diff options
Diffstat (limited to 'Documentation/filesystems')
| -rw-r--r-- | Documentation/filesystems/Locking | 7 | ||||
| -rw-r--r-- | Documentation/filesystems/bfs.txt | 10 | ||||
| -rw-r--r-- | Documentation/filesystems/configfs/configfs.txt | 10 | ||||
| -rw-r--r-- | Documentation/filesystems/configfs/configfs_example.c | 14 | ||||
| -rw-r--r-- | Documentation/filesystems/nfs-rdma.txt | 103 | ||||
| -rw-r--r-- | Documentation/filesystems/omfs.txt | 106 | ||||
| -rw-r--r-- | Documentation/filesystems/proc.txt | 48 | ||||
| -rw-r--r-- | Documentation/filesystems/relay.txt | 10 | ||||
| -rw-r--r-- | Documentation/filesystems/sysfs.txt | 6 | ||||
| -rw-r--r-- | Documentation/filesystems/vfat.txt | 8 | ||||
| -rw-r--r-- | Documentation/filesystems/vfs.txt | 6 |
11 files changed, 260 insertions, 68 deletions
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 8b22d7d8b99..680fb566b92 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -510,6 +510,7 @@ prototypes: void (*close)(struct vm_area_struct*); int (*fault)(struct vm_area_struct*, struct vm_fault *); int (*page_mkwrite)(struct vm_area_struct *, struct page *); + int (*access)(struct vm_area_struct *, unsigned long, void*, int, int); locking rules: BKL mmap_sem PageLocked(page) @@ -517,6 +518,7 @@ open: no yes close: no yes fault: no yes page_mkwrite: no yes no +access: no yes ->page_mkwrite() is called when a previously read-only page is about to become writeable. The file system is responsible for @@ -525,6 +527,11 @@ taking to lock out truncate, the page range should be verified to be within i_size. The page mapping should also be checked that it is not NULL. + ->access() is called when get_user_pages() fails in +acces_process_vm(), typically used to debug a process through +/proc/pid/mem or ptrace. This function is needed only for +VM_IO | VM_PFNMAP VMAs. + ================================================================================ Dubious stuff diff --git a/Documentation/filesystems/bfs.txt b/Documentation/filesystems/bfs.txt index ea825e178e7..78043d5a8fc 100644 --- a/Documentation/filesystems/bfs.txt +++ b/Documentation/filesystems/bfs.txt @@ -26,11 +26,11 @@ You can simplify mounting by just typing: 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 your kernel is compiled with kmod -support (CONFIG_KMOD) enabled. Beware that umount will not -deallocate /dev/loopN device if /etc/mtab file on your system is a -symbolic link to /proc/mounts. You will need to do it manually using -"-d" switch of losetup(8). Read losetup(8) manpage for more info. +loaded automatically, make sure that you have compiled the module and +that modprobe is functioning. Beware that umount will not deallocate +/dev/loopN device if /etc/mtab file on your system is a symbolic link to +/proc/mounts. You will need to do it manually using "-d" switch of +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: diff --git a/Documentation/filesystems/configfs/configfs.txt b/Documentation/filesystems/configfs/configfs.txt index 15838d706ea..44c97e6accb 100644 --- a/Documentation/filesystems/configfs/configfs.txt +++ b/Documentation/filesystems/configfs/configfs.txt @@ -233,12 +233,10 @@ accomplished via the group operations specified on the group's config_item_type. struct configfs_group_operations { - int (*make_item)(struct config_group *group, - const char *name, - struct config_item **new_item); - int (*make_group)(struct config_group *group, - const char *name, - struct config_group **new_group); + struct config_item *(*make_item)(struct config_group *group, + const char *name); + struct config_group *(*make_group)(struct config_group *group, + const char *name); int (*commit_item)(struct config_item *item); void (*disconnect_notify)(struct config_group *group, struct config_item *item); diff --git a/Documentation/filesystems/configfs/configfs_example.c b/Documentation/filesystems/configfs/configfs_example.c index 0b422acd470..03964879170 100644 --- a/Documentation/filesystems/configfs/configfs_example.c +++ b/Documentation/filesystems/configfs/configfs_example.c @@ -273,13 +273,13 @@ static inline struct simple_children *to_simple_children(struct config_item *ite return item ? container_of(to_config_group(item), struct simple_children, group) : NULL; } -static int simple_children_make_item(struct config_group *group, const char *name, struct config_item **new_item) +static struct config_item *simple_children_make_item(struct config_group *group, const char *name) { struct simple_child *simple_child; simple_child = kzalloc(sizeof(struct simple_child), GFP_KERNEL); if (!simple_child) - return -ENOMEM; + return ERR_PTR(-ENOMEM); config_item_init_type_name(&simple_child->item, name, @@ -287,8 +287,7 @@ static int simple_children_make_item(struct config_group *group, const char *nam simple_child->storeme = 0; - *new_item = &simple_child->item; - return 0; + return &simple_child->item; } static struct configfs_attribute simple_children_attr_description = { @@ -360,21 +359,20 @@ static struct configfs_subsystem simple_children_subsys = { * children of its own. */ -static int group_children_make_group(struct config_group *group, const char *name, struct config_group **new_group) +static struct config_group *group_children_make_group(struct config_group *group, const char *name) { struct simple_children *simple_children; simple_children = kzalloc(sizeof(struct simple_children), GFP_KERNEL); if (!simple_children) - return -ENOMEM; + return ERR_PTR(-ENOMEM); config_group_init_type_name(&simple_children->group, name, &simple_children_type); - *new_group = &simple_children->group; - return 0; + return &simple_children->group; } static struct configfs_attribute group_children_attr_description = { diff --git a/Documentation/filesystems/nfs-rdma.txt b/Documentation/filesystems/nfs-rdma.txt index d0ec45ae4e7..44bd766f2e5 100644 --- a/Documentation/filesystems/nfs-rdma.txt +++ b/Documentation/filesystems/nfs-rdma.txt @@ -5,7 +5,7 @@ ################################################################################ Author: NetApp and Open Grid Computing - Date: April 15, 2008 + Date: May 29, 2008 Table of Contents ~~~~~~~~~~~~~~~~~ @@ -60,16 +60,18 @@ Installation The procedures described in this document have been tested with distributions from Red Hat's Fedora Project (http://fedora.redhat.com/). - - Install nfs-utils-1.1.1 or greater on the client + - Install nfs-utils-1.1.2 or greater on the client - An NFS/RDMA mount point can only be obtained by using the mount.nfs - command in nfs-utils-1.1.1 or greater. To see which version of mount.nfs - you are using, type: + An NFS/RDMA mount point can be obtained by using the mount.nfs command in + nfs-utils-1.1.2 or greater (nfs-utils-1.1.1 was the first nfs-utils + version with support for NFS/RDMA mounts, but for various reasons we + recommend using nfs-utils-1.1.2 or greater). To see which version of + mount.nfs you are using, type: - > /sbin/mount.nfs -V + $ /sbin/mount.nfs -V - If the version is less than 1.1.1 or the command does not exist, - then you will need to install the latest version of nfs-utils. + If the version is less than 1.1.2 or the command does not exist, + you should install the latest version of nfs-utils. Download the latest package from: @@ -77,22 +79,33 @@ Installation Uncompress the package and follow the installation instructions. - If you will not be using GSS and NFSv4, the installation process - can be simplified by disabling these features when running configure: + If you will not need the idmapper and gssd executables (you do not need + these to create an NFS/RDMA enabled mount command), the installation + process can be simplified by disabling these features when running + configure: - > ./configure --disable-gss --disable-nfsv4 + $ ./configure --disable-gss --disable-nfsv4 - For more information on this see the package's README and INSTALL files. + To build nfs-utils you will need the tcp_wrappers package installed. For + more information on this see the package's README and INSTALL files. After building the nfs-utils package, there will be a mount.nfs binary in the utils/mount directory. This binary can be used to initiate NFS v2, v3, - or v4 mounts. To initiate a v4 mount, the binary must be called mount.nfs4. - The standard technique is to create a symlink called mount.nfs4 to mount.nfs. + or v4 mounts. To initiate a v4 mount, the binary must be called + mount.nfs4. The standard technique is to create a symlink called + mount.nfs4 to mount.nfs. - NOTE: mount.nfs and therefore nfs-utils-1.1.1 or greater is only needed + This mount.nfs binary should be installed at /sbin/mount.nfs as follows: + + $ sudo cp utils/mount/mount.nfs /sbin/mount.nfs + + In this location, mount.nfs will be invoked automatically for NFS mounts + by the system mount commmand. + + NOTE: mount.nfs and therefore nfs-utils-1.1.2 or greater is only needed on the NFS client machine. You do not need this specific version of nfs-utils on the server. Furthermore, only the mount.nfs command from - nfs-utils-1.1.1 is needed on the client. + nfs-utils-1.1.2 is needed on the client. - Install a Linux kernel with NFS/RDMA @@ -156,8 +169,8 @@ Check RDMA and NFS Setup this time. For example, if you are using a Mellanox Tavor/Sinai/Arbel card: - > modprobe ib_mthca - > modprobe ib_ipoib + $ modprobe ib_mthca + $ modprobe ib_ipoib If you are using InfiniBand, make sure there is a Subnet Manager (SM) running on the network. If your IB switch has an embedded SM, you can @@ -166,7 +179,7 @@ Check RDMA and NFS Setup If an SM is running on your network, you should see the following: - > cat /sys/class/infiniband/driverX/ports/1/state + $ cat /sys/class/infiniband/driverX/ports/1/state 4: ACTIVE where driverX is mthca0, ipath5, ehca3, etc. @@ -174,10 +187,10 @@ Check RDMA and NFS Setup To further test the InfiniBand software stack, use IPoIB (this assumes you have two IB hosts named host1 and host2): - host1> ifconfig ib0 a.b.c.x - host2> ifconfig ib0 a.b.c.y - host1> ping a.b.c.y - host2> ping a.b.c.x + host1$ ifconfig ib0 a.b.c.x + host2$ ifconfig ib0 a.b.c.y + host1$ ping a.b.c.y + host2$ ping a.b.c.x For other device types, follow the appropriate procedures. @@ -202,11 +215,11 @@ NFS/RDMA Setup /vol0 192.168.0.47(fsid=0,rw,async,insecure,no_root_squash) /vol0 192.168.0.0/255.255.255.0(fsid=0,rw,async,insecure,no_root_squash) - The IP address(es) is(are) the client's IPoIB address for an InfiniBand HCA or the - cleint's iWARP address(es) for an RNIC. + The IP address(es) is(are) the client's IPoIB address for an InfiniBand + HCA or the cleint's iWARP address(es) for an RNIC. - NOTE: The "insecure" option must be used because the NFS/RDMA client does not - use a reserved port. + NOTE: The "insecure" option must be used because the NFS/RDMA client does + not use a reserved port. Each time a machine boots: @@ -214,43 +227,45 @@ NFS/RDMA Setup For InfiniBand using a Mellanox adapter: - > modprobe ib_mthca - > modprobe ib_ipoib - > ifconfig ib0 a.b.c.d + $ modprobe ib_mthca + $ modprobe ib_ipoib + $ ifconfig ib0 a.b.c.d NOTE: use unique addresses for the client and server - Start the NFS server - If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config), - load the RDMA transport module: + If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in + kernel config), load the RDMA transport module: - > modprobe svcrdma + $ modprobe svcrdma - Regardless of how the server was built (module or built-in), start the server: + Regardless of how the server was built (module or built-in), start the + server: - > /etc/init.d/nfs start + $ /etc/init.d/nfs start or - > service nfs start + $ service nfs start Instruct the server to listen on the RDMA transport: - > echo rdma 2050 > /proc/fs/nfsd/portlist + $ echo rdma 2050 > /proc/fs/nfsd/portlist - On the client system - If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config), - load the RDMA client module: + If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in + kernel config), load the RDMA client module: - > modprobe xprtrdma.ko + $ modprobe xprtrdma.ko - Regardless of how the client was built (module or built-in), issue the mount.nfs command: + Regardless of how the client was built (module or built-in), use this + command to mount the NFS/RDMA server: - > /path/to/your/mount.nfs <IPoIB-server-name-or-address>:/<export> /mnt -i -o rdma,port=2050 + $ mount -o rdma,port=2050 <IPoIB-server-name-or-address>:/<export> /mnt - To verify that the mount is using RDMA, run "cat /proc/mounts" and check the - "proto" field for the given mount. + To verify that the mount is using RDMA, run "cat /proc/mounts" and check + the "proto" field for the given mount. Congratulations! You're using NFS/RDMA! diff --git a/Documentation/filesystems/omfs.txt b/Documentation/filesystems/omfs.txt new file mode 100644 index 00000000000..1d0d41ff5c6 --- /dev/null +++ b/Documentation/filesystems/omfs.txt @@ -0,0 +1,106 @@ +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/proc.txt b/Documentation/filesystems/proc.txt index 7f268f327d7..64557821ee5 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -296,6 +296,7 @@ Table 1-4: Kernel info in /proc uptime System uptime 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 @@ -557,6 +558,49 @@ VmallocTotal: total size of vmalloc memory area VmallocUsed: amount of vmalloc area which is used VmallocChunk: largest contigious block of vmalloc area which is free +.............................................................................. + +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) + vmalloc vmalloc() area + vmap vmap()ed pages + user VM_USERMAP 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 1.3 IDE devices in /proc/ide ---------------------------- @@ -887,7 +931,7 @@ group_prealloc max_to_scan mb_groups mb_history min_to_scan order2_req stats stream_req mb_groups: -This file gives the details of mutiblock allocator buddy cache of free blocks +This file gives the details of multiblock allocator buddy cache of free blocks mb_history: Multiblock allocation history. @@ -1430,7 +1474,7 @@ used because pages_free(1355) is smaller than watermark + protection[2] normal page requirement. If requirement is DMA zone(index=0), protection[0] (=0) is used. -zone[i]'s protection[j] is calculated by following exprssion. +zone[i]'s protection[j] is calculated by following expression. (i < j): zone[i]->protection[j] diff --git a/Documentation/filesystems/relay.txt b/Documentation/filesystems/relay.txt index 094f2d2f38b..510b722667a 100644 --- a/Documentation/filesystems/relay.txt +++ b/Documentation/filesystems/relay.txt @@ -294,6 +294,16 @@ user-defined data with a channel, and is immediately available (including in create_buf_file()) via chan->private_data or buf->chan->private_data. +Buffer-only channels +-------------------- + +These channels have no files associated and can be created with +relay_open(NULL, NULL, ...). Such channels are useful in scenarios such +as when doing early tracing in the kernel, before the VFS is up. In these +cases, one may open a buffer-only channel and then call +relay_late_setup_files() when the kernel is ready to handle files, +to expose the buffered data to the userspace. + Channel 'modes' --------------- diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt index 7f27b8f840d..9e9c348275a 100644 --- a/Documentation/filesystems/sysfs.txt +++ b/Documentation/filesystems/sysfs.txt @@ -248,6 +248,7 @@ The top level sysfs directory looks like: block/ bus/ class/ +dev/ devices/ firmware/ net/ @@ -274,6 +275,11 @@ fs/ contains a directory for some filesystems. Currently each filesystem wanting to export attributes must create its own hierarchy below fs/ (see ./fuse.txt for an example). +dev/ contains two directories char/ and block/. Inside these two +directories there are symlinks named <major>:<minor>. These symlinks +point to the sysfs directory for the given device. /sys/dev provides a +quick way to lookup the sysfs interface for a device from the result of +a stat(2) operation. More information can driver-model specific features can be found in Documentation/driver-model/. diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt index 2d5e1e582e1..bbac4f1d905 100644 --- a/Documentation/filesystems/vfat.txt +++ b/Documentation/filesystems/vfat.txt @@ -96,6 +96,14 @@ shortname=lower|win95|winnt|mixed emulate the Windows 95 rule for create. Default setting is `lower'. +tz=UTC -- Interpret timestamps as UTC rather than local time. + This option disables the conversion of timestamps + between local time (as used by Windows on FAT) and UTC + (which Linux uses internally). This is particuluarly + useful when mounting devices (like digital cameras) + that are set to UTC in order to avoid the pitfalls of + local time. + <bool>: 0,1,yes,no,true,false TODO diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index b7522c6cbae..c4d348dabe9 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -143,7 +143,7 @@ struct file_system_type { The get_sb() method has the following arguments: - struct file_system_type *fs_type: decribes the filesystem, partly initialized + struct file_system_type *fs_type: describes the filesystem, partly initialized by the specific filesystem code int flags: mount flags @@ -895,9 +895,9 @@ struct dentry_operations { iput() yourself d_dname: called when the pathname of a dentry should be generated. - Usefull for some pseudo filesystems (sockfs, pipefs, ...) to delay + Useful for some pseudo filesystems (sockfs, pipefs, ...) to delay pathname generation. (Instead of doing it when dentry is created, - its done only when the path is needed.). Real filesystems probably + it's done only when the path is needed.). Real filesystems probably dont want to use it, because their dentries are present in global dcache hash, so their hash should be an invariant. As no lock is held, d_dname() should not try to modify the dentry itself, unless |