diff options
| -rw-r--r-- | Documentation/sharedsubtree.txt | 1060 | ||||
| -rw-r--r-- | arch/ia64/Kconfig | 1 | ||||
| -rw-r--r-- | fs/Makefile | 2 | ||||
| -rw-r--r-- | fs/dquot.c | 18 | ||||
| -rw-r--r-- | fs/namespace.c | 697 | ||||
| -rw-r--r-- | fs/pnode.c | 305 | ||||
| -rw-r--r-- | fs/pnode.h | 37 | ||||
| -rw-r--r-- | fs/proc/base.c | 62 | ||||
| -rw-r--r-- | fs/seq_file.c | 12 | ||||
| -rw-r--r-- | fs/super.c | 1 | ||||
| -rw-r--r-- | include/asm-ia64/page.h | 1 | ||||
| -rw-r--r-- | include/linux/acct.h | 3 | ||||
| -rw-r--r-- | include/linux/dcache.h | 1 | ||||
| -rw-r--r-- | include/linux/fs.h | 9 | ||||
| -rw-r--r-- | include/linux/mount.h | 29 | ||||
| -rw-r--r-- | include/linux/namespace.h | 3 | ||||
| -rw-r--r-- | include/linux/quota.h | 1 | ||||
| -rw-r--r-- | kernel/acct.c | 92 |
18 files changed, 2035 insertions, 299 deletions
diff --git a/Documentation/sharedsubtree.txt b/Documentation/sharedsubtree.txt new file mode 100644 index 00000000000..2d8f403eb6e --- /dev/null +++ b/Documentation/sharedsubtree.txt @@ -0,0 +1,1060 @@ +Shared Subtrees +--------------- + +Contents: + 1) Overview + 2) Features + 3) smount command + 4) Use-case + 5) Detailed semantics + 6) Quiz + 7) FAQ + 8) Implementation + + +1) Overview +----------- + +Consider the following situation: + +A process wants to clone its own namespace, but still wants to access the CD +that got mounted recently. Shared subtree semantics provide the necessary +mechanism to accomplish the above. + +It provides the necessary building blocks for features like per-user-namespace +and versioned filesystem. + +2) Features +----------- + +Shared subtree provides four different flavors of mounts; struct vfsmount to be +precise + + a. shared mount + b. slave mount + c. private mount + d. unbindable mount + + +2a) A shared mount can be replicated to as many mountpoints and all the +replicas continue to be exactly same. + + Here is an example: + + Lets say /mnt has a mount that is shared. + mount --make-shared /mnt + + note: mount command does not yet support the --make-shared flag. + I have included a small C program which does the same by executing + 'smount /mnt shared' + + #mount --bind /mnt /tmp + The above command replicates the mount at /mnt to the mountpoint /tmp + and the contents of both the mounts remain identical. + + #ls /mnt + a b c + + #ls /tmp + a b c + + Now lets say we mount a device at /tmp/a + #mount /dev/sd0 /tmp/a + + #ls /tmp/a + t1 t2 t2 + + #ls /mnt/a + t1 t2 t2 + + Note that the mount has propagated to the mount at /mnt as well. + + And the same is true even when /dev/sd0 is mounted on /mnt/a. The + contents will be visible under /tmp/a too. + + +2b) A slave mount is like a shared mount except that mount and umount events + only propagate towards it. + + All slave mounts have a master mount which is a shared. + + Here is an example: + + Lets say /mnt has a mount which is shared. + #mount --make-shared /mnt + + Lets bind mount /mnt to /tmp + #mount --bind /mnt /tmp + + the new mount at /tmp becomes a shared mount and it is a replica of + the mount at /mnt. + + Now lets make the mount at /tmp; a slave of /mnt + #mount --make-slave /tmp + [or smount /tmp slave] + + lets mount /dev/sd0 on /mnt/a + #mount /dev/sd0 /mnt/a + + #ls /mnt/a + t1 t2 t3 + + #ls /tmp/a + t1 t2 t3 + + Note the mount event has propagated to the mount at /tmp + + However lets see what happens if we mount something on the mount at /tmp + + #mount /dev/sd1 /tmp/b + + #ls /tmp/b + s1 s2 s3 + + #ls /mnt/b + + Note how the mount event has not propagated to the mount at + /mnt + + +2c) A private mount does not forward or receive propagation. + + This is the mount we are familiar with. Its the default type. + + +2d) A unbindable mount is a unbindable private mount + + lets say we have a mount at /mnt and we make is unbindable + + #mount --make-unbindable /mnt + [ smount /mnt unbindable ] + + Lets try to bind mount this mount somewhere else. + # mount --bind /mnt /tmp + mount: wrong fs type, bad option, bad superblock on /mnt, + or too many mounted file systems + + Binding a unbindable mount is a invalid operation. + + +3) smount command + + Currently the mount command is not aware of shared subtree features. + Work is in progress to add the support in mount ( util-linux package ). + Till then use the following program. + + ------------------------------------------------------------------------ + // + //this code was developed my Miklos Szeredi <miklos@szeredi.hu> + //and modified by Ram Pai <linuxram@us.ibm.com> + // sample usage: + // smount /tmp shared + // + #include <stdio.h> + #include <stdlib.h> + #include <unistd.h> + #include <sys/mount.h> + #include <sys/fsuid.h> + + #ifndef MS_REC + #define MS_REC 0x4000 /* 16384: Recursive loopback */ + #endif + + #ifndef MS_SHARED + #define MS_SHARED 1<<20 /* Shared */ + #endif + + #ifndef MS_PRIVATE + #define MS_PRIVATE 1<<18 /* Private */ + #endif + + #ifndef MS_SLAVE + #define MS_SLAVE 1<<19 /* Slave */ + #endif + + #ifndef MS_UNBINDABLE + #define MS_UNBINDABLE 1<<17 /* Unbindable */ + #endif + + int main(int argc, char *argv[]) + { + int type; + if(argc != 3) { + fprintf(stderr, "usage: %s dir " + "<rshared|rslave|rprivate|runbindable|shared|slave" + "|private|unbindable>\n" , argv[0]); + return 1; + } + + fprintf(stdout, "%s %s %s\n", argv[0], argv[1], argv[2]); + + if (strcmp(argv[2],"rshared")==0) + type=(MS_SHARED|MS_REC); + else if (strcmp(argv[2],"rslave")==0) + type=(MS_SLAVE|MS_REC); + else if (strcmp(argv[2],"rprivate")==0) + type=(MS_PRIVATE|MS_REC); + else if (strcmp(argv[2],"runbindable")==0) + type=(MS_UNBINDABLE|MS_REC); + else if (strcmp(argv[2],"shared")==0) + type=MS_SHARED; + else if (strcmp(argv[2],"slave")==0) + type=MS_SLAVE; + else if (strcmp(argv[2],"private")==0) + type=MS_PRIVATE; + else if (strcmp(argv[2],"unbindable")==0) + type=MS_UNBINDABLE; + else { + fprintf(stderr, "invalid operation: %s\n", argv[2]); + return 1; + } + setfsuid(getuid()); + + if(mount("", argv[1], "dontcare", type, "") == -1) { + perror("mount"); + return 1; + } + return 0; + } + ----------------------------------------------------------------------- + + Copy the above code snippet into smount.c + gcc -o smount smount.c + + + (i) To mark all the mounts under /mnt as shared execute the following + command: + + smount /mnt rshared + the corresponding syntax planned for mount command is + mount --make-rshared /mnt + + just to mark a mount /mnt as shared, execute the following + command: + smount /mnt shared + the corresponding syntax planned for mount command is + mount --make-shared /mnt + + (ii) To mark all the shared mounts under /mnt as slave execute the + following + + command: + smount /mnt rslave + the corresponding syntax planned for mount command is + mount --make-rslave /mnt + + just to mark a mount /mnt as slave, execute the following + command: + smount /mnt slave + the corresponding syntax planned for mount command is + mount --make-slave /mnt + + (iii) To mark all the mounts under /mnt as private execute the + following command: + + smount /mnt rprivate + the corresponding syntax planned for mount command is + mount --make-rprivate /mnt + + just to mark a mount /mnt as private, execute the following + command: + smount /mnt private + the corresponding syntax planned for mount command is + mount --make-private /mnt + + NOTE: by default all the mounts are created as private. But if + you want to change some shared/slave/unbindable mount as + private at a later point in time, this command can help. + + (iv) To mark all the mounts under /mnt as unbindable execute the + following + + command: + smount /mnt runbindable + the corresponding syntax planned for mount command is + mount --make-runbindable /mnt + + just to mark a mount /mnt as unbindable, execute the following + command: + smount /mnt unbindable + the corresponding syntax planned for mount command is + mount --make-unbindable /mnt + + +4) Use cases +------------ + + A) A process wants to clone its own namespace, but still wants to + access the CD that got mounted recently. + + Solution: + + The system administrator can make the mount at /cdrom shared + mount --bind /cdrom /cdrom + mount --make-shared /cdrom + + Now any process that clones off a new namespace will have a + mount at /cdrom which is a replica of the same mount in the + parent namespace. + + So when a CD is inserted and mounted at /cdrom that mount gets + propagated to the other mount at /cdrom in all the other clone + namespaces. + + B) A process wants its mounts invisible to any other process, but + still be able to see the other system mounts. + + Solution: + + To begin with, the administrator can mark the entire mount tree + as shareable. + + mount --make-rshared / + + A new process can clone off a new namespace. And mark some part + of its namespace as slave + + mount --make-rslave /myprivatetree + + Hence forth any mounts within the /myprivatetree done by the + process will not show up in any other namespace. However mounts + done in the parent namespace under /myprivatetree still shows + up in the process's namespace. + + + Apart from the above semantics this feature provides the + building blocks to solve the following problems: + + C) Per-user namespace + + The above semantics allows a way to share mounts across + namespaces. But namespaces are associated with processes. If + namespaces are made first class objects with user API to + associate/disassociate a namespace with userid, then each user + could have his/her own namespace and tailor it to his/her + requirements. Offcourse its needs support from PAM. + + D) Versioned files + + If the entire mount tree is visible at multiple locations, then + a underlying versioning file system can return different + version of the file depending on the path used to access that + file. + + An example is: + + mount --make-shared / + mount --rbind / /view/v1 + mount --rbind / /view/v2 + mount --rbind / /view/v3 + mount --rbind / /view/v4 + + and if /usr has a versioning filesystem mounted, than that + mount appears at /view/v1/usr, /view/v2/usr, /view/v3/usr and + /view/v4/usr too + + A user can request v3 version of the file /usr/fs/namespace.c + by accessing /view/v3/usr/fs/namespace.c . The underlying + versioning filesystem can then decipher that v3 version of the + filesystem is being requested and return the corresponding + inode. + +5) Detailed semantics: +------------------- + The section below explains the detailed semantics of + bind, rbind, move, mount, umount and clone-namespace operations. + + Note: the word 'vfsmount' and the noun 'mount' have been used + to mean the same thing, throughout this document. + +5a) Mount states + + A given mount can be in one of the following states + 1) shared + 2) slave + 3) shared and slave + 4) private + 5) unbindable + + A 'propagation event' is defined as event generated on a vfsmount + that leads to mount or unmount actions in other vfsmounts. + + A 'peer group' is defined as a group of vfsmounts that propagate + events to each other. + + (1) Shared mounts + + A 'shared mount' is defined as a vfsmount that belongs to a + 'peer group'. + + For example: + mount --make-shared /mnt + mount --bin /mnt /tmp + + The mount at /mnt and that at /tmp are both shared and belong + to the same peer group. Anything mounted or unmounted under + /mnt or /tmp reflect in all the other mounts of its peer + group. + + + (2) Slave mounts + + A 'slave mount' is defined as a vfsmount that receives + propagation events and does not forward propagation events. + + A slave mount as the name implies has a master mount from which + mount/unmount events are received. Events do not propagate from + the slave mount to the master. Only a shared mount can be made + a slave by executing the following command + + mount --make-slave mount + + A shared mount that is made as a slave is no more shared unless + modified to become shared. + + (3) Shared and Slave + + A vfsmount can be both shared as well as slave. This state + indicates that the mount is a slave of some vfsmount, and + has its own peer group too. This vfsmount receives propagation + events from its master vfsmount, and also forwards propagation + events to its 'peer group' and to its slave vfsmounts. + + Strictly speaking, the vfsmount is shared having its own + peer group, and this peer-group is a slave of some other + peer group. + + Only a slave vfsmount can be made as 'shared and slave' by + either executing the following command + mount --make-shared mount + or by moving the slave vfsmount under a shared vfsmount. + + (4) Private mount + + A 'private mount' is defined as vfsmount that does not + receive or forward any propagation events. + + (5) Unbindable mount + + A 'unbindable mount' is defined as vfsmount that does not + receive or forward any propagation events and cannot + be bind mounted. + + + State diagram: + The state diagram below explains the state transition of a mount, + in response to various commands. + ------------------------------------------------------------------------ + | |make-shared | make-slave | make-private |make-unbindab| + --------------|------------|--------------|--------------|-------------| + |shared |shared |*slave/private| private | unbindable | + | | | | | | + |-------------|------------|--------------|--------------|-------------| + |slave |shared | **slave | private | unbindable | + | |and slave | | | | + |-------------|------------|--------------|--------------|-------------| + |shared |shared | slave | private | unbindable | + |and slave |and slave | | | | + |-------------|------------|--------------|--------------|-------------| + |private |shared | **private | private | unbindable | + |-------------|------------|--------------|--------------|-------------| + |unbindable |shared |**unbindable | private | unbindable | + ------------------------------------------------------------------------ + + * if the shared mount is the only mount in its peer group, making it + slave, makes it private automatically. Note that there is no master to + which it can be slaved to. + + ** slaving a non-shared mount has no effect on the mount. + + Apart from the commands listed below, the 'move' operation also changes + the state of a mount depending on type of the destination mount. Its + explained in section 5d. + +5b) Bind semantics + + Consider the following command + + mount --bind A/a B/b + + where 'A' is the source mount, 'a' is the dentry in the mount 'A', 'B' + is the destination mount and 'b' is the dentry in the destination mount. + + The outcome depends on the type of mount of 'A' and 'B'. The table + below contains quick reference. + --------------------------------------------------------------------------- + | BIND MOUNT OPERATION | + |************************************************************************** + |source(A)->| shared | private | slave | unbindable | + | dest(B) | | | | | + | | | | | | | + | v | | | | | + |************************************************************************** + | shared | shared | shared | shared & slave | invalid | + | | | | | | + |non-shared| shared | private | slave | invalid | + *************************************************************************** + + Details: + + 1. 'A' is a shared mount and 'B' is a shared mount. A new mount 'C' + which is clone of 'A', is created. Its root dentry is 'a' . 'C' is + mounted on mount 'B' at dentry 'b'. Also new mount 'C1', 'C2', 'C3' ... + are created and mounted at the dentry 'b' on all mounts where 'B' + propagates to. A new propagation tree containing 'C1',..,'Cn' is + created. This propagation tree is identical to the propagation tree of + 'B'. And finally the peer-group of 'C' is merged with the peer group + of 'A'. + + 2. 'A' is a private mount and 'B' is a shared mount. A new mount 'C' + which is clone of 'A', is created. Its root dentry is 'a'. 'C' is + mounted on mount 'B' at dentry 'b'. Also new mount 'C1', 'C2', 'C3' ... + are created and mounted at the dentry 'b' on all mounts where 'B' + propagates to. A new propagation tree is set containing all new mounts + 'C', 'C1', .., 'Cn' with exactly the same configuration as the + propagation tree for 'B'. + + 3. 'A' is a slave mount of mount 'Z' and 'B' is a shared mount. A new + mount 'C' which is clone of 'A', is created. Its root dentry is 'a' . + 'C' is mounted on mount 'B' at dentry 'b'. Also new mounts 'C1', 'C2', + 'C3' ... are created and mounted at the dentry 'b' on all mounts where + 'B' propagates to. A new propagation tree containing the new mounts + 'C','C1',.. 'Cn' is created. This propagation tree is identical to the + propagation tree for 'B'. And finally the mount 'C' and its peer group + is made the slave of mount 'Z'. In other words, mount 'C' is in the + state 'slave and shared'. + + 4. 'A' is a unbindable mount and 'B' is a shared mount. This is a + invalid operation. + + 5. 'A' is a private mount and 'B' is a non-shared(private or slave or + unbindable) mount. A new mount 'C' which is clone of 'A', is created. + Its root dentry is 'a'. 'C' is mounted on mount 'B' at dentry 'b'. + + 6. 'A' is a shared mount and 'B' is a non-shared mount. A new mount 'C' + which is a clone of 'A' is created. Its root dentry is 'a'. 'C' is + mounted on mount 'B' at dentry 'b'. 'C' is made a member of the + peer-group of 'A'. + + 7. 'A' is a slave mount of mount 'Z' and 'B' is a non-shared mount. A + new mount 'C' which is a clone of 'A' is created. Its root dentry is + 'a'. 'C' is mounted on mount 'B' at dentry 'b'. Also 'C' is set as a + slave mount of 'Z'. In other words 'A' and 'C' are both slave mounts of + 'Z'. All mount/unmount events on 'Z' propagates to 'A' and 'C'. But + mount/unmount on 'A' do not propagate anywhere else. Similarly + mount/unmount on 'C' do not propagate anywhere else. + + 8. 'A' is a unbindable mount and 'B' is a non-shared mount. This is a + invalid operation. A unbindable mount cannot be bind mounted. + +5c) Rbind semantics + + rbind is same as bind. Bind replicates the specified mount. Rbind + replicates all the mounts in the tree belonging to the specified mount. + Rbind mount is bind mount applied to all the mounts in the tree. + + If the source tree that is rbind has some unbindable mounts, + then the subtree under the unbindable mount is pruned in the new + location. + + eg: lets say we have the following mount tree. + + A + / \ + B C + / \ / \ + D E F G + + Lets say all the mount except the mount C in the tree are + of a type other than unbindable. + + If this tree is rbound to say Z + + We will have the following tree at the new location. + + Z + | + A' + / + B' Note how the tree under C is pruned + / \ in the new location. + D' E' + + + +5d) Move semantics + + Consider the following command + + mount --move A B/b + + where 'A' is the source mount, 'B' is the destination mount and 'b' is + the dentry in the destination mount. + + The outcome depends on the type of the mount of 'A' and 'B'. The table + below is a quick reference. + --------------------------------------------------------------------------- + | MOVE MOUNT OPERATION | + |************************************************************************** + | source(A)->| shared | private | slave | unbindable | + | dest(B) | | | | | + | | | | | | | + | v | | | | | + |************************************************************************** + | shared | shared | shared |shared and slave| invalid | + | | | | | | + |non-shared| shared | private | slave | unbindable | + *************************************************************************** + NOTE: moving a mount residing under a shared mount is invalid. + + Details follow: + + 1. 'A' is a shared mount and 'B' is a shared mount. The mount 'A' is + mounted on mount 'B' at dentry 'b'. Also new mounts 'A1', 'A2'...'An' + are created and mounted at dentry 'b' on all mounts that receive + propagation from mount 'B'. A new propagation tree is created in the + exact same configuration as that of 'B'. This new propagation tree + contains all the new mounts 'A1', 'A2'... 'An'. And this new + propagation tree is appended to the already existing propagation tree + of 'A'. + + 2. 'A' is a private mount and 'B' is a shared mount. The mount 'A' is + mounted on mount 'B' at dentry 'b'. Also new mount 'A1', 'A2'... 'An' + are created and mounted at dentry 'b' on all mounts that receive + propagation from mount 'B'. The mount 'A' becomes a shared mount and a + propagation tree is created which is identical to that of + 'B'. This new propagation tree contains all the new mounts 'A1', + 'A2'... 'An'. + + 3. 'A' is a slave mount of mount 'Z' and 'B' is a shared mount. The + mount 'A' is mounted on mount 'B' at dentry 'b'. Also new mounts 'A1', + 'A2'... 'An' are created and mounted at dentry 'b' on all mounts that + receive propagation from mount 'B'. A new propagation tree is created + in the exact same configuration as that of 'B'. This new propagation + tree contains all the new mounts 'A1', 'A2'... 'An'. And this new + propagation tree is appended to the already existing propagation tree of + 'A'. Mount 'A' continues to be the slave mount of 'Z' but it also + becomes 'shared'. + + 4. 'A' is a unbindable mount and 'B' is a shared mount. The operation + is invalid. Because mounting anything on the shared mount 'B' can + create new mounts that get mounted on the mounts that receive + propagation from 'B'. And since the mount 'A' is unbindable, cloning + it to mount at other mountpoints is not possible. + + 5. 'A' is a private mount and 'B' is a non-shared(private or slave or + unbindable) mount. The mount 'A' is mounted on mount 'B' at dentry 'b'. + + 6. 'A' is a shared mount and 'B' is a non-shared mount. The mount 'A' + is mounted on mount 'B' at dentry 'b'. Mount 'A' continues to be a + shared mount. + + 7. 'A' is a slave mount of mount 'Z' and 'B' is a non-shared mount. + The mount 'A' is mounted on mount 'B' at dentry 'b'. Mount 'A' + continues to be a slave mount of mount 'Z'. + + 8. 'A' is a unbindable mount and 'B' is a non-shared mount. The mount + 'A' is mounted on mount 'B' at dentry 'b'. Mount 'A' continues to be a + unbindable mount. + +5e) Mount semantics + + Consider the following command + + mount device B/b + + 'B' is the destination mount and 'b' is the dentry in the destination + mount. + + The above operation is the same as bind operation with the exception + that the source mount is always a private mount. + + +5f) Unmount semantics + + Consider the following command + + umount A + + where 'A' is a mount mounted on mount 'B' at dentry 'b'. + + If mount 'B' is shared, then all most-recently-mounted mounts at dentry + 'b' on mounts that receive propagation from mount 'B' and does not have + sub-mounts within them are unmounted. + + Example: Lets say 'B1', 'B2', 'B3' are shared mounts that propagate to + each other. + + lets say 'A1', 'A2', 'A3' are first mounted at dentry 'b' on mount + 'B1', 'B2' and 'B3' respectively. + + lets say 'C1', 'C2', 'C3' are next mounted at the same dentry 'b' on + mount 'B1', 'B2' and 'B3' respectively. + + if 'C1' is unmounted, all the mounts that are most-recently-mounted on + 'B1' and on the mounts that 'B1' propagates-to are unmounted. + + 'B1' propagates to 'B2' and 'B3'. And the most recently mounted mount + on 'B2' at dentry 'b' is 'C2', and that of mount 'B3' is 'C3'. + + So all 'C1', 'C2' and 'C3' should be unmounted. + + If any of 'C2' or 'C3' has some child mounts, then that mount is not + unmounted, but all other mounts are unmounted. However if 'C1' is told + to be unmounted and 'C1' has some sub-mounts, the umount operation is + failed entirely. + +5g) Clone Namespace + + A cloned namespace contains all the mounts as that of the parent + namespace. + + Lets say 'A' and 'B' are the corresponding mounts in the parent and the + child namespace. + + If 'A' is shared, then 'B' is also shared and 'A' and 'B' propagate to + each other. + + If 'A' is a slave mount of 'Z', then 'B' is also the slave mount of + 'Z'. + + If 'A' is a private mount, then 'B' is a private mount too. + + If 'A' is unbindable mount, then 'B' is a unbindable mount too. + + +6) Quiz + + A. What is the result of the following command sequence? + + mount --bind /mnt /mnt + mount --make-shared /mnt + mount --bind /mnt /tmp + mount --move /tmp /mnt/1 + + what should be the contents of /mnt /mnt/1 /mnt/1/1 should be? + Should they all be identical? or should /mnt and /mnt/1 be + identical only? + + + B. What is the result of the following command sequence? + + mount --make-rshared / + mkdir -p /v/1 + mount --rbind / /v/1 + + what should be the content of /v/1/v/1 be? + + + C. What is the result of the following command sequence? + + mount --bind /mnt /mnt + mount --make-shared /mnt + mkdir -p /mnt/1/2/3 /mnt/1/test + mount --bind /mnt/1 /tmp + mount --make-slave /mnt + mount --make-shared /mnt + mount --bind /mnt/1/2 /tmp1 + mount --make-slave /mnt + + At this point we have the first mount at /tmp and + its root dentry is 1. Lets call this mount 'A' + And then we have a second mount at /tmp1 with root + dentry 2. Lets call this mount 'B' + Next we have a third mount at /mnt with root dentry + mnt. Lets call this mount 'C' + + 'B' is the slave of 'A' and 'C' is a slave of 'B' + A -> B -> C + + at this point if we execute the following command + + mount --bind /bin /tmp/test + + The mount is attempted on 'A' + + will the mount propagate to 'B' and 'C' ? + + what would be the contents of + /mnt/1/test be? + +7) FAQ + + Q1. Why is bind mount needed? How is it different from symbolic links? + symbolic links can get stale if the destination mount gets + unmounted or moved. Bind mounts continue to exist even if the + other mount is unmounted or moved. + + Q2. Why can't the shared subtree be implemented using exportfs? + + exportfs is a heavyweight way of accomplishing part of what + shared subtree can do. I cannot imagine a way to implement the + semantics of slave mount using exportfs? + + Q3 Why is unbindable mount needed? + + Lets say we want to replicate the mount tree at multiple + locations within the same subtree. + + if one rbind mounts a tree within the same subtree 'n' times + the number of mounts created is an exponential function of 'n'. + Having unbindable mount can help prune the unneeded bind + mounts. Here is a example. + + step 1: + lets say the root tree has just two directories with + one vfsmount. + root + / \ + tmp usr + + And we want to replicate the tree at multiple + mountpoints under /root/tmp + + step2: + mount --make-shared /root + + mkdir -p /tmp/m1 + + mount --rbind /root /tmp/m1 + + the new tree now looks like this: + + root + / \ + tmp usr + / + m1 + / \ + tmp usr + / + m1 + + it has two vfsmounts + + step3: + mkdir -p /tmp/m2 + mount --rbind /root /tmp/m2 + + the new tree now looks like this: + + root + / \ + tmp usr + / \ + m1 m2 + / \ / \ + tmp usr tmp usr + / \ / + m1 m2 m1 + / \ / \ + tmp usr tmp usr + / / \ + m1 m1 m2 + / \ + tmp usr + / \ + m1 m2 + + it has 6 vfsmounts + + step 4: + mkdir -p /tmp/m3 + mount --rbind /root /tmp/m3 + + I wont' draw the tree..but it has 24 vfsmounts + + + at step i the number of vfsmounts is V[i] = i*V[i-1]. + This is an exponential function. And this tree has way more + mounts than what we really needed in the first place. + + One could use a series of umount at each step to prune + out the unneeded mounts. But there is a better solution. + Unclonable mounts come in handy here. + + step 1: + lets say the root tree has just two directories with + one vfsmount. + root + / \ + tmp usr + + How do we set up the same tree at multiple locations under + /root/tmp + + step2: + mount --bind /root/tmp /root/tmp + + mount --make-rshared /root + mount --make-unbindable /root/tmp + + mkdir -p /tmp/m1 + + mount --rbind /root /tmp/m1 + + the new tree now looks like this: + + root + / \ + tmp usr + / + m1 + / \ + tmp usr + + step3: + mkdir -p /tmp/m2 + mount --rbind /root /tmp/m2 + + the new tree now looks like this: + + root + / \ + tmp usr + / \ + m1 m2 + / \ / \ + tmp usr tmp usr + + step4: + + mkdir -p /tmp/m3 + mount --rbind /root /tmp/m3 + + the new tree now looks like this: + + root + / \ + tmp usr + / \ \ + m1 m2 m3 + / \ / \ / \ + tmp usr tmp usr tmp usr + +8) Implementation + +8A) Datastructure + + 4 new fields are introduced to struct vfsmount + ->mnt_share + ->mnt_slave_list + ->mnt_slave + ->mnt_master + + ->mnt_share links togather all the mount to/from which this vfsmount + send/receives propagation events. + + ->mnt_slave_list links all the mounts to which this vfsmount propagates + to. + + ->mnt_slave links togather all the slaves that its master vfsmount + propagates to. + + ->mnt_master points to the master vfsmount from which this vfsmount + receives propagation. + + ->mnt_flags takes two more flags to indicate the propagation status of + the vfsmount. MNT_SHARE indicates that the vfsmount is a shared + vfsmount. MNT_UNCLONABLE indicates that the vfsmount cannot be + replicated. + + All the shared vfsmounts in a peer group form a cyclic list through + ->mnt_share. + + All vfsmounts with the same ->mnt_master form on a cyclic list anchored + in ->mnt_master->mnt_slave_list and going through ->mnt_slave. + + ->mnt_master can point to arbitrary (and possibly different) members + of master peer group. To find all immediate slaves of a peer group + you need to go through _all_ ->mnt_slave_list of its members. + Conceptually it's just a single set - distribution among the + individual lists does not affect propagation or the way propagation + tree is modified by operations. + + A example propagation tree looks as shown in the figure below. + [ NOTE: Though it looks like a forest, if we consider all the shared + mounts as a conceptual entity called 'pnode', it becomes a tree] + + + A <--> B <--> C <---> D + /|\ /| |\ + / F G J K H I + / + E<-->K + /|\ + M L N + + In the above figure A,B,C and D all are shared and propagate to each + other. 'A' has got 3 slave mounts 'E' 'F' and 'G' 'C' has got 2 slave + mounts 'J' and 'K' and 'D' has got two slave mounts 'H' and 'I'. + 'E' is also shared with 'K' and they propagate to each other. And + 'K' has 3 slaves 'M', 'L' and 'N' + + A's ->mnt_share links with the ->mnt_share of 'B' 'C' and 'D' + + A's ->mnt_slave_list links with ->mnt_slave of 'E', 'K', 'F' and 'G' + + E's ->mnt_share links with ->mnt_share of K + 'E', 'K', 'F', 'G' have their ->mnt_master point to struct + vfsmount of 'A' + 'M', 'L', 'N' have their ->mnt_master point to struct vfsmount of 'K' + K's ->mnt_slave_list links with ->mnt_slave of 'M', 'L' and 'N' + + C's ->mnt_slave_list links with ->mnt_slave of 'J' and 'K' + J and K's ->mnt_master points to struct vfsmount of C + and finally D's ->mnt_slave_list links with ->mnt_slave of 'H' and 'I' + 'H' and 'I' have their ->mnt_master pointing to struct vfsmount of 'D'. + + + NOTE: The propagation tree is orthogonal to the mount tree. + + +8B Algorithm: + + The crux of the implementation resides in rbind/move operation. + + The overall algorithm breaks the operation into 3 phases: (look at + attach_recursive_mnt() and propagate_mnt()) + + 1. prepare phase. + 2. commit phases. + 3. abort phases. + + Prepare phase: + + for each mount in the source tree: + a) Create the necessary number of mount trees to + be attached to each of the mounts that receive + propagation from the destination mount. + b) Do not attach any of the trees to its destination. + However note down its ->mnt_parent and ->mnt_mountpoint + c) Link all the new mounts to form a propagation tree that + is identical to the propagation tree of the destination + mount. + + If this phase is successful, there should be 'n' new + propagation trees; where 'n' is the number of mounts in the + source tree. Go to the commit phase + + Also there should be 'm' new mount trees, where 'm' is + the number of mounts to which the destination mount + propagates to. + + if any memory allocations fail, go to the abort phase. + + Commit phase + attach each of the mount trees to their corresponding + destination mounts. + + Abort phase + delete all the newly created trees. + + NOTE: all the propagation related functionality resides in the file + pnode.c + + +------------------------------------------------------------------------ + +version 0.1 (created the initial document, Ram Pai linuxram@us.ibm.com) +version 0.2 (Incorporated comments from Al Viro) diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 9f2093c1f44..d4de8a4814b 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -191,6 +191,7 @@ config IOSAPIC config IA64_SGI_SN_XP tristate "Support communication between SGI SSIs" + depends on IA64_GENERIC || IA64_SGI_SN2 select IA64_UNCACHED_ALLOCATOR help An SGI machine can be divided into multiple Single System diff --git a/fs/Makefile b/fs/Makefile index 1972da18627..4c265575907 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -10,7 +10,7 @@ obj-y := open.o read_write.o file_table.o buffer.o bio.o super.o \ ioctl.o readdir.o select.o fifo.o locks.o dcache.o inode.o \ attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \ seq_file.o xattr.o libfs.o fs-writeback.o mpage.o direct-io.o \ - ioprio.o + ioprio.o pnode.o obj-$(CONFIG_INOTIFY) += inotify.o obj-$(CONFIG_EPOLL) += eventpoll.o diff --git a/fs/dquot.c b/fs/dquot.c index afa06a89346..05b60283c9c 100644 --- a/fs/dquot.c +++ b/fs/dquot.c @@ -1321,13 +1321,11 @@ int vfs_quota_off(struct super_block *sb, int type) int cnt; struct quota_info *dqopt = sb_dqopt(sb); struct inode *toputinode[MAXQUOTAS]; - struct vfsmount *toputmnt[MAXQUOTAS]; /* We need to serialize quota_off() for device */ down(&dqopt->dqonoff_sem); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { toputinode[cnt] = NULL; - toputmnt[cnt] = NULL; if (type != -1 && cnt != type) continue; if (!sb_has_quota_enabled(sb, cnt)) @@ -1348,9 +1346,7 @@ int vfs_quota_off(struct super_block *sb, int type) put_quota_format(dqopt->info[cnt].dqi_format); toputinode[cnt] = dqopt->files[cnt]; - toputmnt[cnt] = dqopt->mnt[cnt]; dqopt->files[cnt] = NULL; - dqopt->mnt[cnt] = NULL; dqopt->info[cnt].dqi_flags = 0; dqopt->info[cnt].dqi_igrace = 0; dqopt->info[cnt].dqi_bgrace = 0; @@ -1358,10 +1354,7 @@ int vfs_quota_off(struct super_block *sb, int type) } up(&dqopt->dqonoff_sem); /* Sync the superblock so that buffers with quota data are written to - * disk (and so userspace sees correct data afterwards). - * The reference to vfsmnt we are still holding protects us from - * umount (we don't have it only when quotas are turned on/off for - * journal replay but in that case we are guarded by the fs anyway). */ + * disk (and so userspace sees correct data afterwards). */ if (sb->s_op->sync_fs) sb->s_op->sync_fs(sb, 1); sync_blockdev(sb->s_bdev); @@ -1385,10 +1378,6 @@ int vfs_quota_off(struct super_block *sb, int type) iput(toputinode[cnt]); } up(&dqopt->dqonoff_sem); - /* We don't hold the reference when we turned on quotas - * just for the journal replay... */ - if (toputmnt[cnt]) - mntput(toputmnt[cnt]); } if (sb->s_bdev) invalidate_bdev(sb->s_bdev, 0); @@ -1503,11 +1492,8 @@ int vfs_quota_on(struct super_block *sb, int type, int format_id, char *path) /* Quota file not on the same filesystem? */ if (nd.mnt->mnt_sb != sb) error = -EXDEV; - else { + else error = vfs_quota_on_inode(nd.dentry->d_inode, type, format_id); - if (!error) - sb_dqopt(sb)->mnt[type] = mntget(nd.mnt); - } out_path: path_release(&nd); return error; diff --git a/fs/namespace.c b/fs/namespace.c index 2fa9fdf7d6f..caa9187f67e 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -24,6 +24,7 @@ #include <linux/mount.h> #include <asm/uaccess.h> #include <asm/unistd.h> +#include "pnode.h" extern int __init init_rootfs(void); @@ -37,33 +38,39 @@ static inline int sysfs_init(void) #endif /* spinlock for vfsmount related operations, inplace of dcache_lock */ - __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock); +__cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock); + +static int event; static struct list_head *mount_hashtable; static int hash_mask __read_mostly, hash_bits __read_mostly; -static kmem_cache_t *mnt_cache; +static kmem_cache_t *mnt_cache; +static struct rw_semaphore namespace_sem; static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry) { - unsigned long tmp = ((unsigned long) mnt / L1_CACHE_BYTES); - tmp += ((unsigned long) dentry / L1_CACHE_BYTES); + unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); + tmp += ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> hash_bits); return tmp & hash_mask; } struct vfsmount *alloc_vfsmnt(const char *name) { - struct vfsmount *mnt = kmem_cache_alloc(mnt_cache, GFP_KERNEL); + struct vfsmount *mnt = kmem_cache_alloc(mnt_cache, GFP_KERNEL); if (mnt) { memset(mnt, 0, sizeof(struct vfsmount)); - atomic_set(&mnt->mnt_count,1); + atomic_set(&mnt->mnt_count, 1); INIT_LIST_HEAD(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); INIT_LIST_HEAD(&mnt->mnt_expire); + INIT_LIST_HEAD(&mnt->mnt_share); + INIT_LIST_HEAD(&mnt->mnt_slave_list); + INIT_LIST_HEAD(&mnt->mnt_slave); if (name) { - int size = strlen(name)+1; + int size = strlen(name) + 1; char *newname = kmalloc(size, GFP_KERNEL); if (newname) { memcpy(newname, name, size); @@ -81,36 +88,65 @@ void free_vfsmnt(struct vfsmount *mnt) } /* - * Now, lookup_mnt increments the ref count before returning - * the vfsmount struct. + * find the first or last mount at @dentry on vfsmount @mnt depending on + * @dir. If @dir is set return the first mount else return the last mount. */ -struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) +struct vfsmount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry, + int dir) { - struct list_head * head = mount_hashtable + hash(mnt, dentry); - struct list_head * tmp = head; + struct list_head *head = mount_hashtable + hash(mnt, dentry); + struct list_head *tmp = head; struct vfsmount *p, *found = NULL; - spin_lock(&vfsmount_lock); for (;;) { - tmp = tmp->next; + tmp = dir ? tmp->next : tmp->prev; p = NULL; if (tmp == head) break; p = list_entry(tmp, struct vfsmount, mnt_hash); if (p->mnt_parent == mnt && p->mnt_mountpoint == dentry) { - found = mntget(p); + found = p; break; } } - spin_unlock(&vfsmount_lock); return found; } +/* + * lookup_mnt increments the ref count before returning + * the vfsmount struct. + */ +struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) +{ + struct vfsmount *child_mnt; + spin_lock(&vfsmount_lock); + if ((child_mnt = __lookup_mnt(mnt, dentry, 1))) + mntget(child_mnt); + spin_unlock(&vfsmount_lock); + return child_mnt; +} + static inline int check_mnt(struct vfsmount *mnt) { return mnt->mnt_namespace == current->namespace; } +static void touch_namespace(struct namespace *ns) +{ + if (ns) { + ns->event = ++event; + wake_up_interruptible(&ns->poll); + } +} + +static void __touch_namespace(struct namespace *ns) +{ + if (ns && ns->event != event) { + ns->event = event; + wake_up_interruptible(&ns->poll); + } +} + static void detach_mnt(struct vfsmount *mnt, struct nameidata *old_nd) { old_nd->dentry = mnt->mnt_mountpoint; @@ -122,13 +158,43 @@ static void detach_mnt(struct vfsmount *mnt, struct nameidata *old_nd) old_nd->dentry->d_mounted--; } +void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry, + struct vfsmount *child_mnt) +{ + child_mnt->mnt_parent = mntget(mnt); + child_mnt->mnt_mountpoint = dget(dentry); + dentry->d_mounted++; +} + static void attach_mnt(struct vfsmount *mnt, struct nameidata *nd) { - mnt->mnt_parent = mntget(nd->mnt); - mnt->mnt_mountpoint = dget(nd->dentry); - list_add(&mnt->mnt_hash, mount_hashtable+hash(nd->mnt, nd->dentry)); + mnt_set_mountpoint(nd->mnt, nd->dentry, mnt); + list_add_tail(&mnt->mnt_hash, mount_hashtable + + hash(nd->mnt, nd->dentry)); list_add_tail(&mnt->mnt_child, &nd->mnt->mnt_mounts); - nd->dentry->d_mounted++; +} + +/* + * the caller must hold vfsmount_lock + */ +static void commit_tree(struct vfsmount *mnt) +{ + struct vfsmount *parent = mnt->mnt_parent; + struct vfsmount *m; + LIST_HEAD(head); + struct namespace *n = parent->mnt_namespace; + + BUG_ON(parent == mnt); + + list_add_tail(&head, &mnt->mnt_list); + list_for_each_entry(m, &head, mnt_list) + m->mnt_namespace = n; + list_splice(&head, n->list.prev); + + list_add_tail(&mnt->mnt_hash, mount_hashtable + + hash(parent, mnt->mnt_mountpoint)); + list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); + touch_namespace(n); } static struct vfsmount *next_mnt(struct vfsmount *p, struct vfsmount *root) @@ -147,8 +213,18 @@ static struct vfsmount *next_mnt(struct vfsmount *p, struct vfsmount *root) return list_entry(next, struct vfsmount, mnt_child); } -static struct vfsmount * -clone_mnt(struct vfsmount *old, struct dentry *root) +static struct vfsmount *skip_mnt_tree(struct vfsmount *p) +{ + struct list_head *prev = p->mnt_mounts.prev; + while (prev != &p->mnt_mounts) { + p = list_entry(prev, struct vfsmount, mnt_child); + prev = p->mnt_mounts.prev; + } + return p; +} + +static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root, + int flag) { struct super_block *sb = old->mnt_sb; struct vfsmount *mnt = alloc_vfsmnt(old->mnt_devname); @@ -160,19 +236,34 @@ clone_mnt(struct vfsmount *old, struct dentry *root) mnt->mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt_root; mnt->mnt_parent = mnt; - mnt->mnt_namespace = current->namespace; + + if (flag & CL_SLAVE) { + list_add(&mnt->mnt_slave, &old->mnt_slave_list); + mnt->mnt_master = old; + CLEAR_MNT_SHARED(mnt); + } else { + if ((flag & CL_PROPAGATION) || IS_MNT_SHARED(old)) + list_add(&mnt->mnt_share, &old->mnt_share); + if (IS_MNT_SLAVE(old)) + list_add(&mnt->mnt_slave, &old->mnt_slave); + mnt->mnt_master = old->mnt_master; + } + if (flag & CL_MAKE_SHARED) + set_mnt_shared(mnt); /* stick the duplicate mount on the same expiry list * as the original if that was on one */ - spin_lock(&vfsmount_lock); - if (!list_empty(&old->mnt_expire)) - list_add(&mnt->mnt_expire, &old->mnt_expire); - spin_unlock(&vfsmount_lock); + if (flag & CL_EXPIRE) { + spin_lock(&vfsmount_lock); + if (!list_empty(&old->mnt_expire)) + list_add(&mnt->mnt_expire, &old->mnt_expire); + spin_unlock(&vfsmount_lock); + } } return mnt; } -void __mntput(struct vfsmount *mnt) +static inline void __mntput(struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; dput(mnt->mnt_root); @@ -180,7 +271,46 @@ void __mntput(struct vfsmount *mnt) deactivate_super(sb); } -EXPORT_SYMBOL(__mntput); +void mntput_no_expire(struct vfsmount *mnt) +{ +repeat: + if (atomic_dec_and_lock(&mnt->mnt_count, &vfsmount_lock)) { + if (likely(!mnt->mnt_pinned)) { + spin_unlock(&vfsmount_lock); + __mntput(mnt); + return; + } + atomic_add(mnt->mnt_pinned + 1, &mnt->mnt_count); + mnt->mnt_pinned = 0; + spin_unlock(&vfsmount_lock); + acct_auto_close_mnt(mnt); + security_sb_umount_close(mnt); + goto repeat; + } +} + +EXPORT_SYMBOL(mntput_no_expire); + +void mnt_pin(struct vfsmount *mnt) +{ + spin_lock(&vfsmount_lock); + mnt->mnt_pinned++; + spin_unlock(&vfsmount_lock); +} + +EXPORT_SYMBOL(mnt_pin); + +void mnt_unpin(struct vfsmount *mnt) +{ + spin_lock(&vfsmount_lock); + if (mnt->mnt_pinned) { + atomic_inc(&mnt->mnt_count); + mnt->mnt_pinned--; + } + spin_unlock(&vfsmount_lock); +} + +EXPORT_SYMBOL(mnt_unpin); /* iterator */ static void *m_start(struct seq_file *m, loff_t *pos) @@ -189,7 +319,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) struct list_head *p; loff_t l = *pos; - down_read(&n->sem); + down_read(&namespace_sem); list_for_each(p, &n->list) if (!l--) return list_entry(p, struct vfsmount, mnt_list); @@ -201,13 +331,12 @@ static void *m_next(struct seq_file *m, void *v, loff_t *pos) struct namespace *n = m->private; struct list_head *p = ((struct vfsmount *)v)->mnt_list.next; (*pos)++; - return p==&n->list ? NULL : list_entry(p, struct vfsmount, mnt_list); + return p == &n->list ? NULL : list_entry(p, struct vfsmount, mnt_list); } static void m_stop(struct seq_file *m, void *v) { - struct namespace *n = m->private; - up_read(&n->sem); + up_read(&namespace_sem); } static inline void mangle(struct seq_file *m, const char *s) @@ -275,35 +404,14 @@ struct seq_operations mounts_op = { */ int may_umount_tree(struct vfsmount *mnt) { - struct list_head *next; - struct vfsmount *this_parent = mnt; - int actual_refs; - int minimum_refs; + int actual_refs = 0; + int minimum_refs = 0; + struct vfsmount *p; spin_lock(&vfsmount_lock); - actual_refs = atomic_read(&mnt->mnt_count); - minimum_refs = 2; -repeat: - next = this_parent->mnt_mounts.next; -resume: - while (next != &this_parent->mnt_mounts) { - struct vfsmount *p = list_entry(next, struct vfsmount, mnt_child); - - next = next->next; - + for (p = mnt; p; p = next_mnt(p, mnt)) { actual_refs += atomic_read(&p->mnt_count); minimum_refs += 2; - - if (!list_empty(&p->mnt_mounts)) { - this_parent = p; - goto repeat; - } - } - - if (this_parent != mnt) { - next = this_parent->mnt_child.next; - this_parent = this_parent->mnt_parent; - goto resume; } spin_unlock(&vfsmount_lock); @@ -330,45 +438,67 @@ EXPORT_SYMBOL(may_umount_tree); */ int may_umount(struct vfsmount *mnt) { - if (atomic_read(&mnt->mnt_count) > 2) - return -EBUSY; - return 0; + int ret = 0; + spin_lock(&vfsmount_lock); + if (propagate_mount_busy(mnt, 2)) + ret = -EBUSY; + spin_unlock(&vfsmount_lock); + return ret; } EXPORT_SYMBOL(may_umount); -static void umount_tree(struct vfsmount *mnt) +void release_mounts(struct list_head *head) +{ + struct vfsmount *mnt; + while(!list_empty(head)) { + mnt = list_entry(head->next, struct vfsmount, mnt_hash); + list_del_init(&mnt->mnt_hash); + if (mnt->mnt_parent != mnt) { + struct dentry *dentry; + struct vfsmount *m; + spin_lock(&vfsmount_lock); + dentry = mnt->mnt_mountpoint; + m = mnt->mnt_parent; + mnt->mnt_mountpoint = mnt->mnt_root; + mnt->mnt_parent = mnt; + spin_unlock(&vfsmount_lock); + dput(dentry); + mntput(m); + } + mntput(mnt); + } +} + +void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill) { struct vfsmount *p; - LIST_HEAD(kill); for (p = mnt; p; p = next_mnt(p, mnt)) { - list_del(&p->mnt_list); - list_add(&p->mnt_list, &kill); - p->mnt_namespace = NULL; + list_del(&p->mnt_hash); + list_add(&p->mnt_hash, kill); } - while (!list_empty(&kill)) { - mnt = list_entry(kill.next, struct vfsmount, mnt_list); - list_del_init(&mnt->mnt_list); - list_del_init(&mnt->mnt_expire); - if (mnt->mnt_parent == mnt) { - spin_unlock(&vfsmount_lock); - } else { - struct nameidata old_nd; - detach_mnt(mnt, &old_nd); - spin_unlock(&vfsmount_lock); - path_release(&old_nd); - } - mntput(mnt); - spin_lock(&vfsmount_lock); + if (propagate) + propagate_umount(kill); + + list_for_each_entry(p, kill, mnt_hash) { + list_del_init(&p->mnt_expire); + list_del_init(&p->mnt_list); + __touch_namespace(p->mnt_namespace); + p->mnt_namespace = NULL; + list_del_init(&p->mnt_child); + if (p->mnt_parent != p) + mnt->mnt_mountpoint->d_mounted--; + change_mnt_propagation(p, MS_PRIVATE); } } static int do_umount(struct vfsmount *mnt, int flags) { - struct super_block * sb = mnt->mnt_sb; + struct super_block *sb = mnt->mnt_sb; int retval; + LIST_HEAD(umount_list); retval = security_sb_umount(mnt, flags); if (retval) @@ -403,7 +533,7 @@ static int do_umount(struct vfsmount *mnt, int flags) */ lock_kernel(); - if( (flags&MNT_FORCE) && sb->s_op->umount_begin) + if ((flags & MNT_FORCE) && sb->s_op->umount_begin) sb->s_op->umount_begin(sb); unlock_kernel(); @@ -432,29 +562,21 @@ static int do_umount(struct vfsmount *mnt, int flags) return retval; } - down_write(¤t->namespace->sem); + down_write(&namespace_sem); spin_lock(&vfsmount_lock); + event++; - if (atomic_read(&sb->s_active) == 1) { - /* last instance - try to be smart */ - spin_unlock(&vfsmount_lock); - lock_kernel(); - DQUOT_OFF(sb); - acct_auto_close(sb); - unlock_kernel(); - security_sb_umount_close(mnt); - spin_lock(&vfsmount_lock); - } retval = -EBUSY; - if (atomic_read(&mnt->mnt_count) == 2 || flags & MNT_DETACH) { + if (flags & MNT_DETACH || !propagate_mount_busy(mnt, 2)) { if (!list_empty(&mnt->mnt_list)) - umount_tree(mnt); + umount_tree(mnt, 1, &umount_list); retval = 0; } spin_unlock(&vfsmount_lock); if (retval) security_sb_umount_busy(mnt); - up_write(¤t->namespace->sem); + up_write(&namespace_sem); + release_mounts(&umount_list); return retval; } @@ -494,12 +616,11 @@ out: #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* - * The 2.0 compatible umount. No flags. + * The 2.0 compatible umount. No flags. */ - asmlinkage long sys_oldumount(char __user * name) { - return sys_umount(name,0); + return sys_umount(name, 0); } #endif @@ -522,8 +643,7 @@ static int mount_is_safe(struct nameidata *nd) #endif } -static int -lives_below_in_same_fs(struct dentry *d, struct dentry *dentry) +static int lives_below_in_same_fs(struct dentry *d, struct dentry *dentry) { while (1) { if (d == dentry) @@ -534,12 +654,16 @@ lives_below_in_same_fs(struct dentry *d, struct dentry *dentry) } } -static struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry) +struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry, + int flag) { struct vfsmount *res, *p, *q, *r, *s; struct nameidata nd; - res = q = clone_mnt(mnt, dentry); + if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(mnt)) + return NULL; + + res = q = clone_mnt(mnt, dentry, flag); if (!q) goto Enomem; q->mnt_mountpoint = mnt->mnt_mountpoint; @@ -550,6 +674,10 @@ static struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry) continue; for (s = r; s; s = next_mnt(s, r)) { + if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(s)) { + s = skip_mnt_tree(s); + continue; + } while (p != s->mnt_parent) { p = p->mnt_parent; q = q->mnt_parent; @@ -557,7 +685,7 @@ static struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry) p = s; nd.mnt = q; nd.dentry = p->mnt_mountpoint; - q = clone_mnt(p, p->mnt_root); + q = clone_mnt(p, p->mnt_root, flag); if (!q) goto Enomem; spin_lock(&vfsmount_lock); @@ -567,15 +695,114 @@ static struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry) } } return res; - Enomem: +Enomem: if (res) { + LIST_HEAD(umount_list); spin_lock(&vfsmount_lock); - umount_tree(res); + umount_tree(res, 0, &umount_list); spin_unlock(&vfsmount_lock); + release_mounts(&umount_list); } return NULL; } +/* + * @source_mnt : mount tree to be attached + * @nd : place the mount tree @source_mnt is attached + * @parent_nd : if non-null, detach the source_mnt from its parent and + * store the parent mount and mountpoint dentry. + * (done when source_mnt is moved) + * + * NOTE: in the table below explains the semantics when a source mount + * of a given type is attached to a destination mount of a given type. + * --------------------------------------------------------------------------- + * | BIND MOUNT OPERATION | + * |************************************************************************** + * | source-->| shared | private | slave | unbindable | + * | dest | | | | | + * | | | | | | | + * | v | | | | | + * |************************************************************************** + * | shared | shared (++) | shared (+) | shared(+++)| invalid | + * | | | | | | + * |non-shared| shared (+) | private | slave (*) | invalid | + * *************************************************************************** + * A bind operation clones the source mount and mounts the clone on the + * destination mount. + * + * (++) the cloned mount is propagated to all the mounts in the propagation + * tree of the destination mount and the cloned mount is added to + * the peer group of the source mount. + * (+) the cloned mount is created under the destination mount and is marked + * as shared. The cloned mount is added to the peer group of the source + * mount. + * (+++) the mount is propagated to all the mounts in the propagation tree + * of the destination mount and the cloned mount is made slave + * of the same master as that of the source mount. The cloned mount + * is marked as 'shared and slave'. + * (*) the cloned mount is made a slave of the same master as that of the + * source mount. + * + * --------------------------------------------------------------------------- + * | MOVE MOUNT OPERATION | + * |************************************************************************** + * | source-->| shared | private | slave | unbindable | + * | dest | | | | | + * | | | | | | | + * | v | | | | | + * |************************************************************************** + * | shared | shared (+) | shared (+) | shared(+++) | invalid | + * | | | | | | + * |non-shared| shared (+*) | private | slave (*) | unbindable | + * *************************************************************************** + * + * (+) the mount is moved to the destination. And is then propagated to + * all the mounts in the propagation tree of the destination mount. + * (+*) the mount is moved to the destination. + * (+++) the mount is moved to the destination and is then propagated to + * all the mounts belonging to the destination mount's propagation tree. + * the mount is marked as 'shared and slave'. + * (*) the mount continues to be a slave at the new location. + * + * if the source mount is a tree, the operations explained above is + * applied to each mount in the tree. + * Must be called without spinlocks held, since this function can sleep + * in allocations. + */ +static int attach_recursive_mnt(struct vfsmount *source_mnt, + struct nameidata *nd, struct nameidata *parent_nd) +{ + LIST_HEAD(tree_list); + struct vfsmount *dest_mnt = nd->mnt; + struct dentry *dest_dentry = nd->dentry; + struct vfsmount *child, *p; + + if (propagate_mnt(dest_mnt, dest_dentry, source_mnt, &tree_list)) + return -EINVAL; + + if (IS_MNT_SHARED(dest_mnt)) { + for (p = source_mnt; p; p = next_mnt(p, source_mnt)) + set_mnt_shared(p); + } + + spin_lock(&vfsmount_lock); + if (parent_nd) { + detach_mnt(source_mnt, parent_nd); + attach_mnt(source_mnt, nd); + touch_namespace(current->namespace); + } else { + mnt_set_mountpoint(dest_mnt, dest_dentry, source_mnt); + commit_tree(source_mnt); + } + + list_for_each_entry_safe(child, p, &tree_list, mnt_hash) { + list_del_init(&child->mnt_hash); + commit_tree(child); + } + spin_unlock(&vfsmount_lock); + return 0; +} + static int graft_tree(struct vfsmount *mnt, struct nameidata *nd) { int err; @@ -596,17 +823,8 @@ static int graft_tree(struct vfsmount *mnt, struct nameidata *nd) goto out_unlock; err = -ENOENT; - spin_lock(&vfsmount_lock); - if (IS_ROOT(nd->dentry) || !d_unhashed(nd->dentry)) { - struct list_head head; - - attach_mnt(mnt, nd); - list_add_tail(&head, &mnt->mnt_list); - list_splice(&head, current->namespace->list.prev); - mntget(mnt); - err = 0; - } - spin_unlock(&vfsmount_lock); + if (IS_ROOT(nd->dentry) || !d_unhashed(nd->dentry)) + err = attach_recursive_mnt(mnt, nd, NULL); out_unlock: up(&nd->dentry->d_inode->i_sem); if (!err) @@ -615,6 +833,27 @@ out_unlock: } /* + * recursively change the type of the mountpoint. + */ +static int do_change_type(struct nameidata *nd, int flag) +{ + struct vfsmount *m, *mnt = nd->mnt; + int recurse = flag & MS_REC; + int type = flag & ~MS_REC; + + if (nd->dentry != nd->mnt->mnt_root) + return -EINVAL; + + down_write(&namespace_sem); + spin_lock(&vfsmount_lock); + for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL)) + change_mnt_propagation(m, type); + spin_unlock(&vfsmount_lock); + up_write(&namespace_sem); + return 0; +} + +/* * do loopback mount. */ static int do_loopback(struct nameidata *nd, char *old_name, int recurse) @@ -630,32 +869,34 @@ static int do_loopback(struct nameidata *nd, char *old_name, int recurse) if (err) return err; - down_write(¤t->namespace->sem); + down_write(&namespace_sem); err = -EINVAL; - if (check_mnt(nd->mnt) && (!recurse || check_mnt(old_nd.mnt))) { - err = -ENOMEM; - if (recurse) - mnt = copy_tree(old_nd.mnt, old_nd.dentry); - else - mnt = clone_mnt(old_nd.mnt, old_nd.dentry); - } + if (IS_MNT_UNBINDABLE(old_nd.mnt)) + goto out; - if (mnt) { - /* stop bind mounts from expiring */ + if (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt)) + goto out; + + err = -ENOMEM; + if (recurse) + mnt = copy_tree(old_nd.mnt, old_nd.dentry, 0); + else + mnt = clone_mnt(old_nd.mnt, old_nd.dentry, 0); + + if (!mnt) + goto out; + + err = graft_tree(mnt, nd); + if (err) { + LIST_HEAD(umount_list); spin_lock(&vfsmount_lock); - list_del_init(&mnt->mnt_expire); + umount_tree(mnt, 0, &umount_list); spin_unlock(&vfsmount_lock); - - err = graft_tree(mnt, nd); - if (err) { - spin_lock(&vfsmount_lock); - umount_tree(mnt); - spin_unlock(&vfsmount_lock); - } else - mntput(mnt); + release_mounts(&umount_list); } - up_write(¤t->namespace->sem); +out: + up_write(&namespace_sem); path_release(&old_nd); return err; } @@ -665,12 +906,11 @@ static int do_loopback(struct nameidata *nd, char *old_name, int recurse) * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. */ - static int do_remount(struct nameidata *nd, int flags, int mnt_flags, void *data) { int err; - struct super_block * sb = nd->mnt->mnt_sb; + struct super_block *sb = nd->mnt->mnt_sb; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -684,13 +924,23 @@ static int do_remount(struct nameidata *nd, int flags, int mnt_flags, down_write(&sb->s_umount); err = do_remount_sb(sb, flags, data, 0); if (!err) - nd->mnt->mnt_flags=mnt_flags; + nd->mnt->mnt_flags = mnt_flags; up_write(&sb->s_umount); if (!err) security_sb_post_remount(nd->mnt, flags, data); return err; } +static inline int tree_contains_unbindable(struct vfsmount *mnt) +{ + struct vfsmount *p; + for (p = mnt; p; p = next_mnt(p, mnt)) { + if (IS_MNT_UNBINDABLE(p)) + return 1; + } + return 0; +} + static int do_move_mount(struct nameidata *nd, char *old_name) { struct nameidata old_nd, parent_nd; @@ -704,8 +954,8 @@ static int do_move_mount(struct nameidata *nd, char *old_name) if (err) return err; - down_write(¤t->namespace->sem); - while(d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry)) + down_write(&namespace_sem); + while (d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry)) ; err = -EINVAL; if (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt)) @@ -716,39 +966,47 @@ static int do_move_mount(struct nameidata *nd, char *old_name) if (IS_DEADDIR(nd->dentry->d_inode)) goto out1; - spin_lock(&vfsmount_lock); if (!IS_ROOT(nd->dentry) && d_unhashed(nd->dentry)) - goto out2; + goto out1; err = -EINVAL; if (old_nd.dentry != old_nd.mnt->mnt_root) - goto out2; + goto out1; if (old_nd.mnt == old_nd.mnt->mnt_parent) - goto out2; + goto out1; if (S_ISDIR(nd->dentry->d_inode->i_mode) != S_ISDIR(old_nd.dentry->d_inode->i_mode)) - goto out2; - + goto out1; + /* + * Don't move a mount residing in a shared parent. + */ + if (old_nd.mnt->mnt_parent && IS_MNT_SHARED(old_nd.mnt->mnt_parent)) + goto out1; + /* + * Don't move a mount tree containing unbindable mounts to a destination + * mount which is shared. + */ + if (IS_MNT_SHARED(nd->mnt) && tree_contains_unbindable(old_nd.mnt)) + goto out1; err = -ELOOP; - for (p = nd->mnt; p->mnt_parent!=p; p = p->mnt_parent) + for (p = nd->mnt; p->mnt_parent != p; p = p->mnt_parent) if (p == old_nd.mnt) - goto out2; - err = 0; + goto out1; - detach_mnt(old_nd.mnt, &parent_nd); - attach_mnt(old_nd.mnt, nd); + if ((err = attach_recursive_mnt(old_nd.mnt, nd, &parent_nd))) + goto out1; + spin_lock(&vfsmount_lock); /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old_nd.mnt->mnt_expire); -out2: spin_unlock(&vfsmount_lock); out1: up(&nd->dentry->d_inode->i_sem); out: - up_write(¤t->namespace->sem); + up_write(&namespace_sem); if (!err) path_release(&parent_nd); path_release(&old_nd); @@ -787,9 +1045,9 @@ int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd, { int err; - down_write(¤t->namespace->sem); + down_write(&namespace_sem); /* Something was mounted here while we slept */ - while(d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry)) + while (d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry)) ; err = -EINVAL; if (!check_mnt(nd->mnt)) @@ -806,25 +1064,28 @@ int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd, goto unlock; newmnt->mnt_flags = mnt_flags; - newmnt->mnt_namespace = current->namespace; - err = graft_tree(newmnt, nd); + if ((err = graft_tree(newmnt, nd))) + goto unlock; - if (err == 0 && fslist) { + if (fslist) { /* add to the specified expiration list */ spin_lock(&vfsmount_lock); list_add_tail(&newmnt->mnt_expire, fslist); spin_unlock(&vfsmount_lock); } + up_write(&namespace_sem); + return 0; unlock: - up_write(¤t->namespace->sem); + up_write(&namespace_sem); mntput(newmnt); return err; } EXPORT_SYMBOL_GPL(do_add_mount); -static void expire_mount(struct vfsmount *mnt, struct list_head *mounts) +static void expire_mount(struct vfsmount *mnt, struct list_head *mounts, + struct list_head *umounts) { spin_lock(&vfsmount_lock); @@ -841,27 +1102,13 @@ static void expire_mount(struct vfsmount *mnt, struct list_head *mounts) * Check that it is still dead: the count should now be 2 - as * contributed by the vfsmount parent and the mntget above */ - if (atomic_read(&mnt->mnt_count) == 2) { - struct nameidata old_nd; - + if (!propagate_mount_busy(mnt, 2)) { /* delete from the namespace */ + touch_namespace(mnt->mnt_namespace); list_del_init(&mnt->mnt_list); mnt->mnt_namespace = NULL; - detach_mnt(mnt, &old_nd); + umount_tree(mnt, 1, umounts); spin_unlock(&vfsmount_lock); - path_release(&old_nd); - - /* - * Now lay it to rest if this was the last ref on the superblock - */ - if (atomic_read(&mnt->mnt_sb->s_active) == 1) { - /* last instance - try to be smart */ - lock_kernel(); - DQUOT_OFF(mnt->mnt_sb); - acct_auto_close(mnt->mnt_sb); - unlock_kernel(); - } - mntput(mnt); } else { /* * Someone brought it back to life whilst we didn't have any @@ -910,6 +1157,7 @@ void mark_mounts_for_expiry(struct list_head *mounts) * - dispose of the corpse */ while (!list_empty(&graveyard)) { + LIST_HEAD(umounts); mnt = list_entry(graveyard.next, struct vfsmount, mnt_expire); list_del_init(&mnt->mnt_expire); @@ -921,13 +1169,12 @@ void mark_mounts_for_expiry(struct list_head *mounts) get_namespace(namespace); spin_unlock(&vfsmount_lock); - down_write(&namespace->sem); - expire_mount(mnt, mounts); - up_write(&namespace->sem); - + down_write(&namespace_sem); + expire_mount(mnt, mounts, &umounts); + up_write(&namespace_sem); + release_mounts(&umounts); mntput(mnt); put_namespace(namespace); - spin_lock(&vfsmount_lock); } @@ -942,8 +1189,8 @@ EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); * Note that this function differs from copy_from_user() in that it will oops * on bad values of `to', rather than returning a short copy. */ -static long -exact_copy_from_user(void *to, const void __user *from, unsigned long n) +static long exact_copy_from_user(void *to, const void __user * from, + unsigned long n) { char *t = to; const char __user *f = from; @@ -964,12 +1211,12 @@ exact_copy_from_user(void *to, const void __user *from, unsigned long n) return n; } -int copy_mount_options(const void __user *data, unsigned long *where) +int copy_mount_options(const void __user * data, unsigned long *where) { int i; unsigned long page; unsigned long size; - + *where = 0; if (!data) return 0; @@ -988,7 +1235,7 @@ int copy_mount_options(const void __user *data, unsigned long *where) i = size - exact_copy_from_user((void *)page, data, size); if (!i) { - free_page(page); + free_page(page); return -EFAULT; } if (i != PAGE_SIZE) @@ -1011,7 +1258,7 @@ int copy_mount_options(const void __user *data, unsigned long *where) * Therefore, if this magic number is present, it carries no information * and must be discarded. */ -long do_mount(char * dev_name, char * dir_name, char *type_page, +long do_mount(char *dev_name, char *dir_name, char *type_page, unsigned long flags, void *data_page) { struct nameidata nd; @@ -1039,7 +1286,7 @@ long do_mount(char * dev_name, char * dir_name, char *type_page, mnt_flags |= MNT_NODEV; if (flags & MS_NOEXEC) mnt_flags |= MNT_NOEXEC; - flags &= ~(MS_NOSUID|MS_NOEXEC|MS_NODEV|MS_ACTIVE); + flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE); /* ... and get the mountpoint */ retval = path_lookup(dir_name, LOOKUP_FOLLOW, &nd); @@ -1055,6 +1302,8 @@ long do_mount(char * dev_name, char * dir_name, char *type_page, data_page); else if (flags & MS_BIND) retval = do_loopback(&nd, dev_name, flags & MS_REC); + else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) + retval = do_change_type(&nd, flags); else if (flags & MS_MOVE) retval = do_move_mount(&nd, dev_name); else @@ -1091,14 +1340,16 @@ int copy_namespace(int flags, struct task_struct *tsk) goto out; atomic_set(&new_ns->count, 1); - init_rwsem(&new_ns->sem); INIT_LIST_HEAD(&new_ns->list); + init_waitqueue_head(&new_ns->poll); + new_ns->event = 0; - down_write(&tsk->namespace->sem); + down_write(&namespace_sem); /* First pass: copy the tree topology */ - new_ns->root = copy_tree(namespace->root, namespace->root->mnt_root); + new_ns->root = copy_tree(namespace->root, namespace->root->mnt_root, + CL_COPY_ALL | CL_EXPIRE); if (!new_ns->root) { - up_write(&tsk->namespace->sem); + up_write(&namespace_sem); kfree(new_ns); goto out; } @@ -1132,7 +1383,7 @@ int copy_namespace(int flags, struct task_struct *tsk) p = next_mnt(p, namespace->root); q = next_mnt(q, new_ns->root); } - up_write(&tsk->namespace->sem); + up_write(&namespace_sem); tsk->namespace = new_ns; @@ -1161,7 +1412,7 @@ asmlinkage long sys_mount(char __user * dev_name, char __user * dir_name, unsigned long dev_page; char *dir_page; - retval = copy_mount_options (type, &type_page); + retval = copy_mount_options(type, &type_page); if (retval < 0) return retval; @@ -1170,17 +1421,17 @@ asmlinkage long sys_mount(char __user * dev_name, char __user * dir_name, if (IS_ERR(dir_page)) goto out1; - retval = copy_mount_options (dev_name, &dev_page); + retval = copy_mount_options(dev_name, &dev_page); if (retval < 0) goto out2; - retval = copy_mount_options (data, &data_page); + retval = copy_mount_options(data, &data_page); if (retval < 0) goto out3; lock_kernel(); - retval = do_mount((char*)dev_page, dir_page, (char*)type_page, - flags, (void*)data_page); + retval = do_mount((char *)dev_page, dir_page, (char *)type_page, + flags, (void *)data_page); unlock_kernel(); free_page(data_page); @@ -1249,9 +1500,11 @@ static void chroot_fs_refs(struct nameidata *old_nd, struct nameidata *new_nd) if (fs) { atomic_inc(&fs->count); task_unlock(p); - if (fs->root==old_nd->dentry&&fs->rootmnt==old_nd->mnt) + if (fs->root == old_nd->dentry + && fs->rootmnt == old_nd->mnt) set_fs_root(fs, new_nd->mnt, new_nd->dentry); - if (fs->pwd==old_nd->dentry&&fs->pwdmnt==old_nd->mnt) + if (fs->pwd == old_nd->dentry + && fs->pwdmnt == old_nd->mnt) set_fs_pwd(fs, new_nd->mnt, new_nd->dentry); put_fs_struct(fs); } else @@ -1281,8 +1534,8 @@ static void chroot_fs_refs(struct nameidata *old_nd, struct nameidata *new_nd) * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root * first. */ - -asmlinkage long sys_pivot_root(const char __user *new_root, const char __user *put_old) +asmlinkage long sys_pivot_root(const char __user * new_root, + const char __user * put_old) { struct vfsmount *tmp; struct nameidata new_nd, old_nd, parent_nd, root_parent, user_nd; @@ -1293,14 +1546,15 @@ asmlinkage long sys_pivot_root(const char __user *new_root, const char __user *p lock_kernel(); - error = __user_walk(new_root, LOOKUP_FOLLOW|LOOKUP_DIRECTORY, &new_nd); + error = __user_walk(new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, + &new_nd); if (error) goto out0; error = -EINVAL; if (!check_mnt(new_nd.mnt)) goto out1; - error = __user_walk(put_old, LOOKUP_FOLLOW|LOOKUP_DIRECTORY, &old_nd); + error = __user_walk(put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old_nd); if (error) goto out1; @@ -1314,9 +1568,13 @@ asmlinkage long sys_pivot_root(const char __user *new_root, const char __user *p user_nd.mnt = mntget(current->fs->rootmnt); user_nd.dentry = dget(current->fs->root); read_unlock(¤t->fs->lock); - down_write(¤t->namespace->sem); + down_write(&namespace_sem); down(&old_nd.dentry->d_inode->i_sem); error = -EINVAL; + if (IS_MNT_SHARED(old_nd.mnt) || + IS_MNT_SHARED(new_nd.mnt->mnt_parent) || + IS_MNT_SHARED(user_nd.mnt->mnt_parent)) + goto out2; if (!check_mnt(user_nd.mnt)) goto out2; error = -ENOENT; @@ -1356,6 +1614,7 @@ asmlinkage long sys_pivot_root(const char __user *new_root, const char __user *p detach_mnt(user_nd.mnt, &root_parent); attach_mnt(user_nd.mnt, &old_nd); /* mount old root on put_old */ attach_mnt(new_nd.mnt, &root_parent); /* mount new_root on / */ + touch_namespace(current->namespace); spin_unlock(&vfsmount_lock); chroot_fs_refs(&user_nd, &new_nd); security_sb_post_pivotroot(&user_nd, &new_nd); @@ -1364,7 +1623,7 @@ asmlinkage long sys_pivot_root(const char __user *new_root, const char __user *p path_release(&parent_nd); out2: up(&old_nd.dentry->d_inode->i_sem); - up_write(¤t->namespace->sem); + up_write(&namespace_sem); path_release(&user_nd); path_release(&old_nd); out1: @@ -1391,7 +1650,8 @@ static void __init init_mount_tree(void) panic("Can't allocate initial namespace"); atomic_set(&namespace->count, 1); INIT_LIST_HEAD(&namespace->list); - init_rwsem(&namespace->sem); + init_waitqueue_head(&namespace->poll); + namespace->event = 0; list_add(&mnt->mnt_list, &namespace->list); namespace->root = mnt; mnt->mnt_namespace = namespace; @@ -1414,11 +1674,12 @@ void __init mnt_init(unsigned long mempages) unsigned int nr_hash; int i; + init_rwsem(&namespace_sem); + mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct vfsmount), - 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); + 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL, NULL); - mount_hashtable = (struct list_head *) - __get_free_page(GFP_ATOMIC); + mount_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC); if (!mount_hashtable) panic("Failed to allocate mount hash table\n"); @@ -1440,7 +1701,7 @@ void __init mnt_init(unsigned long mempages) * from the number of bits we can fit. */ nr_hash = 1UL << hash_bits; - hash_mask = nr_hash-1; + hash_mask = nr_hash - 1; printk("Mount-cache hash table entries: %d\n", nr_hash); @@ -1460,12 +1721,14 @@ void __init mnt_init(unsigned long mempages) void __put_namespace(struct namespace *namespace) { struct vfsmount *root = namespace->root; + LIST_HEAD(umount_list); namespace->root = NULL; spin_unlock(&vfsmount_lock); - down_write(&namespace->sem); + down_write(&namespace_sem); spin_lock(&vfsmount_lock); - umount_tree(root); + umount_tree(root, 0, &umount_list); spin_unlock(&vfsmount_lock); - up_write(&namespace->sem); + up_write(&namespace_sem); + release_mounts(&umount_list); kfree(namespace); } diff --git a/fs/pnode.c b/fs/pnode.c new file mode 100644 index 00000000000..aeeec8ba8dd --- /dev/null +++ b/fs/pnode.c @@ -0,0 +1,305 @@ +/* + * linux/fs/pnode.c + * + * (C) Copyright IBM Corporation 2005. + * Released under GPL v2. + * Author : Ram Pai (linuxram@us.ibm.com) + * + */ +#include <linux/namespace.h> +#include <linux/mount.h> +#include <linux/fs.h> +#include "pnode.h" + +/* return the next shared peer mount of @p */ +static inline struct vfsmount *next_peer(struct vfsmount *p) +{ + return list_entry(p->mnt_share.next, struct vfsmount, mnt_share); +} + +static inline struct vfsmount *first_slave(struct vfsmount *p) +{ + return list_entry(p->mnt_slave_list.next, struct vfsmount, mnt_slave); +} + +static inline struct vfsmount *next_slave(struct vfsmount *p) +{ + return list_entry(p->mnt_slave.next, struct vfsmount, mnt_slave); +} + +static int do_make_slave(struct vfsmount *mnt) +{ + struct vfsmount *peer_mnt = mnt, *master = mnt->mnt_master; + struct vfsmount *slave_mnt; + + /* + * slave 'mnt' to a peer mount that has the + * same root dentry. If none is available than + * slave it to anything that is available. + */ + while ((peer_mnt = next_peer(peer_mnt)) != mnt && + peer_mnt->mnt_root != mnt->mnt_root) ; + + if (peer_mnt == mnt) { + peer_mnt = next_peer(mnt); + if (peer_mnt == mnt) + peer_mnt = NULL; + } + list_del_init(&mnt->mnt_share); + + if (peer_mnt) + master = peer_mnt; + + if (master) { + list_for_each_entry(slave_mnt, &mnt->mnt_slave_list, mnt_slave) + slave_mnt->mnt_master = master; + list_del(&mnt->mnt_slave); + list_add(&mnt->mnt_slave, &master->mnt_slave_list); + list_splice(&mnt->mnt_slave_list, master->mnt_slave_list.prev); + INIT_LIST_HEAD(&mnt->mnt_slave_list); + } else { + struct list_head *p = &mnt->mnt_slave_list; + while (!list_empty(p)) { + slave_mnt = list_entry(p->next, + struct vfsmount, mnt_slave); + list_del_init(&slave_mnt->mnt_slave); + slave_mnt->mnt_master = NULL; + } + } + mnt->mnt_master = master; + CLEAR_MNT_SHARED(mnt); + INIT_LIST_HEAD(&mnt->mnt_slave_list); + return 0; +} + +void change_mnt_propagation(struct vfsmount *mnt, int type) +{ + if (type == MS_SHARED) { + set_mnt_shared(mnt); + return; + } + do_make_slave(mnt); + if (type != MS_SLAVE) { + list_del_init(&mnt->mnt_slave); + mnt->mnt_master = NULL; + if (type == MS_UNBINDABLE) + mnt->mnt_flags |= MNT_UNBINDABLE; + } +} + +/* + * get the next mount in the propagation tree. + * @m: the mount seen last + * @origin: the original mount from where the tree walk initiated + */ +static struct vfsmount *propagation_next(struct vfsmount *m, + struct vfsmount *origin) +{ + /* are there any slaves of this mount? */ + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) + return first_slave(m); + + while (1) { + struct vfsmount *next; + struct vfsmount *master = m->mnt_master; + + if ( master == origin->mnt_master ) { + next = next_peer(m); + return ((next == origin) ? NULL : next); + } else if (m->mnt_slave.next != &master->mnt_slave_list) + return next_slave(m); + + /* back at master */ + m = master; + } +} + +/* + * return the source mount to be used for cloning + * + * @dest the current destination mount + * @last_dest the last seen destination mount + * @last_src the last seen source mount + * @type return CL_SLAVE if the new mount has to be + * cloned as a slave. + */ +static struct vfsmount *get_source(struct vfsmount *dest, + struct vfsmount *last_dest, + struct vfsmount *last_src, + int *type) +{ + struct vfsmount *p_last_src = NULL; + struct vfsmount *p_last_dest = NULL; + *type = CL_PROPAGATION;; + + if (IS_MNT_SHARED(dest)) + *type |= CL_MAKE_SHARED; + + while (last_dest != dest->mnt_master) { + p_last_dest = last_dest; + p_last_src = last_src; + last_dest = last_dest->mnt_master; + last_src = last_src->mnt_master; + } + + if (p_last_dest) { + do { + p_last_dest = next_peer(p_last_dest); + } while (IS_MNT_NEW(p_last_dest)); + } + + if (dest != p_last_dest) { + *type |= CL_SLAVE; + return last_src; + } else + return p_last_src; +} + +/* + * mount 'source_mnt' under the destination 'dest_mnt' at + * dentry 'dest_dentry'. And propagate that mount to + * all the peer and slave mounts of 'dest_mnt'. + * Link all the new mounts into a propagation tree headed at + * source_mnt. Also link all the new mounts using ->mnt_list + * headed at source_mnt's ->mnt_list + * + * @dest_mnt: destination mount. + * @dest_dentry: destination dentry. + * @source_mnt: source mount. + * @tree_list : list of heads of trees to be attached. + */ +int propagate_mnt(struct vfsmount *dest_mnt, struct dentry *dest_dentry, + struct vfsmount *source_mnt, struct list_head *tree_list) +{ + struct vfsmount *m, *child; + int ret = 0; + struct vfsmount *prev_dest_mnt = dest_mnt; + struct vfsmount *prev_src_mnt = source_mnt; + LIST_HEAD(tmp_list); + LIST_HEAD(umount_list); + + for (m = propagation_next(dest_mnt, dest_mnt); m; + m = propagation_next(m, dest_mnt)) { + int type; + struct vfsmount *source; + + if (IS_MNT_NEW(m)) + continue; + + source = get_source(m, prev_dest_mnt, prev_src_mnt, &type); + + if (!(child = copy_tree(source, source->mnt_root, type))) { + ret = -ENOMEM; + list_splice(tree_list, tmp_list.prev); + goto out; + } + + if (is_subdir(dest_dentry, m->mnt_root)) { + mnt_set_mountpoint(m, dest_dentry, child); + list_add_tail(&child->mnt_hash, tree_list); + } else { + /* + * This can happen if the parent mount was bind mounted + * on some subdirectory of a shared/slave mount. + */ + list_add_tail(&child->mnt_hash, &tmp_list); + } + prev_dest_mnt = m; + prev_src_mnt = child; + } +out: + spin_lock(&vfsmount_lock); + while (!list_empty(&tmp_list)) { + child = list_entry(tmp_list.next, struct vfsmount, mnt_hash); + list_del_init(&child->mnt_hash); + umount_tree(child, 0, &umount_list); + } + spin_unlock(&vfsmount_lock); + release_mounts(&umount_list); + return ret; +} + +/* + * return true if the refcount is greater than count + */ +static inline int do_refcount_check(struct vfsmount *mnt, int count) +{ + int mycount = atomic_read(&mnt->mnt_count); + return (mycount > count); +} + +/* + * check if the mount 'mnt' can be unmounted successfully. + * @mnt: the mount to be checked for unmount + * NOTE: unmounting 'mnt' would naturally propagate to all + * other mounts its parent propagates to. + * Check if any of these mounts that **do not have submounts** + * have more references than 'refcnt'. If so return busy. + */ +int propagate_mount_busy(struct vfsmount *mnt, int refcnt) +{ + struct vfsmount *m, *child; + struct vfsmount *parent = mnt->mnt_parent; + int ret = 0; + + if (mnt == parent) + return do_refcount_check(mnt, refcnt); + + /* + * quickly check if the current mount can be unmounted. + * If not, we don't have to go checking for all other + * mounts + */ + if (!list_empty(&mnt->mnt_mounts) || do_refcount_check(mnt, refcnt)) + return 1; + + for (m = propagation_next(parent, parent); m; + m = propagation_next(m, parent)) { + child = __lookup_mnt(m, mnt->mnt_mountpoint, 0); + if (child && list_empty(&child->mnt_mounts) && + (ret = do_refcount_check(child, 1))) + break; + } + return ret; +} + +/* + * NOTE: unmounting 'mnt' naturally propagates to all other mounts its + * parent propagates to. + */ +static void __propagate_umount(struct vfsmount *mnt) +{ + struct vfsmount *parent = mnt->mnt_parent; + struct vfsmount *m; + + BUG_ON(parent == mnt); + + for (m = propagation_next(parent, parent); m; + m = propagation_next(m, parent)) { + + struct vfsmount *child = __lookup_mnt(m, + mnt->mnt_mountpoint, 0); + /* + * umount the child only if the child has no + * other children + */ + if (child && list_empty(&child->mnt_mounts)) { + list_del(&child->mnt_hash); + list_add_tail(&child->mnt_hash, &mnt->mnt_hash); + } + } +} + +/* + * collect all mounts that receive propagation from the mount in @list, + * and return these additional mounts in the same list. + * @list: the list of mounts to be unmounted. + */ +int propagate_umount(struct list_head *list) +{ + struct vfsmount *mnt; + + list_for_each_entry(mnt, list, mnt_hash) + __propagate_umount(mnt); + return 0; +} diff --git a/fs/pnode.h b/fs/pnode.h new file mode 100644 index 00000000000..020e1bb60fd --- /dev/null +++ b/fs/pnode.h @@ -0,0 +1,37 @@ +/* + * linux/fs/pnode.h + * + * (C) Copyright IBM Corporation 2005. + * Released under GPL v2. + * + */ +#ifndef _LINUX_PNODE_H +#define _LINUX_PNODE_H + +#include <linux/list.h> +#include <linux/mount.h> + +#define IS_MNT_SHARED(mnt) (mnt->mnt_flags & MNT_SHARED) +#define IS_MNT_SLAVE(mnt) (mnt->mnt_master) +#define IS_MNT_NEW(mnt) (!mnt->mnt_namespace) +#define CLEAR_MNT_SHARED(mnt) (mnt->mnt_flags &= ~MNT_SHARED) +#define IS_MNT_UNBINDABLE(mnt) (mnt->mnt_flags & MNT_UNBINDABLE) + +#define CL_EXPIRE 0x01 +#define CL_SLAVE 0x02 +#define CL_COPY_ALL 0x04 +#define CL_MAKE_SHARED 0x08 +#define CL_PROPAGATION 0x10 + +static inline void set_mnt_shared(struct vfsmount *mnt) +{ + mnt->mnt_flags &= ~MNT_PNODE_MASK; + mnt->mnt_flags |= MNT_SHARED; +} + +void change_mnt_propagation(struct vfsmount *, int); +int propagate_mnt(struct vfsmount *, struct dentry *, struct vfsmount *, + struct list_head *); +int propagate_umount(struct list_head *); +int propagate_mount_busy(struct vfsmount *, int); +#endif /* _LINUX_PNODE_H */ diff --git a/fs/proc/base.c b/fs/proc/base.c index a170450aadb..634355e1698 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -70,6 +70,7 @@ #include <linux/seccomp.h> #include <linux/cpuset.h> #include <linux/audit.h> +#include <linux/poll.h> #include "internal.h" /* @@ -660,26 +661,38 @@ static struct file_operations proc_smaps_operations = { #endif extern struct seq_operations mounts_op; +struct proc_mounts { + struct seq_file m; + int event; +}; + static int mounts_open(struct inode *inode, struct file *file) { struct task_struct *task = proc_task(inode); - int ret = seq_open(file, &mounts_op); + struct namespace *namespace; + struct proc_mounts *p; + int ret = -EINVAL; - if (!ret) { - struct seq_file *m = file->private_data; - struct namespace *namespace; - task_lock(task); - namespace = task->namespace; - if (namespace) - get_namespace(namespace); - task_unlock(task); - - if (namespace) - m->private = namespace; - else { - seq_release(inode, file); - ret = -EINVAL; + task_lock(task); + namespace = task->namespace; + if (namespace) + get_namespace(namespace); + task_unlock(task); + + if (namespace) { + ret = -ENOMEM; + p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL); + if (p) { + file->private_data = &p->m; + ret = seq_open(file, &mounts_op); + if (!ret) { + p->m.private = namespace; + p->event = namespace->event; + return 0; + } + kfree(p); } + put_namespace(namespace); } return ret; } @@ -692,11 +705,30 @@ static int mounts_release(struct inode *inode, struct file *file) return seq_release(inode, file); } +static unsigned mounts_poll(struct file *file, poll_table *wait) +{ + struct proc_mounts *p = file->private_data; + struct namespace *ns = p->m.private; + unsigned res = 0; + + poll_wait(file, &ns->poll, wait); + + spin_lock(&vfsmount_lock); + if (p->event != ns->event) { + p->event = ns->event; + res = POLLERR; + } + spin_unlock(&vfsmount_lock); + + return res; +} + static struct file_operations proc_mounts_operations = { .open = mounts_open, .read = seq_read, .llseek = seq_lseek, .release = mounts_release, + .poll = mounts_poll, }; #define PROC_BLOCK_SIZE (3*1024) /* 4K page size but our output routines use some slack for overruns */ diff --git a/fs/seq_file.c b/fs/seq_file.c index 38ef913767f..7c40570b71d 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -28,13 +28,17 @@ */ int seq_open(struct file *file, struct seq_operations *op) { - struct seq_file *p = kmalloc(sizeof(*p), GFP_KERNEL); - if (!p) - return -ENOMEM; + struct seq_file *p = file->private_data; + + if (!p) { + p = kmalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + file->private_data = p; + } memset(p, 0, sizeof(*p)); sema_init(&p->sem, 1); p->op = op; - file->private_data = p; /* * Wrappers around seq_open(e.g. swaps_open) need to be diff --git a/fs/super.c b/fs/super.c index eed6c313290..6689dded3c8 100644 --- a/fs/super.c +++ b/fs/super.c @@ -171,6 +171,7 @@ void deactivate_super(struct super_block *s) if (atomic_dec_and_lock(&s->s_active, &sb_lock)) { s->s_count -= S_BIAS-1; spin_unlock(&sb_lock); + DQUOT_OFF(s); down_write(&s->s_umount); fs->kill_sb(s); put_filesystem(fs); diff --git a/include/asm-ia64/page.h b/include/asm-ia64/page.h index ef436b9d06a..9d41548b7fe 100644 --- a/include/asm-ia64/page.h +++ b/include/asm-ia64/page.h @@ -120,6 +120,7 @@ extern unsigned long max_low_pfn; #define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) +#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) typedef union ia64_va { struct { diff --git a/include/linux/acct.h b/include/linux/acct.h index 19f70462b3b..93c5b3cdf95 100644 --- a/include/linux/acct.h +++ b/include/linux/acct.h @@ -117,12 +117,15 @@ struct acct_v3 #include <linux/config.h> #ifdef CONFIG_BSD_PROCESS_ACCT +struct vfsmount; struct super_block; +extern void acct_auto_close_mnt(struct vfsmount *m); extern void acct_auto_close(struct super_block *sb); extern void acct_process(long exitcode); extern void acct_update_integrals(struct task_struct *tsk); extern void acct_clear_integrals(struct task_struct *tsk); #else +#define acct_auto_close_mnt(x) do { } while (0) #define acct_auto_close(x) do { } while (0) #define acct_process(x) do { } while (0) #define acct_update_integrals(x) do { } while (0) diff --git a/include/linux/dcache.h b/include/linux/dcache.h index ab04b4f9b0d..46a2ba61759 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -329,6 +329,7 @@ static inline int d_mountpoint(struct dentry *dentry) } extern struct vfsmount *lookup_mnt(struct vfsmount *, struct dentry *); +extern struct vfsmount *__lookup_mnt(struct vfsmount *, struct dentry *, int); extern struct dentry *lookup_create(struct nameidata *nd, int is_dir); extern int sysctl_vfs_cache_pressure; diff --git a/include/linux/fs.h b/include/linux/fs.h index 9a593ef262e..1b5f502a4b8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -104,6 +104,10 @@ extern int dir_notify_enable; #define MS_MOVE 8192 #define MS_REC 16384 #define MS_VERBOSE 32768 +#define MS_UNBINDABLE (1<<17) /* change to unbindable */ +#define MS_PRIVATE (1<<18) /* change to private */ +#define MS_SLAVE (1<<19) /* change to slave */ +#define MS_SHARED (1<<20) /* change to shared */ #define MS_POSIXACL (1<<16) /* VFS does not apply the umask */ #define MS_ACTIVE (1<<30) #define MS_NOUSER (1<<31) @@ -1249,7 +1253,12 @@ extern int unregister_filesystem(struct file_system_type *); extern struct vfsmount *kern_mount(struct file_system_type *); extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); +extern void umount_tree(struct vfsmount *, int, struct list_head *); +extern void release_mounts(struct list_head *); extern long do_mount(char *, char *, char *, unsigned long, void *); +extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int); +extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *, + struct vfsmount *); extern int vfs_statfs(struct super_block *, struct kstatfs *); diff --git a/include/linux/mount.h b/include/linux/mount.h index f8f39937e30..dd4e83eba93 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -17,12 +17,14 @@ #include <linux/spinlock.h> #include <asm/atomic.h> -#define MNT_NOSUID 1 -#define MNT_NODEV 2 -#define MNT_NOEXEC 4 +#define MNT_NOSUID 0x01 +#define MNT_NODEV 0x02 +#define MNT_NOEXEC 0x04 +#define MNT_SHARED 0x10 /* if the vfsmount is a shared mount */ +#define MNT_UNBINDABLE 0x20 /* if the vfsmount is a unbindable mount */ +#define MNT_PNODE_MASK 0x30 /* propogation flag mask */ -struct vfsmount -{ +struct vfsmount { struct list_head mnt_hash; struct vfsmount *mnt_parent; /* fs we are mounted on */ struct dentry *mnt_mountpoint; /* dentry of mountpoint */ @@ -36,7 +38,12 @@ struct vfsmount char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ + struct list_head mnt_share; /* circular list of shared mounts */ + struct list_head mnt_slave_list;/* list of slave mounts */ + struct list_head mnt_slave; /* slave list entry */ + struct vfsmount *mnt_master; /* slave is on master->mnt_slave_list */ struct namespace *mnt_namespace; /* containing namespace */ + int mnt_pinned; }; static inline struct vfsmount *mntget(struct vfsmount *mnt) @@ -46,15 +53,9 @@ static inline struct vfsmount *mntget(struct vfsmount *mnt) return mnt; } -extern void __mntput(struct vfsmount *mnt); - -static inline void mntput_no_expire(struct vfsmount *mnt) -{ - if (mnt) { - if (atomic_dec_and_test(&mnt->mnt_count)) - __mntput(mnt); - } -} +extern void mntput_no_expire(struct vfsmount *mnt); +extern void mnt_pin(struct vfsmount *mnt); +extern void mnt_unpin(struct vfsmount *mnt); static inline void mntput(struct vfsmount *mnt) { diff --git a/include/linux/namespace.h b/include/linux/namespace.h index 0e5a86f13b2..6731977c4c1 100644 --- a/include/linux/namespace.h +++ b/include/linux/namespace.h @@ -9,7 +9,8 @@ struct namespace { atomic_t count; struct vfsmount * root; struct list_head list; - struct rw_semaphore sem; + wait_queue_head_t poll; + int event; }; extern int copy_namespace(int, struct task_struct *); diff --git a/include/linux/quota.h b/include/linux/quota.h index 700ead45084..f33aeb22c26 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -289,7 +289,6 @@ struct quota_info { struct semaphore dqonoff_sem; /* Serialize quotaon & quotaoff */ struct rw_semaphore dqptr_sem; /* serialize ops using quota_info struct, pointers from inode to dquots */ struct inode *files[MAXQUOTAS]; /* inodes of quotafiles */ - struct vfsmount *mnt[MAXQUOTAS]; /* mountpoint entries of filesystems with quota files */ struct mem_dqinfo info[MAXQUOTAS]; /* Information for each quota type */ struct quota_format_ops *ops[MAXQUOTAS]; /* Operations for each type */ }; diff --git a/kernel/acct.c b/kernel/acct.c index 2e3f4a47e7d..6312d6bd43e 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -54,6 +54,7 @@ #include <linux/jiffies.h> #include <linux/times.h> #include <linux/syscalls.h> +#include <linux/mount.h> #include <asm/uaccess.h> #include <asm/div64.h> #include <linux/blkdev.h> /* sector_div */ @@ -192,6 +193,7 @@ static void acct_file_reopen(struct file *file) add_timer(&acct_globals.timer); } if (old_acct) { + mnt_unpin(old_acct->f_vfsmnt); spin_unlock(&acct_globals.lock); do_acct_process(0, old_acct); filp_close(old_acct, NULL); @@ -199,6 +201,42 @@ static void acct_file_reopen(struct file *file) } } +static int acct_on(char *name) +{ + struct file *file; + int error; + + /* Difference from BSD - they don't do O_APPEND */ + file = filp_open(name, O_WRONLY|O_APPEND|O_LARGEFILE, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + + if (!S_ISREG(file->f_dentry->d_inode->i_mode)) { + filp_close(file, NULL); + return -EACCES; + } + + if (!file->f_op->write) { + filp_close(file, NULL); + return -EIO; + } + + error = security_acct(file); + if (error) { + filp_close(file, NULL); + return error; + } + + spin_lock(&acct_globals.lock); + mnt_pin(file->f_vfsmnt); + acct_file_reopen(file); + spin_unlock(&acct_globals.lock); + + mntput(file->f_vfsmnt); /* it's pinned, now give up active reference */ + + return 0; +} + /** * sys_acct - enable/disable process accounting * @name: file name for accounting records or NULL to shutdown accounting @@ -212,47 +250,41 @@ static void acct_file_reopen(struct file *file) */ asmlinkage long sys_acct(const char __user *name) { - struct file *file = NULL; - char *tmp; int error; if (!capable(CAP_SYS_PACCT)) return -EPERM; if (name) { - tmp = getname(name); - if (IS_ERR(tmp)) { + char *tmp = getname(name); + if (IS_ERR(tmp)) return (PTR_ERR(tmp)); - } - /* Difference from BSD - they don't do O_APPEND */ - file = filp_open(tmp, O_WRONLY|O_APPEND|O_LARGEFILE, 0); + error = acct_on(tmp); putname(tmp); - if (IS_ERR(file)) { - return (PTR_ERR(file)); - } - if (!S_ISREG(file->f_dentry->d_inode->i_mode)) { - filp_close(file, NULL); - return (-EACCES); - } - - if (!file->f_op->write) { - filp_close(file, NULL); - return (-EIO); + } else { + error = security_acct(NULL); + if (!error) { + spin_lock(&acct_globals.lock); + acct_file_reopen(NULL); + spin_unlock(&acct_globals.lock); } } + return error; +} - error = security_acct(file); - if (error) { - if (file) - filp_close(file, NULL); - return error; - } - +/** + * acct_auto_close - turn off a filesystem's accounting if it is on + * @m: vfsmount being shut down + * + * If the accounting is turned on for a file in the subtree pointed to + * to by m, turn accounting off. Done when m is about to die. + */ +void acct_auto_close_mnt(struct vfsmount *m) +{ spin_lock(&acct_globals.lock); - acct_file_reopen(file); + if (acct_globals.file && acct_globals.file->f_vfsmnt == m) + acct_file_reopen(NULL); spin_unlock(&acct_globals.lock); - - return (0); } /** @@ -266,8 +298,8 @@ void acct_auto_close(struct super_block *sb) { spin_lock(&acct_globals.lock); if (acct_globals.file && - acct_globals.file->f_dentry->d_inode->i_sb == sb) { - acct_file_reopen((struct file *)NULL); + acct_globals.file->f_vfsmnt->mnt_sb == sb) { + acct_file_reopen(NULL); } spin_unlock(&acct_globals.lock); } |