diff options
Diffstat (limited to 'Documentation/filesystems')
| -rw-r--r-- | Documentation/filesystems/Locking | 8 | ||||
| -rw-r--r-- | Documentation/filesystems/ceph.txt | 18 | ||||
| -rw-r--r-- | Documentation/filesystems/configfs/configfs.txt | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/debugfs.txt | 56 | ||||
| -rw-r--r-- | Documentation/filesystems/ext4.txt | 7 | ||||
| -rw-r--r-- | Documentation/filesystems/nfs/00-INDEX | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/nfs/fault_injection.txt | 69 | ||||
| -rw-r--r-- | Documentation/filesystems/proc.txt | 42 | ||||
| -rw-r--r-- | Documentation/filesystems/squashfs.txt | 6 | ||||
| -rw-r--r-- | Documentation/filesystems/sysfs.txt | 2 | ||||
| -rw-r--r-- | Documentation/filesystems/vfs.txt | 8 |
11 files changed, 189 insertions, 31 deletions
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index d819ba16a0c..4fca82e5276 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -37,15 +37,15 @@ d_manage: no no yes (ref-walk) maybe --------------------------- inode_operations --------------------------- prototypes: - int (*create) (struct inode *,struct dentry *,int, struct nameidata *); + int (*create) (struct inode *,struct dentry *,umode_t, struct nameidata *); struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameid ata *); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct inode *,struct dentry *,const char *); - int (*mkdir) (struct inode *,struct dentry *,int); + int (*mkdir) (struct inode *,struct dentry *,umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct inode *,struct dentry *,int,dev_t); + int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *); int (*readlink) (struct dentry *, char __user *,int); @@ -117,7 +117,7 @@ prototypes: int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*umount_begin) (struct super_block *); - int (*show_options)(struct seq_file *, struct vfsmount *); + int (*show_options)(struct seq_file *, struct dentry *); ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); diff --git a/Documentation/filesystems/ceph.txt b/Documentation/filesystems/ceph.txt index 763d8ebbbeb..d6030aa3337 100644 --- a/Documentation/filesystems/ceph.txt +++ b/Documentation/filesystems/ceph.txt @@ -119,12 +119,20 @@ Mount Options must rely on TCP's error correction to detect data corruption in the data payload. - noasyncreaddir - Disable client's use its local cache to satisfy readdir - requests. (This does not change correctness; the client uses - cached metadata only when a lease or capability ensures it is - valid.) + dcache + Use the dcache contents to perform negative lookups and + readdir when the client has the entire directory contents in + its cache. (This does not change correctness; the client uses + cached metadata only when a lease or capability ensures it is + valid.) + + nodcache + Do not use the dcache as above. This avoids a significant amount of + complex code, sacrificing performance without affecting correctness, + and is useful for tracking down bugs. + noasyncreaddir + Do not use the dcache as above for readdir. More Information ================ diff --git a/Documentation/filesystems/configfs/configfs.txt b/Documentation/filesystems/configfs/configfs.txt index dd57bb6bb39..b40fec9d3f5 100644 --- a/Documentation/filesystems/configfs/configfs.txt +++ b/Documentation/filesystems/configfs/configfs.txt @@ -192,7 +192,7 @@ attribute value uses the store_attribute() method. struct configfs_attribute { char *ca_name; struct module *ca_owner; - mode_t ca_mode; + umode_t ca_mode; }; When a config_item wants an attribute to appear as a file in the item's diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index 742cc06e138..6872c91bce3 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -35,7 +35,7 @@ described below will work. The most general way to create a file within a debugfs directory is with: - struct dentry *debugfs_create_file(const char *name, mode_t mode, + struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); @@ -53,13 +53,13 @@ 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: - struct dentry *debugfs_create_u8(const char *name, mode_t mode, + struct dentry *debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value); - struct dentry *debugfs_create_u16(const char *name, mode_t mode, + struct dentry *debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value); - struct dentry *debugfs_create_u32(const char *name, mode_t mode, + struct dentry *debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value); - struct dentry *debugfs_create_u64(const char *name, mode_t mode, + struct dentry *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 @@ -67,13 +67,13 @@ 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: - struct dentry *debugfs_create_x8(const char *name, mode_t mode, + struct dentry *debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value); - struct dentry *debugfs_create_x16(const char *name, mode_t mode, + struct dentry *debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value); - struct dentry *debugfs_create_x32(const char *name, mode_t mode, + struct dentry *debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, u32 *value); - struct dentry *debugfs_create_x64(const char *name, mode_t mode, + struct dentry *debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, u64 *value); These functions are useful as long as the developer knows the size of the @@ -81,7 +81,7 @@ value to be exported. Some types can have different widths on different architectures, though, complicating the situation somewhat. There is a function meant to help out in one special case: - struct dentry *debugfs_create_size_t(const char *name, mode_t mode, + struct dentry *debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value); @@ -90,21 +90,22 @@ a variable of type size_t. Boolean values can be placed in debugfs with: - struct dentry *debugfs_create_bool(const char *name, mode_t mode, + struct dentry *debugfs_create_bool(const char *name, umode_t mode, struct dentry *parent, u32 *value); 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. -Finally, a block of arbitrary binary data can be exported with: +Another option is exporting a block of arbitrary binary data, with +this structure and function: struct debugfs_blob_wrapper { void *data; unsigned long size; }; - struct dentry *debugfs_create_blob(const char *name, mode_t mode, + struct dentry *debugfs_create_blob(const char *name, umode_t mode, struct dentry *parent, struct debugfs_blob_wrapper *blob); @@ -115,6 +116,35 @@ can be used to export binary information, but there does not appear to be any code which does so in the mainline. Note that all files created with debugfs_create_blob() are read-only. +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. + + struct debugfs_reg32 { + char *name; + unsigned long offset; + }; + + struct debugfs_regset32 { + struct debugfs_reg32 *regs; + int nregs; + void __iomem *base; + }; + + struct dentry *debugfs_create_regset32(const char *name, mode_t mode, + struct dentry *parent, + struct debugfs_regset32 *regset); + + int debugfs_print_regs32(struct seq_file *s, struct debugfs_reg32 *regs, + int nregs, void __iomem *base, char *prefix); + +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. + + There are a couple of other directory-oriented helper functions: struct dentry *debugfs_rename(struct dentry *old_dir, diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt index 4917cf24a5e..10ec4639f15 100644 --- a/Documentation/filesystems/ext4.txt +++ b/Documentation/filesystems/ext4.txt @@ -581,6 +581,13 @@ Table of Ext4 specific ioctls behaviour may change in the future as it is not necessary and has been done this way only for sake of simplicity. + + EXT4_IOC_RESIZE_FS Resize the filesystem to a new size. The number + of blocks of resized filesystem is passed in via + 64 bit integer argument. The kernel allocates + bitmaps and inode table, the userspace tool thus + just passes the new number of blocks. + .............................................................................. References diff --git a/Documentation/filesystems/nfs/00-INDEX b/Documentation/filesystems/nfs/00-INDEX index a57e12411d2..1716874a651 100644 --- a/Documentation/filesystems/nfs/00-INDEX +++ b/Documentation/filesystems/nfs/00-INDEX @@ -2,6 +2,8 @@ - this file (nfs-related documentation). Exporting - explanation of how to make filesystems exportable. +fault_injection.txt + - information for using fault injection on the server knfsd-stats.txt - statistics which the NFS server makes available to user space. nfs.txt diff --git a/Documentation/filesystems/nfs/fault_injection.txt b/Documentation/filesystems/nfs/fault_injection.txt new file mode 100644 index 00000000000..426d166089a --- /dev/null +++ b/Documentation/filesystems/nfs/fault_injection.txt @@ -0,0 +1,69 @@ + +Fault Injection +=============== +Fault injection is a method for forcing errors that may not normally occur, or +may be difficult to reproduce. Forcing these errors in a controlled environment +can help the developer find and fix bugs before their code is shipped in a +production system. Injecting an error on the Linux NFS server will allow us to +observe how the client reacts and if it manages to recover its state correctly. + +NFSD_FAULT_INJECTION must be selected when configuring the kernel to use this +feature. + + +Using Fault Injection +===================== +On the client, mount the fault injection server through NFS v4.0+ and do some +work over NFS (open files, take locks, ...). + +On the server, mount the debugfs filesystem to <debug_dir> and ls +<debug_dir>/nfsd. This will show a list of files that will be used for +injecting faults on the NFS server. As root, write a number n to the file +corresponding to the action you want the server to take. The server will then +process the first n items it finds. So if you want to forget 5 locks, echo '5' +to <debug_dir>/nfsd/forget_locks. A value of 0 will tell the server to forget +all corresponding items. A log message will be created containing the number +of items forgotten (check dmesg). + +Go back to work on the client and check if the client recovered from the error +correctly. + + +Available Faults +================ +forget_clients: + The NFS server keeps a list of clients that have placed a mount call. If + this list is cleared, the server will have no knowledge of who the client + is, forcing the client to reauthenticate with the server. + +forget_openowners: + The NFS server keeps a list of what files are currently opened and who + they were opened by. Clearing this list will force the client to reopen + its files. + +forget_locks: + The NFS server keeps a list of what files are currently locked in the VFS. + Clearing this list will force the client to reclaim its locks (files are + unlocked through the VFS as they are cleared from this list). + +forget_delegations: + A delegation is used to assure the client that a file, or part of a file, + has not changed since the delegation was awarded. Clearing this list will + force the client to reaquire its delegation before accessing the file + again. + +recall_delegations: + Delegations can be recalled by the server when another client attempts to + access a file. This test will notify the client that its delegation has + been revoked, forcing the client to reaquire the delegation before using + the file again. + + +tools/nfs/inject_faults.sh script +================================= +This script has been created to ease the fault injection process. This script +will detect the mounted debugfs directory and write to the files located there +based on the arguments passed by the user. For example, running +`inject_faults.sh forget_locks 1` as root will instruct the server to forget +one lock. Running `inject_faults forget_locks` will instruct the server to +forgetall locks. diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 0ec91f03422..a76a26a1db8 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -41,6 +41,8 @@ Table of Contents 3.5 /proc/<pid>/mountinfo - Information about mounts 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm + 4 Configuring procfs + 4.1 Mount options ------------------------------------------------------------------------------ Preface @@ -305,6 +307,9 @@ Table 1-4: Contents of the stat files (as of 2.6.30-rc7) blkio_ticks time spent waiting for block IO gtime guest time of the task in jiffies cgtime guest time of the task children in jiffies + start_data address above which program data+bss is placed + end_data address below which program data+bss is placed + start_brk address above which program heap can be expanded with brk() .............................................................................. The /proc/PID/maps file containing the currently mapped memory regions and @@ -1542,3 +1547,40 @@ a task to set its own or one of its thread siblings comm value. The comm value is limited in size compared to the cmdline value, so writing anything longer then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated comm value. + + +------------------------------------------------------------------------------ +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). + +hidepid=1 means users may not access any /proc/<pid>/ directories but their +own. Sensitive files like cmdline, sched*, status are now protected against +other users. This makes it impossible to learn whether any user runs +specific program (given the program doesn't reveal itself by its behaviour). +As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users, +poorly written programs passing sensitive information via program arguments are +now protected against local eavesdroppers. + +hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other +users. It doesn't mean that it hides a fact whether a process with a specific +pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"), +but it hides process' uid and gid, which may be learned by stat()'ing +/proc/<pid>/ otherwise. It greatly complicates an intruder's task of gathering +information about running processes, whether some daemon runs with elevated +privileges, whether other user runs some sensitive program, whether other users +run any program at all, etc. + +gid= defines a group authorized to learn processes information otherwise +prohibited by hidepid=. If you use some daemon like identd which needs to learn +information about processes information, just add identd to this group. diff --git a/Documentation/filesystems/squashfs.txt b/Documentation/filesystems/squashfs.txt index 7db3ebda5a4..403c090aca3 100644 --- a/Documentation/filesystems/squashfs.txt +++ b/Documentation/filesystems/squashfs.txt @@ -93,8 +93,8 @@ byte alignment: Compressed data blocks are written to the filesystem as files are read from the source directory, and checked for duplicates. Once all file data has been -written the completed inode, directory, fragment, export and uid/gid lookup -tables are written. +written the completed inode, directory, fragment, export, uid/gid lookup and +xattr tables are written. 3.1 Compression options ----------------------- @@ -151,7 +151,7 @@ in each metadata block. Directories are sorted in alphabetical order, and at lookup the index is scanned linearly looking for the first filename alphabetically larger than the filename being looked up. At this point the location of the metadata block the filename is in has been found. -The general idea of the index is ensure only one metadata block needs to be +The general idea of the index is to ensure only one metadata block needs to be decompressed to do a lookup irrespective of the length of the directory. This scheme has the advantage that it doesn't require extra memory overhead and doesn't require much extra storage on disk. diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt index 07235caec22..a6619b7064b 100644 --- a/Documentation/filesystems/sysfs.txt +++ b/Documentation/filesystems/sysfs.txt @@ -70,7 +70,7 @@ An attribute definition is simply: struct attribute { char * name; struct module *owner; - mode_t mode; + umode_t mode; }; diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 43cbd082172..3d9393b845b 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -225,7 +225,7 @@ struct super_operations { void (*clear_inode) (struct inode *); void (*umount_begin) (struct super_block *); - int (*show_options)(struct seq_file *, struct vfsmount *); + int (*show_options)(struct seq_file *, struct dentry *); ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); @@ -341,14 +341,14 @@ This describes how the VFS can manipulate an inode in your filesystem. As of kernel 2.6.22, the following members are defined: struct inode_operations { - int (*create) (struct inode *,struct dentry *,int, struct nameidata *); + int (*create) (struct inode *,struct dentry *, umode_t, struct nameidata *); struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct inode *,struct dentry *,const char *); - int (*mkdir) (struct inode *,struct dentry *,int); + int (*mkdir) (struct inode *,struct dentry *,umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct inode *,struct dentry *,int,dev_t); + int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *); int (*readlink) (struct dentry *, char __user *,int); |