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high, - unsigned long offset_low, loff_t __user * result, - unsigned int origin) +SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, + unsigned long, offset_low, loff_t __user *, result, + unsigned int, origin) { int retval; struct file * file; @@ -369,7 +369,7 @@ static inline void file_pos_write(struct file *file, loff_t pos) file->f_pos = pos; } -asmlinkage ssize_t sys_read(unsigned int fd, char __user * buf, size_t count) +SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) { struct file *file; ssize_t ret = -EBADF; @@ -386,7 +386,8 @@ asmlinkage ssize_t sys_read(unsigned int fd, char __user * buf, size_t count) return ret; } -asmlinkage ssize_t sys_write(unsigned int fd, const char __user * buf, size_t count) +SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, + size_t, count) { struct file *file; ssize_t ret = -EBADF; @@ -403,8 +404,8 @@ asmlinkage ssize_t sys_write(unsigned int fd, const char __user * buf, size_t co return ret; } -asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf, - size_t count, loff_t pos) +SYSCALL_DEFINE(pread64)(unsigned int fd, char __user *buf, + size_t count, loff_t pos) { struct file *file; ssize_t ret = -EBADF; @@ -423,9 +424,17 @@ asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf, return ret; } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_pread64(long fd, long buf, long count, loff_t pos) +{ + return SYSC_pread64((unsigned int) fd, (char __user *) buf, + (size_t) count, pos); +} +SYSCALL_ALIAS(sys_pread64, SyS_pread64); +#endif -asmlinkage ssize_t sys_pwrite64(unsigned int fd, const char __user *buf, - size_t count, loff_t pos) +SYSCALL_DEFINE(pwrite64)(unsigned int fd, const char __user *buf, + size_t count, loff_t pos) { struct file *file; ssize_t ret = -EBADF; @@ -444,6 +453,14 @@ asmlinkage ssize_t sys_pwrite64(unsigned int fd, const char __user *buf, return ret; } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_pwrite64(long fd, long buf, long count, loff_t pos) +{ + return SYSC_pwrite64((unsigned int) fd, (const char __user *) buf, + (size_t) count, pos); +} +SYSCALL_ALIAS(sys_pwrite64, SyS_pwrite64); +#endif /* * Reduce an iovec's length in-place. Return the resulting number of segments @@ -672,8 +689,8 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, EXPORT_SYMBOL(vfs_writev); -asmlinkage ssize_t -sys_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen) +SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen) { struct file *file; ssize_t ret = -EBADF; @@ -693,8 +710,8 @@ sys_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen) return ret; } -asmlinkage ssize_t -sys_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen) +SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen) { struct file *file; ssize_t ret = -EBADF; @@ -812,7 +829,7 @@ out: return retval; } -asmlinkage ssize_t sys_sendfile(int out_fd, int in_fd, off_t __user *offset, size_t count) +SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count) { loff_t pos; off_t off; @@ -831,7 +848,7 @@ asmlinkage ssize_t sys_sendfile(int out_fd, int in_fd, off_t __user *offset, siz return do_sendfile(out_fd, in_fd, NULL, count, 0); } -asmlinkage ssize_t sys_sendfile64(int out_fd, int in_fd, loff_t __user *offset, size_t count) +SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count) { loff_t pos; ssize_t ret; diff --git a/fs/readdir.c b/fs/readdir.c index b318d9b5af2..7723401f8d8 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -102,7 +102,8 @@ efault: return -EFAULT; } -asmlinkage long old_readdir(unsigned int fd, struct old_linux_dirent __user * dirent, unsigned int count) +SYSCALL_DEFINE3(old_readdir, unsigned int, fd, + struct old_linux_dirent __user *, dirent, unsigned int, count) { int error; struct file * file; @@ -187,7 +188,8 @@ efault: return -EFAULT; } -asmlinkage long sys_getdents(unsigned int fd, struct linux_dirent __user * dirent, unsigned int count) +SYSCALL_DEFINE3(getdents, unsigned int, fd, + struct linux_dirent __user *, dirent, unsigned int, count) { struct file * file; struct linux_dirent __user * lastdirent; @@ -268,7 +270,8 @@ efault: return -EFAULT; } -asmlinkage long sys_getdents64(unsigned int fd, struct linux_dirent64 __user * dirent, unsigned int count) +SYSCALL_DEFINE3(getdents64, unsigned int, fd, + struct linux_dirent64 __user *, dirent, unsigned int, count) { struct file * file; struct linux_dirent64 __user * lastdirent; diff --git a/fs/reiserfs/Kconfig b/fs/reiserfs/Kconfig new file mode 100644 index 00000000000..949b8c6addc --- /dev/null +++ b/fs/reiserfs/Kconfig @@ -0,0 +1,85 @@ +config REISERFS_FS + tristate "Reiserfs support" + help + Stores not just filenames but the files themselves in a balanced + tree. Uses journalling. + + Balanced trees are more efficient than traditional file system + architectural foundations. + + In general, ReiserFS is as fast as ext2, but is very efficient with + large directories and small files. Additional patches are needed + for NFS and quotas, please see <http://www.namesys.com/> for links. + + It is more easily extended to have features currently found in + database and keyword search systems than block allocation based file + systems are. The next version will be so extended, and will support + plugins consistent with our motto ``It takes more than a license to + make source code open.'' + + Read <http://www.namesys.com/> to learn more about reiserfs. + + Sponsored by Threshold Networks, Emusic.com, and Bigstorage.com. + + If you like it, you can pay us to add new features to it that you + need, buy a support contract, or pay us to port it to another OS. + +config REISERFS_CHECK + bool "Enable reiserfs debug mode" + depends on REISERFS_FS + help + If you set this to Y, then ReiserFS will perform every check it can + possibly imagine of its internal consistency throughout its + operation. It will also go substantially slower. More than once we + have forgotten that this was on, and then gone despondent over the + latest benchmarks.:-) Use of this option allows our team to go all + out in checking for consistency when debugging without fear of its + effect on end users. If you are on the verge of sending in a bug + report, say Y and you might get a useful error message. Almost + everyone should say N. + +config REISERFS_PROC_INFO + bool "Stats in /proc/fs/reiserfs" + depends on REISERFS_FS && PROC_FS + help + Create under /proc/fs/reiserfs a hierarchy of files, displaying + various ReiserFS statistics and internal data at the expense of + making your kernel or module slightly larger (+8 KB). This also + increases the amount of kernel memory required for each mount. + Almost everyone but ReiserFS developers and people fine-tuning + reiserfs or tracing problems should say N. + +config REISERFS_FS_XATTR + bool "ReiserFS extended attributes" + depends on REISERFS_FS + 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 REISERFS_FS_POSIX_ACL + bool "ReiserFS POSIX Access Control Lists" + depends on REISERFS_FS_XATTR + select FS_POSIX_ACL + help + Posix Access Control Lists (ACLs) support permissions for users and + groups beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the Posix ACLs for + Linux website <http://acl.bestbits.at/>. + + If you don't know what Access Control Lists are, say N + +config REISERFS_FS_SECURITY + bool "ReiserFS Security Labels" + depends on REISERFS_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 ReiserFS filesystem. + + If you are not using a security module that requires using + extended attributes for file security labels, say N. diff --git a/fs/romfs/Kconfig b/fs/romfs/Kconfig new file mode 100644 index 00000000000..1a17020f9fa --- /dev/null +++ b/fs/romfs/Kconfig @@ -0,0 +1,16 @@ +config ROMFS_FS + tristate "ROM file system support" + depends on BLOCK + ---help--- + This is a very small read-only file system mainly intended for + initial ram disks of installation disks, but it could be used for + other read-only media as well. Read + <file:Documentation/filesystems/romfs.txt> for details. + + To compile this file system support as a module, choose M here: the + module will be called romfs. Note that the file system of your + root partition (the one containing the directory /) cannot be a + module. + + If you don't know whether you need it, then you don't need it: + answer N. diff --git a/fs/select.c b/fs/select.c index 08b91beed80..0fe0e1469df 100644 --- a/fs/select.c +++ b/fs/select.c @@ -557,8 +557,8 @@ out_nofds: return ret; } -asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, - fd_set __user *exp, struct timeval __user *tvp) +SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, + fd_set __user *, exp, struct timeval __user *, tvp) { struct timespec end_time, *to = NULL; struct timeval tv; @@ -582,9 +582,9 @@ asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, } #ifdef HAVE_SET_RESTORE_SIGMASK -asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp, - fd_set __user *exp, struct timespec __user *tsp, - const sigset_t __user *sigmask, size_t sigsetsize) +static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp, + fd_set __user *exp, struct timespec __user *tsp, + const sigset_t __user *sigmask, size_t sigsetsize) { sigset_t ksigmask, sigsaved; struct timespec ts, end_time, *to = NULL; @@ -610,7 +610,7 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } - ret = core_sys_select(n, inp, outp, exp, &end_time); + ret = core_sys_select(n, inp, outp, exp, to); ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); if (ret == -ERESTARTNOHAND) { @@ -636,8 +636,9 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp, * which has a pointer to the sigset_t itself followed by a size_t containing * the sigset size. */ -asmlinkage long sys_pselect6(int n, fd_set __user *inp, fd_set __user *outp, - fd_set __user *exp, struct timespec __user *tsp, void __user *sig) +SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp, + fd_set __user *, exp, struct timespec __user *, tsp, + void __user *, sig) { size_t sigsetsize = 0; sigset_t __user *up = NULL; @@ -650,7 +651,7 @@ asmlinkage long sys_pselect6(int n, fd_set __user *inp, fd_set __user *outp, return -EFAULT; } - return sys_pselect7(n, inp, outp, exp, tsp, up, sigsetsize); + return do_pselect(n, inp, outp, exp, tsp, up, sigsetsize); } #endif /* HAVE_SET_RESTORE_SIGMASK */ @@ -854,8 +855,8 @@ static long do_restart_poll(struct restart_block *restart_block) return ret; } -asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, - long timeout_msecs) +SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, + long, timeout_msecs) { struct timespec end_time, *to = NULL; int ret; @@ -889,9 +890,9 @@ asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, } #ifdef HAVE_SET_RESTORE_SIGMASK -asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds, - struct timespec __user *tsp, const sigset_t __user *sigmask, - size_t sigsetsize) +SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, + struct timespec __user *, tsp, const sigset_t __user *, sigmask, + size_t, sigsetsize) { sigset_t ksigmask, sigsaved; struct timespec ts, end_time, *to = NULL; diff --git a/fs/signalfd.c b/fs/signalfd.c index 9c39bc7f843..b07565c9438 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -205,8 +205,8 @@ static const struct file_operations signalfd_fops = { .read = signalfd_read, }; -asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask, - size_t sizemask, int flags) +SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, + size_t, sizemask, int, flags) { sigset_t sigmask; struct signalfd_ctx *ctx; @@ -259,8 +259,8 @@ asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask, return ufd; } -asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, - size_t sizemask) +SYSCALL_DEFINE3(signalfd, int, ufd, sigset_t __user *, user_mask, + size_t, sizemask) { return sys_signalfd4(ufd, user_mask, sizemask, 0); } diff --git a/fs/smbfs/Kconfig b/fs/smbfs/Kconfig new file mode 100644 index 00000000000..e668127c8b2 --- /dev/null +++ b/fs/smbfs/Kconfig @@ -0,0 +1,55 @@ +config SMB_FS + tristate "SMB file system support (OBSOLETE, please use CIFS)" + depends on INET + select NLS + help + SMB (Server Message Block) is the protocol Windows for Workgroups + (WfW), Windows 95/98, Windows NT and OS/2 Lan Manager use to share + files and printers over local networks. Saying Y here allows you to + mount their file systems (often called "shares" in this context) and + access them just like any other Unix directory. Currently, this + works only if the Windows machines use TCP/IP as the underlying + transport protocol, and not NetBEUI. For details, read + <file:Documentation/filesystems/smbfs.txt> and the SMB-HOWTO, + available from <http://www.tldp.org/docs.html#howto>. + + Note: if you just want your box to act as an SMB *server* and make + files and printing services available to Windows clients (which need + to have a TCP/IP stack), you don't need to say Y here; you can use + the program SAMBA (available from <ftp://ftp.samba.org/pub/samba/>) + for that. + + General information about how to connect Linux, Windows machines and + Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. + + To compile the SMB support as a module, choose M here: + the module will be called smbfs. Most people say N, however. + +config SMB_NLS_DEFAULT + bool "Use a default NLS" + depends on SMB_FS + help + Enabling this will make smbfs use nls translations by default. You + need to specify the local charset (CONFIG_NLS_DEFAULT) in the nls + settings and you need to give the default nls for the SMB server as + CONFIG_SMB_NLS_REMOTE. + + The nls settings can be changed at mount time, if your smbmount + supports that, using the codepage and iocharset parameters. + + smbmount from samba 2.2.0 or later supports this. + +config SMB_NLS_REMOTE + string "Default Remote NLS Option" + depends on SMB_NLS_DEFAULT + default "cp437" + help + This setting allows you to specify a default value for which + codepage the server uses. If this field is left blank no + translations will be done by default. The local codepage/charset + default to CONFIG_NLS_DEFAULT. + + The nls settings can be changed at mount time, if your smbmount + supports that, using the codepage and iocharset parameters. + + smbmount from samba 2.2.0 or later supports this. diff --git a/fs/splice.c b/fs/splice.c index a54b3e3f10a..4ed0ba44a96 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1435,8 +1435,8 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, * Currently we punt and implement it as a normal copy, see pipe_to_user(). * */ -asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov, - unsigned long nr_segs, unsigned int flags) +SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, iov, + unsigned long, nr_segs, unsigned int, flags) { struct file *file; long error; @@ -1461,9 +1461,9 @@ asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov, return error; } -asmlinkage long sys_splice(int fd_in, loff_t __user *off_in, - int fd_out, loff_t __user *off_out, - size_t len, unsigned int flags) +SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, + int, fd_out, loff_t __user *, off_out, + size_t, len, unsigned int, flags) { long error; struct file *in, *out; @@ -1685,7 +1685,7 @@ static long do_tee(struct file *in, struct file *out, size_t len, return ret; } -asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags) +SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) { struct file *in; int error, fput_in; diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig new file mode 100644 index 00000000000..25a00d19d68 --- /dev/null +++ b/fs/squashfs/Kconfig @@ -0,0 +1,51 @@ +config SQUASHFS + tristate "SquashFS 4.0 - Squashed file system support" + depends on BLOCK + select ZLIB_INFLATE + help + Saying Y here includes support for SquashFS 4.0 (a Compressed + Read-Only File System). Squashfs is a highly compressed read-only + filesystem for Linux. It uses zlib compression to compress both + files, inodes and directories. Inodes in the system are very small + and all blocks are packed to minimise data overhead. Block sizes + greater than 4K are supported up to a maximum of 1 Mbytes (default + block size 128K). SquashFS 4.0 supports 64 bit filesystems and files + (larger than 4GB), full uid/gid information, hard links and + timestamps. + + Squashfs is intended for general read-only filesystem use, for + archival use (i.e. in cases where a .tar.gz file may be used), and in + embedded systems where low overhead is needed. Further information + and tools are available from http://squashfs.sourceforge.net. + + If you want to compile this as a module ( = code which can be + inserted in and removed from the running kernel whenever you want), + say M here and read <file:Documentation/modules.txt>. The module + will be called squashfs. Note that the root file system (the one + containing the directory /) cannot be compiled as a module. + + If unsure, say N. + +config SQUASHFS_EMBEDDED + + bool "Additional option for memory-constrained systems" + depends on SQUASHFS + default n + help + Saying Y here allows you to specify cache size. + + If unsure, say N. + +config SQUASHFS_FRAGMENT_CACHE_SIZE + int "Number of fragments cached" if SQUASHFS_EMBEDDED + depends on SQUASHFS + default "3" + help + By default SquashFS caches the last 3 fragments read from + the filesystem. Increasing this amount may mean SquashFS + has to re-read fragments less often from disk, at the expense + of extra system memory. Decreasing this amount will mean + SquashFS uses less memory at the expense of extra reads from disk. + + Note there must be at least one cached fragment. Anything + much more than three will probably not make much difference. diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 6840da1bf21..283daafc568 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -26,7 +26,6 @@ #define SQUASHFS_CACHED_FRAGMENTS CONFIG_SQUASHFS_FRAGMENT_CACHE_SIZE #define SQUASHFS_MAJOR 4 #define SQUASHFS_MINOR 0 -#define SQUASHFS_MAGIC 0x73717368 #define SQUASHFS_START 0 /* size of metadata (inode and directory) blocks */ diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index a0466d7467b..071df5b5b49 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -35,6 +35,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/zlib.h> +#include <linux/magic.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" diff --git a/fs/stat.c b/fs/stat.c index 7e12a6f8279..2db740a0cfb 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -152,7 +152,7 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } -asmlinkage long sys_stat(char __user * filename, struct __old_kernel_stat __user * statbuf) +SYSCALL_DEFINE2(stat, char __user *, filename, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error = vfs_stat_fd(AT_FDCWD, filename, &stat); @@ -162,7 +162,8 @@ asmlinkage long sys_stat(char __user * filename, struct __old_kernel_stat __user return error; } -asmlinkage long sys_lstat(char __user * filename, struct __old_kernel_stat __user * statbuf) + +SYSCALL_DEFINE2(lstat, char __user *, filename, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error = vfs_lstat_fd(AT_FDCWD, filename, &stat); @@ -172,7 +173,8 @@ asmlinkage long sys_lstat(char __user * filename, struct __old_kernel_stat __use return error; } -asmlinkage long sys_fstat(unsigned int fd, struct __old_kernel_stat __user * statbuf) + +SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); @@ -235,7 +237,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } -asmlinkage long sys_newstat(char __user *filename, struct stat __user *statbuf) +SYSCALL_DEFINE2(newstat, char __user *, filename, struct stat __user *, statbuf) { struct kstat stat; int error = vfs_stat_fd(AT_FDCWD, filename, &stat); @@ -246,7 +248,7 @@ asmlinkage long sys_newstat(char __user *filename, struct stat __user *statbuf) return error; } -asmlinkage long sys_newlstat(char __user *filename, struct stat __user *statbuf) +SYSCALL_DEFINE2(newlstat, char __user *, filename, struct stat __user *, statbuf) { struct kstat stat; int error = vfs_lstat_fd(AT_FDCWD, filename, &stat); @@ -258,8 +260,8 @@ asmlinkage long sys_newlstat(char __user *filename, struct stat __user *statbuf) } #if !defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_SYS_NEWFSTATAT) -asmlinkage long sys_newfstatat(int dfd, char __user *filename, - struct stat __user *statbuf, int flag) +SYSCALL_DEFINE4(newfstatat, int, dfd, char __user *, filename, + struct stat __user *, statbuf, int, flag) { struct kstat stat; int error = -EINVAL; @@ -280,7 +282,7 @@ out: } #endif -asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf) +SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); @@ -291,8 +293,8 @@ asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf) return error; } -asmlinkage long sys_readlinkat(int dfd, const char __user *pathname, - char __user *buf, int bufsiz) +SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname, + char __user *, buf, int, bufsiz) { struct path path; int error; @@ -318,8 +320,8 @@ asmlinkage long sys_readlinkat(int dfd, const char __user *pathname, return error; } -asmlinkage long sys_readlink(const char __user *path, char __user *buf, - int bufsiz) +SYSCALL_DEFINE3(readlink, const char __user *, path, char __user *, buf, + int, bufsiz) { return sys_readlinkat(AT_FDCWD, path, buf, bufsiz); } @@ -365,7 +367,7 @@ static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf) return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } -asmlinkage long sys_stat64(char __user * filename, struct stat64 __user * statbuf) +SYSCALL_DEFINE2(stat64, char __user *, filename, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_stat(filename, &stat); @@ -375,7 +377,8 @@ asmlinkage long sys_stat64(char __user * filename, struct stat64 __user * statbu return error; } -asmlinkage long sys_lstat64(char __user * filename, struct stat64 __user * statbuf) + +SYSCALL_DEFINE2(lstat64, char __user *, filename, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_lstat(filename, &stat); @@ -385,7 +388,8 @@ asmlinkage long sys_lstat64(char __user * filename, struct stat64 __user * statb return error; } -asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user * statbuf) + +SYSCALL_DEFINE2(fstat64, unsigned long, fd, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); @@ -396,8 +400,8 @@ asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user * statbuf) return error; } -asmlinkage long sys_fstatat64(int dfd, char __user *filename, - struct stat64 __user *statbuf, int flag) +SYSCALL_DEFINE4(fstatat64, int, dfd, char __user *, filename, + struct stat64 __user *, statbuf, int, flag) { struct kstat stat; int error = -EINVAL; diff --git a/fs/super.c b/fs/super.c index ed080c41716..645e5403f2a 100644 --- a/fs/super.c +++ b/fs/super.c @@ -544,7 +544,7 @@ rescan: return NULL; } -asmlinkage long sys_ustat(unsigned dev, struct ustat __user * ubuf) +SYSCALL_DEFINE2(ustat, unsigned, dev, struct ustat __user *, ubuf) { struct super_block *s; struct ustat tmp; diff --git a/fs/sync.c b/fs/sync.c index ac02b56548b..a16d53e5fe9 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -36,7 +36,7 @@ static void do_sync(unsigned long wait) laptop_sync_completion(); } -asmlinkage long sys_sync(void) +SYSCALL_DEFINE0(sync) { do_sync(1); return 0; @@ -144,12 +144,12 @@ static int do_fsync(unsigned int fd, int datasync) return ret; } -asmlinkage long sys_fsync(unsigned int fd) +SYSCALL_DEFINE1(fsync, unsigned int, fd) { return do_fsync(fd, 0); } -asmlinkage long sys_fdatasync(unsigned int fd) +SYSCALL_DEFINE1(fdatasync, unsigned int, fd) { return do_fsync(fd, 1); } @@ -201,8 +201,8 @@ asmlinkage long sys_fdatasync(unsigned int fd) * already-instantiated disk blocks, there are no guarantees here that the data * will be available after a crash. */ -asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes, - unsigned int flags) +SYSCALL_DEFINE(sync_file_range)(int fd, loff_t offset, loff_t nbytes, + unsigned int flags) { int ret; struct file *file; @@ -262,14 +262,32 @@ out_put: out: return ret; } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_sync_file_range(long fd, loff_t offset, loff_t nbytes, + long flags) +{ + return SYSC_sync_file_range((int) fd, offset, nbytes, + (unsigned int) flags); +} +SYSCALL_ALIAS(sys_sync_file_range, SyS_sync_file_range); +#endif /* It would be nice if people remember that not all the world's an i386 when they introduce new system calls */ -asmlinkage long sys_sync_file_range2(int fd, unsigned int flags, - loff_t offset, loff_t nbytes) +SYSCALL_DEFINE(sync_file_range2)(int fd, unsigned int flags, + loff_t offset, loff_t nbytes) { return sys_sync_file_range(fd, offset, nbytes, flags); } +#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS +asmlinkage long SyS_sync_file_range2(long fd, long flags, + loff_t offset, loff_t nbytes) +{ + return SYSC_sync_file_range2((int) fd, (unsigned int) flags, + offset, nbytes); +} +SYSCALL_ALIAS(sys_sync_file_range2, SyS_sync_file_range2); +#endif /* * `endbyte' is inclusive diff --git a/fs/sysfs/Kconfig b/fs/sysfs/Kconfig new file mode 100644 index 00000000000..f4b67588b9d --- /dev/null +++ b/fs/sysfs/Kconfig @@ -0,0 +1,23 @@ +config SYSFS + bool "sysfs file system support" if EMBEDDED + default y + help + The sysfs filesystem is a virtual filesystem that the kernel uses to + export internal kernel objects, their attributes, and their + relationships to one another. + + Users can use sysfs to ascertain useful information about the running + kernel, such as the devices the kernel has discovered on each bus and + which driver each is bound to. sysfs can also be used to tune devices + and other kernel subsystems. + + Some system agents rely on the information in sysfs to operate. + /sbin/hotplug uses device and object attributes in sysfs to assist in + delegating policy decisions, like persistently naming devices. + + sysfs is currently used by the block subsystem to mount the root + partition. If sysfs is disabled you must specify the boot device on + the kernel boot command line via its major and minor numbers. For + example, "root=03:01" for /dev/hda1. + + Designers of embedded systems may wish to say N here to conserve space. diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index 66f6e58a7e4..f2c478c3424 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -63,6 +63,9 @@ read(struct file *file, char __user *userbuf, size_t bytes, loff_t *off) int count = min_t(size_t, bytes, PAGE_SIZE); char *temp; + if (!bytes) + return 0; + if (size) { if (offs > size) return 0; @@ -131,6 +134,9 @@ static ssize_t write(struct file *file, const char __user *userbuf, int count = min_t(size_t, bytes, PAGE_SIZE); char *temp; + if (!bytes) + return 0; + if (size) { if (offs > size) return 0; diff --git a/fs/sysv/Kconfig b/fs/sysv/Kconfig new file mode 100644 index 00000000000..33aeb4b75db --- /dev/null +++ b/fs/sysv/Kconfig @@ -0,0 +1,36 @@ +config SYSV_FS + tristate "System V/Xenix/V7/Coherent file system support" + depends on BLOCK + help + SCO, Xenix and Coherent are commercial Unix systems for Intel + machines, and Version 7 was used on the DEC PDP-11. Saying Y + here would allow you to read from their floppies and hard disk + partitions. + + If you have floppies or hard disk partitions like that, it is likely + that they contain binaries from those other Unix systems; in order + to run these binaries, you will want to install linux-abi which is + a set of kernel modules that lets you run SCO, Xenix, Wyse, + UnixWare, Dell Unix and System V programs under Linux. It is + available via FTP (user: ftp) from + <ftp://ftp.openlinux.org/pub/people/hch/linux-abi/>). + NOTE: that will work only for binaries from Intel-based systems; + PDP ones will have to wait until somebody ports Linux to -11 ;-) + + If you only intend to mount files from some other Unix over the + network using NFS, you don't need the System V file system support + (but you need NFS file system support obviously). + + Note that this option is generally not needed for floppies, since a + good portable way to transport files and directories between unixes + (and even other operating systems) is given by the tar program ("man + tar" or preferably "info tar"). Note also that this option has + nothing whatsoever to do with the option "System V IPC". Read about + the System V file system in + <file:Documentation/filesystems/sysv-fs.txt>. + Saying Y here will enlarge your kernel by about 27 KB. + + To compile this as a module, choose M here: the module will be called + sysv. + + If you haven't heard about all of this before, it's safe to say N. diff --git a/fs/timerfd.c b/fs/timerfd.c index 0862f0e49d0..6a123b8ff3f 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -177,7 +177,7 @@ static struct file *timerfd_fget(int fd) return file; } -asmlinkage long sys_timerfd_create(int clockid, int flags) +SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) { int ufd; struct timerfd_ctx *ctx; @@ -208,9 +208,9 @@ asmlinkage long sys_timerfd_create(int clockid, int flags) return ufd; } -asmlinkage long sys_timerfd_settime(int ufd, int flags, - const struct itimerspec __user *utmr, - struct itimerspec __user *otmr) +SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, + const struct itimerspec __user *, utmr, + struct itimerspec __user *, otmr) { struct file *file; struct timerfd_ctx *ctx; @@ -265,7 +265,7 @@ asmlinkage long sys_timerfd_settime(int ufd, int flags, return 0; } -asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr) +SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr) { struct file *file; struct timerfd_ctx *ctx; diff --git a/fs/udf/Kconfig b/fs/udf/Kconfig new file mode 100644 index 00000000000..0e0e99bd6bc --- /dev/null +++ b/fs/udf/Kconfig @@ -0,0 +1,18 @@ +config UDF_FS + tristate "UDF file system support" + select CRC_ITU_T + help + This is the new file system used on some CD-ROMs and DVDs. Say Y if + you intend to mount DVD discs or CDRW's written in packet mode, or + if written to by other UDF utilities, such as DirectCD. + Please read <file:Documentation/filesystems/udf.txt>. + + To compile this file system support as a module, choose M here: the + module will be called udf. + + If unsure, say N. + +config UDF_NLS + bool + default y + depends on (UDF_FS=m && NLS) || (UDF_FS=y && NLS=y) diff --git a/fs/ufs/Kconfig b/fs/ufs/Kconfig new file mode 100644 index 00000000000..e4f10a40768 --- /dev/null +++ b/fs/ufs/Kconfig @@ -0,0 +1,43 @@ +config UFS_FS + tristate "UFS file system support (read only)" + depends on BLOCK + help + BSD and derivate versions of Unix (such as SunOS, FreeBSD, NetBSD, + OpenBSD and NeXTstep) use a file system called UFS. Some System V + Unixes can create and mount hard disk partitions and diskettes using + this file system as well. Saying Y here will allow you to read from + these partitions; if you also want to write to them, say Y to the + experimental "UFS file system write support", below. Please read the + file <file:Documentation/filesystems/ufs.txt> for more information. + + The recently released UFS2 variant (used in FreeBSD 5.x) is + READ-ONLY supported. + + Note that this option is generally not needed for floppies, since a + good portable way to transport files and directories between unixes + (and even other operating systems) is given by the tar program ("man + tar" or preferably "info tar"). + + When accessing NeXTstep files, you may need to convert them from the + NeXT character set to the Latin1 character set; use the program + recode ("info recode") for this purpose. + + To compile the UFS file system support as a module, choose M here: the + module will be called ufs. + + If you haven't heard about all of this before, it's safe to say N. + +config UFS_FS_WRITE + bool "UFS file system write support (DANGEROUS)" + depends on UFS_FS && EXPERIMENTAL + help + Say Y here if you want to try writing to UFS partitions. This is + experimental, so you should back up your UFS partitions beforehand. + +config UFS_DEBUG + bool "UFS debugging" + depends on UFS_FS + help + If you are experiencing any problems with the UFS filesystem, say + Y here. This will result in _many_ additional debugging messages to be + written to the system log. diff --git a/fs/utimes.c b/fs/utimes.c index 6929e3e91d0..e4c75db5d37 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -24,7 +24,7 @@ * must be owner or have write permission. * Else, update from *times, must be owner or super user. */ -asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times) +SYSCALL_DEFINE2(utime, char __user *, filename, struct utimbuf __user *, times) { struct timespec tv[2]; @@ -170,7 +170,8 @@ out: return error; } -asmlinkage long sys_utimensat(int dfd, char __user *filename, struct timespec __user *utimes, int flags) +SYSCALL_DEFINE4(utimensat, int, dfd, char __user *, filename, + struct timespec __user *, utimes, int, flags) { struct timespec tstimes[2]; @@ -187,7 +188,8 @@ asmlinkage long sys_utimensat(int dfd, char __user *filename, struct timespec __ return do_utimes(dfd, filename, utimes ? tstimes : NULL, flags); } -asmlinkage long sys_futimesat(int dfd, char __user *filename, struct timeval __user *utimes) +SYSCALL_DEFINE3(futimesat, int, dfd, char __user *, filename, + struct timeval __user *, utimes) { struct timeval times[2]; struct timespec tstimes[2]; @@ -214,7 +216,8 @@ asmlinkage long sys_futimesat(int dfd, char __user *filename, struct timeval __u return do_utimes(dfd, filename, utimes ? tstimes : NULL, 0); } -asmlinkage long sys_utimes(char __user *filename, struct timeval __user *utimes) +SYSCALL_DEFINE2(utimes, char __user *, filename, + struct timeval __user *, utimes) { return sys_futimesat(AT_FDCWD, filename, utimes); } diff --git a/fs/xattr.c b/fs/xattr.c index 237804cd6b5..197c4fcac03 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -251,9 +251,9 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, return error; } -asmlinkage long -sys_setxattr(const char __user *pathname, const char __user *name, - const void __user *value, size_t size, int flags) +SYSCALL_DEFINE5(setxattr, const char __user *, pathname, + const char __user *, name, const void __user *, value, + size_t, size, int, flags) { struct path path; int error; @@ -270,9 +270,9 @@ sys_setxattr(const char __user *pathname, const char __user *name, return error; } -asmlinkage long -sys_lsetxattr(const char __user *pathname, const char __user *name, - const void __user *value, size_t size, int flags) +SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname, + const char __user *, name, const void __user *, value, + size_t, size, int, flags) { struct path path; int error; @@ -289,9 +289,8 @@ sys_lsetxattr(const char __user *pathname, const char __user *name, return error; } -asmlinkage long -sys_fsetxattr(int fd, const char __user *name, const void __user *value, - size_t size, int flags) +SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, + const void __user *,value, size_t, size, int, flags) { struct file *f; struct dentry *dentry; @@ -349,9 +348,8 @@ getxattr(struct dentry *d, const char __user *name, void __user *value, return error; } -asmlinkage ssize_t -sys_getxattr(const char __user *pathname, const char __user *name, - void __user *value, size_t size) +SYSCALL_DEFINE4(getxattr, const char __user *, pathname, + const char __user *, name, void __user *, value, size_t, size) { struct path path; ssize_t error; @@ -364,9 +362,8 @@ sys_getxattr(const char __user *pathname, const char __user *name, return error; } -asmlinkage ssize_t -sys_lgetxattr(const char __user *pathname, const char __user *name, void __user *value, - size_t size) +SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname, + const char __user *, name, void __user *, value, size_t, size) { struct path path; ssize_t error; @@ -379,8 +376,8 @@ sys_lgetxattr(const char __user *pathname, const char __user *name, void __user return error; } -asmlinkage ssize_t -sys_fgetxattr(int fd, const char __user *name, void __user *value, size_t size) +SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, + void __user *, value, size_t, size) { struct file *f; ssize_t error = -EBADF; @@ -424,8 +421,8 @@ listxattr(struct dentry *d, char __user *list, size_t size) return error; } -asmlinkage ssize_t -sys_listxattr(const char __user *pathname, char __user *list, size_t size) +SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list, + size_t, size) { struct path path; ssize_t error; @@ -438,8 +435,8 @@ sys_listxattr(const char __user *pathname, char __user *list, size_t size) return error; } -asmlinkage ssize_t -sys_llistxattr(const char __user *pathname, char __user *list, size_t size) +SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list, + size_t, size) { struct path path; ssize_t error; @@ -452,8 +449,7 @@ sys_llistxattr(const char __user *pathname, char __user *list, size_t size) return error; } -asmlinkage ssize_t -sys_flistxattr(int fd, char __user *list, size_t size) +SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) { struct file *f; ssize_t error = -EBADF; @@ -485,8 +481,8 @@ removexattr(struct dentry *d, const char __user *name) return vfs_removexattr(d, kname); } -asmlinkage long -sys_removexattr(const char __user *pathname, const char __user *name) +SYSCALL_DEFINE2(removexattr, const char __user *, pathname, + const char __user *, name) { struct path path; int error; @@ -503,8 +499,8 @@ sys_removexattr(const char __user *pathname, const char __user *name) return error; } -asmlinkage long -sys_lremovexattr(const char __user *pathname, const char __user *name) +SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname, + const char __user *, name) { struct path path; int error; @@ -521,8 +517,7 @@ sys_lremovexattr(const char __user *pathname, const char __user *name) return error; } -asmlinkage long -sys_fremovexattr(int fd, const char __user *name) +SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) { struct file *f; struct dentry *dentry; diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 3f53dd101f9..29228f5899c 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -1,6 +1,7 @@ config XFS_FS tristate "XFS filesystem support" depends on BLOCK + select EXPORTFS help XFS is a high performance journaling filesystem which originated on the SGI IRIX platform. It is completely multi-threaded, can diff --git a/fs/xfs/linux-2.6/xfs_aops.h b/fs/xfs/linux-2.6/xfs_aops.h index 7b26f5ff969..1dd52884975 100644 --- a/fs/xfs/linux-2.6/xfs_aops.h +++ b/fs/xfs/linux-2.6/xfs_aops.h @@ -21,8 +21,6 @@ extern struct workqueue_struct *xfsdatad_workqueue; extern mempool_t *xfs_ioend_pool; -typedef void (*xfs_ioend_func_t)(void *); - /* * xfs_ioend struct manages large extent writes for XFS. * It can manage several multi-page bio's at once. diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index cb329edc925..d71dc44e21e 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -166,75 +166,6 @@ test_page_region( } /* - * Mapping of multi-page buffers into contiguous virtual space - */ - -typedef struct a_list { - void *vm_addr; - struct a_list *next; -} a_list_t; - -static a_list_t *as_free_head; -static int as_list_len; -static DEFINE_SPINLOCK(as_lock); - -/* - * Try to batch vunmaps because they are costly. - */ -STATIC void -free_address( - void *addr) -{ - a_list_t *aentry; - -#ifdef CONFIG_XEN - /* - * Xen needs to be able to make sure it can get an exclusive - * RO mapping of pages it wants to turn into a pagetable. If - * a newly allocated page is also still being vmap()ed by xfs, - * it will cause pagetable construction to fail. This is a - * quick workaround to always eagerly unmap pages so that Xen - * is happy. - */ - vunmap(addr); - return; -#endif - - aentry = kmalloc(sizeof(a_list_t), GFP_NOWAIT); - if (likely(aentry)) { - spin_lock(&as_lock); - aentry->next = as_free_head; - aentry->vm_addr = addr; - as_free_head = aentry; - as_list_len++; - spin_unlock(&as_lock); - } else { - vunmap(addr); - } -} - -STATIC void -purge_addresses(void) -{ - a_list_t *aentry, *old; - - if (as_free_head == NULL) - return; - - spin_lock(&as_lock); - aentry = as_free_head; - as_free_head = NULL; - as_list_len = 0; - spin_unlock(&as_lock); - - while ((old = aentry) != NULL) { - vunmap(aentry->vm_addr); - aentry = aentry->next; - kfree(old); - } -} - -/* * Internal xfs_buf_t object manipulation */ @@ -333,7 +264,7 @@ xfs_buf_free( uint i; if ((bp->b_flags & XBF_MAPPED) && (bp->b_page_count > 1)) - free_address(bp->b_addr - bp->b_offset); + vm_unmap_ram(bp->b_addr - bp->b_offset, bp->b_page_count); for (i = 0; i < bp->b_page_count; i++) { struct page *page = bp->b_pages[i]; @@ -455,10 +386,8 @@ _xfs_buf_map_pages( bp->b_addr = page_address(bp->b_pages[0]) + bp->b_offset; bp->b_flags |= XBF_MAPPED; } else if (flags & XBF_MAPPED) { - if (as_list_len > 64) - purge_addresses(); - bp->b_addr = vmap(bp->b_pages, bp->b_page_count, - VM_MAP, PAGE_KERNEL); + bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, + -1, PAGE_KERNEL); if (unlikely(bp->b_addr == NULL)) return -ENOMEM; bp->b_addr += bp->b_offset; @@ -1743,8 +1672,6 @@ xfsbufd( count++; } - if (as_list_len > 0) - purge_addresses(); if (count) blk_run_address_space(target->bt_mapping); diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c index 595751f7835..87b8cbd23d4 100644 --- a/fs/xfs/linux-2.6/xfs_export.c +++ b/fs/xfs/linux-2.6/xfs_export.c @@ -126,11 +126,26 @@ xfs_nfs_get_inode( if (ino == 0) return ERR_PTR(-ESTALE); - error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_SHARED, &ip, 0); - if (error) + /* + * The XFS_IGET_BULKSTAT means that an invalid inode number is just + * fine and not an indication of a corrupted filesystem. Because + * clients can send any kind of invalid file handle, e.g. after + * a restore on the server we have to deal with this case gracefully. + */ + error = xfs_iget(mp, NULL, ino, XFS_IGET_BULKSTAT, + XFS_ILOCK_SHARED, &ip, 0); + if (error) { + /* + * EINVAL means the inode cluster doesn't exist anymore. + * This implies the filehandle is stale, so we should + * translate it here. + * We don't use ESTALE directly down the chain to not + * confuse applications using bulkstat that expect EINVAL. + */ + if (error == EINVAL) + error = ESTALE; return ERR_PTR(-error); - if (!ip) - return ERR_PTR(-EIO); + } if (ip->i_d.di_gen != generation) { xfs_iput_new(ip, XFS_ILOCK_SHARED); diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c index e5be1e0be80..4bd112313f3 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl.c +++ b/fs/xfs/linux-2.6/xfs_ioctl.c @@ -50,12 +50,14 @@ #include "xfs_vnodeops.h" #include "xfs_quota.h" #include "xfs_inode_item.h" +#include "xfs_export.h" #include <linux/capability.h> #include <linux/dcache.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/pagemap.h> +#include <linux/exportfs.h> /* * xfs_find_handle maps from userspace xfs_fsop_handlereq structure to @@ -164,97 +166,69 @@ xfs_find_handle( return 0; } - /* - * Convert userspace handle data into inode. - * - * We use the fact that all the fsop_handlereq ioctl calls have a data - * structure argument whose first component is always a xfs_fsop_handlereq_t, - * so we can pass that sub structure into this handy, shared routine. - * - * If no error, caller must always iput the returned inode. + * No need to do permission checks on the various pathname components + * as the handle operations are privileged. */ STATIC int -xfs_vget_fsop_handlereq( - xfs_mount_t *mp, - struct inode *parinode, /* parent inode pointer */ - xfs_fsop_handlereq_t *hreq, - struct inode **inode) +xfs_handle_acceptable( + void *context, + struct dentry *dentry) +{ + return 1; +} + +/* + * Convert userspace handle data into a dentry. + */ +struct dentry * +xfs_handle_to_dentry( + struct file *parfilp, + void __user *uhandle, + u32 hlen) { - void __user *hanp; - size_t hlen; - xfs_fid_t *xfid; - xfs_handle_t *handlep; xfs_handle_t handle; - xfs_inode_t *ip; - xfs_ino_t ino; - __u32 igen; - int error; + struct xfs_fid64 fid; /* * Only allow handle opens under a directory. */ - if (!S_ISDIR(parinode->i_mode)) - return XFS_ERROR(ENOTDIR); - - hanp = hreq->ihandle; - hlen = hreq->ihandlen; - handlep = &handle; - - if (hlen < sizeof(handlep->ha_fsid) || hlen > sizeof(*handlep)) - return XFS_ERROR(EINVAL); - if (copy_from_user(handlep, hanp, hlen)) - return XFS_ERROR(EFAULT); - if (hlen < sizeof(*handlep)) - memset(((char *)handlep) + hlen, 0, sizeof(*handlep) - hlen); - if (hlen > sizeof(handlep->ha_fsid)) { - if (handlep->ha_fid.fid_len != - (hlen - sizeof(handlep->ha_fsid) - - sizeof(handlep->ha_fid.fid_len)) || - handlep->ha_fid.fid_pad) - return XFS_ERROR(EINVAL); - } - - /* - * Crack the handle, obtain the inode # & generation # - */ - xfid = (struct xfs_fid *)&handlep->ha_fid; - if (xfid->fid_len == sizeof(*xfid) - sizeof(xfid->fid_len)) { - ino = xfid->fid_ino; - igen = xfid->fid_gen; - } else { - return XFS_ERROR(EINVAL); - } - - /* - * Get the XFS inode, building a Linux inode to go with it. - */ - error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_SHARED, &ip, 0); - if (error) - return error; - if (ip == NULL) - return XFS_ERROR(EIO); - if (ip->i_d.di_gen != igen) { - xfs_iput_new(ip, XFS_ILOCK_SHARED); - return XFS_ERROR(ENOENT); - } - - xfs_iunlock(ip, XFS_ILOCK_SHARED); + if (!S_ISDIR(parfilp->f_path.dentry->d_inode->i_mode)) + return ERR_PTR(-ENOTDIR); + + if (hlen != sizeof(xfs_handle_t)) + return ERR_PTR(-EINVAL); + if (copy_from_user(&handle, uhandle, hlen)) + return ERR_PTR(-EFAULT); + if (handle.ha_fid.fid_len != + sizeof(handle.ha_fid) - sizeof(handle.ha_fid.fid_len)) + return ERR_PTR(-EINVAL); + + memset(&fid, 0, sizeof(struct fid)); + fid.ino = handle.ha_fid.fid_ino; + fid.gen = handle.ha_fid.fid_gen; + + return exportfs_decode_fh(parfilp->f_path.mnt, (struct fid *)&fid, 3, + FILEID_INO32_GEN | XFS_FILEID_TYPE_64FLAG, + xfs_handle_acceptable, NULL); +} - *inode = VFS_I(ip); - return 0; +STATIC struct dentry * +xfs_handlereq_to_dentry( + struct file *parfilp, + xfs_fsop_handlereq_t *hreq) +{ + return xfs_handle_to_dentry(parfilp, hreq->ihandle, hreq->ihandlen); } int xfs_open_by_handle( - xfs_mount_t *mp, - xfs_fsop_handlereq_t *hreq, struct file *parfilp, - struct inode *parinode) + xfs_fsop_handlereq_t *hreq) { const struct cred *cred = current_cred(); int error; - int new_fd; + int fd; int permflag; struct file *filp; struct inode *inode; @@ -263,19 +237,21 @@ xfs_open_by_handle( if (!capable(CAP_SYS_ADMIN)) return -XFS_ERROR(EPERM); - error = xfs_vget_fsop_handlereq(mp, parinode, hreq, &inode); - if (error) - return -error; + dentry = xfs_handlereq_to_dentry(parfilp, hreq); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + inode = dentry->d_inode; /* Restrict xfs_open_by_handle to directories & regular files. */ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) { - iput(inode); - return -XFS_ERROR(EINVAL); + error = -XFS_ERROR(EPERM); + goto out_dput; } #if BITS_PER_LONG != 32 hreq->oflags |= O_LARGEFILE; #endif + /* Put open permission in namei format. */ permflag = hreq->oflags; if ((permflag+1) & O_ACCMODE) @@ -285,50 +261,45 @@ xfs_open_by_handle( if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) && (permflag & FMODE_WRITE) && IS_APPEND(inode)) { - iput(inode); - return -XFS_ERROR(EPERM); + error = -XFS_ERROR(EPERM); + goto out_dput; } if ((permflag & FMODE_WRITE) && IS_IMMUTABLE(inode)) { - iput(inode); - return -XFS_ERROR(EACCES); + error = -XFS_ERROR(EACCES); + goto out_dput; } /* Can't write directories. */ - if ( S_ISDIR(inode->i_mode) && (permflag & FMODE_WRITE)) { - iput(inode); - return -XFS_ERROR(EISDIR); + if (S_ISDIR(inode->i_mode) && (permflag & FMODE_WRITE)) { + error = -XFS_ERROR(EISDIR); + goto out_dput; } - if ((new_fd = get_unused_fd()) < 0) { - iput(inode); - return new_fd; + fd = get_unused_fd(); + if (fd < 0) { + error = fd; + goto out_dput; } - dentry = d_obtain_alias(inode); - if (IS_ERR(dentry)) { - put_unused_fd(new_fd); - return PTR_ERR(dentry); - } - - /* Ensure umount returns EBUSY on umounts while this file is open. */ - mntget(parfilp->f_path.mnt); - - /* Create file pointer. */ - filp = dentry_open(dentry, parfilp->f_path.mnt, hreq->oflags, cred); + filp = dentry_open(dentry, mntget(parfilp->f_path.mnt), + hreq->oflags, cred); if (IS_ERR(filp)) { - put_unused_fd(new_fd); - return -XFS_ERROR(-PTR_ERR(filp)); + put_unused_fd(fd); + return PTR_ERR(filp); } if (inode->i_mode & S_IFREG) { - /* invisible operation should not change atime */ filp->f_flags |= O_NOATIME; filp->f_mode |= FMODE_NOCMTIME; } - fd_install(new_fd, filp); - return new_fd; + fd_install(fd, filp); + return fd; + + out_dput: + dput(dentry); + return error; } /* @@ -359,11 +330,10 @@ do_readlink( int xfs_readlink_by_handle( - xfs_mount_t *mp, - xfs_fsop_handlereq_t *hreq, - struct inode *parinode) + struct file *parfilp, + xfs_fsop_handlereq_t *hreq) { - struct inode *inode; + struct dentry *dentry; __u32 olen; void *link; int error; @@ -371,26 +341,28 @@ xfs_readlink_by_handle( if (!capable(CAP_SYS_ADMIN)) return -XFS_ERROR(EPERM); - error = xfs_vget_fsop_handlereq(mp, parinode, hreq, &inode); - if (error) - return -error; + dentry = xfs_handlereq_to_dentry(parfilp, hreq); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); /* Restrict this handle operation to symlinks only. */ - if (!S_ISLNK(inode->i_mode)) { + if (!S_ISLNK(dentry->d_inode->i_mode)) { error = -XFS_ERROR(EINVAL); - goto out_iput; + goto out_dput; } if (copy_from_user(&olen, hreq->ohandlen, sizeof(__u32))) { error = -XFS_ERROR(EFAULT); - goto out_iput; + goto out_dput; } link = kmalloc(MAXPATHLEN+1, GFP_KERNEL); - if (!link) - goto out_iput; + if (!link) { + error = -XFS_ERROR(ENOMEM); + goto out_dput; + } - error = -xfs_readlink(XFS_I(inode), link); + error = -xfs_readlink(XFS_I(dentry->d_inode), link); if (error) goto out_kfree; error = do_readlink(hreq->ohandle, olen, link); @@ -399,32 +371,31 @@ xfs_readlink_by_handle( out_kfree: kfree(link); - out_iput: - iput(inode); + out_dput: + dput(dentry); return error; } STATIC int xfs_fssetdm_by_handle( - xfs_mount_t *mp, - void __user *arg, - struct inode *parinode) + struct file *parfilp, + void __user *arg) { int error; struct fsdmidata fsd; xfs_fsop_setdm_handlereq_t dmhreq; - struct inode *inode; + struct dentry *dentry; if (!capable(CAP_MKNOD)) return -XFS_ERROR(EPERM); if (copy_from_user(&dmhreq, arg, sizeof(xfs_fsop_setdm_handlereq_t))) return -XFS_ERROR(EFAULT); - error = xfs_vget_fsop_handlereq(mp, parinode, &dmhreq.hreq, &inode); - if (error) - return -error; + dentry = xfs_handlereq_to_dentry(parfilp, &dmhreq.hreq); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); - if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) { + if (IS_IMMUTABLE(dentry->d_inode) || IS_APPEND(dentry->d_inode)) { error = -XFS_ERROR(EPERM); goto out; } @@ -434,24 +405,23 @@ xfs_fssetdm_by_handle( goto out; } - error = -xfs_set_dmattrs(XFS_I(inode), fsd.fsd_dmevmask, + error = -xfs_set_dmattrs(XFS_I(dentry->d_inode), fsd.fsd_dmevmask, fsd.fsd_dmstate); out: - iput(inode); + dput(dentry); return error; } STATIC int xfs_attrlist_by_handle( - xfs_mount_t *mp, - void __user *arg, - struct inode *parinode) + struct file *parfilp, + void __user *arg) { - int error; + int error = -ENOMEM; attrlist_cursor_kern_t *cursor; xfs_fsop_attrlist_handlereq_t al_hreq; - struct inode *inode; + struct dentry *dentry; char *kbuf; if (!capable(CAP_SYS_ADMIN)) @@ -467,16 +437,16 @@ xfs_attrlist_by_handle( if (al_hreq.flags & ~(ATTR_ROOT | ATTR_SECURE)) return -XFS_ERROR(EINVAL); - error = xfs_vget_fsop_handlereq(mp, parinode, &al_hreq.hreq, &inode); - if (error) - goto out; + dentry = xfs_handlereq_to_dentry(parfilp, &al_hreq.hreq); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); kbuf = kmalloc(al_hreq.buflen, GFP_KERNEL); if (!kbuf) - goto out_vn_rele; + goto out_dput; cursor = (attrlist_cursor_kern_t *)&al_hreq.pos; - error = xfs_attr_list(XFS_I(inode), kbuf, al_hreq.buflen, + error = -xfs_attr_list(XFS_I(dentry->d_inode), kbuf, al_hreq.buflen, al_hreq.flags, cursor); if (error) goto out_kfree; @@ -486,10 +456,9 @@ xfs_attrlist_by_handle( out_kfree: kfree(kbuf); - out_vn_rele: - iput(inode); - out: - return -error; + out_dput: + dput(dentry); + return error; } int @@ -564,15 +533,13 @@ xfs_attrmulti_attr_remove( STATIC int xfs_attrmulti_by_handle( - xfs_mount_t *mp, - void __user *arg, struct file *parfilp, - struct inode *parinode) + void __user *arg) { int error; xfs_attr_multiop_t *ops; xfs_fsop_attrmulti_handlereq_t am_hreq; - struct inode *inode; + struct dentry *dentry; unsigned int i, size; char *attr_name; @@ -581,19 +548,19 @@ xfs_attrmulti_by_handle( if (copy_from_user(&am_hreq, arg, sizeof(xfs_fsop_attrmulti_handlereq_t))) return -XFS_ERROR(EFAULT); - error = xfs_vget_fsop_handlereq(mp, parinode, &am_hreq.hreq, &inode); - if (error) - goto out; + dentry = xfs_handlereq_to_dentry(parfilp, &am_hreq.hreq); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); error = E2BIG; size = am_hreq.opcount * sizeof(xfs_attr_multiop_t); if (!size || size > 16 * PAGE_SIZE) - goto out_vn_rele; + goto out_dput; error = ENOMEM; ops = kmalloc(size, GFP_KERNEL); if (!ops) - goto out_vn_rele; + goto out_dput; error = EFAULT; if (copy_from_user(ops, am_hreq.ops, size)) @@ -615,25 +582,28 @@ xfs_attrmulti_by_handle( switch (ops[i].am_opcode) { case ATTR_OP_GET: - ops[i].am_error = xfs_attrmulti_attr_get(inode, - attr_name, ops[i].am_attrvalue, - &ops[i].am_length, ops[i].am_flags); + ops[i].am_error = xfs_attrmulti_attr_get( + dentry->d_inode, attr_name, + ops[i].am_attrvalue, &ops[i].am_length, + ops[i].am_flags); break; case ATTR_OP_SET: ops[i].am_error = mnt_want_write(parfilp->f_path.mnt); if (ops[i].am_error) break; - ops[i].am_error = xfs_attrmulti_attr_set(inode, - attr_name, ops[i].am_attrvalue, - ops[i].am_length, ops[i].am_flags); + ops[i].am_error = xfs_attrmulti_attr_set( + dentry->d_inode, attr_name, + ops[i].am_attrvalue, ops[i].am_length, + ops[i].am_flags); mnt_drop_write(parfilp->f_path.mnt); break; case ATTR_OP_REMOVE: ops[i].am_error = mnt_want_write(parfilp->f_path.mnt); if (ops[i].am_error) break; - ops[i].am_error = xfs_attrmulti_attr_remove(inode, - attr_name, ops[i].am_flags); + ops[i].am_error = xfs_attrmulti_attr_remove( + dentry->d_inode, attr_name, + ops[i].am_flags); mnt_drop_write(parfilp->f_path.mnt); break; default: @@ -647,9 +617,8 @@ xfs_attrmulti_by_handle( kfree(attr_name); out_kfree_ops: kfree(ops); - out_vn_rele: - iput(inode); - out: + out_dput: + dput(dentry); return -error; } @@ -1440,23 +1409,23 @@ xfs_file_ioctl( if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t))) return -XFS_ERROR(EFAULT); - return xfs_open_by_handle(mp, &hreq, filp, inode); + return xfs_open_by_handle(filp, &hreq); } case XFS_IOC_FSSETDM_BY_HANDLE: - return xfs_fssetdm_by_handle(mp, arg, inode); + return xfs_fssetdm_by_handle(filp, arg); case XFS_IOC_READLINK_BY_HANDLE: { xfs_fsop_handlereq_t hreq; if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t))) return -XFS_ERROR(EFAULT); - return xfs_readlink_by_handle(mp, &hreq, inode); + return xfs_readlink_by_handle(filp, &hreq); } case XFS_IOC_ATTRLIST_BY_HANDLE: - return xfs_attrlist_by_handle(mp, arg, inode); + return xfs_attrlist_by_handle(filp, arg); case XFS_IOC_ATTRMULTI_BY_HANDLE: - return xfs_attrmulti_by_handle(mp, arg, filp, inode); + return xfs_attrmulti_by_handle(filp, arg); case XFS_IOC_SWAPEXT: { struct xfs_swapext sxp; diff --git a/fs/xfs/linux-2.6/xfs_ioctl.h b/fs/xfs/linux-2.6/xfs_ioctl.h index 8c16bf2d7e0..7bd7c6afc1e 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl.h +++ b/fs/xfs/linux-2.6/xfs_ioctl.h @@ -34,16 +34,13 @@ xfs_find_handle( extern int xfs_open_by_handle( - xfs_mount_t *mp, - xfs_fsop_handlereq_t *hreq, struct file *parfilp, - struct inode *parinode); + xfs_fsop_handlereq_t *hreq); extern int xfs_readlink_by_handle( - xfs_mount_t *mp, - xfs_fsop_handlereq_t *hreq, - struct inode *parinode); + struct file *parfilp, + xfs_fsop_handlereq_t *hreq); extern int xfs_attrmulti_attr_get( @@ -67,6 +64,12 @@ xfs_attrmulti_attr_remove( char *name, __uint32_t flags); +extern struct dentry * +xfs_handle_to_dentry( + struct file *parfilp, + void __user *uhandle, + u32 hlen); + extern long xfs_file_ioctl( struct file *filp, diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c index 50903ad3182..c70c4e3db79 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl32.c +++ b/fs/xfs/linux-2.6/xfs_ioctl32.c @@ -17,6 +17,7 @@ */ #include <linux/compat.h> #include <linux/ioctl.h> +#include <linux/mount.h> #include <asm/uaccess.h> #include "xfs.h" #include "xfs_fs.h" @@ -340,96 +341,24 @@ xfs_compat_handlereq_copyin( return 0; } -/* - * Convert userspace handle data into inode. - * - * We use the fact that all the fsop_handlereq ioctl calls have a data - * structure argument whose first component is always a xfs_fsop_handlereq_t, - * so we can pass that sub structure into this handy, shared routine. - * - * If no error, caller must always iput the returned inode. - */ -STATIC int -xfs_vget_fsop_handlereq_compat( - xfs_mount_t *mp, - struct inode *parinode, /* parent inode pointer */ - compat_xfs_fsop_handlereq_t *hreq, - struct inode **inode) +STATIC struct dentry * +xfs_compat_handlereq_to_dentry( + struct file *parfilp, + compat_xfs_fsop_handlereq_t *hreq) { - void __user *hanp; - size_t hlen; - xfs_fid_t *xfid; - xfs_handle_t *handlep; - xfs_handle_t handle; - xfs_inode_t *ip; - xfs_ino_t ino; - __u32 igen; - int error; - - /* - * Only allow handle opens under a directory. - */ - if (!S_ISDIR(parinode->i_mode)) - return XFS_ERROR(ENOTDIR); - - hanp = compat_ptr(hreq->ihandle); - hlen = hreq->ihandlen; - handlep = &handle; - - if (hlen < sizeof(handlep->ha_fsid) || hlen > sizeof(*handlep)) - return XFS_ERROR(EINVAL); - if (copy_from_user(handlep, hanp, hlen)) - return XFS_ERROR(EFAULT); - if (hlen < sizeof(*handlep)) - memset(((char *)handlep) + hlen, 0, sizeof(*handlep) - hlen); - if (hlen > sizeof(handlep->ha_fsid)) { - if (handlep->ha_fid.fid_len != - (hlen - sizeof(handlep->ha_fsid) - - sizeof(handlep->ha_fid.fid_len)) || - handlep->ha_fid.fid_pad) - return XFS_ERROR(EINVAL); - } - - /* - * Crack the handle, obtain the inode # & generation # - */ - xfid = (struct xfs_fid *)&handlep->ha_fid; - if (xfid->fid_len == sizeof(*xfid) - sizeof(xfid->fid_len)) { - ino = xfid->fid_ino; - igen = xfid->fid_gen; - } else { - return XFS_ERROR(EINVAL); - } - - /* - * Get the XFS inode, building a Linux inode to go with it. - */ - error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_SHARED, &ip, 0); - if (error) - return error; - if (ip == NULL) - return XFS_ERROR(EIO); - if (ip->i_d.di_gen != igen) { - xfs_iput_new(ip, XFS_ILOCK_SHARED); - return XFS_ERROR(ENOENT); - } - - xfs_iunlock(ip, XFS_ILOCK_SHARED); - - *inode = VFS_I(ip); - return 0; + return xfs_handle_to_dentry(parfilp, + compat_ptr(hreq->ihandle), hreq->ihandlen); } STATIC int xfs_compat_attrlist_by_handle( - xfs_mount_t *mp, - void __user *arg, - struct inode *parinode) + struct file *parfilp, + void __user *arg) { int error; attrlist_cursor_kern_t *cursor; compat_xfs_fsop_attrlist_handlereq_t al_hreq; - struct inode *inode; + struct dentry *dentry; char *kbuf; if (!capable(CAP_SYS_ADMIN)) @@ -446,17 +375,17 @@ xfs_compat_attrlist_by_handle( if (al_hreq.flags & ~(ATTR_ROOT | ATTR_SECURE)) return -XFS_ERROR(EINVAL); - error = xfs_vget_fsop_handlereq_compat(mp, parinode, &al_hreq.hreq, - &inode); - if (error) - goto out; + dentry = xfs_compat_handlereq_to_dentry(parfilp, &al_hreq.hreq); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + error = -ENOMEM; kbuf = kmalloc(al_hreq.buflen, GFP_KERNEL); if (!kbuf) - goto out_vn_rele; + goto out_dput; cursor = (attrlist_cursor_kern_t *)&al_hreq.pos; - error = xfs_attr_list(XFS_I(inode), kbuf, al_hreq.buflen, + error = -xfs_attr_list(XFS_I(dentry->d_inode), kbuf, al_hreq.buflen, al_hreq.flags, cursor); if (error) goto out_kfree; @@ -466,22 +395,20 @@ xfs_compat_attrlist_by_handle( out_kfree: kfree(kbuf); - out_vn_rele: - iput(inode); - out: - return -error; + out_dput: + dput(dentry); + return error; } STATIC int xfs_compat_attrmulti_by_handle( - xfs_mount_t *mp, - void __user *arg, - struct inode *parinode) + struct file *parfilp, + void __user *arg) { int error; compat_xfs_attr_multiop_t *ops; compat_xfs_fsop_attrmulti_handlereq_t am_hreq; - struct inode *inode; + struct dentry *dentry; unsigned int i, size; char *attr_name; @@ -491,20 +418,19 @@ xfs_compat_attrmulti_by_handle( sizeof(compat_xfs_fsop_attrmulti_handlereq_t))) return -XFS_ERROR(EFAULT); - error = xfs_vget_fsop_handlereq_compat(mp, parinode, &am_hreq.hreq, - &inode); - if (error) - goto out; + dentry = xfs_compat_handlereq_to_dentry(parfilp, &am_hreq.hreq); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); error = E2BIG; size = am_hreq.opcount * sizeof(compat_xfs_attr_multiop_t); if (!size || size > 16 * PAGE_SIZE) - goto out_vn_rele; + goto out_dput; error = ENOMEM; ops = kmalloc(size, GFP_KERNEL); if (!ops) - goto out_vn_rele; + goto out_dput; error = EFAULT; if (copy_from_user(ops, compat_ptr(am_hreq.ops), size)) @@ -527,20 +453,29 @@ xfs_compat_attrmulti_by_handle( switch (ops[i].am_opcode) { case ATTR_OP_GET: - ops[i].am_error = xfs_attrmulti_attr_get(inode, - attr_name, + ops[i].am_error = xfs_attrmulti_attr_get( + dentry->d_inode, attr_name, compat_ptr(ops[i].am_attrvalue), &ops[i].am_length, ops[i].am_flags); break; case ATTR_OP_SET: - ops[i].am_error = xfs_attrmulti_attr_set(inode, - attr_name, + ops[i].am_error = mnt_want_write(parfilp->f_path.mnt); + if (ops[i].am_error) + break; + ops[i].am_error = xfs_attrmulti_attr_set( + dentry->d_inode, attr_name, compat_ptr(ops[i].am_attrvalue), ops[i].am_length, ops[i].am_flags); + mnt_drop_write(parfilp->f_path.mnt); break; case ATTR_OP_REMOVE: - ops[i].am_error = xfs_attrmulti_attr_remove(inode, - attr_name, ops[i].am_flags); + ops[i].am_error = mnt_want_write(parfilp->f_path.mnt); + if (ops[i].am_error) + break; + ops[i].am_error = xfs_attrmulti_attr_remove( + dentry->d_inode, attr_name, + ops[i].am_flags); + mnt_drop_write(parfilp->f_path.mnt); break; default: ops[i].am_error = EINVAL; @@ -553,22 +488,20 @@ xfs_compat_attrmulti_by_handle( kfree(attr_name); out_kfree_ops: kfree(ops); - out_vn_rele: - iput(inode); - out: + out_dput: + dput(dentry); return -error; } STATIC int xfs_compat_fssetdm_by_handle( - xfs_mount_t *mp, - void __user *arg, - struct inode *parinode) + struct file *parfilp, + void __user *arg) { int error; struct fsdmidata fsd; compat_xfs_fsop_setdm_handlereq_t dmhreq; - struct inode *inode; + struct dentry *dentry; if (!capable(CAP_MKNOD)) return -XFS_ERROR(EPERM); @@ -576,12 +509,11 @@ xfs_compat_fssetdm_by_handle( sizeof(compat_xfs_fsop_setdm_handlereq_t))) return -XFS_ERROR(EFAULT); - error = xfs_vget_fsop_handlereq_compat(mp, parinode, &dmhreq.hreq, - &inode); - if (error) - return -error; + dentry = xfs_compat_handlereq_to_dentry(parfilp, &dmhreq.hreq); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); - if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) { + if (IS_IMMUTABLE(dentry->d_inode) || IS_APPEND(dentry->d_inode)) { error = -XFS_ERROR(EPERM); goto out; } @@ -591,11 +523,11 @@ xfs_compat_fssetdm_by_handle( goto out; } - error = -xfs_set_dmattrs(XFS_I(inode), fsd.fsd_dmevmask, + error = -xfs_set_dmattrs(XFS_I(dentry->d_inode), fsd.fsd_dmevmask, fsd.fsd_dmstate); out: - iput(inode); + dput(dentry); return error; } @@ -722,21 +654,21 @@ xfs_file_compat_ioctl( if (xfs_compat_handlereq_copyin(&hreq, arg)) return -XFS_ERROR(EFAULT); - return xfs_open_by_handle(mp, &hreq, filp, inode); + return xfs_open_by_handle(filp, &hreq); } case XFS_IOC_READLINK_BY_HANDLE_32: { struct xfs_fsop_handlereq hreq; if (xfs_compat_handlereq_copyin(&hreq, arg)) return -XFS_ERROR(EFAULT); - return xfs_readlink_by_handle(mp, &hreq, inode); + return xfs_readlink_by_handle(filp, &hreq); } case XFS_IOC_ATTRLIST_BY_HANDLE_32: - return xfs_compat_attrlist_by_handle(mp, arg, inode); + return xfs_compat_attrlist_by_handle(filp, arg); case XFS_IOC_ATTRMULTI_BY_HANDLE_32: - return xfs_compat_attrmulti_by_handle(mp, arg, inode); + return xfs_compat_attrmulti_by_handle(filp, arg); case XFS_IOC_FSSETDM_BY_HANDLE_32: - return xfs_compat_fssetdm_by_handle(mp, arg, inode); + return xfs_compat_fssetdm_by_handle(filp, arg); default: return -XFS_ERROR(ENOIOCTLCMD); } diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 95a97108036..c71e226da7f 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -1197,6 +1197,7 @@ xfs_fs_remount( struct xfs_mount *mp = XFS_M(sb); substring_t args[MAX_OPT_ARGS]; char *p; + int error; while ((p = strsep(&options, ",")) != NULL) { int token; @@ -1247,11 +1248,25 @@ xfs_fs_remount( } } - /* rw/ro -> rw */ + /* ro -> rw */ if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & MS_RDONLY)) { mp->m_flags &= ~XFS_MOUNT_RDONLY; if (mp->m_flags & XFS_MOUNT_BARRIER) xfs_mountfs_check_barriers(mp); + + /* + * If this is the first remount to writeable state we + * might have some superblock changes to update. + */ + if (mp->m_update_flags) { + error = xfs_mount_log_sb(mp, mp->m_update_flags); + if (error) { + cmn_err(CE_WARN, + "XFS: failed to write sb changes"); + return error; + } + mp->m_update_flags = 0; + } } /* rw -> ro */ diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c index 591ca6602bf..6543c0b2975 100644 --- a/fs/xfs/quota/xfs_dquot.c +++ b/fs/xfs/quota/xfs_dquot.c @@ -73,6 +73,8 @@ int xfs_dqreq_num; int xfs_dqerror_mod = 33; #endif +static struct lock_class_key xfs_dquot_other_class; + /* * Allocate and initialize a dquot. We don't always allocate fresh memory; * we try to reclaim a free dquot if the number of incore dquots are above @@ -139,7 +141,15 @@ xfs_qm_dqinit( ASSERT(dqp->q_trace); xfs_dqtrace_entry(dqp, "DQRECLAIMED_INIT"); #endif - } + } + + /* + * In either case we need to make sure group quotas have a different + * lock class than user quotas, to make sure lockdep knows we can + * locks of one of each at the same time. + */ + if (!(type & XFS_DQ_USER)) + lockdep_set_class(&dqp->q_qlock, &xfs_dquot_other_class); /* * log item gets initialized later @@ -421,7 +431,7 @@ xfs_qm_dqalloc( /* * Initialize the bmap freelist prior to calling bmapi code. */ - XFS_BMAP_INIT(&flist, &firstblock); + xfs_bmap_init(&flist, &firstblock); xfs_ilock(quotip, XFS_ILOCK_EXCL); /* * Return if this type of quotas is turned off while we didn't @@ -1383,6 +1393,12 @@ xfs_dqunlock_nonotify( mutex_unlock(&(dqp->q_qlock)); } +/* + * Lock two xfs_dquot structures. + * + * To avoid deadlocks we always lock the quota structure with + * the lowerd id first. + */ void xfs_dqlock2( xfs_dquot_t *d1, @@ -1392,18 +1408,16 @@ xfs_dqlock2( ASSERT(d1 != d2); if (be32_to_cpu(d1->q_core.d_id) > be32_to_cpu(d2->q_core.d_id)) { - xfs_dqlock(d2); - xfs_dqlock(d1); + mutex_lock(&d2->q_qlock); + mutex_lock_nested(&d1->q_qlock, XFS_QLOCK_NESTED); } else { - xfs_dqlock(d1); - xfs_dqlock(d2); - } - } else { - if (d1) { - xfs_dqlock(d1); - } else if (d2) { - xfs_dqlock(d2); + mutex_lock(&d1->q_qlock); + mutex_lock_nested(&d2->q_qlock, XFS_QLOCK_NESTED); } + } else if (d1) { + mutex_lock(&d1->q_qlock); + } else if (d2) { + mutex_lock(&d2->q_qlock); } } diff --git a/fs/xfs/quota/xfs_dquot.h b/fs/xfs/quota/xfs_dquot.h index 7e455337e2b..d443e93b433 100644 --- a/fs/xfs/quota/xfs_dquot.h +++ b/fs/xfs/quota/xfs_dquot.h @@ -97,6 +97,16 @@ typedef struct xfs_dquot { #define dq_hashlist q_lists.dqm_hashlist #define dq_flags q_lists.dqm_flags +/* + * Lock hierachy for q_qlock: + * XFS_QLOCK_NORMAL is the implicit default, + * XFS_QLOCK_NESTED is the dquot with the higher id in xfs_dqlock2 + */ +enum { + XFS_QLOCK_NORMAL = 0, + XFS_QLOCK_NESTED, +}; + #define XFS_DQHOLD(dqp) ((dqp)->q_nrefs++) #ifdef DEBUG diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c index 6b13960cf31..7a2beb64314 100644 --- a/fs/xfs/quota/xfs_qm.c +++ b/fs/xfs/quota/xfs_qm.c @@ -1070,6 +1070,13 @@ xfs_qm_sync( return 0; } +/* + * The hash chains and the mplist use the same xfs_dqhash structure as + * their list head, but we can take the mplist qh_lock and one of the + * hash qh_locks at the same time without any problem as they aren't + * related. + */ +static struct lock_class_key xfs_quota_mplist_class; /* * This initializes all the quota information that's kept in the @@ -1105,6 +1112,8 @@ xfs_qm_init_quotainfo( } xfs_qm_list_init(&qinf->qi_dqlist, "mpdqlist", 0); + lockdep_set_class(&qinf->qi_dqlist.qh_lock, &xfs_quota_mplist_class); + qinf->qi_dqreclaims = 0; /* mutex used to serialize quotaoffs */ diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index a4e293b93ef..642f1db4def 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -22,7 +22,6 @@ * Access Control Lists */ typedef __uint16_t xfs_acl_perm_t; -typedef __int32_t xfs_acl_type_t; typedef __int32_t xfs_acl_tag_t; typedef __int32_t xfs_acl_id_t; diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h index f2e21817a22..143d63ecb20 100644 --- a/fs/xfs/xfs_ag.h +++ b/fs/xfs/xfs_ag.h @@ -231,7 +231,7 @@ typedef struct xfs_perag #define XFS_FSB_TO_AGNO(mp,fsbno) \ ((xfs_agnumber_t)((fsbno) >> (mp)->m_sb.sb_agblklog)) #define XFS_FSB_TO_AGBNO(mp,fsbno) \ - ((xfs_agblock_t)((fsbno) & XFS_MASK32LO((mp)->m_sb.sb_agblklog))) + ((xfs_agblock_t)((fsbno) & xfs_mask32lo((mp)->m_sb.sb_agblklog))) #define XFS_AGB_TO_DADDR(mp,agno,agbno) \ ((xfs_daddr_t)XFS_FSB_TO_BB(mp, \ (xfs_fsblock_t)(agno) * (mp)->m_sb.sb_agblocks + (agbno))) @@ -244,8 +244,8 @@ typedef struct xfs_perag #define XFS_AG_CHECK_DADDR(mp,d,len) \ ((len) == 1 ? \ ASSERT((d) == XFS_SB_DADDR || \ - XFS_DADDR_TO_AGBNO(mp, d) != XFS_SB_DADDR) : \ - ASSERT(XFS_DADDR_TO_AGNO(mp, d) == \ - XFS_DADDR_TO_AGNO(mp, (d) + (len) - 1))) + xfs_daddr_to_agbno(mp, d) != XFS_SB_DADDR) : \ + ASSERT(xfs_daddr_to_agno(mp, d) == \ + xfs_daddr_to_agno(mp, (d) + (len) - 1))) #endif /* __XFS_AG_H__ */ diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c index 733cb75a8c5..c10c3a292d3 100644 --- a/fs/xfs/xfs_alloc_btree.c +++ b/fs/xfs/xfs_alloc_btree.c @@ -115,7 +115,7 @@ xfs_allocbt_free_block( xfs_agblock_t bno; int error; - bno = XFS_DADDR_TO_AGBNO(cur->bc_mp, XFS_BUF_ADDR(bp)); + bno = xfs_daddr_to_agbno(cur->bc_mp, XFS_BUF_ADDR(bp)); error = xfs_alloc_put_freelist(cur->bc_tp, agbp, NULL, bno, 1); if (error) return error; diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c index f7cdc28aff4..5fde1654b43 100644 --- a/fs/xfs/xfs_attr.c +++ b/fs/xfs/xfs_attr.c @@ -374,7 +374,7 @@ xfs_attr_set_int(xfs_inode_t *dp, struct xfs_name *name, * It won't fit in the shortform, transform to a leaf block. * GROT: another possible req'mt for a double-split btree op. */ - XFS_BMAP_INIT(args.flist, args.firstblock); + xfs_bmap_init(args.flist, args.firstblock); error = xfs_attr_shortform_to_leaf(&args); if (!error) { error = xfs_bmap_finish(&args.trans, args.flist, @@ -956,7 +956,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) * Commit that transaction so that the node_addname() call * can manage its own transactions. */ - XFS_BMAP_INIT(args->flist, args->firstblock); + xfs_bmap_init(args->flist, args->firstblock); error = xfs_attr_leaf_to_node(args); if (!error) { error = xfs_bmap_finish(&args->trans, args->flist, @@ -1057,7 +1057,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) * If the result is small enough, shrink it all into the inode. */ if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) { - XFS_BMAP_INIT(args->flist, args->firstblock); + xfs_bmap_init(args->flist, args->firstblock); error = xfs_attr_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ if (!error) { @@ -1135,7 +1135,7 @@ xfs_attr_leaf_removename(xfs_da_args_t *args) * If the result is small enough, shrink it all into the inode. */ if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) { - XFS_BMAP_INIT(args->flist, args->firstblock); + xfs_bmap_init(args->flist, args->firstblock); error = xfs_attr_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ if (!error) { @@ -1290,7 +1290,7 @@ restart: * have been a b-tree. */ xfs_da_state_free(state); - XFS_BMAP_INIT(args->flist, args->firstblock); + xfs_bmap_init(args->flist, args->firstblock); error = xfs_attr_leaf_to_node(args); if (!error) { error = xfs_bmap_finish(&args->trans, @@ -1331,7 +1331,7 @@ restart: * in the index/blkno/rmtblkno/rmtblkcnt fields and * in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields. */ - XFS_BMAP_INIT(args->flist, args->firstblock); + xfs_bmap_init(args->flist, args->firstblock); error = xfs_da_split(state); if (!error) { error = xfs_bmap_finish(&args->trans, args->flist, @@ -1443,7 +1443,7 @@ restart: * Check to see if the tree needs to be collapsed. */ if (retval && (state->path.active > 1)) { - XFS_BMAP_INIT(args->flist, args->firstblock); + xfs_bmap_init(args->flist, args->firstblock); error = xfs_da_join(state); if (!error) { error = xfs_bmap_finish(&args->trans, @@ -1579,7 +1579,7 @@ xfs_attr_node_removename(xfs_da_args_t *args) * Check to see if the tree needs to be collapsed. */ if (retval && (state->path.active > 1)) { - XFS_BMAP_INIT(args->flist, args->firstblock); + xfs_bmap_init(args->flist, args->firstblock); error = xfs_da_join(state); if (!error) { error = xfs_bmap_finish(&args->trans, args->flist, @@ -1630,7 +1630,7 @@ xfs_attr_node_removename(xfs_da_args_t *args) == XFS_ATTR_LEAF_MAGIC); if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) { - XFS_BMAP_INIT(args->flist, args->firstblock); + xfs_bmap_init(args->flist, args->firstblock); error = xfs_attr_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ if (!error) { @@ -2069,7 +2069,7 @@ xfs_attr_rmtval_set(xfs_da_args_t *args) /* * Allocate a single extent, up to the size of the value. */ - XFS_BMAP_INIT(args->flist, args->firstblock); + xfs_bmap_init(args->flist, args->firstblock); nmap = 1; error = xfs_bmapi(args->trans, dp, (xfs_fileoff_t)lblkno, blkcnt, @@ -2123,7 +2123,7 @@ xfs_attr_rmtval_set(xfs_da_args_t *args) /* * Try to remember where we decided to put the value. */ - XFS_BMAP_INIT(args->flist, args->firstblock); + xfs_bmap_init(args->flist, args->firstblock); nmap = 1; error = xfs_bmapi(NULL, dp, (xfs_fileoff_t)lblkno, args->rmtblkcnt, @@ -2188,7 +2188,7 @@ xfs_attr_rmtval_remove(xfs_da_args_t *args) /* * Try to remember where we decided to put the value. */ - XFS_BMAP_INIT(args->flist, args->firstblock); + xfs_bmap_init(args->flist, args->firstblock); nmap = 1; error = xfs_bmapi(NULL, args->dp, (xfs_fileoff_t)lblkno, args->rmtblkcnt, @@ -2229,7 +2229,7 @@ xfs_attr_rmtval_remove(xfs_da_args_t *args) blkcnt = args->rmtblkcnt; done = 0; while (!done) { - XFS_BMAP_INIT(args->flist, args->firstblock); + xfs_bmap_init(args->flist, args->firstblock); error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt, XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA, 1, args->firstblock, args->flist, diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c index 79da6b2ea99..6c323f8a4cd 100644 --- a/fs/xfs/xfs_attr_leaf.c +++ b/fs/xfs/xfs_attr_leaf.c @@ -736,7 +736,7 @@ xfs_attr_shortform_allfit(xfs_dabuf_t *bp, xfs_inode_t *dp) continue; /* don't copy partial entries */ if (!(entry->flags & XFS_ATTR_LOCAL)) return(0); - name_loc = XFS_ATTR_LEAF_NAME_LOCAL(leaf, i); + name_loc = xfs_attr_leaf_name_local(leaf, i); if (name_loc->namelen >= XFS_ATTR_SF_ENTSIZE_MAX) return(0); if (be16_to_cpu(name_loc->valuelen) >= XFS_ATTR_SF_ENTSIZE_MAX) @@ -823,7 +823,7 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff) if (!entry->nameidx) continue; ASSERT(entry->flags & XFS_ATTR_LOCAL); - name_loc = XFS_ATTR_LEAF_NAME_LOCAL(leaf, i); + name_loc = xfs_attr_leaf_name_local(leaf, i); nargs.name = (char *)name_loc->nameval; nargs.namelen = name_loc->namelen; nargs.value = (char *)&name_loc->nameval[nargs.namelen]; @@ -1141,14 +1141,14 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex) * as part of this transaction (a split operation for example). */ if (entry->flags & XFS_ATTR_LOCAL) { - name_loc = XFS_ATTR_LEAF_NAME_LOCAL(leaf, args->index); + name_loc = xfs_attr_leaf_name_local(leaf, args->index); name_loc->namelen = args->namelen; name_loc->valuelen = cpu_to_be16(args->valuelen); memcpy((char *)name_loc->nameval, args->name, args->namelen); memcpy((char *)&name_loc->nameval[args->namelen], args->value, be16_to_cpu(name_loc->valuelen)); } else { - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf, args->index); + name_rmt = xfs_attr_leaf_name_remote(leaf, args->index); name_rmt->namelen = args->namelen; memcpy((char *)name_rmt->name, args->name, args->namelen); entry->flags |= XFS_ATTR_INCOMPLETE; @@ -1159,7 +1159,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex) args->rmtblkcnt = XFS_B_TO_FSB(mp, args->valuelen); } xfs_da_log_buf(args->trans, bp, - XFS_DA_LOGRANGE(leaf, XFS_ATTR_LEAF_NAME(leaf, args->index), + XFS_DA_LOGRANGE(leaf, xfs_attr_leaf_name(leaf, args->index), xfs_attr_leaf_entsize(leaf, args->index))); /* @@ -1749,10 +1749,10 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args) /* * Compress the remaining entries and zero out the removed stuff. */ - memset(XFS_ATTR_LEAF_NAME(leaf, args->index), 0, entsize); + memset(xfs_attr_leaf_name(leaf, args->index), 0, entsize); be16_add_cpu(&hdr->usedbytes, -entsize); xfs_da_log_buf(args->trans, bp, - XFS_DA_LOGRANGE(leaf, XFS_ATTR_LEAF_NAME(leaf, args->index), + XFS_DA_LOGRANGE(leaf, xfs_attr_leaf_name(leaf, args->index), entsize)); tmp = (be16_to_cpu(hdr->count) - args->index) @@ -1985,7 +1985,7 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args) continue; } if (entry->flags & XFS_ATTR_LOCAL) { - name_loc = XFS_ATTR_LEAF_NAME_LOCAL(leaf, probe); + name_loc = xfs_attr_leaf_name_local(leaf, probe); if (name_loc->namelen != args->namelen) continue; if (memcmp(args->name, (char *)name_loc->nameval, args->namelen) != 0) @@ -1995,7 +1995,7 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args) args->index = probe; return(XFS_ERROR(EEXIST)); } else { - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf, probe); + name_rmt = xfs_attr_leaf_name_remote(leaf, probe); if (name_rmt->namelen != args->namelen) continue; if (memcmp(args->name, (char *)name_rmt->name, @@ -2035,7 +2035,7 @@ xfs_attr_leaf_getvalue(xfs_dabuf_t *bp, xfs_da_args_t *args) entry = &leaf->entries[args->index]; if (entry->flags & XFS_ATTR_LOCAL) { - name_loc = XFS_ATTR_LEAF_NAME_LOCAL(leaf, args->index); + name_loc = xfs_attr_leaf_name_local(leaf, args->index); ASSERT(name_loc->namelen == args->namelen); ASSERT(memcmp(args->name, name_loc->nameval, args->namelen) == 0); valuelen = be16_to_cpu(name_loc->valuelen); @@ -2050,7 +2050,7 @@ xfs_attr_leaf_getvalue(xfs_dabuf_t *bp, xfs_da_args_t *args) args->valuelen = valuelen; memcpy(args->value, &name_loc->nameval[args->namelen], valuelen); } else { - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf, args->index); + name_rmt = xfs_attr_leaf_name_remote(leaf, args->index); ASSERT(name_rmt->namelen == args->namelen); ASSERT(memcmp(args->name, name_rmt->name, args->namelen) == 0); valuelen = be32_to_cpu(name_rmt->valuelen); @@ -2143,7 +2143,7 @@ xfs_attr_leaf_moveents(xfs_attr_leafblock_t *leaf_s, int start_s, * off for 6.2, should be revisited later. */ if (entry_s->flags & XFS_ATTR_INCOMPLETE) { /* skip partials? */ - memset(XFS_ATTR_LEAF_NAME(leaf_s, start_s + i), 0, tmp); + memset(xfs_attr_leaf_name(leaf_s, start_s + i), 0, tmp); be16_add_cpu(&hdr_s->usedbytes, -tmp); be16_add_cpu(&hdr_s->count, -1); entry_d--; /* to compensate for ++ in loop hdr */ @@ -2160,11 +2160,11 @@ xfs_attr_leaf_moveents(xfs_attr_leafblock_t *leaf_s, int start_s, entry_d->flags = entry_s->flags; ASSERT(be16_to_cpu(entry_d->nameidx) + tmp <= XFS_LBSIZE(mp)); - memmove(XFS_ATTR_LEAF_NAME(leaf_d, desti), - XFS_ATTR_LEAF_NAME(leaf_s, start_s + i), tmp); + memmove(xfs_attr_leaf_name(leaf_d, desti), + xfs_attr_leaf_name(leaf_s, start_s + i), tmp); ASSERT(be16_to_cpu(entry_s->nameidx) + tmp <= XFS_LBSIZE(mp)); - memset(XFS_ATTR_LEAF_NAME(leaf_s, start_s + i), 0, tmp); + memset(xfs_attr_leaf_name(leaf_s, start_s + i), 0, tmp); be16_add_cpu(&hdr_s->usedbytes, -tmp); be16_add_cpu(&hdr_d->usedbytes, tmp); be16_add_cpu(&hdr_s->count, -1); @@ -2276,12 +2276,12 @@ xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index) ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); if (leaf->entries[index].flags & XFS_ATTR_LOCAL) { - name_loc = XFS_ATTR_LEAF_NAME_LOCAL(leaf, index); - size = XFS_ATTR_LEAF_ENTSIZE_LOCAL(name_loc->namelen, + name_loc = xfs_attr_leaf_name_local(leaf, index); + size = xfs_attr_leaf_entsize_local(name_loc->namelen, be16_to_cpu(name_loc->valuelen)); } else { - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf, index); - size = XFS_ATTR_LEAF_ENTSIZE_REMOTE(name_rmt->namelen); + name_rmt = xfs_attr_leaf_name_remote(leaf, index); + size = xfs_attr_leaf_entsize_remote(name_rmt->namelen); } return(size); } @@ -2297,13 +2297,13 @@ xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize, int *local) { int size; - size = XFS_ATTR_LEAF_ENTSIZE_LOCAL(namelen, valuelen); - if (size < XFS_ATTR_LEAF_ENTSIZE_LOCAL_MAX(blocksize)) { + size = xfs_attr_leaf_entsize_local(namelen, valuelen); + if (size < xfs_attr_leaf_entsize_local_max(blocksize)) { if (local) { *local = 1; } } else { - size = XFS_ATTR_LEAF_ENTSIZE_REMOTE(namelen); + size = xfs_attr_leaf_entsize_remote(namelen); if (local) { *local = 0; } @@ -2372,7 +2372,7 @@ xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context) if (entry->flags & XFS_ATTR_LOCAL) { xfs_attr_leaf_name_local_t *name_loc = - XFS_ATTR_LEAF_NAME_LOCAL(leaf, i); + xfs_attr_leaf_name_local(leaf, i); retval = context->put_listent(context, entry->flags, @@ -2384,7 +2384,7 @@ xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context) return retval; } else { xfs_attr_leaf_name_remote_t *name_rmt = - XFS_ATTR_LEAF_NAME_REMOTE(leaf, i); + xfs_attr_leaf_name_remote(leaf, i); int valuelen = be32_to_cpu(name_rmt->valuelen); @@ -2468,11 +2468,11 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args) #ifdef DEBUG if (entry->flags & XFS_ATTR_LOCAL) { - name_loc = XFS_ATTR_LEAF_NAME_LOCAL(leaf, args->index); + name_loc = xfs_attr_leaf_name_local(leaf, args->index); namelen = name_loc->namelen; name = (char *)name_loc->nameval; } else { - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf, args->index); + name_rmt = xfs_attr_leaf_name_remote(leaf, args->index); namelen = name_rmt->namelen; name = (char *)name_rmt->name; } @@ -2487,7 +2487,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args) if (args->rmtblkno) { ASSERT((entry->flags & XFS_ATTR_LOCAL) == 0); - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf, args->index); + name_rmt = xfs_attr_leaf_name_remote(leaf, args->index); name_rmt->valueblk = cpu_to_be32(args->rmtblkno); name_rmt->valuelen = cpu_to_be32(args->valuelen); xfs_da_log_buf(args->trans, bp, @@ -2534,7 +2534,7 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args) xfs_da_log_buf(args->trans, bp, XFS_DA_LOGRANGE(leaf, entry, sizeof(*entry))); if ((entry->flags & XFS_ATTR_LOCAL) == 0) { - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf, args->index); + name_rmt = xfs_attr_leaf_name_remote(leaf, args->index); name_rmt->valueblk = 0; name_rmt->valuelen = 0; xfs_da_log_buf(args->trans, bp, @@ -2607,20 +2607,20 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args) #ifdef DEBUG if (entry1->flags & XFS_ATTR_LOCAL) { - name_loc = XFS_ATTR_LEAF_NAME_LOCAL(leaf1, args->index); + name_loc = xfs_attr_leaf_name_local(leaf1, args->index); namelen1 = name_loc->namelen; name1 = (char *)name_loc->nameval; } else { - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf1, args->index); + name_rmt = xfs_attr_leaf_name_remote(leaf1, args->index); namelen1 = name_rmt->namelen; name1 = (char *)name_rmt->name; } if (entry2->flags & XFS_ATTR_LOCAL) { - name_loc = XFS_ATTR_LEAF_NAME_LOCAL(leaf2, args->index2); + name_loc = xfs_attr_leaf_name_local(leaf2, args->index2); namelen2 = name_loc->namelen; name2 = (char *)name_loc->nameval; } else { - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf2, args->index2); + name_rmt = xfs_attr_leaf_name_remote(leaf2, args->index2); namelen2 = name_rmt->namelen; name2 = (char *)name_rmt->name; } @@ -2637,7 +2637,7 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args) XFS_DA_LOGRANGE(leaf1, entry1, sizeof(*entry1))); if (args->rmtblkno) { ASSERT((entry1->flags & XFS_ATTR_LOCAL) == 0); - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf1, args->index); + name_rmt = xfs_attr_leaf_name_remote(leaf1, args->index); name_rmt->valueblk = cpu_to_be32(args->rmtblkno); name_rmt->valuelen = cpu_to_be32(args->valuelen); xfs_da_log_buf(args->trans, bp1, @@ -2648,7 +2648,7 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args) xfs_da_log_buf(args->trans, bp2, XFS_DA_LOGRANGE(leaf2, entry2, sizeof(*entry2))); if ((entry2->flags & XFS_ATTR_LOCAL) == 0) { - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf2, args->index2); + name_rmt = xfs_attr_leaf_name_remote(leaf2, args->index2); name_rmt->valueblk = 0; name_rmt->valuelen = 0; xfs_da_log_buf(args->trans, bp2, @@ -2855,7 +2855,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp) for (i = 0; i < be16_to_cpu(leaf->hdr.count); entry++, i++) { if (be16_to_cpu(entry->nameidx) && ((entry->flags & XFS_ATTR_LOCAL) == 0)) { - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf, i); + name_rmt = xfs_attr_leaf_name_remote(leaf, i); if (name_rmt->valueblk) count++; } @@ -2883,7 +2883,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp) for (i = 0; i < be16_to_cpu(leaf->hdr.count); entry++, i++) { if (be16_to_cpu(entry->nameidx) && ((entry->flags & XFS_ATTR_LOCAL) == 0)) { - name_rmt = XFS_ATTR_LEAF_NAME_REMOTE(leaf, i); + name_rmt = xfs_attr_leaf_name_remote(leaf, i); if (name_rmt->valueblk) { lp->valueblk = be32_to_cpu(name_rmt->valueblk); lp->valuelen = XFS_B_TO_FSB(dp->i_mount, diff --git a/fs/xfs/xfs_attr_leaf.h b/fs/xfs/xfs_attr_leaf.h index 83e9af417ca..9c7d22fdcf4 100644 --- a/fs/xfs/xfs_attr_leaf.h +++ b/fs/xfs/xfs_attr_leaf.h @@ -151,8 +151,6 @@ typedef struct xfs_attr_leafblock { /* * Cast typed pointers for "local" and "remote" name/value structs. */ -#define XFS_ATTR_LEAF_NAME_REMOTE(leafp,idx) \ - xfs_attr_leaf_name_remote(leafp,idx) static inline xfs_attr_leaf_name_remote_t * xfs_attr_leaf_name_remote(xfs_attr_leafblock_t *leafp, int idx) { @@ -160,8 +158,6 @@ xfs_attr_leaf_name_remote(xfs_attr_leafblock_t *leafp, int idx) &((char *)leafp)[be16_to_cpu(leafp->entries[idx].nameidx)]; } -#define XFS_ATTR_LEAF_NAME_LOCAL(leafp,idx) \ - xfs_attr_leaf_name_local(leafp,idx) static inline xfs_attr_leaf_name_local_t * xfs_attr_leaf_name_local(xfs_attr_leafblock_t *leafp, int idx) { @@ -169,8 +165,6 @@ xfs_attr_leaf_name_local(xfs_attr_leafblock_t *leafp, int idx) &((char *)leafp)[be16_to_cpu(leafp->entries[idx].nameidx)]; } -#define XFS_ATTR_LEAF_NAME(leafp,idx) \ - xfs_attr_leaf_name(leafp,idx) static inline char *xfs_attr_leaf_name(xfs_attr_leafblock_t *leafp, int idx) { return &((char *)leafp)[be16_to_cpu(leafp->entries[idx].nameidx)]; @@ -181,24 +175,18 @@ static inline char *xfs_attr_leaf_name(xfs_attr_leafblock_t *leafp, int idx) * a "local" name/value structure, a "remote" name/value structure, and * a pointer which might be either. */ -#define XFS_ATTR_LEAF_ENTSIZE_REMOTE(nlen) \ - xfs_attr_leaf_entsize_remote(nlen) static inline int xfs_attr_leaf_entsize_remote(int nlen) { return ((uint)sizeof(xfs_attr_leaf_name_remote_t) - 1 + (nlen) + \ XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1); } -#define XFS_ATTR_LEAF_ENTSIZE_LOCAL(nlen,vlen) \ - xfs_attr_leaf_entsize_local(nlen,vlen) static inline int xfs_attr_leaf_entsize_local(int nlen, int vlen) { return ((uint)sizeof(xfs_attr_leaf_name_local_t) - 1 + (nlen) + (vlen) + XFS_ATTR_LEAF_NAME_ALIGN - 1) & ~(XFS_ATTR_LEAF_NAME_ALIGN - 1); } -#define XFS_ATTR_LEAF_ENTSIZE_LOCAL_MAX(bsize) \ - xfs_attr_leaf_entsize_local_max(bsize) static inline int xfs_attr_leaf_entsize_local_max(int bsize) { return (((bsize) >> 1) + ((bsize) >> 2)); diff --git a/fs/xfs/xfs_bit.h b/fs/xfs/xfs_bit.h index bca7b243c31..f1e3c907044 100644 --- a/fs/xfs/xfs_bit.h +++ b/fs/xfs/xfs_bit.h @@ -23,24 +23,16 @@ */ /* - * masks with n high/low bits set, 32-bit values & 64-bit values + * masks with n high/low bits set, 64-bit values */ -#define XFS_MASK32HI(n) xfs_mask32hi(n) -static inline __uint32_t xfs_mask32hi(int n) -{ - return (__uint32_t)-1 << (32 - (n)); -} -#define XFS_MASK64HI(n) xfs_mask64hi(n) static inline __uint64_t xfs_mask64hi(int n) { return (__uint64_t)-1 << (64 - (n)); } -#define XFS_MASK32LO(n) xfs_mask32lo(n) static inline __uint32_t xfs_mask32lo(int n) { return ((__uint32_t)1 << (n)) - 1; } -#define XFS_MASK64LO(n) xfs_mask64lo(n) static inline __uint64_t xfs_mask64lo(int n) { return ((__uint64_t)1 << (n)) - 1; diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 138308e70d1..c852cd65aae 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -595,9 +595,9 @@ xfs_bmap_add_extent( xfs_iext_insert(ifp, 0, 1, new); ASSERT(cur == NULL); ifp->if_lastex = 0; - if (!ISNULLSTARTBLOCK(new->br_startblock)) { + if (!isnullstartblock(new->br_startblock)) { XFS_IFORK_NEXT_SET(ip, whichfork, 1); - logflags = XFS_ILOG_CORE | XFS_ILOG_FEXT(whichfork); + logflags = XFS_ILOG_CORE | xfs_ilog_fext(whichfork); } else logflags = 0; /* DELTA: single new extent */ @@ -613,7 +613,7 @@ xfs_bmap_add_extent( /* * Any kind of new delayed allocation goes here. */ - else if (ISNULLSTARTBLOCK(new->br_startblock)) { + else if (isnullstartblock(new->br_startblock)) { if (cur) ASSERT((cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL) == 0); @@ -644,11 +644,11 @@ xfs_bmap_add_extent( * in a delayed or unwritten allocation with a real one, or * converting real back to unwritten. */ - if (!ISNULLSTARTBLOCK(new->br_startblock) && + if (!isnullstartblock(new->br_startblock) && new->br_startoff + new->br_blockcount > prev.br_startoff) { if (prev.br_state != XFS_EXT_UNWRITTEN && - ISNULLSTARTBLOCK(prev.br_startblock)) { - da_old = STARTBLOCKVAL(prev.br_startblock); + isnullstartblock(prev.br_startblock)) { + da_old = startblockval(prev.br_startblock); if (cur) ASSERT(cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL); @@ -803,7 +803,7 @@ xfs_bmap_add_extent_delay_real( */ if (STATE_SET_TEST(LEFT_VALID, idx > 0)) { xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx - 1), &LEFT); - STATE_SET(LEFT_DELAY, ISNULLSTARTBLOCK(LEFT.br_startblock)); + STATE_SET(LEFT_DELAY, isnullstartblock(LEFT.br_startblock)); } STATE_SET(LEFT_CONTIG, STATE_TEST(LEFT_VALID) && !STATE_TEST(LEFT_DELAY) && @@ -820,7 +820,7 @@ xfs_bmap_add_extent_delay_real( idx < ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1)) { xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx + 1), &RIGHT); - STATE_SET(RIGHT_DELAY, ISNULLSTARTBLOCK(RIGHT.br_startblock)); + STATE_SET(RIGHT_DELAY, isnullstartblock(RIGHT.br_startblock)); } STATE_SET(RIGHT_CONTIG, STATE_TEST(RIGHT_VALID) && !STATE_TEST(RIGHT_DELAY) && @@ -1019,8 +1019,8 @@ xfs_bmap_add_extent_delay_real( goto done; } temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - STARTBLOCKVAL(PREV.br_startblock)); - xfs_bmbt_set_startblock(ep, NULLSTARTBLOCK((int)temp)); + startblockval(PREV.br_startblock)); + xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); XFS_BMAP_TRACE_POST_UPDATE("LF|LC", ip, idx, XFS_DATA_FORK); *dnew = temp; /* DELTA: The boundary between two in-core extents moved. */ @@ -1067,10 +1067,10 @@ xfs_bmap_add_extent_delay_real( goto done; } temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - STARTBLOCKVAL(PREV.br_startblock) - + startblockval(PREV.br_startblock) - (cur ? cur->bc_private.b.allocated : 0)); ep = xfs_iext_get_ext(ifp, idx + 1); - xfs_bmbt_set_startblock(ep, NULLSTARTBLOCK((int)temp)); + xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); XFS_BMAP_TRACE_POST_UPDATE("LF", ip, idx + 1, XFS_DATA_FORK); *dnew = temp; /* DELTA: One in-core extent is split in two. */ @@ -1110,8 +1110,8 @@ xfs_bmap_add_extent_delay_real( goto done; } temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - STARTBLOCKVAL(PREV.br_startblock)); - xfs_bmbt_set_startblock(ep, NULLSTARTBLOCK((int)temp)); + startblockval(PREV.br_startblock)); + xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); XFS_BMAP_TRACE_POST_UPDATE("RF|RC", ip, idx, XFS_DATA_FORK); *dnew = temp; /* DELTA: The boundary between two in-core extents moved. */ @@ -1157,10 +1157,10 @@ xfs_bmap_add_extent_delay_real( goto done; } temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - STARTBLOCKVAL(PREV.br_startblock) - + startblockval(PREV.br_startblock) - (cur ? cur->bc_private.b.allocated : 0)); ep = xfs_iext_get_ext(ifp, idx); - xfs_bmbt_set_startblock(ep, NULLSTARTBLOCK((int)temp)); + xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); XFS_BMAP_TRACE_POST_UPDATE("RF", ip, idx, XFS_DATA_FORK); *dnew = temp; /* DELTA: One in-core extent is split in two. */ @@ -1213,7 +1213,7 @@ xfs_bmap_add_extent_delay_real( } temp = xfs_bmap_worst_indlen(ip, temp); temp2 = xfs_bmap_worst_indlen(ip, temp2); - diff = (int)(temp + temp2 - STARTBLOCKVAL(PREV.br_startblock) - + diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) - (cur ? cur->bc_private.b.allocated : 0)); if (diff > 0 && xfs_mod_incore_sb(ip->i_mount, XFS_SBS_FDBLOCKS, -((int64_t)diff), rsvd)) { @@ -1241,11 +1241,11 @@ xfs_bmap_add_extent_delay_real( } } ep = xfs_iext_get_ext(ifp, idx); - xfs_bmbt_set_startblock(ep, NULLSTARTBLOCK((int)temp)); + xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); XFS_BMAP_TRACE_POST_UPDATE("0", ip, idx, XFS_DATA_FORK); XFS_BMAP_TRACE_PRE_UPDATE("0", ip, idx + 2, XFS_DATA_FORK); xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, idx + 2), - NULLSTARTBLOCK((int)temp2)); + nullstartblock((int)temp2)); XFS_BMAP_TRACE_POST_UPDATE("0", ip, idx + 2, XFS_DATA_FORK); *dnew = temp + temp2; /* DELTA: One in-core extent is split in three. */ @@ -1365,7 +1365,7 @@ xfs_bmap_add_extent_unwritten_real( */ if (STATE_SET_TEST(LEFT_VALID, idx > 0)) { xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx - 1), &LEFT); - STATE_SET(LEFT_DELAY, ISNULLSTARTBLOCK(LEFT.br_startblock)); + STATE_SET(LEFT_DELAY, isnullstartblock(LEFT.br_startblock)); } STATE_SET(LEFT_CONTIG, STATE_TEST(LEFT_VALID) && !STATE_TEST(LEFT_DELAY) && @@ -1382,7 +1382,7 @@ xfs_bmap_add_extent_unwritten_real( idx < ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1)) { xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx + 1), &RIGHT); - STATE_SET(RIGHT_DELAY, ISNULLSTARTBLOCK(RIGHT.br_startblock)); + STATE_SET(RIGHT_DELAY, isnullstartblock(RIGHT.br_startblock)); } STATE_SET(RIGHT_CONTIG, STATE_TEST(RIGHT_VALID) && !STATE_TEST(RIGHT_DELAY) && @@ -1889,13 +1889,13 @@ xfs_bmap_add_extent_hole_delay( ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); ep = xfs_iext_get_ext(ifp, idx); state = 0; - ASSERT(ISNULLSTARTBLOCK(new->br_startblock)); + ASSERT(isnullstartblock(new->br_startblock)); /* * Check and set flags if this segment has a left neighbor */ if (STATE_SET_TEST(LEFT_VALID, idx > 0)) { xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx - 1), &left); - STATE_SET(LEFT_DELAY, ISNULLSTARTBLOCK(left.br_startblock)); + STATE_SET(LEFT_DELAY, isnullstartblock(left.br_startblock)); } /* * Check and set flags if the current (right) segment exists. @@ -1905,7 +1905,7 @@ xfs_bmap_add_extent_hole_delay( idx < ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t))) { xfs_bmbt_get_all(ep, &right); - STATE_SET(RIGHT_DELAY, ISNULLSTARTBLOCK(right.br_startblock)); + STATE_SET(RIGHT_DELAY, isnullstartblock(right.br_startblock)); } /* * Set contiguity flags on the left and right neighbors. @@ -1938,12 +1938,12 @@ xfs_bmap_add_extent_hole_delay( XFS_BMAP_TRACE_PRE_UPDATE("LC|RC", ip, idx - 1, XFS_DATA_FORK); xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, idx - 1), temp); - oldlen = STARTBLOCKVAL(left.br_startblock) + - STARTBLOCKVAL(new->br_startblock) + - STARTBLOCKVAL(right.br_startblock); + oldlen = startblockval(left.br_startblock) + + startblockval(new->br_startblock) + + startblockval(right.br_startblock); newlen = xfs_bmap_worst_indlen(ip, temp); xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, idx - 1), - NULLSTARTBLOCK((int)newlen)); + nullstartblock((int)newlen)); XFS_BMAP_TRACE_POST_UPDATE("LC|RC", ip, idx - 1, XFS_DATA_FORK); XFS_BMAP_TRACE_DELETE("LC|RC", ip, idx, 1, XFS_DATA_FORK); @@ -1964,11 +1964,11 @@ xfs_bmap_add_extent_hole_delay( XFS_BMAP_TRACE_PRE_UPDATE("LC", ip, idx - 1, XFS_DATA_FORK); xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, idx - 1), temp); - oldlen = STARTBLOCKVAL(left.br_startblock) + - STARTBLOCKVAL(new->br_startblock); + oldlen = startblockval(left.br_startblock) + + startblockval(new->br_startblock); newlen = xfs_bmap_worst_indlen(ip, temp); xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, idx - 1), - NULLSTARTBLOCK((int)newlen)); + nullstartblock((int)newlen)); XFS_BMAP_TRACE_POST_UPDATE("LC", ip, idx - 1, XFS_DATA_FORK); ip->i_df.if_lastex = idx - 1; @@ -1985,11 +1985,11 @@ xfs_bmap_add_extent_hole_delay( */ XFS_BMAP_TRACE_PRE_UPDATE("RC", ip, idx, XFS_DATA_FORK); temp = new->br_blockcount + right.br_blockcount; - oldlen = STARTBLOCKVAL(new->br_startblock) + - STARTBLOCKVAL(right.br_startblock); + oldlen = startblockval(new->br_startblock) + + startblockval(right.br_startblock); newlen = xfs_bmap_worst_indlen(ip, temp); xfs_bmbt_set_allf(ep, new->br_startoff, - NULLSTARTBLOCK((int)newlen), temp, right.br_state); + nullstartblock((int)newlen), temp, right.br_state); XFS_BMAP_TRACE_POST_UPDATE("RC", ip, idx, XFS_DATA_FORK); ip->i_df.if_lastex = idx; /* DELTA: One in-core extent grew into a hole. */ @@ -2085,7 +2085,7 @@ xfs_bmap_add_extent_hole_real( */ if (STATE_SET_TEST(LEFT_VALID, idx > 0)) { xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx - 1), &left); - STATE_SET(LEFT_DELAY, ISNULLSTARTBLOCK(left.br_startblock)); + STATE_SET(LEFT_DELAY, isnullstartblock(left.br_startblock)); } /* * Check and set flags if this segment has a current value. @@ -2095,7 +2095,7 @@ xfs_bmap_add_extent_hole_real( idx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))) { xfs_bmbt_get_all(ep, &right); - STATE_SET(RIGHT_DELAY, ISNULLSTARTBLOCK(right.br_startblock)); + STATE_SET(RIGHT_DELAY, isnullstartblock(right.br_startblock)); } /* * We're inserting a real allocation between "left" and "right". @@ -2143,7 +2143,7 @@ xfs_bmap_add_extent_hole_real( XFS_IFORK_NEXT_SET(ip, whichfork, XFS_IFORK_NEXTENTS(ip, whichfork) - 1); if (cur == NULL) { - rval = XFS_ILOG_CORE | XFS_ILOG_FEXT(whichfork); + rval = XFS_ILOG_CORE | xfs_ilog_fext(whichfork); } else { rval = XFS_ILOG_CORE; if ((error = xfs_bmbt_lookup_eq(cur, @@ -2185,7 +2185,7 @@ xfs_bmap_add_extent_hole_real( XFS_BMAP_TRACE_POST_UPDATE("LC", ip, idx - 1, whichfork); ifp->if_lastex = idx - 1; if (cur == NULL) { - rval = XFS_ILOG_FEXT(whichfork); + rval = xfs_ilog_fext(whichfork); } else { rval = 0; if ((error = xfs_bmbt_lookup_eq(cur, @@ -2220,7 +2220,7 @@ xfs_bmap_add_extent_hole_real( XFS_BMAP_TRACE_POST_UPDATE("RC", ip, idx, whichfork); ifp->if_lastex = idx; if (cur == NULL) { - rval = XFS_ILOG_FEXT(whichfork); + rval = xfs_ilog_fext(whichfork); } else { rval = 0; if ((error = xfs_bmbt_lookup_eq(cur, @@ -2254,7 +2254,7 @@ xfs_bmap_add_extent_hole_real( XFS_IFORK_NEXT_SET(ip, whichfork, XFS_IFORK_NEXTENTS(ip, whichfork) + 1); if (cur == NULL) { - rval = XFS_ILOG_CORE | XFS_ILOG_FEXT(whichfork); + rval = XFS_ILOG_CORE | xfs_ilog_fext(whichfork); } else { rval = XFS_ILOG_CORE; if ((error = xfs_bmbt_lookup_eq(cur, @@ -2482,7 +2482,7 @@ xfs_bmap_adjacent( * try to use it's last block as our starting point. */ if (ap->eof && ap->prevp->br_startoff != NULLFILEOFF && - !ISNULLSTARTBLOCK(ap->prevp->br_startblock) && + !isnullstartblock(ap->prevp->br_startblock) && ISVALID(ap->prevp->br_startblock + ap->prevp->br_blockcount, ap->prevp->br_startblock)) { ap->rval = ap->prevp->br_startblock + ap->prevp->br_blockcount; @@ -2511,7 +2511,7 @@ xfs_bmap_adjacent( * start block based on it. */ if (ap->prevp->br_startoff != NULLFILEOFF && - !ISNULLSTARTBLOCK(ap->prevp->br_startblock) && + !isnullstartblock(ap->prevp->br_startblock) && (prevbno = ap->prevp->br_startblock + ap->prevp->br_blockcount) && ISVALID(prevbno, ap->prevp->br_startblock)) { @@ -2552,7 +2552,7 @@ xfs_bmap_adjacent( * If there's a following (right) block, select a requested * start block based on it. */ - if (!ISNULLSTARTBLOCK(ap->gotp->br_startblock)) { + if (!isnullstartblock(ap->gotp->br_startblock)) { /* * Calculate gap to start of next block. */ @@ -3082,7 +3082,7 @@ xfs_bmap_btree_to_extents( ASSERT(ifp->if_broot == NULL); ASSERT((ifp->if_flags & XFS_IFBROOT) == 0); XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS); - *logflagsp = XFS_ILOG_CORE | XFS_ILOG_FEXT(whichfork); + *logflagsp = XFS_ILOG_CORE | xfs_ilog_fext(whichfork); return 0; } @@ -3136,8 +3136,8 @@ xfs_bmap_del_extent( del_endoff = del->br_startoff + del->br_blockcount; got_endoff = got.br_startoff + got.br_blockcount; ASSERT(got_endoff >= del_endoff); - delay = ISNULLSTARTBLOCK(got.br_startblock); - ASSERT(ISNULLSTARTBLOCK(del->br_startblock) == delay); + delay = isnullstartblock(got.br_startblock); + ASSERT(isnullstartblock(del->br_startblock) == delay); flags = 0; qfield = 0; error = 0; @@ -3189,7 +3189,7 @@ xfs_bmap_del_extent( } da_old = da_new = 0; } else { - da_old = STARTBLOCKVAL(got.br_startblock); + da_old = startblockval(got.br_startblock); da_new = 0; nblks = 0; do_fx = 0; @@ -3213,7 +3213,7 @@ xfs_bmap_del_extent( XFS_IFORK_NEXTENTS(ip, whichfork) - 1); flags |= XFS_ILOG_CORE; if (!cur) { - flags |= XFS_ILOG_FEXT(whichfork); + flags |= xfs_ilog_fext(whichfork); break; } if ((error = xfs_btree_delete(cur, &i))) @@ -3233,7 +3233,7 @@ xfs_bmap_del_extent( if (delay) { temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), da_old); - xfs_bmbt_set_startblock(ep, NULLSTARTBLOCK((int)temp)); + xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); XFS_BMAP_TRACE_POST_UPDATE("2", ip, idx, whichfork); da_new = temp; @@ -3242,7 +3242,7 @@ xfs_bmap_del_extent( xfs_bmbt_set_startblock(ep, del_endblock); XFS_BMAP_TRACE_POST_UPDATE("2", ip, idx, whichfork); if (!cur) { - flags |= XFS_ILOG_FEXT(whichfork); + flags |= xfs_ilog_fext(whichfork); break; } if ((error = xfs_bmbt_update(cur, del_endoff, del_endblock, @@ -3262,7 +3262,7 @@ xfs_bmap_del_extent( if (delay) { temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), da_old); - xfs_bmbt_set_startblock(ep, NULLSTARTBLOCK((int)temp)); + xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); XFS_BMAP_TRACE_POST_UPDATE("1", ip, idx, whichfork); da_new = temp; @@ -3270,7 +3270,7 @@ xfs_bmap_del_extent( } XFS_BMAP_TRACE_POST_UPDATE("1", ip, idx, whichfork); if (!cur) { - flags |= XFS_ILOG_FEXT(whichfork); + flags |= xfs_ilog_fext(whichfork); break; } if ((error = xfs_bmbt_update(cur, got.br_startoff, @@ -3345,22 +3345,22 @@ xfs_bmap_del_extent( } XFS_WANT_CORRUPTED_GOTO(i == 1, done); } else - flags |= XFS_ILOG_FEXT(whichfork); + flags |= xfs_ilog_fext(whichfork); XFS_IFORK_NEXT_SET(ip, whichfork, XFS_IFORK_NEXTENTS(ip, whichfork) + 1); } else { ASSERT(whichfork == XFS_DATA_FORK); temp = xfs_bmap_worst_indlen(ip, temp); - xfs_bmbt_set_startblock(ep, NULLSTARTBLOCK((int)temp)); + xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); temp2 = xfs_bmap_worst_indlen(ip, temp2); - new.br_startblock = NULLSTARTBLOCK((int)temp2); + new.br_startblock = nullstartblock((int)temp2); da_new = temp + temp2; while (da_new > da_old) { if (temp) { temp--; da_new--; xfs_bmbt_set_startblock(ep, - NULLSTARTBLOCK((int)temp)); + nullstartblock((int)temp)); } if (da_new == da_old) break; @@ -3368,7 +3368,7 @@ xfs_bmap_del_extent( temp2--; da_new--; new.br_startblock = - NULLSTARTBLOCK((int)temp2); + nullstartblock((int)temp2); } } } @@ -3545,7 +3545,7 @@ xfs_bmap_extents_to_btree( nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t); for (cnt = i = 0; i < nextents; i++) { ep = xfs_iext_get_ext(ifp, i); - if (!ISNULLSTARTBLOCK(xfs_bmbt_get_startblock(ep))) { + if (!isnullstartblock(xfs_bmbt_get_startblock(ep))) { arp->l0 = cpu_to_be64(ep->l0); arp->l1 = cpu_to_be64(ep->l1); arp++; cnt++; @@ -3572,7 +3572,7 @@ xfs_bmap_extents_to_btree( xfs_btree_log_recs(cur, abp, 1, be16_to_cpu(ablock->bb_numrecs)); ASSERT(*curp == NULL); *curp = cur; - *logflagsp = XFS_ILOG_CORE | XFS_ILOG_FBROOT(whichfork); + *logflagsp = XFS_ILOG_CORE | xfs_ilog_fbroot(whichfork); return 0; } @@ -3676,7 +3676,7 @@ xfs_bmap_local_to_extents( ip->i_d.di_nblocks = 1; XFS_TRANS_MOD_DQUOT_BYINO(args.mp, tp, ip, XFS_TRANS_DQ_BCOUNT, 1L); - flags |= XFS_ILOG_FEXT(whichfork); + flags |= xfs_ilog_fext(whichfork); } else { ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) == 0); xfs_bmap_forkoff_reset(ip->i_mount, ip, whichfork); @@ -4082,7 +4082,7 @@ xfs_bmap_add_attrfork( XFS_IFORK_ASIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t); ip->i_afp->if_flags = XFS_IFEXTENTS; logflags = 0; - XFS_BMAP_INIT(&flist, &firstblock); + xfs_bmap_init(&flist, &firstblock); switch (ip->i_d.di_format) { case XFS_DINODE_FMT_LOCAL: error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock, &flist, @@ -4162,7 +4162,7 @@ xfs_bmap_add_free( ASSERT(bno != NULLFSBLOCK); ASSERT(len > 0); ASSERT(len <= MAXEXTLEN); - ASSERT(!ISNULLSTARTBLOCK(bno)); + ASSERT(!isnullstartblock(bno)); agno = XFS_FSB_TO_AGNO(mp, bno); agbno = XFS_FSB_TO_AGBNO(mp, bno); ASSERT(agno < mp->m_sb.sb_agcount); @@ -4909,7 +4909,7 @@ xfs_bmapi( got.br_startoff = end; inhole = eof || got.br_startoff > bno; wasdelay = wr && !inhole && !(flags & XFS_BMAPI_DELAY) && - ISNULLSTARTBLOCK(got.br_startblock); + isnullstartblock(got.br_startblock); /* * First, deal with the hole before the allocated space * that we found, if any. @@ -5028,7 +5028,7 @@ xfs_bmapi( } ip->i_delayed_blks += alen; - abno = NULLSTARTBLOCK(indlen); + abno = nullstartblock(indlen); } else { /* * If first time, allocate and fill in @@ -5144,8 +5144,8 @@ xfs_bmapi( aoff + alen); #ifdef DEBUG if (flags & XFS_BMAPI_DELAY) { - ASSERT(ISNULLSTARTBLOCK(got.br_startblock)); - ASSERT(STARTBLOCKVAL(got.br_startblock) > 0); + ASSERT(isnullstartblock(got.br_startblock)); + ASSERT(startblockval(got.br_startblock) > 0); } ASSERT(got.br_state == XFS_EXT_NORM || got.br_state == XFS_EXT_UNWRITTEN); @@ -5179,7 +5179,7 @@ xfs_bmapi( ASSERT((bno >= obno) || (n == 0)); ASSERT(bno < end); mval->br_startoff = bno; - if (ISNULLSTARTBLOCK(got.br_startblock)) { + if (isnullstartblock(got.br_startblock)) { ASSERT(!wr || (flags & XFS_BMAPI_DELAY)); mval->br_startblock = DELAYSTARTBLOCK; } else @@ -5201,7 +5201,7 @@ xfs_bmapi( ASSERT(mval->br_blockcount <= len); } else { *mval = got; - if (ISNULLSTARTBLOCK(mval->br_startblock)) { + if (isnullstartblock(mval->br_startblock)) { ASSERT(!wr || (flags & XFS_BMAPI_DELAY)); mval->br_startblock = DELAYSTARTBLOCK; } @@ -5329,12 +5329,12 @@ error0: * Log everything. Do this after conversion, there's no point in * logging the extent records if we've converted to btree format. */ - if ((logflags & XFS_ILOG_FEXT(whichfork)) && + if ((logflags & xfs_ilog_fext(whichfork)) && XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS) - logflags &= ~XFS_ILOG_FEXT(whichfork); - else if ((logflags & XFS_ILOG_FBROOT(whichfork)) && + logflags &= ~xfs_ilog_fext(whichfork); + else if ((logflags & xfs_ilog_fbroot(whichfork)) && XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE) - logflags &= ~XFS_ILOG_FBROOT(whichfork); + logflags &= ~xfs_ilog_fbroot(whichfork); /* * Log whatever the flags say, even if error. Otherwise we might miss * detecting a case where the data is changed, there's an error, @@ -5411,7 +5411,7 @@ xfs_bmapi_single( *fsb = NULLFSBLOCK; return 0; } - ASSERT(!ISNULLSTARTBLOCK(got.br_startblock)); + ASSERT(!isnullstartblock(got.br_startblock)); ASSERT(bno < got.br_startoff + got.br_blockcount); *fsb = got.br_startblock + (bno - got.br_startoff); ifp->if_lastex = lastx; @@ -5543,7 +5543,7 @@ xfs_bunmapi( */ ASSERT(ep != NULL); del = got; - wasdel = ISNULLSTARTBLOCK(del.br_startblock); + wasdel = isnullstartblock(del.br_startblock); if (got.br_startoff < start) { del.br_startoff = start; del.br_blockcount -= start - got.br_startoff; @@ -5638,7 +5638,7 @@ xfs_bunmapi( xfs_bmbt_get_all(xfs_iext_get_ext(ifp, lastx - 1), &prev); ASSERT(prev.br_state == XFS_EXT_NORM); - ASSERT(!ISNULLSTARTBLOCK(prev.br_startblock)); + ASSERT(!isnullstartblock(prev.br_startblock)); ASSERT(del.br_startblock == prev.br_startblock + prev.br_blockcount); if (prev.br_startoff < start) { @@ -5666,7 +5666,7 @@ xfs_bunmapi( } } if (wasdel) { - ASSERT(STARTBLOCKVAL(del.br_startblock) > 0); + ASSERT(startblockval(del.br_startblock) > 0); /* Update realtime/data freespace, unreserve quota */ if (isrt) { xfs_filblks_t rtexts; @@ -5782,12 +5782,12 @@ error0: * Log everything. Do this after conversion, there's no point in * logging the extent records if we've converted to btree format. */ - if ((logflags & XFS_ILOG_FEXT(whichfork)) && + if ((logflags & xfs_ilog_fext(whichfork)) && XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS) - logflags &= ~XFS_ILOG_FEXT(whichfork); - else if ((logflags & XFS_ILOG_FBROOT(whichfork)) && + logflags &= ~xfs_ilog_fext(whichfork); + else if ((logflags & xfs_ilog_fbroot(whichfork)) && XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE) - logflags &= ~XFS_ILOG_FBROOT(whichfork); + logflags &= ~xfs_ilog_fbroot(whichfork); /* * Log inode even in the error case, if the transaction * is dirty we'll need to shut down the filesystem. @@ -5838,7 +5838,7 @@ xfs_getbmapx_fix_eof_hole( if (startblock == DELAYSTARTBLOCK) out->bmv_block = -2; else - out->bmv_block = XFS_FSB_TO_DB(ip, startblock); + out->bmv_block = xfs_fsb_to_db(ip, startblock); fileblock = XFS_BB_TO_FSB(ip->i_mount, out->bmv_offset); ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); if (xfs_iext_bno_to_ext(ifp, fileblock, &lastx) && @@ -5979,7 +5979,7 @@ xfs_getbmap( if (nex > XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1) nex = XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1; - bmapi_flags = XFS_BMAPI_AFLAG(whichfork) | + bmapi_flags = xfs_bmapi_aflag(whichfork) | ((iflags & BMV_IF_PREALLOC) ? 0 : XFS_BMAPI_IGSTATE); /* @@ -6098,7 +6098,7 @@ xfs_bmap_isaeof( */ *aeof = (off >= s.br_startoff && off < s.br_startoff + s.br_blockcount && - ISNULLSTARTBLOCK(s.br_startblock)) || + isnullstartblock(s.br_startblock)) || off >= s.br_startoff + s.br_blockcount; return 0; } diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h index 284571c05ed..be2979d88d3 100644 --- a/fs/xfs/xfs_bmap.h +++ b/fs/xfs/xfs_bmap.h @@ -95,7 +95,6 @@ typedef struct xfs_bmap_free /* need write cache flushing and no */ /* additional allocation alignments */ -#define XFS_BMAPI_AFLAG(w) xfs_bmapi_aflag(w) static inline int xfs_bmapi_aflag(int w) { return (w == XFS_ATTR_FORK ? XFS_BMAPI_ATTRFORK : 0); @@ -107,7 +106,6 @@ static inline int xfs_bmapi_aflag(int w) #define DELAYSTARTBLOCK ((xfs_fsblock_t)-1LL) #define HOLESTARTBLOCK ((xfs_fsblock_t)-2LL) -#define XFS_BMAP_INIT(flp,fbp) xfs_bmap_init(flp,fbp) static inline void xfs_bmap_init(xfs_bmap_free_t *flp, xfs_fsblock_t *fbp) { ((flp)->xbf_first = NULL, (flp)->xbf_count = 0, \ diff --git a/fs/xfs/xfs_bmap_btree.c b/fs/xfs/xfs_bmap_btree.c index 8f1ec73725d..0760d352586 100644 --- a/fs/xfs/xfs_bmap_btree.c +++ b/fs/xfs/xfs_bmap_btree.c @@ -110,25 +110,25 @@ __xfs_bmbt_get_all( ext_flag = (int)(l0 >> (64 - BMBT_EXNTFLAG_BITLEN)); s->br_startoff = ((xfs_fileoff_t)l0 & - XFS_MASK64LO(64 - BMBT_EXNTFLAG_BITLEN)) >> 9; + xfs_mask64lo(64 - BMBT_EXNTFLAG_BITLEN)) >> 9; #if XFS_BIG_BLKNOS - s->br_startblock = (((xfs_fsblock_t)l0 & XFS_MASK64LO(9)) << 43) | + s->br_startblock = (((xfs_fsblock_t)l0 & xfs_mask64lo(9)) << 43) | (((xfs_fsblock_t)l1) >> 21); #else #ifdef DEBUG { xfs_dfsbno_t b; - b = (((xfs_dfsbno_t)l0 & XFS_MASK64LO(9)) << 43) | + b = (((xfs_dfsbno_t)l0 & xfs_mask64lo(9)) << 43) | (((xfs_dfsbno_t)l1) >> 21); - ASSERT((b >> 32) == 0 || ISNULLDSTARTBLOCK(b)); + ASSERT((b >> 32) == 0 || isnulldstartblock(b)); s->br_startblock = (xfs_fsblock_t)b; } #else /* !DEBUG */ s->br_startblock = (xfs_fsblock_t)(((xfs_dfsbno_t)l1) >> 21); #endif /* DEBUG */ #endif /* XFS_BIG_BLKNOS */ - s->br_blockcount = (xfs_filblks_t)(l1 & XFS_MASK64LO(21)); + s->br_blockcount = (xfs_filblks_t)(l1 & xfs_mask64lo(21)); /* This is xfs_extent_state() in-line */ if (ext_flag) { ASSERT(s->br_blockcount != 0); /* saved for DMIG */ @@ -153,7 +153,7 @@ xfs_filblks_t xfs_bmbt_get_blockcount( xfs_bmbt_rec_host_t *r) { - return (xfs_filblks_t)(r->l1 & XFS_MASK64LO(21)); + return (xfs_filblks_t)(r->l1 & xfs_mask64lo(21)); } /* @@ -164,15 +164,15 @@ xfs_bmbt_get_startblock( xfs_bmbt_rec_host_t *r) { #if XFS_BIG_BLKNOS - return (((xfs_fsblock_t)r->l0 & XFS_MASK64LO(9)) << 43) | + return (((xfs_fsblock_t)r->l0 & xfs_mask64lo(9)) << 43) | (((xfs_fsblock_t)r->l1) >> 21); #else #ifdef DEBUG xfs_dfsbno_t b; - b = (((xfs_dfsbno_t)r->l0 & XFS_MASK64LO(9)) << 43) | + b = (((xfs_dfsbno_t)r->l0 & xfs_mask64lo(9)) << 43) | (((xfs_dfsbno_t)r->l1) >> 21); - ASSERT((b >> 32) == 0 || ISNULLDSTARTBLOCK(b)); + ASSERT((b >> 32) == 0 || isnulldstartblock(b)); return (xfs_fsblock_t)b; #else /* !DEBUG */ return (xfs_fsblock_t)(((xfs_dfsbno_t)r->l1) >> 21); @@ -188,7 +188,7 @@ xfs_bmbt_get_startoff( xfs_bmbt_rec_host_t *r) { return ((xfs_fileoff_t)r->l0 & - XFS_MASK64LO(64 - BMBT_EXNTFLAG_BITLEN)) >> 9; + xfs_mask64lo(64 - BMBT_EXNTFLAG_BITLEN)) >> 9; } xfs_exntst_t @@ -219,7 +219,7 @@ xfs_filblks_t xfs_bmbt_disk_get_blockcount( xfs_bmbt_rec_t *r) { - return (xfs_filblks_t)(be64_to_cpu(r->l1) & XFS_MASK64LO(21)); + return (xfs_filblks_t)(be64_to_cpu(r->l1) & xfs_mask64lo(21)); } /* @@ -230,7 +230,7 @@ xfs_bmbt_disk_get_startoff( xfs_bmbt_rec_t *r) { return ((xfs_fileoff_t)be64_to_cpu(r->l0) & - XFS_MASK64LO(64 - BMBT_EXNTFLAG_BITLEN)) >> 9; + xfs_mask64lo(64 - BMBT_EXNTFLAG_BITLEN)) >> 9; } @@ -248,33 +248,33 @@ xfs_bmbt_set_allf( int extent_flag = (state == XFS_EXT_NORM) ? 0 : 1; ASSERT(state == XFS_EXT_NORM || state == XFS_EXT_UNWRITTEN); - ASSERT((startoff & XFS_MASK64HI(64-BMBT_STARTOFF_BITLEN)) == 0); - ASSERT((blockcount & XFS_MASK64HI(64-BMBT_BLOCKCOUNT_BITLEN)) == 0); + ASSERT((startoff & xfs_mask64hi(64-BMBT_STARTOFF_BITLEN)) == 0); + ASSERT((blockcount & xfs_mask64hi(64-BMBT_BLOCKCOUNT_BITLEN)) == 0); #if XFS_BIG_BLKNOS - ASSERT((startblock & XFS_MASK64HI(64-BMBT_STARTBLOCK_BITLEN)) == 0); + ASSERT((startblock & xfs_mask64hi(64-BMBT_STARTBLOCK_BITLEN)) == 0); r->l0 = ((xfs_bmbt_rec_base_t)extent_flag << 63) | ((xfs_bmbt_rec_base_t)startoff << 9) | ((xfs_bmbt_rec_base_t)startblock >> 43); r->l1 = ((xfs_bmbt_rec_base_t)startblock << 21) | ((xfs_bmbt_rec_base_t)blockcount & - (xfs_bmbt_rec_base_t)XFS_MASK64LO(21)); + (xfs_bmbt_rec_base_t)xfs_mask64lo(21)); #else /* !XFS_BIG_BLKNOS */ - if (ISNULLSTARTBLOCK(startblock)) { + if (isnullstartblock(startblock)) { r->l0 = ((xfs_bmbt_rec_base_t)extent_flag << 63) | ((xfs_bmbt_rec_base_t)startoff << 9) | - (xfs_bmbt_rec_base_t)XFS_MASK64LO(9); - r->l1 = XFS_MASK64HI(11) | + (xfs_bmbt_rec_base_t)xfs_mask64lo(9); + r->l1 = xfs_mask64hi(11) | ((xfs_bmbt_rec_base_t)startblock << 21) | ((xfs_bmbt_rec_base_t)blockcount & - (xfs_bmbt_rec_base_t)XFS_MASK64LO(21)); + (xfs_bmbt_rec_base_t)xfs_mask64lo(21)); } else { r->l0 = ((xfs_bmbt_rec_base_t)extent_flag << 63) | ((xfs_bmbt_rec_base_t)startoff << 9); r->l1 = ((xfs_bmbt_rec_base_t)startblock << 21) | ((xfs_bmbt_rec_base_t)blockcount & - (xfs_bmbt_rec_base_t)XFS_MASK64LO(21)); + (xfs_bmbt_rec_base_t)xfs_mask64lo(21)); } #endif /* XFS_BIG_BLKNOS */ } @@ -306,11 +306,11 @@ xfs_bmbt_disk_set_allf( int extent_flag = (state == XFS_EXT_NORM) ? 0 : 1; ASSERT(state == XFS_EXT_NORM || state == XFS_EXT_UNWRITTEN); - ASSERT((startoff & XFS_MASK64HI(64-BMBT_STARTOFF_BITLEN)) == 0); - ASSERT((blockcount & XFS_MASK64HI(64-BMBT_BLOCKCOUNT_BITLEN)) == 0); + ASSERT((startoff & xfs_mask64hi(64-BMBT_STARTOFF_BITLEN)) == 0); + ASSERT((blockcount & xfs_mask64hi(64-BMBT_BLOCKCOUNT_BITLEN)) == 0); #if XFS_BIG_BLKNOS - ASSERT((startblock & XFS_MASK64HI(64-BMBT_STARTBLOCK_BITLEN)) == 0); + ASSERT((startblock & xfs_mask64hi(64-BMBT_STARTBLOCK_BITLEN)) == 0); r->l0 = cpu_to_be64( ((xfs_bmbt_rec_base_t)extent_flag << 63) | @@ -319,17 +319,17 @@ xfs_bmbt_disk_set_allf( r->l1 = cpu_to_be64( ((xfs_bmbt_rec_base_t)startblock << 21) | ((xfs_bmbt_rec_base_t)blockcount & - (xfs_bmbt_rec_base_t)XFS_MASK64LO(21))); + (xfs_bmbt_rec_base_t)xfs_mask64lo(21))); #else /* !XFS_BIG_BLKNOS */ - if (ISNULLSTARTBLOCK(startblock)) { + if (isnullstartblock(startblock)) { r->l0 = cpu_to_be64( ((xfs_bmbt_rec_base_t)extent_flag << 63) | ((xfs_bmbt_rec_base_t)startoff << 9) | - (xfs_bmbt_rec_base_t)XFS_MASK64LO(9)); - r->l1 = cpu_to_be64(XFS_MASK64HI(11) | + (xfs_bmbt_rec_base_t)xfs_mask64lo(9)); + r->l1 = cpu_to_be64(xfs_mask64hi(11) | ((xfs_bmbt_rec_base_t)startblock << 21) | ((xfs_bmbt_rec_base_t)blockcount & - (xfs_bmbt_rec_base_t)XFS_MASK64LO(21))); + (xfs_bmbt_rec_base_t)xfs_mask64lo(21))); } else { r->l0 = cpu_to_be64( ((xfs_bmbt_rec_base_t)extent_flag << 63) | @@ -337,7 +337,7 @@ xfs_bmbt_disk_set_allf( r->l1 = cpu_to_be64( ((xfs_bmbt_rec_base_t)startblock << 21) | ((xfs_bmbt_rec_base_t)blockcount & - (xfs_bmbt_rec_base_t)XFS_MASK64LO(21))); + (xfs_bmbt_rec_base_t)xfs_mask64lo(21))); } #endif /* XFS_BIG_BLKNOS */ } @@ -362,9 +362,9 @@ xfs_bmbt_set_blockcount( xfs_bmbt_rec_host_t *r, xfs_filblks_t v) { - ASSERT((v & XFS_MASK64HI(43)) == 0); - r->l1 = (r->l1 & (xfs_bmbt_rec_base_t)XFS_MASK64HI(43)) | - (xfs_bmbt_rec_base_t)(v & XFS_MASK64LO(21)); + ASSERT((v & xfs_mask64hi(43)) == 0); + r->l1 = (r->l1 & (xfs_bmbt_rec_base_t)xfs_mask64hi(43)) | + (xfs_bmbt_rec_base_t)(v & xfs_mask64lo(21)); } /* @@ -376,21 +376,21 @@ xfs_bmbt_set_startblock( xfs_fsblock_t v) { #if XFS_BIG_BLKNOS - ASSERT((v & XFS_MASK64HI(12)) == 0); - r->l0 = (r->l0 & (xfs_bmbt_rec_base_t)XFS_MASK64HI(55)) | + ASSERT((v & xfs_mask64hi(12)) == 0); + r->l0 = (r->l0 & (xfs_bmbt_rec_base_t)xfs_mask64hi(55)) | (xfs_bmbt_rec_base_t)(v >> 43); - r->l1 = (r->l1 & (xfs_bmbt_rec_base_t)XFS_MASK64LO(21)) | + r->l1 = (r->l1 & (xfs_bmbt_rec_base_t)xfs_mask64lo(21)) | (xfs_bmbt_rec_base_t)(v << 21); #else /* !XFS_BIG_BLKNOS */ - if (ISNULLSTARTBLOCK(v)) { - r->l0 |= (xfs_bmbt_rec_base_t)XFS_MASK64LO(9); - r->l1 = (xfs_bmbt_rec_base_t)XFS_MASK64HI(11) | + if (isnullstartblock(v)) { + r->l0 |= (xfs_bmbt_rec_base_t)xfs_mask64lo(9); + r->l1 = (xfs_bmbt_rec_base_t)xfs_mask64hi(11) | ((xfs_bmbt_rec_base_t)v << 21) | - (r->l1 & (xfs_bmbt_rec_base_t)XFS_MASK64LO(21)); + (r->l1 & (xfs_bmbt_rec_base_t)xfs_mask64lo(21)); } else { - r->l0 &= ~(xfs_bmbt_rec_base_t)XFS_MASK64LO(9); + r->l0 &= ~(xfs_bmbt_rec_base_t)xfs_mask64lo(9); r->l1 = ((xfs_bmbt_rec_base_t)v << 21) | - (r->l1 & (xfs_bmbt_rec_base_t)XFS_MASK64LO(21)); + (r->l1 & (xfs_bmbt_rec_base_t)xfs_mask64lo(21)); } #endif /* XFS_BIG_BLKNOS */ } @@ -403,10 +403,10 @@ xfs_bmbt_set_startoff( xfs_bmbt_rec_host_t *r, xfs_fileoff_t v) { - ASSERT((v & XFS_MASK64HI(9)) == 0); - r->l0 = (r->l0 & (xfs_bmbt_rec_base_t) XFS_MASK64HI(1)) | + ASSERT((v & xfs_mask64hi(9)) == 0); + r->l0 = (r->l0 & (xfs_bmbt_rec_base_t) xfs_mask64hi(1)) | ((xfs_bmbt_rec_base_t)v << 9) | - (r->l0 & (xfs_bmbt_rec_base_t)XFS_MASK64LO(9)); + (r->l0 & (xfs_bmbt_rec_base_t)xfs_mask64lo(9)); } /* @@ -419,9 +419,9 @@ xfs_bmbt_set_state( { ASSERT(v == XFS_EXT_NORM || v == XFS_EXT_UNWRITTEN); if (v == XFS_EXT_NORM) - r->l0 &= XFS_MASK64LO(64 - BMBT_EXNTFLAG_BITLEN); + r->l0 &= xfs_mask64lo(64 - BMBT_EXNTFLAG_BITLEN); else - r->l0 |= XFS_MASK64HI(BMBT_EXNTFLAG_BITLEN); + r->l0 |= xfs_mask64hi(BMBT_EXNTFLAG_BITLEN); } /* diff --git a/fs/xfs/xfs_bmap_btree.h b/fs/xfs/xfs_bmap_btree.h index a4555abb662..0e8df007615 100644 --- a/fs/xfs/xfs_bmap_btree.h +++ b/fs/xfs/xfs_bmap_btree.h @@ -76,26 +76,22 @@ typedef struct xfs_bmbt_rec_host { #define DSTARTBLOCKMASK \ (((((xfs_dfsbno_t)1) << DSTARTBLOCKMASKBITS) - 1) << STARTBLOCKVALBITS) -#define ISNULLSTARTBLOCK(x) isnullstartblock(x) static inline int isnullstartblock(xfs_fsblock_t x) { return ((x) & STARTBLOCKMASK) == STARTBLOCKMASK; } -#define ISNULLDSTARTBLOCK(x) isnulldstartblock(x) static inline int isnulldstartblock(xfs_dfsbno_t x) { return ((x) & DSTARTBLOCKMASK) == DSTARTBLOCKMASK; } -#define NULLSTARTBLOCK(k) nullstartblock(k) static inline xfs_fsblock_t nullstartblock(int k) { ASSERT(k < (1 << STARTBLOCKVALBITS)); return STARTBLOCKMASK | (k); } -#define STARTBLOCKVAL(x) startblockval(x) static inline xfs_filblks_t startblockval(xfs_fsblock_t x) { return (xfs_filblks_t)((x) & ~STARTBLOCKMASK); diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c index 7ed59267420..e73c332eb23 100644 --- a/fs/xfs/xfs_btree.c +++ b/fs/xfs/xfs_btree.c @@ -730,8 +730,8 @@ xfs_btree_readahead_lblock( struct xfs_btree_block *block) { int rval = 0; - xfs_fsblock_t left = be64_to_cpu(block->bb_u.l.bb_leftsib); - xfs_fsblock_t right = be64_to_cpu(block->bb_u.l.bb_rightsib); + xfs_dfsbno_t left = be64_to_cpu(block->bb_u.l.bb_leftsib); + xfs_dfsbno_t right = be64_to_cpu(block->bb_u.l.bb_rightsib); if ((lr & XFS_BTCUR_LEFTRA) && left != NULLDFSBNO) { xfs_btree_reada_bufl(cur->bc_mp, left, 1); @@ -843,7 +843,7 @@ xfs_btree_ptr_is_null( union xfs_btree_ptr *ptr) { if (cur->bc_flags & XFS_BTREE_LONG_PTRS) - return be64_to_cpu(ptr->l) == NULLFSBLOCK; + return be64_to_cpu(ptr->l) == NULLDFSBNO; else return be32_to_cpu(ptr->s) == NULLAGBLOCK; } @@ -854,7 +854,7 @@ xfs_btree_set_ptr_null( union xfs_btree_ptr *ptr) { if (cur->bc_flags & XFS_BTREE_LONG_PTRS) - ptr->l = cpu_to_be64(NULLFSBLOCK); + ptr->l = cpu_to_be64(NULLDFSBNO); else ptr->s = cpu_to_be32(NULLAGBLOCK); } @@ -918,8 +918,8 @@ xfs_btree_init_block( new->bb_numrecs = cpu_to_be16(numrecs); if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { - new->bb_u.l.bb_leftsib = cpu_to_be64(NULLFSBLOCK); - new->bb_u.l.bb_rightsib = cpu_to_be64(NULLFSBLOCK); + new->bb_u.l.bb_leftsib = cpu_to_be64(NULLDFSBNO); + new->bb_u.l.bb_rightsib = cpu_to_be64(NULLDFSBNO); } else { new->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK); new->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK); @@ -960,7 +960,7 @@ xfs_btree_buf_to_ptr( ptr->l = cpu_to_be64(XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp))); else { - ptr->s = cpu_to_be32(XFS_DADDR_TO_AGBNO(cur->bc_mp, + ptr->s = cpu_to_be32(xfs_daddr_to_agbno(cur->bc_mp, XFS_BUF_ADDR(bp))); } } @@ -971,7 +971,7 @@ xfs_btree_ptr_to_daddr( union xfs_btree_ptr *ptr) { if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { - ASSERT(be64_to_cpu(ptr->l) != NULLFSBLOCK); + ASSERT(be64_to_cpu(ptr->l) != NULLDFSBNO); return XFS_FSB_TO_DADDR(cur->bc_mp, be64_to_cpu(ptr->l)); } else { @@ -2454,7 +2454,7 @@ xfs_btree_new_iroot( xfs_btree_log_ptrs(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs)); *logflags |= - XFS_ILOG_CORE | XFS_ILOG_FBROOT(cur->bc_private.b.whichfork); + XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_private.b.whichfork); *stat = 1; XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT); return 0; @@ -3048,7 +3048,7 @@ xfs_btree_kill_iroot( cur->bc_bufs[level - 1] = NULL; be16_add_cpu(&block->bb_level, -1); xfs_trans_log_inode(cur->bc_tp, ip, - XFS_ILOG_CORE | XFS_ILOG_FBROOT(cur->bc_private.b.whichfork)); + XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_private.b.whichfork)); cur->bc_nlevels--; out0: XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT); diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c index a11a8390bf6..c45f74ff1a5 100644 --- a/fs/xfs/xfs_da_btree.c +++ b/fs/xfs/xfs_da_btree.c @@ -1597,7 +1597,7 @@ xfs_da_grow_inode(xfs_da_args_t *args, xfs_dablk_t *new_blkno) nmap = 1; ASSERT(args->firstblock != NULL); if ((error = xfs_bmapi(tp, dp, bno, count, - XFS_BMAPI_AFLAG(w)|XFS_BMAPI_WRITE|XFS_BMAPI_METADATA| + xfs_bmapi_aflag(w)|XFS_BMAPI_WRITE|XFS_BMAPI_METADATA| XFS_BMAPI_CONTIG, args->firstblock, args->total, &map, &nmap, args->flist, NULL))) { @@ -1618,7 +1618,7 @@ xfs_da_grow_inode(xfs_da_args_t *args, xfs_dablk_t *new_blkno) nmap = MIN(XFS_BMAP_MAX_NMAP, count); c = (int)(bno + count - b); if ((error = xfs_bmapi(tp, dp, b, c, - XFS_BMAPI_AFLAG(w)|XFS_BMAPI_WRITE| + xfs_bmapi_aflag(w)|XFS_BMAPI_WRITE| XFS_BMAPI_METADATA, args->firstblock, args->total, &mapp[mapi], &nmap, args->flist, @@ -1882,7 +1882,7 @@ xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno, * the last block to the place we want to kill. */ if ((error = xfs_bunmapi(tp, dp, dead_blkno, count, - XFS_BMAPI_AFLAG(w)|XFS_BMAPI_METADATA, + xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA, 0, args->firstblock, args->flist, NULL, &done)) == ENOSPC) { if (w != XFS_DATA_FORK) @@ -1987,7 +1987,7 @@ xfs_da_do_buf( if ((error = xfs_bmapi(trans, dp, (xfs_fileoff_t)bno, nfsb, XFS_BMAPI_METADATA | - XFS_BMAPI_AFLAG(whichfork), + xfs_bmapi_aflag(whichfork), NULL, 0, mapp, &nmap, NULL, NULL))) goto exit0; } diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c index e2fa0a1d8e9..e1f0a06aaf0 100644 --- a/fs/xfs/xfs_dir2_block.c +++ b/fs/xfs/xfs_dir2_block.c @@ -517,9 +517,9 @@ xfs_dir2_block_getdents( /* * If it didn't fit, set the final offset to here & return. */ - if (filldir(dirent, dep->name, dep->namelen, cook, + if (filldir(dirent, dep->name, dep->namelen, cook & 0x7fffffff, ino, DT_UNKNOWN)) { - *offset = cook; + *offset = cook & 0x7fffffff; xfs_da_brelse(NULL, bp); return 0; } @@ -529,7 +529,8 @@ xfs_dir2_block_getdents( * Reached the end of the block. * Set the offset to a non-existent block 1 and return. */ - *offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0); + *offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) & + 0x7fffffff; xfs_da_brelse(NULL, bp); return 0; } diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c index 93535992cb6..ef805a374ee 100644 --- a/fs/xfs/xfs_dir2_leaf.c +++ b/fs/xfs/xfs_dir2_leaf.c @@ -1092,7 +1092,7 @@ xfs_dir2_leaf_getdents( * Won't fit. Return to caller. */ if (filldir(dirent, dep->name, dep->namelen, - xfs_dir2_byte_to_dataptr(mp, curoff), + xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff, ino, DT_UNKNOWN)) break; @@ -1108,9 +1108,9 @@ xfs_dir2_leaf_getdents( * All done. Set output offset value to current offset. */ if (curoff > xfs_dir2_dataptr_to_byte(mp, XFS_DIR2_MAX_DATAPTR)) - *offset = XFS_DIR2_MAX_DATAPTR; + *offset = XFS_DIR2_MAX_DATAPTR & 0x7fffffff; else - *offset = xfs_dir2_byte_to_dataptr(mp, curoff); + *offset = xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff; kmem_free(map); if (bp) xfs_da_brelse(NULL, bp); diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c index b46af0013ec..a8a8a6efad5 100644 --- a/fs/xfs/xfs_dir2_sf.c +++ b/fs/xfs/xfs_dir2_sf.c @@ -752,8 +752,8 @@ xfs_dir2_sf_getdents( #if XFS_BIG_INUMS ino += mp->m_inoadd; #endif - if (filldir(dirent, ".", 1, dot_offset, ino, DT_DIR)) { - *offset = dot_offset; + if (filldir(dirent, ".", 1, dot_offset & 0x7fffffff, ino, DT_DIR)) { + *offset = dot_offset & 0x7fffffff; return 0; } } @@ -766,8 +766,8 @@ xfs_dir2_sf_getdents( #if XFS_BIG_INUMS ino += mp->m_inoadd; #endif - if (filldir(dirent, "..", 2, dotdot_offset, ino, DT_DIR)) { - *offset = dotdot_offset; + if (filldir(dirent, "..", 2, dotdot_offset & 0x7fffffff, ino, DT_DIR)) { + *offset = dotdot_offset & 0x7fffffff; return 0; } } @@ -791,14 +791,15 @@ xfs_dir2_sf_getdents( #endif if (filldir(dirent, sfep->name, sfep->namelen, - off, ino, DT_UNKNOWN)) { - *offset = off; + off & 0x7fffffff, ino, DT_UNKNOWN)) { + *offset = off & 0x7fffffff; return 0; } sfep = xfs_dir2_sf_nextentry(sfp, sfep); } - *offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0); + *offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) & + 0x7fffffff; return 0; } diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c index e6ebbaeb4dc..ab016e5ae7b 100644 --- a/fs/xfs/xfs_ialloc.c +++ b/fs/xfs/xfs_ialloc.c @@ -357,7 +357,7 @@ xfs_ialloc_ag_alloc( int ioffset = i << args.mp->m_sb.sb_inodelog; uint isize = sizeof(struct xfs_dinode); - free = XFS_MAKE_IPTR(args.mp, fbuf, i); + free = xfs_make_iptr(args.mp, fbuf, i); free->di_magic = cpu_to_be16(XFS_DINODE_MAGIC); free->di_version = version; free->di_gen = cpu_to_be32(gen); @@ -937,7 +937,7 @@ nextag: } } } - offset = XFS_IALLOC_FIND_FREE(&rec.ir_free); + offset = xfs_ialloc_find_free(&rec.ir_free); ASSERT(offset >= 0); ASSERT(offset < XFS_INODES_PER_CHUNK); ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) % @@ -1279,7 +1279,7 @@ xfs_imap( offset = XFS_INO_TO_OFFSET(mp, ino); ASSERT(offset < mp->m_sb.sb_inopblock); - cluster_agbno = XFS_DADDR_TO_AGBNO(mp, imap->im_blkno); + cluster_agbno = xfs_daddr_to_agbno(mp, imap->im_blkno); offset += (agbno - cluster_agbno) * mp->m_sb.sb_inopblock; imap->im_len = XFS_FSB_TO_BB(mp, blks_per_cluster); diff --git a/fs/xfs/xfs_ialloc.h b/fs/xfs/xfs_ialloc.h index 50f558a4e0a..aeee8278f92 100644 --- a/fs/xfs/xfs_ialloc.h +++ b/fs/xfs/xfs_ialloc.h @@ -39,7 +39,6 @@ struct xfs_trans; /* * Make an inode pointer out of the buffer/offset. */ -#define XFS_MAKE_IPTR(mp,b,o) xfs_make_iptr(mp,b,o) static inline struct xfs_dinode * xfs_make_iptr(struct xfs_mount *mp, struct xfs_buf *b, int o) { @@ -50,7 +49,6 @@ xfs_make_iptr(struct xfs_mount *mp, struct xfs_buf *b, int o) /* * Find a free (set) bit in the inode bitmask. */ -#define XFS_IALLOC_FIND_FREE(fp) xfs_ialloc_find_free(fp) static inline int xfs_ialloc_find_free(xfs_inofree_t *fp) { return xfs_lowbit64(*fp); diff --git a/fs/xfs/xfs_ialloc_btree.h b/fs/xfs/xfs_ialloc_btree.h index 37e5dd01a57..5580e255ff0 100644 --- a/fs/xfs/xfs_ialloc_btree.h +++ b/fs/xfs/xfs_ialloc_btree.h @@ -36,7 +36,6 @@ typedef __uint64_t xfs_inofree_t; #define XFS_INODES_PER_CHUNK_LOG (XFS_NBBYLOG + 3) #define XFS_INOBT_ALL_FREE ((xfs_inofree_t)-1) -#define XFS_INOBT_MASKN(i,n) xfs_inobt_maskn(i,n) static inline xfs_inofree_t xfs_inobt_maskn(int i, int n) { return (((n) >= XFS_INODES_PER_CHUNK ? \ diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 5a5e035e5d3..e7ae08d1df4 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -424,6 +424,19 @@ xfs_iformat( case XFS_DINODE_FMT_LOCAL: atp = (xfs_attr_shortform_t *)XFS_DFORK_APTR(dip); size = be16_to_cpu(atp->hdr.totsize); + + if (unlikely(size < sizeof(struct xfs_attr_sf_hdr))) { + xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount, + "corrupt inode %Lu " + "(bad attr fork size %Ld).", + (unsigned long long) ip->i_ino, + (long long) size); + XFS_CORRUPTION_ERROR("xfs_iformat(8)", + XFS_ERRLEVEL_LOW, + ip->i_mount, dip); + return XFS_ERROR(EFSCORRUPTED); + } + error = xfs_iformat_local(ip, dip, XFS_ATTR_FORK, size); break; case XFS_DINODE_FMT_EXTENTS: @@ -1601,10 +1614,10 @@ xfs_itruncate_finish( * in this file with garbage in them once recovery * runs. */ - XFS_BMAP_INIT(&free_list, &first_block); + xfs_bmap_init(&free_list, &first_block); error = xfs_bunmapi(ntp, ip, first_unmap_block, unmap_len, - XFS_BMAPI_AFLAG(fork) | + xfs_bmapi_aflag(fork) | (sync ? 0 : XFS_BMAPI_ASYNC), XFS_ITRUNC_MAX_EXTENTS, &first_block, &free_list, @@ -2557,7 +2570,7 @@ xfs_iextents_copy( for (i = 0; i < nrecs; i++) { xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, i); start_block = xfs_bmbt_get_startblock(ep); - if (ISNULLSTARTBLOCK(start_block)) { + if (isnullstartblock(start_block)) { /* * It's a delayed allocation extent, so skip it. */ diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h index 1ff04cc323a..9957d0602d5 100644 --- a/fs/xfs/xfs_inode_item.h +++ b/fs/xfs/xfs_inode_item.h @@ -111,20 +111,16 @@ typedef struct xfs_inode_log_format_64 { #define XFS_ILI_IOLOCKED_ANY (XFS_ILI_IOLOCKED_EXCL | XFS_ILI_IOLOCKED_SHARED) - -#define XFS_ILOG_FBROOT(w) xfs_ilog_fbroot(w) static inline int xfs_ilog_fbroot(int w) { return (w == XFS_DATA_FORK ? XFS_ILOG_DBROOT : XFS_ILOG_ABROOT); } -#define XFS_ILOG_FEXT(w) xfs_ilog_fext(w) static inline int xfs_ilog_fext(int w) { return (w == XFS_DATA_FORK ? XFS_ILOG_DEXT : XFS_ILOG_AEXT); } -#define XFS_ILOG_FDATA(w) xfs_ilog_fdata(w) static inline int xfs_ilog_fdata(int w) { return (w == XFS_DATA_FORK ? XFS_ILOG_DDATA : XFS_ILOG_ADATA); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 911062cf73a..08ce72316bf 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -155,7 +155,7 @@ xfs_imap_to_bmap( iomapp->iomap_bn = IOMAP_DADDR_NULL; iomapp->iomap_flags |= IOMAP_DELAY; } else { - iomapp->iomap_bn = XFS_FSB_TO_DB(ip, start_block); + iomapp->iomap_bn = xfs_fsb_to_db(ip, start_block); if (ISUNWRITTEN(imap)) iomapp->iomap_flags |= IOMAP_UNWRITTEN; } @@ -261,7 +261,7 @@ xfs_iomap( xfs_iunlock(ip, lockmode); lockmode = 0; - if (nimaps && !ISNULLSTARTBLOCK(imap.br_startblock)) { + if (nimaps && !isnullstartblock(imap.br_startblock)) { xfs_iomap_map_trace(XFS_IOMAP_WRITE_MAP, ip, offset, count, iomapp, &imap, flags); break; @@ -491,7 +491,7 @@ xfs_iomap_write_direct( /* * Issue the xfs_bmapi() call to allocate the blocks */ - XFS_BMAP_INIT(&free_list, &firstfsb); + xfs_bmap_init(&free_list, &firstfsb); nimaps = 1; error = xfs_bmapi(tp, ip, offset_fsb, count_fsb, bmapi_flag, &firstfsb, 0, &imap, &nimaps, &free_list, NULL); @@ -751,7 +751,7 @@ xfs_iomap_write_allocate( xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); xfs_trans_ihold(tp, ip); - XFS_BMAP_INIT(&free_list, &first_block); + xfs_bmap_init(&free_list, &first_block); /* * it is possible that the extents have changed since @@ -911,7 +911,7 @@ xfs_iomap_write_unwritten( /* * Modify the unwritten extent state of the buffer. */ - XFS_BMAP_INIT(&free_list, &firstfsb); + xfs_bmap_init(&free_list, &firstfsb); nimaps = 1; error = xfs_bmapi(tp, ip, offset_fsb, count_fsb, XFS_BMAPI_WRITE|XFS_BMAPI_CONVERT, &firstfsb, diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index e19d0a8d561..cf98a805ec9 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -453,7 +453,7 @@ xfs_bulkstat( (chunkidx = agino - gino + 1) < XFS_INODES_PER_CHUNK && /* there are some left allocated */ - XFS_INOBT_MASKN(chunkidx, + xfs_inobt_maskn(chunkidx, XFS_INODES_PER_CHUNK - chunkidx) & ~gfree) { /* * Grab the chunk record. Mark all the @@ -464,7 +464,7 @@ xfs_bulkstat( if (XFS_INOBT_MASK(i) & ~gfree) gcnt++; } - gfree |= XFS_INOBT_MASKN(0, chunkidx); + gfree |= xfs_inobt_maskn(0, chunkidx); irbp->ir_startino = gino; irbp->ir_freecount = gcnt; irbp->ir_free = gfree; @@ -535,7 +535,7 @@ xfs_bulkstat( chunkidx < XFS_INODES_PER_CHUNK; chunkidx += nicluster, agbno += nbcluster) { - if (XFS_INOBT_MASKN(chunkidx, + if (xfs_inobt_maskn(chunkidx, nicluster) & ~gfree) xfs_btree_reada_bufs(mp, agno, agbno, nbcluster); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 3c97c6463a4..35300250e86 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -45,7 +45,6 @@ #include "xfs_fsops.h" #include "xfs_utils.h" -STATIC int xfs_mount_log_sb(xfs_mount_t *, __int64_t); STATIC int xfs_uuid_mount(xfs_mount_t *); STATIC void xfs_unmountfs_wait(xfs_mount_t *); @@ -682,7 +681,7 @@ xfs_initialize_perag_data(xfs_mount_t *mp, xfs_agnumber_t agcount) * Update alignment values based on mount options and sb values */ STATIC int -xfs_update_alignment(xfs_mount_t *mp, __uint64_t *update_flags) +xfs_update_alignment(xfs_mount_t *mp) { xfs_sb_t *sbp = &(mp->m_sb); @@ -736,11 +735,11 @@ xfs_update_alignment(xfs_mount_t *mp, __uint64_t *update_flags) if (xfs_sb_version_hasdalign(sbp)) { if (sbp->sb_unit != mp->m_dalign) { sbp->sb_unit = mp->m_dalign; - *update_flags |= XFS_SB_UNIT; + mp->m_update_flags |= XFS_SB_UNIT; } if (sbp->sb_width != mp->m_swidth) { sbp->sb_width = mp->m_swidth; - *update_flags |= XFS_SB_WIDTH; + mp->m_update_flags |= XFS_SB_WIDTH; } } } else if ((mp->m_flags & XFS_MOUNT_NOALIGN) != XFS_MOUNT_NOALIGN && @@ -905,7 +904,6 @@ xfs_mountfs( xfs_sb_t *sbp = &(mp->m_sb); xfs_inode_t *rip; __uint64_t resblks; - __int64_t update_flags = 0LL; uint quotamount, quotaflags; int uuid_mounted = 0; int error = 0; @@ -933,7 +931,7 @@ xfs_mountfs( "XFS: correcting sb_features alignment problem"); sbp->sb_features2 |= sbp->sb_bad_features2; sbp->sb_bad_features2 = sbp->sb_features2; - update_flags |= XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2; + mp->m_update_flags |= XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2; /* * Re-check for ATTR2 in case it was found in bad_features2 @@ -947,11 +945,11 @@ xfs_mountfs( if (xfs_sb_version_hasattr2(&mp->m_sb) && (mp->m_flags & XFS_MOUNT_NOATTR2)) { xfs_sb_version_removeattr2(&mp->m_sb); - update_flags |= XFS_SB_FEATURES2; + mp->m_update_flags |= XFS_SB_FEATURES2; /* update sb_versionnum for the clearing of the morebits */ if (!sbp->sb_features2) - update_flags |= XFS_SB_VERSIONNUM; + mp->m_update_flags |= XFS_SB_VERSIONNUM; } /* @@ -960,7 +958,7 @@ xfs_mountfs( * allocator alignment is within an ag, therefore ag has * to be aligned at stripe boundary. */ - error = xfs_update_alignment(mp, &update_flags); + error = xfs_update_alignment(mp); if (error) goto error1; @@ -1137,10 +1135,12 @@ xfs_mountfs( } /* - * If fs is not mounted readonly, then update the superblock changes. + * If this is a read-only mount defer the superblock updates until + * the next remount into writeable mode. Otherwise we would never + * perform the update e.g. for the root filesystem. */ - if (update_flags && !(mp->m_flags & XFS_MOUNT_RDONLY)) { - error = xfs_mount_log_sb(mp, update_flags); + if (mp->m_update_flags && !(mp->m_flags & XFS_MOUNT_RDONLY)) { + error = xfs_mount_log_sb(mp, mp->m_update_flags); if (error) { cmn_err(CE_WARN, "XFS: failed to write sb changes"); goto error4; @@ -1820,7 +1820,7 @@ xfs_uuid_mount( * be altered by the mount options, as well as any potential sb_features2 * fixup. Only the first superblock is updated. */ -STATIC int +int xfs_mount_log_sb( xfs_mount_t *mp, __int64_t fields) diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index c1e02846732..f5e9937f9bd 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -44,9 +44,9 @@ typedef struct xfs_trans_reservations { #ifndef __KERNEL__ -#define XFS_DADDR_TO_AGNO(mp,d) \ +#define xfs_daddr_to_agno(mp,d) \ ((xfs_agnumber_t)(XFS_BB_TO_FSBT(mp, d) / (mp)->m_sb.sb_agblocks)) -#define XFS_DADDR_TO_AGBNO(mp,d) \ +#define xfs_daddr_to_agbno(mp,d) \ ((xfs_agblock_t)(XFS_BB_TO_FSBT(mp, d) % (mp)->m_sb.sb_agblocks)) #else /* __KERNEL__ */ @@ -327,6 +327,8 @@ typedef struct xfs_mount { spinlock_t m_sync_lock; /* work item list lock */ int m_sync_seq; /* sync thread generation no. */ wait_queue_head_t m_wait_single_sync_task; + __int64_t m_update_flags; /* sb flags we need to update + on the next remount,rw */ } xfs_mount_t; /* @@ -439,7 +441,6 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname, */ #define XFS_MFSI_QUIET 0x40 /* Be silent if mount errors found */ -#define XFS_DADDR_TO_AGNO(mp,d) xfs_daddr_to_agno(mp,d) static inline xfs_agnumber_t xfs_daddr_to_agno(struct xfs_mount *mp, xfs_daddr_t d) { @@ -448,7 +449,6 @@ xfs_daddr_to_agno(struct xfs_mount *mp, xfs_daddr_t d) return (xfs_agnumber_t) ld; } -#define XFS_DADDR_TO_AGBNO(mp,d) xfs_daddr_to_agbno(mp,d) static inline xfs_agblock_t xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d) { @@ -514,6 +514,7 @@ extern int xfs_mod_incore_sb_unlocked(xfs_mount_t *, xfs_sb_field_t, int64_t, int); extern int xfs_mod_incore_sb_batch(xfs_mount_t *, xfs_mod_sb_t *, uint, int); +extern int xfs_mount_log_sb(xfs_mount_t *, __int64_t); extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int); extern int xfs_readsb(xfs_mount_t *, int); extern void xfs_freesb(xfs_mount_t *); diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c index 86471bb40fd..58f85e9cd11 100644 --- a/fs/xfs/xfs_rename.c +++ b/fs/xfs/xfs_rename.c @@ -147,7 +147,7 @@ xfs_rename( xfs_sort_for_rename(src_dp, target_dp, src_ip, target_ip, inodes, &num_inodes); - XFS_BMAP_INIT(&free_list, &first_block); + xfs_bmap_init(&free_list, &first_block); tp = xfs_trans_alloc(mp, XFS_TRANS_RENAME); cancel_flags = XFS_TRANS_RELEASE_LOG_RES; spaceres = XFS_RENAME_SPACE_RES(mp, target_name->len); diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index edf12c7b834..c5bb86f3ec0 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -120,7 +120,7 @@ xfs_growfs_rt_alloc( if ((error = xfs_trans_iget(mp, tp, ino, 0, XFS_ILOCK_EXCL, &ip))) goto error_cancel; - XFS_BMAP_INIT(&flist, &firstblock); + xfs_bmap_init(&flist, &firstblock); /* * Allocate blocks to the bitmap file. */ diff --git a/fs/xfs/xfs_rw.h b/fs/xfs/xfs_rw.h index f87db5344ce..f76c003ec55 100644 --- a/fs/xfs/xfs_rw.h +++ b/fs/xfs/xfs_rw.h @@ -28,7 +28,6 @@ struct xfs_mount; * file is a real time file or not, because the bmap code * does. */ -#define XFS_FSB_TO_DB(ip,fsb) xfs_fsb_to_db(ip,fsb) static inline xfs_daddr_t xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb) { diff --git a/fs/xfs/xfs_sb.h b/fs/xfs/xfs_sb.h index 1ed71916e4c..1b017c65749 100644 --- a/fs/xfs/xfs_sb.h +++ b/fs/xfs/xfs_sb.h @@ -505,7 +505,7 @@ static inline void xfs_sb_version_removeattr2(xfs_sb_t *sbp) #define XFS_HDR_BLOCK(mp,d) ((xfs_agblock_t)XFS_BB_TO_FSBT(mp,d)) #define XFS_DADDR_TO_FSB(mp,d) XFS_AGB_TO_FSB(mp, \ - XFS_DADDR_TO_AGNO(mp,d), XFS_DADDR_TO_AGBNO(mp,d)) + xfs_daddr_to_agno(mp,d), xfs_daddr_to_agbno(mp,d)) #define XFS_FSB_TO_DADDR(mp,fsbno) XFS_AGB_TO_DADDR(mp, \ XFS_FSB_TO_AGNO(mp,fsbno), XFS_FSB_TO_AGBNO(mp,fsbno)) diff --git a/fs/xfs/xfs_types.h b/fs/xfs/xfs_types.h index 0f5191644ab..b2f724502f1 100644 --- a/fs/xfs/xfs_types.h +++ b/fs/xfs/xfs_types.h @@ -45,7 +45,7 @@ typedef __uint32_t prid_t; /* project ID */ typedef __uint32_t inst_t; /* an instruction */ typedef __s64 xfs_off_t; /* <file offset> type */ -typedef __u64 xfs_ino_t; /* <inode> type */ +typedef unsigned long long xfs_ino_t; /* <inode> type */ typedef __s64 xfs_daddr_t; /* <disk address> type */ typedef char * xfs_caddr_t; /* <core address> type */ typedef __u32 xfs_dev_t; @@ -111,8 +111,6 @@ typedef __uint64_t xfs_fileoff_t; /* block number in a file */ typedef __int64_t xfs_sfiloff_t; /* signed block number in a file */ typedef __uint64_t xfs_filblks_t; /* number of blocks in a file */ -typedef __uint8_t xfs_arch_t; /* architecture of an xfs fs */ - /* * Null values for the types. */ diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index f07bf8768c3..0e55c5d7db5 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -862,7 +862,7 @@ xfs_inactive_symlink_rmt( * Find the block(s) so we can inval and unmap them. */ done = 0; - XFS_BMAP_INIT(&free_list, &first_block); + xfs_bmap_init(&free_list, &first_block); nmaps = ARRAY_SIZE(mval); if ((error = xfs_bmapi(tp, ip, 0, XFS_B_TO_FSB(mp, size), XFS_BMAPI_METADATA, &first_block, 0, mval, &nmaps, @@ -1288,7 +1288,7 @@ xfs_inactive( /* * Free the inode. */ - XFS_BMAP_INIT(&free_list, &first_block); + xfs_bmap_init(&free_list, &first_block); error = xfs_ifree(tp, ip, &free_list); if (error) { /* @@ -1461,7 +1461,7 @@ xfs_create( xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT); unlock_dp_on_error = B_TRUE; - XFS_BMAP_INIT(&free_list, &first_block); + xfs_bmap_init(&free_list, &first_block); ASSERT(ip == NULL); @@ -1879,7 +1879,7 @@ xfs_remove( } } - XFS_BMAP_INIT(&free_list, &first_block); + xfs_bmap_init(&free_list, &first_block); error = xfs_dir_removename(tp, dp, name, ip->i_ino, &first_block, &free_list, resblks); if (error) { @@ -2059,7 +2059,7 @@ xfs_link( if (error) goto error_return; - XFS_BMAP_INIT(&free_list, &first_block); + xfs_bmap_init(&free_list, &first_block); error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino, &first_block, &free_list, resblks); @@ -2231,7 +2231,7 @@ xfs_mkdir( xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL); unlock_dp_on_error = B_FALSE; - XFS_BMAP_INIT(&free_list, &first_block); + xfs_bmap_init(&free_list, &first_block); error = xfs_dir_createname(tp, dp, dir_name, cdp->i_ino, &first_block, &free_list, resblks ? @@ -2438,7 +2438,7 @@ xfs_symlink( * Initialize the bmap freelist prior to calling either * bmapi or the directory create code. */ - XFS_BMAP_INIT(&free_list, &first_block); + xfs_bmap_init(&free_list, &first_block); /* * Allocate an inode for the symlink. @@ -2860,7 +2860,7 @@ retry: /* * Issue the xfs_bmapi() call to allocate the blocks */ - XFS_BMAP_INIT(&free_list, &firstfsb); + xfs_bmap_init(&free_list, &firstfsb); error = xfs_bmapi(tp, ip, startoffset_fsb, allocatesize_fsb, bmapi_flag, &firstfsb, 0, imapp, &nimaps, @@ -2980,7 +2980,7 @@ xfs_zero_remaining_bytes( XFS_BUF_UNDONE(bp); XFS_BUF_UNWRITE(bp); XFS_BUF_READ(bp); - XFS_BUF_SET_ADDR(bp, XFS_FSB_TO_DB(ip, imap.br_startblock)); + XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock)); xfsbdstrat(mp, bp); error = xfs_iowait(bp); if (error) { @@ -3186,7 +3186,7 @@ xfs_free_file_space( /* * issue the bunmapi() call to free the blocks */ - XFS_BMAP_INIT(&free_list, &firstfsb); + xfs_bmap_init(&free_list, &firstfsb); error = xfs_bunmapi(tp, ip, startoffset_fsb, endoffset_fsb - startoffset_fsb, 0, 2, &firstfsb, &free_list, NULL, &done); |