diff options
Diffstat (limited to 'Documentation/filesystems')
22 files changed, 152 insertions, 169 deletions
diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt index 13de64c..2c03214 100644 --- a/Documentation/filesystems/9p.txt +++ b/Documentation/filesystems/9p.txt @@ -92,7 +92,7 @@ OPTIONS wfdno=n the file descriptor for writing with trans=fd - maxdata=n the number of bytes to use for 9p packet payload (msize) + msize=n the number of bytes to use for 9p packet payload port=n port to connect to on the remote server diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 57d827d..d819ba1 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -29,6 +29,7 @@ d_hash no no no maybe d_compare: yes no no maybe d_delete: no yes no no d_release: no no yes no +d_prune: no yes no no d_iput: no no yes no d_dname: no no no no d_automount: no no yes no @@ -52,7 +53,7 @@ ata *); void (*put_link) (struct dentry *, struct nameidata *, void *); void (*truncate) (struct inode *); int (*permission) (struct inode *, int, unsigned int); - int (*check_acl)(struct inode *, int, unsigned int); + int (*get_acl)(struct inode *, int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); @@ -80,7 +81,7 @@ put_link: no truncate: yes (see below) setattr: yes permission: no (may not block if called in rcu-walk mode) -check_acl: no +get_acl: no getattr: no setxattr: yes getxattr: no @@ -338,21 +339,21 @@ fl_release_private: maybe no ----------------------- lock_manager_operations --------------------------- prototypes: - int (*fl_compare_owner)(struct file_lock *, struct file_lock *); - void (*fl_notify)(struct file_lock *); /* unblock callback */ - int (*fl_grant)(struct file_lock *, struct file_lock *, int); - void (*fl_release_private)(struct file_lock *); - void (*fl_break)(struct file_lock *); /* break_lease callback */ - int (*fl_change)(struct file_lock **, int); + int (*lm_compare_owner)(struct file_lock *, struct file_lock *); + void (*lm_notify)(struct file_lock *); /* unblock callback */ + int (*lm_grant)(struct file_lock *, struct file_lock *, int); + void (*lm_release_private)(struct file_lock *); + void (*lm_break)(struct file_lock *); /* break_lease callback */ + int (*lm_change)(struct file_lock **, int); locking rules: file_lock_lock may block -fl_compare_owner: yes no -fl_notify: yes no -fl_grant: no no -fl_release_private: maybe no -fl_break: yes no -fl_change yes no +lm_compare_owner: yes no +lm_notify: yes no +lm_grant: no no +lm_release_private: maybe no +lm_break: yes no +lm_change yes no --------------------------- buffer_head ----------------------------------- prototypes: @@ -412,7 +413,7 @@ prototypes: int (*open) (struct inode *, struct file *); int (*flush) (struct file *); int (*release) (struct inode *, struct file *); - int (*fsync) (struct file *, int datasync); + int (*fsync) (struct file *, loff_t start, loff_t end, int datasync); int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); @@ -438,9 +439,7 @@ prototypes: locking rules: All may block except for ->setlease. - No VFS locks held on entry except for ->fsync and ->setlease. - -->fsync() has i_mutex on inode. + No VFS locks held on entry except for ->setlease. ->setlease has the file_list_lock held and must not sleep. diff --git a/Documentation/filesystems/befs.txt b/Documentation/filesystems/befs.txt index 6e49c36..da45e6c 100644 --- a/Documentation/filesystems/befs.txt +++ b/Documentation/filesystems/befs.txt @@ -27,7 +27,7 @@ His original code can still be found at: Does anyone know of a more current email address for Makoto? He doesn't respond to the address given above... -Current maintainer: Sergey S. Kostyliov <rathamahata@php4.ru> +This filesystem doesn't have a maintainer. WHAT IS THIS DRIVER? ================== diff --git a/Documentation/filesystems/btrfs.txt b/Documentation/filesystems/btrfs.txt index 64087c3..7671352 100644 --- a/Documentation/filesystems/btrfs.txt +++ b/Documentation/filesystems/btrfs.txt @@ -63,8 +63,8 @@ IRC network. Userspace tools for creating and manipulating Btrfs file systems are available from the git repository at the following location: - http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs-unstable.git - git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs-unstable.git + http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs.git + git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs.git These include the following tools: diff --git a/Documentation/filesystems/caching/object.txt b/Documentation/filesystems/caching/object.txt index e8b0a35..5831334 100644 --- a/Documentation/filesystems/caching/object.txt +++ b/Documentation/filesystems/caching/object.txt @@ -127,9 +127,9 @@ fscache_enqueue_object()). PROVISION OF CPU TIME --------------------- -The work to be done by the various states is given CPU time by the threads of -the slow work facility (see Documentation/slow-work.txt). This is used in -preference to the workqueue facility because: +The work to be done by the various states was given CPU time by the threads of +the slow work facility. This was used in preference to the workqueue facility +because: (1) Threads may be completely occupied for very long periods of time by a particular work item. These state actions may be doing sequences of diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index ed52af6..742cc06 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -73,8 +73,8 @@ the following functions can be used instead: struct dentry *parent, u16 *value); struct dentry *debugfs_create_x32(const char *name, mode_t mode, struct dentry *parent, u32 *value); - -Note that there is no debugfs_create_x64(). + struct dentry *debugfs_create_x64(const char *name, mode_t mode, + struct dentry *parent, u64 *value); These functions are useful as long as the developer knows the size of the value to be exported. Some types can have different widths on different diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt index 272f80d5..b100adc 100644 --- a/Documentation/filesystems/ext3.txt +++ b/Documentation/filesystems/ext3.txt @@ -73,14 +73,6 @@ nobarrier (*) This also requires an IO stack which can support also be used to enable or disable barriers, for consistency with other ext3 mount options. -orlov (*) This enables the new Orlov block allocator. It is - enabled by default. - -oldalloc This disables the Orlov block allocator and enables - the old block allocator. Orlov should have better - performance - we'd like to get some feedback if it's - the contrary for you. - user_xattr Enables Extended User Attributes. Additionally, you need to have extended attribute support enabled in the kernel configuration (CONFIG_EXT3_FS_XATTR). See the @@ -147,15 +139,6 @@ grpjquota=<file> during journal replay. They replace the above package for more details (http://sourceforge.net/projects/linuxquota). -bh (*) ext3 associates buffer heads to data pages to -nobh (a) cache disk block mapping information - (b) link pages into transaction to provide - ordering guarantees. - "bh" option forces use of buffer heads. - "nobh" option tries to avoid associating buffer - heads (supported only for "writeback" mode). - - Specification ============= Ext3 shares all disk implementation with the ext2 filesystem, and adds @@ -227,5 +210,5 @@ kernel source: <file:fs/ext3/> programs: http://e2fsprogs.sourceforge.net/ http://ext2resize.sourceforge.net -useful links: http://www.ibm.com/developerworks/library/l-fs7.html - http://www.ibm.com/developerworks/library/l-fs8.html +useful links: http://www.ibm.com/developerworks/library/l-fs7/index.html + http://www.ibm.com/developerworks/library/l-fs8/index.html diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 3ae9bc9..4917cf2 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -68,12 +68,12 @@ Note: More extensive information for getting started with ext4 can be '-o barriers=[0|1]' mount option for both ext3 and ext4 filesystems for a fair comparison. When tuning ext3 for best benchmark numbers, it is often worthwhile to try changing the data journaling mode; '-o - data=writeback,nobh' can be faster for some workloads. (Note - however that running mounted with data=writeback can potentially - leave stale data exposed in recently written files in case of an - unclean shutdown, which could be a security exposure in some - situations.) Configuring the filesystem with a large journal can - also be helpful for metadata-intensive workloads. + data=writeback' can be faster for some workloads. (Note however that + running mounted with data=writeback can potentially leave stale data + exposed in recently written files in case of an unclean shutdown, + which could be a security exposure in some situations.) Configuring + the filesystem with a large journal can also be helpful for + metadata-intensive workloads. 2. Features =========== @@ -160,7 +160,9 @@ noload if the filesystem was not unmounted cleanly, lead to any number of problems. data=journal All data are committed into the journal prior to being - written into the main file system. + written into the main file system. Enabling + this mode will disable delayed allocation and + O_DIRECT support. data=ordered (*) All data are forced directly out to the main file system prior to its metadata being committed to the @@ -201,30 +203,19 @@ inode_readahead_blks=n This tuning parameter controls the maximum table readahead algorithm will pre-read into the buffer cache. The default value is 32 blocks. -orlov (*) This enables the new Orlov block allocator. It is - enabled by default. - -oldalloc This disables the Orlov block allocator and enables - the old block allocator. Orlov should have better - performance - we'd like to get some feedback if it's - the contrary for you. - -user_xattr Enables Extended User Attributes. Additionally, you - need to have extended attribute support enabled in the - kernel configuration (CONFIG_EXT4_FS_XATTR). See the - attr(5) manual page and http://acl.bestbits.at/ to - learn more about extended attributes. - -nouser_xattr Disables Extended User Attributes. - -acl Enables POSIX Access Control Lists support. - Additionally, you need to have ACL support enabled in - the kernel configuration (CONFIG_EXT4_FS_POSIX_ACL). - See the acl(5) manual page and http://acl.bestbits.at/ - for more information. +nouser_xattr Disables Extended User Attributes. If you have extended + attribute support enabled in the kernel configuration + (CONFIG_EXT4_FS_XATTR), extended attribute support + is enabled by default on mount. See the attr(5) manual + page and http://acl.bestbits.at/ for more information + about extended attributes. noacl This option disables POSIX Access Control List - support. + support. If ACL support is enabled in the kernel + configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL is + enabled by default on mount. See the acl(5) manual + page and http://acl.bestbits.at/ for more information + about acl. bsddf (*) Make 'df' act like BSD. minixdf Make 'df' act like Minix. @@ -272,14 +263,6 @@ grpjquota=<file> during journal replay. They replace the above package for more details (http://sourceforge.net/projects/linuxquota). -bh (*) ext4 associates buffer heads to data pages to -nobh (a) cache disk block mapping information - (b) link pages into transaction to provide - ordering guarantees. - "bh" option forces use of buffer heads. - "nobh" option tries to avoid associating buffer - heads (supported only for "writeback" mode). - stripe=n Number of filesystem blocks that mballoc will try to use for allocation size and alignment. For RAID5/6 systems this should be the number of data @@ -393,8 +376,7 @@ dioread_nolock locking. If the dioread_nolock option is specified write and convert the extent to initialized after IO completes. This approach allows ext4 code to avoid using inode mutex, which improves scalability on high - speed storages. However this does not work with nobh - option and the mount will fail. Nor does it work with + speed storages. However this does not work with data journaling and dioread_nolock option will be ignored with kernel warning. Note that dioread_nolock code path is only used for extent-based files. @@ -428,8 +410,8 @@ written to the journal first, and then to its final location. In the event of a crash, the journal can be replayed, bringing both data and metadata into a consistent state. This mode is the slowest except when data needs to be read from and written to disk at the same time where it -outperforms all others modes. Currently ext4 does not have delayed -allocation support if this data journalling mode is selected. +outperforms all others modes. Enabling this mode will disable delayed +allocation and O_DIRECT support. /proc entries ============= diff --git a/Documentation/filesystems/hfs.txt b/Documentation/filesystems/hfs.txt index bd0fa77..d096df6 100644 --- a/Documentation/filesystems/hfs.txt +++ b/Documentation/filesystems/hfs.txt @@ -1,3 +1,4 @@ +Note: This filesystem doesn't have a maintainer. Macintosh HFS Filesystem for Linux ================================== @@ -76,8 +77,6 @@ hformat that can be used to create HFS filesystem. See Credits ======= -The HFS drivers was written by Paul H. Hargrovea (hargrove@sccm.Stanford.EDU) -and is now maintained by Roman Zippel (roman@ardistech.com) at Ardis -Technologies. -Roman rewrote large parts of the code and brought in btree routines derived -from Brad Boyer's hfsplus driver (also maintained by Roman now). +The HFS drivers was written by Paul H. Hargrovea (hargrove@sccm.Stanford.EDU). +Roman Zippel (roman@ardistech.com) rewrote large parts of the code and brought +in btree routines derived from Brad Boyer's hfsplus driver. diff --git a/Documentation/filesystems/inotify.txt b/Documentation/filesystems/inotify.txt index 59a919f..cfd0271 100644 --- a/Documentation/filesystems/inotify.txt +++ b/Documentation/filesystems/inotify.txt @@ -194,7 +194,8 @@ associated with the inotify_handle, and on which events are queued. Each watch is associated with an inotify_watch structure. Watches are chained off of each associated inotify_handle and each associated inode. -See fs/inotify.c and fs/inotify_user.c for the locking and lifetime rules. +See fs/notify/inotify/inotify_fsnotify.c and fs/notify/inotify/inotify_user.c +for the locking and lifetime rules. (vi) Rationale diff --git a/Documentation/filesystems/locks.txt b/Documentation/filesystems/locks.txt index fab857a..2cf8108 100644 --- a/Documentation/filesystems/locks.txt +++ b/Documentation/filesystems/locks.txt @@ -53,11 +53,12 @@ fcntl(), with all the problems that implies. 1.3 Mandatory Locking As A Mount Option --------------------------------------- -Mandatory locking, as described in 'Documentation/filesystems/mandatory.txt' -was prior to this release a general configuration option that was valid for -all mounted filesystems. This had a number of inherent dangers, not the -least of which was the ability to freeze an NFS server by asking it to read -a file for which a mandatory lock existed. +Mandatory locking, as described in +'Documentation/filesystems/mandatory-locking.txt' was prior to this release a +general configuration option that was valid for all mounted filesystems. This +had a number of inherent dangers, not the least of which was the ability to +freeze an NFS server by asking it to read a file for which a mandatory lock +existed. From this release of the kernel, mandatory locking can be turned on and off on a per-filesystem basis, using the mount options 'mand' and 'nomand'. diff --git a/Documentation/filesystems/nfs/Exporting b/Documentation/filesystems/nfs/Exporting index 87019d2..09994c2 100644 --- a/Documentation/filesystems/nfs/Exporting +++ b/Documentation/filesystems/nfs/Exporting @@ -92,7 +92,14 @@ For a filesystem to be exportable it must: 1/ provide the filehandle fragment routines described below. 2/ make sure that d_splice_alias is used rather than d_add when ->lookup finds an inode for a given parent and name. - Typically the ->lookup routine will end with a: + + If inode is NULL, d_splice_alias(inode, dentry) is eqivalent to + + d_add(dentry, inode), NULL + + Similarly, d_splice_alias(ERR_PTR(err), dentry) = ERR_PTR(err) + + Typically the ->lookup routine will simply end with a: return d_splice_alias(inode, dentry); } diff --git a/Documentation/filesystems/nfs/idmapper.txt b/Documentation/filesystems/nfs/idmapper.txt index 9c8fd61..120fd3c 100644 --- a/Documentation/filesystems/nfs/idmapper.txt +++ b/Documentation/filesystems/nfs/idmapper.txt @@ -47,7 +47,7 @@ request-key will find the first matching line and corresponding program. In this case, /some/other/program will handle all uid lookups and /usr/sbin/nfs.idmap will handle gid, user, and group lookups. -See <file:Documentation/security/keys-request-keys.txt> for more information +See <file:Documentation/security/keys-request-key.txt> for more information about the request-key function. diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt index 0488491..092fad9 100644 --- a/Documentation/filesystems/nfs/nfs41-server.txt +++ b/Documentation/filesystems/nfs/nfs41-server.txt @@ -39,27 +39,17 @@ interoperability problems with future clients. Known issues: from a linux client are possible, but we aren't really conformant with the spec (for example, we don't use kerberos on the backchannel correctly). - - no trunking support: no clients currently take advantage of - trunking, but this is a mandatory feature, and its use is - recommended to clients in a number of places. (E.g. to ensure - timely renewal in case an existing connection's retry timeouts - have gotten too long; see section 8.3 of the RFC.) - Therefore, lack of this feature may cause future clients to - fail. - Incomplete backchannel support: incomplete backchannel gss support and no support for BACKCHANNEL_CTL mean that callbacks (hence delegations and layouts) may not be available and clients confused by the incomplete implementation may fail. - - Server reboot recovery is unsupported; if the server reboots, - clients may fail. - We do not support SSV, which provides security for shared client-server state (thus preventing unauthorized tampering with locks and opens, for example). It is mandatory for servers to support this, though no clients use it yet. - Mandatory operations which we do not support, such as - DESTROY_CLIENTID, FREE_STATEID, SECINFO_NO_NAME, and - TEST_STATEID, are not currently used by clients, but will be + DESTROY_CLIENTID, are not currently used by clients, but will be (and the spec recommends their uses in common cases), and clients should not be expected to know how to recover from the case where they are not supported. This will eventually cause @@ -69,8 +59,9 @@ In addition, some limitations are inherited from the current NFSv4 implementation: - Incomplete delegation enforcement: if a file is renamed or - unlinked, a client holding a delegation may continue to - indefinitely allow opens of the file under the old name. + unlinked by a local process, a client holding a delegation may + continue to indefinitely allow opens of the file under the old + name. The table below, taken from the NFSv4.1 document, lists the operations that are mandatory to implement (REQ), optional @@ -99,7 +90,7 @@ Operations +----------------------+------------+--------------+----------------+ | ACCESS | REQ | | Section 18.1 | NS | BACKCHANNEL_CTL | REQ | | Section 18.33 | -NS | BIND_CONN_TO_SESSION | REQ | | Section 18.34 | +I | BIND_CONN_TO_SESSION | REQ | | Section 18.34 | | CLOSE | REQ | | Section 18.2 | | COMMIT | REQ | | Section 18.3 | | CREATE | REQ | | Section 18.4 | @@ -111,7 +102,7 @@ NS*| DELEGPURGE | OPT | FDELG (REQ) | Section 18.5 | NS | DESTROY_CLIENTID | REQ | | Section 18.50 | I | DESTROY_SESSION | REQ | | Section 18.37 | I | EXCHANGE_ID | REQ | | Section 18.35 | -NS | FREE_STATEID | REQ | | Section 18.38 | +I | FREE_STATEID | REQ | | Section 18.38 | | GETATTR | REQ | | Section 18.7 | P | GETDEVICEINFO | OPT | pNFS (REQ) | Section 18.40 | P | GETDEVICELIST | OPT | pNFS (OPT) | Section 18.41 | @@ -145,14 +136,14 @@ NS*| OPENATTR | OPT | | Section 18.17 | | RESTOREFH | REQ | | Section 18.27 | | SAVEFH | REQ | | Section 18.28 | | SECINFO | REQ | | Section 18.29 | -NS | SECINFO_NO_NAME | REC | pNFS files | Section 18.45, | +I | SECINFO_NO_NAME | REC | pNFS files | Section 18.45, | | | | layout (REQ) | Section 13.12 | I | SEQUENCE | REQ | | Section 18.46 | | SETATTR | REQ | | Section 18.30 | | SETCLIENTID | MNI | | N/A | | SETCLIENTID_CONFIRM | MNI | | N/A | NS | SET_SSV | REQ | | Section 18.47 | -NS | TEST_STATEID | REQ | | Section 18.48 | +I | TEST_STATEID | REQ | | Section 18.48 | | VERIFY | REQ | | Section 18.31 | NS*| WANT_DELEGATION | OPT | FDELG (OPT) | Section 18.49 | | WRITE | REQ | | Section 18.32 | @@ -206,12 +197,6 @@ CREATE_SESSION: SEQUENCE: * no support for dynamic slot table renegotiation (optional) -nfsv4.1 COMPOUND rules: -The following cases aren't supported yet: -* Enforcing of NFS4ERR_NOT_ONLY_OP for: BIND_CONN_TO_SESSION, CREATE_SESSION, - DESTROY_CLIENTID, DESTROY_SESSION, EXCHANGE_ID. -* DESTROY_SESSION MUST be the final operation in the COMPOUND request. - Nonstandard compound limitations: * No support for a sessions fore channel RPC compound that requires both a ca_maxrequestsize request and a ca_maxresponsesize reply, so we may @@ -219,3 +204,5 @@ Nonstandard compound limitations: negotiation. * No more than one IO operation (read, write, readdir) allowed per compound. + +See also http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues. diff --git a/Documentation/filesystems/nfs/nfsroot.txt b/Documentation/filesystems/nfs/nfsroot.txt index 90c71c6..ffdd9d8 100644 --- a/Documentation/filesystems/nfs/nfsroot.txt +++ b/Documentation/filesystems/nfs/nfsroot.txt @@ -226,7 +226,7 @@ They depend on various facilities being available: cdrecord. e.g. - cdrecord dev=ATAPI:1,0,0 arch/i386/boot/image.iso + cdrecord dev=ATAPI:1,0,0 arch/x86/boot/image.iso For more information on isolinux, including how to create bootdisks for prebuilt kernels, see http://syslinux.zytor.com/ diff --git a/Documentation/filesystems/pohmelfs/design_notes.txt b/Documentation/filesystems/pohmelfs/design_notes.txt index dcf8335..8aef9133 100644 --- a/Documentation/filesystems/pohmelfs/design_notes.txt +++ b/Documentation/filesystems/pohmelfs/design_notes.txt @@ -58,8 +58,9 @@ data transfers. POHMELFS clients operate with a working set of servers and are capable of balancing read-only operations (like lookups or directory listings) between them according to IO priorities. Administrators can add or remove servers from the set at run-time via special commands (described -in Documentation/pohmelfs/info.txt file). Writes are replicated to all servers, which are connected -with write permission turned on. IO priority and permissions can be changed in run-time. +in Documentation/filesystems/pohmelfs/info.txt file). Writes are replicated to all servers, which +are connected with write permission turned on. IO priority and permissions can be changed in +run-time. POHMELFS is capable of full data channel encryption and/or strong crypto hashing. One can select any kernel supported cipher, encryption mode, hash type and operation mode diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index 6e29954..b4a3d76 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -400,10 +400,32 @@ a file off. -- [mandatory] - --- -[mandatory] ->get_sb() is gone. Switch to use of ->mount(). Typically it's just a matter of switching from calling get_sb_... to mount_... and changing the function type. If you were doing it manually, just switch from setting ->mnt_root to some pointer to returning that pointer. On errors return ERR_PTR(...). + +-- +[mandatory] + ->permission() and generic_permission()have lost flags +argument; instead of passing IPERM_FLAG_RCU we add MAY_NOT_BLOCK into mask. + generic_permission() has also lost the check_acl argument; ACL checking +has been taken to VFS and filesystems need to provide a non-NULL ->i_op->get_acl +to read an ACL from disk. + +-- +[mandatory] + If you implement your own ->llseek() you must handle SEEK_HOLE and +SEEK_DATA. You can hanle this by returning -EINVAL, but it would be nicer to +support it in some way. The generic handler assumes that the entire file is +data and there is a virtual hole at the end of the file. So if the provided +offset is less than i_size and SEEK_DATA is specified, return the same offset. +If the above is true for the offset and you are given SEEK_HOLE, return the end +of the file. If the offset is i_size or greater return -ENXIO in either case. + +[mandatory] + If you have your own ->fsync() you must make sure to call +filemap_write_and_wait_range() so that all dirty pages are synced out properly. +You must also keep in mind that ->fsync() is not called with i_mutex held +anymore, so if you require i_mutex locking you must make sure to take it and +release it yourself. diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index db3b1ab..404a097 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1263,7 +1263,7 @@ review the kernel documentation in the directory /usr/src/linux/Documentation. This chapter is heavily based on the documentation included in the pre 2.2 kernels, and became part of it in version 2.2.1 of the Linux kernel. -Please see: Documentation/sysctls/ directory for descriptions of these +Please see: Documentation/sysctl/ directory for descriptions of these entries. ------------------------------------------------------------------------------ @@ -1293,8 +1293,8 @@ may allocate from based on an estimation of its current memory and swap use. For example, if a task is using all allowed memory, its badness score will be 1000. If it is using half of its allowed memory, its score will be 500. -There is an additional factor included in the badness score: root -processes are given 3% extra memory over other tasks. +There is an additional factor included in the badness score: the current memory +and swap usage is discounted by 3% for root processes. The amount of "allowed" memory depends on the context in which the oom killer was called. If it is due to the memory assigned to the allocating task's cpuset diff --git a/Documentation/filesystems/squashfs.txt b/Documentation/filesystems/squashfs.txt index d4d4146..7db3ebd 100644 --- a/Documentation/filesystems/squashfs.txt +++ b/Documentation/filesystems/squashfs.txt @@ -2,7 +2,7 @@ SQUASHFS 4.0 FILESYSTEM ======================= Squashfs is a compressed read-only filesystem for Linux. -It uses zlib/lzo compression to compress files, inodes and directories. +It uses zlib/lzo/xz compression to compress 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 1Mbytes (default block size 128K). @@ -55,6 +55,8 @@ create populated squashfs filesystems. This and other squashfs utilities can be obtained from http://www.squashfs.org. Usage instructions can be obtained from this site also. +The squashfs-tools development tree is now located on kernel.org + git://git.kernel.org/pub/scm/fs/squashfs/squashfs-tools.git 3. SQUASHFS FILESYSTEM DESIGN ----------------------------- diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt index 597f728..07235ca 100644 --- a/Documentation/filesystems/sysfs.txt +++ b/Documentation/filesystems/sysfs.txt @@ -4,7 +4,7 @@ sysfs - _The_ filesystem for exporting kernel objects. Patrick Mochel <mochel@osdl.org> Mike Murphy <mamurph@cs.clemson.edu> -Revised: 15 July 2010 +Revised: 16 August 2011 Original: 10 January 2003 @@ -370,3 +370,11 @@ int driver_create_file(struct device_driver *, const struct driver_attribute *); void driver_remove_file(struct device_driver *, const struct driver_attribute *); +Documentation +~~~~~~~~~~~~~ + +The sysfs directory structure and the attributes in each directory define an +ABI between the kernel and user space. As for any ABI, it is important that +this ABI is stable and properly documented. All new sysfs attributes must be +documented in Documentation/ABI. See also Documentation/ABI/README for more +information. diff --git a/Documentation/filesystems/ubifs.txt b/Documentation/filesystems/ubifs.txt index 8e4fab6..a0a61d2 100644 --- a/Documentation/filesystems/ubifs.txt +++ b/Documentation/filesystems/ubifs.txt @@ -111,34 +111,6 @@ The following is an example of the kernel boot arguments to attach mtd0 to UBI and mount volume "rootfs": ubi.mtd=0 root=ubi0:rootfs rootfstype=ubifs - -Module Parameters for Debugging -=============================== - -When UBIFS has been compiled with debugging enabled, there are 2 module -parameters that are available to control aspects of testing and debugging. - -debug_chks Selects extra checks that UBIFS can do while running: - - Check Flag value - - General checks 1 - Check Tree Node Cache (TNC) 2 - Check indexing tree size 4 - Check orphan area 8 - Check old indexing tree 16 - Check LEB properties (lprops) 32 - Check leaf nodes and inodes 64 - -debug_tsts Selects a mode of testing, as follows: - - Test mode Flag value - - Failure mode for recovery testing 4 - -For example, set debug_chks to 3 to enable general and TNC checks. - - References ========== diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 88b9f55..43cbd08 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -229,6 +229,8 @@ struct super_operations { ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); + int (*nr_cached_objects)(struct super_block *); + void (*free_cached_objects)(struct super_block *, int); }; All methods are called without any locks being held, unless otherwise @@ -301,6 +303,26 @@ or bottom half). quota_write: called by the VFS to write to filesystem quota file. + nr_cached_objects: called by the sb cache shrinking function for the + filesystem to return the number of freeable cached objects it contains. + Optional. + + free_cache_objects: called by the sb cache shrinking function for the + filesystem to scan the number of objects indicated to try to free them. + Optional, but any filesystem implementing this method needs to also + implement ->nr_cached_objects for it to be called correctly. + + We can't do anything with any errors that the filesystem might + encountered, hence the void return type. This will never be called if + the VM is trying to reclaim under GFP_NOFS conditions, hence this + method does not need to handle that situation itself. + + Implementations must include conditional reschedule calls inside any + scanning loop that is done. This allows the VFS to determine + appropriate scan batch sizes without having to worry about whether + implementations will cause holdoff problems due to large scan batch + sizes. + Whoever sets up the inode is responsible for filling in the "i_op" field. This is a pointer to a "struct inode_operations" which describes the methods that can be performed on individual inodes. @@ -333,8 +355,8 @@ struct inode_operations { void * (*follow_link) (struct dentry *, struct nameidata *); void (*put_link) (struct dentry *, struct nameidata *, void *); void (*truncate) (struct inode *); - int (*permission) (struct inode *, int, unsigned int); - int (*check_acl)(struct inode *, int, unsigned int); + int (*permission) (struct inode *, int); + int (*get_acl)(struct inode *, int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); @@ -423,7 +445,7 @@ otherwise noted. permission: called by the VFS to check for access rights on a POSIX-like filesystem. - May be called in rcu-walk mode (flags & IPERM_FLAG_RCU). If in rcu-walk + May be called in rcu-walk mode (mask & MAY_NOT_BLOCK). If in rcu-walk mode, the filesystem must check the permission without blocking or storing to the inode. @@ -755,7 +777,7 @@ struct file_operations { int (*open) (struct inode *, struct file *); int (*flush) (struct file *); int (*release) (struct inode *, struct file *); - int (*fsync) (struct file *, int datasync); + int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); @@ -1031,9 +1053,6 @@ manipulate dentries: and the dentry is returned. The caller must use dput() to free the dentry when it finishes using it. -For further information on dentry locking, please refer to the document -Documentation/filesystems/dentry-locking.txt. - Mount Options ============= |