diff options
Diffstat (limited to 'Documentation/filesystems')
-rw-r--r-- | Documentation/filesystems/9p.rst (renamed from Documentation/filesystems/9p.txt) | 124 | ||||
-rw-r--r-- | Documentation/filesystems/adfs.rst (renamed from Documentation/filesystems/adfs.txt) | 29 | ||||
-rw-r--r-- | Documentation/filesystems/affs.rst (renamed from Documentation/filesystems/affs.txt) | 62 | ||||
-rw-r--r-- | Documentation/filesystems/afs.rst (renamed from Documentation/filesystems/afs.txt) | 73 | ||||
-rw-r--r-- | Documentation/filesystems/autofs-mount-control.rst (renamed from Documentation/filesystems/autofs-mount-control.txt) | 108 | ||||
-rw-r--r-- | Documentation/filesystems/befs.rst (renamed from Documentation/filesystems/befs.txt) | 59 | ||||
-rw-r--r-- | Documentation/filesystems/bfs.rst (renamed from Documentation/filesystems/bfs.txt) | 37 | ||||
-rw-r--r-- | Documentation/filesystems/btrfs.rst (renamed from Documentation/filesystems/btrfs.txt) | 3 | ||||
-rw-r--r-- | Documentation/filesystems/ceph.rst (renamed from Documentation/filesystems/ceph.txt) | 32 | ||||
-rw-r--r-- | Documentation/filesystems/cifs/cifsroot.txt | 2 | ||||
-rw-r--r-- | Documentation/filesystems/cramfs.rst (renamed from Documentation/filesystems/cramfs.txt) | 19 | ||||
-rw-r--r-- | Documentation/filesystems/debugfs.rst (renamed from Documentation/filesystems/debugfs.txt) | 66 | ||||
-rw-r--r-- | Documentation/filesystems/dlmfs.rst (renamed from Documentation/filesystems/dlmfs.txt) | 28 | ||||
-rw-r--r-- | Documentation/filesystems/ecryptfs.rst (renamed from Documentation/filesystems/ecryptfs.txt) | 51 | ||||
-rw-r--r-- | Documentation/filesystems/efivarfs.rst (renamed from Documentation/filesystems/efivarfs.txt) | 5 | ||||
-rw-r--r-- | Documentation/filesystems/erofs.rst (renamed from Documentation/filesystems/erofs.txt) | 177 | ||||
-rw-r--r-- | Documentation/filesystems/ext2.rst (renamed from Documentation/filesystems/ext2.txt) | 41 | ||||
-rw-r--r-- | Documentation/filesystems/ext3.rst (renamed from Documentation/filesystems/ext3.txt) | 2 | ||||
-rw-r--r-- | Documentation/filesystems/f2fs.rst (renamed from Documentation/filesystems/f2fs.txt) | 258 | ||||
-rw-r--r-- | Documentation/filesystems/fiemap.txt | 6 | ||||
-rw-r--r-- | Documentation/filesystems/fscrypt.rst | 11 | ||||
-rw-r--r-- | Documentation/filesystems/fuse.rst | 5 | ||||
-rw-r--r-- | Documentation/filesystems/gfs2-uevents.rst (renamed from Documentation/filesystems/gfs2-uevents.txt) | 20 | ||||
-rw-r--r-- | Documentation/filesystems/gfs2.rst (renamed from Documentation/filesystems/gfs2.txt) | 20 | ||||
-rw-r--r-- | Documentation/filesystems/hfs.rst (renamed from Documentation/filesystems/hfs.txt) | 23 | ||||
-rw-r--r-- | Documentation/filesystems/hfsplus.rst (renamed from Documentation/filesystems/hfsplus.txt) | 2 | ||||
-rw-r--r-- | Documentation/filesystems/hpfs.rst (renamed from Documentation/filesystems/hpfs.txt) | 239 | ||||
-rw-r--r-- | Documentation/filesystems/index.rst | 47 | ||||
-rw-r--r-- | Documentation/filesystems/inotify.rst (renamed from Documentation/filesystems/inotify.txt) | 33 | ||||
-rw-r--r-- | Documentation/filesystems/isofs.rst | 64 | ||||
-rw-r--r-- | Documentation/filesystems/isofs.txt | 48 | ||||
-rw-r--r-- | Documentation/filesystems/nfs/index.rst | 13 | ||||
-rw-r--r-- | Documentation/filesystems/nfs/knfsd-stats.rst (renamed from Documentation/filesystems/nfs/knfsd-stats.txt) | 17 | ||||
-rw-r--r-- | Documentation/filesystems/nfs/nfs41-server.rst | 256 | ||||
-rw-r--r-- | Documentation/filesystems/nfs/nfs41-server.txt | 173 | ||||
-rw-r--r-- | Documentation/filesystems/nfs/pnfs.rst (renamed from Documentation/filesystems/nfs/pnfs.txt) | 25 | ||||
-rw-r--r-- | Documentation/filesystems/nfs/rpc-cache.rst (renamed from Documentation/filesystems/nfs/rpc-cache.txt) | 136 | ||||
-rw-r--r-- | Documentation/filesystems/nfs/rpc-server-gss.rst (renamed from Documentation/filesystems/nfs/rpc-server-gss.txt) | 19 | ||||
-rw-r--r-- | Documentation/filesystems/nilfs2.rst (renamed from Documentation/filesystems/nilfs2.txt) | 40 | ||||
-rw-r--r-- | Documentation/filesystems/ntfs.rst (renamed from Documentation/filesystems/ntfs.txt) | 145 | ||||
-rw-r--r-- | Documentation/filesystems/ocfs2-online-filecheck.rst (renamed from Documentation/filesystems/ocfs2-online-filecheck.txt) | 45 | ||||
-rw-r--r-- | Documentation/filesystems/ocfs2.rst (renamed from Documentation/filesystems/ocfs2.txt) | 31 | ||||
-rw-r--r-- | Documentation/filesystems/omfs.rst | 112 | ||||
-rw-r--r-- | Documentation/filesystems/omfs.txt | 106 | ||||
-rw-r--r-- | Documentation/filesystems/orangefs.rst (renamed from Documentation/filesystems/orangefs.txt) | 209 | ||||
-rw-r--r-- | Documentation/filesystems/overlayfs.rst | 82 | ||||
-rw-r--r-- | Documentation/filesystems/path-lookup.rst | 7 | ||||
-rw-r--r-- | Documentation/filesystems/proc.rst (renamed from Documentation/filesystems/proc.txt) | 1544 | ||||
-rw-r--r-- | Documentation/filesystems/qnx6.rst (renamed from Documentation/filesystems/qnx6.txt) | 24 | ||||
-rw-r--r-- | Documentation/filesystems/ramfs-rootfs-initramfs.rst (renamed from Documentation/filesystems/ramfs-rootfs-initramfs.txt) | 54 | ||||
-rw-r--r-- | Documentation/filesystems/relay.rst (renamed from Documentation/filesystems/relay.txt) | 139 | ||||
-rw-r--r-- | Documentation/filesystems/romfs.rst (renamed from Documentation/filesystems/romfs.txt) | 42 | ||||
-rw-r--r-- | Documentation/filesystems/squashfs.rst (renamed from Documentation/filesystems/squashfs.txt) | 60 | ||||
-rw-r--r-- | Documentation/filesystems/sysfs.rst (renamed from Documentation/filesystems/sysfs.txt) | 324 | ||||
-rw-r--r-- | Documentation/filesystems/sysv-fs.rst (renamed from Documentation/filesystems/sysv-fs.txt) | 153 | ||||
-rw-r--r-- | Documentation/filesystems/tmpfs.rst (renamed from Documentation/filesystems/tmpfs.txt) | 44 | ||||
-rw-r--r-- | Documentation/filesystems/ubifs-authentication.rst | 10 | ||||
-rw-r--r-- | Documentation/filesystems/ubifs.rst (renamed from Documentation/filesystems/ubifs.txt) | 25 | ||||
-rw-r--r-- | Documentation/filesystems/udf.rst (renamed from Documentation/filesystems/udf.txt) | 21 | ||||
-rw-r--r-- | Documentation/filesystems/virtiofs.rst | 2 | ||||
-rw-r--r-- | Documentation/filesystems/zonefs.rst (renamed from Documentation/filesystems/zonefs.txt) | 108 |
61 files changed, 3296 insertions, 2364 deletions
diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.rst index fec7144e817c..671fef39a802 100644 --- a/Documentation/filesystems/9p.txt +++ b/Documentation/filesystems/9p.rst @@ -1,7 +1,10 @@ - v9fs: Plan 9 Resource Sharing for Linux - ======================================= +.. SPDX-License-Identifier: GPL-2.0 -ABOUT +======================================= +v9fs: Plan 9 Resource Sharing for Linux +======================================= + +About ===== v9fs is a Unix implementation of the Plan 9 9p remote filesystem protocol. @@ -14,32 +17,34 @@ and Maya Gokhale. Additional development by Greg Watson The best detailed explanation of the Linux implementation and applications of the 9p client is available in the form of a USENIX paper: + http://www.usenix.org/events/usenix05/tech/freenix/hensbergen.html Other applications are described in the following papers: + * XCPU & Clustering - http://xcpu.org/papers/xcpu-talk.pdf + http://xcpu.org/papers/xcpu-talk.pdf * KVMFS: control file system for KVM - http://xcpu.org/papers/kvmfs.pdf + http://xcpu.org/papers/kvmfs.pdf * CellFS: A New Programming Model for the Cell BE - http://xcpu.org/papers/cellfs-talk.pdf + http://xcpu.org/papers/cellfs-talk.pdf * PROSE I/O: Using 9p to enable Application Partitions - http://plan9.escet.urjc.es/iwp9/cready/PROSE_iwp9_2006.pdf + http://plan9.escet.urjc.es/iwp9/cready/PROSE_iwp9_2006.pdf * VirtFS: A Virtualization Aware File System pass-through - http://goo.gl/3WPDg + http://goo.gl/3WPDg -USAGE +Usage ===== -For remote file server: +For remote file server:: mount -t 9p 10.10.1.2 /mnt/9 -For Plan 9 From User Space applications (http://swtch.com/plan9) +For Plan 9 From User Space applications (http://swtch.com/plan9):: mount -t 9p `namespace`/acme /mnt/9 -o trans=unix,uname=$USER -For server running on QEMU host with virtio transport: +For server running on QEMU host with virtio transport:: mount -t 9p -o trans=virtio <mount_tag> /mnt/9 @@ -48,18 +53,22 @@ mount points. Each 9P export is seen by the client as a virtio device with an associated "mount_tag" property. Available mount tags can be seen by reading /sys/bus/virtio/drivers/9pnet_virtio/virtio<n>/mount_tag files. -OPTIONS +Options ======= + ============= =============================================================== trans=name select an alternative transport. Valid options are currently: - unix - specifying a named pipe mount point - tcp - specifying a normal TCP/IP connection - fd - used passed file descriptors for connection - (see rfdno and wfdno) - virtio - connect to the next virtio channel available - (from QEMU with trans_virtio module) - rdma - connect to a specified RDMA channel + + ======== ============================================ + unix specifying a named pipe mount point + tcp specifying a normal TCP/IP connection + fd used passed file descriptors for connection + (see rfdno and wfdno) + virtio connect to the next virtio channel available + (from QEMU with trans_virtio module) + rdma connect to a specified RDMA channel + ======== ============================================ uname=name user name to attempt mount as on the remote server. The server may override or ignore this value. Certain user @@ -69,28 +78,36 @@ OPTIONS offering several exported file systems. cache=mode specifies a caching policy. By default, no caches are used. - none = default no cache policy, metadata and data + + none + default no cache policy, metadata and data alike are synchronous. - loose = no attempts are made at consistency, + loose + no attempts are made at consistency, intended for exclusive, read-only mounts - fscache = use FS-Cache for a persistent, read-only + fscache + use FS-Cache for a persistent, read-only cache backend. - mmap = minimal cache that is only used for read-write + mmap + minimal cache that is only used for read-write mmap. Northing else is cached, like cache=none debug=n specifies debug level. The debug level is a bitmask. - 0x01 = display verbose error messages - 0x02 = developer debug (DEBUG_CURRENT) - 0x04 = display 9p trace - 0x08 = display VFS trace - 0x10 = display Marshalling debug - 0x20 = display RPC debug - 0x40 = display transport debug - 0x80 = display allocation debug - 0x100 = display protocol message debug - 0x200 = display Fid debug - 0x400 = display packet debug - 0x800 = display fscache tracing debug + + ===== ================================ + 0x01 display verbose error messages + 0x02 developer debug (DEBUG_CURRENT) + 0x04 display 9p trace + 0x08 display VFS trace + 0x10 display Marshalling debug + 0x20 display RPC debug + 0x40 display transport debug + 0x80 display allocation debug + 0x100 display protocol message debug + 0x200 display Fid debug + 0x400 display packet debug + 0x800 display fscache tracing debug + ===== ================================ rfdno=n the file descriptor for reading with trans=fd @@ -103,9 +120,12 @@ OPTIONS noextend force legacy mode (no 9p2000.u or 9p2000.L semantics) version=name Select 9P protocol version. Valid options are: - 9p2000 - Legacy mode (same as noextend) - 9p2000.u - Use 9P2000.u protocol - 9p2000.L - Use 9P2000.L protocol + + ======== ============================== + 9p2000 Legacy mode (same as noextend) + 9p2000.u Use 9P2000.u protocol + 9p2000.L Use 9P2000.L protocol + ======== ============================== dfltuid attempt to mount as a particular uid @@ -118,22 +138,37 @@ OPTIONS hosts. This functionality will be expanded in later versions. access there are four access modes. - user = if a user tries to access a file on v9fs + user + if a user tries to access a file on v9fs filesystem for the first time, v9fs sends an attach command (Tattach) for that user. This is the default mode. - <uid> = allows only user with uid=<uid> to access + <uid> + allows only user with uid=<uid> to access the files on the mounted filesystem - any = v9fs does single attach and performs all + any + v9fs does single attach and performs all operations as one user - client = ACL based access check on the 9p client + clien + ACL based access check on the 9p client side for access validation cachetag cache tag to use the specified persistent cache. cache tags for existing cache sessions can be listed at /sys/fs/9p/caches. (applies only to cache=fscache) + ============= =============================================================== + +Behavior +======== + +This section aims at describing 9p 'quirks' that can be different +from a local filesystem behaviors. -RESOURCES + - Setting O_NONBLOCK on a file will make client reads return as early + as the server returns some data instead of trying to fill the read + buffer with the requested amount of bytes or end of file is reached. + +Resources ========= Protocol specifications are maintained on github: @@ -158,4 +193,3 @@ http://plan9.bell-labs.com/plan9 For information on Plan 9 from User Space (Plan 9 applications and libraries ported to Linux/BSD/OSX/etc) check out http://swtch.com/plan9 - diff --git a/Documentation/filesystems/adfs.txt b/Documentation/filesystems/adfs.rst index 0baa8e8c1fc1..5b22cae38e5e 100644 --- a/Documentation/filesystems/adfs.txt +++ b/Documentation/filesystems/adfs.rst @@ -1,3 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=============================== +Acorn Disc Filing System - ADFS +=============================== + Filesystems supported by ADFS ----------------------------- @@ -25,6 +31,7 @@ directory updates, specifically updating the access mode and timestamp. Mount options for ADFS ---------------------- + ============ ====================================================== uid=nnn All files in the partition will be owned by user id nnn. Default 0 (root). gid=nnn All files in the partition will be in group @@ -36,22 +43,23 @@ Mount options for ADFS ftsuffix=n When ftsuffix=0, no file type suffix will be applied. When ftsuffix=1, a hexadecimal suffix corresponding to the RISC OS file type will be added. Default 0. + ============ ====================================================== Mapping of ADFS permissions to Linux permissions ------------------------------------------------ ADFS permissions consist of the following: - Owner read - Owner write - Other read - Other write + - Owner read + - Owner write + - Other read + - Other write (In older versions, an 'execute' permission did exist, but this - does not hold the same meaning as the Linux 'execute' permission - and is now obsolete). + does not hold the same meaning as the Linux 'execute' permission + and is now obsolete). - The mapping is performed as follows: + The mapping is performed as follows:: Owner read -> -r--r--r-- Owner write -> --w--w---w @@ -66,17 +74,18 @@ Mapping of ADFS permissions to Linux permissions Possible other mode permissions -> ----rwxrwx Hence, with the default masks, if a file is owner read/write, and - not a UnixExec filetype, then the permissions will be: + not a UnixExec filetype, then the permissions will be:: -rw------- However, if the masks were ownmask=0770,othmask=0007, then this would - be modified to: + be modified to:: + -rw-rw---- There is no restriction on what you can do with these masks. You may wish that either read bits give read access to the file for all, but - keep the default write protection (ownmask=0755,othmask=0577): + keep the default write protection (ownmask=0755,othmask=0577):: -rw-r--r-- diff --git a/Documentation/filesystems/affs.txt b/Documentation/filesystems/affs.rst index 71b63c2b9841..7f1a40dce6d3 100644 --- a/Documentation/filesystems/affs.txt +++ b/Documentation/filesystems/affs.rst @@ -1,9 +1,13 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================= Overview of Amiga Filesystems ============================= Not all varieties of the Amiga filesystems are supported for reading and writing. The Amiga currently knows six different filesystems: +============== =============================================================== DOS\0 The old or original filesystem, not really suited for hard disks and normally not used on them, either. Supported read/write. @@ -23,6 +27,7 @@ DOS\4 The original filesystem with directory cache. The directory sense on hard disks. Supported read only. DOS\5 The Fast File System with directory cache. Supported read only. +============== =============================================================== All of the above filesystems allow block sizes from 512 to 32K bytes. Supported block sizes are: 512, 1024, 2048 and 4096 bytes. Larger blocks @@ -36,14 +41,18 @@ are supported, too. Mount options for the AFFS ========================== -protect If this option is set, the protection bits cannot be altered. +protect + If this option is set, the protection bits cannot be altered. -setuid[=uid] This sets the owner of all files and directories in the file +setuid[=uid] + This sets the owner of all files and directories in the file system to uid or the uid of the current user, respectively. -setgid[=gid] Same as above, but for gid. +setgid[=gid] + Same as above, but for gid. -mode=mode Sets the mode flags to the given (octal) value, regardless +mode=mode + Sets the mode flags to the given (octal) value, regardless of the original permissions. Directories will get an x permission if the corresponding r bit is set. This is useful since most of the plain AmigaOS files @@ -53,33 +62,41 @@ nofilenametruncate The file system will return an error when filename exceeds standard maximum filename length (30 characters). -reserved=num Sets the number of reserved blocks at the start of the +reserved=num + Sets the number of reserved blocks at the start of the partition to num. You should never need this option. Default is 2. -root=block Sets the block number of the root block. This should never +root=block + Sets the block number of the root block. This should never be necessary. -bs=blksize Sets the blocksize to blksize. Valid block sizes are 512, +bs=blksize + Sets the blocksize to blksize. Valid block sizes are 512, 1024, 2048 and 4096. Like the root option, this should never be necessary, as the affs can figure it out itself. -quiet The file system will not return an error for disallowed +quiet + The file system will not return an error for disallowed mode changes. -verbose The volume name, file system type and block size will +verbose + The volume name, file system type and block size will be written to the syslog when the filesystem is mounted. -mufs The filesystem is really a muFS, also it doesn't +mufs + The filesystem is really a muFS, also it doesn't identify itself as one. This option is necessary if the filesystem wasn't formatted as muFS, but is used as one. -prefix=path Path will be prefixed to every absolute path name of +prefix=path + Path will be prefixed to every absolute path name of symbolic links on an AFFS partition. Default = "/". (See below.) -volume=name When symbolic links with an absolute path are created +volume=name + When symbolic links with an absolute path are created on an AFFS partition, name will be prepended as the volume name. Default = "" (empty string). (See below.) @@ -119,7 +136,7 @@ The Linux rwxrwxrwx file mode is handled as follows: - All other flags (suid, sgid, ...) are ignored and will not be retained. - + Newly created files and directories will get the user and group ID of the current user and a mode according to the umask. @@ -148,11 +165,13 @@ might be "User", "WB" and "Graphics", the mount points /amiga/User, Examples ======== -Command line: +Command line:: + mount Archive/Amiga/Workbench3.1.adf /mnt -t affs -o loop,verbose mount /dev/sda3 /Amiga -t affs -/etc/fstab entry: +/etc/fstab entry:: + /dev/sdb5 /amiga/Workbench affs noauto,user,exec,verbose 0 0 IMPORTANT NOTE @@ -170,7 +189,8 @@ before booting Windows! If the damage is already done, the following should fix the RDB (where <disk> is the device name). -DO AT YOUR OWN RISK: + +DO AT YOUR OWN RISK:: dd if=/dev/<disk> of=rdb.tmp count=1 cp rdb.tmp rdb.fixed @@ -189,10 +209,14 @@ By default, filenames are truncated to 30 characters without warning. 'nofilenametruncate' mount option can change that behavior. Case is ignored by the affs in filename matching, but Linux shells -do care about the case. Example (with /wb being an affs mounted fs): +do care about the case. Example (with /wb being an affs mounted fs):: + rm /wb/WRONGCASE -will remove /mnt/wrongcase, but + +will remove /mnt/wrongcase, but:: + rm /wb/WR* + will not since the names are matched by the shell. The block allocation is designed for hard disk partitions. If more @@ -219,4 +243,4 @@ due to an incompatibility with the Amiga floppy controller. If you are interested in an Amiga Emulator for Linux, look at -http://web.archive.org/web/*/http://www.freiburg.linux.de/~uae/ +http://web.archive.org/web/%2E/http://www.freiburg.linux.de/~uae/ diff --git a/Documentation/filesystems/afs.txt b/Documentation/filesystems/afs.rst index 8c6ea7b41048..c4ec39a5966e 100644 --- a/Documentation/filesystems/afs.txt +++ b/Documentation/filesystems/afs.rst @@ -1,8 +1,10 @@ - ==================== - kAFS: AFS FILESYSTEM - ==================== +.. SPDX-License-Identifier: GPL-2.0 -Contents: +==================== +kAFS: AFS FILESYSTEM +==================== + +.. Contents: - Overview. - Usage. @@ -14,8 +16,7 @@ Contents: - The @sys substitution. -======== -OVERVIEW +Overview ======== This filesystem provides a fairly simple secure AFS filesystem driver. It is @@ -35,35 +36,33 @@ It does not yet support the following AFS features: (*) pioctl() system call. -=========== -COMPILATION +Compilation =========== The filesystem should be enabled by turning on the kernel configuration -options: +options:: CONFIG_AF_RXRPC - The RxRPC protocol transport CONFIG_RXKAD - The RxRPC Kerberos security handler CONFIG_AFS - The AFS filesystem -Additionally, the following can be turned on to aid debugging: +Additionally, the following can be turned on to aid debugging:: CONFIG_AF_RXRPC_DEBUG - Permit AF_RXRPC debugging to be enabled CONFIG_AFS_DEBUG - Permit AFS debugging to be enabled They permit the debugging messages to be turned on dynamically by manipulating -the masks in the following files: +the masks in the following files:: /sys/module/af_rxrpc/parameters/debug /sys/module/kafs/parameters/debug -===== -USAGE +Usage ===== When inserting the driver modules the root cell must be specified along with a -list of volume location server IP addresses: +list of volume location server IP addresses:: modprobe rxrpc modprobe kafs rootcell=cambridge.redhat.com:172.16.18.73:172.16.18.91 @@ -77,14 +76,14 @@ The second module is the kerberos RxRPC security driver, and the third module is the actual filesystem driver for the AFS filesystem. Once the module has been loaded, more modules can be added by the following -procedure: +procedure:: echo add grand.central.org 18.9.48.14:128.2.203.61:130.237.48.87 >/proc/fs/afs/cells Where the parameters to the "add" command are the name of a cell and a list of volume location servers within that cell, with the latter separated by colons. -Filesystems can be mounted anywhere by commands similar to the following: +Filesystems can be mounted anywhere by commands similar to the following:: mount -t afs "%cambridge.redhat.com:root.afs." /afs mount -t afs "#cambridge.redhat.com:root.cell." /afs/cambridge @@ -104,8 +103,7 @@ named volume will be looked up in the cell specified during modprobe. Additional cells can be added through /proc (see later section). -=========== -MOUNTPOINTS +Mountpoints =========== AFS has a concept of mountpoints. In AFS terms, these are specially formatted @@ -123,42 +121,40 @@ culled first. If all are culled, then the requested volume will also be unmounted, otherwise error EBUSY will be returned. This can be used by the administrator to attempt to unmount the whole AFS tree -mounted on /afs in one go by doing: +mounted on /afs in one go by doing:: umount /afs -============ -DYNAMIC ROOT +Dynamic Root ============ A mount option is available to create a serverless mount that is only usable -for dynamic lookup. Creating such a mount can be done by, for example: +for dynamic lookup. Creating such a mount can be done by, for example:: mount -t afs none /afs -o dyn This creates a mount that just has an empty directory at the root. Attempting to look up a name in this directory will cause a mountpoint to be created that -looks up a cell of the same name, for example: +looks up a cell of the same name, for example:: ls /afs/grand.central.org/ -=============== -PROC FILESYSTEM +Proc Filesystem =============== The AFS modules creates a "/proc/fs/afs/" directory and populates it: (*) A "cells" file that lists cells currently known to the afs module and - their usage counts: + their usage counts:: [root@andromeda ~]# cat /proc/fs/afs/cells USE NAME 3 cambridge.redhat.com (*) A directory per cell that contains files that list volume location - servers, volumes, and active servers known within that cell. + servers, volumes, and active servers known within that cell:: [root@andromeda ~]# cat /proc/fs/afs/cambridge.redhat.com/servers USE ADDR STATE @@ -171,8 +167,7 @@ The AFS modules creates a "/proc/fs/afs/" directory and populates it: 1 Val 20000000 20000001 20000002 root.afs -================= -THE CELL DATABASE +The Cell Database ================= The filesystem maintains an internal database of all the cells it knows and the @@ -181,7 +176,7 @@ the system belongs is added to the database when modprobe is performed by the "rootcell=" argument or, if compiled in, using a "kafs.rootcell=" argument on the kernel command line. -Further cells can be added by commands similar to the following: +Further cells can be added by commands similar to the following:: echo add CELLNAME VLADDR[:VLADDR][:VLADDR]... >/proc/fs/afs/cells echo add grand.central.org 18.9.48.14:128.2.203.61:130.237.48.87 >/proc/fs/afs/cells @@ -189,8 +184,7 @@ Further cells can be added by commands similar to the following: No other cell database operations are available at this time. -======== -SECURITY +Security ======== Secure operations are initiated by acquiring a key using the klog program. A @@ -198,17 +192,17 @@ very primitive klog program is available at: http://people.redhat.com/~dhowells/rxrpc/klog.c -This should be compiled by: +This should be compiled by:: make klog LDLIBS="-lcrypto -lcrypt -lkrb4 -lkeyutils" -And then run as: +And then run as:: ./klog Assuming it's successful, this adds a key of type RxRPC, named for the service and cell, eg: "afs@<cellname>". This can be viewed with the keyctl program or -by cat'ing /proc/keys: +by cat'ing /proc/keys:: [root@andromeda ~]# keyctl show Session Keyring @@ -232,20 +226,19 @@ socket), then the operations on the file will be made with key that was used to open the file. -===================== -THE @SYS SUBSTITUTION +The @sys Substitution ===================== The list of up to 16 @sys substitutions for the current network namespace can -be configured by writing a list to /proc/fs/afs/sysname: +be configured by writing a list to /proc/fs/afs/sysname:: [root@andromeda ~]# echo foo amd64_linux_26 >/proc/fs/afs/sysname -or cleared entirely by writing an empty list: +or cleared entirely by writing an empty list:: [root@andromeda ~]# echo >/proc/fs/afs/sysname -The current list for current network namespace can be retrieved by: +The current list for current network namespace can be retrieved by:: [root@andromeda ~]# cat /proc/fs/afs/sysname foo diff --git a/Documentation/filesystems/autofs-mount-control.txt b/Documentation/filesystems/autofs-mount-control.rst index acc02fc57993..2903aed92316 100644 --- a/Documentation/filesystems/autofs-mount-control.txt +++ b/Documentation/filesystems/autofs-mount-control.rst @@ -1,4 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 +==================================================================== Miscellaneous Device control operations for the autofs kernel module ==================================================================== @@ -36,24 +38,24 @@ For example, there are two types of automount maps, direct (in the kernel module source you will see a third type called an offset, which is just a direct mount in disguise) and indirect. -Here is a master map with direct and indirect map entries: +Here is a master map with direct and indirect map entries:: -/- /etc/auto.direct -/test /etc/auto.indirect + /- /etc/auto.direct + /test /etc/auto.indirect -and the corresponding map files: +and the corresponding map files:: -/etc/auto.direct: + /etc/auto.direct: -/automount/dparse/g6 budgie:/autofs/export1 -/automount/dparse/g1 shark:/autofs/export1 -and so on. + /automount/dparse/g6 budgie:/autofs/export1 + /automount/dparse/g1 shark:/autofs/export1 + and so on. -/etc/auto.indirect: +/etc/auto.indirect:: -g1 shark:/autofs/export1 -g6 budgie:/autofs/export1 -and so on. + g1 shark:/autofs/export1 + g6 budgie:/autofs/export1 + and so on. For the above indirect map an autofs file system is mounted on /test and mounts are triggered for each sub-directory key by the inode lookup @@ -69,23 +71,23 @@ use the follow_link inode operation to trigger the mount. But, each entry in direct and indirect maps can have offsets (making them multi-mount map entries). -For example, an indirect mount map entry could also be: +For example, an indirect mount map entry could also be:: -g1 \ - / shark:/autofs/export5/testing/test \ - /s1 shark:/autofs/export/testing/test/s1 \ - /s2 shark:/autofs/export5/testing/test/s2 \ - /s1/ss1 shark:/autofs/export1 \ - /s2/ss2 shark:/autofs/export2 + g1 \ + / shark:/autofs/export5/testing/test \ + /s1 shark:/autofs/export/testing/test/s1 \ + /s2 shark:/autofs/export5/testing/test/s2 \ + /s1/ss1 shark:/autofs/export1 \ + /s2/ss2 shark:/autofs/export2 -and a similarly a direct mount map entry could also be: +and a similarly a direct mount map entry could also be:: -/automount/dparse/g1 \ - / shark:/autofs/export5/testing/test \ - /s1 shark:/autofs/export/testing/test/s1 \ - /s2 shark:/autofs/export5/testing/test/s2 \ - /s1/ss1 shark:/autofs/export2 \ - /s2/ss2 shark:/autofs/export2 + /automount/dparse/g1 \ + / shark:/autofs/export5/testing/test \ + /s1 shark:/autofs/export/testing/test/s1 \ + /s2 shark:/autofs/export5/testing/test/s2 \ + /s1/ss1 shark:/autofs/export2 \ + /s2/ss2 shark:/autofs/export2 One of the issues with version 4 of autofs was that, when mounting an entry with a large number of offsets, possibly with nesting, we needed @@ -170,32 +172,32 @@ autofs Miscellaneous Device mount control interface The control interface is opening a device node, typically /dev/autofs. All the ioctls use a common structure to pass the needed parameter -information and return operation results: - -struct autofs_dev_ioctl { - __u32 ver_major; - __u32 ver_minor; - __u32 size; /* total size of data passed in - * including this struct */ - __s32 ioctlfd; /* automount command fd */ - - /* Command parameters */ - union { - struct args_protover protover; - struct args_protosubver protosubver; - struct args_openmount openmount; - struct args_ready ready; - struct args_fail fail; - struct args_setpipefd setpipefd; - struct args_timeout timeout; - struct args_requester requester; - struct args_expire expire; - struct args_askumount askumount; - struct args_ismountpoint ismountpoint; - }; - - char path[0]; -}; +information and return operation results:: + + struct autofs_dev_ioctl { + __u32 ver_major; + __u32 ver_minor; + __u32 size; /* total size of data passed in + * including this struct */ + __s32 ioctlfd; /* automount command fd */ + + /* Command parameters */ + union { + struct args_protover protover; + struct args_protosubver protosubver; + struct args_openmount openmount; + struct args_ready ready; + struct args_fail fail; + struct args_setpipefd setpipefd; + struct args_timeout timeout; + struct args_requester requester; + struct args_expire expire; + struct args_askumount askumount; + struct args_ismountpoint ismountpoint; + }; + + char path[0]; + }; The ioctlfd field is a mount point file descriptor of an autofs mount point. It is returned by the open call and is used by all calls except @@ -212,7 +214,7 @@ is used account for the increased structure length when translating the structure sent from user space. This structure can be initialized before setting specific fields by using -the void function call init_autofs_dev_ioctl(struct autofs_dev_ioctl *). +the void function call init_autofs_dev_ioctl(``struct autofs_dev_ioctl *``). All of the ioctls perform a copy of this structure from user space to kernel space and return -EINVAL if the size parameter is smaller than diff --git a/Documentation/filesystems/befs.txt b/Documentation/filesystems/befs.rst index da45e6c842b8..79f9740d76ff 100644 --- a/Documentation/filesystems/befs.txt +++ b/Documentation/filesystems/befs.rst @@ -1,48 +1,54 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================= BeOS filesystem for Linux +========================= Document last updated: Dec 6, 2001 -WARNING +Warning ======= Make sure you understand that this is alpha software. This means that the -implementation is neither complete nor well-tested. +implementation is neither complete nor well-tested. I DISCLAIM ALL RESPONSIBILITY FOR ANY POSSIBLE BAD EFFECTS OF THIS CODE! -LICENSE -===== -This software is covered by the GNU General Public License. +License +======= +This software is covered by the GNU General Public License. See the file COPYING for the complete text of the license. Or the GNU website: <http://www.gnu.org/licenses/licenses.html> -AUTHOR -===== +Author +====== The largest part of the code written by Will Dyson <will_dyson@pobox.com> He has been working on the code since Aug 13, 2001. See the changelog for details. Original Author: Makoto Kato <m_kato@ga2.so-net.ne.jp> + His original code can still be found at: <http://hp.vector.co.jp/authors/VA008030/bfs/> + Does anyone know of a more current email address for Makoto? He doesn't respond to the address given above... This filesystem doesn't have a maintainer. -WHAT IS THIS DRIVER? -================== -This module implements the native filesystem of BeOS http://www.beincorporated.com/ +What is this Driver? +==================== +This module implements the native filesystem of BeOS http://www.beincorporated.com/ for the linux 2.4.1 and later kernels. Currently it is a read-only implementation. Which is it, BFS or BEFS? -================ -Be, Inc said, "BeOS Filesystem is officially called BFS, not BeFS". +========================= +Be, Inc said, "BeOS Filesystem is officially called BFS, not BeFS". But Unixware Boot Filesystem is called bfs, too. And they are already in the kernel. Because of this naming conflict, on Linux the BeOS filesystem is called befs. -HOW TO INSTALL +How to Install ============== step 1. Install the BeFS patch into the source code tree of linux. @@ -54,16 +60,16 @@ is called patch-befs-xxx, you would do the following: patch -p1 < /path/to/patch-befs-xxx if the patching step fails (i.e. there are rejected hunks), you can try to -figure it out yourself (it shouldn't be hard), or mail the maintainer +figure it out yourself (it shouldn't be hard), or mail the maintainer (Will Dyson <will_dyson@pobox.com>) for help. step 2. Configuration & make kernel The linux kernel has many compile-time options. Most of them are beyond the scope of this document. I suggest the Kernel-HOWTO document as a good general -reference on this topic. http://www.linuxdocs.org/HOWTOs/Kernel-HOWTO-4.html +reference on this topic. http://www.linuxdocs.org/HOWTOs/Kernel-HOWTO-4.html -However, to use the BeFS module, you must enable it at configure time. +However, to use the BeFS module, you must enable it at configure time:: cd /foo/bar/linux make menuconfig (or xconfig) @@ -82,35 +88,40 @@ step 3. Install See the kernel howto <http://www.linux.com/howto/Kernel-HOWTO.html> for instructions on this critical step. -USING BFS +Using BFS ========= To use the BeOS filesystem, use filesystem type 'befs'. -ex) +ex:: + mount -t befs /dev/fd0 /beos -MOUNT OPTIONS +Mount Options ============= + +============= =========================================================== uid=nnn All files in the partition will be owned by user id nnn. gid=nnn All files in the partition will be in group nnn. iocharset=xxx Use xxx as the name of the NLS translation table. debug The driver will output debugging information to the syslog. +============= =========================================================== -HOW TO GET LASTEST VERSION +How to Get Lastest Version ========================== The latest version is currently available at: <http://befs-driver.sourceforge.net/> -ANY KNOWN BUGS? -=========== +Any Known Bugs? +=============== As of Jan 20, 2002: - + None -SPECIAL THANKS +Special Thanks ============== Dominic Giampalo ... Writing "Practical file system design with Be filesystem" + Hiroyuki Yamada ... Testing LinuxPPC. diff --git a/Documentation/filesystems/bfs.txt b/Documentation/filesystems/bfs.rst index 843ce91a2e40..ce14b9018807 100644 --- a/Documentation/filesystems/bfs.txt +++ b/Documentation/filesystems/bfs.rst @@ -1,4 +1,7 @@ -BFS FILESYSTEM FOR LINUX +.. SPDX-License-Identifier: GPL-2.0 + +======================== +BFS Filesystem for Linux ======================== The BFS filesystem is used by SCO UnixWare OS for the /stand slice, which @@ -9,22 +12,22 @@ In order to access /stand partition under Linux you obviously need to know the partition number and the kernel must support UnixWare disk slices (CONFIG_UNIXWARE_DISKLABEL config option). However BFS support does not depend on having UnixWare disklabel support because one can also mount -BFS filesystem via loopback: +BFS filesystem via loopback:: -# losetup /dev/loop0 stand.img -# mount -t bfs /dev/loop0 /mnt/stand + # losetup /dev/loop0 stand.img + # mount -t bfs /dev/loop0 /mnt/stand -where stand.img is a file containing the image of BFS filesystem. +where stand.img is a file containing the image of BFS filesystem. When you have finished using it and umounted you need to also deallocate -/dev/loop0 device by: +/dev/loop0 device by:: -# losetup -d /dev/loop0 + # losetup -d /dev/loop0 -You can simplify mounting by just typing: +You can simplify mounting by just typing:: -# mount -t bfs -o loop stand.img /mnt/stand + # mount -t bfs -o loop stand.img /mnt/stand -this will allocate the first available loopback device (and load loop.o +this will allocate the first available loopback device (and load loop.o kernel module if necessary) automatically. If the loopback driver is not loaded automatically, make sure that you have compiled the module and that modprobe is functioning. Beware that umount will not deallocate @@ -33,21 +36,21 @@ that modprobe is functioning. Beware that umount will not deallocate losetup(8). Read losetup(8) manpage for more info. To create the BFS image under UnixWare you need to find out first which -slice contains it. The command prtvtoc(1M) is your friend: +slice contains it. The command prtvtoc(1M) is your friend:: -# prtvtoc /dev/rdsk/c0b0t0d0s0 + # prtvtoc /dev/rdsk/c0b0t0d0s0 (assuming your root disk is on target=0, lun=0, bus=0, controller=0). Then you look for the slice with tag "STAND", which is usually slice 10. With this -information you can use dd(1) to create the BFS image: +information you can use dd(1) to create the BFS image:: -# umount /stand -# dd if=/dev/rdsk/c0b0t0d0sa of=stand.img bs=512 + # umount /stand + # dd if=/dev/rdsk/c0b0t0d0sa of=stand.img bs=512 Just in case, you can verify that you have done the right thing by checking -the magic number: +the magic number:: -# od -Ad -tx4 stand.img | more + # od -Ad -tx4 stand.img | more The first 4 bytes should be 0x1badface. diff --git a/Documentation/filesystems/btrfs.txt b/Documentation/filesystems/btrfs.rst index f9dad22d95ce..d0904f602819 100644 --- a/Documentation/filesystems/btrfs.txt +++ b/Documentation/filesystems/btrfs.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===== BTRFS ===== diff --git a/Documentation/filesystems/ceph.txt b/Documentation/filesystems/ceph.rst index b19b6a03f91c..0aa70750df0f 100644 --- a/Documentation/filesystems/ceph.txt +++ b/Documentation/filesystems/ceph.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================ Ceph Distributed File System ============================ @@ -15,6 +18,7 @@ Basic features include: * Easy deployment: most FS components are userspace daemons Also, + * Flexible snapshots (on any directory) * Recursive accounting (nested files, directories, bytes) @@ -63,7 +67,7 @@ no 'du' or similar recursive scan of the file system is required. Finally, Ceph also allows quotas to be set on any directory in the system. The quota can restrict the number of bytes or the number of files stored beneath that point in the directory hierarchy. Quotas can be set using -extended attributes 'ceph.quota.max_files' and 'ceph.quota.max_bytes', eg: +extended attributes 'ceph.quota.max_files' and 'ceph.quota.max_bytes', eg:: setfattr -n ceph.quota.max_bytes -v 100000000 /some/dir getfattr -n ceph.quota.max_bytes /some/dir @@ -76,7 +80,7 @@ from writing as much data as it needs. Mount Syntax ============ -The basic mount syntax is: +The basic mount syntax is:: # mount -t ceph monip[:port][,monip2[:port]...]:/[subdir] mnt @@ -84,7 +88,7 @@ You only need to specify a single monitor, as the client will get the full list when it connects. (However, if the monitor you specify happens to be down, the mount won't succeed.) The port can be left off if the monitor is using the default. So if the monitor is at -1.2.3.4, +1.2.3.4:: # mount -t ceph 1.2.3.4:/ /mnt/ceph @@ -103,17 +107,17 @@ Mount Options address its connection to the monitor originates from. wsize=X - Specify the maximum write size in bytes. Default: 16 MB. + Specify the maximum write size in bytes. Default: 64 MB. rsize=X - Specify the maximum read size in bytes. Default: 16 MB. + Specify the maximum read size in bytes. Default: 64 MB. rasize=X Specify the maximum readahead size in bytes. Default: 8 MB. mount_timeout=X Specify the timeout value for mount (in seconds), in the case - of a non-responsive Ceph file system. The default is 30 + of a non-responsive Ceph file system. The default is 60 seconds. caps_max=X @@ -163,14 +167,14 @@ Mount Options available modes are "no" and "clean". The default is "no". * no: never attempt to reconnect when client detects that it has been - blacklisted. Operations will generally fail after being blacklisted. + blacklisted. Operations will generally fail after being blacklisted. * clean: client reconnects to the ceph cluster automatically when it - detects that it has been blacklisted. During reconnect, client drops - dirty data/metadata, invalidates page caches and writable file handles. - After reconnect, file locks become stale because the MDS loses track - of them. If an inode contains any stale file locks, read/write on the - inode is not allowed until applications release all stale file locks. + detects that it has been blacklisted. During reconnect, client drops + dirty data/metadata, invalidates page caches and writable file handles. + After reconnect, file locks become stale because the MDS loses track + of them. If an inode contains any stale file locks, read/write on the + inode is not allowed until applications release all stale file locks. More Information ================ @@ -179,8 +183,8 @@ For more information on Ceph, see the home page at https://ceph.com/ The Linux kernel client source tree is available at - https://github.com/ceph/ceph-client.git - git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git + - https://github.com/ceph/ceph-client.git + - git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git and the source for the full system is at https://github.com/ceph/ceph.git diff --git a/Documentation/filesystems/cifs/cifsroot.txt b/Documentation/filesystems/cifs/cifsroot.txt index 0fa1a2c36a40..947b7ec6ce9e 100644 --- a/Documentation/filesystems/cifs/cifsroot.txt +++ b/Documentation/filesystems/cifs/cifsroot.txt @@ -13,7 +13,7 @@ network by utilizing SMB or CIFS protocol. In order to mount, the network stack will also need to be set up by using 'ip=' config option. For more details, see -Documentation/filesystems/nfs/nfsroot.txt. +Documentation/admin-guide/nfs/nfsroot.rst. A CIFS root mount currently requires the use of SMB1+UNIX Extensions which is only supported by the Samba server. SMB1 is the older diff --git a/Documentation/filesystems/cramfs.txt b/Documentation/filesystems/cramfs.rst index 8e19a53d648b..afbdbde98bd2 100644 --- a/Documentation/filesystems/cramfs.txt +++ b/Documentation/filesystems/cramfs.rst @@ -1,12 +1,15 @@ +.. SPDX-License-Identifier: GPL-2.0 - Cramfs - cram a filesystem onto a small ROM +=========================================== +Cramfs - cram a filesystem onto a small ROM +=========================================== -cramfs is designed to be simple and small, and to compress things well. +cramfs is designed to be simple and small, and to compress things well. It uses the zlib routines to compress a file one page at a time, and allows random page access. The meta-data is not compressed, but is expressed in a very terse representation to make it use much less -diskspace than traditional filesystems. +diskspace than traditional filesystems. You can't write to a cramfs filesystem (making it compressible and compact also makes it _very_ hard to update on-the-fly), so you have to @@ -28,9 +31,9 @@ issue. Hard links are supported, but hard linked files will still have a link count of 1 in the cramfs image. -Cramfs directories have no `.' or `..' entries. Directories (like +Cramfs directories have no ``.`` or ``..`` entries. Directories (like every other file on cramfs) always have a link count of 1. (There's -no need to use -noleaf in `find', btw.) +no need to use -noleaf in ``find``, btw.) No timestamps are stored in a cramfs, so these default to the epoch (1970 GMT). Recently-accessed files may have updated timestamps, but @@ -70,9 +73,9 @@ MTD drivers are cfi_cmdset_0001 (Intel/Sharp CFI flash) or physmap (Flash device in physical memory map). MTD partitions based on such devices are fine too. Then that device should be specified with the "mtd:" prefix as the mount device argument. For example, to mount the MTD device named -"fs_partition" on the /mnt directory: +"fs_partition" on the /mnt directory:: -$ mount -t cramfs mtd:fs_partition /mnt + $ mount -t cramfs mtd:fs_partition /mnt To boot a kernel with this as root filesystem, suffice to specify something like "root=mtd:fs_partition" on the kernel command line. @@ -90,6 +93,7 @@ https://github.com/npitre/cramfs-tools For /usr/share/magic -------------------- +===== ======================= ======================= 0 ulelong 0x28cd3d45 Linux cramfs offset 0 >4 ulelong x size %d >8 ulelong x flags 0x%x @@ -110,6 +114,7 @@ For /usr/share/magic >552 ulelong x fsid.blocks %d >556 ulelong x fsid.files %d >560 string >\0 name "%.16s" +===== ======================= ======================= Hacker Notes diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.rst index 55336a47a110..6c032db235a5 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.rst @@ -1,4 +1,11 @@ -Copyright 2009 Jonathan Corbet <corbet@lwn.net> +.. SPDX-License-Identifier: GPL-2.0 +.. include:: <isonum.txt> + +======= +DebugFS +======= + +Copyright |copy| 2009 Jonathan Corbet <corbet@lwn.net> Debugfs exists as a simple way for kernel developers to make information available to user space. Unlike /proc, which is only meant for information @@ -6,11 +13,11 @@ about a process, or sysfs, which has strict one-value-per-file rules, debugfs has no rules at all. Developers can put any information they want there. The debugfs filesystem is also intended to not serve as a stable ABI to user space; in theory, there are no stability constraints placed on -files exported there. The real world is not always so simple, though [1]; +files exported there. The real world is not always so simple, though [1]_; even debugfs interfaces are best designed with the idea that they will need to be maintained forever. -Debugfs is typically mounted with a command like: +Debugfs is typically mounted with a command like:: mount -t debugfs none /sys/kernel/debug @@ -23,7 +30,7 @@ Note that the debugfs API is exported GPL-only to modules. Code using debugfs should include <linux/debugfs.h>. Then, the first order of business will be to create at least one directory to hold a set of -debugfs files: +debugfs files:: struct dentry *debugfs_create_dir(const char *name, struct dentry *parent); @@ -36,7 +43,7 @@ something went wrong. If ERR_PTR(-ENODEV) is returned, that is an indication that the kernel has been built without debugfs support and none of the functions described below will work. -The most general way to create a file within a debugfs directory is with: +The most general way to create a file within a debugfs directory is with:: struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, @@ -53,12 +60,12 @@ ERR_PTR(-ERROR) on error, or ERR_PTR(-ENODEV) if debugfs support is missing. Create a file with an initial size, the following function can be used -instead: +instead:: - struct dentry *debugfs_create_file_size(const char *name, umode_t mode, - struct dentry *parent, void *data, - const struct file_operations *fops, - loff_t file_size); + void debugfs_create_file_size(const char *name, umode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fops, + loff_t file_size); file_size is the initial file size. The other parameters are the same as the function debugfs_create_file. @@ -66,21 +73,21 @@ as the function debugfs_create_file. In a number of cases, the creation of a set of file operations is not actually necessary; the debugfs code provides a number of helper functions for simple situations. Files containing a single integer value can be -created with any of: +created with any of:: void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value); void debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value); - struct dentry *debugfs_create_u32(const char *name, umode_t mode, - struct dentry *parent, u32 *value); + void debugfs_create_u32(const char *name, umode_t mode, + struct dentry *parent, u32 *value); void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value); These files support both reading and writing the given value; if a specific file should not be written to, simply set the mode bits accordingly. The values in these files are in decimal; if hexadecimal is more appropriate, -the following functions can be used instead: +the following functions can be used instead:: void debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value); @@ -94,7 +101,7 @@ the following functions can be used instead: 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 architectures, though, complicating the situation somewhat. There are -functions meant to help out in such special cases: +functions meant to help out in such special cases:: void debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value); @@ -103,7 +110,7 @@ As might be expected, this function will create a debugfs file to represent a variable of type size_t. Similarly, there are helpers for variables of type unsigned long, in decimal -and hexadecimal: +and hexadecimal:: struct dentry *debugfs_create_ulong(const char *name, umode_t mode, struct dentry *parent, @@ -111,7 +118,7 @@ and hexadecimal: void debugfs_create_xul(const char *name, umode_t mode, struct dentry *parent, unsigned long *value); -Boolean values can be placed in debugfs with: +Boolean values can be placed in debugfs with:: struct dentry *debugfs_create_bool(const char *name, umode_t mode, struct dentry *parent, bool *value); @@ -120,7 +127,7 @@ A read on the resulting file will yield either Y (for non-zero values) or N, followed by a newline. If written to, it will accept either upper- or lower-case values, or 1 or 0. Any other input will be silently ignored. -Also, atomic_t values can be placed in debugfs with: +Also, atomic_t values can be placed in debugfs with:: void debugfs_create_atomic_t(const char *name, umode_t mode, struct dentry *parent, atomic_t *value) @@ -129,7 +136,7 @@ A read of this file will get atomic_t values, and a write of this file will set atomic_t values. Another option is exporting a block of arbitrary binary data, with -this structure and function: +this structure and function:: struct debugfs_blob_wrapper { void *data; @@ -151,7 +158,7 @@ If you want to dump a block of registers (something that happens quite often during development, even if little such code reaches mainline. Debugfs offers two functions: one to make a registers-only file, and another to insert a register block in the middle of another sequential -file. +file:: struct debugfs_reg32 { char *name; @@ -175,7 +182,7 @@ The "base" argument may be 0, but you may want to build the reg32 array using __stringify, and a number of register names (macros) are actually byte offsets over a base for the register block. -If you want to dump an u32 array in debugfs, you can create file with: +If you want to dump an u32 array in debugfs, you can create file with:: void debugfs_create_u32_array(const char *name, umode_t mode, struct dentry *parent, @@ -185,7 +192,7 @@ The "array" argument provides data, and the "elements" argument is the number of elements in the array. Note: Once array is created its size can not be changed. -There is a helper function to create device related seq_file: +There is a helper function to create device related seq_file:: struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name, @@ -197,14 +204,14 @@ The "dev" argument is the device related to this debugfs file, and the "read_fn" is a function pointer which to be called to print the seq_file content. -There are a couple of other directory-oriented helper functions: +There are a couple of other directory-oriented helper functions:: - struct dentry *debugfs_rename(struct dentry *old_dir, + struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, - struct dentry *new_dir, + struct dentry *new_dir, const char *new_name); - struct dentry *debugfs_create_symlink(const char *name, + struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *target); @@ -219,7 +226,7 @@ module is unloaded without explicitly removing debugfs entries, the result will be a lot of stale pointers and no end of highly antisocial behavior. So all debugfs users - at least those which can be built as modules - must be prepared to remove all files and directories they create there. A file -can be removed with: +can be removed with:: void debugfs_remove(struct dentry *dentry); @@ -229,7 +236,7 @@ be removed. Once upon a time, debugfs users were required to remember the dentry pointer for every debugfs file they created so that all files could be cleaned up. We live in more civilized times now, though, and debugfs users -can call: +can call:: void debugfs_remove_recursive(struct dentry *dentry); @@ -237,5 +244,4 @@ If this function is passed a pointer for the dentry corresponding to the top-level directory, the entire hierarchy below that directory will be removed. -Notes: - [1] http://lwn.net/Articles/309298/ +.. [1] http://lwn.net/Articles/309298/ diff --git a/Documentation/filesystems/dlmfs.txt b/Documentation/filesystems/dlmfs.rst index fcf4d509d118..68daaa7facf9 100644 --- a/Documentation/filesystems/dlmfs.txt +++ b/Documentation/filesystems/dlmfs.rst @@ -1,20 +1,25 @@ -dlmfs -================== +.. SPDX-License-Identifier: GPL-2.0 +.. include:: <isonum.txt> + +===== +DLMFS +===== + A minimal DLM userspace interface implemented via a virtual file system. dlmfs is built with OCFS2 as it requires most of its infrastructure. -Project web page: http://ocfs2.wiki.kernel.org -Tools web page: https://github.com/markfasheh/ocfs2-tools -OCFS2 mailing lists: http://oss.oracle.com/projects/ocfs2/mailman/ +:Project web page: http://ocfs2.wiki.kernel.org +:Tools web page: https://github.com/markfasheh/ocfs2-tools +:OCFS2 mailing lists: http://oss.oracle.com/projects/ocfs2/mailman/ All code copyright 2005 Oracle except when otherwise noted. -CREDITS +Credits ======= -Some code taken from ramfs which is Copyright (C) 2000 Linus Torvalds +Some code taken from ramfs which is Copyright |copy| 2000 Linus Torvalds and Transmeta Corp. Mark Fasheh <mark.fasheh@oracle.com> @@ -96,14 +101,19 @@ operation. If the lock succeeds, you'll get an fd. open(2) with O_CREAT to ensure the resource inode is created - dlmfs does not automatically create inodes for existing lock resources. +============ =========================== Open Flag Lock Request Type ---------- ----------------- +============ =========================== O_RDONLY Shared Read O_RDWR Exclusive +============ =========================== + +============ =========================== Open Flag Resulting Locking Behavior ---------- -------------------------- +============ =========================== O_NONBLOCK Trylock operation +============ =========================== You must provide exactly one of O_RDONLY or O_RDWR. diff --git a/Documentation/filesystems/ecryptfs.txt b/Documentation/filesystems/ecryptfs.rst index 01d8a08351ac..1f2edef4c57a 100644 --- a/Documentation/filesystems/ecryptfs.txt +++ b/Documentation/filesystems/ecryptfs.rst @@ -1,14 +1,18 @@ +.. SPDX-License-Identifier: GPL-2.0 + +====================================================== eCryptfs: A stacked cryptographic filesystem for Linux +====================================================== eCryptfs is free software. Please see the file COPYING for details. For documentation, please see the files in the doc/ subdirectory. For building and installation instructions please see the INSTALL file. -Maintainer: Phillip Hellewell -Lead developer: Michael A. Halcrow <mhalcrow@us.ibm.com> -Developers: Michael C. Thompson - Kent Yoder -Web Site: http://ecryptfs.sf.net +:Maintainer: Phillip Hellewell +:Lead developer: Michael A. Halcrow <mhalcrow@us.ibm.com> +:Developers: Michael C. Thompson + Kent Yoder +:Web Site: http://ecryptfs.sf.net This software is currently undergoing development. Make sure to maintain a backup copy of any data you write into eCryptfs. @@ -19,34 +23,36 @@ SourceForge site: http://sourceforge.net/projects/ecryptfs/ Userspace requirements include: - - David Howells' userspace keyring headers and libraries (version - 1.0 or higher), obtainable from - http://people.redhat.com/~dhowells/keyutils/ - - Libgcrypt + +- David Howells' userspace keyring headers and libraries (version + 1.0 or higher), obtainable from + http://people.redhat.com/~dhowells/keyutils/ +- Libgcrypt -NOTES +.. note:: -In the beta/experimental releases of eCryptfs, when you upgrade -eCryptfs, you should copy the files to an unencrypted location and -then copy the files back into the new eCryptfs mount to migrate the -files. + In the beta/experimental releases of eCryptfs, when you upgrade + eCryptfs, you should copy the files to an unencrypted location and + then copy the files back into the new eCryptfs mount to migrate the + files. -MOUNT-WIDE PASSPHRASE +Mount-wide Passphrase +===================== Create a new directory into which eCryptfs will write its encrypted files (i.e., /root/crypt). Then, create the mount point directory -(i.e., /mnt/crypt). Now it's time to mount eCryptfs: +(i.e., /mnt/crypt). Now it's time to mount eCryptfs:: -mount -t ecryptfs /root/crypt /mnt/crypt + mount -t ecryptfs /root/crypt /mnt/crypt You should be prompted for a passphrase and a salt (the salt may be blank). -Try writing a new file: +Try writing a new file:: -echo "Hello, World" > /mnt/crypt/hello.txt + echo "Hello, World" > /mnt/crypt/hello.txt The operation will complete. Notice that there is a new file in /root/crypt that is at least 12288 bytes in size (depending on your @@ -59,10 +65,13 @@ keyctl clear @u Then umount /mnt/crypt and mount again per the instructions given above. -cat /mnt/crypt/hello.txt +:: + + cat /mnt/crypt/hello.txt -NOTES +Notes +===== eCryptfs version 0.1 should only be mounted on (1) empty directories or (2) directories containing files only created by eCryptfs. If you diff --git a/Documentation/filesystems/efivarfs.txt b/Documentation/filesystems/efivarfs.rst index 686a64bba775..90ac65683e7e 100644 --- a/Documentation/filesystems/efivarfs.txt +++ b/Documentation/filesystems/efivarfs.rst @@ -1,5 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 +======================================= efivarfs - a (U)EFI variable filesystem +======================================= The efivarfs filesystem was created to address the shortcomings of using entries in sysfs to maintain EFI variables. The old sysfs EFI @@ -11,7 +14,7 @@ than a single page, sysfs isn't the best interface for this. Variables can be created, deleted and modified with the efivarfs filesystem. -efivarfs is typically mounted like this, +efivarfs is typically mounted like this:: mount -t efivarfs none /sys/firmware/efi/efivars diff --git a/Documentation/filesystems/erofs.txt b/Documentation/filesystems/erofs.rst index db6d39c3ae71..bf145171c2bf 100644 --- a/Documentation/filesystems/erofs.txt +++ b/Documentation/filesystems/erofs.rst @@ -1,3 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +====================================== +Enhanced Read-Only File System - EROFS +====================================== + Overview ======== @@ -6,6 +12,7 @@ from other read-only file systems, it aims to be designed for flexibility, scalability, but be kept simple and high performance. It is designed as a better filesystem solution for the following scenarios: + - read-only storage media or - part of a fully trusted read-only solution, which means it needs to be @@ -17,6 +24,7 @@ It is designed as a better filesystem solution for the following scenarios: for those embedded devices with limited memory (ex, smartphone); Here is the main features of EROFS: + - Little endian on-disk design; - Currently 4KB block size (nobh) and therefore maximum 16TB address space; @@ -24,13 +32,17 @@ Here is the main features of EROFS: - Metadata & data could be mixed by design; - 2 inode versions for different requirements: + + ===================== ============ ===================================== compact (v1) extended (v2) - Inode metadata size: 32 bytes 64 bytes - Max file size: 4 GB 16 EB (also limited by max. vol size) - Max uids/gids: 65536 4294967296 - File change time: no yes (64 + 32-bit timestamp) - Max hardlinks: 65536 4294967296 - Metadata reserved: 4 bytes 14 bytes + ===================== ============ ===================================== + Inode metadata size 32 bytes 64 bytes + Max file size 4 GB 16 EB (also limited by max. vol size) + Max uids/gids 65536 4294967296 + File change time no yes (64 + 32-bit timestamp) + Max hardlinks 65536 4294967296 + Metadata reserved 4 bytes 14 bytes + ===================== ============ ===================================== - Support extended attributes (xattrs) as an option; @@ -43,29 +55,36 @@ Here is the main features of EROFS: The following git tree provides the file system user-space tools under development (ex, formatting tool mkfs.erofs): ->> git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs-utils.git + +- git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs-utils.git Bugs and patches are welcome, please kindly help us and send to the following linux-erofs mailing list: ->> linux-erofs mailing list <linux-erofs@lists.ozlabs.org> + +- linux-erofs mailing list <linux-erofs@lists.ozlabs.org> Mount options ============= +=================== ========================================================= (no)user_xattr Setup Extended User Attributes. Note: xattr is enabled by default if CONFIG_EROFS_FS_XATTR is selected. (no)acl Setup POSIX Access Control List. Note: acl is enabled by default if CONFIG_EROFS_FS_POSIX_ACL is selected. cache_strategy=%s Select a strategy for cached decompression from now on: - disabled: In-place I/O decompression only; - readahead: Cache the last incomplete compressed physical + + ========== ============================================= + disabled In-place I/O decompression only; + readahead Cache the last incomplete compressed physical cluster for further reading. It still does in-place I/O decompression for the rest compressed physical clusters; - readaround: Cache the both ends of incomplete compressed + readaround Cache the both ends of incomplete compressed physical clusters for further reading. It still does in-place I/O decompression for the rest compressed physical clusters. + ========== ============================================= +=================== ========================================================= On-disk details =============== @@ -73,7 +92,7 @@ On-disk details Summary ------- Different from other read-only file systems, an EROFS volume is designed -to be as simple as possible: +to be as simple as possible:: |-> aligned with the block size ____________________________________________________________ @@ -83,41 +102,45 @@ to be as simple as possible: All data areas should be aligned with the block size, but metadata areas may not. All metadatas can be now observed in two different spaces (views): + 1. Inode metadata space + Each valid inode should be aligned with an inode slot, which is a fixed value (32 bytes) and designed to be kept in line with compact inode size. Each inode can be directly found with the following formula: inode offset = meta_blkaddr * block_size + 32 * nid - |-> aligned with 8B - |-> followed closely - + meta_blkaddr blocks |-> another slot - _____________________________________________________________________ - | ... | inode | xattrs | extents | data inline | ... | inode ... - |________|_______|(optional)|(optional)|__(optional)_|_____|__________ - |-> aligned with the inode slot size - . . - . . - . . - . . - . . - . . - .____________________________________________________|-> aligned with 4B - | xattr_ibody_header | shared xattrs | inline xattrs | - |____________________|_______________|_______________| - |-> 12 bytes <-|->x * 4 bytes<-| . - . . . - . . . - . . . - ._______________________________.______________________. - | id | id | id | id | ... | id | ent | ... | ent| ... | - |____|____|____|____|______|____|_____|_____|____|_____| - |-> aligned with 4B - |-> aligned with 4B + :: + + |-> aligned with 8B + |-> followed closely + + meta_blkaddr blocks |-> another slot + _____________________________________________________________________ + | ... | inode | xattrs | extents | data inline | ... | inode ... + |________|_______|(optional)|(optional)|__(optional)_|_____|__________ + |-> aligned with the inode slot size + . . + . . + . . + . . + . . + . . + .____________________________________________________|-> aligned with 4B + | xattr_ibody_header | shared xattrs | inline xattrs | + |____________________|_______________|_______________| + |-> 12 bytes <-|->x * 4 bytes<-| . + . . . + . . . + . . . + ._______________________________.______________________. + | id | id | id | id | ... | id | ent | ... | ent| ... | + |____|____|____|____|______|____|_____|_____|____|_____| + |-> aligned with 4B + |-> aligned with 4B Inode could be 32 or 64 bytes, which can be distinguished from a common - field which all inode versions have -- i_format: + field which all inode versions have -- i_format:: __________________ __________________ | i_format | | i_format | @@ -132,16 +155,19 @@ may not. All metadatas can be now observed in two different spaces (views): proper alignment, and they could be optional for different data mappings. _currently_ total 4 valid data mappings are supported: + == ==================================================================== 0 flat file data without data inline (no extent); 1 fixed-sized output data compression (with non-compacted indexes); 2 flat file data with tail packing data inline (no extent); 3 fixed-sized output data compression (with compacted indexes, v5.3+). + == ==================================================================== The size of the optional xattrs is indicated by i_xattr_count in inode header. Large xattrs or xattrs shared by many different files can be stored in shared xattrs metadata rather than inlined right after inode. 2. Shared xattrs metadata space + Shared xattrs space is similar to the above inode space, started with a specific block indicated by xattr_blkaddr, organized one by one with proper align. @@ -149,11 +175,13 @@ may not. All metadatas can be now observed in two different spaces (views): Each share xattr can also be directly found by the following formula: xattr offset = xattr_blkaddr * block_size + 4 * xattr_id - |-> aligned by 4 bytes - + xattr_blkaddr blocks |-> aligned with 4 bytes - _________________________________________________________________________ - | ... | xattr_entry | xattr data | ... | xattr_entry | xattr data ... - |________|_____________|_____________|_____|______________|_______________ + :: + + |-> aligned by 4 bytes + + xattr_blkaddr blocks |-> aligned with 4 bytes + _________________________________________________________________________ + | ... | xattr_entry | xattr data | ... | xattr_entry | xattr data ... + |________|_____________|_____________|_____|______________|_______________ Directories ----------- @@ -163,19 +191,21 @@ random file lookup, and all directory entries are _strictly_ recorded in alphabetical order in order to support improved prefix binary search algorithm (could refer to the related source code). - ___________________________ - / | - / ______________|________________ - / / | nameoff1 | nameoffN-1 - ____________.______________._______________v________________v__________ -| dirent | dirent | ... | dirent | filename | filename | ... | filename | -|___.0___|____1___|_____|___N-1__|____0_____|____1_____|_____|___N-1____| - \ ^ - \ | * could have - \ | trailing '\0' - \________________________| nameoff0 +:: + + ___________________________ + / | + / ______________|________________ + / / | nameoff1 | nameoffN-1 + ____________.______________._______________v________________v__________ + | dirent | dirent | ... | dirent | filename | filename | ... | filename | + |___.0___|____1___|_____|___N-1__|____0_____|____1_____|_____|___N-1____| + \ ^ + \ | * could have + \ | trailing '\0' + \________________________| nameoff0 - Directory block + Directory block Note that apart from the offset of the first filename, nameoff0 also indicates the total number of directory entries in this block since it is no need to @@ -184,28 +214,27 @@ introduce another on-disk field at all. Compression ----------- Currently, EROFS supports 4KB fixed-sized output transparent file compression, -as illustrated below: - - |---- Variant-Length Extent ----|-------- VLE --------|----- VLE ----- - clusterofs clusterofs clusterofs - | | | logical data -_________v_______________________________v_____________________v_______________ -... | . | | . | | . | ... -____|____.________|_____________|________.____|_____________|__.__________|____ - |-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-| - size size size size size - . . . . - . . . . - . . . . - _______._____________._____________._____________._____________________ - ... | | | | ... physical data - _______|_____________|_____________|_____________|_____________________ - |-> cluster <-|-> cluster <-|-> cluster <-| - size size size +as illustrated below:: + + |---- Variant-Length Extent ----|-------- VLE --------|----- VLE ----- + clusterofs clusterofs clusterofs + | | | logical data + _________v_______________________________v_____________________v_______________ + ... | . | | . | | . | ... + ____|____.________|_____________|________.____|_____________|__.__________|____ + |-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-| + size size size size size + . . . . + . . . . + . . . . + _______._____________._____________._____________._____________________ + ... | | | | ... physical data + _______|_____________|_____________|_____________|_____________________ + |-> cluster <-|-> cluster <-|-> cluster <-| + size size size Currently each on-disk physical cluster can contain 4KB (un)compressed data at most. For each logical cluster, there is a corresponding on-disk index to describe its cluster type, physical cluster address, etc. See "struct z_erofs_vle_decompressed_index" in erofs_fs.h for more details. - diff --git a/Documentation/filesystems/ext2.txt b/Documentation/filesystems/ext2.rst index 94c2cf0292f5..d83dbbb162e2 100644 --- a/Documentation/filesystems/ext2.txt +++ b/Documentation/filesystems/ext2.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: GPL-2.0 + The Second Extended Filesystem ============================== @@ -14,8 +16,9 @@ Options Most defaults are determined by the filesystem superblock, and can be set using tune2fs(8). Kernel-determined defaults are indicated by (*). -bsddf (*) Makes `df' act like BSD. -minixdf Makes `df' act like Minix. +==================== === ================================================ +bsddf (*) Makes ``df`` act like BSD. +minixdf Makes ``df`` act like Minix. check=none, nocheck (*) Don't do extra checking of bitmaps on mount (check=normal and check=strict options removed) @@ -62,6 +65,7 @@ quota, usrquota Enable user disk quota support grpquota Enable group disk quota support (requires CONFIG_QUOTA). +==================== === ================================================ noquota option ls silently ignored by ext2. @@ -294,9 +298,9 @@ respective fsck programs. If you're exceptionally paranoid, there are 3 ways of making metadata writes synchronous on ext2: -per-file if you have the program source: use the O_SYNC flag to open() -per-file if you don't have the source: use "chattr +S" on the file -per-filesystem: add the "sync" option to mount (or in /etc/fstab) +- per-file if you have the program source: use the O_SYNC flag to open() +- per-file if you don't have the source: use "chattr +S" on the file +- per-filesystem: add the "sync" option to mount (or in /etc/fstab) the first and last are not ext2 specific but do force the metadata to be written synchronously. See also Journaling below. @@ -316,10 +320,12 @@ Most of these limits could be overcome with slight changes in the on-disk format and using a compatibility flag to signal the format change (at the expense of some compatibility). -Filesystem block size: 1kB 2kB 4kB 8kB - -File size limit: 16GB 256GB 2048GB 2048GB -Filesystem size limit: 2047GB 8192GB 16384GB 32768GB +===================== ======= ======= ======= ======== +Filesystem block size 1kB 2kB 4kB 8kB +===================== ======= ======= ======= ======== +File size limit 16GB 256GB 2048GB 2048GB +Filesystem size limit 2047GB 8192GB 16384GB 32768GB +===================== ======= ======= ======= ======== There is a 2.4 kernel limit of 2048GB for a single block device, so no filesystem larger than that can be created at this time. There is also @@ -370,19 +376,24 @@ ext4 and journaling. References ========== +======================= =============================================== The kernel source file:/usr/src/linux/fs/ext2/ e2fsprogs (e2fsck) http://e2fsprogs.sourceforge.net/ Design & Implementation http://e2fsprogs.sourceforge.net/ext2intro.html Journaling (ext3) ftp://ftp.uk.linux.org/pub/linux/sct/fs/jfs/ Filesystem Resizing http://ext2resize.sourceforge.net/ -Compression (*) http://e2compr.sourceforge.net/ +Compression [1]_ http://e2compr.sourceforge.net/ +======================= =============================================== Implementations for: + +======================= =========================================================== Windows 95/98/NT/2000 http://www.chrysocome.net/explore2fs -Windows 95 (*) http://www.yipton.net/content.html#FSDEXT2 -DOS client (*) ftp://metalab.unc.edu/pub/Linux/system/filesystems/ext2/ -OS/2 (+) ftp://metalab.unc.edu/pub/Linux/system/filesystems/ext2/ +Windows 95 [1]_ http://www.yipton.net/content.html#FSDEXT2 +DOS client [1]_ ftp://metalab.unc.edu/pub/Linux/system/filesystems/ext2/ +OS/2 [2]_ ftp://metalab.unc.edu/pub/Linux/system/filesystems/ext2/ RISC OS client http://www.esw-heim.tu-clausthal.de/~marco/smorbrod/IscaFS/ +======================= =========================================================== -(*) no longer actively developed/supported (as of Apr 2001) -(+) no longer actively developed/supported (as of Mar 2009) +.. [1] no longer actively developed/supported (as of Apr 2001) +.. [2] no longer actively developed/supported (as of Mar 2009) diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.rst index 58758fbef9e0..c06cec3a8fdc 100644 --- a/Documentation/filesystems/ext3.txt +++ b/Documentation/filesystems/ext3.rst @@ -1,4 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 +=============== Ext3 Filesystem =============== diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.rst index 4eb3e2ddd00e..87d794bc75a4 100644 --- a/Documentation/filesystems/f2fs.txt +++ b/Documentation/filesystems/f2fs.rst @@ -1,6 +1,8 @@ -================================================================================ +.. SPDX-License-Identifier: GPL-2.0 + +========================================== WHAT IS Flash-Friendly File System (F2FS)? -================================================================================ +========================================== NAND flash memory-based storage devices, such as SSD, eMMC, and SD cards, have been equipped on a variety systems ranging from mobile to server systems. Since @@ -20,14 +22,15 @@ layout, but also for selecting allocation and cleaning algorithms. The following git tree provides the file system formatting tool (mkfs.f2fs), a consistency checking tool (fsck.f2fs), and a debugging tool (dump.f2fs). ->> git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs-tools.git + +- git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs-tools.git For reporting bugs and sending patches, please use the following mailing list: ->> linux-f2fs-devel@lists.sourceforge.net -================================================================================ -BACKGROUND AND DESIGN ISSUES -================================================================================ +- linux-f2fs-devel@lists.sourceforge.net + +Background and Design issues +============================ Log-structured File System (LFS) -------------------------------- @@ -61,6 +64,7 @@ needs to reclaim these obsolete blocks seamlessly to users. This job is called as a cleaning process. The process consists of three operations as follows. + 1. A victim segment is selected through referencing segment usage table. 2. It loads parent index structures of all the data in the victim identified by segment summary blocks. @@ -71,9 +75,8 @@ This cleaning job may cause unexpected long delays, so the most important goal is to hide the latencies to users. And also definitely, it should reduce the amount of valid data to be moved, and move them quickly as well. -================================================================================ -KEY FEATURES -================================================================================ +Key Features +============ Flash Awareness --------------- @@ -94,10 +97,11 @@ Cleaning Overhead - Support multi-head logs for static/dynamic hot and cold data separation - Introduce adaptive logging for efficient block allocation -================================================================================ -MOUNT OPTIONS -================================================================================ +Mount Options +============= + +====================== ============================================================ background_gc=%s Turn on/off cleaning operations, namely garbage collection, triggered in background when I/O subsystem is idle. If background_gc=on, it will turn on the garbage @@ -167,7 +171,10 @@ fault_injection=%d Enable fault injection in all supported types with fault_type=%d Support configuring fault injection type, should be enabled with fault_injection option, fault type value is shown below, it supports single or combined type. + + =================== =========== Type_Name Type_Value + =================== =========== FAULT_KMALLOC 0x000000001 FAULT_KVMALLOC 0x000000002 FAULT_PAGE_ALLOC 0x000000004 @@ -183,6 +190,7 @@ fault_type=%d Support configuring fault injection type, should be FAULT_CHECKPOINT 0x000001000 FAULT_DISCARD 0x000002000 FAULT_WRITE_IO 0x000004000 + =================== =========== mode=%s Control block allocation mode which supports "adaptive" and "lfs". In "lfs" mode, there should be no random writes towards main area. @@ -219,7 +227,7 @@ fsync_mode=%s Control the policy of fsync. Currently supports "posix", non-atomic files likewise "nobarrier" mount option. test_dummy_encryption Enable dummy encryption, which provides a fake fscrypt context. The fake fscrypt context is used by xfstests. -checkpoint=%s[:%u[%]] Set to "disable" to turn off checkpointing. Set to "enable" +checkpoint=%s[:%u[%]] Set to "disable" to turn off checkpointing. Set to "enable" to reenable checkpointing. Is enabled by default. While disabled, any unmounting or unexpected shutdowns will cause the filesystem contents to appear as they did when the @@ -235,8 +243,8 @@ checkpoint=%s[:%u[%]] Set to "disable" to turn off checkpointing. Set to "en hide up to all remaining free space. The actual space that would be unusable can be viewed at /sys/fs/f2fs/<disk>/unusable This space is reclaimed once checkpoint=enable. -compress_algorithm=%s Control compress algorithm, currently f2fs supports "lzo" - and "lz4" algorithm. +compress_algorithm=%s Control compress algorithm, currently f2fs supports "lzo", + "lz4" and "zstd" algorithm. compress_log_size=%u Support configuring compress cluster size, the size will be 4KB * (1 << %u), 16KB is minimum size, also it's default size. @@ -246,22 +254,22 @@ compress_extension=%s Support adding specified extension, so that f2fs can enab on compression extension list and enable compression on these file by default rather than to enable it via ioctl. For other files, we can still enable compression via ioctl. +====================== ============================================================ -================================================================================ -DEBUGFS ENTRIES -================================================================================ +Debugfs Entries +=============== /sys/kernel/debug/f2fs/ contains information about all the partitions mounted as f2fs. Each file shows the whole f2fs information. /sys/kernel/debug/f2fs/status includes: + - major file system information managed by f2fs currently - average SIT information about whole segments - current memory footprint consumed by f2fs. -================================================================================ -SYSFS ENTRIES -================================================================================ +Sysfs Entries +============= Information about mounted f2fs file systems can be found in /sys/fs/f2fs. Each mounted filesystem will have a directory in @@ -271,22 +279,24 @@ The files in each per-device directory are shown in table below. Files in /sys/fs/f2fs/<devname> (see also Documentation/ABI/testing/sysfs-fs-f2fs) -================================================================================ -USAGE -================================================================================ +Usage +===== 1. Download userland tools and compile them. 2. Skip, if f2fs was compiled statically inside kernel. - Otherwise, insert the f2fs.ko module. - # insmod f2fs.ko + Otherwise, insert the f2fs.ko module:: + + # insmod f2fs.ko -3. Create a directory trying to mount - # mkdir /mnt/f2fs +3. Create a directory trying to mount:: -4. Format the block device, and then mount as f2fs - # mkfs.f2fs -l label /dev/block_device - # mount -t f2fs /dev/block_device /mnt/f2fs + # mkdir /mnt/f2fs + +4. Format the block device, and then mount as f2fs:: + + # mkfs.f2fs -l label /dev/block_device + # mount -t f2fs /dev/block_device /mnt/f2fs mkfs.f2fs --------- @@ -294,18 +304,26 @@ The mkfs.f2fs is for the use of formatting a partition as the f2fs filesystem, which builds a basic on-disk layout. The options consist of: --l [label] : Give a volume label, up to 512 unicode name. --a [0 or 1] : Split start location of each area for heap-based allocation. - 1 is set by default, which performs this. --o [int] : Set overprovision ratio in percent over volume size. - 5 is set by default. --s [int] : Set the number of segments per section. - 1 is set by default. --z [int] : Set the number of sections per zone. - 1 is set by default. --e [str] : Set basic extension list. e.g. "mp3,gif,mov" --t [0 or 1] : Disable discard command or not. - 1 is set by default, which conducts discard. + +=============== =========================================================== +``-l [label]`` Give a volume label, up to 512 unicode name. +``-a [0 or 1]`` Split start location of each area for heap-based allocation. + + 1 is set by default, which performs this. +``-o [int]`` Set overprovision ratio in percent over volume size. + + 5 is set by default. +``-s [int]`` Set the number of segments per section. + + 1 is set by default. +``-z [int]`` Set the number of sections per zone. + + 1 is set by default. +``-e [str]`` Set basic extension list. e.g. "mp3,gif,mov" +``-t [0 or 1]`` Disable discard command or not. + + 1 is set by default, which conducts discard. +=============== =========================================================== fsck.f2fs --------- @@ -314,7 +332,8 @@ partition, which examines whether the filesystem metadata and user-made data are cross-referenced correctly or not. Note that, initial version of the tool does not fix any inconsistency. -The options consist of: +The options consist of:: + -d debug level [default:0] dump.f2fs @@ -327,20 +346,21 @@ It shows on-disk inode information recognized by a given inode number, and is able to dump all the SSA and SIT entries into predefined files, ./dump_ssa and ./dump_sit respectively. -The options consist of: +The options consist of:: + -d debug level [default:0] -i inode no (hex) -s [SIT dump segno from #1~#2 (decimal), for all 0~-1] -a [SSA dump segno from #1~#2 (decimal), for all 0~-1] -Examples: -# dump.f2fs -i [ino] /dev/sdx -# dump.f2fs -s 0~-1 /dev/sdx (SIT dump) -# dump.f2fs -a 0~-1 /dev/sdx (SSA dump) +Examples:: + + # dump.f2fs -i [ino] /dev/sdx + # dump.f2fs -s 0~-1 /dev/sdx (SIT dump) + # dump.f2fs -a 0~-1 /dev/sdx (SSA dump) -================================================================================ -DESIGN -================================================================================ +Design +====== On-disk Layout -------------- @@ -351,7 +371,7 @@ consists of a set of sections. By default, section and zone sizes are set to one segment size identically, but users can easily modify the sizes by mkfs. F2FS splits the entire volume into six areas, and all the areas except superblock -consists of multiple segments as described below. +consists of multiple segments as described below:: align with the zone size <-| |-> align with the segment size @@ -373,28 +393,28 @@ consists of multiple segments as described below. |__zone__| - Superblock (SB) - : It is located at the beginning of the partition, and there exist two copies + It is located at the beginning of the partition, and there exist two copies to avoid file system crash. It contains basic partition information and some default parameters of f2fs. - Checkpoint (CP) - : It contains file system information, bitmaps for valid NAT/SIT sets, orphan + It contains file system information, bitmaps for valid NAT/SIT sets, orphan inode lists, and summary entries of current active segments. - Segment Information Table (SIT) - : It contains segment information such as valid block count and bitmap for the + It contains segment information such as valid block count and bitmap for the validity of all the blocks. - Node Address Table (NAT) - : It is composed of a block address table for all the node blocks stored in + It is composed of a block address table for all the node blocks stored in Main area. - Segment Summary Area (SSA) - : It contains summary entries which contains the owner information of all the + It contains summary entries which contains the owner information of all the data and node blocks stored in Main area. - Main Area - : It contains file and directory data including their indices. + It contains file and directory data including their indices. In order to avoid misalignment between file system and flash-based storage, F2FS aligns the start block address of CP with the segment size. Also, it aligns the @@ -414,7 +434,7 @@ One of them always indicates the last valid data, which is called as shadow copy mechanism. In addition to CP, NAT and SIT also adopt the shadow copy mechanism. For file system consistency, each CP points to which NAT and SIT copies are -valid, as shown as below. +valid, as shown as below:: +--------+----------+---------+ | CP | SIT | NAT | @@ -438,7 +458,7 @@ indirect node. F2FS assigns 4KB to an inode block which contains 923 data block indices, two direct node pointers, two indirect node pointers, and one double indirect node pointer as described below. One direct node block contains 1018 data blocks, and one indirect node block contains also 1018 node blocks. Thus, -one inode block (i.e., a file) covers: +one inode block (i.e., a file) covers:: 4KB * (923 + 2 * 1018 + 2 * 1018 * 1018 + 1018 * 1018 * 1018) := 3.94TB. @@ -473,6 +493,8 @@ A dentry block consists of 214 dentry slots and file names. Therein a bitmap is used to represent whether each dentry is valid or not. A dentry block occupies 4KB with the following composition. +:: + Dentry Block(4 K) = bitmap (27 bytes) + reserved (3 bytes) + dentries(11 * 214 bytes) + file name (8 * 214 bytes) @@ -498,23 +520,25 @@ F2FS implements multi-level hash tables for directory structure. Each level has a hash table with dedicated number of hash buckets as shown below. Note that "A(2B)" means a bucket includes 2 data blocks. ----------------------- -A : bucket -B : block -N : MAX_DIR_HASH_DEPTH ----------------------- +:: + + ---------------------- + A : bucket + B : block + N : MAX_DIR_HASH_DEPTH + ---------------------- -level #0 | A(2B) - | -level #1 | A(2B) - A(2B) - | -level #2 | A(2B) - A(2B) - A(2B) - A(2B) - . | . . . . -level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B) - . | . . . . -level #N | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B) + level #0 | A(2B) + | + level #1 | A(2B) - A(2B) + | + level #2 | A(2B) - A(2B) - A(2B) - A(2B) + . | . . . . + level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B) + . | . . . . + level #N | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B) -The number of blocks and buckets are determined by, +The number of blocks and buckets are determined by:: ,- 2, if n < MAX_DIR_HASH_DEPTH / 2, # of blocks in level #n = | @@ -532,7 +556,7 @@ dentry consisting of the file name and its inode number. If not found, F2FS scans the next hash table in level #1. In this way, F2FS scans hash tables in each levels incrementally from 1 to N. In each levels F2FS needs to scan only one bucket determined by the following equation, which shows O(log(# of files)) -complexity. +complexity:: bucket number to scan in level #n = (hash value) % (# of buckets in level #n) @@ -540,7 +564,8 @@ In the case of file creation, F2FS finds empty consecutive slots that cover the file name. F2FS searches the empty slots in the hash tables of whole levels from 1 to N in the same way as the lookup operation. -The following figure shows an example of two cases holding children. +The following figure shows an example of two cases holding children:: + --------------> Dir <-------------- | | child child @@ -611,14 +636,15 @@ Write-hint Policy 2) whint_mode=user-based. F2FS tries to pass down hints given by users. +===================== ======================== =================== User F2FS Block ----- ---- ----- +===================== ======================== =================== META WRITE_LIFE_NOT_SET HOT_NODE " WARM_NODE " COLD_NODE " -*ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME -*extension list " " +ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME +extension list " " -- buffered io WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME @@ -635,11 +661,13 @@ WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET WRITE_LIFE_NONE " WRITE_LIFE_NONE WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM WRITE_LIFE_LONG " WRITE_LIFE_LONG +===================== ======================== =================== 3) whint_mode=fs-based. F2FS passes down hints with its policy. +===================== ======================== =================== User F2FS Block ----- ---- ----- +===================== ======================== =================== META WRITE_LIFE_MEDIUM; HOT_NODE WRITE_LIFE_NOT_SET WARM_NODE " @@ -662,6 +690,7 @@ WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET WRITE_LIFE_NONE " WRITE_LIFE_NONE WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM WRITE_LIFE_LONG " WRITE_LIFE_LONG +===================== ======================== =================== Fallocate(2) Policy ------------------- @@ -681,6 +710,7 @@ Allocating disk space However, once F2FS receives ioctl(fd, F2FS_IOC_SET_PIN_FILE) in prior to fallocate(fd, DEFAULT_MODE), it allocates on-disk blocks addressess having zero or random data, which is useful to the below scenario where: + 1. create(fd) 2. ioctl(fd, F2FS_IOC_SET_PIN_FILE) 3. fallocate(fd, 0, 0, size) @@ -692,39 +722,41 @@ Compression implementation -------------------------- - New term named cluster is defined as basic unit of compression, file can -be divided into multiple clusters logically. One cluster includes 4 << n -(n >= 0) logical pages, compression size is also cluster size, each of -cluster can be compressed or not. + be divided into multiple clusters logically. One cluster includes 4 << n + (n >= 0) logical pages, compression size is also cluster size, each of + cluster can be compressed or not. - In cluster metadata layout, one special block address is used to indicate -cluster is compressed one or normal one, for compressed cluster, following -metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs -stores data including compress header and compressed data. + cluster is compressed one or normal one, for compressed cluster, following + metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs + stores data including compress header and compressed data. - In order to eliminate write amplification during overwrite, F2FS only -support compression on write-once file, data can be compressed only when -all logical blocks in file are valid and cluster compress ratio is lower -than specified threshold. + support compression on write-once file, data can be compressed only when + all logical blocks in file are valid and cluster compress ratio is lower + than specified threshold. - To enable compression on regular inode, there are three ways: -* chattr +c file -* chattr +c dir; touch dir/file -* mount w/ -o compress_extension=ext; touch file.ext - -Compress metadata layout: - [Dnode Structure] - +-----------------------------------------------+ - | cluster 1 | cluster 2 | ......... | cluster N | - +-----------------------------------------------+ - . . . . - . . . . - . Compressed Cluster . . Normal Cluster . -+----------+---------+---------+---------+ +---------+---------+---------+---------+ -|compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | -+----------+---------+---------+---------+ +---------+---------+---------+---------+ - . . - . . - . . - +-------------+-------------+----------+----------------------------+ - | data length | data chksum | reserved | compressed data | - +-------------+-------------+----------+----------------------------+ + + * chattr +c file + * chattr +c dir; touch dir/file + * mount w/ -o compress_extension=ext; touch file.ext + +Compress metadata layout:: + + [Dnode Structure] + +-----------------------------------------------+ + | cluster 1 | cluster 2 | ......... | cluster N | + +-----------------------------------------------+ + . . . . + . . . . + . Compressed Cluster . . Normal Cluster . + +----------+---------+---------+---------+ +---------+---------+---------+---------+ + |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 | + +----------+---------+---------+---------+ +---------+---------+---------+---------+ + . . + . . + . . + +-------------+-------------+----------+----------------------------+ + | data length | data chksum | reserved | compressed data | + +-------------+-------------+----------+----------------------------+ diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt index f6d9c99103a4..ac87e6fda842 100644 --- a/Documentation/filesystems/fiemap.txt +++ b/Documentation/filesystems/fiemap.txt @@ -115,8 +115,10 @@ data. Note that the opposite is not true - it would be valid for FIEMAP_EXTENT_NOT_ALIGNED to appear alone. * FIEMAP_EXTENT_LAST -This is the last extent in the file. A mapping attempt past this -extent will return nothing. +This is generally the last extent in the file. A mapping attempt past +this extent may return nothing. Some implementations set this flag to +indicate this extent is the last one in the range queried by the user +(via fiemap->fm_length). * FIEMAP_EXTENT_UNKNOWN The location of this extent is currently unknown. This may indicate diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index bd9932344804..aa072112cfff 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -633,6 +633,17 @@ from a passphrase or other low-entropy user credential. FS_IOC_GET_ENCRYPTION_PWSALT is deprecated. Instead, prefer to generate and manage any needed salt(s) in userspace. +Getting a file's encryption nonce +--------------------------------- + +Since Linux v5.7, the ioctl FS_IOC_GET_ENCRYPTION_NONCE is supported. +On encrypted files and directories it gets the inode's 16-byte nonce. +On unencrypted files and directories, it fails with ENODATA. + +This ioctl can be useful for automated tests which verify that the +encryption is being done correctly. It is not needed for normal use +of fscrypt. + Adding keys ----------- diff --git a/Documentation/filesystems/fuse.rst b/Documentation/filesystems/fuse.rst index 8e455065ce9e..cd717f9bf940 100644 --- a/Documentation/filesystems/fuse.rst +++ b/Documentation/filesystems/fuse.rst @@ -1,7 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0 -============== + +==== FUSE -============== +==== Definitions =========== diff --git a/Documentation/filesystems/gfs2-uevents.txt b/Documentation/filesystems/gfs2-uevents.rst index 19a19ebebc34..f162a2c76c69 100644 --- a/Documentation/filesystems/gfs2-uevents.txt +++ b/Documentation/filesystems/gfs2-uevents.rst @@ -1,14 +1,18 @@ - uevents and GFS2 - ================== +.. SPDX-License-Identifier: GPL-2.0 + +================ +uevents and GFS2 +================ During the lifetime of a GFS2 mount, a number of uevents are generated. This document explains what the events are and what they are used for (by gfs_controld in gfs2-utils). A list of GFS2 uevents ------------------------ +====================== 1. ADD +------ The ADD event occurs at mount time. It will always be the first uevent generated by the newly created filesystem. If the mount @@ -21,6 +25,7 @@ with no journal assigned), and read-only (with journal assigned) status of the filesystem respectively. 2. ONLINE +--------- The ONLINE uevent is generated after a successful mount or remount. It has the same environment variables as the ADD uevent. The ONLINE @@ -29,6 +34,7 @@ RDONLY are a relatively recent addition (2.6.32-rc+) and will not be generated by older kernels. 3. CHANGE +--------- The CHANGE uevent is used in two places. One is when reporting the successful mount of the filesystem by the first node (FIRSTMOUNT=Done). @@ -52,6 +58,7 @@ cluster. For this reason the ONLINE uevent was used when adding a new uevent for a successful mount or remount. 4. OFFLINE +---------- The OFFLINE uevent is only generated due to filesystem errors and is used as part of the "withdraw" mechanism. Currently this doesn't give any @@ -59,6 +66,7 @@ information about what the error is, which is something that needs to be fixed. 5. REMOVE +--------- The REMOVE uevent is generated at the end of an unsuccessful mount or at the end of a umount of the filesystem. All REMOVE uevents will @@ -68,9 +76,10 @@ kobject subsystem. Information common to all GFS2 uevents (uevent environment variables) ----------------------------------------------------------------------- +===================================================================== 1. LOCKTABLE= +-------------- The LOCKTABLE is a string, as supplied on the mount command line (locktable=) or via fstab. It is used as a filesystem label @@ -78,6 +87,7 @@ as well as providing the information for a lock_dlm mount to be able to join the cluster. 2. LOCKPROTO= +------------- The LOCKPROTO is a string, and its value depends on what is set on the mount command line, or via fstab. It will be either @@ -85,12 +95,14 @@ lock_nolock or lock_dlm. In the future other lock managers may be supported. 3. JOURNALID= +------------- If a journal is in use by the filesystem (journals are not assigned for spectator mounts) then this will give the numeric journal id in all GFS2 uevents. 4. UUID= +-------- With recent versions of gfs2-utils, mkfs.gfs2 writes a UUID into the filesystem superblock. If it exists, this will diff --git a/Documentation/filesystems/gfs2.txt b/Documentation/filesystems/gfs2.rst index cc4f2306609e..8d1ab589ce18 100644 --- a/Documentation/filesystems/gfs2.txt +++ b/Documentation/filesystems/gfs2.rst @@ -1,5 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================== Global File System ------------------- +================== https://fedorahosted.org/cluster/wiki/HomePage @@ -14,16 +17,18 @@ on one machine show up immediately on all other machines in the cluster. GFS uses interchangeable inter-node locking mechanisms, the currently supported mechanisms are: - lock_nolock -- allows gfs to be used as a local file system + lock_nolock + - allows gfs to be used as a local file system - lock_dlm -- uses a distributed lock manager (dlm) for inter-node locking - The dlm is found at linux/fs/dlm/ + lock_dlm + - uses a distributed lock manager (dlm) for inter-node locking. + The dlm is found at linux/fs/dlm/ Lock_dlm depends on user space cluster management systems found at the URL above. To use gfs as a local file system, no external clustering systems are -needed, simply: +needed, simply:: $ mkfs -t gfs2 -p lock_nolock -j 1 /dev/block_device $ mount -t gfs2 /dev/block_device /dir @@ -37,9 +42,12 @@ GFS2 is not on-disk compatible with previous versions of GFS, but it is pretty close. The following man pages can be found at the URL above: + + ============ ============================================= fsck.gfs2 to repair a filesystem gfs2_grow to expand a filesystem online gfs2_jadd to add journals to a filesystem online tunegfs2 to manipulate, examine and tune a filesystem - gfs2_convert to convert a gfs filesystem to gfs2 in-place + gfs2_convert to convert a gfs filesystem to gfs2 in-place mkfs.gfs2 to make a filesystem + ============ ============================================= diff --git a/Documentation/filesystems/hfs.txt b/Documentation/filesystems/hfs.rst index d096df6db07a..ab17a005e9b1 100644 --- a/Documentation/filesystems/hfs.txt +++ b/Documentation/filesystems/hfs.rst @@ -1,11 +1,16 @@ -Note: This filesystem doesn't have a maintainer. +.. SPDX-License-Identifier: GPL-2.0 +================================== Macintosh HFS Filesystem for Linux ================================== -HFS stands for ``Hierarchical File System'' and is the filesystem used + +.. Note:: This filesystem doesn't have a maintainer. + + +HFS stands for ``Hierarchical File System`` and is the filesystem used by the Mac Plus and all later Macintosh models. Earlier Macintosh -models used MFS (``Macintosh File System''), which is not supported, +models used MFS (``Macintosh File System``), which is not supported, MacOS 8.1 and newer support a filesystem called HFS+ that's similar to HFS but is extended in various areas. Use the hfsplus filesystem driver to access such filesystems from Linux. @@ -49,25 +54,25 @@ Writing to HFS Filesystems HFS is not a UNIX filesystem, thus it does not have the usual features you'd expect: - o You can't modify the set-uid, set-gid, sticky or executable bits or the uid + * You can't modify the set-uid, set-gid, sticky or executable bits or the uid and gid of files. - o You can't create hard- or symlinks, device files, sockets or FIFOs. + * You can't create hard- or symlinks, device files, sockets or FIFOs. HFS does on the other have the concepts of multiple forks per file. These non-standard forks are represented as hidden additional files in the normal filesystems namespace which is kind of a cludge and makes the semantics for the a little strange: - o You can't create, delete or rename resource forks of files or the + * You can't create, delete or rename resource forks of files or the Finder's metadata. - o They are however created (with default values), deleted and renamed + * They are however created (with default values), deleted and renamed along with the corresponding data fork or directory. - o Copying files to a different filesystem will loose those attributes + * Copying files to a different filesystem will loose those attributes that are essential for MacOS to work. Creating HFS filesystems -=================================== +======================== The hfsutils package from Robert Leslie contains a program called hformat that can be used to create HFS filesystem. See diff --git a/Documentation/filesystems/hfsplus.txt b/Documentation/filesystems/hfsplus.rst index 59f7569fc9ed..f02f4f5fc020 100644 --- a/Documentation/filesystems/hfsplus.txt +++ b/Documentation/filesystems/hfsplus.rst @@ -1,4 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 +====================================== Macintosh HFSPlus Filesystem for Linux ====================================== diff --git a/Documentation/filesystems/hpfs.txt b/Documentation/filesystems/hpfs.rst index 74630bd504fb..0db152278572 100644 --- a/Documentation/filesystems/hpfs.txt +++ b/Documentation/filesystems/hpfs.rst @@ -1,13 +1,21 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== Read/Write HPFS 2.09 +==================== + 1998-2004, Mikulas Patocka -email: mikulas@artax.karlin.mff.cuni.cz -homepage: http://artax.karlin.mff.cuni.cz/~mikulas/vyplody/hpfs/index-e.cgi +:email: mikulas@artax.karlin.mff.cuni.cz +:homepage: http://artax.karlin.mff.cuni.cz/~mikulas/vyplody/hpfs/index-e.cgi -CREDITS: +Credits +======= Chris Smith, 1993, original read-only HPFS, some code and hpfs structures file is taken from it + Jacques Gelinas, MSDos mmap, Inspired by fs/nfs/mmap.c (Jon Tombs 15 Aug 1993) + Werner Almesberger, 1992, 1993, MSDos option parser & CR/LF conversion Mount options @@ -50,6 +58,7 @@ timeshift=(-)nnn (default 0) File names +========== As in OS/2, filenames are case insensitive. However, shell thinks that names are case sensitive, so for example when you create a file FOO, you can use @@ -64,6 +73,7 @@ access it under names 'a.', 'a..', 'a . . . ' etc. Extended attributes +=================== On HPFS partitions, OS/2 can associate to each file a special information called extended attributes. Extended attributes are pairs of (key,value) where key is @@ -88,6 +98,7 @@ values doesn't work. Symlinks +======== You can do symlinks on HPFS partition, symlinks are achieved by setting extended attribute named "SYMLINK" with symlink value. Like on ext2, you can chown and @@ -101,6 +112,7 @@ to analyze or change OS2SYS.INI. Codepages +========= HPFS can contain several uppercasing tables for several codepages and each file has a pointer to codepage its name is in. However OS/2 was created in @@ -128,6 +140,7 @@ this codepage - if you don't try to do what I described above :-) Known bugs +========== HPFS386 on OS/2 server is not supported. HPFS386 installed on normal OS/2 client should work. If you have OS/2 server, use only read-only mode. I don't know how @@ -152,7 +165,8 @@ would result in directory tree splitting, that takes disk space. Workaround is to delete other files that are leaf (probability that the file is non-leaf is about 1/50) or to truncate file first to make some space. You encounter this problem only if you have many directories so that -preallocated directory band is full i.e. +preallocated directory band is full i.e.:: + number_of_directories / size_of_filesystem_in_mb > 4. You can't delete open directories. @@ -174,6 +188,7 @@ anybody know what does it mean? What does "unbalanced tree" message mean? +========================================= Old versions of this driver created sometimes unbalanced dnode trees. OS/2 chkdsk doesn't scream if the tree is unbalanced (and sometimes creates @@ -187,6 +202,7 @@ whole created by this driver, it is BUG - let me know about it. Bugs in OS/2 +============ When you have two (or more) lost directories pointing each to other, chkdsk locks up when repairing filesystem. @@ -199,98 +215,139 @@ File names like "a .b" are marked as 'long' by OS/2 but chkdsk "corrects" it and marks them as short (and writes "minor fs error corrected"). This bug is not in HPFS386. -Codepage bugs described above. +Codepage bugs described above +============================= If you don't install fixpacks, there are many, many more... History +======= + +====== ========================================================================= +0.90 First public release +0.91 Fixed bug that caused shooting to memory when write_inode was called on + open inode (rarely happened) +0.92 Fixed a little memory leak in freeing directory inodes +0.93 Fixed bug that locked up the machine when there were too many filenames + with first 15 characters same + Fixed write_file to zero file when writing behind file end +0.94 Fixed a little memory leak when trying to delete busy file or directory +0.95 Fixed a bug that i_hpfs_parent_dir was not updated when moving files +1.90 First version for 2.1.1xx kernels +1.91 Fixed a bug that chk_sectors failed when sectors were at the end of disk + Fixed a race-condition when write_inode is called while deleting file + Fixed a bug that could possibly happen (with very low probability) when + using 0xff in filenames. + + Rewritten locking to avoid race-conditions + + Mount option 'eas' now works + + Fsync no longer returns error + + Files beginning with '.' are marked hidden + + Remount support added + + Alloc is not so slow when filesystem becomes full + + Atimes are no more updated because it slows down operation + + Code cleanup (removed all commented debug prints) +1.92 Corrected a bug when sync was called just before closing file +1.93 Modified, so that it works with kernels >= 2.1.131, I don't know if it + works with previous versions + + Fixed a possible problem with disks > 64G (but I don't have one, so I can't + test it) + + Fixed a file overflow at 2G + + Added new option 'timeshift' + + Changed behaviour on HPFS386: It is now possible to operate on HPFS386 in + read-only mode + + Fixed a bug that slowed down alloc and prevented allocating 100% space + (this bug was not destructive) +1.94 Added workaround for one bug in Linux + + Fixed one buffer leak + + Fixed some incompatibilities with large extended attributes (but it's still + not 100% ok, I have no info on it and OS/2 doesn't want to create them) + + Rewritten allocation -0.90 First public release -0.91 Fixed bug that caused shooting to memory when write_inode was called on - open inode (rarely happened) -0.92 Fixed a little memory leak in freeing directory inodes -0.93 Fixed bug that locked up the machine when there were too many filenames - with first 15 characters same - Fixed write_file to zero file when writing behind file end -0.94 Fixed a little memory leak when trying to delete busy file or directory -0.95 Fixed a bug that i_hpfs_parent_dir was not updated when moving files -1.90 First version for 2.1.1xx kernels -1.91 Fixed a bug that chk_sectors failed when sectors were at the end of disk - Fixed a race-condition when write_inode is called while deleting file - Fixed a bug that could possibly happen (with very low probability) when - using 0xff in filenames - Rewritten locking to avoid race-conditions - Mount option 'eas' now works - Fsync no longer returns error - Files beginning with '.' are marked hidden - Remount support added - Alloc is not so slow when filesystem becomes full - Atimes are no more updated because it slows down operation - Code cleanup (removed all commented debug prints) -1.92 Corrected a bug when sync was called just before closing file -1.93 Modified, so that it works with kernels >= 2.1.131, I don't know if it - works with previous versions - Fixed a possible problem with disks > 64G (but I don't have one, so I can't - test it) - Fixed a file overflow at 2G - Added new option 'timeshift' - Changed behaviour on HPFS386: It is now possible to operate on HPFS386 in - read-only mode - Fixed a bug that slowed down alloc and prevented allocating 100% space - (this bug was not destructive) -1.94 Added workaround for one bug in Linux - Fixed one buffer leak - Fixed some incompatibilities with large extended attributes (but it's still - not 100% ok, I have no info on it and OS/2 doesn't want to create them) - Rewritten allocation - Fixed a bug with i_blocks (du sometimes didn't display correct values) - Directories have no longer archive attribute set (some programs don't like - it) - Fixed a bug that it set badly one flag in large anode tree (it was not - destructive) -1.95 Fixed one buffer leak, that could happen on corrupted filesystem - Fixed one bug in allocation in 1.94 -1.96 Added workaround for one bug in OS/2 (HPFS locked up, HPFS386 reported - error sometimes when opening directories in PMSHELL) - Fixed a possible bitmap race - Fixed possible problem on large disks - You can now delete open files - Fixed a nondestructive race in rename -1.97 Support for HPFS v3 (on large partitions) - Fixed a bug that it didn't allow creation of files > 128M (it should be 2G) + Fixed a bug with i_blocks (du sometimes didn't display correct values) + + Directories have no longer archive attribute set (some programs don't like + it) + + Fixed a bug that it set badly one flag in large anode tree (it was not + destructive) +1.95 Fixed one buffer leak, that could happen on corrupted filesystem + + Fixed one bug in allocation in 1.94 +1.96 Added workaround for one bug in OS/2 (HPFS locked up, HPFS386 reported + error sometimes when opening directories in PMSHELL) + + Fixed a possible bitmap race + + Fixed possible problem on large disks + + You can now delete open files + + Fixed a nondestructive race in rename +1.97 Support for HPFS v3 (on large partitions) + + ZFixed a bug that it didn't allow creation of files > 128M + (it should be 2G) 1.97.1 Changed names of global symbols + Fixed a bug when chmoding or chowning root directory -1.98 Fixed a deadlock when using old_readdir - Better directory handling; workaround for "unbalanced tree" bug in OS/2 -1.99 Corrected a possible problem when there's not enough space while deleting - file - Now it tries to truncate the file if there's not enough space when deleting - Removed a lot of redundant code -2.00 Fixed a bug in rename (it was there since 1.96) - Better anti-fragmentation strategy -2.01 Fixed problem with directory listing over NFS - Directory lseek now checks for proper parameters - Fixed race-condition in buffer code - it is in all filesystems in Linux; - when reading device (cat /dev/hda) while creating files on it, files - could be damaged -2.02 Workaround for bug in breada in Linux. breada could cause accesses beyond - end of partition -2.03 Char, block devices and pipes are correctly created - Fixed non-crashing race in unlink (Alexander Viro) - Now it works with Japanese version of OS/2 -2.04 Fixed error when ftruncate used to extend file -2.05 Fixed crash when got mount parameters without = - Fixed crash when allocation of anode failed due to full disk - Fixed some crashes when block io or inode allocation failed -2.06 Fixed some crash on corrupted disk structures - Better allocation strategy - Reschedule points added so that it doesn't lock CPU long time - It should work in read-only mode on Warp Server -2.07 More fixes for Warp Server. Now it really works -2.08 Creating new files is not so slow on large disks - An attempt to sync deleted file does not generate filesystem error -2.09 Fixed error on extremely fragmented files - - - vim: set textwidth=80: +1.98 Fixed a deadlock when using old_readdir + Better directory handling; workaround for "unbalanced tree" bug in OS/2 +1.99 Corrected a possible problem when there's not enough space while deleting + file + + Now it tries to truncate the file if there's not enough space when + deleting + + Removed a lot of redundant code +2.00 Fixed a bug in rename (it was there since 1.96) + Better anti-fragmentation strategy +2.01 Fixed problem with directory listing over NFS + + Directory lseek now checks for proper parameters + + Fixed race-condition in buffer code - it is in all filesystems in Linux; + when reading device (cat /dev/hda) while creating files on it, files + could be damaged +2.02 Workaround for bug in breada in Linux. breada could cause accesses beyond + end of partition +2.03 Char, block devices and pipes are correctly created + + Fixed non-crashing race in unlink (Alexander Viro) + + Now it works with Japanese version of OS/2 +2.04 Fixed error when ftruncate used to extend file +2.05 Fixed crash when got mount parameters without = + + Fixed crash when allocation of anode failed due to full disk + + Fixed some crashes when block io or inode allocation failed +2.06 Fixed some crash on corrupted disk structures + + Better allocation strategy + + Reschedule points added so that it doesn't lock CPU long time + + It should work in read-only mode on Warp Server +2.07 More fixes for Warp Server. Now it really works +2.08 Creating new files is not so slow on large disks + + An attempt to sync deleted file does not generate filesystem error +2.09 Fixed error on extremely fragmented files +====== ========================================================================= diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst index 386eaad008b2..e7b46dac7079 100644 --- a/Documentation/filesystems/index.rst +++ b/Documentation/filesystems/index.rst @@ -1,3 +1,5 @@ +.. _filesystems_index: + =============================== Filesystems in the Linux kernel =============================== @@ -46,8 +48,53 @@ Documentation for filesystem implementations. .. toctree:: :maxdepth: 2 + 9p + adfs + affs + afs autofs + autofs-mount-control + befs + bfs + btrfs + ceph + cramfs + debugfs + dlmfs + ecryptfs + efivarfs + erofs + ext2 + ext3 + f2fs + gfs2 + gfs2-uevents + hfs + hfsplus + hpfs fuse + inotify + isofs + nilfs2 + nfs/index + ntfs + ocfs2 + ocfs2-online-filecheck + omfs + orangefs overlayfs + proc + qnx6 + ramfs-rootfs-initramfs + relay + romfs + squashfs + sysfs + sysv-fs + tmpfs + ubifs + ubifs-authentication.rst + udf virtiofs vfat + zonefs diff --git a/Documentation/filesystems/inotify.txt b/Documentation/filesystems/inotify.rst index 51f61db787fb..7f7ef8af0e1e 100644 --- a/Documentation/filesystems/inotify.txt +++ b/Documentation/filesystems/inotify.rst @@ -1,27 +1,36 @@ - inotify - a powerful yet simple file change notification system +.. SPDX-License-Identifier: GPL-2.0 + +=============================================================== +Inotify - A Powerful yet Simple File Change Notification System +=============================================================== Document started 15 Mar 2005 by Robert Love <rml@novell.com> + Document updated 4 Jan 2015 by Zhang Zhen <zhenzhang.zhang@huawei.com> - --Deleted obsoleted interface, just refer to manpages for user interface. + + - Deleted obsoleted interface, just refer to manpages for user interface. (i) Rationale -Q: What is the design decision behind not tying the watch to the open fd of +Q: + What is the design decision behind not tying the watch to the open fd of the watched object? -A: Watches are associated with an open inotify device, not an open file. +A: + Watches are associated with an open inotify device, not an open file. This solves the primary problem with dnotify: keeping the file open pins the file and thus, worse, pins the mount. Dnotify is therefore infeasible for use on a desktop system with removable media as the media cannot be unmounted. Watching a file should not require that it be open. -Q: What is the design decision behind using an-fd-per-instance as opposed to +Q: + What is the design decision behind using an-fd-per-instance as opposed to an fd-per-watch? -A: An fd-per-watch quickly consumes more file descriptors than are allowed, +A: + An fd-per-watch quickly consumes more file descriptors than are allowed, more fd's than are feasible to manage, and more fd's than are optimally select()-able. Yes, root can bump the per-process fd limit and yes, users can use epoll, but requiring both is a silly and extraneous requirement. @@ -29,8 +38,8 @@ A: An fd-per-watch quickly consumes more file descriptors than are allowed, spaces is thus sensible. The current design is what user-space developers want: Users initialize inotify, once, and add n watches, requiring but one fd and no twiddling with fd limits. Initializing an inotify instance two - thousand times is silly. If we can implement user-space's preferences - cleanly--and we can, the idr layer makes stuff like this trivial--then we + thousand times is silly. If we can implement user-space's preferences + cleanly--and we can, the idr layer makes stuff like this trivial--then we should. There are other good arguments. With a single fd, there is a single @@ -65,9 +74,11 @@ A: An fd-per-watch quickly consumes more file descriptors than are allowed, need not be a one-fd-per-process mapping; it is one-fd-per-queue and a process can easily want more than one queue. -Q: Why the system call approach? +Q: + Why the system call approach? -A: The poor user-space interface is the second biggest problem with dnotify. +A: + The poor user-space interface is the second biggest problem with dnotify. Signals are a terrible, terrible interface for file notification. Or for anything, for that matter. The ideal solution, from all perspectives, is a file descriptor-based one that allows basic file I/O and poll/select. diff --git a/Documentation/filesystems/isofs.rst b/Documentation/filesystems/isofs.rst new file mode 100644 index 000000000000..08fd469091d4 --- /dev/null +++ b/Documentation/filesystems/isofs.rst @@ -0,0 +1,64 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================== +ISO9660 Filesystem +================== + +Mount options that are the same as for msdos and vfat partitions. + + ========= ======================================================== + gid=nnn All files in the partition will be in group nnn. + uid=nnn All files in the partition will be owned by user id nnn. + umask=nnn The permission mask (see umask(1)) for the partition. + ========= ======================================================== + +Mount options that are the same as vfat partitions. These are only useful +when using discs encoded using Microsoft's Joliet extensions. + + ============== ============================================================= + iocharset=name Character set to use for converting from Unicode to + ASCII. Joliet filenames are stored in Unicode format, but + Unix for the most part doesn't know how to deal with Unicode. + There is also an option of doing UTF-8 translations with the + utf8 option. + utf8 Encode Unicode names in UTF-8 format. Default is no. + ============== ============================================================= + +Mount options unique to the isofs filesystem. + + ================= ============================================================ + block=512 Set the block size for the disk to 512 bytes + block=1024 Set the block size for the disk to 1024 bytes + block=2048 Set the block size for the disk to 2048 bytes + check=relaxed Matches filenames with different cases + check=strict Matches only filenames with the exact same case + cruft Try to handle badly formatted CDs. + map=off Do not map non-Rock Ridge filenames to lower case + map=normal Map non-Rock Ridge filenames to lower case + map=acorn As map=normal but also apply Acorn extensions if present + mode=xxx Sets the permissions on files to xxx unless Rock Ridge + extensions set the permissions otherwise + dmode=xxx Sets the permissions on directories to xxx unless Rock Ridge + extensions set the permissions otherwise + overriderockperm Set permissions on files and directories according to + 'mode' and 'dmode' even though Rock Ridge extensions are + present. + nojoliet Ignore Joliet extensions if they are present. + norock Ignore Rock Ridge extensions if they are present. + hide Completely strip hidden files from the file system. + showassoc Show files marked with the 'associated' bit + unhide Deprecated; showing hidden files is now default; + If given, it is a synonym for 'showassoc' which will + recreate previous unhide behavior + session=x Select number of session on multisession CD + sbsector=xxx Session begins from sector xxx + ================= ============================================================ + +Recommended documents about ISO 9660 standard are located at: + +- http://www.y-adagio.com/ +- ftp://ftp.ecma.ch/ecma-st/Ecma-119.pdf + +Quoting from the PDF "This 2nd Edition of Standard ECMA-119 is technically +identical with ISO 9660.", so it is a valid and gratis substitute of the +official ISO specification. diff --git a/Documentation/filesystems/isofs.txt b/Documentation/filesystems/isofs.txt deleted file mode 100644 index ba0a93384de0..000000000000 --- a/Documentation/filesystems/isofs.txt +++ /dev/null @@ -1,48 +0,0 @@ -Mount options that are the same as for msdos and vfat partitions. - - gid=nnn All files in the partition will be in group nnn. - uid=nnn All files in the partition will be owned by user id nnn. - umask=nnn The permission mask (see umask(1)) for the partition. - -Mount options that are the same as vfat partitions. These are only useful -when using discs encoded using Microsoft's Joliet extensions. - iocharset=name Character set to use for converting from Unicode to - ASCII. Joliet filenames are stored in Unicode format, but - Unix for the most part doesn't know how to deal with Unicode. - There is also an option of doing UTF-8 translations with the - utf8 option. - utf8 Encode Unicode names in UTF-8 format. Default is no. - -Mount options unique to the isofs filesystem. - block=512 Set the block size for the disk to 512 bytes - block=1024 Set the block size for the disk to 1024 bytes - block=2048 Set the block size for the disk to 2048 bytes - check=relaxed Matches filenames with different cases - check=strict Matches only filenames with the exact same case - cruft Try to handle badly formatted CDs. - map=off Do not map non-Rock Ridge filenames to lower case - map=normal Map non-Rock Ridge filenames to lower case - map=acorn As map=normal but also apply Acorn extensions if present - mode=xxx Sets the permissions on files to xxx unless Rock Ridge - extensions set the permissions otherwise - dmode=xxx Sets the permissions on directories to xxx unless Rock Ridge - extensions set the permissions otherwise - overriderockperm Set permissions on files and directories according to - 'mode' and 'dmode' even though Rock Ridge extensions are - present. - nojoliet Ignore Joliet extensions if they are present. - norock Ignore Rock Ridge extensions if they are present. - hide Completely strip hidden files from the file system. - showassoc Show files marked with the 'associated' bit - unhide Deprecated; showing hidden files is now default; - If given, it is a synonym for 'showassoc' which will - recreate previous unhide behavior - session=x Select number of session on multisession CD - sbsector=xxx Session begins from sector xxx - -Recommended documents about ISO 9660 standard are located at: -http://www.y-adagio.com/ -ftp://ftp.ecma.ch/ecma-st/Ecma-119.pdf -Quoting from the PDF "This 2nd Edition of Standard ECMA-119 is technically -identical with ISO 9660.", so it is a valid and gratis substitute of the -official ISO specification. diff --git a/Documentation/filesystems/nfs/index.rst b/Documentation/filesystems/nfs/index.rst new file mode 100644 index 000000000000..65805624e39b --- /dev/null +++ b/Documentation/filesystems/nfs/index.rst @@ -0,0 +1,13 @@ +=============================== +NFS +=============================== + + +.. toctree:: + :maxdepth: 1 + + pnfs + rpc-cache + rpc-server-gss + nfs41-server + knfsd-stats diff --git a/Documentation/filesystems/nfs/knfsd-stats.txt b/Documentation/filesystems/nfs/knfsd-stats.rst index 1a5d82180b84..80bcf13550de 100644 --- a/Documentation/filesystems/nfs/knfsd-stats.txt +++ b/Documentation/filesystems/nfs/knfsd-stats.rst @@ -1,7 +1,9 @@ - +============================ Kernel NFS Server Statistics ============================ +:Authors: Greg Banks <gnb@sgi.com> - 26 Mar 2009 + This document describes the format and semantics of the statistics which the kernel NFS server makes available to userspace. These statistics are available in several text form pseudo files, each of @@ -18,7 +20,7 @@ by parsing routines. All other lines contain a sequence of fields separated by whitespace. /proc/fs/nfsd/pool_stats ------------------------- +======================== This file is available in kernels from 2.6.30 onwards, if the /proc/fs/nfsd filesystem is mounted (it almost always should be). @@ -109,15 +111,12 @@ this case), or the transport can be enqueued for later attention (sockets-enqueued counts this case), or the packet can be temporarily deferred because the transport is currently being used by an nfsd thread. This last case is not very interesting and is not explicitly -counted, but can be inferred from the other counters thus: +counted, but can be inferred from the other counters thus:: -packets-deferred = packets-arrived - ( sockets-enqueued + threads-woken ) + packets-deferred = packets-arrived - ( sockets-enqueued + threads-woken ) More ----- -Descriptions of the other statistics file should go here. - +==== -Greg Banks <gnb@sgi.com> -26 Mar 2009 +Descriptions of the other statistics file should go here. diff --git a/Documentation/filesystems/nfs/nfs41-server.rst b/Documentation/filesystems/nfs/nfs41-server.rst new file mode 100644 index 000000000000..16b5f02f81c3 --- /dev/null +++ b/Documentation/filesystems/nfs/nfs41-server.rst @@ -0,0 +1,256 @@ +============================= +NFSv4.1 Server Implementation +============================= + +Server support for minorversion 1 can be controlled using the +/proc/fs/nfsd/versions control file. The string output returned +by reading this file will contain either "+4.1" or "-4.1" +correspondingly. + +Currently, server support for minorversion 1 is enabled by default. +It can be disabled at run time by writing the string "-4.1" to +the /proc/fs/nfsd/versions control file. Note that to write this +control file, the nfsd service must be taken down. You can use rpc.nfsd +for this; see rpc.nfsd(8). + +(Warning: older servers will interpret "+4.1" and "-4.1" as "+4" and +"-4", respectively. Therefore, code meant to work on both new and old +kernels must turn 4.1 on or off *before* turning support for version 4 +on or off; rpc.nfsd does this correctly.) + +The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based +on RFC 5661. + +From the many new features in NFSv4.1 the current implementation +focuses on the mandatory-to-implement NFSv4.1 Sessions, providing +"exactly once" semantics and better control and throttling of the +resources allocated for each client. + +The table below, taken from the NFSv4.1 document, lists +the operations that are mandatory to implement (REQ), optional +(OPT), and NFSv4.0 operations that are required not to implement (MNI) +in minor version 1. The first column indicates the operations that +are not supported yet by the linux server implementation. + +The OPTIONAL features identified and their abbreviations are as follows: + +- **pNFS** Parallel NFS +- **FDELG** File Delegations +- **DDELG** Directory Delegations + +The following abbreviations indicate the linux server implementation status. + +- **I** Implemented NFSv4.1 operations. +- **NS** Not Supported. +- **NS\*** Unimplemented optional feature. + +Operations +========== + ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| Implementation status | Operation | REQ,REC, OPT or NMI | Feature (REQ, REC or OPT) | Definition | ++=======================+======================+=====================+===========================+================+ +| | ACCESS | REQ | | Section 18.1 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| I | BACKCHANNEL_CTL | REQ | | Section 18.33 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| I | BIND_CONN_TO_SESSION | REQ | | Section 18.34 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | CLOSE | REQ | | Section 18.2 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | COMMIT | REQ | | Section 18.3 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | CREATE | REQ | | Section 18.4 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| I | CREATE_SESSION | REQ | | Section 18.36 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| NS* | DELEGPURGE | OPT | FDELG (REQ) | Section 18.5 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | DELEGRETURN | OPT | FDELG, | Section 18.6 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | | | DDELG, pNFS | | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | | | (REQ) | | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| I | DESTROY_CLIENTID | REQ | | Section 18.50 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| I | DESTROY_SESSION | REQ | | Section 18.37 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| I | EXCHANGE_ID | REQ | | Section 18.35 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| I | FREE_STATEID | REQ | | Section 18.38 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | GETATTR | REQ | | Section 18.7 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| I | GETDEVICEINFO | OPT | pNFS (REQ) | Section 18.40 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| NS* | GETDEVICELIST | OPT | pNFS (OPT) | Section 18.41 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | GETFH | REQ | | Section 18.8 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| NS* | GET_DIR_DELEGATION | OPT | DDELG (REQ) | Section 18.39 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| I | LAYOUTCOMMIT | OPT | pNFS (REQ) | Section 18.42 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| I | LAYOUTGET | OPT | pNFS (REQ) | Section 18.43 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| I | LAYOUTRETURN | OPT | pNFS (REQ) | Section 18.44 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | LINK | OPT | | Section 18.9 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | LOCK | REQ | | Section 18.10 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | LOCKT | REQ | | Section 18.11 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | LOCKU | REQ | | Section 18.12 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | LOOKUP | REQ | | Section 18.13 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | LOOKUPP | REQ | | Section 18.14 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | NVERIFY | REQ | | Section 18.15 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | OPEN | REQ | | Section 18.16 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| NS* | OPENATTR | OPT | | Section 18.17 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | OPEN_CONFIRM | MNI | | N/A | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | OPEN_DOWNGRADE | REQ | | Section 18.18 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | PUTFH | REQ | | Section 18.19 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | PUTPUBFH | REQ | | Section 18.20 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | PUTROOTFH | REQ | | Section 18.21 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | READ | REQ | | Section 18.22 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | READDIR | REQ | | Section 18.23 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | READLINK | OPT | | Section 18.24 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | RECLAIM_COMPLETE | REQ | | Section 18.51 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | RELEASE_LOCKOWNER | MNI | | N/A | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | REMOVE | REQ | | Section 18.25 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | RENAME | REQ | | Section 18.26 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | RENEW | MNI | | N/A | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | RESTOREFH | REQ | | Section 18.27 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | SAVEFH | REQ | | Section 18.28 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| | SECINFO | REQ | | Section 18.29 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| 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 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ +| 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 | ++-----------------------+----------------------+---------------------+---------------------------+----------------+ + + +Callback Operations +=================== ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| Implementation status | Operation | REQ,REC, OPT or NMI | Feature (REQ, REC or OPT) | Definition | ++=======================+=========================+=====================+===========================+===============+ +| | CB_GETATTR | OPT | FDELG (REQ) | Section 20.1 | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| I | CB_LAYOUTRECALL | OPT | pNFS (REQ) | Section 20.3 | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| NS* | CB_NOTIFY | OPT | DDELG (REQ) | Section 20.4 | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| NS* | CB_NOTIFY_DEVICEID | OPT | pNFS (OPT) | Section 20.12 | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| NS* | CB_NOTIFY_LOCK | OPT | | Section 20.11 | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| NS* | CB_PUSH_DELEG | OPT | FDELG (OPT) | Section 20.5 | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| | CB_RECALL | OPT | FDELG, | Section 20.2 | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| | | | DDELG, pNFS | | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| | | | (REQ) | | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| NS* | CB_RECALL_ANY | OPT | FDELG, | Section 20.6 | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| | | | DDELG, pNFS | | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| | | | (REQ) | | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| NS | CB_RECALL_SLOT | REQ | | Section 20.8 | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| NS* | CB_RECALLABLE_OBJ_AVAIL | OPT | DDELG, pNFS | Section 20.7 | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| | | | (REQ) | | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| I | CB_SEQUENCE | OPT | FDELG, | Section 20.9 | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| | | | DDELG, pNFS | | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| | | | (REQ) | | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| NS* | CB_WANTS_CANCELLED | OPT | FDELG, | Section 20.10 | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| | | | DDELG, pNFS | | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ +| | | | (REQ) | | ++-----------------------+-------------------------+---------------------+---------------------------+---------------+ + + +Implementation notes: +===================== + +SSV: + The spec claims this is mandatory, but we don't actually know of any + implementations, so we're ignoring it for now. The server returns + NFS4ERR_ENCR_ALG_UNSUPP on EXCHANGE_ID, which should be future-proof. + +GSS on the backchannel: + Again, theoretically required but not widely implemented (in + particular, the current Linux client doesn't request it). We return + NFS4ERR_ENCR_ALG_UNSUPP on CREATE_SESSION. + +DELEGPURGE: + mandatory only for servers that support CLAIM_DELEGATE_PREV and/or + CLAIM_DELEG_PREV_FH (which allows clients to keep delegations that + persist across client reboots). Thus we need not implement this for + now. + +EXCHANGE_ID: + implementation ids are ignored + +CREATE_SESSION: + backchannel attributes are ignored + +SEQUENCE: + no support for dynamic slot table renegotiation (optional) + +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 + fail to live up to the promise we made in CREATE_SESSION fore channel + negotiation. + +See also http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues. diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt deleted file mode 100644 index 682a59fabe3f..000000000000 --- a/Documentation/filesystems/nfs/nfs41-server.txt +++ /dev/null @@ -1,173 +0,0 @@ -NFSv4.1 Server Implementation - -Server support for minorversion 1 can be controlled using the -/proc/fs/nfsd/versions control file. The string output returned -by reading this file will contain either "+4.1" or "-4.1" -correspondingly. - -Currently, server support for minorversion 1 is enabled by default. -It can be disabled at run time by writing the string "-4.1" to -the /proc/fs/nfsd/versions control file. Note that to write this -control file, the nfsd service must be taken down. You can use rpc.nfsd -for this; see rpc.nfsd(8). - -(Warning: older servers will interpret "+4.1" and "-4.1" as "+4" and -"-4", respectively. Therefore, code meant to work on both new and old -kernels must turn 4.1 on or off *before* turning support for version 4 -on or off; rpc.nfsd does this correctly.) - -The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based -on RFC 5661. - -From the many new features in NFSv4.1 the current implementation -focuses on the mandatory-to-implement NFSv4.1 Sessions, providing -"exactly once" semantics and better control and throttling of the -resources allocated for each client. - -The table below, taken from the NFSv4.1 document, lists -the operations that are mandatory to implement (REQ), optional -(OPT), and NFSv4.0 operations that are required not to implement (MNI) -in minor version 1. The first column indicates the operations that -are not supported yet by the linux server implementation. - -The OPTIONAL features identified and their abbreviations are as follows: - pNFS Parallel NFS - FDELG File Delegations - DDELG Directory Delegations - -The following abbreviations indicate the linux server implementation status. - I Implemented NFSv4.1 operations. - NS Not Supported. - NS* Unimplemented optional feature. - -Operations - - +----------------------+------------+--------------+----------------+ - | Operation | REQ, REC, | Feature | Definition | - | | OPT, or | (REQ, REC, | | - | | MNI | or OPT) | | - +----------------------+------------+--------------+----------------+ - | ACCESS | REQ | | Section 18.1 | -I | BACKCHANNEL_CTL | REQ | | Section 18.33 | -I | BIND_CONN_TO_SESSION | REQ | | Section 18.34 | - | CLOSE | REQ | | Section 18.2 | - | COMMIT | REQ | | Section 18.3 | - | CREATE | REQ | | Section 18.4 | -I | CREATE_SESSION | REQ | | Section 18.36 | -NS*| DELEGPURGE | OPT | FDELG (REQ) | Section 18.5 | - | DELEGRETURN | OPT | FDELG, | Section 18.6 | - | | | DDELG, pNFS | | - | | | (REQ) | | -I | DESTROY_CLIENTID | REQ | | Section 18.50 | -I | DESTROY_SESSION | REQ | | Section 18.37 | -I | EXCHANGE_ID | REQ | | Section 18.35 | -I | FREE_STATEID | REQ | | Section 18.38 | - | GETATTR | REQ | | Section 18.7 | -I | GETDEVICEINFO | OPT | pNFS (REQ) | Section 18.40 | -NS*| GETDEVICELIST | OPT | pNFS (OPT) | Section 18.41 | - | GETFH | REQ | | Section 18.8 | -NS*| GET_DIR_DELEGATION | OPT | DDELG (REQ) | Section 18.39 | -I | LAYOUTCOMMIT | OPT | pNFS (REQ) | Section 18.42 | -I | LAYOUTGET | OPT | pNFS (REQ) | Section 18.43 | -I | LAYOUTRETURN | OPT | pNFS (REQ) | Section 18.44 | - | LINK | OPT | | Section 18.9 | - | LOCK | REQ | | Section 18.10 | - | LOCKT | REQ | | Section 18.11 | - | LOCKU | REQ | | Section 18.12 | - | LOOKUP | REQ | | Section 18.13 | - | LOOKUPP | REQ | | Section 18.14 | - | NVERIFY | REQ | | Section 18.15 | - | OPEN | REQ | | Section 18.16 | -NS*| OPENATTR | OPT | | Section 18.17 | - | OPEN_CONFIRM | MNI | | N/A | - | OPEN_DOWNGRADE | REQ | | Section 18.18 | - | PUTFH | REQ | | Section 18.19 | - | PUTPUBFH | REQ | | Section 18.20 | - | PUTROOTFH | REQ | | Section 18.21 | - | READ | REQ | | Section 18.22 | - | READDIR | REQ | | Section 18.23 | - | READLINK | OPT | | Section 18.24 | - | RECLAIM_COMPLETE | REQ | | Section 18.51 | - | RELEASE_LOCKOWNER | MNI | | N/A | - | REMOVE | REQ | | Section 18.25 | - | RENAME | REQ | | Section 18.26 | - | RENEW | MNI | | N/A | - | RESTOREFH | REQ | | Section 18.27 | - | SAVEFH | REQ | | Section 18.28 | - | SECINFO | REQ | | Section 18.29 | -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 | -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 | - -Callback Operations - - +-------------------------+-----------+-------------+---------------+ - | Operation | REQ, REC, | Feature | Definition | - | | OPT, or | (REQ, REC, | | - | | MNI | or OPT) | | - +-------------------------+-----------+-------------+---------------+ - | CB_GETATTR | OPT | FDELG (REQ) | Section 20.1 | -I | CB_LAYOUTRECALL | OPT | pNFS (REQ) | Section 20.3 | -NS*| CB_NOTIFY | OPT | DDELG (REQ) | Section 20.4 | -NS*| CB_NOTIFY_DEVICEID | OPT | pNFS (OPT) | Section 20.12 | -NS*| CB_NOTIFY_LOCK | OPT | | Section 20.11 | -NS*| CB_PUSH_DELEG | OPT | FDELG (OPT) | Section 20.5 | - | CB_RECALL | OPT | FDELG, | Section 20.2 | - | | | DDELG, pNFS | | - | | | (REQ) | | -NS*| CB_RECALL_ANY | OPT | FDELG, | Section 20.6 | - | | | DDELG, pNFS | | - | | | (REQ) | | -NS | CB_RECALL_SLOT | REQ | | Section 20.8 | -NS*| CB_RECALLABLE_OBJ_AVAIL | OPT | DDELG, pNFS | Section 20.7 | - | | | (REQ) | | -I | CB_SEQUENCE | OPT | FDELG, | Section 20.9 | - | | | DDELG, pNFS | | - | | | (REQ) | | -NS*| CB_WANTS_CANCELLED | OPT | FDELG, | Section 20.10 | - | | | DDELG, pNFS | | - | | | (REQ) | | - +-------------------------+-----------+-------------+---------------+ - -Implementation notes: - -SSV: -* The spec claims this is mandatory, but we don't actually know of any - implementations, so we're ignoring it for now. The server returns - NFS4ERR_ENCR_ALG_UNSUPP on EXCHANGE_ID, which should be future-proof. - -GSS on the backchannel: -* Again, theoretically required but not widely implemented (in - particular, the current Linux client doesn't request it). We return - NFS4ERR_ENCR_ALG_UNSUPP on CREATE_SESSION. - -DELEGPURGE: -* mandatory only for servers that support CLAIM_DELEGATE_PREV and/or - CLAIM_DELEG_PREV_FH (which allows clients to keep delegations that - persist across client reboots). Thus we need not implement this for - now. - -EXCHANGE_ID: -* implementation ids are ignored - -CREATE_SESSION: -* backchannel attributes are ignored - -SEQUENCE: -* no support for dynamic slot table renegotiation (optional) - -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 - fail to live up to the promise we made in CREATE_SESSION fore channel - negotiation. - -See also http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues. diff --git a/Documentation/filesystems/nfs/pnfs.txt b/Documentation/filesystems/nfs/pnfs.rst index 80dc0bdc302a..7c470ecdc3a9 100644 --- a/Documentation/filesystems/nfs/pnfs.txt +++ b/Documentation/filesystems/nfs/pnfs.rst @@ -1,15 +1,17 @@ -Reference counting in pnfs: +========================== +Reference counting in pnfs ========================== The are several inter-related caches. We have layouts which can reference multiple devices, each of which can reference multiple data servers. Each data server can be referenced by multiple devices. Each device -can be referenced by multiple layouts. To keep all of this straight, +can be referenced by multiple layouts. To keep all of this straight, we need to reference count. struct pnfs_layout_hdr ----------------------- +====================== + The on-the-wire command LAYOUTGET corresponds to struct pnfs_layout_segment, usually referred to by the variable name lseg. Each nfs_inode may hold a pointer to a cache of these layout @@ -25,7 +27,8 @@ the reference count, as the layout is kept around by the lseg that keeps it in the list. deviceid_cache --------------- +============== + lsegs reference device ids, which are resolved per nfs_client and layout driver type. The device ids are held in a RCU cache (struct nfs4_deviceid_cache). The cache itself is referenced across each @@ -38,24 +41,26 @@ justification, but seems reasonable given that we can have multiple deviceid's per filesystem, and multiple filesystems per nfs_client. The hash code is copied from the nfsd code base. A discussion of -hashing and variations of this algorithm can be found at: -http://groups.google.com/group/comp.lang.c/browse_thread/thread/9522965e2b8d3809 +hashing and variations of this algorithm can be found `here. +<http://groups.google.com/group/comp.lang.c/browse_thread/thread/9522965e2b8d3809>`_ data server cache ------------------ +================= + file driver devices refer to data servers, which are kept in a module level cache. Its reference is held over the lifetime of the deviceid pointing to it. lseg ----- +==== + lseg maintains an extra reference corresponding to the NFS_LSEG_VALID bit which holds it in the pnfs_layout_hdr's list. When the final lseg is removed from the pnfs_layout_hdr's list, the NFS_LAYOUT_DESTROYED bit is set, preventing any new lsegs from being added. layout drivers --------------- +============== PNFS utilizes what is called layout drivers. The STD defines 4 basic layout types: "files", "objects", "blocks", and "flexfiles". For each @@ -68,6 +73,6 @@ Blocks-layout-driver code is in: fs/nfs/blocklayout/.. directory Flexfiles-layout-driver code is in: fs/nfs/flexfilelayout/.. directory blocks-layout setup -------------------- +=================== TODO: Document the setup needs of the blocks layout driver diff --git a/Documentation/filesystems/nfs/rpc-cache.txt b/Documentation/filesystems/nfs/rpc-cache.rst index c4dac829db0f..bb164eea969b 100644 --- a/Documentation/filesystems/nfs/rpc-cache.txt +++ b/Documentation/filesystems/nfs/rpc-cache.rst @@ -1,9 +1,14 @@ - This document gives a brief introduction to the caching +========= +RPC Cache +========= + +This document gives a brief introduction to the caching mechanisms in the sunrpc layer that is used, in particular, for NFS authentication. -CACHES +Caches ====== + The caching replaces the old exports table and allows for a wide variety of values to be caches. @@ -12,6 +17,7 @@ quite possibly very different in content and use. There is a corpus of common code for managing these caches. Examples of caches that are likely to be needed are: + - mapping from IP address to client name - mapping from client name and filesystem to export options - mapping from UID to list of GIDs, to work around NFS's limitation @@ -21,6 +27,7 @@ Examples of caches that are likely to be needed are: - mapping from network identify to public key for crypto authentication. The common code handles such things as: + - general cache lookup with correct locking - supporting 'NEGATIVE' as well as positive entries - allowing an EXPIRED time on cache items, and removing @@ -35,60 +42,66 @@ The common code handles such things as: Creating a Cache ---------------- -1/ A cache needs a datum to store. This is in the form of a - structure definition that must contain a - struct cache_head +- A cache needs a datum to store. This is in the form of a + structure definition that must contain a struct cache_head as an element, usually the first. It will also contain a key and some content. Each cache element is reference counted and contains expiry and update times for use in cache management. -2/ A cache needs a "cache_detail" structure that +- A cache needs a "cache_detail" structure that describes the cache. This stores the hash table, some parameters for cache management, and some operations detailing how to work with particular cache items. - The operations requires are: - struct cache_head *alloc(void) - This simply allocates appropriate memory and returns - a pointer to the cache_detail embedded within the - structure - void cache_put(struct kref *) - This is called when the last reference to an item is - dropped. The pointer passed is to the 'ref' field - in the cache_head. cache_put should release any - references create by 'cache_init' and, if CACHE_VALID - is set, any references created by cache_update. - It should then release the memory allocated by - 'alloc'. - int match(struct cache_head *orig, struct cache_head *new) - test if the keys in the two structures match. Return - 1 if they do, 0 if they don't. - void init(struct cache_head *orig, struct cache_head *new) - Set the 'key' fields in 'new' from 'orig'. This may - include taking references to shared objects. - void update(struct cache_head *orig, struct cache_head *new) - Set the 'content' fileds in 'new' from 'orig'. - int cache_show(struct seq_file *m, struct cache_detail *cd, - struct cache_head *h) - Optional. Used to provide a /proc file that lists the - contents of a cache. This should show one item, - usually on just one line. - int cache_request(struct cache_detail *cd, struct cache_head *h, - char **bpp, int *blen) - Format a request to be send to user-space for an item - to be instantiated. *bpp is a buffer of size *blen. - bpp should be moved forward over the encoded message, - and *blen should be reduced to show how much free - space remains. Return 0 on success or <0 if not - enough room or other problem. - int cache_parse(struct cache_detail *cd, char *buf, int len) - A message from user space has arrived to fill out a - cache entry. It is in 'buf' of length 'len'. - cache_parse should parse this, find the item in the - cache with sunrpc_cache_lookup_rcu, and update the item - with sunrpc_cache_update. - - -3/ A cache needs to be registered using cache_register(). This + + The operations are: + + struct cache_head \*alloc(void) + This simply allocates appropriate memory and returns + a pointer to the cache_detail embedded within the + structure + + void cache_put(struct kref \*) + This is called when the last reference to an item is + dropped. The pointer passed is to the 'ref' field + in the cache_head. cache_put should release any + references create by 'cache_init' and, if CACHE_VALID + is set, any references created by cache_update. + It should then release the memory allocated by + 'alloc'. + + int match(struct cache_head \*orig, struct cache_head \*new) + test if the keys in the two structures match. Return + 1 if they do, 0 if they don't. + + void init(struct cache_head \*orig, struct cache_head \*new) + Set the 'key' fields in 'new' from 'orig'. This may + include taking references to shared objects. + + void update(struct cache_head \*orig, struct cache_head \*new) + Set the 'content' fileds in 'new' from 'orig'. + + int cache_show(struct seq_file \*m, struct cache_detail \*cd, struct cache_head \*h) + Optional. Used to provide a /proc file that lists the + contents of a cache. This should show one item, + usually on just one line. + + int cache_request(struct cache_detail \*cd, struct cache_head \*h, char \*\*bpp, int \*blen) + Format a request to be send to user-space for an item + to be instantiated. \*bpp is a buffer of size \*blen. + bpp should be moved forward over the encoded message, + and \*blen should be reduced to show how much free + space remains. Return 0 on success or <0 if not + enough room or other problem. + + int cache_parse(struct cache_detail \*cd, char \*buf, int len) + A message from user space has arrived to fill out a + cache entry. It is in 'buf' of length 'len'. + cache_parse should parse this, find the item in the + cache with sunrpc_cache_lookup_rcu, and update the item + with sunrpc_cache_update. + + +- A cache needs to be registered using cache_register(). This includes it on a list of caches that will be regularly cleaned to discard old data. @@ -107,7 +120,7 @@ cache_check will return -ENOENT in the entry is negative or if an up call is needed but not possible, -EAGAIN if an upcall is pending, or 0 if the data is valid; -cache_check can be passed a "struct cache_req *". This structure is +cache_check can be passed a "struct cache_req\*". This structure is typically embedded in the actual request and can be used to create a deferred copy of the request (struct cache_deferred_req). This is done when the found cache item is not uptodate, but the is reason to @@ -139,9 +152,11 @@ The 'channel' works a bit like a datagram socket. Each 'write' is passed as a whole to the cache for parsing and interpretation. Each cache can treat the write requests differently, but it is expected that a message written will contain: + - a key - an expiry time - a content. + with the intention that an item in the cache with the give key should be create or updated to have the given content, and the expiry time should be set on that item. @@ -156,7 +171,8 @@ If there are no more requests to return, read will return EOF, but a select or poll for read will block waiting for another request to be added. -Thus a user-space helper is likely to: +Thus a user-space helper is likely to:: + open the channel. select for readable read a request @@ -175,12 +191,13 @@ Each cache should also define a "cache_request" method which takes a cache item and encodes a request into the buffer provided. -Note: If a cache has no active readers on the channel, and has had not -active readers for more than 60 seconds, further requests will not be -added to the channel but instead all lookups that do not find a valid -entry will fail. This is partly for backward compatibility: The -previous nfs exports table was deemed to be authoritative and a -failed lookup meant a definite 'no'. +.. note:: + If a cache has no active readers on the channel, and has had not + active readers for more than 60 seconds, further requests will not be + added to the channel but instead all lookups that do not find a valid + entry will fail. This is partly for backward compatibility: The + previous nfs exports table was deemed to be authoritative and a + failed lookup meant a definite 'no'. request/response format ----------------------- @@ -193,10 +210,11 @@ with precisely one newline character which should be at the end. Fields within the record should be separated by spaces, normally one. If spaces, newlines, or nul characters are needed in a field they much be quoted. two mechanisms are available: -1/ If a field begins '\x' then it must contain an even number of + +- If a field begins '\x' then it must contain an even number of hex digits, and pairs of these digits provide the bytes in the field. -2/ otherwise a \ in the field must be followed by 3 octal digits +- otherwise a \ in the field must be followed by 3 octal digits which give the code for a byte. Other characters are treated as them selves. At the very least, space, newline, nul, and '\' must be quoted in this way. diff --git a/Documentation/filesystems/nfs/rpc-server-gss.txt b/Documentation/filesystems/nfs/rpc-server-gss.rst index 310bbbaf9080..812754576845 100644 --- a/Documentation/filesystems/nfs/rpc-server-gss.txt +++ b/Documentation/filesystems/nfs/rpc-server-gss.rst @@ -1,4 +1,4 @@ - +========================================= rpcsec_gss support for kernel RPC servers ========================================= @@ -9,14 +9,17 @@ NFSv4.1 and higher don't require the client to act as a server for the purposes of authentication.) RPCGSS is specified in a few IETF documents: + - RFC2203 v1: http://tools.ietf.org/rfc/rfc2203.txt - RFC5403 v2: http://tools.ietf.org/rfc/rfc5403.txt + and there is a 3rd version being proposed: + - http://tools.ietf.org/id/draft-williams-rpcsecgssv3.txt (At draft n. 02 at the time of writing) Background ----------- +========== The RPCGSS Authentication method describes a way to perform GSSAPI Authentication for NFS. Although GSSAPI is itself completely mechanism @@ -29,6 +32,7 @@ depends on GSSAPI extensions that are KRB5 specific. GSSAPI is a complex library, and implementing it completely in kernel is unwarranted. However GSSAPI operations are fundementally separable in 2 parts: + - initial context establishment - integrity/privacy protection (signing and encrypting of individual packets) @@ -41,7 +45,7 @@ kernel, but leave the initial context establishment to userspace. We need upcalls to request userspace to perform context establishment. NFS Server Legacy Upcall Mechanism ----------------------------------- +================================== The classic upcall mechanism uses a custom text based upcall mechanism to talk to a custom daemon called rpc.svcgssd that is provide by the @@ -62,21 +66,20 @@ groups) due to limitation on the size of the buffer that can be send back to the kernel (4KiB). NFS Server New RPC Upcall Mechanism ------------------------------------ +=================================== The newer upcall mechanism uses RPC over a unix socket to a daemon called gss-proxy, implemented by a userspace program called Gssproxy. -The gss_proxy RPC protocol is currently documented here: - - https://fedorahosted.org/gss-proxy/wiki/ProtocolDocumentation +The gss_proxy RPC protocol is currently documented `here +<https://fedorahosted.org/gss-proxy/wiki/ProtocolDocumentation>`_. This upcall mechanism uses the kernel rpc client and connects to the gssproxy userspace program over a regular unix socket. The gssproxy protocol does not suffer from the size limitations of the legacy protocol. Negotiating Upcall Mechanisms ------------------------------ +============================= To provide backward compatibility, the kernel defaults to using the legacy mechanism. To switch to the new mechanism, gss-proxy must bind diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.rst index f2f3f8592a6f..6c49f04e9e0a 100644 --- a/Documentation/filesystems/nilfs2.txt +++ b/Documentation/filesystems/nilfs2.rst @@ -1,5 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +====== NILFS2 ------- +====== NILFS2 is a log-structured file system (LFS) supporting continuous snapshotting. In addition to versioning capability of the entire file @@ -25,9 +28,9 @@ available from the following download page. At least "mkfs.nilfs2", cleaner or garbage collector) are required. Details on the tools are described in the man pages included in the package. -Project web page: https://nilfs.sourceforge.io/ -Download page: https://nilfs.sourceforge.io/en/download.html -List info: http://vger.kernel.org/vger-lists.html#linux-nilfs +:Project web page: https://nilfs.sourceforge.io/ +:Download page: https://nilfs.sourceforge.io/en/download.html +:List info: http://vger.kernel.org/vger-lists.html#linux-nilfs Caveats ======= @@ -47,6 +50,7 @@ Mount options NILFS2 supports the following mount options: (*) == default +======================= ======================================================= barrier(*) This enables/disables the use of write barriers. This nobarrier requires an IO stack which can support barriers, and if nilfs gets an error on a barrier write, it will @@ -79,6 +83,7 @@ discard This enables/disables the use of discard/TRIM commands. nodiscard(*) The discard/TRIM commands are sent to the underlying block device when blocks are freed. This is useful for SSD devices and sparse/thinly-provisioned LUNs. +======================= ======================================================= Ioctls ====== @@ -87,9 +92,11 @@ There is some NILFS2 specific functionality which can be accessed by application through the system call interfaces. The list of all NILFS2 specific ioctls are shown in the table below. -Table of NILFS2 specific ioctls -.............................................................................. +Table of NILFS2 specific ioctls: + + ============================== =============================================== Ioctl Description + ============================== =============================================== NILFS_IOCTL_CHANGE_CPMODE Change mode of given checkpoint between checkpoint and snapshot state. This ioctl is used in chcp and mkcp utilities. @@ -142,11 +149,12 @@ Table of NILFS2 specific ioctls NILFS_IOCTL_SET_ALLOC_RANGE Define lower limit of segments in bytes and upper limit of segments in bytes. This ioctl is used by nilfs_resize utility. + ============================== =============================================== NILFS2 usage ============ -To use nilfs2 as a local file system, simply: +To use nilfs2 as a local file system, simply:: # mkfs -t nilfs2 /dev/block_device # mount -t nilfs2 /dev/block_device /dir @@ -157,18 +165,20 @@ This will also invoke the cleaner through the mount helper program Checkpoints and snapshots are managed by the following commands. Their manpages are included in the nilfs-utils package above. + ==== =========================================================== lscp list checkpoints or snapshots. mkcp make a checkpoint or a snapshot. chcp change an existing checkpoint to a snapshot or vice versa. rmcp invalidate specified checkpoint(s). + ==== =========================================================== -To mount a snapshot, +To mount a snapshot:: # mount -t nilfs2 -r -o cp=<cno> /dev/block_device /snap_dir where <cno> is the checkpoint number of the snapshot. -To unmount the NILFS2 mount point or snapshot, simply: +To unmount the NILFS2 mount point or snapshot, simply:: # umount /dir @@ -181,7 +191,7 @@ Disk format A nilfs2 volume is equally divided into a number of segments except for the super block (SB) and segment #0. A segment is the container of logs. Each log is composed of summary information blocks, payload -blocks, and an optional super root block (SR): +blocks, and an optional super root block (SR):: ______________________________________________________ | |SB| | Segment | Segment | Segment | ... | Segment | | @@ -200,7 +210,7 @@ blocks, and an optional super root block (SR): |_blocks__|_________________|__| The payload blocks are organized per file, and each file consists of -data blocks and B-tree node blocks: +data blocks and B-tree node blocks:: |<--- File-A --->|<--- File-B --->| _______________________________________________________________ @@ -213,7 +223,7 @@ files without data blocks or B-tree node blocks. The organization of the blocks is recorded in the summary information blocks, which contains a header structure (nilfs_segment_summary), per -file structures (nilfs_finfo), and per block structures (nilfs_binfo): +file structures (nilfs_finfo), and per block structures (nilfs_binfo):: _________________________________________________________________________ | Summary | finfo | binfo | ... | binfo | finfo | binfo | ... | binfo |... @@ -223,7 +233,7 @@ file structures (nilfs_finfo), and per block structures (nilfs_binfo): The logs include regular files, directory files, symbolic link files and several meta data files. The mata data files are the files used to maintain file system meta data. The current version of NILFS2 uses -the following meta data files: +the following meta data files:: 1) Inode file (ifile) -- Stores on-disk inodes 2) Checkpoint file (cpfile) -- Stores checkpoints @@ -232,7 +242,7 @@ the following meta data files: (DAT) block numbers. This file serves to make on-disk blocks relocatable. -The following figure shows a typical organization of the logs: +The following figure shows a typical organization of the logs:: _________________________________________________________________________ | Summary | regular file | file | ... | ifile | cpfile | sufile | DAT |SR| @@ -250,7 +260,7 @@ three special inodes, inodes for the DAT, cpfile, and sufile. Inodes of regular files, directories, symlinks and other special files, are included in the ifile. The inode of ifile itself is included in the corresponding checkpoint entry in the cpfile. Thus, the hierarchy -among NILFS2 files can be depicted as follows: +among NILFS2 files can be depicted as follows:: Super block (SB) | diff --git a/Documentation/filesystems/ntfs.txt b/Documentation/filesystems/ntfs.rst index 553f10d03076..5bb093a26485 100644 --- a/Documentation/filesystems/ntfs.txt +++ b/Documentation/filesystems/ntfs.rst @@ -1,19 +1,21 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================ The Linux NTFS filesystem driver ================================ -Table of contents -================= +.. Table of contents -- Overview -- Web site -- Features -- Supported mount options -- Known bugs and (mis-)features -- Using NTFS volume and stripe sets - - The Device-Mapper driver - - The Software RAID / MD driver - - Limitations when using the MD driver + - Overview + - Web site + - Features + - Supported mount options + - Known bugs and (mis-)features + - Using NTFS volume and stripe sets + - The Device-Mapper driver + - The Software RAID / MD driver + - Limitations when using the MD driver Overview @@ -66,8 +68,10 @@ Features partition by creating a large file while in Windows and then loopback mounting the file while in Linux and creating a Linux filesystem on it that is used to install Linux on it. -- A comparison of the two drivers using: +- A comparison of the two drivers using:: + time find . -type f -exec md5sum "{}" \; + run three times in sequence with each driver (after a reboot) on a 1.4GiB NTFS partition, showed the new driver to be 20% faster in total time elapsed (from 9:43 minutes on average down to 7:53). The time spent in user space @@ -104,6 +108,7 @@ In addition to the generic mount options described by the manual page for the mount command (man 8 mount, also see man 5 fstab), the NTFS driver supports the following mount options: +======================= ======================================================= iocharset=name Deprecated option. Still supported but please use nls=name in the future. See description for nls=name. @@ -175,16 +180,22 @@ disable_sparse=<BOOL> If disable_sparse is specified, creation of sparse errors=opt What to do when critical filesystem errors are found. Following values can be used for "opt": - continue: DEFAULT, try to clean-up as much as + + ======== ========================================= + continue DEFAULT, try to clean-up as much as possible, e.g. marking a corrupt inode as bad so it is no longer accessed, and then continue. - recover: At present only supported is recovery of + recover At present only supported is recovery of the boot sector from the backup copy. If read-only mount, the recovery is done in memory only and not written to disk. - Note that the options are additive, i.e. specifying: + ======== ========================================= + + Note that the options are additive, i.e. specifying:: + errors=continue,errors=recover + means the driver will attempt to recover and if that fails it will clean-up as much as possible and continue. @@ -202,12 +213,18 @@ mft_zone_multiplier= Set the MFT zone multiplier for the volume (this In general use the default. If you have a lot of small files then use a higher value. The values have the following meaning: + + ===== ================================= Value MFT zone size (% of volume size) + ===== ================================= 1 12.5% 2 25% 3 37.5% 4 50% + ===== ================================= + Note this option is irrelevant for read-only mounts. +======================= ======================================================= Known bugs and (mis-)features @@ -252,18 +269,18 @@ To create the table describing your volume you will need to know each of its components and their sizes in sectors, i.e. multiples of 512-byte blocks. For NT4 fault tolerant volumes you can obtain the sizes using fdisk. So for -example if one of your partitions is /dev/hda2 you would do: +example if one of your partitions is /dev/hda2 you would do:: -$ fdisk -ul /dev/hda + $ fdisk -ul /dev/hda -Disk /dev/hda: 81.9 GB, 81964302336 bytes -255 heads, 63 sectors/track, 9964 cylinders, total 160086528 sectors -Units = sectors of 1 * 512 = 512 bytes + Disk /dev/hda: 81.9 GB, 81964302336 bytes + 255 heads, 63 sectors/track, 9964 cylinders, total 160086528 sectors + Units = sectors of 1 * 512 = 512 bytes - Device Boot Start End Blocks Id System - /dev/hda1 * 63 4209029 2104483+ 83 Linux - /dev/hda2 4209030 37768814 16779892+ 86 NTFS - /dev/hda3 37768815 46170809 4200997+ 83 Linux + Device Boot Start End Blocks Id System + /dev/hda1 * 63 4209029 2104483+ 83 Linux + /dev/hda2 4209030 37768814 16779892+ 86 NTFS + /dev/hda3 37768815 46170809 4200997+ 83 Linux And you would know that /dev/hda2 has a size of 37768814 - 4209030 + 1 = 33559785 sectors. @@ -271,15 +288,17 @@ And you would know that /dev/hda2 has a size of 37768814 - 4209030 + 1 = For Win2k and later dynamic disks, you can for example use the ldminfo utility which is part of the Linux LDM tools (the latest version at the time of writing is linux-ldm-0.0.8.tar.bz2). You can download it from: + http://www.linux-ntfs.org/ + Simply extract the downloaded archive (tar xvjf linux-ldm-0.0.8.tar.bz2), go into it (cd linux-ldm-0.0.8) and change to the test directory (cd test). You will find the precompiled (i386) ldminfo utility there. NOTE: You will not be able to compile this yourself easily so use the binary version! -Then you would use ldminfo in dump mode to obtain the necessary information: +Then you would use ldminfo in dump mode to obtain the necessary information:: -$ ./ldminfo --dump /dev/hda + $ ./ldminfo --dump /dev/hda This would dump the LDM database found on /dev/hda which describes all of your dynamic disks and all the volumes on them. At the bottom you will see the @@ -305,42 +324,36 @@ give you the correct information to do this. Assuming you know all your devices and their sizes things are easy. For a linear raid the table would look like this (note all values are in -512-byte sectors): +512-byte sectors):: ---- cut here --- -# Offset into Size of this Raid type Device Start sector -# volume device of device -0 1028161 linear /dev/hda1 0 -1028161 3903762 linear /dev/hdb2 0 -4931923 2103211 linear /dev/hdc1 0 ---- cut here --- + # Offset into Size of this Raid type Device Start sector + # volume device of device + 0 1028161 linear /dev/hda1 0 + 1028161 3903762 linear /dev/hdb2 0 + 4931923 2103211 linear /dev/hdc1 0 For a striped volume, i.e. raid level 0, you will need to know the chunk size you used when creating the volume. Windows uses 64kiB as the default, so it will probably be this unless you changes the defaults when creating the array. For a raid level 0 the table would look like this (note all values are in -512-byte sectors): +512-byte sectors):: ---- cut here --- -# Offset Size Raid Number Chunk 1st Start 2nd Start -# into of the type of size Device in Device in -# volume volume stripes device device -0 2056320 striped 2 128 /dev/hda1 0 /dev/hdb1 0 ---- cut here --- + # Offset Size Raid Number Chunk 1st Start 2nd Start + # into of the type of size Device in Device in + # volume volume stripes device device + 0 2056320 striped 2 128 /dev/hda1 0 /dev/hdb1 0 If there are more than two devices, just add each of them to the end of the line. Finally, for a mirrored volume, i.e. raid level 1, the table would look like -this (note all values are in 512-byte sectors): +this (note all values are in 512-byte sectors):: ---- cut here --- -# Ofs Size Raid Log Number Region Should Number Source Start Target Start -# in of the type type of log size sync? of Device in Device in -# vol volume params mirrors Device Device -0 2056320 mirror core 2 16 nosync 2 /dev/hda1 0 /dev/hdb1 0 ---- cut here --- + # Ofs Size Raid Log Number Region Should Number Source Start Target Start + # in of the type type of log size sync? of Device in Device in + # vol volume params mirrors Device Device + 0 2056320 mirror core 2 16 nosync 2 /dev/hda1 0 /dev/hdb1 0 If you are mirroring to multiple devices you can specify further targets at the end of the line. @@ -353,17 +366,17 @@ to the "Target Device" or if you specified multiple target devices to all of them. Once you have your table, save it in a file somewhere (e.g. /etc/ntfsvolume1), -and hand it over to dmsetup to work with, like so: +and hand it over to dmsetup to work with, like so:: -$ dmsetup create myvolume1 /etc/ntfsvolume1 + $ dmsetup create myvolume1 /etc/ntfsvolume1 You can obviously replace "myvolume1" with whatever name you like. If it all worked, you will now have the device /dev/device-mapper/myvolume1 which you can then just use as an argument to the mount command as usual to -mount the ntfs volume. For example: +mount the ntfs volume. For example:: -$ mount -t ntfs -o ro /dev/device-mapper/myvolume1 /mnt/myvol1 + $ mount -t ntfs -o ro /dev/device-mapper/myvolume1 /mnt/myvol1 (You need to create the directory /mnt/myvol1 first and of course you can use anything you like instead of /mnt/myvol1 as long as it is an existing @@ -395,18 +408,18 @@ Windows by default uses a stripe chunk size of 64k, so you probably want the "chunk-size 64k" option for each raid-disk, too. For example, if you have a stripe set consisting of two partitions /dev/hda5 -and /dev/hdb1 your /etc/raidtab would look like this: - -raiddev /dev/md0 - raid-level 0 - nr-raid-disks 2 - nr-spare-disks 0 - persistent-superblock 0 - chunk-size 64k - device /dev/hda5 - raid-disk 0 - device /dev/hdb1 - raid-disk 1 +and /dev/hdb1 your /etc/raidtab would look like this:: + + raiddev /dev/md0 + raid-level 0 + nr-raid-disks 2 + nr-spare-disks 0 + persistent-superblock 0 + chunk-size 64k + device /dev/hda5 + raid-disk 0 + device /dev/hdb1 + raid-disk 1 For linear raid, just change the raid-level above to "raid-level linear", for mirrors, change it to "raid-level 1", and for stripe sets with parity, change @@ -427,7 +440,9 @@ Once the raidtab is setup, run for example raid0run -a to start all devices or raid0run /dev/md0 to start a particular md device, in this case /dev/md0. Then just use the mount command as usual to mount the ntfs volume using for -example: mount -t ntfs -o ro /dev/md0 /mnt/myntfsvolume +example:: + + mount -t ntfs -o ro /dev/md0 /mnt/myntfsvolume It is advisable to do the mount read-only to see if the md volume has been setup correctly to avoid the possibility of causing damage to the data on the diff --git a/Documentation/filesystems/ocfs2-online-filecheck.txt b/Documentation/filesystems/ocfs2-online-filecheck.rst index 139fab175c8a..2257bb53edc1 100644 --- a/Documentation/filesystems/ocfs2-online-filecheck.txt +++ b/Documentation/filesystems/ocfs2-online-filecheck.rst @@ -1,5 +1,8 @@ - OCFS2 online file check - ----------------------- +.. SPDX-License-Identifier: GPL-2.0 + +===================================== +OCFS2 file system - online file check +===================================== This document will describe OCFS2 online file check feature. @@ -40,7 +43,7 @@ When there are errors in the OCFS2 filesystem, they are usually accompanied by the inode number which caused the error. This inode number would be the input to check/fix the file. -There is a sysfs directory for each OCFS2 file system mounting: +There is a sysfs directory for each OCFS2 file system mounting:: /sys/fs/ocfs2/<devname>/filecheck @@ -50,34 +53,36 @@ communicate with kernel space, tell which file(inode number) will be checked or fixed. Currently, three operations are supported, which includes checking inode, fixing inode and setting the size of result record history. -1. If you want to know what error exactly happened to <inode> before fixing, do +1. If you want to know what error exactly happened to <inode> before fixing, do:: + + # echo "<inode>" > /sys/fs/ocfs2/<devname>/filecheck/check + # cat /sys/fs/ocfs2/<devname>/filecheck/check + +The output is like this:: - # echo "<inode>" > /sys/fs/ocfs2/<devname>/filecheck/check - # cat /sys/fs/ocfs2/<devname>/filecheck/check + INO DONE ERROR + 39502 1 GENERATION -The output is like this: - INO DONE ERROR -39502 1 GENERATION + <INO> lists the inode numbers. + <DONE> indicates whether the operation has been finished. + <ERROR> says what kind of errors was found. For the detailed error numbers, + please refer to the file linux/fs/ocfs2/filecheck.h. -<INO> lists the inode numbers. -<DONE> indicates whether the operation has been finished. -<ERROR> says what kind of errors was found. For the detailed error numbers, -please refer to the file linux/fs/ocfs2/filecheck.h. +2. If you determine to fix this inode, do:: -2. If you determine to fix this inode, do + # echo "<inode>" > /sys/fs/ocfs2/<devname>/filecheck/fix + # cat /sys/fs/ocfs2/<devname>/filecheck/fix - # echo "<inode>" > /sys/fs/ocfs2/<devname>/filecheck/fix - # cat /sys/fs/ocfs2/<devname>/filecheck/fix +The output is like this::: -The output is like this: - INO DONE ERROR -39502 1 SUCCESS + INO DONE ERROR + 39502 1 SUCCESS This time, the <ERROR> column indicates whether this fix is successful or not. 3. The record cache is used to store the history of check/fix results. It's default size is 10, and can be adjust between the range of 10 ~ 100. You can -adjust the size like this: +adjust the size like this:: # echo "<size>" > /sys/fs/ocfs2/<devname>/filecheck/set diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.rst index 4c49e5410595..412386bc6506 100644 --- a/Documentation/filesystems/ocfs2.txt +++ b/Documentation/filesystems/ocfs2.rst @@ -1,5 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================ OCFS2 filesystem -================== +================ + 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 @@ -14,22 +18,26 @@ OCFS2 mailing lists: http://oss.oracle.com/projects/ocfs2/mailman/ All code copyright 2005 Oracle except when otherwise noted. -CREDITS: +Credits +======= + Lots of code taken from ext3 and other projects. Authors in alphabetical order: -Joel Becker <joel.becker@oracle.com> -Zach Brown <zach.brown@oracle.com> -Mark Fasheh <mfasheh@suse.com> -Kurt Hackel <kurt.hackel@oracle.com> -Tao Ma <tao.ma@oracle.com> -Sunil Mushran <sunil.mushran@oracle.com> -Manish Singh <manish.singh@oracle.com> -Tiger Yang <tiger.yang@oracle.com> + +- Joel Becker <joel.becker@oracle.com> +- Zach Brown <zach.brown@oracle.com> +- Mark Fasheh <mfasheh@suse.com> +- Kurt Hackel <kurt.hackel@oracle.com> +- Tao Ma <tao.ma@oracle.com> +- Sunil Mushran <sunil.mushran@oracle.com> +- Manish Singh <manish.singh@oracle.com> +- Tiger Yang <tiger.yang@oracle.com> Caveats ======= Features which OCFS2 does not support yet: + - Directory change notification (F_NOTIFY) - Distributed Caching (F_SETLEASE/F_GETLEASE/break_lease) @@ -37,8 +45,10 @@ Mount options ============= OCFS2 supports the following mount options: + (*) == default +======================= ======================================================== barrier=1 This enables/disables barriers. barrier=0 disables it, barrier=1 enables it. errors=remount-ro(*) Remount the filesystem read-only on an error. @@ -104,3 +114,4 @@ journal_async_commit Commit block can be written to disk without waiting for descriptor blocks. If enabled older kernels cannot mount the device. This will enable 'journal_checksum' internally. +======================= ======================================================== diff --git a/Documentation/filesystems/omfs.rst b/Documentation/filesystems/omfs.rst new file mode 100644 index 000000000000..4c8bb3074169 --- /dev/null +++ b/Documentation/filesystems/omfs.rst @@ -0,0 +1,112 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================ +Optimized MPEG Filesystem (OMFS) +================================ + +Overview +======== + +OMFS is a filesystem created by SonicBlue for use in the ReplayTV DVR +and Rio Karma MP3 player. The filesystem is extent-based, utilizing +block sizes from 2k to 8k, with hash-based directories. This +filesystem driver may be used to read and write disks from these +devices. + +Note, it is not recommended that this FS be used in place of a general +filesystem for your own streaming media device. Native Linux filesystems +will likely perform better. + +More information is available at: + + http://linux-karma.sf.net/ + +Various utilities, including mkomfs and omfsck, are included with +omfsprogs, available at: + + http://bobcopeland.com/karma/ + +Instructions are included in its README. + +Options +======= + +OMFS supports the following mount-time options: + + ============ ======================================== + uid=n make all files owned by specified user + gid=n make all files owned by specified group + umask=xxx set permission umask to xxx + fmask=xxx set umask to xxx for files + dmask=xxx set umask to xxx for directories + ============ ======================================== + +Disk format +=========== + +OMFS discriminates between "sysblocks" and normal data blocks. The sysblock +group consists of super block information, file metadata, directory structures, +and extents. Each sysblock has a header containing CRCs of the entire +sysblock, and may be mirrored in successive blocks on the disk. A sysblock may +have a smaller size than a data block, but since they are both addressed by the +same 64-bit block number, any remaining space in the smaller sysblock is +unused. + +Sysblock header information:: + + struct omfs_header { + __be64 h_self; /* FS block where this is located */ + __be32 h_body_size; /* size of useful data after header */ + __be16 h_crc; /* crc-ccitt of body_size bytes */ + char h_fill1[2]; + u8 h_version; /* version, always 1 */ + char h_type; /* OMFS_INODE_X */ + u8 h_magic; /* OMFS_IMAGIC */ + u8 h_check_xor; /* XOR of header bytes before this */ + __be32 h_fill2; + }; + +Files and directories are both represented by omfs_inode:: + + struct omfs_inode { + struct omfs_header i_head; /* header */ + __be64 i_parent; /* parent containing this inode */ + __be64 i_sibling; /* next inode in hash bucket */ + __be64 i_ctime; /* ctime, in milliseconds */ + char i_fill1[35]; + char i_type; /* OMFS_[DIR,FILE] */ + __be32 i_fill2; + char i_fill3[64]; + char i_name[OMFS_NAMELEN]; /* filename */ + __be64 i_size; /* size of file, in bytes */ + }; + +Directories in OMFS are implemented as a large hash table. Filenames are +hashed then prepended into the bucket list beginning at OMFS_DIR_START. +Lookup requires hashing the filename, then seeking across i_sibling pointers +until a match is found on i_name. Empty buckets are represented by block +pointers with all-1s (~0). + +A file is an omfs_inode structure followed by an extent table beginning at +OMFS_EXTENT_START:: + + struct omfs_extent_entry { + __be64 e_cluster; /* start location of a set of blocks */ + __be64 e_blocks; /* number of blocks after e_cluster */ + }; + + struct omfs_extent { + __be64 e_next; /* next extent table location */ + __be32 e_extent_count; /* total # extents in this table */ + __be32 e_fill; + struct omfs_extent_entry e_entry; /* start of extent entries */ + }; + +Each extent holds the block offset followed by number of blocks allocated to +the extent. The final extent in each table is a terminator with e_cluster +being ~0 and e_blocks being ones'-complement of the total number of blocks +in the table. + +If this table overflows, a continuation inode is written and pointed to by +e_next. These have a header but lack the rest of the inode structure. + diff --git a/Documentation/filesystems/omfs.txt b/Documentation/filesystems/omfs.txt deleted file mode 100644 index 1d0d41ff5c65..000000000000 --- a/Documentation/filesystems/omfs.txt +++ /dev/null @@ -1,106 +0,0 @@ -Optimized MPEG Filesystem (OMFS) - -Overview -======== - -OMFS is a filesystem created by SonicBlue for use in the ReplayTV DVR -and Rio Karma MP3 player. The filesystem is extent-based, utilizing -block sizes from 2k to 8k, with hash-based directories. This -filesystem driver may be used to read and write disks from these -devices. - -Note, it is not recommended that this FS be used in place of a general -filesystem for your own streaming media device. Native Linux filesystems -will likely perform better. - -More information is available at: - - http://linux-karma.sf.net/ - -Various utilities, including mkomfs and omfsck, are included with -omfsprogs, available at: - - http://bobcopeland.com/karma/ - -Instructions are included in its README. - -Options -======= - -OMFS supports the following mount-time options: - - uid=n - make all files owned by specified user - gid=n - make all files owned by specified group - umask=xxx - set permission umask to xxx - fmask=xxx - set umask to xxx for files - dmask=xxx - set umask to xxx for directories - -Disk format -=========== - -OMFS discriminates between "sysblocks" and normal data blocks. The sysblock -group consists of super block information, file metadata, directory structures, -and extents. Each sysblock has a header containing CRCs of the entire -sysblock, and may be mirrored in successive blocks on the disk. A sysblock may -have a smaller size than a data block, but since they are both addressed by the -same 64-bit block number, any remaining space in the smaller sysblock is -unused. - -Sysblock header information: - -struct omfs_header { - __be64 h_self; /* FS block where this is located */ - __be32 h_body_size; /* size of useful data after header */ - __be16 h_crc; /* crc-ccitt of body_size bytes */ - char h_fill1[2]; - u8 h_version; /* version, always 1 */ - char h_type; /* OMFS_INODE_X */ - u8 h_magic; /* OMFS_IMAGIC */ - u8 h_check_xor; /* XOR of header bytes before this */ - __be32 h_fill2; -}; - -Files and directories are both represented by omfs_inode: - -struct omfs_inode { - struct omfs_header i_head; /* header */ - __be64 i_parent; /* parent containing this inode */ - __be64 i_sibling; /* next inode in hash bucket */ - __be64 i_ctime; /* ctime, in milliseconds */ - char i_fill1[35]; - char i_type; /* OMFS_[DIR,FILE] */ - __be32 i_fill2; - char i_fill3[64]; - char i_name[OMFS_NAMELEN]; /* filename */ - __be64 i_size; /* size of file, in bytes */ -}; - -Directories in OMFS are implemented as a large hash table. Filenames are -hashed then prepended into the bucket list beginning at OMFS_DIR_START. -Lookup requires hashing the filename, then seeking across i_sibling pointers -until a match is found on i_name. Empty buckets are represented by block -pointers with all-1s (~0). - -A file is an omfs_inode structure followed by an extent table beginning at -OMFS_EXTENT_START: - -struct omfs_extent_entry { - __be64 e_cluster; /* start location of a set of blocks */ - __be64 e_blocks; /* number of blocks after e_cluster */ -}; - -struct omfs_extent { - __be64 e_next; /* next extent table location */ - __be32 e_extent_count; /* total # extents in this table */ - __be32 e_fill; - struct omfs_extent_entry e_entry; /* start of extent entries */ -}; - -Each extent holds the block offset followed by number of blocks allocated to -the extent. The final extent in each table is a terminator with e_cluster -being ~0 and e_blocks being ones'-complement of the total number of blocks -in the table. - -If this table overflows, a continuation inode is written and pointed to by -e_next. These have a header but lack the rest of the inode structure. - diff --git a/Documentation/filesystems/orangefs.txt b/Documentation/filesystems/orangefs.rst index f4ba94950e3f..e41369709c5b 100644 --- a/Documentation/filesystems/orangefs.txt +++ b/Documentation/filesystems/orangefs.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======== ORANGEFS ======== @@ -21,43 +24,33 @@ Orangefs features include: * Stateless -MAILING LIST ARCHIVES +Mailing List Archives ===================== http://lists.orangefs.org/pipermail/devel_lists.orangefs.org/ -MAILING LIST SUBMISSIONS +Mailing List Submissions ======================== devel@lists.orangefs.org -DOCUMENTATION +Documentation ============= http://www.orangefs.org/documentation/ - -USERSPACE FILESYSTEM SOURCE -=========================== - -http://www.orangefs.org/download - -Orangefs versions prior to 2.9.3 would not be compatible with the -upstream version of the kernel client. - - -RUNNING ORANGEFS ON A SINGLE SERVER +Running ORANGEFS On a Single Server =================================== OrangeFS is usually run in large installations with multiple servers and clients, but a complete filesystem can be run on a single machine for development and testing. -On Fedora, install orangefs and orangefs-server. +On Fedora, install orangefs and orangefs-server:: -dnf -y install orangefs orangefs-server + dnf -y install orangefs orangefs-server There is an example server configuration file in /etc/orangefs/orangefs.conf. Change localhost to your hostname if @@ -70,29 +63,37 @@ single line. Uncomment it and change the hostname if necessary. This controls clients which use libpvfs2. This does not control the pvfs2-client-core. -Create the filesystem. +Create the filesystem:: -pvfs2-server -f /etc/orangefs/orangefs.conf + pvfs2-server -f /etc/orangefs/orangefs.conf -Start the server. +Start the server:: -systemctl start orangefs-server + systemctl start orangefs-server -Test the server. +Test the server:: -pvfs2-ping -m /pvfsmnt + pvfs2-ping -m /pvfsmnt Start the client. The module must be compiled in or loaded before this -point. +point:: -systemctl start orangefs-client + systemctl start orangefs-client -Mount the filesystem. +Mount the filesystem:: -mount -t pvfs2 tcp://localhost:3334/orangefs /pvfsmnt + mount -t pvfs2 tcp://localhost:3334/orangefs /pvfsmnt +Userspace Filesystem Source +=========================== -BUILDING ORANGEFS ON A SINGLE SERVER +http://www.orangefs.org/download + +Orangefs versions prior to 2.9.3 would not be compatible with the +upstream version of the kernel client. + + +Building ORANGEFS on a Single Server ==================================== Where OrangeFS cannot be installed from distribution packages, it may be @@ -102,49 +103,57 @@ You can omit --prefix if you don't care that things are sprinkled around in /usr/local. As of version 2.9.6, OrangeFS uses Berkeley DB by default, we will probably be changing the default to LMDB soon. -./configure --prefix=/opt/ofs --with-db-backend=lmdb +:: + + ./configure --prefix=/opt/ofs --with-db-backend=lmdb --disable-usrint -make + make -make install + make install -Create an orangefs config file. +Create an orangefs config file by running pvfs2-genconfig and +specifying a target config file. Pvfs2-genconfig will prompt you +through. Generally it works fine to take the defaults, but you +should use your server's hostname, rather than "localhost" when +it comes to that question:: -/opt/ofs/bin/pvfs2-genconfig /etc/pvfs2.conf + /opt/ofs/bin/pvfs2-genconfig /etc/pvfs2.conf -Create an /etc/pvfs2tab file. +Create an /etc/pvfs2tab file:: -echo tcp://localhost:3334/orangefs /pvfsmnt pvfs2 defaults,noauto 0 0 > \ - /etc/pvfs2tab +Localhost is fine for your pvfs2tab file: -Create the mount point you specified in the tab file if needed. + echo tcp://localhost:3334/orangefs /pvfsmnt pvfs2 defaults,noauto 0 0 > \ + /etc/pvfs2tab -mkdir /pvfsmnt +Create the mount point you specified in the tab file if needed:: -Bootstrap the server. + mkdir /pvfsmnt -/opt/ofs/sbin/pvfs2-server -f /etc/pvfs2.conf +Bootstrap the server:: -Start the server. + /opt/ofs/sbin/pvfs2-server -f /etc/pvfs2.conf -/opt/osf/sbin/pvfs2-server /etc/pvfs2.conf +Start the server:: + + /opt/ofs/sbin/pvfs2-server /etc/pvfs2.conf Now the server should be running. Pvfs2-ls is a simple -test to verify that the server is running. +test to verify that the server is running:: -/opt/ofs/bin/pvfs2-ls /pvfsmnt + /opt/ofs/bin/pvfs2-ls /pvfsmnt If stuff seems to be working, load the kernel module and -turn on the client core. +turn on the client core:: -/opt/ofs/sbin/pvfs2-client -p /opt/osf/sbin/pvfs2-client-core + /opt/ofs/sbin/pvfs2-client -p /opt/ofs/sbin/pvfs2-client-core -Mount your filesystem. +Mount your filesystem:: -mount -t pvfs2 tcp://localhost:3334/orangefs /pvfsmnt + mount -t pvfs2 tcp://`hostname`:3334/orangefs /pvfsmnt -RUNNING XFSTESTS +Running xfstests ================ It is useful to use a scratch filesystem with xfstests. This can be @@ -159,21 +168,23 @@ Then there are two FileSystem sections: orangefs and scratch. This change should be made before creating the filesystem. -pvfs2-server -f /etc/orangefs/orangefs.conf +:: + + pvfs2-server -f /etc/orangefs/orangefs.conf -To run xfstests, create /etc/xfsqa.config. +To run xfstests, create /etc/xfsqa.config:: -TEST_DIR=/orangefs -TEST_DEV=tcp://localhost:3334/orangefs -SCRATCH_MNT=/scratch -SCRATCH_DEV=tcp://localhost:3334/scratch + TEST_DIR=/orangefs + TEST_DEV=tcp://localhost:3334/orangefs + SCRATCH_MNT=/scratch + SCRATCH_DEV=tcp://localhost:3334/scratch -Then xfstests can be run +Then xfstests can be run:: -./check -pvfs2 + ./check -pvfs2 -OPTIONS +Options ======= The following mount options are accepted: @@ -193,32 +204,32 @@ The following mount options are accepted: Distributed locking is being worked on for the future. -DEBUGGING +Debugging ========= If you want the debug (GOSSIP) statements in a particular -source file (inode.c for example) go to syslog: +source file (inode.c for example) go to syslog:: echo inode > /sys/kernel/debug/orangefs/kernel-debug -No debugging (the default): +No debugging (the default):: echo none > /sys/kernel/debug/orangefs/kernel-debug -Debugging from several source files: +Debugging from several source files:: echo inode,dir > /sys/kernel/debug/orangefs/kernel-debug -All debugging: +All debugging:: echo all > /sys/kernel/debug/orangefs/kernel-debug -Get a list of all debugging keywords: +Get a list of all debugging keywords:: cat /sys/kernel/debug/orangefs/debug-help -PROTOCOL BETWEEN KERNEL MODULE AND USERSPACE +Protocol between Kernel Module and Userspace ============================================ Orangefs is a user space filesystem and an associated kernel module. @@ -234,7 +245,8 @@ The kernel module implements a pseudo device that userspace can read from and write to. Userspace can also manipulate the kernel module through the pseudo device with ioctl. -THE BUFMAP: +The Bufmap +---------- At startup userspace allocates two page-size-aligned (posix_memalign) mlocked memory buffers, one is used for IO and one is used for readdir @@ -250,7 +262,8 @@ copied from user space to kernel space with copy_from_user and is used to initialize the kernel module's "bufmap" (struct orangefs_bufmap), which then contains: - * refcnt - a reference counter + * refcnt + - a reference counter * desc_size - PVFS2_BUFMAP_DEFAULT_DESC_SIZE (4194304) - the IO buffer's partition size, which represents the filesystem's block size and is used for s_blocksize in super blocks. @@ -259,17 +272,19 @@ then contains: * desc_shift - log2(desc_size), used for s_blocksize_bits in super blocks. * total_size - the total size of the IO buffer. * page_count - the number of 4096 byte pages in the IO buffer. - * page_array - a pointer to page_count * (sizeof(struct page*)) bytes + * page_array - a pointer to ``page_count * (sizeof(struct page*))`` bytes of kcalloced memory. This memory is used as an array of pointers to each of the pages in the IO buffer through a call to get_user_pages. - * desc_array - a pointer to desc_count * (sizeof(struct orangefs_bufmap_desc)) + * desc_array - a pointer to ``desc_count * (sizeof(struct orangefs_bufmap_desc))`` bytes of kcalloced memory. This memory is further intialized: user_desc is the kernel's copy of the IO buffer's ORANGEFS_dev_map_desc structure. user_desc->ptr points to the IO buffer. - pages_per_desc = bufmap->desc_size / PAGE_SIZE - offset = 0 + :: + + pages_per_desc = bufmap->desc_size / PAGE_SIZE + offset = 0 bufmap->desc_array[0].page_array = &bufmap->page_array[offset] bufmap->desc_array[0].array_count = pages_per_desc = 1024 @@ -293,7 +308,8 @@ then contains: * readdir_index_lock - a spinlock to protect readdir_index_array during update. -OPERATIONS: +Operations +---------- The kernel module builds an "op" (struct orangefs_kernel_op_s) when it needs to communicate with userspace. Part of the op contains the "upcall" @@ -308,13 +324,19 @@ in flight at any given time. Ops are stateful: - * unknown - op was just initialized - * waiting - op is on request_list (upward bound) - * inprogr - op is in progress (waiting for downcall) - * serviced - op has matching downcall; ok - * purged - op has to start a timer since client-core + * unknown + - op was just initialized + * waiting + - op is on request_list (upward bound) + * inprogr + - op is in progress (waiting for downcall) + * serviced + - op has matching downcall; ok + * purged + - op has to start a timer since client-core exited uncleanly before servicing op - * given up - submitter has given up waiting for it + * given up + - submitter has given up waiting for it When some arbitrary userspace program needs to perform a filesystem operation on Orangefs (readdir, I/O, create, whatever) @@ -389,10 +411,15 @@ union of structs, each of which is associated with a particular response type. The several members outside of the union are: - - int32_t type - type of operation. - - int32_t status - return code for the operation. - - int64_t trailer_size - 0 unless readdir operation. - - char *trailer_buf - initialized to NULL, used during readdir operations. + + ``int32_t type`` + - type of operation. + ``int32_t status`` + - return code for the operation. + ``int64_t trailer_size`` + - 0 unless readdir operation. + ``char *trailer_buf`` + - initialized to NULL, used during readdir operations. The appropriate member inside the union is filled out for any particular response. @@ -449,18 +476,20 @@ Userspace uses writev() on /dev/pvfs2-req to pass responses to the requests made by the kernel side. A buffer_list containing: + - a pointer to the prepared response to the request from the kernel (struct pvfs2_downcall_t). - and also, in the case of a readdir request, a pointer to a buffer containing descriptors for the objects in the target directory. + ... is sent to the function (PINT_dev_write_list) which performs the writev. PINT_dev_write_list has a local iovec array: struct iovec io_array[10]; The first four elements of io_array are initialized like this for all -responses: +responses:: io_array[0].iov_base = address of local variable "proto_ver" (int32_t) io_array[0].iov_len = sizeof(int32_t) @@ -475,7 +504,7 @@ responses: of global variable vfs_request (vfs_request_t) io_array[3].iov_len = sizeof(pvfs2_downcall_t) -Readdir responses initialize the fifth element io_array like this: +Readdir responses initialize the fifth element io_array like this:: io_array[4].iov_base = contents of member trailer_buf (char *) from out_downcall member of global variable @@ -517,13 +546,13 @@ from a dentry is cheap, obtaining it from userspace is relatively expensive, hence the motivation to use the dentry when possible. The timeout values d_time and getattr_time are jiffy based, and the -code is designed to avoid the jiffy-wrap problem: +code is designed to avoid the jiffy-wrap problem:: -"In general, if the clock may have wrapped around more than once, there -is no way to tell how much time has elapsed. However, if the times t1 -and t2 are known to be fairly close, we can reliably compute the -difference in a way that takes into account the possibility that the -clock may have wrapped between times." + "In general, if the clock may have wrapped around more than once, there + is no way to tell how much time has elapsed. However, if the times t1 + and t2 are known to be fairly close, we can reliably compute the + difference in a way that takes into account the possibility that the + clock may have wrapped between times." - from course notes by instructor Andy Wang +from course notes by instructor Andy Wang diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst index e443be7928db..c9d2bf96b02d 100644 --- a/Documentation/filesystems/overlayfs.rst +++ b/Documentation/filesystems/overlayfs.rst @@ -40,13 +40,46 @@ On 64bit systems, even if all overlay layers are not on the same underlying filesystem, the same compliant behavior could be achieved with the "xino" feature. The "xino" feature composes a unique object identifier from the real object st_ino and an underlying fsid index. + If all underlying filesystems support NFS file handles and export file handles with 32bit inode number encoding (e.g. ext4), overlay filesystem will use the high inode number bits for fsid. Even when the underlying filesystem uses 64bit inode numbers, users can still enable the "xino" feature with the "-o xino=on" overlay mount option. That is useful for the case of underlying filesystems like xfs and tmpfs, which use 64bit inode -numbers, but are very unlikely to use the high inode number bit. +numbers, but are very unlikely to use the high inode number bits. In case +the underlying inode number does overflow into the high xino bits, overlay +filesystem will fall back to the non xino behavior for that inode. + +The following table summarizes what can be expected in different overlay +configurations. + +Inode properties +```````````````` + ++--------------+------------+------------+-----------------+----------------+ +|Configuration | Persistent | Uniform | st_ino == d_ino | d_ino == i_ino | +| | st_ino | st_dev | | [*] | ++==============+=====+======+=====+======+========+========+========+=======+ +| | dir | !dir | dir | !dir | dir + !dir | dir | !dir | ++--------------+-----+------+-----+------+--------+--------+--------+-------+ +| All layers | Y | Y | Y | Y | Y | Y | Y | Y | +| on same fs | | | | | | | | | ++--------------+-----+------+-----+------+--------+--------+--------+-------+ +| Layers not | N | Y | Y | N | N | Y | N | Y | +| on same fs, | | | | | | | | | +| xino=off | | | | | | | | | ++--------------+-----+------+-----+------+--------+--------+--------+-------+ +| xino=on/auto | Y | Y | Y | Y | Y | Y | Y | Y | +| | | | | | | | | | ++--------------+-----+------+-----+------+--------+--------+--------+-------+ +| xino=on/auto,| N | Y | Y | N | N | Y | N | Y | +| ino overflow | | | | | | | | | ++--------------+-----+------+-----+------+--------+--------+--------+-------+ + +[*] nfsd v3 readdirplus verifies d_ino == i_ino. i_ino is exposed via several +/proc files, such as /proc/locks and /proc/self/fdinfo/<fd> of an inotify +file descriptor. Upper and Lower @@ -248,6 +281,50 @@ overlay filesystem (though an operation on the name of the file such as rename or unlink will of course be noticed and handled). +Permission model +---------------- + +Permission checking in the overlay filesystem follows these principles: + + 1) permission check SHOULD return the same result before and after copy up + + 2) task creating the overlay mount MUST NOT gain additional privileges + + 3) non-mounting task MAY gain additional privileges through the overlay, + compared to direct access on underlying lower or upper filesystems + +This is achieved by performing two permission checks on each access + + a) check if current task is allowed access based on local DAC (owner, + group, mode and posix acl), as well as MAC checks + + b) check if mounting task would be allowed real operation on lower or + upper layer based on underlying filesystem permissions, again including + MAC checks + +Check (a) ensures consistency (1) since owner, group, mode and posix acls +are copied up. On the other hand it can result in server enforced +permissions (used by NFS, for example) being ignored (3). + +Check (b) ensures that no task gains permissions to underlying layers that +the mounting task does not have (2). This also means that it is possible +to create setups where the consistency rule (1) does not hold; normally, +however, the mounting task will have sufficient privileges to perform all +operations. + +Another way to demonstrate this model is drawing parallels between + + mount -t overlay overlay -olowerdir=/lower,upperdir=/upper,... /merged + +and + + cp -a /lower /upper + mount --bind /upper /merged + +The resulting access permissions should be the same. The difference is in +the time of copy (on-demand vs. up-front). + + Multiple lower layers --------------------- @@ -383,7 +460,8 @@ guarantee that the values of st_ino and st_dev returned by stat(2) and the value of d_ino returned by readdir(3) will act like on a normal filesystem. E.g. the value of st_dev may be different for two objects in the same overlay filesystem and the value of st_ino for directory objects may not be -persistent and could change even while the overlay filesystem is mounted. +persistent and could change even while the overlay filesystem is mounted, as +summarized in the `Inode properties`_ table above. Changes to underlying filesystems diff --git a/Documentation/filesystems/path-lookup.rst b/Documentation/filesystems/path-lookup.rst index a3216979298b..f46b05e9b96c 100644 --- a/Documentation/filesystems/path-lookup.rst +++ b/Documentation/filesystems/path-lookup.rst @@ -404,11 +404,8 @@ that is the "next" component in the pathname. ``int last_type`` ~~~~~~~~~~~~~~~~~ -This is one of ``LAST_NORM``, ``LAST_ROOT``, ``LAST_DOT``, ``LAST_DOTDOT``, or -``LAST_BIND``. The ``last`` field is only valid if the type is -``LAST_NORM``. ``LAST_BIND`` is used when following a symlink and no -components of the symlink have been processed yet. Others should be -fairly self-explanatory. +This is one of ``LAST_NORM``, ``LAST_ROOT``, ``LAST_DOT`` or ``LAST_DOTDOT``. +The ``last`` field is only valid if the type is ``LAST_NORM``. ``struct path root`` ~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.rst index 99ca040e3f90..38b606991065 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.rst @@ -1,19 +1,20 @@ ------------------------------------------------------------------------------- - T H E /proc F I L E S Y S T E M ------------------------------------------------------------------------------- -/proc/sys Terrehon Bowden <terrehon@pacbell.net> October 7 1999 - Bodo Bauer <bb@ricochet.net> +.. SPDX-License-Identifier: GPL-2.0 + +==================== +The /proc Filesystem +==================== + +===================== ======================================= ================ +/proc/sys Terrehon Bowden <terrehon@pacbell.net>, October 7 1999 + Bodo Bauer <bb@ricochet.net> +2.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000 +move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009 +fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009 +===================== ======================================= ================ + -2.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000 -move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009 ------------------------------------------------------------------------------- -Version 1.3 Kernel version 2.2.12 - Kernel version 2.4.0-test11-pre4 ------------------------------------------------------------------------------- -fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009 -Table of Contents ------------------ +.. Table of Contents 0 Preface 0.1 Introduction/Credits @@ -50,9 +51,8 @@ Table of Contents 4 Configuring procfs 4.1 Mount options ------------------------------------------------------------------------------- Preface ------------------------------------------------------------------------------- +======= 0.1 Introduction/Credits ------------------------ @@ -95,20 +95,18 @@ We don't guarantee the correctness of this document, and if you come to us complaining about how you screwed up your system because of incorrect documentation, we won't feel responsible... ------------------------------------------------------------------------------- -CHAPTER 1: COLLECTING SYSTEM INFORMATION ------------------------------------------------------------------------------- +Chapter 1: Collecting System Information +======================================== ------------------------------------------------------------------------------- In This Chapter ------------------------------------------------------------------------------- +--------------- * Investigating the properties of the pseudo file system /proc and its ability to provide information on the running Linux system * Examining /proc's structure * Uncovering various information about the kernel and the processes running on the system ------------------------------------------------------------------------------- +------------------------------------------------------------------------------ The proc file system acts as an interface to internal data structures in the kernel. It can be used to obtain information about the system and to change @@ -134,9 +132,11 @@ never act on any new process that the kernel may, through chance, have also assigned the process ID <pid>. Instead, operations on these FDs usually fail with ESRCH. -Table 1-1: Process specific entries in /proc -.............................................................................. +.. table:: Table 1-1: Process specific entries in /proc + + ============= =============================================================== File Content + ============= =============================================================== clear_refs Clears page referenced bits shown in smaps output cmdline Command line arguments cpu Current and last cpu in which it was executed (2.4)(smp) @@ -160,10 +160,10 @@ Table 1-1: Process specific entries in /proc can be derived from smaps, but is faster and more convenient numa_maps An extension based on maps, showing the memory locality and binding policy as well as mem usage (in pages) of each mapping. -.............................................................................. + ============= =============================================================== For example, to get the status information of a process, all you have to do is -read the file /proc/PID/status: +read the file /proc/PID/status:: >cat /proc/self/status Name: cat @@ -222,14 +222,17 @@ contains details information about the process itself. Its fields are explained in Table 1-4. (for SMP CONFIG users) + For making accounting scalable, RSS related information are handled in an asynchronous manner and the value may not be very precise. To see a precise snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table. It's slow but very precise. -Table 1-2: Contents of the status files (as of 4.19) -.............................................................................. +.. table:: Table 1-2: Contents of the status files (as of 4.19) + + ========================== =================================================== Field Content + ========================== =================================================== Name filename of the executable Umask file mode creation mask State state (R is running, S is sleeping, D is sleeping @@ -254,7 +257,8 @@ Table 1-2: Contents of the status files (as of 4.19) VmPin pinned memory size VmHWM peak resident set size ("high water mark") VmRSS size of memory portions. It contains the three - following parts (VmRSS = RssAnon + RssFile + RssShmem) + following parts + (VmRSS = RssAnon + RssFile + RssShmem) RssAnon size of resident anonymous memory RssFile size of resident file mappings RssShmem size of resident shmem memory (includes SysV shm, @@ -292,27 +296,32 @@ Table 1-2: Contents of the status files (as of 4.19) Mems_allowed_list Same as previous, but in "list format" voluntary_ctxt_switches number of voluntary context switches nonvoluntary_ctxt_switches number of non voluntary context switches -.............................................................................. + ========================== =================================================== -Table 1-3: Contents of the statm files (as of 2.6.8-rc3) -.............................................................................. + +.. table:: Table 1-3: Contents of the statm files (as of 2.6.8-rc3) + + ======== =============================== ============================== Field Content + ======== =============================== ============================== size total program size (pages) (same as VmSize in status) resident size of memory portions (pages) (same as VmRSS in status) shared number of pages that are shared (i.e. backed by a file, same as RssFile+RssShmem in status) trs number of pages that are 'code' (not including libs; broken, - includes data segment) + includes data segment) lrs number of pages of library (always 0 on 2.6) drs number of pages of data/stack (including libs; broken, - includes library text) + includes library text) dt number of dirty pages (always 0 on 2.6) -.............................................................................. + ======== =============================== ============================== + +.. table:: Table 1-4: Contents of the stat files (as of 2.6.30-rc7) -Table 1-4: Contents of the stat files (as of 2.6.30-rc7) -.............................................................................. - Field Content + ============= =============================================================== + Field Content + ============= =============================================================== pid process id tcomm filename of the executable state state (R is running, S is sleeping, D is sleeping in an @@ -348,7 +357,8 @@ Table 1-4: Contents of the stat files (as of 2.6.30-rc7) blocked bitmap of blocked signals sigign bitmap of ignored signals sigcatch bitmap of caught signals - 0 (place holder, used to be the wchan address, use /proc/PID/wchan instead) + 0 (place holder, used to be the wchan address, + use /proc/PID/wchan instead) 0 (place holder) 0 (place holder) exit_signal signal to send to parent thread on exit @@ -365,39 +375,40 @@ Table 1-4: Contents of the stat files (as of 2.6.30-rc7) arg_end address below which program command line is placed env_start address above which program environment is placed env_end address below which program environment is placed - exit_code the thread's exit_code in the form reported by the waitpid system call -.............................................................................. + exit_code the thread's exit_code in the form reported by the waitpid + system call + ============= =============================================================== The /proc/PID/maps file contains the currently mapped memory regions and their access permissions. -The format is: - -address perms offset dev inode pathname - -08048000-08049000 r-xp 00000000 03:00 8312 /opt/test -08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test -0804a000-0806b000 rw-p 00000000 00:00 0 [heap] -a7cb1000-a7cb2000 ---p 00000000 00:00 0 -a7cb2000-a7eb2000 rw-p 00000000 00:00 0 -a7eb2000-a7eb3000 ---p 00000000 00:00 0 -a7eb3000-a7ed5000 rw-p 00000000 00:00 0 -a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 -a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6 -a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6 -a800b000-a800e000 rw-p 00000000 00:00 0 -a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0 -a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0 -a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0 -a8024000-a8027000 rw-p 00000000 00:00 0 -a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2 -a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2 -a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2 -aff35000-aff4a000 rw-p 00000000 00:00 0 [stack] -ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso] +The format is:: + + address perms offset dev inode pathname + + 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test + 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test + 0804a000-0806b000 rw-p 00000000 00:00 0 [heap] + a7cb1000-a7cb2000 ---p 00000000 00:00 0 + a7cb2000-a7eb2000 rw-p 00000000 00:00 0 + a7eb2000-a7eb3000 ---p 00000000 00:00 0 + a7eb3000-a7ed5000 rw-p 00000000 00:00 0 + a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 + a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6 + a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6 + a800b000-a800e000 rw-p 00000000 00:00 0 + a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0 + a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0 + a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0 + a8024000-a8027000 rw-p 00000000 00:00 0 + a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2 + a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2 + a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2 + aff35000-aff4a000 rw-p 00000000 00:00 0 [stack] + ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso] where "address" is the address space in the process that it occupies, "perms" -is a set of permissions: +is a set of permissions:: r = read w = write @@ -411,42 +422,44 @@ with the memory region, as the case would be with BSS (uninitialized data). The "pathname" shows the name associated file for this mapping. If the mapping is not associated with a file: - [heap] = the heap of the program - [stack] = the stack of the main process - [vdso] = the "virtual dynamic shared object", + ======= ==================================== + [heap] the heap of the program + [stack] the stack of the main process + [vdso] the "virtual dynamic shared object", the kernel system call handler + ======= ==================================== or if empty, the mapping is anonymous. The /proc/PID/smaps is an extension based on maps, showing the memory consumption for each of the process's mappings. For each mapping (aka Virtual -Memory Area, or VMA) there is a series of lines such as the following: - -08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash - -Size: 1084 kB -KernelPageSize: 4 kB -MMUPageSize: 4 kB -Rss: 892 kB -Pss: 374 kB -Shared_Clean: 892 kB -Shared_Dirty: 0 kB -Private_Clean: 0 kB -Private_Dirty: 0 kB -Referenced: 892 kB -Anonymous: 0 kB -LazyFree: 0 kB -AnonHugePages: 0 kB -ShmemPmdMapped: 0 kB -Shared_Hugetlb: 0 kB -Private_Hugetlb: 0 kB -Swap: 0 kB -SwapPss: 0 kB -KernelPageSize: 4 kB -MMUPageSize: 4 kB -Locked: 0 kB -THPeligible: 0 -VmFlags: rd ex mr mw me dw +Memory Area, or VMA) there is a series of lines such as the following:: + + 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash + + Size: 1084 kB + KernelPageSize: 4 kB + MMUPageSize: 4 kB + Rss: 892 kB + Pss: 374 kB + Shared_Clean: 892 kB + Shared_Dirty: 0 kB + Private_Clean: 0 kB + Private_Dirty: 0 kB + Referenced: 892 kB + Anonymous: 0 kB + LazyFree: 0 kB + AnonHugePages: 0 kB + ShmemPmdMapped: 0 kB + Shared_Hugetlb: 0 kB + Private_Hugetlb: 0 kB + Swap: 0 kB + SwapPss: 0 kB + KernelPageSize: 4 kB + MMUPageSize: 4 kB + Locked: 0 kB + THPeligible: 0 + VmFlags: rd ex mr mw me dw The first of these lines shows the same information as is displayed for the mapping in /proc/PID/maps. Following lines show the size of the mapping @@ -461,26 +474,35 @@ The "proportional set size" (PSS) of a process is the count of pages it has in memory, where each page is divided by the number of processes sharing it. So if a process has 1000 pages all to itself, and 1000 shared with one other process, its PSS will be 1500. + Note that even a page which is part of a MAP_SHARED mapping, but has only a single pte mapped, i.e. is currently used by only one process, is accounted as private and not as shared. + "Referenced" indicates the amount of memory currently marked as referenced or accessed. + "Anonymous" shows the amount of memory that does not belong to any file. Even a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE and a page is modified, the file page is replaced by a private anonymous copy. + "LazyFree" shows the amount of memory which is marked by madvise(MADV_FREE). The memory isn't freed immediately with madvise(). It's freed in memory pressure if the memory is clean. Please note that the printed value might be lower than the real value due to optimizations used in the current implementation. If this is not desirable please file a bug report. + "AnonHugePages" shows the ammount of memory backed by transparent hugepage. + "ShmemPmdMapped" shows the ammount of shared (shmem/tmpfs) memory backed by huge pages. + "Shared_Hugetlb" and "Private_Hugetlb" show the ammounts of memory backed by hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field. + "Swap" shows how much would-be-anonymous memory is also used, but out on swap. + For shmem mappings, "Swap" includes also the size of the mapped (and not replaced by copy-on-write) part of the underlying shmem object out on swap. "SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this @@ -489,36 +511,39 @@ does not take into account swapped out page of underlying shmem objects. "THPeligible" indicates whether the mapping is eligible for allocating THP pages - 1 if true, 0 otherwise. It just shows the current status. -"VmFlags" field deserves a separate description. This member represents the kernel -flags associated with the particular virtual memory area in two letter encoded -manner. The codes are the following: - rd - readable - wr - writeable - ex - executable - sh - shared - mr - may read - mw - may write - me - may execute - ms - may share - gd - stack segment growns down - pf - pure PFN range - dw - disabled write to the mapped file - lo - pages are locked in memory - io - memory mapped I/O area - sr - sequential read advise provided - rr - random read advise provided - dc - do not copy area on fork - de - do not expand area on remapping - ac - area is accountable - nr - swap space is not reserved for the area - ht - area uses huge tlb pages - ar - architecture specific flag - dd - do not include area into core dump - sd - soft-dirty flag - mm - mixed map area - hg - huge page advise flag - nh - no-huge page advise flag - mg - mergable advise flag +"VmFlags" field deserves a separate description. This member represents the +kernel flags associated with the particular virtual memory area in two letter +encoded manner. The codes are the following: + + == ======================================= + rd readable + wr writeable + ex executable + sh shared + mr may read + mw may write + me may execute + ms may share + gd stack segment growns down + pf pure PFN range + dw disabled write to the mapped file + lo pages are locked in memory + io memory mapped I/O area + sr sequential read advise provided + rr random read advise provided + dc do not copy area on fork + de do not expand area on remapping + ac area is accountable + nr swap space is not reserved for the area + ht area uses huge tlb pages + ar architecture specific flag + dd do not include area into core dump + sd soft dirty flag + mm mixed map area + hg huge page advise flag + nh no huge page advise flag + mg mergable advise flag + == ======================================= Note that there is no guarantee that every flag and associated mnemonic will be present in all further kernel releases. Things get changed, the flags may @@ -531,6 +556,7 @@ enabled. Note: reading /proc/PID/maps or /proc/PID/smaps is inherently racy (consistent output can be achieved only in the single read call). + This typically manifests when doing partial reads of these files while the memory map is being modified. Despite the races, we do provide the following guarantees: @@ -544,9 +570,9 @@ The /proc/PID/smaps_rollup file includes the same fields as /proc/PID/smaps, but their values are the sums of the corresponding values for all mappings of the process. Additionally, it contains these fields: -Pss_Anon -Pss_File -Pss_Shmem +- Pss_Anon +- Pss_File +- Pss_Shmem They represent the proportional shares of anonymous, file, and shmem pages, as described for smaps above. These fields are omitted in smaps since each @@ -558,20 +584,25 @@ The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG bits on both physical and virtual pages associated with a process, and the soft-dirty bit on pte (see Documentation/admin-guide/mm/soft-dirty.rst for details). -To clear the bits for all the pages associated with the process +To clear the bits for all the pages associated with the process:: + > echo 1 > /proc/PID/clear_refs -To clear the bits for the anonymous pages associated with the process +To clear the bits for the anonymous pages associated with the process:: + > echo 2 > /proc/PID/clear_refs -To clear the bits for the file mapped pages associated with the process +To clear the bits for the file mapped pages associated with the process:: + > echo 3 > /proc/PID/clear_refs -To clear the soft-dirty bit +To clear the soft-dirty bit:: + > echo 4 > /proc/PID/clear_refs To reset the peak resident set size ("high water mark") to the process's -current value: +current value:: + > echo 5 > /proc/PID/clear_refs Any other value written to /proc/PID/clear_refs will have no effect. @@ -584,30 +615,33 @@ Documentation/admin-guide/mm/pagemap.rst. The /proc/pid/numa_maps is an extension based on maps, showing the memory locality and binding policy, as well as the memory usage (in pages) of each mapping. The output follows a general format where mapping details get -summarized separated by blank spaces, one mapping per each file line: - -address policy mapping details - -00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4 -00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4 -3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4 -320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 -3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 -3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4 -3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4 -320698b000 default file=/lib64/libc-2.12.so -3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4 -3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 -3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4 -7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4 -7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4 -7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048 -7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4 -7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4 +summarized separated by blank spaces, one mapping per each file line:: + + address policy mapping details + + 00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4 + 00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4 + 3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4 + 320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 + 3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 + 3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4 + 3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4 + 320698b000 default file=/lib64/libc-2.12.so + 3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4 + 3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 + 3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4 + 7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4 + 7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4 + 7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048 + 7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4 + 7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4 Where: + "address" is the starting address for the mapping; + "policy" reports the NUMA memory policy set for the mapping (see Documentation/admin-guide/mm/numa_memory_policy.rst); + "mapping details" summarizes mapping data such as mapping type, page usage counters, node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page size, in KB, that is backing the mapping up. @@ -621,81 +655,83 @@ the running kernel. The files used to obtain this information are contained in system. It depends on the kernel configuration and the loaded modules, which files are there, and which are missing. -Table 1-5: Kernel info in /proc -.............................................................................. - File Content - apm Advanced power management info - buddyinfo Kernel memory allocator information (see text) (2.5) - bus Directory containing bus specific information - cmdline Kernel command line - cpuinfo Info about the CPU - devices Available devices (block and character) - dma Used DMS channels - filesystems Supported filesystems - driver Various drivers grouped here, currently rtc (2.4) - execdomains Execdomains, related to security (2.4) - fb Frame Buffer devices (2.4) - fs File system parameters, currently nfs/exports (2.4) - ide Directory containing info about the IDE subsystem - interrupts Interrupt usage - iomem Memory map (2.4) - ioports I/O port usage - irq Masks for irq to cpu affinity (2.4)(smp?) - isapnp ISA PnP (Plug&Play) Info (2.4) - kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4)) - kmsg Kernel messages - ksyms Kernel symbol table - loadavg Load average of last 1, 5 & 15 minutes - locks Kernel locks - meminfo Memory info - misc Miscellaneous - modules List of loaded modules - mounts Mounted filesystems - net Networking info (see text) +.. table:: Table 1-5: Kernel info in /proc + + ============ =============================================================== + File Content + ============ =============================================================== + apm Advanced power management info + buddyinfo Kernel memory allocator information (see text) (2.5) + bus Directory containing bus specific information + cmdline Kernel command line + cpuinfo Info about the CPU + devices Available devices (block and character) + dma Used DMS channels + filesystems Supported filesystems + driver Various drivers grouped here, currently rtc (2.4) + execdomains Execdomains, related to security (2.4) + fb Frame Buffer devices (2.4) + fs File system parameters, currently nfs/exports (2.4) + ide Directory containing info about the IDE subsystem + interrupts Interrupt usage + iomem Memory map (2.4) + ioports I/O port usage + irq Masks for irq to cpu affinity (2.4)(smp?) + isapnp ISA PnP (Plug&Play) Info (2.4) + kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4)) + kmsg Kernel messages + ksyms Kernel symbol table + loadavg Load average of last 1, 5 & 15 minutes + locks Kernel locks + meminfo Memory info + misc Miscellaneous + modules List of loaded modules + mounts Mounted filesystems + net Networking info (see text) pagetypeinfo Additional page allocator information (see text) (2.5) - partitions Table of partitions known to the system - pci Deprecated info of PCI bus (new way -> /proc/bus/pci/, - decoupled by lspci (2.4) - rtc Real time clock - scsi SCSI info (see text) - slabinfo Slab pool info - softirqs softirq usage - stat Overall statistics - swaps Swap space utilization - sys See chapter 2 - sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4) - tty Info of tty drivers - uptime Wall clock since boot, combined idle time of all cpus - version Kernel version - video bttv info of video resources (2.4) - vmallocinfo Show vmalloced areas -.............................................................................. + partitions Table of partitions known to the system + pci Deprecated info of PCI bus (new way -> /proc/bus/pci/, + decoupled by lspci (2.4) + rtc Real time clock + scsi SCSI info (see text) + slabinfo Slab pool info + softirqs softirq usage + stat Overall statistics + swaps Swap space utilization + sys See chapter 2 + sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4) + tty Info of tty drivers + uptime Wall clock since boot, combined idle time of all cpus + version Kernel version + video bttv info of video resources (2.4) + vmallocinfo Show vmalloced areas + ============ =============================================================== You can, for example, check which interrupts are currently in use and what -they are used for by looking in the file /proc/interrupts: - - > cat /proc/interrupts - CPU0 - 0: 8728810 XT-PIC timer - 1: 895 XT-PIC keyboard - 2: 0 XT-PIC cascade - 3: 531695 XT-PIC aha152x - 4: 2014133 XT-PIC serial - 5: 44401 XT-PIC pcnet_cs - 8: 2 XT-PIC rtc - 11: 8 XT-PIC i82365 - 12: 182918 XT-PIC PS/2 Mouse - 13: 1 XT-PIC fpu - 14: 1232265 XT-PIC ide0 - 15: 7 XT-PIC ide1 - NMI: 0 +they are used for by looking in the file /proc/interrupts:: + + > cat /proc/interrupts + CPU0 + 0: 8728810 XT-PIC timer + 1: 895 XT-PIC keyboard + 2: 0 XT-PIC cascade + 3: 531695 XT-PIC aha152x + 4: 2014133 XT-PIC serial + 5: 44401 XT-PIC pcnet_cs + 8: 2 XT-PIC rtc + 11: 8 XT-PIC i82365 + 12: 182918 XT-PIC PS/2 Mouse + 13: 1 XT-PIC fpu + 14: 1232265 XT-PIC ide0 + 15: 7 XT-PIC ide1 + NMI: 0 In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the -output of a SMP machine): +output of a SMP machine):: - > cat /proc/interrupts + > cat /proc/interrupts - CPU0 CPU1 + CPU0 CPU1 0: 1243498 1214548 IO-APIC-edge timer 1: 8949 8958 IO-APIC-edge keyboard 2: 0 0 XT-PIC cascade @@ -708,8 +744,8 @@ output of a SMP machine): 15: 2183 2415 IO-APIC-edge ide1 17: 30564 30414 IO-APIC-level eth0 18: 177 164 IO-APIC-level bttv - NMI: 2457961 2457959 - LOC: 2457882 2457881 + NMI: 2457961 2457959 + LOC: 2457882 2457881 ERR: 2155 NMI is incremented in this case because every timer interrupt generates a NMI @@ -726,21 +762,25 @@ In 2.6.2* /proc/interrupts was expanded again. This time the goal was for /proc/interrupts to display every IRQ vector in use by the system, not just those considered 'most important'. The new vectors are: - THR -- interrupt raised when a machine check threshold counter +THR + interrupt raised when a machine check threshold counter (typically counting ECC corrected errors of memory or cache) exceeds a configurable threshold. Only available on some systems. - TRM -- a thermal event interrupt occurs when a temperature threshold +TRM + a thermal event interrupt occurs when a temperature threshold has been exceeded for the CPU. This interrupt may also be generated when the temperature drops back to normal. - SPU -- a spurious interrupt is some interrupt that was raised then lowered +SPU + a spurious interrupt is some interrupt that was raised then lowered by some IO device before it could be fully processed by the APIC. Hence the APIC sees the interrupt but does not know what device it came from. For this case the APIC will generate the interrupt with a IRQ vector of 0xff. This might also be generated by chipset bugs. - RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are +RES, CAL, TLB] + rescheduling, call and TLB flush interrupts are sent from one CPU to another per the needs of the OS. Typically, their statistics are used by kernel developers and interested users to determine the occurrence of interrupts of the given type. @@ -756,7 +796,8 @@ IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and prof_cpu_mask. -For example +For example:: + > ls /proc/irq/ 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask 1 11 13 15 17 19 3 5 7 9 default_smp_affinity @@ -764,20 +805,20 @@ For example smp_affinity smp_affinity is a bitmask, in which you can specify which CPUs can handle the -IRQ, you can set it by doing: +IRQ, you can set it by doing:: > echo 1 > /proc/irq/10/smp_affinity This means that only the first CPU will handle the IRQ, but you can also echo 5 which means that only the first and third CPU can handle the IRQ. -The contents of each smp_affinity file is the same by default: +The contents of each smp_affinity file is the same by default:: > cat /proc/irq/0/smp_affinity ffffffff There is an alternate interface, smp_affinity_list which allows specifying -a cpu range instead of a bitmask: +a cpu range instead of a bitmask:: > cat /proc/irq/0/smp_affinity_list 1024-1031 @@ -810,46 +851,46 @@ Linux uses slab pools for memory management above page level in version 2.2. Commonly used objects have their own slab pool (such as network buffers, directory cache, and so on). -.............................................................................. +:: -> cat /proc/buddyinfo + > cat /proc/buddyinfo -Node 0, zone DMA 0 4 5 4 4 3 ... -Node 0, zone Normal 1 0 0 1 101 8 ... -Node 0, zone HighMem 2 0 0 1 1 0 ... + Node 0, zone DMA 0 4 5 4 4 3 ... + Node 0, zone Normal 1 0 0 1 101 8 ... + Node 0, zone HighMem 2 0 0 1 1 0 ... External fragmentation is a problem under some workloads, and buddyinfo is a -useful tool for helping diagnose these problems. Buddyinfo will give you a +useful tool for helping diagnose these problems. Buddyinfo will give you a clue as to how big an area you can safely allocate, or why a previous allocation failed. -Each column represents the number of pages of a certain order which are -available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in -ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE -available in ZONE_NORMAL, etc... +Each column represents the number of pages of a certain order which are +available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in +ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE +available in ZONE_NORMAL, etc... More information relevant to external fragmentation can be found in -pagetypeinfo. - -> cat /proc/pagetypeinfo -Page block order: 9 -Pages per block: 512 - -Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10 -Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0 -Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0 -Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2 -Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0 -Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0 -Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9 -Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0 -Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452 -Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0 -Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0 - -Number of blocks type Unmovable Reclaimable Movable Reserve Isolate -Node 0, zone DMA 2 0 5 1 0 -Node 0, zone DMA32 41 6 967 2 0 +pagetypeinfo:: + + > cat /proc/pagetypeinfo + Page block order: 9 + Pages per block: 512 + + Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10 + Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0 + Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0 + Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2 + Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0 + Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0 + Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9 + Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0 + Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452 + Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0 + Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0 + + Number of blocks type Unmovable Reclaimable Movable Reserve Isolate + Node 0, zone DMA 2 0 5 1 0 + Node 0, zone DMA32 41 6 967 2 0 Fragmentation avoidance in the kernel works by grouping pages of different migrate types into the same contiguous regions of memory called page blocks. @@ -870,59 +911,63 @@ unless memory has been mlock()'d. Some of the Reclaimable blocks should also be allocatable although a lot of filesystem metadata may have to be reclaimed to achieve this. -.............................................................................. -meminfo: +meminfo +~~~~~~~ Provides information about distribution and utilization of memory. This varies by architecture and compile options. The following is from a 16GB PIII, which has highmem enabled. You may not have all of these fields. -> cat /proc/meminfo - -MemTotal: 16344972 kB -MemFree: 13634064 kB -MemAvailable: 14836172 kB -Buffers: 3656 kB -Cached: 1195708 kB -SwapCached: 0 kB -Active: 891636 kB -Inactive: 1077224 kB -HighTotal: 15597528 kB -HighFree: 13629632 kB -LowTotal: 747444 kB -LowFree: 4432 kB -SwapTotal: 0 kB -SwapFree: 0 kB -Dirty: 968 kB -Writeback: 0 kB -AnonPages: 861800 kB -Mapped: 280372 kB -Shmem: 644 kB -KReclaimable: 168048 kB -Slab: 284364 kB -SReclaimable: 159856 kB -SUnreclaim: 124508 kB -PageTables: 24448 kB -NFS_Unstable: 0 kB -Bounce: 0 kB -WritebackTmp: 0 kB -CommitLimit: 7669796 kB -Committed_AS: 100056 kB -VmallocTotal: 112216 kB -VmallocUsed: 428 kB -VmallocChunk: 111088 kB -Percpu: 62080 kB -HardwareCorrupted: 0 kB -AnonHugePages: 49152 kB -ShmemHugePages: 0 kB -ShmemPmdMapped: 0 kB - - - MemTotal: Total usable ram (i.e. physical ram minus a few reserved +:: + + > cat /proc/meminfo + + MemTotal: 16344972 kB + MemFree: 13634064 kB + MemAvailable: 14836172 kB + Buffers: 3656 kB + Cached: 1195708 kB + SwapCached: 0 kB + Active: 891636 kB + Inactive: 1077224 kB + HighTotal: 15597528 kB + HighFree: 13629632 kB + LowTotal: 747444 kB + LowFree: 4432 kB + SwapTotal: 0 kB + SwapFree: 0 kB + Dirty: 968 kB + Writeback: 0 kB + AnonPages: 861800 kB + Mapped: 280372 kB + Shmem: 644 kB + KReclaimable: 168048 kB + Slab: 284364 kB + SReclaimable: 159856 kB + SUnreclaim: 124508 kB + PageTables: 24448 kB + NFS_Unstable: 0 kB + Bounce: 0 kB + WritebackTmp: 0 kB + CommitLimit: 7669796 kB + Committed_AS: 100056 kB + VmallocTotal: 112216 kB + VmallocUsed: 428 kB + VmallocChunk: 111088 kB + Percpu: 62080 kB + HardwareCorrupted: 0 kB + AnonHugePages: 49152 kB + ShmemHugePages: 0 kB + ShmemPmdMapped: 0 kB + +MemTotal + Total usable ram (i.e. physical ram minus a few reserved bits and the kernel binary code) - MemFree: The sum of LowFree+HighFree -MemAvailable: An estimate of how much memory is available for starting new +MemFree + The sum of LowFree+HighFree +MemAvailable + An estimate of how much memory is available for starting new applications, without swapping. Calculated from MemFree, SReclaimable, the size of the file LRU lists, and the low watermarks in each zone. @@ -930,69 +975,99 @@ MemAvailable: An estimate of how much memory is available for starting new page cache to function well, and that not all reclaimable slab will be reclaimable, due to items being in use. The impact of those factors will vary from system to system. - Buffers: Relatively temporary storage for raw disk blocks +Buffers + Relatively temporary storage for raw disk blocks shouldn't get tremendously large (20MB or so) - Cached: in-memory cache for files read from the disk (the +Cached + in-memory cache for files read from the disk (the pagecache). Doesn't include SwapCached - SwapCached: Memory that once was swapped out, is swapped back in but +SwapCached + Memory that once was swapped out, is swapped back in but still also is in the swapfile (if memory is needed it doesn't need to be swapped out AGAIN because it is already in the swapfile. This saves I/O) - Active: Memory that has been used more recently and usually not +Active + Memory that has been used more recently and usually not reclaimed unless absolutely necessary. - Inactive: Memory which has been less recently used. It is more +Inactive + Memory which has been less recently used. It is more eligible to be reclaimed for other purposes - HighTotal: - HighFree: Highmem is all memory above ~860MB of physical memory +HighTotal, HighFree + Highmem is all memory above ~860MB of physical memory Highmem areas are for use by userspace programs, or for the pagecache. The kernel must use tricks to access this memory, making it slower to access than lowmem. - LowTotal: - LowFree: Lowmem is memory which can be used for everything that +LowTotal, LowFree + Lowmem is memory which can be used for everything that highmem can be used for, but it is also available for the kernel's use for its own data structures. Among many other things, it is where everything from the Slab is allocated. Bad things happen when you're out of lowmem. - SwapTotal: total amount of swap space available - SwapFree: Memory which has been evicted from RAM, and is temporarily +SwapTotal + total amount of swap space available +SwapFree + Memory which has been evicted from RAM, and is temporarily on the disk - Dirty: Memory which is waiting to get written back to the disk - Writeback: Memory which is actively being written back to the disk - AnonPages: Non-file backed pages mapped into userspace page tables -HardwareCorrupted: The amount of RAM/memory in KB, the kernel identifies as +Dirty + Memory which is waiting to get written back to the disk +Writeback + Memory which is actively being written back to the disk +AnonPages + Non-file backed pages mapped into userspace page tables +HardwareCorrupted + The amount of RAM/memory in KB, the kernel identifies as corrupted. -AnonHugePages: Non-file backed huge pages mapped into userspace page tables - Mapped: files which have been mmaped, such as libraries - Shmem: Total memory used by shared memory (shmem) and tmpfs -ShmemHugePages: Memory used by shared memory (shmem) and tmpfs allocated +AnonHugePages + Non-file backed huge pages mapped into userspace page tables +Mapped + files which have been mmaped, such as libraries +Shmem + Total memory used by shared memory (shmem) and tmpfs +ShmemHugePages + Memory used by shared memory (shmem) and tmpfs allocated with huge pages -ShmemPmdMapped: Shared memory mapped into userspace with huge pages -KReclaimable: Kernel allocations that the kernel will attempt to reclaim +ShmemPmdMapped + Shared memory mapped into userspace with huge pages +KReclaimable + Kernel allocations that the kernel will attempt to reclaim under memory pressure. Includes SReclaimable (below), and other direct allocations with a shrinker. - Slab: in-kernel data structures cache -SReclaimable: Part of Slab, that might be reclaimed, such as caches - SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure - PageTables: amount of memory dedicated to the lowest level of page +Slab + in-kernel data structures cache +SReclaimable + Part of Slab, that might be reclaimed, such as caches +SUnreclaim + Part of Slab, that cannot be reclaimed on memory pressure +PageTables + amount of memory dedicated to the lowest level of page tables. -NFS_Unstable: NFS pages sent to the server, but not yet committed to stable +NFS_Unstable + NFS pages sent to the server, but not yet committed to stable storage - Bounce: Memory used for block device "bounce buffers" -WritebackTmp: Memory used by FUSE for temporary writeback buffers - CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'), +Bounce + Memory used for block device "bounce buffers" +WritebackTmp + Memory used by FUSE for temporary writeback buffers +CommitLimit + Based on the overcommit ratio ('vm.overcommit_ratio'), this is the total amount of memory currently available to be allocated on the system. This limit is only adhered to if strict overcommit accounting is enabled (mode 2 in 'vm.overcommit_memory'). - The CommitLimit is calculated with the following formula: - CommitLimit = ([total RAM pages] - [total huge TLB pages]) * - overcommit_ratio / 100 + [total swap pages] + + The CommitLimit is calculated with the following formula:: + + CommitLimit = ([total RAM pages] - [total huge TLB pages]) * + overcommit_ratio / 100 + [total swap pages] + For example, on a system with 1G of physical RAM and 7G of swap with a `vm.overcommit_ratio` of 30 it would yield a CommitLimit of 7.3G. + For more details, see the memory overcommit documentation in vm/overcommit-accounting. -Committed_AS: The amount of memory presently allocated on the system. +Committed_AS + The amount of memory presently allocated on the system. The committed memory is a sum of all of the memory which has been allocated by processes, even if it has not been "used" by them as of yet. A process which malloc()'s 1G @@ -1005,21 +1080,25 @@ Committed_AS: The amount of memory presently allocated on the system. This is useful if one needs to guarantee that processes will not fail due to lack of memory once that memory has been successfully allocated. -VmallocTotal: total size of vmalloc memory area - VmallocUsed: amount of vmalloc area which is used -VmallocChunk: largest contiguous block of vmalloc area which is free - Percpu: Memory allocated to the percpu allocator used to back percpu +VmallocTotal + total size of vmalloc memory area +VmallocUsed + amount of vmalloc area which is used +VmallocChunk + largest contiguous block of vmalloc area which is free +Percpu + Memory allocated to the percpu allocator used to back percpu allocations. This stat excludes the cost of metadata. -.............................................................................. - -vmallocinfo: +vmallocinfo +~~~~~~~~~~~ Provides information about vmalloced/vmaped areas. One line per area, containing the virtual address range of the area, size in bytes, caller information of the creator, and optional information depending on the kind of area : + ========== =================================================== pages=nr number of pages phys=addr if a physical address was specified ioremap I/O mapping (ioremap() and friends) @@ -1029,49 +1108,54 @@ on the kind of area : vpages buffer for pages pointers was vmalloced (huge area) N<node>=nr (Only on NUMA kernels) Number of pages allocated on memory node <node> - -> cat /proc/vmallocinfo -0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ... - /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 -0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ... - /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 -0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f... - phys=7fee8000 ioremap -0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f... - phys=7fee7000 ioremap -0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210 -0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ... - /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 -0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ... - pages=2 vmalloc N1=2 -0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ... - /0x130 [x_tables] pages=4 vmalloc N0=4 -0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ... - pages=14 vmalloc N2=14 -0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ... - pages=4 vmalloc N1=4 -0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ... - pages=2 vmalloc N1=2 -0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ... - pages=10 vmalloc N0=10 - -.............................................................................. - -softirqs: + ========== =================================================== + +:: + + > cat /proc/vmallocinfo + 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ... + /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 + 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ... + /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 + 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f... + phys=7fee8000 ioremap + 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f... + phys=7fee7000 ioremap + 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210 + 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ... + /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 + 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ... + pages=2 vmalloc N1=2 + 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ... + /0x130 [x_tables] pages=4 vmalloc N0=4 + 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ... + pages=14 vmalloc N2=14 + 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ... + pages=4 vmalloc N1=4 + 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ... + pages=2 vmalloc N1=2 + 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ... + pages=10 vmalloc N0=10 + + +softirqs +~~~~~~~~ Provides counts of softirq handlers serviced since boot time, for each cpu. -> cat /proc/softirqs - CPU0 CPU1 CPU2 CPU3 - HI: 0 0 0 0 - TIMER: 27166 27120 27097 27034 - NET_TX: 0 0 0 17 - NET_RX: 42 0 0 39 - BLOCK: 0 0 107 1121 - TASKLET: 0 0 0 290 - SCHED: 27035 26983 26971 26746 - HRTIMER: 0 0 0 0 - RCU: 1678 1769 2178 2250 +:: + + > cat /proc/softirqs + CPU0 CPU1 CPU2 CPU3 + HI: 0 0 0 0 + TIMER: 27166 27120 27097 27034 + NET_TX: 0 0 0 17 + NET_RX: 42 0 0 39 + BLOCK: 0 0 107 1121 + TASKLET: 0 0 0 290 + SCHED: 27035 26983 26971 26746 + HRTIMER: 0 0 0 0 + RCU: 1678 1769 2178 2250 1.3 IDE devices in /proc/ide @@ -1083,7 +1167,7 @@ file drivers and a link for each IDE device, pointing to the device directory in the controller specific subtree. The file drivers contains general information about the drivers used for the -IDE devices: +IDE devices:: > cat /proc/ide/drivers ide-cdrom version 4.53 @@ -1094,57 +1178,61 @@ subdirectories. These are named ide0, ide1 and so on. Each of these directories contains the files shown in table 1-6. -Table 1-6: IDE controller info in /proc/ide/ide? -.............................................................................. - File Content - channel IDE channel (0 or 1) - config Configuration (only for PCI/IDE bridge) - mate Mate name - model Type/Chipset of IDE controller -.............................................................................. +.. table:: Table 1-6: IDE controller info in /proc/ide/ide? + + ======= ======================================= + File Content + ======= ======================================= + channel IDE channel (0 or 1) + config Configuration (only for PCI/IDE bridge) + mate Mate name + model Type/Chipset of IDE controller + ======= ======================================= Each device connected to a controller has a separate subdirectory in the controllers directory. The files listed in table 1-7 are contained in these directories. -Table 1-7: IDE device information -.............................................................................. - File Content - cache The cache - capacity Capacity of the medium (in 512Byte blocks) - driver driver and version - geometry physical and logical geometry - identify device identify block - media media type - model device identifier - settings device setup - smart_thresholds IDE disk management thresholds - smart_values IDE disk management values -.............................................................................. - -The most interesting file is settings. This file contains a nice overview of -the drive parameters: - - # cat /proc/ide/ide0/hda/settings - name value min max mode - ---- ----- --- --- ---- - bios_cyl 526 0 65535 rw - bios_head 255 0 255 rw - bios_sect 63 0 63 rw - breada_readahead 4 0 127 rw - bswap 0 0 1 r - file_readahead 72 0 2097151 rw - io_32bit 0 0 3 rw - keepsettings 0 0 1 rw - max_kb_per_request 122 1 127 rw - multcount 0 0 8 rw - nice1 1 0 1 rw - nowerr 0 0 1 rw - pio_mode write-only 0 255 w - slow 0 0 1 rw - unmaskirq 0 0 1 rw - using_dma 0 0 1 rw +.. table:: Table 1-7: IDE device information + + ================ ========================================== + File Content + ================ ========================================== + cache The cache + capacity Capacity of the medium (in 512Byte blocks) + driver driver and version + geometry physical and logical geometry + identify device identify block + media media type + model device identifier + settings device setup + smart_thresholds IDE disk management thresholds + smart_values IDE disk management values + ================ ========================================== + +The most interesting file is ``settings``. This file contains a nice +overview of the drive parameters:: + + # cat /proc/ide/ide0/hda/settings + name value min max mode + ---- ----- --- --- ---- + bios_cyl 526 0 65535 rw + bios_head 255 0 255 rw + bios_sect 63 0 63 rw + breada_readahead 4 0 127 rw + bswap 0 0 1 r + file_readahead 72 0 2097151 rw + io_32bit 0 0 3 rw + keepsettings 0 0 1 rw + max_kb_per_request 122 1 127 rw + multcount 0 0 8 rw + nice1 1 0 1 rw + nowerr 0 0 1 rw + pio_mode write-only 0 255 w + slow 0 0 1 rw + unmaskirq 0 0 1 rw + using_dma 0 0 1 rw 1.4 Networking info in /proc/net @@ -1155,67 +1243,70 @@ additional values you get for IP version 6 if you configure the kernel to support this. Table 1-9 lists the files and their meaning. -Table 1-8: IPv6 info in /proc/net -.............................................................................. - File Content - udp6 UDP sockets (IPv6) - tcp6 TCP sockets (IPv6) - raw6 Raw device statistics (IPv6) - igmp6 IP multicast addresses, which this host joined (IPv6) - if_inet6 List of IPv6 interface addresses - ipv6_route Kernel routing table for IPv6 - rt6_stats Global IPv6 routing tables statistics - sockstat6 Socket statistics (IPv6) - snmp6 Snmp data (IPv6) -.............................................................................. - - -Table 1-9: Network info in /proc/net -.............................................................................. - File Content - arp Kernel ARP table - dev network devices with statistics +.. table:: Table 1-8: IPv6 info in /proc/net + + ========== ===================================================== + File Content + ========== ===================================================== + udp6 UDP sockets (IPv6) + tcp6 TCP sockets (IPv6) + raw6 Raw device statistics (IPv6) + igmp6 IP multicast addresses, which this host joined (IPv6) + if_inet6 List of IPv6 interface addresses + ipv6_route Kernel routing table for IPv6 + rt6_stats Global IPv6 routing tables statistics + sockstat6 Socket statistics (IPv6) + snmp6 Snmp data (IPv6) + ========== ===================================================== + +.. table:: Table 1-9: Network info in /proc/net + + ============= ================================================================ + File Content + ============= ================================================================ + arp Kernel ARP table + dev network devices with statistics dev_mcast the Layer2 multicast groups a device is listening too (interface index, label, number of references, number of bound - addresses). - dev_stat network device status - ip_fwchains Firewall chain linkage - ip_fwnames Firewall chain names - ip_masq Directory containing the masquerading tables - ip_masquerade Major masquerading table - netstat Network statistics - raw raw device statistics - route Kernel routing table - rpc Directory containing rpc info - rt_cache Routing cache - snmp SNMP data - sockstat Socket statistics - tcp TCP sockets - udp UDP sockets - unix UNIX domain sockets - wireless Wireless interface data (Wavelan etc) - igmp IP multicast addresses, which this host joined - psched Global packet scheduler parameters. - netlink List of PF_NETLINK sockets - ip_mr_vifs List of multicast virtual interfaces - ip_mr_cache List of multicast routing cache -.............................................................................. + addresses). + dev_stat network device status + ip_fwchains Firewall chain linkage + ip_fwnames Firewall chain names + ip_masq Directory containing the masquerading tables + ip_masquerade Major masquerading table + netstat Network statistics + raw raw device statistics + route Kernel routing table + rpc Directory containing rpc info + rt_cache Routing cache + snmp SNMP data + sockstat Socket statistics + tcp TCP sockets + udp UDP sockets + unix UNIX domain sockets + wireless Wireless interface data (Wavelan etc) + igmp IP multicast addresses, which this host joined + psched Global packet scheduler parameters. + netlink List of PF_NETLINK sockets + ip_mr_vifs List of multicast virtual interfaces + ip_mr_cache List of multicast routing cache + ============= ================================================================ You can use this information to see which network devices are available in -your system and how much traffic was routed over those devices: - - > cat /proc/net/dev - Inter-|Receive |[... - face |bytes packets errs drop fifo frame compressed multicast|[... - lo: 908188 5596 0 0 0 0 0 0 [... - ppp0:15475140 20721 410 0 0 410 0 0 [... - eth0: 614530 7085 0 0 0 0 0 1 [... - - ...] Transmit - ...] bytes packets errs drop fifo colls carrier compressed - ...] 908188 5596 0 0 0 0 0 0 - ...] 1375103 17405 0 0 0 0 0 0 - ...] 1703981 5535 0 0 0 3 0 0 +your system and how much traffic was routed over those devices:: + + > cat /proc/net/dev + Inter-|Receive |[... + face |bytes packets errs drop fifo frame compressed multicast|[... + lo: 908188 5596 0 0 0 0 0 0 [... + ppp0:15475140 20721 410 0 0 410 0 0 [... + eth0: 614530 7085 0 0 0 0 0 1 [... + + ...] Transmit + ...] bytes packets errs drop fifo colls carrier compressed + ...] 908188 5596 0 0 0 0 0 0 + ...] 1375103 17405 0 0 0 0 0 0 + ...] 1703981 5535 0 0 0 3 0 0 In addition, each Channel Bond interface has its own directory. For example, the bond0 device will have a directory called /proc/net/bond0/. @@ -1228,62 +1319,62 @@ many times the slaves link has failed. If you have a SCSI host adapter in your system, you'll find a subdirectory named after the driver for this adapter in /proc/scsi. You'll also see a list -of all recognized SCSI devices in /proc/scsi: +of all recognized SCSI devices in /proc/scsi:: - >cat /proc/scsi/scsi - Attached devices: - Host: scsi0 Channel: 00 Id: 00 Lun: 00 - Vendor: IBM Model: DGHS09U Rev: 03E0 - Type: Direct-Access ANSI SCSI revision: 03 - Host: scsi0 Channel: 00 Id: 06 Lun: 00 - Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04 - Type: CD-ROM ANSI SCSI revision: 02 + >cat /proc/scsi/scsi + Attached devices: + Host: scsi0 Channel: 00 Id: 00 Lun: 00 + Vendor: IBM Model: DGHS09U Rev: 03E0 + Type: Direct-Access ANSI SCSI revision: 03 + Host: scsi0 Channel: 00 Id: 06 Lun: 00 + Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04 + Type: CD-ROM ANSI SCSI revision: 02 The directory named after the driver has one file for each adapter found in the system. These files contain information about the controller, including the used IRQ and the IO address range. The amount of information shown is dependent on the adapter you use. The example shows the output for an Adaptec -AHA-2940 SCSI adapter: - - > cat /proc/scsi/aic7xxx/0 - - Adaptec AIC7xxx driver version: 5.1.19/3.2.4 - Compile Options: - TCQ Enabled By Default : Disabled - AIC7XXX_PROC_STATS : Disabled - AIC7XXX_RESET_DELAY : 5 - Adapter Configuration: - SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter - Ultra Wide Controller - PCI MMAPed I/O Base: 0xeb001000 - Adapter SEEPROM Config: SEEPROM found and used. - Adaptec SCSI BIOS: Enabled - IRQ: 10 - SCBs: Active 0, Max Active 2, - Allocated 15, HW 16, Page 255 - Interrupts: 160328 - BIOS Control Word: 0x18b6 - Adapter Control Word: 0x005b - Extended Translation: Enabled - Disconnect Enable Flags: 0xffff - Ultra Enable Flags: 0x0001 - Tag Queue Enable Flags: 0x0000 - Ordered Queue Tag Flags: 0x0000 - Default Tag Queue Depth: 8 - Tagged Queue By Device array for aic7xxx host instance 0: - {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} - Actual queue depth per device for aic7xxx host instance 0: - {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} - Statistics: - (scsi0:0:0:0) - Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 - Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) - Total transfers 160151 (74577 reads and 85574 writes) - (scsi0:0:6:0) - Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 - Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) - Total transfers 0 (0 reads and 0 writes) +AHA-2940 SCSI adapter:: + + > cat /proc/scsi/aic7xxx/0 + + Adaptec AIC7xxx driver version: 5.1.19/3.2.4 + Compile Options: + TCQ Enabled By Default : Disabled + AIC7XXX_PROC_STATS : Disabled + AIC7XXX_RESET_DELAY : 5 + Adapter Configuration: + SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter + Ultra Wide Controller + PCI MMAPed I/O Base: 0xeb001000 + Adapter SEEPROM Config: SEEPROM found and used. + Adaptec SCSI BIOS: Enabled + IRQ: 10 + SCBs: Active 0, Max Active 2, + Allocated 15, HW 16, Page 255 + Interrupts: 160328 + BIOS Control Word: 0x18b6 + Adapter Control Word: 0x005b + Extended Translation: Enabled + Disconnect Enable Flags: 0xffff + Ultra Enable Flags: 0x0001 + Tag Queue Enable Flags: 0x0000 + Ordered Queue Tag Flags: 0x0000 + Default Tag Queue Depth: 8 + Tagged Queue By Device array for aic7xxx host instance 0: + {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} + Actual queue depth per device for aic7xxx host instance 0: + {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} + Statistics: + (scsi0:0:0:0) + Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 + Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) + Total transfers 160151 (74577 reads and 85574 writes) + (scsi0:0:6:0) + Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 + Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) + Total transfers 0 (0 reads and 0 writes) 1.6 Parallel port info in /proc/parport @@ -1296,18 +1387,20 @@ number (0,1,2,...). These directories contain the four files shown in Table 1-10. -Table 1-10: Files in /proc/parport -.............................................................................. - File Content - autoprobe Any IEEE-1284 device ID information that has been acquired. +.. table:: Table 1-10: Files in /proc/parport + + ========= ==================================================================== + File Content + ========= ==================================================================== + autoprobe Any IEEE-1284 device ID information that has been acquired. devices list of the device drivers using that port. A + will appear by the name of the device currently using the port (it might not appear - against any). - hardware Parallel port's base address, IRQ line and DMA channel. + against any). + hardware Parallel port's base address, IRQ line and DMA channel. irq IRQ that parport is using for that port. This is in a separate file to allow you to alter it by writing a new value in (IRQ - number or none). -.............................................................................. + number or none). + ========= ==================================================================== 1.7 TTY info in /proc/tty ------------------------- @@ -1317,29 +1410,31 @@ directory /proc/tty.You'll find entries for drivers and line disciplines in this directory, as shown in Table 1-11. -Table 1-11: Files in /proc/tty -.............................................................................. - File Content - drivers list of drivers and their usage - ldiscs registered line disciplines - driver/serial usage statistic and status of single tty lines -.............................................................................. +.. table:: Table 1-11: Files in /proc/tty + + ============= ============================================== + File Content + ============= ============================================== + drivers list of drivers and their usage + ldiscs registered line disciplines + driver/serial usage statistic and status of single tty lines + ============= ============================================== To see which tty's are currently in use, you can simply look into the file -/proc/tty/drivers: - - > cat /proc/tty/drivers - pty_slave /dev/pts 136 0-255 pty:slave - pty_master /dev/ptm 128 0-255 pty:master - pty_slave /dev/ttyp 3 0-255 pty:slave - pty_master /dev/pty 2 0-255 pty:master - serial /dev/cua 5 64-67 serial:callout - serial /dev/ttyS 4 64-67 serial - /dev/tty0 /dev/tty0 4 0 system:vtmaster - /dev/ptmx /dev/ptmx 5 2 system - /dev/console /dev/console 5 1 system:console - /dev/tty /dev/tty 5 0 system:/dev/tty - unknown /dev/tty 4 1-63 console +/proc/tty/drivers:: + + > cat /proc/tty/drivers + pty_slave /dev/pts 136 0-255 pty:slave + pty_master /dev/ptm 128 0-255 pty:master + pty_slave /dev/ttyp 3 0-255 pty:slave + pty_master /dev/pty 2 0-255 pty:master + serial /dev/cua 5 64-67 serial:callout + serial /dev/ttyS 4 64-67 serial + /dev/tty0 /dev/tty0 4 0 system:vtmaster + /dev/ptmx /dev/ptmx 5 2 system + /dev/console /dev/console 5 1 system:console + /dev/tty /dev/tty 5 0 system:/dev/tty + unknown /dev/tty 4 1-63 console 1.8 Miscellaneous kernel statistics in /proc/stat @@ -1347,7 +1442,7 @@ To see which tty's are currently in use, you can simply look into the file Various pieces of information about kernel activity are available in the /proc/stat file. All of the numbers reported in this file are aggregates -since the system first booted. For a quick look, simply cat the file: +since the system first booted. For a quick look, simply cat the file:: > cat /proc/stat cpu 2255 34 2290 22625563 6290 127 456 0 0 0 @@ -1372,6 +1467,7 @@ second). The meanings of the columns are as follows, from left to right: - idle: twiddling thumbs - iowait: In a word, iowait stands for waiting for I/O to complete. But there are several problems: + 1. Cpu will not wait for I/O to complete, iowait is the time that a task is waiting for I/O to complete. When cpu goes into idle state for outstanding task io, another task will be scheduled on this CPU. @@ -1379,6 +1475,7 @@ second). The meanings of the columns are as follows, from left to right: on any CPU, so the iowait of each CPU is difficult to calculate. 3. The value of iowait field in /proc/stat will decrease in certain conditions. + So, the iowait is not reliable by reading from /proc/stat. - irq: servicing interrupts - softirq: servicing softirqs @@ -1422,18 +1519,19 @@ Information about mounted ext4 file systems can be found in /proc/fs/ext4/dm-0). The files in each per-device directory are shown in Table 1-12, below. -Table 1-12: Files in /proc/fs/ext4/<devname> -.............................................................................. - File Content +.. table:: Table 1-12: Files in /proc/fs/ext4/<devname> + + ============== ========================================================== + File Content mb_groups details of multiblock allocator buddy cache of free blocks -.............................................................................. + ============== ========================================================== 2.0 /proc/consoles ------------------ Shows registered system console lines. To see which character device lines are currently used for the system console -/dev/console, you may simply look into the file /proc/consoles: +/dev/console, you may simply look into the file /proc/consoles:: > cat /proc/consoles tty0 -WU (ECp) 4:7 @@ -1441,41 +1539,45 @@ To see which character device lines are currently used for the system console The columns are: - device name of the device - operations R = can do read operations - W = can do write operations - U = can do unblank - flags E = it is enabled - C = it is preferred console - B = it is primary boot console - p = it is used for printk buffer - b = it is not a TTY but a Braille device - a = it is safe to use when cpu is offline - major:minor major and minor number of the device separated by a colon ++--------------------+-------------------------------------------------------+ +| device | name of the device | ++====================+=======================================================+ +| operations | * R = can do read operations | +| | * W = can do write operations | +| | * U = can do unblank | ++--------------------+-------------------------------------------------------+ +| flags | * E = it is enabled | +| | * C = it is preferred console | +| | * B = it is primary boot console | +| | * p = it is used for printk buffer | +| | * b = it is not a TTY but a Braille device | +| | * a = it is safe to use when cpu is offline | ++--------------------+-------------------------------------------------------+ +| major:minor | major and minor number of the device separated by a | +| | colon | ++--------------------+-------------------------------------------------------+ ------------------------------------------------------------------------------- Summary ------------------------------------------------------------------------------- +------- + The /proc file system serves information about the running system. It not only allows access to process data but also allows you to request the kernel status by reading files in the hierarchy. The directory structure of /proc reflects the types of information and makes it easy, if not obvious, where to look for specific data. ------------------------------------------------------------------------------- ------------------------------------------------------------------------------- -CHAPTER 2: MODIFYING SYSTEM PARAMETERS ------------------------------------------------------------------------------- +Chapter 2: Modifying System Parameters +====================================== ------------------------------------------------------------------------------- In This Chapter ------------------------------------------------------------------------------- +--------------- + * Modifying kernel parameters by writing into files found in /proc/sys * Exploring the files which modify certain parameters * Review of the /proc/sys file tree ------------------------------------------------------------------------------- +------------------------------------------------------------------------------ A very interesting part of /proc is the directory /proc/sys. This is not only a source of information, it also allows you to change parameters within the @@ -1503,19 +1605,18 @@ kernels, and became part of it in version 2.2.1 of the Linux kernel. Please see: Documentation/admin-guide/sysctl/ directory for descriptions of these entries. ------------------------------------------------------------------------------- Summary ------------------------------------------------------------------------------- +------- + Certain aspects of kernel behavior can be modified at runtime, without the need to recompile the kernel, or even to reboot the system. The files in the /proc/sys tree can not only be read, but also modified. You can use the echo command to write value into these files, thereby changing the default settings of the kernel. ------------------------------------------------------------------------------- ------------------------------------------------------------------------------- -CHAPTER 3: PER-PROCESS PARAMETERS ------------------------------------------------------------------------------- + +Chapter 3: Per-process Parameters +================================= 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score -------------------------------------------------------------------------------- @@ -1588,26 +1689,28 @@ process should be killed in an out-of-memory situation. This file contains IO statistics for each running process Example -------- +~~~~~~~ + +:: -test:/tmp # dd if=/dev/zero of=/tmp/test.dat & -[1] 3828 + test:/tmp # dd if=/dev/zero of=/tmp/test.dat & + [1] 3828 -test:/tmp # cat /proc/3828/io -rchar: 323934931 -wchar: 323929600 -syscr: 632687 -syscw: 632675 -read_bytes: 0 -write_bytes: 323932160 -cancelled_write_bytes: 0 + test:/tmp # cat /proc/3828/io + rchar: 323934931 + wchar: 323929600 + syscr: 632687 + syscw: 632675 + read_bytes: 0 + write_bytes: 323932160 + cancelled_write_bytes: 0 Description ------------ +~~~~~~~~~~~ rchar ------ +^^^^^ I/O counter: chars read The number of bytes which this task has caused to be read from storage. This @@ -1618,7 +1721,7 @@ pagecache) wchar ------ +^^^^^ I/O counter: chars written The number of bytes which this task has caused, or shall cause to be written @@ -1626,7 +1729,7 @@ to disk. Similar caveats apply here as with rchar. syscr ------ +^^^^^ I/O counter: read syscalls Attempt to count the number of read I/O operations, i.e. syscalls like read() @@ -1634,7 +1737,7 @@ and pread(). syscw ------ +^^^^^ I/O counter: write syscalls Attempt to count the number of write I/O operations, i.e. syscalls like @@ -1642,7 +1745,7 @@ write() and pwrite(). read_bytes ----------- +^^^^^^^^^^ I/O counter: bytes read Attempt to count the number of bytes which this process really did cause to @@ -1652,7 +1755,7 @@ CIFS at a later time> write_bytes ------------ +^^^^^^^^^^^ I/O counter: bytes written Attempt to count the number of bytes which this process caused to be sent to @@ -1660,7 +1763,7 @@ the storage layer. This is done at page-dirtying time. cancelled_write_bytes ---------------------- +^^^^^^^^^^^^^^^^^^^^^ The big inaccuracy here is truncate. If a process writes 1MB to a file and then deletes the file, it will in fact perform no writeout. But it will have @@ -1673,12 +1776,11 @@ from the truncating task's write_bytes, but there is information loss in doing that. -Note ----- +.. Note:: -At its current implementation state, this is a bit racy on 32-bit machines: if -process A reads process B's /proc/pid/io while process B is updating one of -those 64-bit counters, process A could see an intermediate result. + At its current implementation state, this is a bit racy on 32-bit machines: + if process A reads process B's /proc/pid/io while process B is updating one + of those 64-bit counters, process A could see an intermediate result. More information about this can be found within the taskstats documentation in @@ -1698,12 +1800,13 @@ of memory types. If a bit of the bitmask is set, memory segments of the corresponding memory type are dumped, otherwise they are not dumped. The following 9 memory types are supported: + - (bit 0) anonymous private memory - (bit 1) anonymous shared memory - (bit 2) file-backed private memory - (bit 3) file-backed shared memory - (bit 4) ELF header pages in file-backed private memory areas (it is - effective only if the bit 2 is cleared) + effective only if the bit 2 is cleared) - (bit 5) hugetlb private memory - (bit 6) hugetlb shared memory - (bit 7) DAX private memory @@ -1719,13 +1822,13 @@ The default value of coredump_filter is 0x33; this means all anonymous memory segments, ELF header pages and hugetlb private memory are dumped. If you don't want to dump all shared memory segments attached to pid 1234, -write 0x31 to the process's proc file. +write 0x31 to the process's proc file:: $ echo 0x31 > /proc/1234/coredump_filter When a new process is created, the process inherits the bitmask status from its parent. It is useful to set up coredump_filter before the program runs. -For example: +For example:: $ echo 0x7 > /proc/self/coredump_filter $ ./some_program @@ -1733,35 +1836,37 @@ For example: 3.5 /proc/<pid>/mountinfo - Information about mounts -------------------------------------------------------- -This file contains lines of the form: +This file contains lines of the form:: -36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue -(1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11) + 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue + (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11) -(1) mount ID: unique identifier of the mount (may be reused after umount) -(2) parent ID: ID of parent (or of self for the top of the mount tree) -(3) major:minor: value of st_dev for files on filesystem -(4) root: root of the mount within the filesystem -(5) mount point: mount point relative to the process's root -(6) mount options: per mount options -(7) optional fields: zero or more fields of the form "tag[:value]" -(8) separator: marks the end of the optional fields -(9) filesystem type: name of filesystem of the form "type[.subtype]" -(10) mount source: filesystem specific information or "none" -(11) super options: per super block options + (1) mount ID: unique identifier of the mount (may be reused after umount) + (2) parent ID: ID of parent (or of self for the top of the mount tree) + (3) major:minor: value of st_dev for files on filesystem + (4) root: root of the mount within the filesystem + (5) mount point: mount point relative to the process's root + (6) mount options: per mount options + (7) optional fields: zero or more fields of the form "tag[:value]" + (8) separator: marks the end of the optional fields + (9) filesystem type: name of filesystem of the form "type[.subtype]" + (10) mount source: filesystem specific information or "none" + (11) super options: per super block options Parsers should ignore all unrecognised optional fields. Currently the possible optional fields are: -shared:X mount is shared in peer group X -master:X mount is slave to peer group X -propagate_from:X mount is slave and receives propagation from peer group X (*) -unbindable mount is unbindable +================ ============================================================== +shared:X mount is shared in peer group X +master:X mount is slave to peer group X +propagate_from:X mount is slave and receives propagation from peer group X [#]_ +unbindable mount is unbindable +================ ============================================================== -(*) X is the closest dominant peer group under the process's root. If -X is the immediate master of the mount, or if there's no dominant peer -group under the same root, then only the "master:X" field is present -and not the "propagate_from:X" field. +.. [#] X is the closest dominant peer group under the process's root. If + X is the immediate master of the mount, or if there's no dominant peer + group under the same root, then only the "master:X" field is present + and not the "propagate_from:X" field. For more information on mount propagation see: @@ -1804,77 +1909,86 @@ created with [see open(2) for details] and 'mnt_id' represents mount ID of the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo for details]. -A typical output is +A typical output is:: pos: 0 flags: 0100002 mnt_id: 19 -All locks associated with a file descriptor are shown in its fdinfo too. +All locks associated with a file descriptor are shown in its fdinfo too:: -lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF + lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags pair provide additional information particular to the objects they represent. - Eventfd files - ~~~~~~~~~~~~~ +Eventfd files +~~~~~~~~~~~~~ + +:: + pos: 0 flags: 04002 mnt_id: 9 eventfd-count: 5a - where 'eventfd-count' is hex value of a counter. +where 'eventfd-count' is hex value of a counter. + +Signalfd files +~~~~~~~~~~~~~~ + +:: - Signalfd files - ~~~~~~~~~~~~~~ pos: 0 flags: 04002 mnt_id: 9 sigmask: 0000000000000200 - where 'sigmask' is hex value of the signal mask associated - with a file. +where 'sigmask' is hex value of the signal mask associated +with a file. + +Epoll files +~~~~~~~~~~~ + +:: - Epoll files - ~~~~~~~~~~~ pos: 0 flags: 02 mnt_id: 9 tfd: 5 events: 1d data: ffffffffffffffff pos:0 ino:61af sdev:7 - where 'tfd' is a target file descriptor number in decimal form, - 'events' is events mask being watched and the 'data' is data - associated with a target [see epoll(7) for more details]. +where 'tfd' is a target file descriptor number in decimal form, +'events' is events mask being watched and the 'data' is data +associated with a target [see epoll(7) for more details]. - The 'pos' is current offset of the target file in decimal form - [see lseek(2)], 'ino' and 'sdev' are inode and device numbers - where target file resides, all in hex format. +The 'pos' is current offset of the target file in decimal form +[see lseek(2)], 'ino' and 'sdev' are inode and device numbers +where target file resides, all in hex format. - Fsnotify files - ~~~~~~~~~~~~~~ - For inotify files the format is the following +Fsnotify files +~~~~~~~~~~~~~~ +For inotify files the format is the following:: pos: 0 flags: 02000000 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d - where 'wd' is a watch descriptor in decimal form, ie a target file - descriptor number, 'ino' and 'sdev' are inode and device where the - target file resides and the 'mask' is the mask of events, all in hex - form [see inotify(7) for more details]. +where 'wd' is a watch descriptor in decimal form, ie a target file +descriptor number, 'ino' and 'sdev' are inode and device where the +target file resides and the 'mask' is the mask of events, all in hex +form [see inotify(7) for more details]. - If the kernel was built with exportfs support, the path to the target - file is encoded as a file handle. The file handle is provided by three - fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex - format. +If the kernel was built with exportfs support, the path to the target +file is encoded as a file handle. The file handle is provided by three +fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex +format. - If the kernel is built without exportfs support the file handle won't be - printed out. +If the kernel is built without exportfs support the file handle won't be +printed out. - If there is no inotify mark attached yet the 'inotify' line will be omitted. +If there is no inotify mark attached yet the 'inotify' line will be omitted. - For fanotify files the format is +For fanotify files the format is:: pos: 0 flags: 02 @@ -1883,20 +1997,22 @@ pair provide additional information particular to the objects they represent. fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4 - where fanotify 'flags' and 'event-flags' are values used in fanotify_init - call, 'mnt_id' is the mount point identifier, 'mflags' is the value of - flags associated with mark which are tracked separately from events - mask. 'ino', 'sdev' are target inode and device, 'mask' is the events - mask and 'ignored_mask' is the mask of events which are to be ignored. - All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask' - does provide information about flags and mask used in fanotify_mark - call [see fsnotify manpage for details]. +where fanotify 'flags' and 'event-flags' are values used in fanotify_init +call, 'mnt_id' is the mount point identifier, 'mflags' is the value of +flags associated with mark which are tracked separately from events +mask. 'ino', 'sdev' are target inode and device, 'mask' is the events +mask and 'ignored_mask' is the mask of events which are to be ignored. +All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask' +does provide information about flags and mask used in fanotify_mark +call [see fsnotify manpage for details]. + +While the first three lines are mandatory and always printed, the rest is +optional and may be omitted if no marks created yet. - While the first three lines are mandatory and always printed, the rest is - optional and may be omitted if no marks created yet. +Timerfd files +~~~~~~~~~~~~~ - Timerfd files - ~~~~~~~~~~~~~ +:: pos: 0 flags: 02 @@ -1907,18 +2023,18 @@ pair provide additional information particular to the objects they represent. it_value: (0, 49406829) it_interval: (1, 0) - where 'clockid' is the clock type and 'ticks' is the number of the timer expirations - that have occurred [see timerfd_create(2) for details]. 'settime flags' are - flags in octal form been used to setup the timer [see timerfd_settime(2) for - details]. 'it_value' is remaining time until the timer exiration. - 'it_interval' is the interval for the timer. Note the timer might be set up - with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value' - still exhibits timer's remaining time. +where 'clockid' is the clock type and 'ticks' is the number of the timer expirations +that have occurred [see timerfd_create(2) for details]. 'settime flags' are +flags in octal form been used to setup the timer [see timerfd_settime(2) for +details]. 'it_value' is remaining time until the timer exiration. +'it_interval' is the interval for the timer. Note the timer might be set up +with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value' +still exhibits timer's remaining time. 3.9 /proc/<pid>/map_files - Information about memory mapped files --------------------------------------------------------------------- This directory contains symbolic links which represent memory mapped files -the process is maintaining. Example output: +the process is maintaining. Example output:: | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so @@ -1976,17 +2092,22 @@ When CONFIG_PROC_PID_ARCH_STATUS is enabled, this file displays the architecture specific status of the task. Example -------- +~~~~~~~ + +:: + $ cat /proc/6753/arch_status AVX512_elapsed_ms: 8 Description ------------ +~~~~~~~~~~~ x86 specific entries: ---------------------- - AVX512_elapsed_ms: - ------------------ +~~~~~~~~~~~~~~~~~~~~~ + +AVX512_elapsed_ms: +^^^^^^^^^^^^^^^^^^ + If AVX512 is supported on the machine, this entry shows the milliseconds elapsed since the last time AVX512 usage was recorded. The recording happens on a best effort basis when a task is scheduled out. This means @@ -2010,17 +2131,18 @@ x86 specific entries: the task is unlikely an AVX512 user, but depends on the workload and the scheduling scenario, it also could be a false negative mentioned above. ------------------------------------------------------------------------------- Configuring procfs ------------------------------------------------------------------------------- +------------------ 4.1 Mount options --------------------- The following mount options are supported: + ========= ======================================================== hidepid= Set /proc/<pid>/ access mode. gid= Set the group authorized to learn processes information. + ========= ======================================================== hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories (default). diff --git a/Documentation/filesystems/qnx6.txt b/Documentation/filesystems/qnx6.rst index 48ea68f15845..fd13433d362c 100644 --- a/Documentation/filesystems/qnx6.txt +++ b/Documentation/filesystems/qnx6.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=================== The QNX6 Filesystem =================== @@ -14,10 +17,12 @@ Specification qnx6fs shares many properties with traditional Unix filesystems. It has the concepts of blocks, inodes and directories. + On QNX it is possible to create little endian and big endian qnx6 filesystems. This feature makes it possible to create and use a different endianness fs for the target (QNX is used on quite a range of embedded systems) platform running on a different endianness. + The Linux driver handles endianness transparently. (LE and BE) Blocks @@ -26,6 +31,7 @@ Blocks The space in the device or file is split up into blocks. These are a fixed size of 512, 1024, 2048 or 4096, which is decided when the filesystem is created. + Blockpointers are 32bit, so the maximum space that can be addressed is 2^32 * 4096 bytes or 16TB @@ -50,6 +56,7 @@ Each of these root nodes holds information like total size of the stored data and the addressing levels in that specific tree. If the level value is 0, up to 16 direct blocks can be addressed by each node. + Level 1 adds an additional indirect addressing level where each indirect addressing block holds up to blocksize / 4 bytes pointers to data blocks. Level 2 adds an additional indirect addressing block level (so, already up @@ -57,11 +64,13 @@ to 16 * 256 * 256 = 1048576 blocks that can be addressed by such a tree). Unused block pointers are always set to ~0 - regardless of root node, indirect addressing blocks or inodes. + Data leaves are always on the lowest level. So no data is stored on upper tree levels. The first Superblock is located at 0x2000. (0x2000 is the bootblock size) The Audi MMI 3G first superblock directly starts at byte 0. + Second superblock position can either be calculated from the superblock information (total number of filesystem blocks) or by taking the highest device address, zeroing the last 3 bytes and then subtracting 0x1000 from @@ -84,6 +93,7 @@ Object mode field is POSIX format. (which makes things easier) There are also pointers to the first 16 blocks, if the object data can be addressed with 16 direct blocks. + For more than 16 blocks an indirect addressing in form of another tree is used. (scheme is the same as the one used for the superblock root nodes) @@ -96,13 +106,18 @@ Directories A directory is a filesystem object and has an inode just like a file. It is a specially formatted file containing records which associate each name with an inode number. + '.' inode number points to the directory inode + '..' inode number points to the parent directory inode + Eeach filename record additionally got a filename length field. One special case are long filenames or subdirectory names. + These got set a filename length field of 0xff in the corresponding directory record plus the longfile inode number also stored in that record. + With that longfilename inode number, the longfilename tree can be walked starting with the superblock longfilename root node pointers. @@ -111,6 +126,7 @@ Special files Symbolic links are also filesystem objects with inodes. They got a specific bit in the inode mode field identifying them as symbolic link. + The directory entry file inode pointer points to the target file inode. Hard links got an inode, a directory entry, but a specific mode bit set, @@ -126,9 +142,11 @@ Long filenames Long filenames are stored in a separate addressing tree. The staring point is the longfilename root node in the active superblock. + Each data block (tree leaves) holds one long filename. That filename is limited to 510 bytes. The first two starting bytes are used as length field for the actual filename. + If that structure shall fit for all allowed blocksizes, it is clear why there is a limit of 510 bytes for the actual filename stored. @@ -138,6 +156,7 @@ Bitmap The qnx6fs filesystem allocation bitmap is stored in a tree under bitmap root node in the superblock and each bit in the bitmap represents one filesystem block. + The first block is block 0, which starts 0x1000 after superblock start. So for a normal qnx6fs 0x3000 (bootblock + superblock) is the physical address at which block 0 is located. @@ -149,11 +168,14 @@ Bitmap system area ------------------ The bitmap itself is divided into three parts. + First the system area, that is split into two halves. + Then userspace. The requirement for a static, fixed preallocated system area comes from how qnx6fs deals with writes. + Each superblock got it's own half of the system area. So superblock #1 always uses blocks from the lower half while superblock #2 just writes to blocks represented by the upper half bitmap system area bits. @@ -163,7 +185,7 @@ tree structures are treated as system blocks. The rational behind that is that a write request can work on a new snapshot (system area of the inactive - resp. lower serial numbered superblock) while -at the same time there is still a complete stable filesystem structer in the +at the same time there is still a complete stable filesystem structure in the other half of the system area. When finished with writing (a sync write is completed, the maximum sync leap diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.txt b/Documentation/filesystems/ramfs-rootfs-initramfs.rst index 97d42ccaa92d..6c576e241d86 100644 --- a/Documentation/filesystems/ramfs-rootfs-initramfs.txt +++ b/Documentation/filesystems/ramfs-rootfs-initramfs.rst @@ -1,5 +1,11 @@ -ramfs, rootfs and initramfs +.. SPDX-License-Identifier: GPL-2.0 + +=========================== +Ramfs, rootfs and initramfs +=========================== + October 17, 2005 + Rob Landley <rob@landley.net> ============================= @@ -99,14 +105,14 @@ out of that. All this differs from the old initrd in several ways: - The old initrd was always a separate file, while the initramfs archive is - linked into the linux kernel image. (The directory linux-*/usr is devoted - to generating this archive during the build.) + linked into the linux kernel image. (The directory ``linux-*/usr`` is + devoted to generating this archive during the build.) - The old initrd file was a gzipped filesystem image (in some file format, such as ext2, that needed a driver built into the kernel), while the new initramfs archive is a gzipped cpio archive (like tar only simpler, - see cpio(1) and Documentation/driver-api/early-userspace/buffer-format.rst). The - kernel's cpio extraction code is not only extremely small, it's also + see cpio(1) and Documentation/driver-api/early-userspace/buffer-format.rst). + The kernel's cpio extraction code is not only extremely small, it's also __init text and data that can be discarded during the boot process. - The program run by the old initrd (which was called /initrd, not /init) did @@ -139,7 +145,7 @@ and living in usr/Kconfig) can be used to specify a source for the initramfs archive, which will automatically be incorporated into the resulting binary. This option can point to an existing gzipped cpio archive, a directory containing files to be archived, or a text file -specification such as the following example: +specification such as the following example:: dir /dev 755 0 0 nod /dev/console 644 0 0 c 5 1 @@ -175,12 +181,12 @@ or extracting your own preprepared cpio files to feed to the kernel build (instead of a config file or directory). The following command line can extract a cpio image (either by the above script -or by the kernel build) back into its component files: +or by the kernel build) back into its component files:: cpio -i -d -H newc -F initramfs_data.cpio --no-absolute-filenames The following shell script can create a prebuilt cpio archive you can -use in place of the above config file: +use in place of the above config file:: #!/bin/sh @@ -202,14 +208,17 @@ use in place of the above config file: exit 1 fi -Note: The cpio man page contains some bad advice that will break your initramfs -archive if you follow it. It says "A typical way to generate the list -of filenames is with the find command; you should give find the -depth option -to minimize problems with permissions on directories that are unwritable or not -searchable." Don't do this when creating initramfs.cpio.gz images, it won't -work. The Linux kernel cpio extractor won't create files in a directory that -doesn't exist, so the directory entries must go before the files that go in -those directories. The above script gets them in the right order. +.. Note:: + + The cpio man page contains some bad advice that will break your initramfs + archive if you follow it. It says "A typical way to generate the list + of filenames is with the find command; you should give find the -depth + option to minimize problems with permissions on directories that are + unwritable or not searchable." Don't do this when creating + initramfs.cpio.gz images, it won't work. The Linux kernel cpio extractor + won't create files in a directory that doesn't exist, so the directory + entries must go before the files that go in those directories. + The above script gets them in the right order. External initramfs images: -------------------------- @@ -236,9 +245,10 @@ An initramfs archive is a complete self-contained root filesystem for Linux. If you don't already understand what shared libraries, devices, and paths you need to get a minimal root filesystem up and running, here are some references: -http://www.tldp.org/HOWTO/Bootdisk-HOWTO/ -http://www.tldp.org/HOWTO/From-PowerUp-To-Bash-Prompt-HOWTO.html -http://www.linuxfromscratch.org/lfs/view/stable/ + +- http://www.tldp.org/HOWTO/Bootdisk-HOWTO/ +- http://www.tldp.org/HOWTO/From-PowerUp-To-Bash-Prompt-HOWTO.html +- http://www.linuxfromscratch.org/lfs/view/stable/ The "klibc" package (http://www.kernel.org/pub/linux/libs/klibc) is designed to be a tiny C library to statically link early userspace @@ -255,7 +265,7 @@ name lookups, even when otherwise statically linked.) A good first step is to get initramfs to run a statically linked "hello world" program as init, and test it under an emulator like qemu (www.qemu.org) or -User Mode Linux, like so: +User Mode Linux, like so:: cat > hello.c << EOF #include <stdio.h> @@ -326,8 +336,8 @@ the above threads) is: explained his reasoning: - http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1550.html - http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1638.html + - http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1550.html + - http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1638.html and, most importantly, designed and implemented the initramfs code. diff --git a/Documentation/filesystems/relay.txt b/Documentation/filesystems/relay.rst index cd709a94d054..04ad083cfe62 100644 --- a/Documentation/filesystems/relay.txt +++ b/Documentation/filesystems/relay.rst @@ -1,3 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================== relay interface (formerly relayfs) ================================== @@ -108,6 +111,7 @@ The relay interface implements basic file operations for user space access to relay channel buffer data. Here are the file operations that are available and some comments regarding their behavior: +=========== ============================================================ open() enables user to open an _existing_ channel buffer. mmap() results in channel buffer being mapped into the caller's @@ -136,13 +140,16 @@ poll() POLLIN/POLLRDNORM/POLLERR supported. User applications are close() decrements the channel buffer's refcount. When the refcount reaches 0, i.e. when no process or kernel client has the buffer open, the channel buffer is freed. +=========== ============================================================ In order for a user application to make use of relay files, the -host filesystem must be mounted. For example, +host filesystem must be mounted. For example:: mount -t debugfs debugfs /sys/kernel/debug -NOTE: the host filesystem doesn't need to be mounted for kernel +.. Note:: + + the host filesystem doesn't need to be mounted for kernel clients to create or use channels - it only needs to be mounted when user space applications need access to the buffer data. @@ -154,7 +161,7 @@ The relay interface kernel API Here's a summary of the API the relay interface provides to in-kernel clients: TBD(curr. line MT:/API/) - channel management functions: + channel management functions:: relay_open(base_filename, parent, subbuf_size, n_subbufs, callbacks, private_data) @@ -162,17 +169,17 @@ TBD(curr. line MT:/API/) relay_flush(chan) relay_reset(chan) - channel management typically called on instigation of userspace: + channel management typically called on instigation of userspace:: relay_subbufs_consumed(chan, cpu, subbufs_consumed) - write functions: + write functions:: relay_write(chan, data, length) __relay_write(chan, data, length) relay_reserve(chan, length) - callbacks: + callbacks:: subbuf_start(buf, subbuf, prev_subbuf, prev_padding) buf_mapped(buf, filp) @@ -180,7 +187,7 @@ TBD(curr. line MT:/API/) create_buf_file(filename, parent, mode, buf, is_global) remove_buf_file(dentry) - helper functions: + helper functions:: relay_buf_full(buf) subbuf_start_reserve(buf, length) @@ -215,41 +222,41 @@ the file(s) created in create_buf_file() and is called during relay_close(). Here are some typical definitions for these callbacks, in this case -using debugfs: - -/* - * create_buf_file() callback. Creates relay file in debugfs. - */ -static struct dentry *create_buf_file_handler(const char *filename, - struct dentry *parent, - umode_t mode, - struct rchan_buf *buf, - int *is_global) -{ - return debugfs_create_file(filename, mode, parent, buf, - &relay_file_operations); -} - -/* - * remove_buf_file() callback. Removes relay file from debugfs. - */ -static int remove_buf_file_handler(struct dentry *dentry) -{ - debugfs_remove(dentry); - - return 0; -} - -/* - * relay interface callbacks - */ -static struct rchan_callbacks relay_callbacks = -{ - .create_buf_file = create_buf_file_handler, - .remove_buf_file = remove_buf_file_handler, -}; - -And an example relay_open() invocation using them: +using debugfs:: + + /* + * create_buf_file() callback. Creates relay file in debugfs. + */ + static struct dentry *create_buf_file_handler(const char *filename, + struct dentry *parent, + umode_t mode, + struct rchan_buf *buf, + int *is_global) + { + return debugfs_create_file(filename, mode, parent, buf, + &relay_file_operations); + } + + /* + * remove_buf_file() callback. Removes relay file from debugfs. + */ + static int remove_buf_file_handler(struct dentry *dentry) + { + debugfs_remove(dentry); + + return 0; + } + + /* + * relay interface callbacks + */ + static struct rchan_callbacks relay_callbacks = + { + .create_buf_file = create_buf_file_handler, + .remove_buf_file = remove_buf_file_handler, + }; + +And an example relay_open() invocation using them:: chan = relay_open("cpu", NULL, SUBBUF_SIZE, N_SUBBUFS, &relay_callbacks, NULL); @@ -339,23 +346,23 @@ whether or not to actually move on to the next sub-buffer. To implement 'no-overwrite' mode, the userspace client would provide an implementation of the subbuf_start() callback something like the -following: +following:: -static int subbuf_start(struct rchan_buf *buf, - void *subbuf, - void *prev_subbuf, - unsigned int prev_padding) -{ - if (prev_subbuf) - *((unsigned *)prev_subbuf) = prev_padding; + static int subbuf_start(struct rchan_buf *buf, + void *subbuf, + void *prev_subbuf, + unsigned int prev_padding) + { + if (prev_subbuf) + *((unsigned *)prev_subbuf) = prev_padding; - if (relay_buf_full(buf)) - return 0; + if (relay_buf_full(buf)) + return 0; - subbuf_start_reserve(buf, sizeof(unsigned int)); + subbuf_start_reserve(buf, sizeof(unsigned int)); - return 1; -} + return 1; + } If the current buffer is full, i.e. all sub-buffers remain unconsumed, the callback returns 0 to indicate that the buffer switch should not @@ -370,20 +377,20 @@ ready sub-buffers will relay_buf_full() return 0, in which case the buffer switch can continue. The implementation of the subbuf_start() callback for 'overwrite' mode -would be very similar: +would be very similar:: -static int subbuf_start(struct rchan_buf *buf, - void *subbuf, - void *prev_subbuf, - size_t prev_padding) -{ - if (prev_subbuf) - *((unsigned *)prev_subbuf) = prev_padding; + static int subbuf_start(struct rchan_buf *buf, + void *subbuf, + void *prev_subbuf, + size_t prev_padding) + { + if (prev_subbuf) + *((unsigned *)prev_subbuf) = prev_padding; - subbuf_start_reserve(buf, sizeof(unsigned int)); + subbuf_start_reserve(buf, sizeof(unsigned int)); - return 1; -} + return 1; + } In this case, the relay_buf_full() check is meaningless and the callback always returns 1, causing the buffer switch to occur diff --git a/Documentation/filesystems/romfs.txt b/Documentation/filesystems/romfs.rst index e2b07cc9120a..465b11efa9be 100644 --- a/Documentation/filesystems/romfs.txt +++ b/Documentation/filesystems/romfs.rst @@ -1,4 +1,8 @@ -ROMFS - ROM FILE SYSTEM +.. SPDX-License-Identifier: GPL-2.0 + +======================= +ROMFS - ROM File System +======================= This is a quite dumb, read only filesystem, mainly for initial RAM disks of installation disks. It has grown up by the need of having @@ -51,9 +55,9 @@ the 16 byte padding for the name and the contents, also 16+14+15 = 45 bytes. This is quite rare however, since most file names are longer than 3 bytes, and shorter than 15 bytes. -The layout of the filesystem is the following: +The layout of the filesystem is the following:: -offset content + offset content +---+---+---+---+ 0 | - | r | o | m | \ @@ -84,9 +88,9 @@ the source. This algorithm was chosen because although it's not quite reliable, it does not require any tables, and it is very simple. The following bytes are now part of the file system; each file header -must begin on a 16 byte boundary. +must begin on a 16 byte boundary:: -offset content + offset content +---+---+---+---+ 0 | next filehdr|X| The offset of the next file header @@ -114,7 +118,9 @@ file is user and group 0, this should never be a problem for the intended use. The mapping of the 8 possible values to file types is the following: +== =============== ============================================ mapping spec.info means +== =============== ============================================ 0 hard link link destination [file header] 1 directory first file's header 2 regular file unused, must be zero [MBZ] @@ -123,6 +129,7 @@ the following: 5 char device - " - 6 socket unused, MBZ 7 fifo unused, MBZ +== =============== ============================================ Note that hard links are specifically marked in this filesystem, but they will behave as you can expect (i.e. share the inode number). @@ -158,24 +165,24 @@ to romfs-subscribe@shadow.banki.hu, the content is irrelevant. Pending issues: - Permissions and owner information are pretty essential features of a -Un*x like system, but romfs does not provide the full possibilities. -I have never found this limiting, but others might. + Un*x like system, but romfs does not provide the full possibilities. + I have never found this limiting, but others might. - The file system is read only, so it can be very small, but in case -one would want to write _anything_ to a file system, he still needs -a writable file system, thus negating the size advantages. Possible -solutions: implement write access as a compile-time option, or a new, -similarly small writable filesystem for RAM disks. + one would want to write _anything_ to a file system, he still needs + a writable file system, thus negating the size advantages. Possible + solutions: implement write access as a compile-time option, or a new, + similarly small writable filesystem for RAM disks. - Since the files are only required to have alignment on a 16 byte -boundary, it is currently possibly suboptimal to read or execute files -from the filesystem. It might be resolved by reordering file data to -have most of it (i.e. except the start and the end) laying at "natural" -boundaries, thus it would be possible to directly map a big portion of -the file contents to the mm subsystem. + boundary, it is currently possibly suboptimal to read or execute files + from the filesystem. It might be resolved by reordering file data to + have most of it (i.e. except the start and the end) laying at "natural" + boundaries, thus it would be possible to directly map a big portion of + the file contents to the mm subsystem. - Compression might be an useful feature, but memory is quite a -limiting factor in my eyes. + limiting factor in my eyes. - Where it is used? @@ -183,4 +190,5 @@ limiting factor in my eyes. Have fun, + Janos Farkas <chexum@shadow.banki.hu> diff --git a/Documentation/filesystems/squashfs.txt b/Documentation/filesystems/squashfs.rst index e5274f84dc56..df42106bae71 100644 --- a/Documentation/filesystems/squashfs.txt +++ b/Documentation/filesystems/squashfs.rst @@ -1,7 +1,11 @@ -SQUASHFS 4.0 FILESYSTEM +.. SPDX-License-Identifier: GPL-2.0 + +======================= +Squashfs 4.0 Filesystem ======================= Squashfs is a compressed read-only filesystem for Linux. + It uses zlib, lz4, lzo, or 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 @@ -15,31 +19,33 @@ needed. Mailing list: squashfs-devel@lists.sourceforge.net Web site: www.squashfs.org -1. FILESYSTEM FEATURES +1. Filesystem Features ---------------------- Squashfs filesystem features versus Cramfs: +============================== ========= ========== Squashfs Cramfs - -Max filesystem size: 2^64 256 MiB -Max file size: ~ 2 TiB 16 MiB -Max files: unlimited unlimited -Max directories: unlimited unlimited -Max entries per directory: unlimited unlimited -Max block size: 1 MiB 4 KiB -Metadata compression: yes no -Directory indexes: yes no -Sparse file support: yes no -Tail-end packing (fragments): yes no -Exportable (NFS etc.): yes no -Hard link support: yes no -"." and ".." in readdir: yes no -Real inode numbers: yes no -32-bit uids/gids: yes no -File creation time: yes no -Xattr support: yes no -ACL support: no no +============================== ========= ========== +Max filesystem size 2^64 256 MiB +Max file size ~ 2 TiB 16 MiB +Max files unlimited unlimited +Max directories unlimited unlimited +Max entries per directory unlimited unlimited +Max block size 1 MiB 4 KiB +Metadata compression yes no +Directory indexes yes no +Sparse file support yes no +Tail-end packing (fragments) yes no +Exportable (NFS etc.) yes no +Hard link support yes no +"." and ".." in readdir yes no +Real inode numbers yes no +32-bit uids/gids yes no +File creation time yes no +Xattr support yes no +ACL support no no +============================== ========= ========== Squashfs compresses data, inodes and directories. In addition, inode and directory data are highly compacted, and packed on byte boundaries. Each @@ -47,7 +53,7 @@ compressed inode is on average 8 bytes in length (the exact length varies on file type, i.e. regular file, directory, symbolic link, and block/char device inodes have different sizes). -2. USING SQUASHFS +2. Using Squashfs ----------------- As squashfs is a read-only filesystem, the mksquashfs program must be used to @@ -58,11 +64,11 @@ 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 +3. Squashfs Filesystem Design ----------------------------- A squashfs filesystem consists of a maximum of nine parts, packed together on a -byte alignment: +byte alignment:: --------------- | superblock | @@ -229,15 +235,15 @@ location of the xattr list inside each inode, a 32-bit xattr id is stored. This xattr id is mapped into the location of the xattr list using a second xattr id lookup table. -4. TODOS AND OUTSTANDING ISSUES +4. TODOs and Outstanding Issues ------------------------------- -4.1 Todo list +4.1 TODO list ------------- Implement ACL support. -4.2 Squashfs internal cache +4.2 Squashfs Internal Cache --------------------------- Blocks in Squashfs are compressed. To avoid repeatedly decompressing diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.rst index ddf15b1b0d5a..290891c3fecb 100644 --- a/Documentation/filesystems/sysfs.txt +++ b/Documentation/filesystems/sysfs.rst @@ -1,32 +1,36 @@ +.. SPDX-License-Identifier: GPL-2.0 -sysfs - _The_ filesystem for exporting kernel objects. +===================================================== +sysfs - _The_ filesystem for exporting kernel objects +===================================================== Patrick Mochel <mochel@osdl.org> + Mike Murphy <mamurph@cs.clemson.edu> -Revised: 16 August 2011 -Original: 10 January 2003 +:Revised: 16 August 2011 +:Original: 10 January 2003 What it is: ~~~~~~~~~~~ sysfs is a ram-based filesystem initially based on ramfs. It provides -a means to export kernel data structures, their attributes, and the -linkages between them to userspace. +a means to export kernel data structures, their attributes, and the +linkages between them to userspace. sysfs is tied inherently to the kobject infrastructure. Please read Documentation/kobject.txt for more information concerning the kobject -interface. +interface. Using sysfs ~~~~~~~~~~~ sysfs is always compiled in if CONFIG_SYSFS is defined. You can access -it by doing: +it by doing:: - mount -t sysfs sysfs /sys + mount -t sysfs sysfs /sys Directory Creation @@ -37,7 +41,7 @@ created for it in sysfs. That directory is created as a subdirectory of the kobject's parent, expressing internal object hierarchies to userspace. Top-level directories in sysfs represent the common ancestors of object hierarchies; i.e. the subsystems the objects -belong to. +belong to. Sysfs internally stores a pointer to the kobject that implements a directory in the kernfs_node object associated with the directory. In @@ -58,63 +62,63 @@ attributes. Attributes should be ASCII text files, preferably with only one value per file. It is noted that it may not be efficient to contain only one value per file, so it is socially acceptable to express an array of -values of the same type. +values of the same type. Mixing types, expressing multiple lines of data, and doing fancy formatting of data is heavily frowned upon. Doing these things may get -you publicly humiliated and your code rewritten without notice. +you publicly humiliated and your code rewritten without notice. -An attribute definition is simply: +An attribute definition is simply:: -struct attribute { - char * name; - struct module *owner; - umode_t mode; -}; + struct attribute { + char * name; + struct module *owner; + umode_t mode; + }; -int sysfs_create_file(struct kobject * kobj, const struct attribute * attr); -void sysfs_remove_file(struct kobject * kobj, const struct attribute * attr); + int sysfs_create_file(struct kobject * kobj, const struct attribute * attr); + void sysfs_remove_file(struct kobject * kobj, const struct attribute * attr); A bare attribute contains no means to read or write the value of the attribute. Subsystems are encouraged to define their own attribute structure and wrapper functions for adding and removing attributes for -a specific object type. +a specific object type. -For example, the driver model defines struct device_attribute like: +For example, the driver model defines struct device_attribute like:: -struct device_attribute { - struct attribute attr; - ssize_t (*show)(struct device *dev, struct device_attribute *attr, - char *buf); - ssize_t (*store)(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count); -}; + struct device_attribute { + struct attribute attr; + ssize_t (*show)(struct device *dev, struct device_attribute *attr, + char *buf); + ssize_t (*store)(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count); + }; -int device_create_file(struct device *, const struct device_attribute *); -void device_remove_file(struct device *, const struct device_attribute *); + int device_create_file(struct device *, const struct device_attribute *); + void device_remove_file(struct device *, const struct device_attribute *); -It also defines this helper for defining device attributes: +It also defines this helper for defining device attributes:: -#define DEVICE_ATTR(_name, _mode, _show, _store) \ -struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store) + #define DEVICE_ATTR(_name, _mode, _show, _store) \ + struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store) -For example, declaring +For example, declaring:: -static DEVICE_ATTR(foo, S_IWUSR | S_IRUGO, show_foo, store_foo); + static DEVICE_ATTR(foo, S_IWUSR | S_IRUGO, show_foo, store_foo); -is equivalent to doing: +is equivalent to doing:: -static struct device_attribute dev_attr_foo = { - .attr = { - .name = "foo", - .mode = S_IWUSR | S_IRUGO, - }, - .show = show_foo, - .store = store_foo, -}; + static struct device_attribute dev_attr_foo = { + .attr = { + .name = "foo", + .mode = S_IWUSR | S_IRUGO, + }, + .show = show_foo, + .store = store_foo, + }; Note as stated in include/linux/kernel.h "OTHER_WRITABLE? Generally considered a bad idea." so trying to set a sysfs file writable for @@ -127,15 +131,21 @@ readable. The above case could be shortened to: static struct device_attribute dev_attr_foo = __ATTR_RW(foo); the list of helpers available to define your wrapper function is: -__ATTR_RO(name): assumes default name_show and mode 0444 -__ATTR_WO(name): assumes a name_store only and is restricted to mode + +__ATTR_RO(name): + assumes default name_show and mode 0444 +__ATTR_WO(name): + assumes a name_store only and is restricted to mode 0200 that is root write access only. -__ATTR_RO_MODE(name, mode): fore more restrictive RO access currently +__ATTR_RO_MODE(name, mode): + fore more restrictive RO access currently only use case is the EFI System Resource Table (see drivers/firmware/efi/esrt.c) -__ATTR_RW(name): assumes default name_show, name_store and setting +__ATTR_RW(name): + assumes default name_show, name_store and setting mode to 0644. -__ATTR_NULL: which sets the name to NULL and is used as end of list +__ATTR_NULL: + which sets the name to NULL and is used as end of list indicator (see: kernel/workqueue.c) Subsystem-Specific Callbacks @@ -143,12 +153,12 @@ Subsystem-Specific Callbacks When a subsystem defines a new attribute type, it must implement a set of sysfs operations for forwarding read and write calls to the -show and store methods of the attribute owners. +show and store methods of the attribute owners:: -struct sysfs_ops { - ssize_t (*show)(struct kobject *, struct attribute *, char *); - ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t); -}; + struct sysfs_ops { + ssize_t (*show)(struct kobject *, struct attribute *, char *); + ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t); + }; [ Subsystems should have already defined a struct kobj_type as a descriptor for this type, which is where the sysfs_ops pointer is @@ -157,29 +167,29 @@ stored. See the kobject documentation for more information. ] When a file is read or written, sysfs calls the appropriate method for the type. The method then translates the generic struct kobject and struct attribute pointers to the appropriate pointer types, and -calls the associated methods. +calls the associated methods. -To illustrate: +To illustrate:: -#define to_dev(obj) container_of(obj, struct device, kobj) -#define to_dev_attr(_attr) container_of(_attr, struct device_attribute, attr) + #define to_dev(obj) container_of(obj, struct device, kobj) + #define to_dev_attr(_attr) container_of(_attr, struct device_attribute, attr) -static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr, - char *buf) -{ - struct device_attribute *dev_attr = to_dev_attr(attr); - struct device *dev = to_dev(kobj); - ssize_t ret = -EIO; + static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) + { + struct device_attribute *dev_attr = to_dev_attr(attr); + struct device *dev = to_dev(kobj); + ssize_t ret = -EIO; - if (dev_attr->show) - ret = dev_attr->show(dev, dev_attr, buf); - if (ret >= (ssize_t)PAGE_SIZE) { - printk("dev_attr_show: %pS returned bad count\n", - dev_attr->show); - } - return ret; -} + if (dev_attr->show) + ret = dev_attr->show(dev, dev_attr, buf); + if (ret >= (ssize_t)PAGE_SIZE) { + printk("dev_attr_show: %pS returned bad count\n", + dev_attr->show); + } + return ret; + } @@ -188,11 +198,11 @@ Reading/Writing Attribute Data To read or write attributes, show() or store() methods must be specified when declaring the attribute. The method types should be as -simple as those defined for device attributes: +simple as those defined for device attributes:: -ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf); -ssize_t (*store)(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count); + ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf); + ssize_t (*store)(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count); IOW, they should take only an object, an attribute, and a buffer as parameters. @@ -200,11 +210,11 @@ IOW, they should take only an object, an attribute, and a buffer as parameters. sysfs allocates a buffer of size (PAGE_SIZE) and passes it to the method. Sysfs will call the method exactly once for each read or write. This forces the following behavior on the method -implementations: +implementations: -- On read(2), the show() method should fill the entire buffer. +- On read(2), the show() method should fill the entire buffer. Recall that an attribute should only be exporting one value, or an - array of similar values, so this shouldn't be that expensive. + array of similar values, so this shouldn't be that expensive. This allows userspace to do partial reads and forward seeks arbitrarily over the entire file at will. If userspace seeks back to @@ -218,10 +228,10 @@ implementations: When writing sysfs files, userspace processes should first read the entire file, modify the values it wishes to change, then write the - entire buffer back. + entire buffer back. Attribute method implementations should operate on an identical - buffer when reading and writing values. + buffer when reading and writing values. Other notes: @@ -229,7 +239,7 @@ Other notes: file position. - The buffer will always be PAGE_SIZE bytes in length. On i386, this - is 4096. + is 4096. - show() methods should return the number of bytes printed into the buffer. This is the return value of scnprintf(). @@ -246,31 +256,31 @@ Other notes: through, be sure to return an error. - The object passed to the methods will be pinned in memory via sysfs - referencing counting its embedded object. However, the physical - entity (e.g. device) the object represents may not be present. Be - sure to have a way to check this, if necessary. + referencing counting its embedded object. However, the physical + entity (e.g. device) the object represents may not be present. Be + sure to have a way to check this, if necessary. -A very simple (and naive) implementation of a device attribute is: +A very simple (and naive) implementation of a device attribute is:: -static ssize_t show_name(struct device *dev, struct device_attribute *attr, - char *buf) -{ - return scnprintf(buf, PAGE_SIZE, "%s\n", dev->name); -} + static ssize_t show_name(struct device *dev, struct device_attribute *attr, + char *buf) + { + return scnprintf(buf, PAGE_SIZE, "%s\n", dev->name); + } -static ssize_t store_name(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) -{ - snprintf(dev->name, sizeof(dev->name), "%.*s", - (int)min(count, sizeof(dev->name) - 1), buf); - return count; -} + static ssize_t store_name(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) + { + snprintf(dev->name, sizeof(dev->name), "%.*s", + (int)min(count, sizeof(dev->name) - 1), buf); + return count; + } -static DEVICE_ATTR(name, S_IRUGO, show_name, store_name); + static DEVICE_ATTR(name, S_IRUGO, show_name, store_name); -(Note that the real implementation doesn't allow userspace to set the +(Note that the real implementation doesn't allow userspace to set the name for a device.) @@ -278,25 +288,25 @@ Top Level Directory Layout ~~~~~~~~~~~~~~~~~~~~~~~~~~ The sysfs directory arrangement exposes the relationship of kernel -data structures. +data structures. -The top level sysfs directory looks like: +The top level sysfs directory looks like:: -block/ -bus/ -class/ -dev/ -devices/ -firmware/ -net/ -fs/ + block/ + bus/ + class/ + dev/ + devices/ + firmware/ + net/ + fs/ devices/ contains a filesystem representation of the device tree. It maps directly to the internal kernel device tree, which is a hierarchy of -struct device. +struct device. bus/ contains flat directory layout of the various bus types in the -kernel. Each bus's directory contains two subdirectories: +kernel. Each bus's directory contains two subdirectories:: devices/ drivers/ @@ -331,71 +341,71 @@ Current Interfaces The following interface layers currently exist in sysfs: -- devices (include/linux/device.h) ----------------------------------- -Structure: +devices (include/linux/device.h) +-------------------------------- +Structure:: -struct device_attribute { - struct attribute attr; - ssize_t (*show)(struct device *dev, struct device_attribute *attr, - char *buf); - ssize_t (*store)(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count); -}; + struct device_attribute { + struct attribute attr; + ssize_t (*show)(struct device *dev, struct device_attribute *attr, + char *buf); + ssize_t (*store)(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count); + }; -Declaring: +Declaring:: -DEVICE_ATTR(_name, _mode, _show, _store); + DEVICE_ATTR(_name, _mode, _show, _store); -Creation/Removal: +Creation/Removal:: -int device_create_file(struct device *dev, const struct device_attribute * attr); -void device_remove_file(struct device *dev, const struct device_attribute * attr); + int device_create_file(struct device *dev, const struct device_attribute * attr); + void device_remove_file(struct device *dev, const struct device_attribute * attr); -- bus drivers (include/linux/device.h) --------------------------------------- -Structure: +bus drivers (include/linux/device.h) +------------------------------------ +Structure:: -struct bus_attribute { - struct attribute attr; - ssize_t (*show)(struct bus_type *, char * buf); - ssize_t (*store)(struct bus_type *, const char * buf, size_t count); -}; + struct bus_attribute { + struct attribute attr; + ssize_t (*show)(struct bus_type *, char * buf); + ssize_t (*store)(struct bus_type *, const char * buf, size_t count); + }; -Declaring: +Declaring:: -static BUS_ATTR_RW(name); -static BUS_ATTR_RO(name); -static BUS_ATTR_WO(name); + static BUS_ATTR_RW(name); + static BUS_ATTR_RO(name); + static BUS_ATTR_WO(name); -Creation/Removal: +Creation/Removal:: -int bus_create_file(struct bus_type *, struct bus_attribute *); -void bus_remove_file(struct bus_type *, struct bus_attribute *); + int bus_create_file(struct bus_type *, struct bus_attribute *); + void bus_remove_file(struct bus_type *, struct bus_attribute *); -- device drivers (include/linux/device.h) ------------------------------------------ +device drivers (include/linux/device.h) +--------------------------------------- -Structure: +Structure:: -struct driver_attribute { - struct attribute attr; - ssize_t (*show)(struct device_driver *, char * buf); - ssize_t (*store)(struct device_driver *, const char * buf, - size_t count); -}; + struct driver_attribute { + struct attribute attr; + ssize_t (*show)(struct device_driver *, char * buf); + ssize_t (*store)(struct device_driver *, const char * buf, + size_t count); + }; -Declaring: +Declaring:: -DRIVER_ATTR_RO(_name) -DRIVER_ATTR_RW(_name) + DRIVER_ATTR_RO(_name) + DRIVER_ATTR_RW(_name) -Creation/Removal: +Creation/Removal:: -int driver_create_file(struct device_driver *, const struct driver_attribute *); -void driver_remove_file(struct device_driver *, const struct driver_attribute *); + int driver_create_file(struct device_driver *, const struct driver_attribute *); + void driver_remove_file(struct device_driver *, const struct driver_attribute *); Documentation diff --git a/Documentation/filesystems/sysv-fs.txt b/Documentation/filesystems/sysv-fs.rst index 253b50d1328e..89e40911ad7c 100644 --- a/Documentation/filesystems/sysv-fs.txt +++ b/Documentation/filesystems/sysv-fs.rst @@ -1,25 +1,40 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================== +SystemV Filesystem +================== + It implements all of - Xenix FS, - SystemV/386 FS, - Coherent FS. To install: + * Answer the 'System V and Coherent filesystem support' question with 'y' when configuring the kernel. -* To mount a disk or a partition, use +* To mount a disk or a partition, use:: + mount [-r] -t sysv device mountpoint - The file system type names + + The file system type names:: + -t sysv -t xenix -t coherent + may be used interchangeably, but the last two will eventually disappear. Bugs in the present implementation: + - Coherent FS: + - The "free list interleave" n:m is currently ignored. - Only file systems with no filesystem name and no pack name are recognized. - (See Coherent "man mkfs" for a description of these features.) + (See Coherent "man mkfs" for a description of these features.) + - SystemV Release 2 FS: + The superblock is only searched in the blocks 9, 15, 18, which corresponds to the beginning of track 1 on floppy disks. No support for this FS on hard disk yet. @@ -28,12 +43,14 @@ Bugs in the present implementation: These filesystems are rather similar. Here is a comparison with Minix FS: * Linux fdisk reports on partitions + - Minix FS 0x81 Linux/Minix - Xenix FS ?? - SystemV FS ?? - Coherent FS 0x08 AIX bootable * Size of a block or zone (data allocation unit on disk) + - Minix FS 1024 - Xenix FS 1024 (also 512 ??) - SystemV FS 1024 (also 512 and 2048) @@ -45,37 +62,51 @@ These filesystems are rather similar. Here is a comparison with Minix FS: all the block numbers (including the super block) are offset by one track. * Byte ordering of "short" (16 bit entities) on disk: + - Minix FS little endian 0 1 - Xenix FS little endian 0 1 - SystemV FS little endian 0 1 - Coherent FS little endian 0 1 + Of course, this affects only the file system, not the data of files on it! * Byte ordering of "long" (32 bit entities) on disk: + - Minix FS little endian 0 1 2 3 - Xenix FS little endian 0 1 2 3 - SystemV FS little endian 0 1 2 3 - Coherent FS PDP-11 2 3 0 1 + Of course, this affects only the file system, not the data of files on it! * Inode on disk: "short", 0 means non-existent, the root dir ino is: - - Minix FS 1 - - Xenix FS, SystemV FS, Coherent FS 2 + + ================================= == + Minix FS 1 + Xenix FS, SystemV FS, Coherent FS 2 + ================================= == * Maximum number of hard links to a file: - - Minix FS 250 - - Xenix FS ?? - - SystemV FS ?? - - Coherent FS >=10000 + + =========== ========= + Minix FS 250 + Xenix FS ?? + SystemV FS ?? + Coherent FS >=10000 + =========== ========= * Free inode management: - - Minix FS a bitmap + + - Minix FS + a bitmap - Xenix FS, SystemV FS, Coherent FS There is a cache of a certain number of free inodes in the super-block. When it is exhausted, new free inodes are found using a linear search. * Free block management: - - Minix FS a bitmap + + - Minix FS + a bitmap - Xenix FS, SystemV FS, Coherent FS Free blocks are organized in a "free list". Maybe a misleading term, since it is not true that every free block contains a pointer to @@ -86,13 +117,18 @@ These filesystems are rather similar. Here is a comparison with Minix FS: 0 on Xenix FS and SystemV FS, with a block zeroed out on Coherent FS. * Super-block location: - - Minix FS block 1 = bytes 1024..2047 - - Xenix FS block 1 = bytes 1024..2047 - - SystemV FS bytes 512..1023 - - Coherent FS block 1 = bytes 512..1023 + + =========== ========================== + Minix FS block 1 = bytes 1024..2047 + Xenix FS block 1 = bytes 1024..2047 + SystemV FS bytes 512..1023 + Coherent FS block 1 = bytes 512..1023 + =========== ========================== * Super-block layout: - - Minix FS + + - Minix FS:: + unsigned short s_ninodes; unsigned short s_nzones; unsigned short s_imap_blocks; @@ -101,7 +137,9 @@ These filesystems are rather similar. Here is a comparison with Minix FS: unsigned short s_log_zone_size; unsigned long s_max_size; unsigned short s_magic; - - Xenix FS, SystemV FS, Coherent FS + + - Xenix FS, SystemV FS, Coherent FS:: + unsigned short s_firstdatazone; unsigned long s_nzones; unsigned short s_fzone_count; @@ -120,23 +158,33 @@ These filesystems are rather similar. Here is a comparison with Minix FS: unsigned short s_interleave_m,s_interleave_n; -- Coherent FS only char s_fname[6]; char s_fpack[6]; + then they differ considerably: - Xenix FS + + Xenix FS:: + char s_clean; char s_fill[371]; long s_magic; long s_type; - SystemV FS + + SystemV FS:: + long s_fill[12 or 14]; long s_state; long s_magic; long s_type; - Coherent FS + + Coherent FS:: + unsigned long s_unique; + Note that Coherent FS has no magic. * Inode layout: - - Minix FS + + - Minix FS:: + unsigned short i_mode; unsigned short i_uid; unsigned long i_size; @@ -144,7 +192,9 @@ These filesystems are rather similar. Here is a comparison with Minix FS: unsigned char i_gid; unsigned char i_nlinks; unsigned short i_zone[7+1+1]; - - Xenix FS, SystemV FS, Coherent FS + + - Xenix FS, SystemV FS, Coherent FS:: + unsigned short i_mode; unsigned short i_nlink; unsigned short i_uid; @@ -155,38 +205,55 @@ These filesystems are rather similar. Here is a comparison with Minix FS: unsigned long i_mtime; unsigned long i_ctime; + * Regular file data blocks are organized as - - Minix FS - 7 direct blocks - 1 indirect block (pointers to blocks) - 1 double-indirect block (pointer to pointers to blocks) - - Xenix FS, SystemV FS, Coherent FS - 10 direct blocks - 1 indirect block (pointers to blocks) - 1 double-indirect block (pointer to pointers to blocks) - 1 triple-indirect block (pointer to pointers to pointers to blocks) -* Inode size, inodes per block - - Minix FS 32 32 - - Xenix FS 64 16 - - SystemV FS 64 16 - - Coherent FS 64 8 + - Minix FS: + + - 7 direct blocks + - 1 indirect block (pointers to blocks) + - 1 double-indirect block (pointer to pointers to blocks) + + - Xenix FS, SystemV FS, Coherent FS: + + - 10 direct blocks + - 1 indirect block (pointers to blocks) + - 1 double-indirect block (pointer to pointers to blocks) + - 1 triple-indirect block (pointer to pointers to pointers to blocks) + + + =========== ========== ================ + Inode size inodes per block + =========== ========== ================ + Minix FS 32 32 + Xenix FS 64 16 + SystemV FS 64 16 + Coherent FS 64 8 + =========== ========== ================ * Directory entry on disk - - Minix FS + + - Minix FS:: + unsigned short inode; char name[14/30]; - - Xenix FS, SystemV FS, Coherent FS + + - Xenix FS, SystemV FS, Coherent FS:: + unsigned short inode; char name[14]; -* Dir entry size, dir entries per block - - Minix FS 16/32 64/32 - - Xenix FS 16 64 - - SystemV FS 16 64 - - Coherent FS 16 32 + =========== ============== ===================== + Dir entry size dir entries per block + =========== ============== ===================== + Minix FS 16/32 64/32 + Xenix FS 16 64 + SystemV FS 16 64 + Coherent FS 16 32 + =========== ============== ===================== * How to implement symbolic links such that the host fsck doesn't scream: + - Minix FS normal - Xenix FS kludge: as regular files with chmod 1000 - SystemV FS ?? diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.rst index 5ecbc03e6b2f..4e95929301a5 100644 --- a/Documentation/filesystems/tmpfs.txt +++ b/Documentation/filesystems/tmpfs.rst @@ -1,3 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===== +Tmpfs +===== + Tmpfs is a file system which keeps all files in virtual memory. @@ -14,7 +20,7 @@ If you compare it to ramfs (which was the template to create tmpfs) you gain swapping and limit checking. Another similar thing is the RAM disk (/dev/ram*), which simulates a fixed size hard disk in physical RAM, where you have to create an ordinary filesystem on top. Ramdisks -cannot swap and you do not have the possibility to resize them. +cannot swap and you do not have the possibility to resize them. Since tmpfs lives completely in the page cache and on swap, all tmpfs pages will be shown as "Shmem" in /proc/meminfo and "Shared" in @@ -26,7 +32,7 @@ tmpfs has the following uses: 1) There is always a kernel internal mount which you will not see at all. This is used for shared anonymous mappings and SYSV shared - memory. + memory. This mount does not depend on CONFIG_TMPFS. If CONFIG_TMPFS is not set, the user visible part of tmpfs is not build. But the internal @@ -34,7 +40,7 @@ tmpfs has the following uses: 2) glibc 2.2 and above expects tmpfs to be mounted at /dev/shm for POSIX shared memory (shm_open, shm_unlink). Adding the following - line to /etc/fstab should take care of this: + line to /etc/fstab should take care of this:: tmpfs /dev/shm tmpfs defaults 0 0 @@ -56,15 +62,17 @@ tmpfs has the following uses: tmpfs has three mount options for sizing: -size: The limit of allocated bytes for this tmpfs instance. The +========= ============================================================ +size The limit of allocated bytes for this tmpfs instance. The default is half of your physical RAM without swap. If you oversize your tmpfs instances the machine will deadlock since the OOM handler will not be able to free that memory. -nr_blocks: The same as size, but in blocks of PAGE_SIZE. -nr_inodes: The maximum number of inodes for this instance. The default +nr_blocks The same as size, but in blocks of PAGE_SIZE. +nr_inodes The maximum number of inodes for this instance. The default is half of the number of your physical RAM pages, or (on a machine with highmem) the number of lowmem RAM pages, whichever is the lower. +========= ============================================================ These parameters accept a suffix k, m or g for kilo, mega and giga and can be changed on remount. The size parameter also accepts a suffix % @@ -82,6 +90,7 @@ tmpfs has a mount option to set the NUMA memory allocation policy for all files in that instance (if CONFIG_NUMA is enabled) - which can be adjusted on the fly via 'mount -o remount ...' +======================== ============================================== mpol=default use the process allocation policy (see set_mempolicy(2)) mpol=prefer:Node prefers to allocate memory from the given Node @@ -89,6 +98,7 @@ mpol=bind:NodeList allocates memory only from nodes in NodeList mpol=interleave prefers to allocate from each node in turn mpol=interleave:NodeList allocates from each node of NodeList in turn mpol=local prefers to allocate memory from the local node +======================== ============================================== NodeList format is a comma-separated list of decimal numbers and ranges, a range being two hyphen-separated decimal numbers, the smallest and @@ -98,9 +108,9 @@ A memory policy with a valid NodeList will be saved, as specified, for use at file creation time. When a task allocates a file in the file system, the mount option memory policy will be applied with a NodeList, if any, modified by the calling task's cpuset constraints -[See Documentation/admin-guide/cgroup-v1/cpusets.rst] and any optional flags, listed -below. If the resulting NodeLists is the empty set, the effective memory -policy for the file will revert to "default" policy. +[See Documentation/admin-guide/cgroup-v1/cpusets.rst] and any optional flags, +listed below. If the resulting NodeLists is the empty set, the effective +memory policy for the file will revert to "default" policy. NUMA memory allocation policies have optional flags that can be used in conjunction with their modes. These optional flags can be specified @@ -109,6 +119,8 @@ See Documentation/admin-guide/mm/numa_memory_policy.rst for a list of all available memory allocation policy mode flags and their effect on memory policy. +:: + =static is equivalent to MPOL_F_STATIC_NODES =relative is equivalent to MPOL_F_RELATIVE_NODES @@ -128,9 +140,11 @@ on MountPoint, by 'mount -o remount,mpol=Policy:NodeList MountPoint'. To specify the initial root directory you can use the following mount options: -mode: The permissions as an octal number -uid: The user id -gid: The group id +==== ================================== +mode The permissions as an octal number +uid The user id +gid The group id +==== ================================== These options do not have any effect on remount. You can change these parameters with chmod(1), chown(1) and chgrp(1) on a mounted filesystem. @@ -141,9 +155,9 @@ will give you tmpfs instance on /mytmpfs which can allocate 10GB RAM/SWAP in 10240 inodes and it is only accessible by root. -Author: +:Author: Christoph Rohland <cr@sap.com>, 1.12.01 -Updated: +:Updated: Hugh Dickins, 4 June 2007 -Updated: +:Updated: KOSAKI Motohiro, 16 Mar 2010 diff --git a/Documentation/filesystems/ubifs-authentication.rst b/Documentation/filesystems/ubifs-authentication.rst index 6a9584f6ff46..16efd729bf7c 100644 --- a/Documentation/filesystems/ubifs-authentication.rst +++ b/Documentation/filesystems/ubifs-authentication.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: GPL-2.0 + :orphan: .. UBIFS Authentication @@ -92,11 +94,11 @@ UBIFS Index & Tree Node Cache ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Basic on-flash UBIFS entities are called *nodes*. UBIFS knows different types -of nodes. Eg. data nodes (`struct ubifs_data_node`) which store chunks of file -contents or inode nodes (`struct ubifs_ino_node`) which represent VFS inodes. -Almost all types of nodes share a common header (`ubifs_ch`) containing basic +of nodes. Eg. data nodes (``struct ubifs_data_node``) which store chunks of file +contents or inode nodes (``struct ubifs_ino_node``) which represent VFS inodes. +Almost all types of nodes share a common header (``ubifs_ch``) containing basic information like node type, node length, a sequence number, etc. (see -`fs/ubifs/ubifs-media.h`in kernel source). Exceptions are entries of the LPT +``fs/ubifs/ubifs-media.h`` in kernel source). Exceptions are entries of the LPT and some less important node types like padding nodes which are used to pad unusable content at the end of LEBs. diff --git a/Documentation/filesystems/ubifs.txt b/Documentation/filesystems/ubifs.rst index acc80442a3bb..e6ee99762534 100644 --- a/Documentation/filesystems/ubifs.txt +++ b/Documentation/filesystems/ubifs.rst @@ -1,5 +1,11 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=============== +UBI File System +=============== + Introduction -============= +============ UBIFS file-system stands for UBI File System. UBI stands for "Unsorted Block Images". UBIFS is a flash file system, which means it is designed @@ -79,6 +85,7 @@ Mount options (*) == default. +==================== ======================================================= bulk_read read more in one go to take advantage of flash media that read faster sequentially no_bulk_read (*) do not bulk-read @@ -98,6 +105,7 @@ auth_key= specify the key used for authenticating the filesystem. auth_hash_name= The hash algorithm used for authentication. Used for both hashing and for creating HMACs. Typical values include "sha256" or "sha512" +==================== ======================================================= Quick usage instructions @@ -107,12 +115,14 @@ The UBI volume to mount is specified using "ubiX_Y" or "ubiX:NAME" syntax, where "X" is UBI device number, "Y" is UBI volume number, and "NAME" is UBI volume name. -Mount volume 0 on UBI device 0 to /mnt/ubifs: -$ mount -t ubifs ubi0_0 /mnt/ubifs +Mount volume 0 on UBI device 0 to /mnt/ubifs:: + + $ mount -t ubifs ubi0_0 /mnt/ubifs Mount "rootfs" volume of UBI device 0 to /mnt/ubifs ("rootfs" is volume -name): -$ mount -t ubifs ubi0:rootfs /mnt/ubifs +name):: + + $ mount -t ubifs ubi0:rootfs /mnt/ubifs The following is an example of the kernel boot arguments to attach mtd0 to UBI and mount volume "rootfs": @@ -122,5 +132,6 @@ References ========== UBIFS documentation and FAQ/HOWTO at the MTD web site: -http://www.linux-mtd.infradead.org/doc/ubifs.html -http://www.linux-mtd.infradead.org/faq/ubifs.html + +- http://www.linux-mtd.infradead.org/doc/ubifs.html +- http://www.linux-mtd.infradead.org/faq/ubifs.html diff --git a/Documentation/filesystems/udf.txt b/Documentation/filesystems/udf.rst index e2f2faf32f18..d9badbf285b2 100644 --- a/Documentation/filesystems/udf.txt +++ b/Documentation/filesystems/udf.rst @@ -1,6 +1,8 @@ -* -* Documentation/filesystems/udf.txt -* +.. SPDX-License-Identifier: GPL-2.0 + +=============== +UDF file system +=============== If you encounter problems with reading UDF discs using this driver, please report them according to MAINTAINERS file. @@ -18,8 +20,10 @@ performance due to very poor read-modify-write support supplied internally by drive firmware. ------------------------------------------------------------------------------- + The following mount options are supported: + =========== ====================================== gid= Set the default group. umask= Set the default umask. mode= Set the default file permissions. @@ -34,6 +38,7 @@ The following mount options are supported: longad Use long ad's (default) nostrict Unset strict conformance iocharset= Set the NLS character set + =========== ====================================== The uid= and gid= options need a bit more explaining. They will accept a decimal numeric value and all inodes on that mount will then appear as @@ -47,13 +52,17 @@ the interactive user will always see the files on the disk as belonging to him. The remaining are for debugging and disaster recovery: - novrs Skip volume sequence recognition + ===== ================================ + novrs Skip volume sequence recognition + ===== ================================ The following expect a offset from 0. + ========== ================================================= session= Set the CDROM session (default= last session) anchor= Override standard anchor location. (default= 256) lastblock= Set the last block of the filesystem/ + ========== ================================================= ------------------------------------------------------------------------------- @@ -62,5 +71,5 @@ For the latest version and toolset see: https://github.com/pali/udftools Documentation on UDF and ECMA 167 is available FREE from: - http://www.osta.org/ - http://www.ecma-international.org/ + - http://www.osta.org/ + - http://www.ecma-international.org/ diff --git a/Documentation/filesystems/virtiofs.rst b/Documentation/filesystems/virtiofs.rst index 4f338e3cb3f7..e06e4951cb39 100644 --- a/Documentation/filesystems/virtiofs.rst +++ b/Documentation/filesystems/virtiofs.rst @@ -1,5 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 +.. _virtiofs_index: + =================================================== virtiofs: virtio-fs host<->guest shared file system =================================================== diff --git a/Documentation/filesystems/zonefs.txt b/Documentation/filesystems/zonefs.rst index 78813c34ec47..71d845c6a700 100644 --- a/Documentation/filesystems/zonefs.txt +++ b/Documentation/filesystems/zonefs.rst @@ -1,4 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================================ ZoneFS - Zone filesystem for Zoned block devices +================================================ Introduction ============ @@ -29,6 +33,7 @@ Zoned block devices Zoned storage devices belong to a class of storage devices with an address space that is divided into zones. A zone is a group of consecutive LBAs and all zones are contiguous (there are no LBA gaps). Zones may have different types. + * Conventional zones: there are no access constraints to LBAs belonging to conventional zones. Any read or write access can be executed, similarly to a regular block device. @@ -158,6 +163,7 @@ Format options -------------- Several optional features of zonefs can be enabled at format time. + * Conventional zone aggregation: ranges of contiguous conventional zones can be aggregated into a single larger file instead of the default one file per zone. * File ownership: The owner UID and GID of zone files is by default 0 (root) @@ -249,7 +255,7 @@ permissions. Further action taken by zonefs I/O error recovery can be controlled by the user with the "errors=xxx" mount option. The table below summarizes the result of zonefs I/O error processing depending on the mount option and on the zone -conditions. +conditions:: +--------------+-----------+-----------------------------------------+ | | | Post error state | @@ -275,6 +281,7 @@ conditions. +--------------+-----------+-----------------------------------------+ Further notes: + * The "errors=remount-ro" mount option is the default behavior of zonefs I/O error processing if no errors mount option is specified. * With the "errors=remount-ro" mount option, the change of the file access @@ -302,6 +309,7 @@ Mount options zonefs define the "errors=<behavior>" mount option to allow the user to specify zonefs behavior in response to I/O errors, inode size inconsistencies or zone condition changes. The defined behaviors are as follow: + * remount-ro (default) * zone-ro * zone-offline @@ -333,78 +341,78 @@ Examples -------- The following formats a 15TB host-managed SMR HDD with 256 MB zones -with the conventional zones aggregation feature enabled. +with the conventional zones aggregation feature enabled:: -# mkzonefs -o aggr_cnv /dev/sdX -# mount -t zonefs /dev/sdX /mnt -# ls -l /mnt/ -total 0 -dr-xr-xr-x 2 root root 1 Nov 25 13:23 cnv -dr-xr-xr-x 2 root root 55356 Nov 25 13:23 seq + # mkzonefs -o aggr_cnv /dev/sdX + # mount -t zonefs /dev/sdX /mnt + # ls -l /mnt/ + total 0 + dr-xr-xr-x 2 root root 1 Nov 25 13:23 cnv + dr-xr-xr-x 2 root root 55356 Nov 25 13:23 seq The size of the zone files sub-directories indicate the number of files existing for each type of zones. In this example, there is only one conventional zone file (all conventional zones are aggregated under a single -file). +file):: -# ls -l /mnt/cnv -total 137101312 --rw-r----- 1 root root 140391743488 Nov 25 13:23 0 + # ls -l /mnt/cnv + total 137101312 + -rw-r----- 1 root root 140391743488 Nov 25 13:23 0 -This aggregated conventional zone file can be used as a regular file. +This aggregated conventional zone file can be used as a regular file:: -# mkfs.ext4 /mnt/cnv/0 -# mount -o loop /mnt/cnv/0 /data + # mkfs.ext4 /mnt/cnv/0 + # mount -o loop /mnt/cnv/0 /data The "seq" sub-directory grouping files for sequential write zones has in this -example 55356 zones. +example 55356 zones:: -# ls -lv /mnt/seq -total 14511243264 --rw-r----- 1 root root 0 Nov 25 13:23 0 --rw-r----- 1 root root 0 Nov 25 13:23 1 --rw-r----- 1 root root 0 Nov 25 13:23 2 -... --rw-r----- 1 root root 0 Nov 25 13:23 55354 --rw-r----- 1 root root 0 Nov 25 13:23 55355 + # ls -lv /mnt/seq + total 14511243264 + -rw-r----- 1 root root 0 Nov 25 13:23 0 + -rw-r----- 1 root root 0 Nov 25 13:23 1 + -rw-r----- 1 root root 0 Nov 25 13:23 2 + ... + -rw-r----- 1 root root 0 Nov 25 13:23 55354 + -rw-r----- 1 root root 0 Nov 25 13:23 55355 For sequential write zone files, the file size changes as data is appended at -the end of the file, similarly to any regular file system. +the end of the file, similarly to any regular file system:: -# dd if=/dev/zero of=/mnt/seq/0 bs=4096 count=1 conv=notrunc oflag=direct -1+0 records in -1+0 records out -4096 bytes (4.1 kB, 4.0 KiB) copied, 0.00044121 s, 9.3 MB/s + # dd if=/dev/zero of=/mnt/seq/0 bs=4096 count=1 conv=notrunc oflag=direct + 1+0 records in + 1+0 records out + 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.00044121 s, 9.3 MB/s -# ls -l /mnt/seq/0 --rw-r----- 1 root root 4096 Nov 25 13:23 /mnt/seq/0 + # ls -l /mnt/seq/0 + -rw-r----- 1 root root 4096 Nov 25 13:23 /mnt/seq/0 The written file can be truncated to the zone size, preventing any further -write operation. +write operation:: -# truncate -s 268435456 /mnt/seq/0 -# ls -l /mnt/seq/0 --rw-r----- 1 root root 268435456 Nov 25 13:49 /mnt/seq/0 + # truncate -s 268435456 /mnt/seq/0 + # ls -l /mnt/seq/0 + -rw-r----- 1 root root 268435456 Nov 25 13:49 /mnt/seq/0 Truncation to 0 size allows freeing the file zone storage space and restart -append-writes to the file. +append-writes to the file:: -# truncate -s 0 /mnt/seq/0 -# ls -l /mnt/seq/0 --rw-r----- 1 root root 0 Nov 25 13:49 /mnt/seq/0 + # truncate -s 0 /mnt/seq/0 + # ls -l /mnt/seq/0 + -rw-r----- 1 root root 0 Nov 25 13:49 /mnt/seq/0 Since files are statically mapped to zones on the disk, the number of blocks of -a file as reported by stat() and fstat() indicates the size of the file zone. - -# stat /mnt/seq/0 - File: /mnt/seq/0 - Size: 0 Blocks: 524288 IO Block: 4096 regular empty file -Device: 870h/2160d Inode: 50431 Links: 1 -Access: (0640/-rw-r-----) Uid: ( 0/ root) Gid: ( 0/ root) -Access: 2019-11-25 13:23:57.048971997 +0900 -Modify: 2019-11-25 13:52:25.553805765 +0900 -Change: 2019-11-25 13:52:25.553805765 +0900 - Birth: - +a file as reported by stat() and fstat() indicates the size of the file zone:: + + # stat /mnt/seq/0 + File: /mnt/seq/0 + Size: 0 Blocks: 524288 IO Block: 4096 regular empty file + Device: 870h/2160d Inode: 50431 Links: 1 + Access: (0640/-rw-r-----) Uid: ( 0/ root) Gid: ( 0/ root) + Access: 2019-11-25 13:23:57.048971997 +0900 + Modify: 2019-11-25 13:52:25.553805765 +0900 + Change: 2019-11-25 13:52:25.553805765 +0900 + Birth: - The number of blocks of the file ("Blocks") in units of 512B blocks gives the maximum file size of 524288 * 512 B = 256 MB, corresponding to the device zone |