diff options
94 files changed, 3263 insertions, 2006 deletions
diff --git a/Documentation/ioctl-number.txt b/Documentation/ioctl-number.txt index 769f925c8526..87f4d052e39c 100644 --- a/Documentation/ioctl-number.txt +++ b/Documentation/ioctl-number.txt @@ -130,8 +130,6 @@ Code Seq# Include File Comments <mailto:zapman@interlan.net> 'i' 00-3F linux/i2o.h 'j' 00-3F linux/joystick.h -'k' all asm-sparc/kbio.h - asm-sparc64/kbio.h 'l' 00-3F linux/tcfs_fs.h transparent cryptographic file system <http://mikonos.dia.unisa.it/tcfs> 'l' 40-7F linux/udf_fs_i.h in development: diff --git a/Documentation/sharedsubtree.txt b/Documentation/sharedsubtree.txt new file mode 100644 index 000000000000..2d8f403eb6eb --- /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/arm/Kconfig b/arch/arm/Kconfig index 296bc03d1cf1..91d5ef3397be 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -324,7 +324,7 @@ menu "Kernel Features" config SMP bool "Symmetric Multi-Processing (EXPERIMENTAL)" - depends on EXPERIMENTAL && BROKEN #&& n + depends on EXPERIMENTAL && REALVIEW_MPCORE help This enables support for systems with more than one CPU. If you have a system with only one CPU, like most personal computers, say N. If @@ -585,7 +585,7 @@ config FPE_NWFPE config FPE_NWFPE_XP bool "Support extended precision" - depends on FPE_NWFPE && !CPU_BIG_ENDIAN + depends on FPE_NWFPE help Say Y to include 80-bit support in the kernel floating-point emulator. Otherwise, only 32 and 64-bit support is compiled in. diff --git a/arch/arm/mach-ixp2000/core.c b/arch/arm/mach-ixp2000/core.c index df140962bb0f..6851abaf5524 100644 --- a/arch/arm/mach-ixp2000/core.c +++ b/arch/arm/mach-ixp2000/core.c @@ -84,63 +84,54 @@ static struct map_desc ixp2000_io_desc[] __initdata = { .virtual = IXP2000_CAP_VIRT_BASE, .pfn = __phys_to_pfn(IXP2000_CAP_PHYS_BASE), .length = IXP2000_CAP_SIZE, - .type = MT_DEVICE + .type = MT_IXP2000_DEVICE, }, { .virtual = IXP2000_INTCTL_VIRT_BASE, .pfn = __phys_to_pfn(IXP2000_INTCTL_PHYS_BASE), .length = IXP2000_INTCTL_SIZE, - .type = MT_DEVICE + .type = MT_IXP2000_DEVICE, }, { .virtual = IXP2000_PCI_CREG_VIRT_BASE, .pfn = __phys_to_pfn(IXP2000_PCI_CREG_PHYS_BASE), .length = IXP2000_PCI_CREG_SIZE, - .type = MT_DEVICE + .type = MT_IXP2000_DEVICE, }, { .virtual = IXP2000_PCI_CSR_VIRT_BASE, .pfn = __phys_to_pfn(IXP2000_PCI_CSR_PHYS_BASE), .length = IXP2000_PCI_CSR_SIZE, - .type = MT_DEVICE + .type = MT_IXP2000_DEVICE, }, { .virtual = IXP2000_MSF_VIRT_BASE, .pfn = __phys_to_pfn(IXP2000_MSF_PHYS_BASE), .length = IXP2000_MSF_SIZE, - .type = MT_DEVICE + .type = MT_IXP2000_DEVICE, }, { .virtual = IXP2000_PCI_IO_VIRT_BASE, .pfn = __phys_to_pfn(IXP2000_PCI_IO_PHYS_BASE), .length = IXP2000_PCI_IO_SIZE, - .type = MT_DEVICE + .type = MT_IXP2000_DEVICE, }, { .virtual = IXP2000_PCI_CFG0_VIRT_BASE, .pfn = __phys_to_pfn(IXP2000_PCI_CFG0_PHYS_BASE), .length = IXP2000_PCI_CFG0_SIZE, - .type = MT_DEVICE + .type = MT_IXP2000_DEVICE, }, { .virtual = IXP2000_PCI_CFG1_VIRT_BASE, .pfn = __phys_to_pfn(IXP2000_PCI_CFG1_PHYS_BASE), .length = IXP2000_PCI_CFG1_SIZE, - .type = MT_DEVICE + .type = MT_IXP2000_DEVICE, } }; void __init ixp2000_map_io(void) { - extern unsigned int processor_id; - /* - * On IXP2400 CPUs we need to use MT_IXP2000_DEVICE for - * tweaking the PMDs so XCB=101. On IXP2800s we use the normal - * PMD flags. + * On IXP2400 CPUs we need to use MT_IXP2000_DEVICE so that + * XCB=101 (to avoid triggering erratum #66), and given that + * this mode speeds up I/O accesses and we have write buffer + * flushes in the right places anyway, it doesn't hurt to use + * XCB=101 for all IXP2000s. */ - if ((processor_id & 0xfffffff0) == 0x69054190) { - int i; - - printk(KERN_INFO "Enabling IXP2400 erratum #66 workaround\n"); - - for(i=0;i<ARRAY_SIZE(ixp2000_io_desc);i++) - ixp2000_io_desc[i].type = MT_IXP2000_DEVICE; - } - iotable_init(ixp2000_io_desc, ARRAY_SIZE(ixp2000_io_desc)); /* Set slowport to 8-bit mode. */ diff --git a/arch/arm/mach-realview/Kconfig b/arch/arm/mach-realview/Kconfig index 4b63dc9eabfe..129976866d47 100644 --- a/arch/arm/mach-realview/Kconfig +++ b/arch/arm/mach-realview/Kconfig @@ -8,4 +8,13 @@ config MACH_REALVIEW_EB help Include support for the ARM(R) RealView Emulation Baseboard platform. +config REALVIEW_MPCORE + bool "Support MPcore tile" + depends on MACH_REALVIEW_EB + help + Enable support for the MPCore tile on the Realview platform. + Since there are device address and interrupt differences, a + kernel built with this option enabled is not compatible with + other tiles. + endmenu diff --git a/arch/arm/mach-realview/Makefile b/arch/arm/mach-realview/Makefile index 8d37ea1605fd..011a85c10627 100644 --- a/arch/arm/mach-realview/Makefile +++ b/arch/arm/mach-realview/Makefile @@ -4,3 +4,4 @@ obj-y := core.o clock.o obj-$(CONFIG_MACH_REALVIEW_EB) += realview_eb.o +obj-$(CONFIG_SMP) += platsmp.o headsmp.o diff --git a/arch/arm/mach-realview/core.h b/arch/arm/mach-realview/core.h index 575599db74db..d83e8bad2038 100644 --- a/arch/arm/mach-realview/core.h +++ b/arch/arm/mach-realview/core.h @@ -23,6 +23,7 @@ #define __ASM_ARCH_REALVIEW_H #include <asm/hardware/amba.h> +#include <asm/leds.h> #include <asm/io.h> #define __io_address(n) __io(IO_ADDRESS(n)) diff --git a/arch/arm/mach-realview/headsmp.S b/arch/arm/mach-realview/headsmp.S new file mode 100644 index 000000000000..4075473cf68a --- /dev/null +++ b/arch/arm/mach-realview/headsmp.S @@ -0,0 +1,39 @@ +/* + * linux/arch/arm/mach-realview/headsmp.S + * + * Copyright (c) 2003 ARM Limited + * All Rights Reserved + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/linkage.h> +#include <linux/init.h> + + __INIT + +/* + * Realview specific entry point for secondary CPUs. This provides + * a "holding pen" into which all secondary cores are held until we're + * ready for them to initialise. + */ +ENTRY(realview_secondary_startup) + mrc p15, 0, r0, c0, c0, 5 + and r0, r0, #15 + adr r4, 1f + ldmia r4, {r5, r6} + sub r4, r4, r5 + add r6, r6, r4 +pen: ldr r7, [r6] + cmp r7, r0 + bne pen + + /* + * we've been released from the holding pen: secondary_stack + * should now contain the SVC stack for this core + */ + b secondary_startup + +1: .long . + .long pen_release diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c new file mode 100644 index 000000000000..9844644d0fb5 --- /dev/null +++ b/arch/arm/mach-realview/platsmp.c @@ -0,0 +1,195 @@ +/* + * linux/arch/arm/mach-realview/platsmp.c + * + * Copyright (C) 2002 ARM Ltd. + * All Rights Reserved + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/smp.h> + +#include <asm/cacheflush.h> +#include <asm/hardware/arm_scu.h> +#include <asm/hardware.h> + +#include "core.h" + +extern void realview_secondary_startup(void); + +/* + * control for which core is the next to come out of the secondary + * boot "holding pen" + */ +volatile int __cpuinitdata pen_release = -1; + +static unsigned int __init get_core_count(void) +{ + unsigned int ncores; + + ncores = __raw_readl(IO_ADDRESS(REALVIEW_MPCORE_SCU_BASE) + SCU_CONFIG); + + return (ncores & 0x03) + 1; +} + +static DEFINE_SPINLOCK(boot_lock); + +void __cpuinit platform_secondary_init(unsigned int cpu) +{ + /* + * the primary core may have used a "cross call" soft interrupt + * to get this processor out of WFI in the BootMonitor - make + * sure that we are no longer being sent this soft interrupt + */ + smp_cross_call_done(cpumask_of_cpu(cpu)); + + /* + * if any interrupts are already enabled for the primary + * core (e.g. timer irq), then they will not have been enabled + * for us: do so + */ + gic_cpu_init(__io_address(REALVIEW_GIC_CPU_BASE)); + + /* + * let the primary processor know we're out of the + * pen, then head off into the C entry point + */ + pen_release = -1; + + /* + * Synchronise with the boot thread. + */ + spin_lock(&boot_lock); + spin_unlock(&boot_lock); +} + +int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle) +{ + unsigned long timeout; + + /* + * set synchronisation state between this boot processor + * and the secondary one + */ + spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from + * the holding pen - release it, then wait for it to flag + * that it has been released by resetting pen_release. + * + * Note that "pen_release" is the hardware CPU ID, whereas + * "cpu" is Linux's internal ID. + */ + pen_release = cpu; + flush_cache_all(); + + /* + * XXX + * + * This is a later addition to the booting protocol: the + * bootMonitor now puts secondary cores into WFI, so + * poke_milo() no longer gets the cores moving; we need + * to send a soft interrupt to wake the secondary core. + * Use smp_cross_call() for this, since there's little + * point duplicating the code here + */ + smp_cross_call(cpumask_of_cpu(cpu)); + + timeout = jiffies + (1 * HZ); + while (time_before(jiffies, timeout)) { + if (pen_release == -1) + break; + + udelay(10); + } + + /* + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ + spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; +} + +static void __init poke_milo(void) +{ + extern void secondary_startup(void); + + /* nobody is to be released from the pen yet */ + pen_release = -1; + + /* + * write the address of secondary startup into the system-wide + * flags register, then clear the bottom two bits, which is what + * BootMonitor is waiting for + */ +#if 1 +#define REALVIEW_SYS_FLAGSS_OFFSET 0x30 + __raw_writel(virt_to_phys(realview_secondary_startup), + (IO_ADDRESS(REALVIEW_SYS_BASE) + + REALVIEW_SYS_FLAGSS_OFFSET)); +#define REALVIEW_SYS_FLAGSC_OFFSET 0x34 + __raw_writel(3, + (IO_ADDRESS(REALVIEW_SYS_BASE) + + REALVIEW_SYS_FLAGSC_OFFSET)); +#endif + + mb(); +} + +void __init smp_prepare_cpus(unsigned int max_cpus) +{ + unsigned int ncores = get_core_count(); + unsigned int cpu = smp_processor_id(); + int i; + + /* sanity check */ + if (ncores == 0) { + printk(KERN_ERR + "Realview: strange CM count of 0? Default to 1\n"); + + ncores = 1; + } + + if (ncores > NR_CPUS) { + printk(KERN_WARNING + "Realview: no. of cores (%d) greater than configured " + "maximum of %d - clipping\n", + ncores, NR_CPUS); + ncores = NR_CPUS; + } + + smp_store_cpu_info(cpu); + + /* + * are we trying to boot more cores than exist? + */ + if (max_cpus > ncores) + max_cpus = ncores; + + /* + * Initialise the possible/present maps. + * cpu_possible_map describes the set of CPUs which may be present + * cpu_present_map describes the set of CPUs populated + */ + for (i = 0; i < max_cpus; i++) { + cpu_set(i, cpu_possible_map); + cpu_set(i, cpu_present_map); + } + + /* + * Do we need any more CPUs? If so, then let them know where + * to start. Note that, on modern versions of MILO, the "poke" + * doesn't actually do anything until each individual core is + * sent a soft interrupt to get it out of WFI + */ + if (max_cpus > 1) + poke_milo(); +} diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c index 267bb07e39b7..7dc32503fdf2 100644 --- a/arch/arm/mach-realview/realview_eb.c +++ b/arch/arm/mach-realview/realview_eb.c @@ -136,6 +136,11 @@ static struct amba_device *amba_devs[] __initdata = { static void __init gic_init_irq(void) { +#ifdef CONFIG_REALVIEW_MPCORE + writel(0x0000a05f, __io_address(REALVIEW_SYS_LOCK)); + writel(0x008003c0, __io_address(REALVIEW_SYS_BASE) + 0xd8); + writel(0x00000000, __io_address(REALVIEW_SYS_LOCK)); +#endif gic_dist_init(__io_address(REALVIEW_GIC_DIST_BASE)); gic_cpu_init(__io_address(REALVIEW_GIC_CPU_BASE)); } diff --git a/arch/arm/mm/mm-armv.c b/arch/arm/mm/mm-armv.c index fb5b40289de2..9e50127be635 100644 --- a/arch/arm/mm/mm-armv.c +++ b/arch/arm/mm/mm-armv.c @@ -354,7 +354,7 @@ void __init build_mem_type_table(void) { struct cachepolicy *cp; unsigned int cr = get_cr(); - unsigned int user_pgprot; + unsigned int user_pgprot, kern_pgprot; int cpu_arch = cpu_architecture(); int i; @@ -381,7 +381,7 @@ void __init build_mem_type_table(void) } cp = &cache_policies[cachepolicy]; - user_pgprot = cp->pte; + kern_pgprot = user_pgprot = cp->pte; /* * ARMv6 and above have extended page tables. @@ -393,6 +393,7 @@ void __init build_mem_type_table(void) */ mem_types[MT_MEMORY].prot_sect &= ~PMD_BIT4; mem_types[MT_ROM].prot_sect &= ~PMD_BIT4; + /* * Mark cache clean areas and XIP ROM read only * from SVC mode and no access from userspace. @@ -412,32 +413,47 @@ void __init build_mem_type_table(void) * (iow, non-global) */ user_pgprot |= L_PTE_ASID; + +#ifdef CONFIG_SMP + /* + * Mark memory with the "shared" attribute for SMP systems + */ + user_pgprot |= L_PTE_SHARED; + kern_pgprot |= L_PTE_SHARED; + mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; +#endif } + for (i = 0; i < 16; i++) { + unsigned long v = pgprot_val(protection_map[i]); + v = (v & ~(L_PTE_BUFFERABLE|L_PTE_CACHEABLE)) | user_pgprot; + protection_map[i] = __pgprot(v); + } + + mem_types[MT_LOW_VECTORS].prot_pte |= kern_pgprot; + mem_types[MT_HIGH_VECTORS].prot_pte |= kern_pgprot; + if (cpu_arch >= CPU_ARCH_ARMv5) { - mem_types[MT_LOW_VECTORS].prot_pte |= cp->pte & PTE_CACHEABLE; - mem_types[MT_HIGH_VECTORS].prot_pte |= cp->pte & PTE_CACHEABLE; +#ifndef CONFIG_SMP + /* + * Only use write-through for non-SMP systems + */ + mem_types[MT_LOW_VECTORS].prot_pte &= ~L_PTE_BUFFERABLE; + mem_types[MT_HIGH_VECTORS].prot_pte &= ~L_PTE_BUFFERABLE; +#endif } else { - mem_types[MT_LOW_VECTORS].prot_pte |= cp->pte; - mem_types[MT_HIGH_VECTORS].prot_pte |= cp->pte; mem_types[MT_MINICLEAN].prot_sect &= ~PMD_SECT_TEX(1); } + pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | + L_PTE_DIRTY | L_PTE_WRITE | + L_PTE_EXEC | kern_pgprot); + mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd; mem_types[MT_ROM].prot_sect |= cp->pmd; - for (i = 0; i < 16; i++) { - unsigned long v = pgprot_val(protection_map[i]); - v = (v & ~(PTE_BUFFERABLE|PTE_CACHEABLE)) | user_pgprot; - protection_map[i] = __pgprot(v); - } - - pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | - L_PTE_DIRTY | L_PTE_WRITE | - L_PTE_EXEC | cp->pte); - switch (cp->pmd) { case PMD_SECT_WT: mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_WT; diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 9bb5fff406fb..92f3ca31b7b9 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -12,6 +12,7 @@ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/asm-offsets.h> +#include <asm/hardware/arm_scu.h> #include <asm/procinfo.h> #include <asm/pgtable.h> @@ -112,6 +113,9 @@ ENTRY(cpu_v6_dcache_clean_area) ENTRY(cpu_v6_switch_mm) mov r2, #0 ldr r1, [r1, #MM_CONTEXT_ID] @ get mm->context.id +#ifdef CONFIG_SMP + orr r0, r0, #2 @ set shared pgtable +#endif mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB mcr p15, 0, r2, c7, c10, 4 @ drain write buffer mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 @@ -140,7 +144,7 @@ ENTRY(cpu_v6_switch_mm) ENTRY(cpu_v6_set_pte) str r1, [r0], #-2048 @ linux version - bic r2, r1, #0x000007f0 + bic r2, r1, #0x000003f0 bic r2, r2, #0x00000003 orr r2, r2, #PTE_EXT_AP0 | 2 @@ -191,6 +195,23 @@ cpu_v6_name: * - cache type register is implemented */ __v6_setup: +#ifdef CONFIG_SMP + /* Set up the SCU on core 0 only */ + mrc p15, 0, r0, c0, c0, 5 @ CPU core number + ands r0, r0, #15 + moveq r0, #0x10000000 @ SCU_BASE + orreq r0, r0, #0x00100000 + ldreq r5, [r0, #SCU_CTRL] + orreq r5, r5, #1 + streq r5, [r0, #SCU_CTRL] + +#ifndef CONFIG_CPU_DCACHE_DISABLE + mrc p15, 0, r0, c1, c0, 1 @ Enable SMP/nAMP mode + orr r0, r0, #0x20 + mcr p15, 0, r0, c1, c0, 1 +#endif +#endif + mov r0, #0 mcr p15, 0, r0, c7, c14, 0 @ clean+invalidate D cache mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache @@ -198,6 +219,9 @@ __v6_setup: mcr p15, 0, r0, c7, c10, 4 @ drain write buffer mcr p15, 0, r0, c8, c7, 0 @ invalidate I + D TLBs mcr p15, 0, r0, c2, c0, 2 @ TTB control register +#ifdef CONFIG_SMP + orr r4, r4, #2 @ set shared pgtable +#endif mcr p15, 0, r4, c2, c0, 1 @ load TTB1 #ifdef CONFIG_VFP mrc p15, 0, r0, c1, c0, 2 diff --git a/arch/arm/nwfpe/fpa11.h b/arch/arm/nwfpe/fpa11.h index 9677ae8448e8..da4c616b6c49 100644 --- a/arch/arm/nwfpe/fpa11.h +++ b/arch/arm/nwfpe/fpa11.h @@ -60,7 +60,7 @@ typedef union tagFPREG { #ifdef CONFIG_FPE_NWFPE_XP floatx80 fExtended; #else - int padding[3]; + u32 padding[3]; #endif } FPREG; diff --git a/arch/arm/nwfpe/fpa11_cpdt.c b/arch/arm/nwfpe/fpa11_cpdt.c index b0db5cbcc3b1..32859fa8dcfc 100644 --- a/arch/arm/nwfpe/fpa11_cpdt.c +++ b/arch/arm/nwfpe/fpa11_cpdt.c @@ -59,8 +59,13 @@ static inline void loadExtended(const unsigned int Fn, const unsigned int __user p = (unsigned int *) &fpa11->fpreg[Fn].fExtended; fpa11->fType[Fn] = typeExtended; get_user(p[0], &pMem[0]); /* sign & exponent */ +#ifdef __ARMEB__ + get_user(p[1], &pMem[1]); /* ms bits */ + get_user(p[2], &pMem[2]); /* ls bits */ +#else get_user(p[1], &pMem[2]); /* ls bits */ get_user(p[2], &pMem[1]); /* ms bits */ +#endif } #endif @@ -177,8 +182,13 @@ static inline void storeExtended(const unsigned int Fn, unsigned int __user *pMe } put_user(val.i[0], &pMem[0]); /* sign & exp */ +#ifdef __ARMEB__ + put_user(val.i[1], &pMem[1]); /* msw */ + put_user(val.i[2], &pMem[2]); +#else put_user(val.i[1], &pMem[2]); put_user(val.i[2], &pMem[1]); /* msw */ +#endif } #endif diff --git a/arch/arm/nwfpe/fpopcode.c b/arch/arm/nwfpe/fpopcode.c index 4c9f5703148c..67ff2ab08ea0 100644 --- a/arch/arm/nwfpe/fpopcode.c +++ b/arch/arm/nwfpe/fpopcode.c @@ -29,14 +29,14 @@ #ifdef CONFIG_FPE_NWFPE_XP const floatx80 floatx80Constant[] = { - {0x0000, 0x0000000000000000ULL}, /* extended 0.0 */ - {0x3fff, 0x8000000000000000ULL}, /* extended 1.0 */ - {0x4000, 0x8000000000000000ULL}, /* extended 2.0 */ - {0x4000, 0xc000000000000000ULL}, /* extended 3.0 */ - {0x4001, 0x8000000000000000ULL}, /* extended 4.0 */ - {0x4001, 0xa000000000000000ULL}, /* extended 5.0 */ - {0x3ffe, 0x8000000000000000ULL}, /* extended 0.5 */ - {0x4002, 0xa000000000000000ULL} /* extended 10.0 */ + { .high = 0x0000, .low = 0x0000000000000000ULL},/* extended 0.0 */ + { .high = 0x3fff, .low = 0x8000000000000000ULL},/* extended 1.0 */ + { .high = 0x4000, .low = 0x8000000000000000ULL},/* extended 2.0 */ + { .high = 0x4000, .low = 0xc000000000000000ULL},/* extended 3.0 */ + { .high = 0x4001, .low = 0x8000000000000000ULL},/* extended 4.0 */ + { .high = 0x4001, .low = 0xa000000000000000ULL},/* extended 5.0 */ + { .high = 0x3ffe, .low = 0x8000000000000000ULL},/* extended 0.5 */ + { .high = 0x4002, .low = 0xa000000000000000ULL},/* extended 10.0 */ }; #endif diff --git a/arch/arm/nwfpe/softfloat-specialize b/arch/arm/nwfpe/softfloat-specialize index acf409144763..d4a4c8e06635 100644 --- a/arch/arm/nwfpe/softfloat-specialize +++ b/arch/arm/nwfpe/softfloat-specialize @@ -332,6 +332,7 @@ static floatx80 commonNaNToFloatx80( commonNaNT a ) z.low = LIT64( 0xC000000000000000 ) | ( a.high>>1 ); z.high = ( ( (bits16) a.sign )<<15 ) | 0x7FFF; + z.__padding = 0; return z; } diff --git a/arch/arm/nwfpe/softfloat.c b/arch/arm/nwfpe/softfloat.c index f9f049132a17..0f9656e482ba 100644 --- a/arch/arm/nwfpe/softfloat.c +++ b/arch/arm/nwfpe/softfloat.c @@ -531,6 +531,7 @@ INLINE floatx80 packFloatx80( flag zSign, int32 zExp, bits64 zSig ) z.low = zSig; z.high = ( ( (bits16) zSign )<<15 ) + zExp; + z.__padding = 0; return z; } @@ -2831,6 +2832,7 @@ static floatx80 subFloatx80Sigs( struct roundingData *roundData, floatx80 a, flo roundData->exception |= float_flag_invalid; z.low = floatx80_default_nan_low; z.high = floatx80_default_nan_high; + z.__padding = 0; return z; } if ( aExp == 0 ) { @@ -2950,6 +2952,7 @@ floatx80 floatx80_mul( struct roundingData *roundData, floatx80 a, floatx80 b ) roundData->exception |= float_flag_invalid; z.low = floatx80_default_nan_low; z.high = floatx80_default_nan_high; + z.__padding = 0; return z; } return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); @@ -3015,6 +3018,7 @@ floatx80 floatx80_div( struct roundingData *roundData, floatx80 a, floatx80 b ) roundData->exception |= float_flag_invalid; z.low = floatx80_default_nan_low; z.high = floatx80_default_nan_high; + z.__padding = 0; return z; } roundData->exception |= float_flag_divbyzero; @@ -3093,6 +3097,7 @@ floatx80 floatx80_rem( struct roundingData *roundData, floatx80 a, floatx80 b ) roundData->exception |= float_flag_invalid; z.low = floatx80_default_nan_low; z.high = floatx80_default_nan_high; + z.__padding = 0; return z; } normalizeFloatx80Subnormal( bSig, &bExp, &bSig ); @@ -3184,6 +3189,7 @@ floatx80 floatx80_sqrt( struct roundingData *roundData, floatx80 a ) roundData->exception |= float_flag_invalid; z.low = floatx80_default_nan_low; z.high = floatx80_default_nan_high; + z.__padding = 0; return z; } if ( aExp == 0 ) { diff --git a/arch/arm/nwfpe/softfloat.h b/arch/arm/nwfpe/softfloat.h index 14151700b6b2..978c699673c6 100644 --- a/arch/arm/nwfpe/softfloat.h +++ b/arch/arm/nwfpe/softfloat.h @@ -51,11 +51,17 @@ input or output the `floatx80' type will be defined. Software IEC/IEEE floating-point types. ------------------------------------------------------------------------------- */ -typedef unsigned long int float32; -typedef unsigned long long float64; +typedef u32 float32; +typedef u64 float64; typedef struct { - unsigned short high; - unsigned long long low; +#ifdef __ARMEB__ + u16 __padding; + u16 high; +#else + u16 high; + u16 __padding; +#endif + u64 low; } floatx80; /* diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c index caa9f7711343..871366b83b3f 100644 --- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -377,10 +377,9 @@ acpi_cpufreq_cpu_init ( arg0.buffer.length = 12; arg0.buffer.pointer = (u8 *) arg0_buf; - data = kmalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL); + data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL); if (!data) return (-ENOMEM); - memset(data, 0, sizeof(struct cpufreq_acpi_io)); acpi_io_data[cpu] = data; diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k7.c b/arch/i386/kernel/cpu/cpufreq/powernow-k7.c index 73a5dc5b26b8..edcd626001da 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k7.c +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k7.c @@ -171,10 +171,9 @@ static int get_ranges (unsigned char *pst) unsigned int speed; u8 fid, vid; - powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table) * (number_scales + 1)), GFP_KERNEL); + powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) * (number_scales + 1)), GFP_KERNEL); if (!powernow_table) return -ENOMEM; - memset(powernow_table, 0, (sizeof(struct cpufreq_frequency_table) * (number_scales + 1))); for (j=0 ; j < number_scales; j++) { fid = *pst++; @@ -305,16 +304,13 @@ static int powernow_acpi_init(void) goto err0; } - acpi_processor_perf = kmalloc(sizeof(struct acpi_processor_performance), + acpi_processor_perf = kzalloc(sizeof(struct acpi_processor_performance), GFP_KERNEL); - if (!acpi_processor_perf) { retval = -ENOMEM; goto err0; } - memset(acpi_processor_perf, 0, sizeof(struct acpi_processor_performance)); - if (acpi_processor_register_performance(acpi_processor_perf, 0)) { retval = -EIO; goto err1; @@ -337,14 +333,12 @@ static int powernow_acpi_init(void) goto err2; } - powernow_table = kmalloc((number_scales + 1) * (sizeof(struct cpufreq_frequency_table)), GFP_KERNEL); + powernow_table = kzalloc((number_scales + 1) * (sizeof(struct cpufreq_frequency_table)), GFP_KERNEL); if (!powernow_table) { retval = -ENOMEM; goto err2; } - memset(powernow_table, 0, ((number_scales + 1) * sizeof(struct cpufreq_frequency_table))); - pc.val = (unsigned long) acpi_processor_perf->states[0].control; for (i = 0; i < number_scales; i++) { u8 fid, vid; diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c index 2d5c9adba0cd..68a1fc87f4ca 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c @@ -462,7 +462,6 @@ static int check_supported_cpu(unsigned int cpu) oldmask = current->cpus_allowed; set_cpus_allowed(current, cpumask_of_cpu(cpu)); - schedule(); if (smp_processor_id() != cpu) { printk(KERN_ERR "limiting to cpu %u failed\n", cpu); @@ -497,9 +496,7 @@ static int check_supported_cpu(unsigned int cpu) out: set_cpus_allowed(current, oldmask); - schedule(); return rc; - } static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, u8 maxvid) @@ -913,7 +910,6 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi /* only run on specific CPU from here on */ oldmask = current->cpus_allowed; set_cpus_allowed(current, cpumask_of_cpu(pol->cpu)); - schedule(); if (smp_processor_id() != pol->cpu) { printk(KERN_ERR "limiting to cpu %u failed\n", pol->cpu); @@ -968,8 +964,6 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi err_out: set_cpus_allowed(current, oldmask); - schedule(); - return ret; } @@ -991,12 +985,11 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol) if (!check_supported_cpu(pol->cpu)) return -ENODEV; - data = kmalloc(sizeof(struct powernow_k8_data), GFP_KERNEL); + data = kzalloc(sizeof(struct powernow_k8_data), GFP_KERNEL); if (!data) { printk(KERN_ERR PFX "unable to alloc powernow_k8_data"); return -ENOMEM; } - memset(data,0,sizeof(struct powernow_k8_data)); data->cpu = pol->cpu; @@ -1026,7 +1019,6 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol) /* only run on specific CPU from here on */ oldmask = current->cpus_allowed; set_cpus_allowed(current, cpumask_of_cpu(pol->cpu)); - schedule(); if (smp_processor_id() != pol->cpu) { printk(KERN_ERR "limiting to cpu %u failed\n", pol->cpu); @@ -1045,7 +1037,6 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol) /* run on any CPU again */ set_cpus_allowed(current, oldmask); - schedule(); pol->governor = CPUFREQ_DEFAULT_GOVERNOR; pol->cpus = cpu_core_map[pol->cpu]; @@ -1080,7 +1071,6 @@ static int __init powernowk8_cpu_init(struct cpufreq_policy *pol) err_out: set_cpus_allowed(current, oldmask); - schedule(); powernow_k8_cpu_exit_acpi(data); kfree(data); @@ -1116,17 +1106,14 @@ static unsigned int powernowk8_get (unsigned int cpu) set_cpus_allowed(current, oldmask); return 0; } - preempt_disable(); - + if (query_current_values_with_pending_wait(data)) goto out; khz = find_khz_freq_from_fid(data->currfid); - out: - preempt_enable_no_resched(); +out: set_cpus_allowed(current, oldmask); - return khz; } diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c index 0ea010a7afb1..edb9873e27e3 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c @@ -423,12 +423,11 @@ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) } } - centrino_model[cpu] = kmalloc(sizeof(struct cpu_model), GFP_KERNEL); + centrino_model[cpu] = kzalloc(sizeof(struct cpu_model), GFP_KERNEL); if (!centrino_model[cpu]) { result = -ENOMEM; goto err_unreg; } - memset(centrino_model[cpu], 0, sizeof(struct cpu_model)); centrino_model[cpu]->model_name=NULL; centrino_model[cpu]->max_freq = p.states[0].core_frequency * 1000; diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 9f2093c1f44b..d4de8a4814be 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/arch/sparc/Kconfig b/arch/sparc/Kconfig index 6537445dac0e..3cfb8be3ff6d 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -201,6 +201,14 @@ config SUN_OPENPROMFS Only choose N if you know in advance that you will not need to modify OpenPROM settings on the running system. +config SPARC_LED + tristate "Sun4m LED driver" + help + This driver toggles the front-panel LED on sun4m systems + in a user-specifyable manner. It's state can be probed + by reading /proc/led and it's blinking mode can be changed + via writes to /proc/led + source "fs/Kconfig.binfmt" config SUNOS_EMUL diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile index 3d22ba2af01c..1b83e21841b5 100644 --- a/arch/sparc/kernel/Makefile +++ b/arch/sparc/kernel/Makefile @@ -21,6 +21,7 @@ obj-$(CONFIG_SUN_AUXIO) += auxio.o obj-$(CONFIG_PCI) += ebus.o obj-$(CONFIG_SUN_PM) += apc.o pmc.o obj-$(CONFIG_MODULES) += module.o sparc_ksyms.o +obj-$(CONFIG_SPARC_LED) += led.o ifdef CONFIG_SUNOS_EMUL obj-y += sys_sunos.o sunos_ioctl.o diff --git a/arch/sparc/kernel/led.c b/arch/sparc/kernel/led.c new file mode 100644 index 000000000000..2a3afca453c9 --- /dev/null +++ b/arch/sparc/kernel/led.c @@ -0,0 +1,139 @@ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/string.h> + +#include <asm/auxio.h> + +#define LED_MAX_LENGTH 8 /* maximum chars written to proc file */ + +static inline void led_toggle(void) +{ + unsigned char val = get_auxio(); + unsigned char on, off; + + if (val & AUXIO_LED) { + on = 0; + off = AUXIO_LED; + } else { + on = AUXIO_LED; + off = 0; + } + + set_auxio(on, off); +} + +static struct timer_list led_blink_timer; + +static void led_blink(unsigned long timeout) +{ + led_toggle(); + + /* reschedule */ + if (!timeout) { /* blink according to load */ + led_blink_timer.expires = jiffies + + ((1 + (avenrun[0] >> FSHIFT)) * HZ); + led_blink_timer.data = 0; + } else { /* blink at user specified interval */ + led_blink_timer.expires = jiffies + (timeout * HZ); + led_blink_timer.data = timeout; + } + add_timer(&led_blink_timer); +} + +static int led_read_proc(char *buf, char **start, off_t offset, int count, + int *eof, void *data) +{ + int len = 0; + + if (get_auxio() & AUXIO_LED) + len = sprintf(buf, "on\n"); + else + len = sprintf(buf, "off\n"); + + return len; +} + +static int led_write_proc(struct file *file, const char *buffer, + unsigned long count, void *data) +{ + char *buf = NULL; + + if (count > LED_MAX_LENGTH) + count = LED_MAX_LENGTH; + + buf = kmalloc(sizeof(char) * (count + 1), GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, buffer, count)) { + kfree(buf); + return -EFAULT; + } + + buf[count] = '\0'; + + /* work around \n when echo'ing into proc */ + if (buf[count - 1] == '\n') + buf[count - 1] = '\0'; + + /* before we change anything we want to stop any running timers, + * otherwise calls such as on will have no persistent effect + */ + del_timer_sync(&led_blink_timer); + + if (!strcmp(buf, "on")) { + auxio_set_led(AUXIO_LED_ON); + } else if (!strcmp(buf, "toggle")) { + led_toggle(); + } else if ((*buf > '0') && (*buf <= '9')) { + led_blink(simple_strtoul(buf, NULL, 10)); + } else if (!strcmp(buf, "load")) { + led_blink(0); + } else { + auxio_set_led(AUXIO_LED_OFF); + } + + kfree(buf); + + return count; +} + +static struct proc_dir_entry *led; + +#define LED_VERSION "0.1" + +static int __init led_init(void) +{ + init_timer(&led_blink_timer); + led_blink_timer.function = led_blink; + + led = create_proc_entry("led", 0, NULL); + if (!led) + return -ENOMEM; + + led->read_proc = led_read_proc; /* reader function */ + led->write_proc = led_write_proc; /* writer function */ + led->owner = THIS_MODULE; + + printk(KERN_INFO + "led: version %s, Lars Kotthoff <metalhead@metalhead.ws>\n", + LED_VERSION); + + return 0; +} + +static void __exit led_exit(void) +{ + remove_proc_entry("led", NULL); + del_timer_sync(&led_blink_timer); +} + +module_init(led_init); +module_exit(led_exit); + +MODULE_AUTHOR("Lars Kotthoff <metalhead@metalhead.ws>"); +MODULE_DESCRIPTION("Provides control of the front LED on SPARC systems."); +MODULE_LICENSE("GPL"); +MODULE_VERSION(LED_VERSION); diff --git a/arch/sparc/kernel/sunos_ioctl.c b/arch/sparc/kernel/sunos_ioctl.c index df1c0b31a930..a6ba3d26222c 100644 --- a/arch/sparc/kernel/sunos_ioctl.c +++ b/arch/sparc/kernel/sunos_ioctl.c @@ -23,7 +23,6 @@ #include <linux/smp_lock.h> #include <linux/syscalls.h> #include <linux/file.h> -#include <asm/kbio.h> #if 0 extern char sunkbd_type; diff --git a/arch/sparc64/kernel/ioctl32.c b/arch/sparc64/kernel/ioctl32.c index e6a00325075a..92e26304de90 100644 --- a/arch/sparc64/kernel/ioctl32.c +++ b/arch/sparc64/kernel/ioctl32.c @@ -11,33 +11,14 @@ #define INCLUDES #include "compat_ioctl.c" -#include <linux/ncp_fs.h> #include <linux/syscalls.h> #include <asm/fbio.h> -#include <asm/kbio.h> -#include <asm/vuid_event.h> -#include <asm/envctrl.h> -#include <asm/display7seg.h> -#include <asm/openpromio.h> -#include <asm/audioio.h> -#include <asm/watchdog.h> /* Use this to get at 32-bit user passed pointers. * See sys_sparc32.c for description about it. */ #define A(__x) compat_ptr(__x) -static __inline__ void *alloc_user_space(long len) -{ - struct pt_regs *regs = current_thread_info()->kregs; - unsigned long usp = regs->u_regs[UREG_I6]; - - if (!(test_thread_flag(TIF_32BIT))) - usp += STACK_BIAS; - - return (void *) (usp - len); -} - #define CODE #include "compat_ioctl.c" @@ -111,357 +92,6 @@ static int fbiogscursor(unsigned int fd, unsigned int cmd, unsigned long arg) return sys_ioctl (fd, FBIOSCURSOR, (unsigned long)p); } -#if defined(CONFIG_DRM) || defined(CONFIG_DRM_MODULE) -/* This really belongs in include/linux/drm.h -DaveM */ -#include "../../../drivers/char/drm/drm.h" - -typedef struct drm32_version { - int version_major; /* Major version */ - int version_minor; /* Minor version */ - int version_patchlevel;/* Patch level */ - int name_len; /* Length of name buffer */ - u32 name; /* Name of driver */ - int date_len; /* Length of date buffer */ - u32 date; /* User-space buffer to hold date */ - int desc_len; /* Length of desc buffer */ - u32 desc; /* User-space buffer to hold desc */ -} drm32_version_t; -#define DRM32_IOCTL_VERSION DRM_IOWR(0x00, drm32_version_t) - -static int drm32_version(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - drm32_version_t __user *uversion = (drm32_version_t __user *)arg; - drm_version_t __user *p = compat_alloc_user_space(sizeof(*p)); - compat_uptr_t addr; - int n; - int ret; - - if (clear_user(p, 3 * sizeof(int)) || - get_user(n, &uversion->name_len) || - put_user(n, &p->name_len) || - get_user(addr, &uversion->name) || - put_user(compat_ptr(addr), &p->name) || - get_user(n, &uversion->date_len) || - put_user(n, &p->date_len) || - get_user(addr, &uversion->date) || - put_user(compat_ptr(addr), &p->date) || - get_user(n, &uversion->desc_len) || - put_user(n, &p->desc_len) || - get_user(addr, &uversion->desc) || - put_user(compat_ptr(addr), &p->desc)) - return -EFAULT; - - ret = sys_ioctl(fd, DRM_IOCTL_VERSION, (unsigned long)p); - if (ret) - return ret; - - if (copy_in_user(uversion, p, 3 * sizeof(int)) || - get_user(n, &p->name_len) || - put_user(n, &uversion->name_len) || - get_user(n, &p->date_len) || - put_user(n, &uversion->date_len) || - get_user(n, &p->desc_len) || - put_user(n, &uversion->desc_len)) - return -EFAULT; - - return 0; -} - -typedef struct drm32_unique { - int unique_len; /* Length of unique */ - u32 unique; /* Unique name for driver instantiation */ -} drm32_unique_t; -#define DRM32_IOCTL_GET_UNIQUE DRM_IOWR(0x01, drm32_unique_t) -#define DRM32_IOCTL_SET_UNIQUE DRM_IOW( 0x10, drm32_unique_t) - -static int drm32_getsetunique(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - drm32_unique_t __user *uarg = (drm32_unique_t __user *)arg; - drm_unique_t __user *p = compat_alloc_user_space(sizeof(*p)); - compat_uptr_t addr; - int n; - int ret; - - if (get_user(n, &uarg->unique_len) || - put_user(n, &p->unique_len) || - get_user(addr, &uarg->unique) || - put_user(compat_ptr(addr), &p->unique)) - return -EFAULT; - - if (cmd == DRM32_IOCTL_GET_UNIQUE) - ret = sys_ioctl (fd, DRM_IOCTL_GET_UNIQUE, (unsigned long)p); - else - ret = sys_ioctl (fd, DRM_IOCTL_SET_UNIQUE, (unsigned long)p); - - if (ret) - return ret; - - if (get_user(n, &p->unique_len) || put_user(n, &uarg->unique_len)) - return -EFAULT; - - return 0; -} - -typedef struct drm32_map { - u32 offset; /* Requested physical address (0 for SAREA)*/ - u32 size; /* Requested physical size (bytes) */ - drm_map_type_t type; /* Type of memory to map */ - drm_map_flags_t flags; /* Flags */ - u32 handle; /* User-space: "Handle" to pass to mmap */ - /* Kernel-space: kernel-virtual address */ - int mtrr; /* MTRR slot used */ - /* Private data */ -} drm32_map_t; -#define DRM32_IOCTL_ADD_MAP DRM_IOWR(0x15, drm32_map_t) - -static int drm32_addmap(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - drm32_map_t __user *uarg = (drm32_map_t __user *) arg; - drm_map_t karg; - mm_segment_t old_fs; - u32 tmp; - int ret; - - ret = get_user(karg.offset, &uarg->offset); - ret |= get_user(karg.size, &uarg->size); - ret |= get_user(karg.type, &uarg->type); - ret |= get_user(karg.flags, &uarg->flags); - ret |= get_user(tmp, &uarg->handle); - ret |= get_user(karg.mtrr, &uarg->mtrr); - if (ret) - return -EFAULT; - - karg.handle = (void *) (unsigned long) tmp; - - old_fs = get_fs(); - set_fs(KERNEL_DS); - ret = sys_ioctl(fd, DRM_IOCTL_ADD_MAP, (unsigned long) &karg); - set_fs(old_fs); - - if (!ret) { - ret = put_user(karg.offset, &uarg->offset); - ret |= put_user(karg.size, &uarg->size); - ret |= put_user(karg.type, &uarg->type); - ret |= put_user(karg.flags, &uarg->flags); - tmp = (u32) (long)karg.handle; - ret |= put_user(tmp, &uarg->handle); - ret |= put_user(karg.mtrr, &uarg->mtrr); - if (ret) - ret = -EFAULT; - } - - return ret; -} - -typedef struct drm32_buf_info { - int count; /* Entries in list */ - u32 list; /* (drm_buf_desc_t *) */ -} drm32_buf_info_t; -#define DRM32_IOCTL_INFO_BUFS DRM_IOWR(0x18, drm32_buf_info_t) - -static int drm32_info_bufs(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - drm32_buf_info_t __user *uarg = (drm32_buf_info_t __user *)arg; - drm_buf_info_t __user *p = compat_alloc_user_space(sizeof(*p)); - compat_uptr_t addr; - int n; - int ret; - - if (get_user(n, &uarg->count) || put_user(n, &p->count) || - get_user(addr, &uarg->list) || put_user(compat_ptr(addr), &p->list)) - return -EFAULT; - - ret = sys_ioctl(fd, DRM_IOCTL_INFO_BUFS, (unsigned long)p); - if (ret) - return ret; - - if (get_user(n, &p->count) || put_user(n, &uarg->count)) - return -EFAULT; - - return 0; -} - -typedef struct drm32_buf_free { - int count; - u32 list; /* (int *) */ -} drm32_buf_free_t; -#define DRM32_IOCTL_FREE_BUFS DRM_IOW( 0x1a, drm32_buf_free_t) - -static int drm32_free_bufs(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - drm32_buf_free_t __user *uarg = (drm32_buf_free_t __user *)arg; - drm_buf_free_t __user *p = compat_alloc_user_space(sizeof(*p)); - compat_uptr_t addr; - int n; - - if (get_user(n, &uarg->count) || put_user(n, &p->count) || - get_user(addr, &uarg->list) || put_user(compat_ptr(addr), &p->list)) - return -EFAULT; - - return sys_ioctl(fd, DRM_IOCTL_FREE_BUFS, (unsigned long)p); -} - -typedef struct drm32_buf_pub { - int idx; /* Index into master buflist */ - int total; /* Buffer size */ - int used; /* Amount of buffer in use (for DMA) */ - u32 address; /* Address of buffer (void *) */ -} drm32_buf_pub_t; - -typedef struct drm32_buf_map { - int count; /* Length of buflist */ - u32 virtual; /* Mmaped area in user-virtual (void *) */ - u32 list; /* Buffer information (drm_buf_pub_t *) */ -} drm32_buf_map_t; -#define DRM32_IOCTL_MAP_BUFS DRM_IOWR(0x19, drm32_buf_map_t) - -static int drm32_map_bufs(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - drm32_buf_map_t __user *uarg = (drm32_buf_map_t __user *)arg; - drm32_buf_pub_t __user *ulist; - drm_buf_map_t __user *arg64; - drm_buf_pub_t __user *list; - int orig_count, ret, i; - int n; - compat_uptr_t addr; - - if (get_user(orig_count, &uarg->count)) - return -EFAULT; - - arg64 = compat_alloc_user_space(sizeof(drm_buf_map_t) + - (size_t)orig_count * sizeof(drm_buf_pub_t)); - list = (void __user *)(arg64 + 1); - - if (put_user(orig_count, &arg64->count) || - put_user(list, &arg64->list) || - get_user(addr, &uarg->virtual) || - put_user(compat_ptr(addr), &arg64->virtual) || - get_user(addr, &uarg->list)) - return -EFAULT; - - ulist = compat_ptr(addr); - - for (i = 0; i < orig_count; i++) { - if (get_user(n, &ulist[i].idx) || - put_user(n, &list[i].idx) || - get_user(n, &ulist[i].total) || - put_user(n, &list[i].total) || - get_user(n, &ulist[i].used) || - put_user(n, &list[i].used) || - get_user(addr, &ulist[i].address) || - put_user(compat_ptr(addr), &list[i].address)) - return -EFAULT; - } - - ret = sys_ioctl(fd, DRM_IOCTL_MAP_BUFS, (unsigned long) arg64); - if (ret) - return ret; - - for (i = 0; i < orig_count; i++) { - void __user *p; - if (get_user(n, &list[i].idx) || - put_user(n, &ulist[i].idx) || - get_user(n, &list[i].total) || - put_user(n, &ulist[i].total) || - get_user(n, &list[i].used) || - put_user(n, &ulist[i].used) || - get_user(p, &list[i].address) || - put_user((unsigned long)p, &ulist[i].address)) - return -EFAULT; - } - - if (get_user(n, &arg64->count) || put_user(n, &uarg->count)) - return -EFAULT; - - return 0; -} - -typedef struct drm32_dma { - /* Indices here refer to the offset into - buflist in drm_buf_get_t. */ - int context; /* Context handle */ - int send_count; /* Number of buffers to send */ - u32 send_indices; /* List of handles to buffers (int *) */ - u32 send_sizes; /* Lengths of data to send (int *) */ - drm_dma_flags_t flags; /* Flags */ - int request_count; /* Number of buffers requested */ - int request_size; /* Desired size for buffers */ - u32 request_indices; /* Buffer information (int *) */ - u32 request_sizes; /* (int *) */ - int granted_count; /* Number of buffers granted */ -} drm32_dma_t; -#define DRM32_IOCTL_DMA DRM_IOWR(0x29, drm32_dma_t) - -/* RED PEN The DRM layer blindly dereferences the send/request - * index/size arrays even though they are userland - * pointers. -DaveM - */ -static int drm32_dma(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - drm32_dma_t __user *uarg = (drm32_dma_t __user *) arg; - drm_dma_t __user *p = compat_alloc_user_space(sizeof(*p)); - compat_uptr_t addr; - int ret; - - if (copy_in_user(p, uarg, 2 * sizeof(int)) || - get_user(addr, &uarg->send_indices) || - put_user(compat_ptr(addr), &p->send_indices) || - get_user(addr, &uarg->send_sizes) || - put_user(compat_ptr(addr), &p->send_sizes) || - copy_in_user(&p->flags, &uarg->flags, sizeof(drm_dma_flags_t)) || - copy_in_user(&p->request_count, &uarg->request_count, sizeof(int))|| - copy_in_user(&p->request_size, &uarg->request_size, sizeof(int)) || - get_user(addr, &uarg->request_indices) || - put_user(compat_ptr(addr), &p->request_indices) || - get_user(addr, &uarg->request_sizes) || - put_user(compat_ptr(addr), &p->request_sizes) || - copy_in_user(&p->granted_count, &uarg->granted_count, sizeof(int))) - return -EFAULT; - - ret = sys_ioctl(fd, DRM_IOCTL_DMA, (unsigned long)p); - if (ret) - return ret; - - if (copy_in_user(uarg, p, 2 * sizeof(int)) || - copy_in_user(&uarg->flags, &p->flags, sizeof(drm_dma_flags_t)) || - copy_in_user(&uarg->request_count, &p->request_count, sizeof(int))|| - copy_in_user(&uarg->request_size, &p->request_size, sizeof(int)) || - copy_in_user(&uarg->granted_count, &p->granted_count, sizeof(int))) - return -EFAULT; - - return 0; -} - -typedef struct drm32_ctx_res { - int count; - u32 contexts; /* (drm_ctx_t *) */ -} drm32_ctx_res_t; -#define DRM32_IOCTL_RES_CTX DRM_IOWR(0x26, drm32_ctx_res_t) - -static int drm32_res_ctx(unsigned int fd, unsigned int cmd, unsigned long arg) -{ - drm32_ctx_res_t __user *uarg = (drm32_ctx_res_t __user *) arg; - drm_ctx_res_t __user *p = compat_alloc_user_space(sizeof(*p)); - compat_uptr_t addr; - int ret; - - if (copy_in_user(p, uarg, sizeof(int)) || - get_user(addr, &uarg->contexts) || - put_user(compat_ptr(addr), &p->contexts)) - return -EFAULT; - - ret = sys_ioctl(fd, DRM_IOCTL_RES_CTX, (unsigned long)p); - if (ret) - return ret; - - if (copy_in_user(uarg, p, sizeof(int))) - return -EFAULT; - - return 0; -} - -#endif - typedef int (* ioctl32_handler_t)(unsigned int, unsigned int, unsigned long, struct file *); #define COMPATIBLE_IOCTL(cmd) HANDLE_IOCTL((cmd),sys_ioctl) @@ -485,103 +115,14 @@ COMPATIBLE_IOCTL(FBIOSCURPOS) COMPATIBLE_IOCTL(FBIOGCURPOS) COMPATIBLE_IOCTL(FBIOGCURMAX) /* Little k */ -COMPATIBLE_IOCTL(KIOCTYPE) -COMPATIBLE_IOCTL(KIOCLAYOUT) -COMPATIBLE_IOCTL(KIOCGTRANS) -COMPATIBLE_IOCTL(KIOCTRANS) -COMPATIBLE_IOCTL(KIOCCMD) -COMPATIBLE_IOCTL(KIOCSDIRECT) -COMPATIBLE_IOCTL(KIOCSLED) -COMPATIBLE_IOCTL(KIOCGLED) -COMPATIBLE_IOCTL(KIOCSRATE) -COMPATIBLE_IOCTL(KIOCGRATE) -COMPATIBLE_IOCTL(VUIDSFORMAT) -COMPATIBLE_IOCTL(VUIDGFORMAT) /* Little v, the video4linux ioctls */ COMPATIBLE_IOCTL(_IOR('p', 20, int[7])) /* RTCGET */ COMPATIBLE_IOCTL(_IOW('p', 21, int[7])) /* RTCSET */ -COMPATIBLE_IOCTL(ENVCTRL_RD_WARNING_TEMPERATURE) -COMPATIBLE_IOCTL(ENVCTRL_RD_SHUTDOWN_TEMPERATURE) -COMPATIBLE_IOCTL(ENVCTRL_RD_CPU_TEMPERATURE) -COMPATIBLE_IOCTL(ENVCTRL_RD_FAN_STATUS) -COMPATIBLE_IOCTL(ENVCTRL_RD_VOLTAGE_STATUS) -COMPATIBLE_IOCTL(ENVCTRL_RD_SCSI_TEMPERATURE) -COMPATIBLE_IOCTL(ENVCTRL_RD_ETHERNET_TEMPERATURE) -COMPATIBLE_IOCTL(ENVCTRL_RD_MTHRBD_TEMPERATURE) -COMPATIBLE_IOCTL(ENVCTRL_RD_CPU_VOLTAGE) -COMPATIBLE_IOCTL(ENVCTRL_RD_GLOBALADDRESS) -/* COMPATIBLE_IOCTL(D7SIOCRD) same value as ENVCTRL_RD_VOLTAGE_STATUS */ -COMPATIBLE_IOCTL(D7SIOCWR) -COMPATIBLE_IOCTL(D7SIOCTM) -/* OPENPROMIO, SunOS/Solaris only, the NetBSD one's have - * embedded pointers in the arg which we'd need to clean up... - */ -COMPATIBLE_IOCTL(OPROMGETOPT) -COMPATIBLE_IOCTL(OPROMSETOPT) -COMPATIBLE_IOCTL(OPROMNXTOPT) -COMPATIBLE_IOCTL(OPROMSETOPT2) -COMPATIBLE_IOCTL(OPROMNEXT) -COMPATIBLE_IOCTL(OPROMCHILD) -COMPATIBLE_IOCTL(OPROMGETPROP) -COMPATIBLE_IOCTL(OPROMNXTPROP) -COMPATIBLE_IOCTL(OPROMU2P) -COMPATIBLE_IOCTL(OPROMGETCONS) -COMPATIBLE_IOCTL(OPROMGETFBNAME) -COMPATIBLE_IOCTL(OPROMGETBOOTARGS) -COMPATIBLE_IOCTL(OPROMSETCUR) -COMPATIBLE_IOCTL(OPROMPCI2NODE) -COMPATIBLE_IOCTL(OPROMPATH2NODE) -/* Big L */ -COMPATIBLE_IOCTL(LOOP_SET_STATUS64) -COMPATIBLE_IOCTL(LOOP_GET_STATUS64) -/* Big A */ -COMPATIBLE_IOCTL(AUDIO_GETINFO) -COMPATIBLE_IOCTL(AUDIO_SETINFO) -COMPATIBLE_IOCTL(AUDIO_DRAIN) -COMPATIBLE_IOCTL(AUDIO_GETDEV) -COMPATIBLE_IOCTL(AUDIO_GETDEV_SUNOS) -COMPATIBLE_IOCTL(AUDIO_FLUSH) -COMPATIBLE_IOCTL(AUTOFS_IOC_EXPIRE_MULTI) -#if defined(CONFIG_DRM) || defined(CONFIG_DRM_MODULE) -COMPATIBLE_IOCTL(DRM_IOCTL_GET_MAGIC) -COMPATIBLE_IOCTL(DRM_IOCTL_IRQ_BUSID) -COMPATIBLE_IOCTL(DRM_IOCTL_AUTH_MAGIC) -COMPATIBLE_IOCTL(DRM_IOCTL_BLOCK) -COMPATIBLE_IOCTL(DRM_IOCTL_UNBLOCK) -COMPATIBLE_IOCTL(DRM_IOCTL_CONTROL) -COMPATIBLE_IOCTL(DRM_IOCTL_ADD_BUFS) -COMPATIBLE_IOCTL(DRM_IOCTL_MARK_BUFS) -COMPATIBLE_IOCTL(DRM_IOCTL_ADD_CTX) -COMPATIBLE_IOCTL(DRM_IOCTL_RM_CTX) -COMPATIBLE_IOCTL(DRM_IOCTL_MOD_CTX) -COMPATIBLE_IOCTL(DRM_IOCTL_GET_CTX) -COMPATIBLE_IOCTL(DRM_IOCTL_SWITCH_CTX) -COMPATIBLE_IOCTL(DRM_IOCTL_NEW_CTX) -COMPATIBLE_IOCTL(DRM_IOCTL_ADD_DRAW) -COMPATIBLE_IOCTL(DRM_IOCTL_RM_DRAW) -COMPATIBLE_IOCTL(DRM_IOCTL_LOCK) -COMPATIBLE_IOCTL(DRM_IOCTL_UNLOCK) -COMPATIBLE_IOCTL(DRM_IOCTL_FINISH) -#endif /* DRM */ -COMPATIBLE_IOCTL(WIOCSTART) -COMPATIBLE_IOCTL(WIOCSTOP) -COMPATIBLE_IOCTL(WIOCGSTAT) /* And these ioctls need translation */ /* Note SIOCRTMSG is no longer, so this is safe and * the user would have seen just an -EINVAL anyways. */ HANDLE_IOCTL(FBIOPUTCMAP32, fbiogetputcmap) HANDLE_IOCTL(FBIOGETCMAP32, fbiogetputcmap) HANDLE_IOCTL(FBIOSCURSOR32, fbiogscursor) -#if defined(CONFIG_DRM) || defined(CONFIG_DRM_MODULE) -HANDLE_IOCTL(DRM32_IOCTL_VERSION, drm32_version) -HANDLE_IOCTL(DRM32_IOCTL_GET_UNIQUE, drm32_getsetunique) -HANDLE_IOCTL(DRM32_IOCTL_SET_UNIQUE, drm32_getsetunique) -HANDLE_IOCTL(DRM32_IOCTL_ADD_MAP, drm32_addmap) -HANDLE_IOCTL(DRM32_IOCTL_INFO_BUFS, drm32_info_bufs) -HANDLE_IOCTL(DRM32_IOCTL_FREE_BUFS, drm32_free_bufs) -HANDLE_IOCTL(DRM32_IOCTL_MAP_BUFS, drm32_map_bufs) -HANDLE_IOCTL(DRM32_IOCTL_DMA, drm32_dma) -HANDLE_IOCTL(DRM32_IOCTL_RES_CTX, drm32_res_ctx) -#endif /* DRM */ #if 0 HANDLE_IOCTL(RTC32_IRQP_READ, do_rtc_ioctl) HANDLE_IOCTL(RTC32_IRQP_SET, do_rtc_ioctl) diff --git a/arch/sparc64/kernel/setup.c b/arch/sparc64/kernel/setup.c index c1f34237cdf2..bf1849dd9c49 100644 --- a/arch/sparc64/kernel/setup.c +++ b/arch/sparc64/kernel/setup.c @@ -154,6 +154,7 @@ int prom_callback(long *args) pud_t *pudp; pmd_t *pmdp; pte_t *ptep; + pte_t pte; for_each_process(p) { mm = p->mm; @@ -178,8 +179,9 @@ int prom_callback(long *args) * being called from inside OBP. */ ptep = pte_offset_map(pmdp, va); - if (pte_present(*ptep)) { - tte = pte_val(*ptep); + pte = *ptep; + if (pte_present(pte)) { + tte = pte_val(pte); res = PROM_TRUE; } pte_unmap(ptep); @@ -218,6 +220,7 @@ int prom_callback(long *args) pud_t *pudp; pmd_t *pmdp; pte_t *ptep; + pte_t pte; int error; if ((va >= LOW_OBP_ADDRESS) && (va < HI_OBP_ADDRESS)) { @@ -240,8 +243,9 @@ int prom_callback(long *args) * being called from inside OBP. */ ptep = pte_offset_kernel(pmdp, va); - if (pte_present(*ptep)) { - tte = pte_val(*ptep); + pte = *ptep; + if (pte_present(pte)) { + tte = pte_val(pte); res = PROM_TRUE; } goto done; diff --git a/arch/sparc64/kernel/signal32.c b/arch/sparc64/kernel/signal32.c index aecccd0df1d1..009a86e5ded4 100644 --- a/arch/sparc64/kernel/signal32.c +++ b/arch/sparc64/kernel/signal32.c @@ -863,6 +863,7 @@ static void new_setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, pud_t *pudp = pud_offset(pgdp, address); pmd_t *pmdp = pmd_offset(pudp, address); pte_t *ptep; + pte_t pte; regs->u_regs[UREG_I7] = (unsigned long) (&(sf->insns[0]) - 2); @@ -873,9 +874,10 @@ static void new_setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, preempt_disable(); ptep = pte_offset_map(pmdp, address); - if (pte_present(*ptep)) { + pte = *ptep; + if (pte_present(pte)) { unsigned long page = (unsigned long) - page_address(pte_page(*ptep)); + page_address(pte_page(pte)); wmb(); __asm__ __volatile__("flush %0 + %1" diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c index b137fd63f5e1..5d90ee9aebf1 100644 --- a/arch/sparc64/kernel/smp.c +++ b/arch/sparc64/kernel/smp.c @@ -839,43 +839,29 @@ void smp_flush_tlb_all(void) * questionable (in theory the big win for threads is the massive sharing of * address space state across processors). */ + +/* This currently is only used by the hugetlb arch pre-fault + * hook on UltraSPARC-III+ and later when changing the pagesize + * bits of the context register for an address space. + */ void smp_flush_tlb_mm(struct mm_struct *mm) { - /* - * This code is called from two places, dup_mmap and exit_mmap. In the - * former case, we really need a flush. In the later case, the callers - * are single threaded exec_mmap (really need a flush), multithreaded - * exec_mmap case (do not need to flush, since the caller gets a new - * context via activate_mm), and all other callers of mmput() whence - * the flush can be optimized since the associated threads are dead and - * the mm is being torn down (__exit_mm and other mmput callers) or the - * owning thread is dissociating itself from the mm. The - * (atomic_read(&mm->mm_users) == 0) check ensures real work is done - * for single thread exec and dup_mmap cases. An alternate check might - * have been (current->mm != mm). - * Kanoj Sarcar - */ - if (atomic_read(&mm->mm_users) == 0) - return; - - { - u32 ctx = CTX_HWBITS(mm->context); - int cpu = get_cpu(); + u32 ctx = CTX_HWBITS(mm->context); + int cpu = get_cpu(); - if (atomic_read(&mm->mm_users) == 1) { - mm->cpu_vm_mask = cpumask_of_cpu(cpu); - goto local_flush_and_out; - } + if (atomic_read(&mm->mm_users) == 1) { + mm->cpu_vm_mask = cpumask_of_cpu(cpu); + goto local_flush_and_out; + } - smp_cross_call_masked(&xcall_flush_tlb_mm, - ctx, 0, 0, - mm->cpu_vm_mask); + smp_cross_call_masked(&xcall_flush_tlb_mm, + ctx, 0, 0, + mm->cpu_vm_mask); - local_flush_and_out: - __flush_tlb_mm(ctx, SECONDARY_CONTEXT); +local_flush_and_out: + __flush_tlb_mm(ctx, SECONDARY_CONTEXT); - put_cpu(); - } + put_cpu(); } void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long *vaddrs) @@ -883,34 +869,13 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long u32 ctx = CTX_HWBITS(mm->context); int cpu = get_cpu(); - if (mm == current->active_mm && atomic_read(&mm->mm_users) == 1) { + if (mm == current->active_mm && atomic_read(&mm->mm_users) == 1) mm->cpu_vm_mask = cpumask_of_cpu(cpu); - goto local_flush_and_out; - } else { - /* This optimization is not valid. Normally - * we will be holding the page_table_lock, but - * there is an exception which is copy_page_range() - * when forking. The lock is held during the individual - * page table updates in the parent, but not at the - * top level, which is where we are invoked. - */ - if (0) { - cpumask_t this_cpu_mask = cpumask_of_cpu(cpu); - - /* By virtue of running under the mm->page_table_lock, - * and mmu_context.h:switch_mm doing the same, the - * following operation is safe. - */ - if (cpus_equal(mm->cpu_vm_mask, this_cpu_mask)) - goto local_flush_and_out; - } - } - - smp_cross_call_masked(&xcall_flush_tlb_pending, - ctx, nr, (unsigned long) vaddrs, - mm->cpu_vm_mask); + else + smp_cross_call_masked(&xcall_flush_tlb_pending, + ctx, nr, (unsigned long) vaddrs, + mm->cpu_vm_mask); -local_flush_and_out: __flush_tlb_pending(ctx, nr, vaddrs); put_cpu(); diff --git a/arch/sparc64/kernel/sunos_ioctl32.c b/arch/sparc64/kernel/sunos_ioctl32.c index 7654b8a7f03a..3f619ead22cc 100644 --- a/arch/sparc64/kernel/sunos_ioctl32.c +++ b/arch/sparc64/kernel/sunos_ioctl32.c @@ -24,7 +24,6 @@ #include <linux/smp_lock.h> #include <linux/syscalls.h> #include <linux/compat.h> -#include <asm/kbio.h> #define SUNOS_NR_OPEN 256 diff --git a/arch/sparc64/kernel/time.c b/arch/sparc64/kernel/time.c index 38c5525087a2..459c8fbe02b4 100644 --- a/arch/sparc64/kernel/time.c +++ b/arch/sparc64/kernel/time.c @@ -60,17 +60,6 @@ static void __iomem *mstk48t59_regs; static int set_rtc_mmss(unsigned long); -static __init unsigned long dummy_get_tick(void) -{ - return 0; -} - -static __initdata struct sparc64_tick_ops dummy_tick_ops = { - .get_tick = dummy_get_tick, -}; - -struct sparc64_tick_ops *tick_ops __read_mostly = &dummy_tick_ops; - #define TICK_PRIV_BIT (1UL << 63) #ifdef CONFIG_SMP @@ -200,6 +189,8 @@ static struct sparc64_tick_ops tick_operations __read_mostly = { .softint_mask = 1UL << 0, }; +struct sparc64_tick_ops *tick_ops __read_mostly = &tick_operations; + static void stick_init_tick(unsigned long offset) { tick_disable_protection(); diff --git a/drivers/char/agp/ali-agp.c b/drivers/char/agp/ali-agp.c index b02fc2267159..ba54b5872578 100644 --- a/drivers/char/agp/ali-agp.c +++ b/drivers/char/agp/ali-agp.c @@ -389,6 +389,7 @@ static struct pci_device_id agp_ali_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_ali_pci_table); static struct pci_driver agp_ali_pci_driver = { + .owner = THIS_MODULE, .name = "agpgart-ali", .id_table = agp_ali_pci_table, .probe = agp_ali_probe, diff --git a/drivers/char/agp/amd-k7-agp.c b/drivers/char/agp/amd-k7-agp.c index 3a41672e4d66..40fcd88b2cea 100644 --- a/drivers/char/agp/amd-k7-agp.c +++ b/drivers/char/agp/amd-k7-agp.c @@ -94,19 +94,16 @@ static int amd_create_gatt_pages(int nr_tables) int retval = 0; int i; - tables = kmalloc((nr_tables + 1) * sizeof(struct amd_page_map *), - GFP_KERNEL); + tables = kzalloc((nr_tables + 1) * sizeof(struct amd_page_map *),GFP_KERNEL); if (tables == NULL) return -ENOMEM; - memset (tables, 0, sizeof(struct amd_page_map *) * (nr_tables + 1)); for (i = 0; i < nr_tables; i++) { - entry = kmalloc(sizeof(struct amd_page_map), GFP_KERNEL); + entry = kzalloc(sizeof(struct amd_page_map), GFP_KERNEL); if (entry == NULL) { retval = -ENOMEM; break; } - memset (entry, 0, sizeof(struct amd_page_map)); tables[i] = entry; retval = amd_create_page_map(entry); if (retval != 0) @@ -518,6 +515,7 @@ static struct pci_device_id agp_amdk7_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_amdk7_pci_table); static struct pci_driver agp_amdk7_pci_driver = { + .owner = THIS_MODULE, .name = "agpgart-amdk7", .id_table = agp_amdk7_pci_table, .probe = agp_amdk7_probe, diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c index 78ce98a69f37..8f748fddca94 100644 --- a/drivers/char/agp/amd64-agp.c +++ b/drivers/char/agp/amd64-agp.c @@ -703,6 +703,7 @@ static struct pci_device_id agp_amd64_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_amd64_pci_table); static struct pci_driver agp_amd64_pci_driver = { + .owner = THIS_MODULE, .name = "agpgart-amd64", .id_table = agp_amd64_pci_table, .probe = agp_amd64_probe, diff --git a/drivers/char/agp/ati-agp.c b/drivers/char/agp/ati-agp.c index 0b6e72642d6e..fbd415565463 100644 --- a/drivers/char/agp/ati-agp.c +++ b/drivers/char/agp/ati-agp.c @@ -118,14 +118,12 @@ static int ati_create_gatt_pages(int nr_tables) int retval = 0; int i; - tables = kmalloc((nr_tables + 1) * sizeof(ati_page_map *), - GFP_KERNEL); + tables = kzalloc((nr_tables + 1) * sizeof(ati_page_map *),GFP_KERNEL); if (tables == NULL) return -ENOMEM; - memset(tables, 0, sizeof(ati_page_map *) * (nr_tables + 1)); for (i = 0; i < nr_tables; i++) { - entry = kmalloc(sizeof(ati_page_map), GFP_KERNEL); + entry = kzalloc(sizeof(ati_page_map), GFP_KERNEL); if (entry == NULL) { while (i>0) { kfree (tables[i-1]); @@ -136,7 +134,6 @@ static int ati_create_gatt_pages(int nr_tables) retval = -ENOMEM; break; } - memset(entry, 0, sizeof(ati_page_map)); tables[i] = entry; retval = ati_create_page_map(entry); if (retval != 0) break; @@ -524,6 +521,7 @@ static struct pci_device_id agp_ati_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_ati_pci_table); static struct pci_driver agp_ati_pci_driver = { + .owner = THIS_MODULE, .name = "agpgart-ati", .id_table = agp_ati_pci_table, .probe = agp_ati_probe, diff --git a/drivers/char/agp/backend.c b/drivers/char/agp/backend.c index 82b43c541c8d..73f333f491bd 100644 --- a/drivers/char/agp/backend.c +++ b/drivers/char/agp/backend.c @@ -222,12 +222,12 @@ static void agp_backend_cleanup(struct agp_bridge_data *bridge) struct agp_bridge_data *agp_alloc_bridge(void) { - struct agp_bridge_data *bridge = kmalloc(sizeof(*bridge), GFP_KERNEL); - + struct agp_bridge_data *bridge; + + bridge = kzalloc(sizeof(*bridge), GFP_KERNEL); if (!bridge) return NULL; - memset(bridge, 0, sizeof(*bridge)); atomic_set(&bridge->agp_in_use, 0); atomic_set(&bridge->current_memory_agp, 0); diff --git a/drivers/char/agp/efficeon-agp.c b/drivers/char/agp/efficeon-agp.c index ac19fdcd21c1..d41e0a62e32e 100644 --- a/drivers/char/agp/efficeon-agp.c +++ b/drivers/char/agp/efficeon-agp.c @@ -219,7 +219,7 @@ static int efficeon_create_gatt_table(struct agp_bridge_data *bridge) efficeon_private.l1_table[index] = page; - value = virt_to_gart(page) | pati | present | index; + value = virt_to_gart((unsigned long *)page) | pati | present | index; pci_write_config_dword(agp_bridge->dev, EFFICEON_ATTPAGE, value); @@ -429,6 +429,7 @@ static struct pci_device_id agp_efficeon_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_efficeon_pci_table); static struct pci_driver agp_efficeon_pci_driver = { + .owner = THIS_MODULE, .name = "agpgart-efficeon", .id_table = agp_efficeon_pci_table, .probe = agp_efficeon_probe, diff --git a/drivers/char/agp/frontend.c b/drivers/char/agp/frontend.c index 3dfb6648547b..17f520c9d471 100644 --- a/drivers/char/agp/frontend.c +++ b/drivers/char/agp/frontend.c @@ -189,13 +189,12 @@ static int agp_create_segment(struct agp_client *client, struct agp_region *regi struct agp_segment *user_seg; size_t i; - seg = kmalloc((sizeof(struct agp_segment_priv) * region->seg_count), GFP_KERNEL); + seg = kzalloc((sizeof(struct agp_segment_priv) * region->seg_count), GFP_KERNEL); if (seg == NULL) { kfree(region->seg_list); region->seg_list = NULL; return -ENOMEM; } - memset(seg, 0, (sizeof(struct agp_segment_priv) * region->seg_count)); user_seg = region->seg_list; for (i = 0; i < region->seg_count; i++) { @@ -332,14 +331,11 @@ static struct agp_controller *agp_create_controller(pid_t id) { struct agp_controller *controller; - controller = kmalloc(sizeof(struct agp_controller), GFP_KERNEL); - + controller = kzalloc(sizeof(struct agp_controller), GFP_KERNEL); if (controller == NULL) return NULL; - memset(controller, 0, sizeof(struct agp_controller)); controller->pid = id; - return controller; } @@ -540,12 +536,10 @@ static struct agp_client *agp_create_client(pid_t id) { struct agp_client *new_client; - new_client = kmalloc(sizeof(struct agp_client), GFP_KERNEL); - + new_client = kzalloc(sizeof(struct agp_client), GFP_KERNEL); if (new_client == NULL) return NULL; - memset(new_client, 0, sizeof(struct agp_client)); new_client->pid = id; agp_insert_client(new_client); return new_client; @@ -709,11 +703,10 @@ static int agp_open(struct inode *inode, struct file *file) if (minor != AGPGART_MINOR) goto err_out; - priv = kmalloc(sizeof(struct agp_file_private), GFP_KERNEL); + priv = kzalloc(sizeof(struct agp_file_private), GFP_KERNEL); if (priv == NULL) goto err_out_nomem; - memset(priv, 0, sizeof(struct agp_file_private)); set_bit(AGP_FF_ALLOW_CLIENT, &priv->access_flags); priv->my_pid = current->pid; diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c index ac9da0ca36b7..c4a38715c6f9 100644 --- a/drivers/char/agp/generic.c +++ b/drivers/char/agp/generic.c @@ -105,12 +105,10 @@ struct agp_memory *agp_create_memory(int scratch_pages) { struct agp_memory *new; - new = kmalloc(sizeof(struct agp_memory), GFP_KERNEL); - + new = kzalloc(sizeof(struct agp_memory), GFP_KERNEL); if (new == NULL) return NULL; - memset(new, 0, sizeof(struct agp_memory)); new->key = agp_get_key(); if (new->key < 0) { @@ -414,7 +412,8 @@ static void agp_v2_parse_one(u32 *requested_mode, u32 *bridge_agpstat, u32 *vga_ u32 tmp; if (*requested_mode & AGP2_RESERVED_MASK) { - printk(KERN_INFO PFX "reserved bits set in mode 0x%x. Fixed.\n", *requested_mode); + printk(KERN_INFO PFX "reserved bits set (%x) in mode 0x%x. Fixed.\n", + *requested_mode & AGP2_RESERVED_MASK, *requested_mode); *requested_mode &= ~AGP2_RESERVED_MASK; } @@ -492,7 +491,8 @@ static void agp_v3_parse_one(u32 *requested_mode, u32 *bridge_agpstat, u32 *vga_ u32 tmp; if (*requested_mode & AGP3_RESERVED_MASK) { - printk(KERN_INFO PFX "reserved bits set in mode 0x%x. Fixed.\n", *requested_mode); + printk(KERN_INFO PFX "reserved bits set (%x) in mode 0x%x. Fixed.\n", + *requested_mode & AGP3_RESERVED_MASK, *requested_mode); *requested_mode &= ~AGP3_RESERVED_MASK; } diff --git a/drivers/char/agp/i460-agp.c b/drivers/char/agp/i460-agp.c index a2d9e5e48bbe..58944cd271ea 100644 --- a/drivers/char/agp/i460-agp.c +++ b/drivers/char/agp/i460-agp.c @@ -227,10 +227,9 @@ static int i460_configure (void) */ if (I460_IO_PAGE_SHIFT > PAGE_SHIFT) { size = current_size->num_entries * sizeof(i460.lp_desc[0]); - i460.lp_desc = kmalloc(size, GFP_KERNEL); + i460.lp_desc = kzalloc(size, GFP_KERNEL); if (!i460.lp_desc) return -ENOMEM; - memset(i460.lp_desc, 0, size); } return 0; } @@ -366,13 +365,12 @@ static int i460_alloc_large_page (struct lp_desc *lp) } map_size = ((I460_KPAGES_PER_IOPAGE + BITS_PER_LONG - 1) & -BITS_PER_LONG)/8; - lp->alloced_map = kmalloc(map_size, GFP_KERNEL); + lp->alloced_map = kzalloc(map_size, GFP_KERNEL); if (!lp->alloced_map) { free_pages((unsigned long) lpage, order); printk(KERN_ERR PFX "Out of memory, we're in trouble...\n"); return -ENOMEM; } - memset(lp->alloced_map, 0, map_size); lp->paddr = virt_to_gart(lpage); lp->refcount = 0; @@ -619,6 +617,7 @@ static struct pci_device_id agp_intel_i460_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_intel_i460_pci_table); static struct pci_driver agp_intel_i460_pci_driver = { + .owner = THIS_MODULE, .name = "agpgart-intel-i460", .id_table = agp_intel_i460_pci_table, .probe = agp_intel_i460_probe, diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index 1f7d415f432c..bf4cc9ffd5b1 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -1824,6 +1824,7 @@ static struct pci_device_id agp_intel_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_intel_pci_table); static struct pci_driver agp_intel_pci_driver = { + .owner = THIS_MODULE, .name = "agpgart-intel", .id_table = agp_intel_pci_table, .probe = agp_intel_probe, diff --git a/drivers/char/agp/nvidia-agp.c b/drivers/char/agp/nvidia-agp.c index 80dafa3030bd..3aed0c5e2f92 100644 --- a/drivers/char/agp/nvidia-agp.c +++ b/drivers/char/agp/nvidia-agp.c @@ -398,6 +398,7 @@ static struct pci_device_id agp_nvidia_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_nvidia_pci_table); static struct pci_driver agp_nvidia_pci_driver = { + .owner = THIS_MODULE, .name = "agpgart-nvidia", .id_table = agp_nvidia_pci_table, .probe = agp_nvidia_probe, diff --git a/drivers/char/agp/sgi-agp.c b/drivers/char/agp/sgi-agp.c index 7957fc91f6ad..4df7734b51c2 100644 --- a/drivers/char/agp/sgi-agp.c +++ b/drivers/char/agp/sgi-agp.c @@ -289,6 +289,8 @@ static int __devinit agp_sgi_init(void) j = 0; list_for_each_entry(info, &tioca_list, ca_list) { struct list_head *tmp; + if (list_empty(info->ca_devices)) + continue; list_for_each(tmp, info->ca_devices) { u8 cap_ptr; pdev = pci_dev_b(tmp); diff --git a/drivers/char/agp/sis-agp.c b/drivers/char/agp/sis-agp.c index ebc05554045c..a701361a8890 100644 --- a/drivers/char/agp/sis-agp.c +++ b/drivers/char/agp/sis-agp.c @@ -332,6 +332,7 @@ static struct pci_device_id agp_sis_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_sis_pci_table); static struct pci_driver agp_sis_pci_driver = { + .owner = THIS_MODULE, .name = "agpgart-sis", .id_table = agp_sis_pci_table, .probe = agp_sis_probe, diff --git a/drivers/char/agp/sworks-agp.c b/drivers/char/agp/sworks-agp.c index 71ea59a1dbeb..5a5392dd1254 100644 --- a/drivers/char/agp/sworks-agp.c +++ b/drivers/char/agp/sworks-agp.c @@ -102,19 +102,17 @@ static int serverworks_create_gatt_pages(int nr_tables) int retval = 0; int i; - tables = kmalloc((nr_tables + 1) * sizeof(struct serverworks_page_map *), + tables = kzalloc((nr_tables + 1) * sizeof(struct serverworks_page_map *), GFP_KERNEL); - if (tables == NULL) { + if (tables == NULL) return -ENOMEM; - } - memset(tables, 0, sizeof(struct serverworks_page_map *) * (nr_tables + 1)); + for (i = 0; i < nr_tables; i++) { - entry = kmalloc(sizeof(struct serverworks_page_map), GFP_KERNEL); + entry = kzalloc(sizeof(struct serverworks_page_map), GFP_KERNEL); if (entry == NULL) { retval = -ENOMEM; break; } - memset(entry, 0, sizeof(struct serverworks_page_map)); tables[i] = entry; retval = serverworks_create_page_map(entry); if (retval != 0) break; @@ -244,13 +242,27 @@ static int serverworks_fetch_size(void) */ static void serverworks_tlbflush(struct agp_memory *temp) { + unsigned long timeout; + writeb(1, serverworks_private.registers+SVWRKS_POSTFLUSH); - while (readb(serverworks_private.registers+SVWRKS_POSTFLUSH) == 1) + timeout = jiffies + 3*HZ; + while (readb(serverworks_private.registers+SVWRKS_POSTFLUSH) == 1) { cpu_relax(); + if (time_after(jiffies, timeout)) { + printk(KERN_ERR PFX "TLB post flush took more than 3 seconds\n"); + break; + } + } writel(1, serverworks_private.registers+SVWRKS_DIRFLUSH); - while(readl(serverworks_private.registers+SVWRKS_DIRFLUSH) == 1) + timeout = jiffies + 3*HZ; + while (readl(serverworks_private.registers+SVWRKS_DIRFLUSH) == 1) { cpu_relax(); + if (time_after(jiffies, timeout)) { + printk(KERN_ERR PFX "TLB Dir flush took more than 3 seconds\n"); + break; + } + } } static int serverworks_configure(void) @@ -533,6 +545,7 @@ static struct pci_device_id agp_serverworks_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_serverworks_pci_table); static struct pci_driver agp_serverworks_pci_driver = { + .owner = THIS_MODULE, .name = "agpgart-serverworks", .id_table = agp_serverworks_pci_table, .probe = agp_serverworks_probe, diff --git a/drivers/char/agp/uninorth-agp.c b/drivers/char/agp/uninorth-agp.c index c8255312b8c1..183c50acab27 100644 --- a/drivers/char/agp/uninorth-agp.c +++ b/drivers/char/agp/uninorth-agp.c @@ -658,6 +658,7 @@ static struct pci_device_id agp_uninorth_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_uninorth_pci_table); static struct pci_driver agp_uninorth_pci_driver = { + .owner = THIS_MODULE, .name = "agpgart-uninorth", .id_table = agp_uninorth_pci_table, .probe = agp_uninorth_probe, diff --git a/drivers/char/agp/via-agp.c b/drivers/char/agp/via-agp.c index c847df575cf5..5d9a13700074 100644 --- a/drivers/char/agp/via-agp.c +++ b/drivers/char/agp/via-agp.c @@ -518,6 +518,7 @@ MODULE_DEVICE_TABLE(pci, agp_via_pci_table); static struct pci_driver agp_via_pci_driver = { + .owner = THIS_MODULE, .name = "agpgart-via", .id_table = agp_via_pci_table, .probe = agp_via_probe, diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 6c6121b85a54..25acf478c9e8 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -593,12 +593,11 @@ static int cpufreq_add_dev (struct sys_device * sys_dev) goto module_out; } - policy = kmalloc(sizeof(struct cpufreq_policy), GFP_KERNEL); + policy = kzalloc(sizeof(struct cpufreq_policy), GFP_KERNEL); if (!policy) { ret = -ENOMEM; goto nomem_out; } - memset(policy, 0, sizeof(struct cpufreq_policy)); policy->cpu = cpu; policy->cpus = cpumask_of_cpu(cpu); diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index c1fc9c62bb51..17741111246b 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -48,7 +48,10 @@ * All times here are in uS. */ static unsigned int def_sampling_rate; -#define MIN_SAMPLING_RATE (def_sampling_rate / 2) +#define MIN_SAMPLING_RATE_RATIO (2) +/* for correct statistics, we need at least 10 ticks between each measure */ +#define MIN_STAT_SAMPLING_RATE (MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10)) +#define MIN_SAMPLING_RATE (def_sampling_rate / MIN_SAMPLING_RATE_RATIO) #define MAX_SAMPLING_RATE (500 * def_sampling_rate) #define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER (1000) #define DEF_SAMPLING_DOWN_FACTOR (1) @@ -416,13 +419,16 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, if (dbs_enable == 1) { unsigned int latency; /* policy latency is in nS. Convert it to uS first */ + latency = policy->cpuinfo.transition_latency / 1000; + if (latency == 0) + latency = 1; - latency = policy->cpuinfo.transition_latency; - if (latency < 1000) - latency = 1000; - - def_sampling_rate = (latency / 1000) * + def_sampling_rate = latency * DEF_SAMPLING_RATE_LATENCY_MULTIPLIER; + + if (def_sampling_rate < MIN_STAT_SAMPLING_RATE) + def_sampling_rate = MIN_STAT_SAMPLING_RATE; + dbs_tuners_ins.sampling_rate = def_sampling_rate; dbs_tuners_ins.ignore_nice = 0; diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index 3597f25d5efa..0bddb8e694d9 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -193,11 +193,15 @@ cpufreq_stats_create_table (struct cpufreq_policy *policy, unsigned int cpu = policy->cpu; if (cpufreq_stats_table[cpu]) return -EBUSY; - if ((stat = kmalloc(sizeof(struct cpufreq_stats), GFP_KERNEL)) == NULL) + if ((stat = kzalloc(sizeof(struct cpufreq_stats), GFP_KERNEL)) == NULL) return -ENOMEM; - memset(stat, 0, sizeof (struct cpufreq_stats)); data = cpufreq_cpu_get(cpu); + if (data == NULL) { + ret = -EINVAL; + goto error_get_fail; + } + if ((ret = sysfs_create_group(&data->kobj, &stats_attr_group))) goto error_out; @@ -217,12 +221,11 @@ cpufreq_stats_create_table (struct cpufreq_policy *policy, alloc_size += count * count * sizeof(int); #endif stat->max_state = count; - stat->time_in_state = kmalloc(alloc_size, GFP_KERNEL); + stat->time_in_state = kzalloc(alloc_size, GFP_KERNEL); if (!stat->time_in_state) { ret = -ENOMEM; goto error_out; } - memset(stat->time_in_state, 0, alloc_size); stat->freq_table = (unsigned int *)(stat->time_in_state + count); #ifdef CONFIG_CPU_FREQ_STAT_DETAILS @@ -245,6 +248,7 @@ cpufreq_stats_create_table (struct cpufreq_policy *policy, return 0; error_out: cpufreq_cpu_put(data); +error_get_fail: kfree(stat); cpufreq_stats_table[cpu] = NULL; return ret; diff --git a/drivers/mmc/mmc.c b/drivers/mmc/mmc.c index ceae379a4d4c..da528390acf8 100644 --- a/drivers/mmc/mmc.c +++ b/drivers/mmc/mmc.c @@ -1263,7 +1263,7 @@ EXPORT_SYMBOL(mmc_suspend_host); */ int mmc_resume_host(struct mmc_host *host) { - mmc_detect_change(host, 0); + mmc_rescan(host); return 0; } diff --git a/drivers/sbus/char/cpwatchdog.c b/drivers/sbus/char/cpwatchdog.c index c82abeb59d3a..071ae24be892 100644 --- a/drivers/sbus/char/cpwatchdog.c +++ b/drivers/sbus/char/cpwatchdog.c @@ -26,6 +26,7 @@ #include <linux/interrupt.h> #include <linux/ioport.h> #include <linux/timer.h> +#include <linux/smp_lock.h> #include <asm/irq.h> #include <asm/ebus.h> #include <asm/oplib.h> @@ -394,6 +395,28 @@ static int wd_ioctl(struct inode *inode, struct file *file, return(0); } +static long wd_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + int rval = -ENOIOCTLCMD; + + switch (cmd) { + /* solaris ioctls are specific to this driver */ + case WIOCSTART: + case WIOCSTOP: + case WIOCGSTAT: + lock_kernel(); + rval = wd_ioctl(file->f_dentry->d_inode, file, cmd, arg); + lock_kernel(); + break; + /* everything else is handled by the generic compat layer */ + default: + break; + } + + return rval; +} + static ssize_t wd_write(struct file *file, const char __user *buf, size_t count, @@ -441,6 +464,7 @@ static irqreturn_t wd_interrupt(int irq, void *dev_id, struct pt_regs *regs) static struct file_operations wd_fops = { .owner = THIS_MODULE, .ioctl = wd_ioctl, + .compat_ioctl = wd_compat_ioctl, .open = wd_open, .write = wd_write, .read = wd_read, diff --git a/drivers/sbus/char/display7seg.c b/drivers/sbus/char/display7seg.c index 24ed5893b4f0..39f54213a6d5 100644 --- a/drivers/sbus/char/display7seg.c +++ b/drivers/sbus/char/display7seg.c @@ -15,6 +15,7 @@ #include <linux/init.h> #include <linux/miscdevice.h> #include <linux/ioport.h> /* request_region */ +#include <linux/smp_lock.h> #include <asm/atomic.h> #include <asm/ebus.h> /* EBus device */ #include <asm/oplib.h> /* OpenProm Library */ @@ -114,22 +115,25 @@ static int d7s_release(struct inode *inode, struct file *f) return 0; } -static int d7s_ioctl(struct inode *inode, struct file *f, - unsigned int cmd, unsigned long arg) +static long d7s_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { __u8 regs = readb(d7s_regs); __u8 ireg = 0; + int error = 0 - if (D7S_MINOR != iminor(inode)) + if (D7S_MINOR != iminor(file->f_dentry->d_inode)) return -ENODEV; + lock_kernel(); switch (cmd) { case D7SIOCWR: /* assign device register values * we mask-out D7S_FLIP if in sol_compat mode */ - if (get_user(ireg, (int __user *) arg)) - return -EFAULT; + if (get_user(ireg, (int __user *) arg)) { + error = -EFAULT; + break; + } if (0 != sol_compat) { (regs & D7S_FLIP) ? (ireg |= D7S_FLIP) : (ireg &= ~D7S_FLIP); @@ -144,8 +148,10 @@ static int d7s_ioctl(struct inode *inode, struct file *f, * This driver will not misinform you about the state * of your hardware while in sol_compat mode */ - if (put_user(regs, (int __user *) arg)) - return -EFAULT; + if (put_user(regs, (int __user *) arg)) { + error = -EFAULT; + break; + } break; case D7SIOCTM: @@ -155,15 +161,17 @@ static int d7s_ioctl(struct inode *inode, struct file *f, writeb(regs, d7s_regs); break; }; + lock_kernel(); - return 0; + return error; } static struct file_operations d7s_fops = { - .owner = THIS_MODULE, - .ioctl = d7s_ioctl, - .open = d7s_open, - .release = d7s_release, + .owner = THIS_MODULE, + .unlocked_ioctl = d7s_ioctl, + .compat_ioctl = d7s_ioctl, + .open = d7s_open, + .release = d7s_release, }; static struct miscdevice d7s_miscdev = { D7S_MINOR, D7S_DEVNAME, &d7s_fops }; diff --git a/drivers/sbus/char/envctrl.c b/drivers/sbus/char/envctrl.c index ba56762b05f6..19e8eddf887a 100644 --- a/drivers/sbus/char/envctrl.c +++ b/drivers/sbus/char/envctrl.c @@ -654,9 +654,8 @@ envctrl_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) /* Function Description: Command what to read. Mapped to user ioctl(). * Return: Gives 0 for implemented commands, -EINVAL otherwise. */ -static int -envctrl_ioctl(struct inode *inode, struct file *file, - unsigned int cmd, unsigned long arg) +static long +envctrl_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { char __user *infobuf; @@ -715,11 +714,14 @@ envctrl_release(struct inode *inode, struct file *file) } static struct file_operations envctrl_fops = { - .owner = THIS_MODULE, - .read = envctrl_read, - .ioctl = envctrl_ioctl, - .open = envctrl_open, - .release = envctrl_release, + .owner = THIS_MODULE, + .read = envctrl_read, + .unlocked_ioctl = envctrl_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = envctrl_ioctl, +#endif + .open = envctrl_open, + .release = envctrl_release, }; static struct miscdevice envctrl_dev = { diff --git a/drivers/sbus/char/openprom.c b/drivers/sbus/char/openprom.c index 58ed33749571..5028ac214326 100644 --- a/drivers/sbus/char/openprom.c +++ b/drivers/sbus/char/openprom.c @@ -39,6 +39,7 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/miscdevice.h> +#include <linux/smp_lock.h> #include <linux/init.h> #include <linux/fs.h> #include <asm/oplib.h> @@ -565,6 +566,38 @@ static int openprom_ioctl(struct inode * inode, struct file * file, } } +static long openprom_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + long rval = -ENOTTY; + + /* + * SunOS/Solaris only, the NetBSD one's have embedded pointers in + * the arg which we'd need to clean up... + */ + switch (cmd) { + case OPROMGETOPT: + case OPROMSETOPT: + case OPROMNXTOPT: + case OPROMSETOPT2: + case OPROMNEXT: + case OPROMCHILD: + case OPROMGETPROP: + case OPROMNXTPROP: + case OPROMU2P: + case OPROMGETCONS: + case OPROMGETFBNAME: + case OPROMGETBOOTARGS: + case OPROMSETCUR: + case OPROMPCI2NODE: + case OPROMPATH2NODE: + lock_kernel(); + rval = openprom_ioctl(file->f_dentry->d_inode, file, cmd, arg); + lock_kernel(); + break; + } +} + static int openprom_open(struct inode * inode, struct file * file) { DATA *data; diff --git a/drivers/serial/sunsu.c b/drivers/serial/sunsu.c index 656c0e8d160e..f0738533f39a 100644 --- a/drivers/serial/sunsu.c +++ b/drivers/serial/sunsu.c @@ -1441,7 +1441,7 @@ static void sunsu_console_write(struct console *co, const char *s, * - initialize the serial port * Return non-zero if we didn't find a serial port. */ -static int __init sunsu_console_setup(struct console *co, char *options) +static int sunsu_console_setup(struct console *co, char *options) { struct uart_port *port; int baud = 9600; diff --git a/drivers/video/cg6.c b/drivers/video/cg6.c index 3280bb9560e2..414c4409e924 100644 --- a/drivers/video/cg6.c +++ b/drivers/video/cg6.c @@ -653,12 +653,6 @@ static void cg6_chip_init(struct fb_info *info) sbus_writel(0, &fbc->clipminy); sbus_writel(info->var.xres - 1, &fbc->clipmaxx); sbus_writel(info->var.yres - 1, &fbc->clipmaxy); - - /* Disable cursor in Brooktree DAC. */ - sbus_writel(0x06 << 24, &par->bt->addr); - tmp = sbus_readl(&par->bt->control); - tmp &= ~(0x03 << 24); - sbus_writel(tmp, &par->bt->control); } struct all_info { diff --git a/fs/Makefile b/fs/Makefile index 1972da186272..4c2655759078 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 afa06a893468..05b60283c9c2 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 2fa9fdf7d6f5..caa9187f67e5 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 000000000000..aeeec8ba8dd2 --- /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 000000000000..020e1bb60fdb --- /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 a170450aadb1..634355e16986 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 38ef913767ff..7c40570b71dc 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 eed6c3132905..6689dded3c84 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-arm/arch-realview/entry-macro.S b/include/asm-arm/arch-realview/entry-macro.S index 2712ba77bb3a..4df469bf42e2 100644 --- a/include/asm-arm/arch-realview/entry-macro.S +++ b/include/asm-arm/arch-realview/entry-macro.S @@ -47,3 +47,17 @@ cmpcs \irqnr, \irqnr .endm + + /* We assume that irqstat (the raw value of the IRQ acknowledge + * register) is preserved from the macro above. + * If there is an IPI, we immediately signal end of interrupt on the + * controller, since this requires the original irqstat value which + * we won't easily be able to recreate later. + */ + + .macro test_for_ipi, irqnr, irqstat, base, tmp + bic \irqnr, \irqstat, #0x1c00 + cmp \irqnr, #16 + strcc \irqstat, [\base, #GIC_CPU_EOI] + cmpcs \irqnr, \irqnr + .endm diff --git a/include/asm-arm/arch-realview/platform.h b/include/asm-arm/arch-realview/platform.h index 4b6de13a6b9a..aef9b36b3c37 100644 --- a/include/asm-arm/arch-realview/platform.h +++ b/include/asm-arm/arch-realview/platform.h @@ -203,8 +203,14 @@ /* Reserved 0x1001A000 - 0x1001FFFF */ #define REALVIEW_CLCD_BASE 0x10020000 /* CLCD */ #define REALVIEW_DMAC_BASE 0x10030000 /* DMA controller */ +#ifndef CONFIG_REALVIEW_MPCORE #define REALVIEW_GIC_CPU_BASE 0x10040000 /* Generic interrupt controller CPU interface */ #define REALVIEW_GIC_DIST_BASE 0x10041000 /* Generic interrupt controller distributor */ +#else +#define REALVIEW_MPCORE_SCU_BASE 0x10100000 /* SCU registers */ +#define REALVIEW_GIC_CPU_BASE 0x10100100 /* Generic interrupt controller CPU interface */ +#define REALVIEW_GIC_DIST_BASE 0x10101000 /* Generic interrupt controller distributor */ +#endif #define REALVIEW_SMC_BASE 0x10080000 /* SMC */ /* Reserved 0x10090000 - 0x100EFFFF */ @@ -265,6 +271,7 @@ * Interrupts - bit assignment (primary) * ------------------------------------------------------------------------ */ +#ifndef CONFIG_REALVIEW_MPCORE #define INT_WDOGINT 0 /* Watchdog timer */ #define INT_SOFTINT 1 /* Software interrupt */ #define INT_COMMRx 2 /* Debug Comm Rx interrupt */ @@ -297,6 +304,55 @@ #define INT_USB 29 /* USB controller */ #define INT_TSPENINT 30 /* Touchscreen pen */ #define INT_TSKPADINT 31 /* Touchscreen keypad */ +#else +#define INT_LOCALTIMER 29 +#define INT_LOCALWDOG 30 + +#define INT_AACI 0 +#define INT_TIMERINT0_1 1 +#define INT_TIMERINT2_3 2 +#define INT_USB 3 +#define INT_UARTINT0 4 +#define INT_UARTINT1 5 +#define INT_RTCINT 6 +#define INT_KMI0 7 +#define INT_KMI1 8 +#define INT_ETH 9 +#define INT_EB_IRQ1 10 /* main GIC */ +#define INT_EB_IRQ2 11 /* tile GIC */ +#define INT_EB_FIQ1 12 /* main GIC */ +#define INT_EB_FIQ2 13 /* tile GIC */ +#define INT_MMCI0A 14 +#define INT_MMCI0B 15 + +#define INT_PMU_CPU0 17 +#define INT_PMU_CPU1 18 +#define INT_PMU_CPU2 19 +#define INT_PMU_CPU3 20 +#define INT_PMU_SCU0 21 +#define INT_PMU_SCU1 22 +#define INT_PMU_SCU2 23 +#define INT_PMU_SCU3 24 +#define INT_PMU_SCU4 25 +#define INT_PMU_SCU5 26 +#define INT_PMU_SCU6 27 +#define INT_PMU_SCU7 28 + +#define INT_L220_EVENT 29 +#define INT_L220_SLAVE 30 +#define INT_L220_DECODE 31 + +#define INT_UARTINT2 -1 +#define INT_UARTINT3 -1 +#define INT_CLCDINT -1 +#define INT_DMAINT -1 +#define INT_WDOGINT -1 +#define INT_GPIOINT0 -1 +#define INT_GPIOINT1 -1 +#define INT_GPIOINT2 -1 +#define INT_SCIINT -1 +#define INT_SSPINT -1 +#endif /* * Interrupt bit positions diff --git a/include/asm-arm/arch-realview/smp.h b/include/asm-arm/arch-realview/smp.h new file mode 100644 index 000000000000..fc87783e8e8b --- /dev/null +++ b/include/asm-arm/arch-realview/smp.h @@ -0,0 +1,31 @@ +#ifndef ASMARM_ARCH_SMP_H +#define ASMARM_ARCH_SMP_H + +#include <linux/config.h> + +#include <asm/hardware/gic.h> + +#define hard_smp_processor_id() \ + ({ \ + unsigned int cpunum; \ + __asm__("mrc p15, 0, %0, c0, c0, 5" \ + : "=r" (cpunum)); \ + cpunum &= 0x0F; \ + }) + +/* + * We use IRQ1 as the IPI + */ +static inline void smp_cross_call(cpumask_t callmap) +{ + gic_raise_softirq(callmap, 1); +} + +/* + * Do nothing on MPcore. + */ +static inline void smp_cross_call_done(cpumask_t callmap) +{ +} + +#endif diff --git a/include/asm-arm/hardware/arm_scu.h b/include/asm-arm/hardware/arm_scu.h new file mode 100644 index 000000000000..9903f60c84b7 --- /dev/null +++ b/include/asm-arm/hardware/arm_scu.h @@ -0,0 +1,13 @@ +#ifndef ASMARM_HARDWARE_ARM_SCU_H +#define ASMARM_HARDWARE_ARM_SCU_H + +/* + * SCU registers + */ +#define SCU_CTRL 0x00 +#define SCU_CONFIG 0x04 +#define SCU_CPU_STATUS 0x08 +#define SCU_INVALIDATE 0x0c +#define SCU_FPGA_REVISION 0x10 + +#endif diff --git a/include/asm-ia64/page.h b/include/asm-ia64/page.h index ef436b9d06ad..9d41548b7fef 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/asm-m68k/kbio.h b/include/asm-m68k/kbio.h deleted file mode 100644 index e1fbf8fba3e8..000000000000 --- a/include/asm-m68k/kbio.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-sparc/kbio.h> diff --git a/include/asm-m68k/vuid_event.h b/include/asm-m68k/vuid_event.h deleted file mode 100644 index 52ecb521a395..000000000000 --- a/include/asm-m68k/vuid_event.h +++ /dev/null @@ -1,4 +0,0 @@ -#ifndef _M68K_VUID_EVENT_H -#define _M68K_VUID_EVENT_H -#include <asm-sparc/vuid_event.h> -#endif diff --git a/include/asm-sparc/audioio.h b/include/asm-sparc/audioio.h deleted file mode 100644 index cf16173f521b..000000000000 --- a/include/asm-sparc/audioio.h +++ /dev/null @@ -1,234 +0,0 @@ -/* - * include/asm-sparc/audioio.h - * - * Sparc Audio Midlayer - * Copyright (C) 1996 Thomas K. Dyas (tdyas@noc.rutgers.edu) - */ - -#ifndef _AUDIOIO_H_ -#define _AUDIOIO_H_ - -/* - * SunOS/Solaris /dev/audio interface - */ - -#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2) -#include <linux/types.h> -#include <linux/time.h> -#include <linux/ioctl.h> -#endif - -/* - * This structure contains state information for audio device IO streams. - */ -typedef struct audio_prinfo { - /* - * The following values describe the audio data encoding. - */ - unsigned int sample_rate; /* samples per second */ - unsigned int channels; /* number of interleaved channels */ - unsigned int precision; /* bit-width of each sample */ - unsigned int encoding; /* data encoding method */ - - /* - * The following values control audio device configuration - */ - unsigned int gain; /* gain level: 0 - 255 */ - unsigned int port; /* selected I/O port (see below) */ - unsigned int avail_ports; /* available I/O ports (see below) */ - unsigned int _xxx[2]; /* Reserved for future use */ - - unsigned int buffer_size; /* I/O buffer size */ - - /* - * The following values describe driver state - */ - unsigned int samples; /* number of samples converted */ - unsigned int eof; /* End Of File counter (play only) */ - - unsigned char pause; /* non-zero for pause, zero to resume */ - unsigned char error; /* non-zero if overflow/underflow */ - unsigned char waiting; /* non-zero if a process wants access */ - unsigned char balance; /* stereo channel balance */ - - unsigned short minordev; - - /* - * The following values are read-only state flags - */ - unsigned char open; /* non-zero if open access permitted */ - unsigned char active; /* non-zero if I/O is active */ -} audio_prinfo_t; - - -/* - * This structure describes the current state of the audio device. - */ -typedef struct audio_info { - /* - * Per-stream information - */ - audio_prinfo_t play; /* output status information */ - audio_prinfo_t record; /* input status information */ - - /* - * Per-unit/channel information - */ - unsigned int monitor_gain; /* input to output mix: 0 - 255 */ - unsigned char output_muted; /* non-zero if output is muted */ - unsigned char _xxx[3]; /* Reserved for future use */ - unsigned int _yyy[3]; /* Reserved for future use */ -} audio_info_t; - - -/* - * Audio encoding types - */ -#define AUDIO_ENCODING_NONE (0) /* no encoding assigned */ -#define AUDIO_ENCODING_ULAW (1) /* u-law encoding */ -#define AUDIO_ENCODING_ALAW (2) /* A-law encoding */ -#define AUDIO_ENCODING_LINEAR (3) /* Linear PCM encoding */ -#define AUDIO_ENCODING_FLOAT (4) /* IEEE float (-1. <-> +1.) */ -#define AUDIO_ENCODING_DVI (104) /* DVI ADPCM */ -#define AUDIO_ENCODING_LINEAR8 (105) /* 8 bit UNSIGNED */ -#define AUDIO_ENCODING_LINEARLE (106) /* Linear PCM LE encoding */ - -/* - * These ranges apply to record, play, and monitor gain values - */ -#define AUDIO_MIN_GAIN (0) /* minimum gain value */ -#define AUDIO_MAX_GAIN (255) /* maximum gain value */ - -/* - * These values apply to the balance field to adjust channel gain values - */ -#define AUDIO_LEFT_BALANCE (0) /* left channel only */ -#define AUDIO_MID_BALANCE (32) /* equal left/right channel */ -#define AUDIO_RIGHT_BALANCE (64) /* right channel only */ -#define AUDIO_BALANCE_SHIFT (3) - -/* - * Generic minimum/maximum limits for number of channels, both modes - */ -#define AUDIO_MIN_PLAY_CHANNELS (1) -#define AUDIO_MAX_PLAY_CHANNELS (4) -#define AUDIO_MIN_REC_CHANNELS (1) -#define AUDIO_MAX_REC_CHANNELS (4) - -/* - * Generic minimum/maximum limits for sample precision - */ -#define AUDIO_MIN_PLAY_PRECISION (8) -#define AUDIO_MAX_PLAY_PRECISION (32) -#define AUDIO_MIN_REC_PRECISION (8) -#define AUDIO_MAX_REC_PRECISION (32) - -/* - * Define some convenient names for typical audio ports - */ -/* - * output ports (several may be enabled simultaneously) - */ -#define AUDIO_SPEAKER 0x01 /* output to built-in speaker */ -#define AUDIO_HEADPHONE 0x02 /* output to headphone jack */ -#define AUDIO_LINE_OUT 0x04 /* output to line out */ - -/* - * input ports (usually only one at a time) - */ -#define AUDIO_MICROPHONE 0x01 /* input from microphone */ -#define AUDIO_LINE_IN 0x02 /* input from line in */ -#define AUDIO_CD 0x04 /* input from on-board CD inputs */ -#define AUDIO_INTERNAL_CD_IN AUDIO_CD /* input from internal CDROM */ -#define AUDIO_ANALOG_LOOPBACK 0x40 /* input from output */ - - -/* - * This macro initializes an audio_info structure to 'harmless' values. - * Note that (~0) might not be a harmless value for a flag that was - * a signed int. - */ -#define AUDIO_INITINFO(i) { \ - unsigned int *__x__; \ - for (__x__ = (unsigned int *)(i); \ - (char *) __x__ < (((char *)(i)) + sizeof (audio_info_t)); \ - *__x__++ = ~0); \ -} - -/* - * These allow testing for what the user wants to set - */ -#define AUD_INITVALUE (~0) -#define Modify(X) ((unsigned int)(X) != AUD_INITVALUE) -#define Modifys(X) ((X) != (unsigned short)AUD_INITVALUE) -#define Modifyc(X) ((X) != (unsigned char)AUD_INITVALUE) - -/* - * Parameter for the AUDIO_GETDEV ioctl to determine current - * audio devices. - */ -#define MAX_AUDIO_DEV_LEN (16) -typedef struct audio_device { - char name[MAX_AUDIO_DEV_LEN]; - char version[MAX_AUDIO_DEV_LEN]; - char config[MAX_AUDIO_DEV_LEN]; -} audio_device_t; - - -/* - * Ioctl calls for the audio device. - */ - -/* - * AUDIO_GETINFO retrieves the current state of the audio device. - * - * AUDIO_SETINFO copies all fields of the audio_info structure whose - * values are not set to the initialized value (-1) to the device state. - * It performs an implicit AUDIO_GETINFO to return the new state of the - * device. Note that the record.samples and play.samples fields are set - * to the last value before the AUDIO_SETINFO took effect. This allows - * an application to reset the counters while atomically retrieving the - * last value. - * - * AUDIO_DRAIN suspends the calling process until the write buffers are - * empty. - * - * AUDIO_GETDEV returns a structure of type audio_device_t which contains - * three strings. The string "name" is a short identifying string (for - * example, the SBus Fcode name string), the string "version" identifies - * the current version of the device, and the "config" string identifies - * the specific configuration of the audio stream. All fields are - * device-dependent -- see the device specific manual pages for details. - * - * AUDIO_GETDEV_SUNOS returns a number which is an audio device defined - * herein (making it not too portable) - * - * AUDIO_FLUSH stops all playback and recording, clears all queued buffers, - * resets error counters, and restarts recording and playback as appropriate - * for the current sampling mode. - */ -#define AUDIO_GETINFO _IOR('A', 1, audio_info_t) -#define AUDIO_SETINFO _IOWR('A', 2, audio_info_t) -#define AUDIO_DRAIN _IO('A', 3) -#define AUDIO_GETDEV _IOR('A', 4, audio_device_t) -#define AUDIO_GETDEV_SUNOS _IOR('A', 4, int) -#define AUDIO_FLUSH _IO('A', 5) - -/* Define possible audio hardware configurations for - * old SunOS-style AUDIO_GETDEV ioctl */ -#define AUDIO_DEV_UNKNOWN (0) /* not defined */ -#define AUDIO_DEV_AMD (1) /* audioamd device */ -#define AUDIO_DEV_SPEAKERBOX (2) /* dbri device with speakerbox */ -#define AUDIO_DEV_CODEC (3) /* dbri device (internal speaker) */ -#define AUDIO_DEV_CS4231 (5) /* cs4231 device */ - -/* - * The following ioctl sets the audio device into an internal loopback mode, - * if the hardware supports this. The argument is TRUE to set loopback, - * FALSE to reset to normal operation. If the hardware does not support - * internal loopback, the ioctl should fail with EINVAL. - * Causes ADC data to be digitally mixed in and sent to the DAC. - */ -#define AUDIO_DIAG_LOOPBACK _IOW('A', 101, int) - -#endif /* _AUDIOIO_H_ */ diff --git a/include/asm-sparc/kbio.h b/include/asm-sparc/kbio.h deleted file mode 100644 index 3cf496bdf399..000000000000 --- a/include/asm-sparc/kbio.h +++ /dev/null @@ -1,56 +0,0 @@ -#ifndef __LINUX_KBIO_H -#define __LINUX_KBIO_H - -/* Return keyboard type */ -#define KIOCTYPE _IOR('k', 9, int) -/* Return Keyboard layout */ -#define KIOCLAYOUT _IOR('k', 20, int) - -enum { - TR_NONE, - TR_ASCII, /* keyboard is in regular state */ - TR_EVENT, /* keystrokes sent as firm events */ - TR_UNTRANS_EVENT /* EVENT+up and down+no translation */ -}; - -/* Return the current keyboard translation */ -#define KIOCGTRANS _IOR('k', 5, int) -/* Set the keyboard translation */ -#define KIOCTRANS _IOW('k', 0, int) - -/* Send a keyboard command */ -#define KIOCCMD _IOW('k', 8, int) - -/* Return if keystrokes are being sent to /dev/kbd */ - -/* Set routing of keystrokes to /dev/kbd */ -#define KIOCSDIRECT _IOW('k', 10, int) - -/* Set keyboard leds */ -#define KIOCSLED _IOW('k', 14, unsigned char) - -/* Get keyboard leds */ -#define KIOCGLED _IOR('k', 15, unsigned char) - -/* Used by KIOC[GS]RATE */ -struct kbd_rate { - unsigned char delay; /* Delay in Hz before first repeat. */ - unsigned char rate; /* In characters per second (0..50). */ -}; - -/* Set keyboard rate */ -#define KIOCSRATE _IOW('k', 40, struct kbd_rate) - -/* Get keyboard rate */ -#define KIOCGRATE _IOW('k', 41, struct kbd_rate) - -/* Top bit records if the key is up or down */ -#define KBD_UP 0x80 - -/* Usable information */ -#define KBD_KEYMASK 0x7f - -/* All keys up */ -#define KBD_IDLE 0x75 - -#endif /* __LINUX_KBIO_H */ diff --git a/include/asm-sparc/termios.h b/include/asm-sparc/termios.h index 0a8ad4cac125..d05f83c80989 100644 --- a/include/asm-sparc/termios.h +++ b/include/asm-sparc/termios.h @@ -38,15 +38,6 @@ struct sunos_ttysize { int st_columns; /* Columns on the terminal */ }; -/* Used for packet mode */ -#define TIOCPKT_DATA 0 -#define TIOCPKT_FLUSHREAD 1 -#define TIOCPKT_FLUSHWRITE 2 -#define TIOCPKT_STOP 4 -#define TIOCPKT_START 8 -#define TIOCPKT_NOSTOP 16 -#define TIOCPKT_DOSTOP 32 - struct winsize { unsigned short ws_row; unsigned short ws_col; diff --git a/include/asm-sparc/vuid_event.h b/include/asm-sparc/vuid_event.h deleted file mode 100644 index 7781e9f2fdd3..000000000000 --- a/include/asm-sparc/vuid_event.h +++ /dev/null @@ -1,41 +0,0 @@ -/* SunOS Virtual User Input Device (VUID) compatibility */ - - -typedef struct firm_event { - unsigned short id; /* tag for this event */ - unsigned char pair_type; /* unused by X11 */ - unsigned char pair; /* unused by X11 */ - int value; /* VKEY_UP, VKEY_DOWN or delta */ - struct timeval time; -} Firm_event; - -enum { - FE_PAIR_NONE, - FE_PAIR_SET, - FE_PAIR_DELTA, - FE_PAIR_ABSOLUTE -}; - -/* VUID stream formats */ -#define VUID_NATIVE 0 /* Native byte stream format */ -#define VUID_FIRM_EVENT 1 /* send firm_event structures */ - -/* ioctls */ - /* Set input device byte stream format (any of VUID_{NATIVE,FIRM_EVENT}) */ -#define VUIDSFORMAT _IOW('v', 1, int) - /* Retrieve input device byte stream format */ -#define VUIDGFORMAT _IOR('v', 2, int) - -/* Possible tag values */ -/* mouse buttons: */ -#define MS_LEFT 0x7f20 -#define MS_MIDDLE 0x7f21 -#define MS_RIGHT 0x7f22 -/* motion: */ -#define LOC_X_DELTA 0x7f80 -#define LOC_Y_DELTA 0x7f81 -#define LOC_X_ABSOLUTE 0x7f82 /* X compat, unsupported */ -#define LOC_Y_ABSOLUTE 0x7f83 /* X compat, unsupported */ - -#define VKEY_UP 0 -#define VKEY_DOWN 1 diff --git a/include/asm-sparc64/audioio.h b/include/asm-sparc64/audioio.h deleted file mode 100644 index cf16173f521b..000000000000 --- a/include/asm-sparc64/audioio.h +++ /dev/null @@ -1,234 +0,0 @@ -/* - * include/asm-sparc/audioio.h - * - * Sparc Audio Midlayer - * Copyright (C) 1996 Thomas K. Dyas (tdyas@noc.rutgers.edu) - */ - -#ifndef _AUDIOIO_H_ -#define _AUDIOIO_H_ - -/* - * SunOS/Solaris /dev/audio interface - */ - -#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2) -#include <linux/types.h> -#include <linux/time.h> -#include <linux/ioctl.h> -#endif - -/* - * This structure contains state information for audio device IO streams. - */ -typedef struct audio_prinfo { - /* - * The following values describe the audio data encoding. - */ - unsigned int sample_rate; /* samples per second */ - unsigned int channels; /* number of interleaved channels */ - unsigned int precision; /* bit-width of each sample */ - unsigned int encoding; /* data encoding method */ - - /* - * The following values control audio device configuration - */ - unsigned int gain; /* gain level: 0 - 255 */ - unsigned int port; /* selected I/O port (see below) */ - unsigned int avail_ports; /* available I/O ports (see below) */ - unsigned int _xxx[2]; /* Reserved for future use */ - - unsigned int buffer_size; /* I/O buffer size */ - - /* - * The following values describe driver state - */ - unsigned int samples; /* number of samples converted */ - unsigned int eof; /* End Of File counter (play only) */ - - unsigned char pause; /* non-zero for pause, zero to resume */ - unsigned char error; /* non-zero if overflow/underflow */ - unsigned char waiting; /* non-zero if a process wants access */ - unsigned char balance; /* stereo channel balance */ - - unsigned short minordev; - - /* - * The following values are read-only state flags - */ - unsigned char open; /* non-zero if open access permitted */ - unsigned char active; /* non-zero if I/O is active */ -} audio_prinfo_t; - - -/* - * This structure describes the current state of the audio device. - */ -typedef struct audio_info { - /* - * Per-stream information - */ - audio_prinfo_t play; /* output status information */ - audio_prinfo_t record; /* input status information */ - - /* - * Per-unit/channel information - */ - unsigned int monitor_gain; /* input to output mix: 0 - 255 */ - unsigned char output_muted; /* non-zero if output is muted */ - unsigned char _xxx[3]; /* Reserved for future use */ - unsigned int _yyy[3]; /* Reserved for future use */ -} audio_info_t; - - -/* - * Audio encoding types - */ -#define AUDIO_ENCODING_NONE (0) /* no encoding assigned */ -#define AUDIO_ENCODING_ULAW (1) /* u-law encoding */ -#define AUDIO_ENCODING_ALAW (2) /* A-law encoding */ -#define AUDIO_ENCODING_LINEAR (3) /* Linear PCM encoding */ -#define AUDIO_ENCODING_FLOAT (4) /* IEEE float (-1. <-> +1.) */ -#define AUDIO_ENCODING_DVI (104) /* DVI ADPCM */ -#define AUDIO_ENCODING_LINEAR8 (105) /* 8 bit UNSIGNED */ -#define AUDIO_ENCODING_LINEARLE (106) /* Linear PCM LE encoding */ - -/* - * These ranges apply to record, play, and monitor gain values - */ -#define AUDIO_MIN_GAIN (0) /* minimum gain value */ -#define AUDIO_MAX_GAIN (255) /* maximum gain value */ - -/* - * These values apply to the balance field to adjust channel gain values - */ -#define AUDIO_LEFT_BALANCE (0) /* left channel only */ -#define AUDIO_MID_BALANCE (32) /* equal left/right channel */ -#define AUDIO_RIGHT_BALANCE (64) /* right channel only */ -#define AUDIO_BALANCE_SHIFT (3) - -/* - * Generic minimum/maximum limits for number of channels, both modes - */ -#define AUDIO_MIN_PLAY_CHANNELS (1) -#define AUDIO_MAX_PLAY_CHANNELS (4) -#define AUDIO_MIN_REC_CHANNELS (1) -#define AUDIO_MAX_REC_CHANNELS (4) - -/* - * Generic minimum/maximum limits for sample precision - */ -#define AUDIO_MIN_PLAY_PRECISION (8) -#define AUDIO_MAX_PLAY_PRECISION (32) -#define AUDIO_MIN_REC_PRECISION (8) -#define AUDIO_MAX_REC_PRECISION (32) - -/* - * Define some convenient names for typical audio ports - */ -/* - * output ports (several may be enabled simultaneously) - */ -#define AUDIO_SPEAKER 0x01 /* output to built-in speaker */ -#define AUDIO_HEADPHONE 0x02 /* output to headphone jack */ -#define AUDIO_LINE_OUT 0x04 /* output to line out */ - -/* - * input ports (usually only one at a time) - */ -#define AUDIO_MICROPHONE 0x01 /* input from microphone */ -#define AUDIO_LINE_IN 0x02 /* input from line in */ -#define AUDIO_CD 0x04 /* input from on-board CD inputs */ -#define AUDIO_INTERNAL_CD_IN AUDIO_CD /* input from internal CDROM */ -#define AUDIO_ANALOG_LOOPBACK 0x40 /* input from output */ - - -/* - * This macro initializes an audio_info structure to 'harmless' values. - * Note that (~0) might not be a harmless value for a flag that was - * a signed int. - */ -#define AUDIO_INITINFO(i) { \ - unsigned int *__x__; \ - for (__x__ = (unsigned int *)(i); \ - (char *) __x__ < (((char *)(i)) + sizeof (audio_info_t)); \ - *__x__++ = ~0); \ -} - -/* - * These allow testing for what the user wants to set - */ -#define AUD_INITVALUE (~0) -#define Modify(X) ((unsigned int)(X) != AUD_INITVALUE) -#define Modifys(X) ((X) != (unsigned short)AUD_INITVALUE) -#define Modifyc(X) ((X) != (unsigned char)AUD_INITVALUE) - -/* - * Parameter for the AUDIO_GETDEV ioctl to determine current - * audio devices. - */ -#define MAX_AUDIO_DEV_LEN (16) -typedef struct audio_device { - char name[MAX_AUDIO_DEV_LEN]; - char version[MAX_AUDIO_DEV_LEN]; - char config[MAX_AUDIO_DEV_LEN]; -} audio_device_t; - - -/* - * Ioctl calls for the audio device. - */ - -/* - * AUDIO_GETINFO retrieves the current state of the audio device. - * - * AUDIO_SETINFO copies all fields of the audio_info structure whose - * values are not set to the initialized value (-1) to the device state. - * It performs an implicit AUDIO_GETINFO to return the new state of the - * device. Note that the record.samples and play.samples fields are set - * to the last value before the AUDIO_SETINFO took effect. This allows - * an application to reset the counters while atomically retrieving the - * last value. - * - * AUDIO_DRAIN suspends the calling process until the write buffers are - * empty. - * - * AUDIO_GETDEV returns a structure of type audio_device_t which contains - * three strings. The string "name" is a short identifying string (for - * example, the SBus Fcode name string), the string "version" identifies - * the current version of the device, and the "config" string identifies - * the specific configuration of the audio stream. All fields are - * device-dependent -- see the device specific manual pages for details. - * - * AUDIO_GETDEV_SUNOS returns a number which is an audio device defined - * herein (making it not too portable) - * - * AUDIO_FLUSH stops all playback and recording, clears all queued buffers, - * resets error counters, and restarts recording and playback as appropriate - * for the current sampling mode. - */ -#define AUDIO_GETINFO _IOR('A', 1, audio_info_t) -#define AUDIO_SETINFO _IOWR('A', 2, audio_info_t) -#define AUDIO_DRAIN _IO('A', 3) -#define AUDIO_GETDEV _IOR('A', 4, audio_device_t) -#define AUDIO_GETDEV_SUNOS _IOR('A', 4, int) -#define AUDIO_FLUSH _IO('A', 5) - -/* Define possible audio hardware configurations for - * old SunOS-style AUDIO_GETDEV ioctl */ -#define AUDIO_DEV_UNKNOWN (0) /* not defined */ -#define AUDIO_DEV_AMD (1) /* audioamd device */ -#define AUDIO_DEV_SPEAKERBOX (2) /* dbri device with speakerbox */ -#define AUDIO_DEV_CODEC (3) /* dbri device (internal speaker) */ -#define AUDIO_DEV_CS4231 (5) /* cs4231 device */ - -/* - * The following ioctl sets the audio device into an internal loopback mode, - * if the hardware supports this. The argument is TRUE to set loopback, - * FALSE to reset to normal operation. If the hardware does not support - * internal loopback, the ioctl should fail with EINVAL. - * Causes ADC data to be digitally mixed in and sent to the DAC. - */ -#define AUDIO_DIAG_LOOPBACK _IOW('A', 101, int) - -#endif /* _AUDIOIO_H_ */ diff --git a/include/asm-sparc64/ebus.h b/include/asm-sparc64/ebus.h index 543e4e500a72..7a408a030f52 100644 --- a/include/asm-sparc64/ebus.h +++ b/include/asm-sparc64/ebus.h @@ -79,6 +79,7 @@ extern int ebus_dma_request(struct ebus_dma_info *p, dma_addr_t bus_addr, size_t len); extern void ebus_dma_prepare(struct ebus_dma_info *p, int write); extern unsigned int ebus_dma_residue(struct ebus_dma_info *p); +extern unsigned int ebus_dma_addr(struct ebus_dma_info *p); extern void ebus_dma_enable(struct ebus_dma_info *p, int on); extern struct linux_ebus *ebus_chain; diff --git a/include/asm-sparc64/kbio.h b/include/asm-sparc64/kbio.h deleted file mode 100644 index 3cf496bdf399..000000000000 --- a/include/asm-sparc64/kbio.h +++ /dev/null @@ -1,56 +0,0 @@ -#ifndef __LINUX_KBIO_H -#define __LINUX_KBIO_H - -/* Return keyboard type */ -#define KIOCTYPE _IOR('k', 9, int) -/* Return Keyboard layout */ -#define KIOCLAYOUT _IOR('k', 20, int) - -enum { - TR_NONE, - TR_ASCII, /* keyboard is in regular state */ - TR_EVENT, /* keystrokes sent as firm events */ - TR_UNTRANS_EVENT /* EVENT+up and down+no translation */ -}; - -/* Return the current keyboard translation */ -#define KIOCGTRANS _IOR('k', 5, int) -/* Set the keyboard translation */ -#define KIOCTRANS _IOW('k', 0, int) - -/* Send a keyboard command */ -#define KIOCCMD _IOW('k', 8, int) - -/* Return if keystrokes are being sent to /dev/kbd */ - -/* Set routing of keystrokes to /dev/kbd */ -#define KIOCSDIRECT _IOW('k', 10, int) - -/* Set keyboard leds */ -#define KIOCSLED _IOW('k', 14, unsigned char) - -/* Get keyboard leds */ -#define KIOCGLED _IOR('k', 15, unsigned char) - -/* Used by KIOC[GS]RATE */ -struct kbd_rate { - unsigned char delay; /* Delay in Hz before first repeat. */ - unsigned char rate; /* In characters per second (0..50). */ -}; - -/* Set keyboard rate */ -#define KIOCSRATE _IOW('k', 40, struct kbd_rate) - -/* Get keyboard rate */ -#define KIOCGRATE _IOW('k', 41, struct kbd_rate) - -/* Top bit records if the key is up or down */ -#define KBD_UP 0x80 - -/* Usable information */ -#define KBD_KEYMASK 0x7f - -/* All keys up */ -#define KBD_IDLE 0x75 - -#endif /* __LINUX_KBIO_H */ diff --git a/include/asm-sparc64/mmu_context.h b/include/asm-sparc64/mmu_context.h index 87c43c67866e..08ba72d7722c 100644 --- a/include/asm-sparc64/mmu_context.h +++ b/include/asm-sparc64/mmu_context.h @@ -87,37 +87,35 @@ extern void __flush_tlb_mm(unsigned long, unsigned long); static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk) { unsigned long ctx_valid; + int cpu; + /* Note: page_table_lock is used here to serialize switch_mm + * and activate_mm, and their calls to get_new_mmu_context. + * This use of page_table_lock is unrelated to its other uses. + */ spin_lock(&mm->page_table_lock); - if (CTX_VALID(mm->context)) - ctx_valid = 1; - else - ctx_valid = 0; + ctx_valid = CTX_VALID(mm->context); + if (!ctx_valid) + get_new_mmu_context(mm); + spin_unlock(&mm->page_table_lock); if (!ctx_valid || (old_mm != mm)) { - if (!ctx_valid) - get_new_mmu_context(mm); - load_secondary_context(mm); reload_tlbmiss_state(tsk, mm); } - { - int cpu = smp_processor_id(); - - /* Even if (mm == old_mm) we _must_ check - * the cpu_vm_mask. If we do not we could - * corrupt the TLB state because of how - * smp_flush_tlb_{page,range,mm} on sparc64 - * and lazy tlb switches work. -DaveM - */ - if (!ctx_valid || !cpu_isset(cpu, mm->cpu_vm_mask)) { - cpu_set(cpu, mm->cpu_vm_mask); - __flush_tlb_mm(CTX_HWBITS(mm->context), - SECONDARY_CONTEXT); - } + /* Even if (mm == old_mm) we _must_ check + * the cpu_vm_mask. If we do not we could + * corrupt the TLB state because of how + * smp_flush_tlb_{page,range,mm} on sparc64 + * and lazy tlb switches work. -DaveM + */ + cpu = smp_processor_id(); + if (!ctx_valid || !cpu_isset(cpu, mm->cpu_vm_mask)) { + cpu_set(cpu, mm->cpu_vm_mask); + __flush_tlb_mm(CTX_HWBITS(mm->context), + SECONDARY_CONTEXT); } - spin_unlock(&mm->page_table_lock); } #define deactivate_mm(tsk,mm) do { } while (0) @@ -127,6 +125,10 @@ static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm { int cpu; + /* Note: page_table_lock is used here to serialize switch_mm + * and activate_mm, and their calls to get_new_mmu_context. + * This use of page_table_lock is unrelated to its other uses. + */ spin_lock(&mm->page_table_lock); if (!CTX_VALID(mm->context)) get_new_mmu_context(mm); diff --git a/include/asm-sparc64/termios.h b/include/asm-sparc64/termios.h index 9777a9cca88a..ee26a071c677 100644 --- a/include/asm-sparc64/termios.h +++ b/include/asm-sparc64/termios.h @@ -38,15 +38,6 @@ struct sunos_ttysize { int st_columns; /* Columns on the terminal */ }; -/* Used for packet mode */ -#define TIOCPKT_DATA 0 -#define TIOCPKT_FLUSHREAD 1 -#define TIOCPKT_FLUSHWRITE 2 -#define TIOCPKT_STOP 4 -#define TIOCPKT_START 8 -#define TIOCPKT_NOSTOP 16 -#define TIOCPKT_DOSTOP 32 - struct winsize { unsigned short ws_row; unsigned short ws_col; diff --git a/include/asm-sparc64/tlb.h b/include/asm-sparc64/tlb.h index 66138d959df5..61c01882b562 100644 --- a/include/asm-sparc64/tlb.h +++ b/include/asm-sparc64/tlb.h @@ -58,11 +58,9 @@ static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm, unsigned i static inline void tlb_flush_mmu(struct mmu_gather *mp) { if (mp->need_flush) { + free_pages_and_swap_cache(mp->pages, mp->pages_nr); + mp->pages_nr = 0; mp->need_flush = 0; - if (!tlb_fast_mode(mp)) { - free_pages_and_swap_cache(mp->pages, mp->pages_nr); - mp->pages_nr = 0; - } } } @@ -78,11 +76,9 @@ static inline void tlb_finish_mmu(struct mmu_gather *mp, unsigned long start, un { tlb_flush_mmu(mp); - if (mp->fullmm) { - if (CTX_VALID(mp->mm->context)) - do_flush_tlb_mm(mp->mm); + if (mp->fullmm) mp->fullmm = 0; - } else + else flush_tlb_pending(); /* keep the page table cache within bounds */ @@ -93,11 +89,11 @@ static inline void tlb_finish_mmu(struct mmu_gather *mp, unsigned long start, un static inline void tlb_remove_page(struct mmu_gather *mp, struct page *page) { - mp->need_flush = 1; if (tlb_fast_mode(mp)) { free_page_and_swap_cache(page); return; } + mp->need_flush = 1; mp->pages[mp->pages_nr++] = page; if (mp->pages_nr >= FREE_PTE_NR) tlb_flush_mmu(mp); diff --git a/include/asm-sparc64/vuid_event.h b/include/asm-sparc64/vuid_event.h deleted file mode 100644 index 9ef4d17ad08f..000000000000 --- a/include/asm-sparc64/vuid_event.h +++ /dev/null @@ -1,40 +0,0 @@ -/* SunOS Virtual User Input Device (VUID) compatibility */ - -typedef struct firm_event { - unsigned short id; /* tag for this event */ - unsigned char pair_type; /* unused by X11 */ - unsigned char pair; /* unused by X11 */ - int value; /* VKEY_UP, VKEY_DOWN or delta */ - struct timeval time; -} Firm_event; - -enum { - FE_PAIR_NONE, - FE_PAIR_SET, - FE_PAIR_DELTA, - FE_PAIR_ABSOLUTE -}; - -/* VUID stream formats */ -#define VUID_NATIVE 0 /* Native byte stream format */ -#define VUID_FIRM_EVENT 1 /* send firm_event structures */ - -/* ioctls */ - /* Set input device byte stream format (any of VUID_{NATIVE,FIRM_EVENT}) */ -#define VUIDSFORMAT _IOW('v', 1, int) - /* Retrieve input device byte stream format */ -#define VUIDGFORMAT _IOR('v', 2, int) - -/* Possible tag values */ -/* mouse buttons: */ -#define MS_LEFT 0x7f20 -#define MS_MIDDLE 0x7f21 -#define MS_RIGHT 0x7f22 -/* motion: */ -#define LOC_X_DELTA 0x7f80 -#define LOC_Y_DELTA 0x7f81 -#define LOC_X_ABSOLUTE 0x7f82 /* X compat, unsupported */ -#define LOC_Y_ABSOLUTE 0x7f83 /* X compat, unsupported */ - -#define VKEY_UP 0 -#define VKEY_DOWN 1 diff --git a/include/linux/acct.h b/include/linux/acct.h index 19f70462b3be..93c5b3cdf951 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 ab04b4f9b0db..46a2ba617595 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 9a593ef262ef..1b5f502a4b8f 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 f8f39937e301..dd4e83eba933 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 0e5a86f13b2f..6731977c4c13 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 700ead45084f..f33aeb22c26a 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 2e3f4a47e7d0..6312d6bd43e3 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); } diff --git a/kernel/fork.c b/kernel/fork.c index efac2c58ec7d..158710d22566 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -470,13 +470,6 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) if (clone_flags & CLONE_VM) { atomic_inc(&oldmm->mm_users); mm = oldmm; - /* - * There are cases where the PTL is held to ensure no - * new threads start up in user mode using an mm, which - * allows optimizing out ipis; the tlb_gather_mmu code - * is an example. - */ - spin_unlock_wait(&oldmm->page_table_lock); goto good_mm; } diff --git a/sound/sparc/cs4231.c b/sound/sparc/cs4231.c index f4361c518e46..1f8d27a6152e 100644 --- a/sound/sparc/cs4231.c +++ b/sound/sparc/cs4231.c @@ -61,13 +61,37 @@ MODULE_DESCRIPTION("Sun CS4231"); MODULE_LICENSE("GPL"); MODULE_SUPPORTED_DEVICE("{{Sun,CS4231}}"); -typedef struct snd_cs4231 { - spinlock_t lock; - void __iomem *port; +#ifdef SBUS_SUPPORT +typedef struct sbus_dma_info { + spinlock_t lock; + int dir; + void __iomem *regs; +} sbus_dma_info_t; +#endif + +typedef struct snd_cs4231 cs4231_t; + +typedef struct cs4231_dma_control { + void (*prepare)(struct cs4231_dma_control *dma_cont, int dir); + void (*enable)(struct cs4231_dma_control *dma_cont, int on); + int (*request)(struct cs4231_dma_control *dma_cont, dma_addr_t bus_addr, size_t len); + unsigned int (*address)(struct cs4231_dma_control *dma_cont); + void (*reset)(cs4231_t *chip); + void (*preallocate)(cs4231_t *chip, snd_pcm_t *pcm); #ifdef EBUS_SUPPORT - struct ebus_dma_info eb2c; - struct ebus_dma_info eb2p; + struct ebus_dma_info ebus_info; +#endif +#ifdef SBUS_SUPPORT + struct sbus_dma_info sbus_info; #endif +} cs4231_dma_control_t; + +struct snd_cs4231 { + spinlock_t lock; + void __iomem *port; + + cs4231_dma_control_t p_dma; + cs4231_dma_control_t c_dma; u32 flags; #define CS4231_FLAG_EBUS 0x00000001 @@ -106,7 +130,7 @@ typedef struct snd_cs4231 { unsigned int irq[2]; unsigned int regs_size; struct snd_cs4231 *next; -} cs4231_t; +}; static cs4231_t *cs4231_list; @@ -251,6 +275,15 @@ static cs4231_t *cs4231_list; #define APCPNVA 0x38UL /* APC Play DMA Next Address */ #define APCPNC 0x3cUL /* APC Play Next Count */ +/* Defines for SBUS DMA-routines */ + +#define APCVA 0x0UL /* APC DMA Address */ +#define APCC 0x4UL /* APC Count */ +#define APCNVA 0x8UL /* APC DMA Next Address */ +#define APCNC 0xcUL /* APC Next Count */ +#define APC_PLAY 0x30UL /* Play registers start at 0x30 */ +#define APC_RECORD 0x20UL /* Record registers start at 0x20 */ + /* APCCSR bits */ #define APC_INT_PENDING 0x800000 /* Interrupt Pending */ @@ -569,8 +602,7 @@ static void snd_cs4231_mce_down(cs4231_t *chip) spin_unlock_irqrestore(&chip->lock, flags); } -#ifdef EBUS_SUPPORT -static void snd_cs4231_ebus_advance_dma(struct ebus_dma_info *p, snd_pcm_substream_t *substream, unsigned int *periods_sent) +static void snd_cs4231_advance_dma(struct cs4231_dma_control *dma_cont, snd_pcm_substream_t *substream, unsigned int *periods_sent) { snd_pcm_runtime_t *runtime = substream->runtime; @@ -581,129 +613,41 @@ static void snd_cs4231_ebus_advance_dma(struct ebus_dma_info *p, snd_pcm_substre if (period_size >= (1 << 24)) BUG(); - if (ebus_dma_request(p, runtime->dma_addr + offset, period_size)) + if (dma_cont->request(dma_cont, runtime->dma_addr + offset, period_size)) return; (*periods_sent) = ((*periods_sent) + 1) % runtime->periods; } } -#endif - -#ifdef SBUS_SUPPORT -static void snd_cs4231_sbus_advance_dma(snd_pcm_substream_t *substream, unsigned int *periods_sent) -{ - cs4231_t *chip = snd_pcm_substream_chip(substream); - snd_pcm_runtime_t *runtime = substream->runtime; - - unsigned int period_size = snd_pcm_lib_period_bytes(substream); - unsigned int offset = period_size * (*periods_sent % runtime->periods); - - if (runtime->period_size > 0xffff + 1) - BUG(); - - switch (substream->stream) { - case SNDRV_PCM_STREAM_PLAYBACK: - sbus_writel(runtime->dma_addr + offset, chip->port + APCPNVA); - sbus_writel(period_size, chip->port + APCPNC); - break; - case SNDRV_PCM_STREAM_CAPTURE: - sbus_writel(runtime->dma_addr + offset, chip->port + APCCNVA); - sbus_writel(period_size, chip->port + APCCNC); - break; - } - - (*periods_sent) = (*periods_sent + 1) % runtime->periods; -} -#endif static void cs4231_dma_trigger(snd_pcm_substream_t *substream, unsigned int what, int on) { cs4231_t *chip = snd_pcm_substream_chip(substream); + cs4231_dma_control_t *dma_cont; -#ifdef EBUS_SUPPORT - if (chip->flags & CS4231_FLAG_EBUS) { - if (what & CS4231_PLAYBACK_ENABLE) { - if (on) { - ebus_dma_prepare(&chip->eb2p, 0); - ebus_dma_enable(&chip->eb2p, 1); - snd_cs4231_ebus_advance_dma(&chip->eb2p, - chip->playback_substream, - &chip->p_periods_sent); - } else { - ebus_dma_enable(&chip->eb2p, 0); - } - } - if (what & CS4231_RECORD_ENABLE) { - if (on) { - ebus_dma_prepare(&chip->eb2c, 1); - ebus_dma_enable(&chip->eb2c, 1); - snd_cs4231_ebus_advance_dma(&chip->eb2c, - chip->capture_substream, - &chip->c_periods_sent); - } else { - ebus_dma_enable(&chip->eb2c, 0); - } - } - } else { -#endif -#ifdef SBUS_SUPPORT - u32 csr = sbus_readl(chip->port + APCCSR); - /* I don't know why, but on sbus the period counter must - * only start counting after the first period is sent. - * Therefore this dummy thing. - */ - unsigned int dummy = 0; - - switch (what) { - case CS4231_PLAYBACK_ENABLE: + if (what & CS4231_PLAYBACK_ENABLE) { + dma_cont = &chip->p_dma; if (on) { - csr &= ~APC_XINT_PLAY; - sbus_writel(csr, chip->port + APCCSR); - - csr &= ~APC_PPAUSE; - sbus_writel(csr, chip->port + APCCSR); - - snd_cs4231_sbus_advance_dma(substream, &dummy); - - csr |= APC_GENL_INT | APC_PLAY_INT | APC_XINT_ENA | - APC_XINT_PLAY | APC_XINT_EMPT | APC_XINT_GENL | - APC_XINT_PENA | APC_PDMA_READY; - sbus_writel(csr, chip->port + APCCSR); + dma_cont->prepare(dma_cont, 0); + dma_cont->enable(dma_cont, 1); + snd_cs4231_advance_dma(dma_cont, + chip->playback_substream, + &chip->p_periods_sent); } else { - csr |= APC_PPAUSE; - sbus_writel(csr, chip->port + APCCSR); - - csr &= ~APC_PDMA_READY; - sbus_writel(csr, chip->port + APCCSR); + dma_cont->enable(dma_cont, 0); } - break; - case CS4231_RECORD_ENABLE: + } + if (what & CS4231_RECORD_ENABLE) { + dma_cont = &chip->c_dma; if (on) { - csr &= ~APC_XINT_CAPT; - sbus_writel(csr, chip->port + APCCSR); - - csr &= ~APC_CPAUSE; - sbus_writel(csr, chip->port + APCCSR); - - snd_cs4231_sbus_advance_dma(substream, &dummy); - - csr |= APC_GENL_INT | APC_CAPT_INT | APC_XINT_ENA | - APC_XINT_CAPT | APC_XINT_CEMP | APC_XINT_GENL | - APC_CDMA_READY; - - sbus_writel(csr, chip->port + APCCSR); + dma_cont->prepare(dma_cont, 1); + dma_cont->enable(dma_cont, 1); + snd_cs4231_advance_dma(dma_cont, + chip->capture_substream, + &chip->c_periods_sent); } else { - csr |= APC_CPAUSE; - sbus_writel(csr, chip->port + APCCSR); - - csr &= ~APC_CDMA_READY; - sbus_writel(csr, chip->port + APCCSR); + dma_cont->enable(dma_cont, 0); } - break; - } -#endif -#ifdef EBUS_SUPPORT } -#endif } static int snd_cs4231_trigger(snd_pcm_substream_t *substream, int cmd) @@ -1136,10 +1080,7 @@ static int snd_cs4231_playback_prepare(snd_pcm_substream_t *substream) if (runtime->period_size > 0xffff + 1) BUG(); - snd_cs4231_out(chip, CS4231_PLY_LWR_CNT, (runtime->period_size - 1) & 0x00ff); - snd_cs4231_out(chip, CS4231_PLY_UPR_CNT, (runtime->period_size - 1) >> 8 & 0x00ff); chip->p_periods_sent = 0; - spin_unlock_irqrestore(&chip->lock, flags); return 0; @@ -1171,16 +1112,14 @@ static int snd_cs4231_capture_hw_free(snd_pcm_substream_t *substream) static int snd_cs4231_capture_prepare(snd_pcm_substream_t *substream) { cs4231_t *chip = snd_pcm_substream_chip(substream); - snd_pcm_runtime_t *runtime = substream->runtime; unsigned long flags; spin_lock_irqsave(&chip->lock, flags); chip->image[CS4231_IFACE_CTRL] &= ~(CS4231_RECORD_ENABLE | CS4231_RECORD_PIO); - snd_cs4231_out(chip, CS4231_REC_LWR_CNT, (runtime->period_size - 1) & 0x00ff); - snd_cs4231_out(chip, CS4231_REC_LWR_CNT, (runtime->period_size - 1) >> 8 & 0x00ff); + chip->c_periods_sent = 0; spin_unlock_irqrestore(&chip->lock, flags); return 0; @@ -1199,134 +1138,55 @@ static void snd_cs4231_overrange(cs4231_t *chip) chip->capture_substream->runtime->overrange++; } -static irqreturn_t snd_cs4231_generic_interrupt(cs4231_t *chip) -{ - unsigned long flags; - unsigned char status; - - /*This is IRQ is not raised by the cs4231*/ - if (!(__cs4231_readb(chip, CS4231P(chip, STATUS)) & CS4231_GLOBALIRQ)) - return IRQ_NONE; - - status = snd_cs4231_in(chip, CS4231_IRQ_STATUS); - - if (status & CS4231_TIMER_IRQ) { - if (chip->timer) - snd_timer_interrupt(chip->timer, chip->timer->sticks); - } - - if (status & CS4231_RECORD_IRQ) - snd_cs4231_overrange(chip); - - /* ACK the CS4231 interrupt. */ - spin_lock_irqsave(&chip->lock, flags); - snd_cs4231_outm(chip, CS4231_IRQ_STATUS, ~CS4231_ALL_IRQS | ~status, 0); - spin_unlock_irqrestore(&chip->lock, flags); - - return 0; -} - -#ifdef SBUS_SUPPORT -static irqreturn_t snd_cs4231_sbus_interrupt(int irq, void *dev_id, struct pt_regs *regs) -{ - cs4231_t *chip = dev_id; - - /* ACK the APC interrupt. */ - u32 csr = sbus_readl(chip->port + APCCSR); - - sbus_writel(csr, chip->port + APCCSR); - - if ((chip->image[CS4231_IFACE_CTRL] & CS4231_PLAYBACK_ENABLE) && - (csr & APC_PLAY_INT) && - (csr & APC_XINT_PNVA) && - !(csr & APC_XINT_EMPT)) { - snd_cs4231_sbus_advance_dma(chip->playback_substream, - &chip->p_periods_sent); - snd_pcm_period_elapsed(chip->playback_substream); - } - - if ((chip->image[CS4231_IFACE_CTRL] & CS4231_RECORD_ENABLE) && - (csr & APC_CAPT_INT) && - (csr & APC_XINT_CNVA)) { - snd_cs4231_sbus_advance_dma(chip->capture_substream, - &chip->c_periods_sent); - snd_pcm_period_elapsed(chip->capture_substream); - } - - return snd_cs4231_generic_interrupt(chip); -} -#endif - -#ifdef EBUS_SUPPORT -static void snd_cs4231_ebus_play_callback(struct ebus_dma_info *p, int event, void *cookie) +static void snd_cs4231_play_callback(cs4231_t *cookie) { cs4231_t *chip = cookie; if (chip->image[CS4231_IFACE_CTRL] & CS4231_PLAYBACK_ENABLE) { snd_pcm_period_elapsed(chip->playback_substream); - snd_cs4231_ebus_advance_dma(p, chip->playback_substream, + snd_cs4231_advance_dma(&chip->p_dma, chip->playback_substream, &chip->p_periods_sent); } } -static void snd_cs4231_ebus_capture_callback(struct ebus_dma_info *p, int event, void *cookie) +static void snd_cs4231_capture_callback(cs4231_t *cookie) { cs4231_t *chip = cookie; if (chip->image[CS4231_IFACE_CTRL] & CS4231_RECORD_ENABLE) { snd_pcm_period_elapsed(chip->capture_substream); - snd_cs4231_ebus_advance_dma(p, chip->capture_substream, + snd_cs4231_advance_dma(&chip->c_dma, chip->capture_substream, &chip->c_periods_sent); } } -#endif static snd_pcm_uframes_t snd_cs4231_playback_pointer(snd_pcm_substream_t *substream) { cs4231_t *chip = snd_pcm_substream_chip(substream); - size_t ptr, residue, period_bytes; - + cs4231_dma_control_t *dma_cont = &chip->p_dma; + size_t ptr; + if (!(chip->image[CS4231_IFACE_CTRL] & CS4231_PLAYBACK_ENABLE)) return 0; - period_bytes = snd_pcm_lib_period_bytes(substream); - ptr = period_bytes * chip->p_periods_sent; -#ifdef EBUS_SUPPORT - if (chip->flags & CS4231_FLAG_EBUS) { - residue = ebus_dma_residue(&chip->eb2p); - } else { -#endif -#ifdef SBUS_SUPPORT - residue = sbus_readl(chip->port + APCPC); -#endif -#ifdef EBUS_SUPPORT - } -#endif - ptr += period_bytes - residue; - + ptr = dma_cont->address(dma_cont); + if (ptr != 0) + ptr -= substream->runtime->dma_addr; + return bytes_to_frames(substream->runtime, ptr); } static snd_pcm_uframes_t snd_cs4231_capture_pointer(snd_pcm_substream_t * substream) { cs4231_t *chip = snd_pcm_substream_chip(substream); - size_t ptr, residue, period_bytes; + cs4231_dma_control_t *dma_cont = &chip->c_dma; + size_t ptr; if (!(chip->image[CS4231_IFACE_CTRL] & CS4231_RECORD_ENABLE)) return 0; - period_bytes = snd_pcm_lib_period_bytes(substream); - ptr = period_bytes * chip->c_periods_sent; -#ifdef EBUS_SUPPORT - if (chip->flags & CS4231_FLAG_EBUS) { - residue = ebus_dma_residue(&chip->eb2c); - } else { -#endif -#ifdef SBUS_SUPPORT - residue = sbus_readl(chip->port + APCCC); -#endif -#ifdef EBUS_SUPPORT - } -#endif - ptr += period_bytes - residue; + ptr = dma_cont->address(dma_cont); + if (ptr != 0) + ptr -= substream->runtime->dma_addr; + return bytes_to_frames(substream->runtime, ptr); } @@ -1362,30 +1222,8 @@ static int snd_cs4231_probe(cs4231_t *chip) spin_lock_irqsave(&chip->lock, flags); - /* Reset DMA engine. */ -#ifdef EBUS_SUPPORT - if (chip->flags & CS4231_FLAG_EBUS) { - /* Done by ebus_dma_register */ - } else { -#endif -#ifdef SBUS_SUPPORT - sbus_writel(APC_CHIP_RESET, chip->port + APCCSR); - sbus_writel(0x00, chip->port + APCCSR); - sbus_writel(sbus_readl(chip->port + APCCSR) | APC_CDC_RESET, - chip->port + APCCSR); - - udelay(20); - - sbus_writel(sbus_readl(chip->port + APCCSR) & ~APC_CDC_RESET, - chip->port + APCCSR); - sbus_writel(sbus_readl(chip->port + APCCSR) | (APC_XINT_ENA | - APC_XINT_PENA | - APC_XINT_CENA), - chip->port + APCCSR); -#endif -#ifdef EBUS_SUPPORT - } -#endif + /* Reset DMA engine (sbus only). */ + chip->p_dma.reset(chip); __cs4231_readb(chip, CS4231P(chip, STATUS)); /* clear any pendings IRQ */ __cs4231_writeb(chip, 0, CS4231P(chip, STATUS)); @@ -1505,8 +1343,8 @@ static int snd_cs4231_playback_close(snd_pcm_substream_t *substream) { cs4231_t *chip = snd_pcm_substream_chip(substream); - chip->playback_substream = NULL; snd_cs4231_close(chip, CS4231_MODE_PLAY); + chip->playback_substream = NULL; return 0; } @@ -1515,8 +1353,8 @@ static int snd_cs4231_capture_close(snd_pcm_substream_t *substream) { cs4231_t *chip = snd_pcm_substream_chip(substream); - chip->capture_substream = NULL; snd_cs4231_close(chip, CS4231_MODE_RECORD); + chip->capture_substream = NULL; return 0; } @@ -1571,21 +1409,7 @@ int snd_cs4231_pcm(cs4231_t *chip) pcm->info_flags = SNDRV_PCM_INFO_JOINT_DUPLEX; strcpy(pcm->name, "CS4231"); -#ifdef EBUS_SUPPORT - if (chip->flags & CS4231_FLAG_EBUS) { - snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, - snd_dma_pci_data(chip->dev_u.pdev), - 64*1024, 128*1024); - } else { -#endif -#ifdef SBUS_SUPPORT - snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_SBUS, - snd_dma_sbus_data(chip->dev_u.sdev), - 64*1024, 128*1024); -#endif -#ifdef EBUS_SUPPORT - } -#endif + chip->p_dma.preallocate(chip, pcm); chip->pcm = pcm; @@ -1942,6 +1766,180 @@ out_err: } #ifdef SBUS_SUPPORT + +static irqreturn_t snd_cs4231_sbus_interrupt(int irq, void *dev_id, struct pt_regs *regs) +{ + unsigned long flags; + unsigned char status; + u32 csr; + cs4231_t *chip = dev_id; + + /*This is IRQ is not raised by the cs4231*/ + if (!(__cs4231_readb(chip, CS4231P(chip, STATUS)) & CS4231_GLOBALIRQ)) + return IRQ_NONE; + + /* ACK the APC interrupt. */ + csr = sbus_readl(chip->port + APCCSR); + + sbus_writel(csr, chip->port + APCCSR); + + if ((csr & APC_PDMA_READY) && + (csr & APC_PLAY_INT) && + (csr & APC_XINT_PNVA) && + !(csr & APC_XINT_EMPT)) + snd_cs4231_play_callback(chip); + + if ((csr & APC_CDMA_READY) && + (csr & APC_CAPT_INT) && + (csr & APC_XINT_CNVA) && + !(csr & APC_XINT_EMPT)) + snd_cs4231_capture_callback(chip); + + status = snd_cs4231_in(chip, CS4231_IRQ_STATUS); + + if (status & CS4231_TIMER_IRQ) { + if (chip->timer) + snd_timer_interrupt(chip->timer, chip->timer->sticks); + } + + if ((status & CS4231_RECORD_IRQ) && (csr & APC_CDMA_READY)) + snd_cs4231_overrange(chip); + + /* ACK the CS4231 interrupt. */ + spin_lock_irqsave(&chip->lock, flags); + snd_cs4231_outm(chip, CS4231_IRQ_STATUS, ~CS4231_ALL_IRQS | ~status, 0); + spin_unlock_irqrestore(&chip->lock, flags); + + return 0; +} + +/* + * SBUS DMA routines + */ + +int sbus_dma_request(struct cs4231_dma_control *dma_cont, dma_addr_t bus_addr, size_t len) +{ + unsigned long flags; + u32 test, csr; + int err; + sbus_dma_info_t *base = &dma_cont->sbus_info; + + if (len >= (1 << 24)) + return -EINVAL; + spin_lock_irqsave(&base->lock, flags); + csr = sbus_readl(base->regs + APCCSR); + err = -EINVAL; + test = APC_CDMA_READY; + if ( base->dir == APC_PLAY ) + test = APC_PDMA_READY; + if (!(csr & test)) + goto out; + err = -EBUSY; + csr = sbus_readl(base->regs + APCCSR); + test = APC_XINT_CNVA; + if ( base->dir == APC_PLAY ) + test = APC_XINT_PNVA; + if (!(csr & test)) + goto out; + err = 0; + sbus_writel(bus_addr, base->regs + base->dir + APCNVA); + sbus_writel(len, base->regs + base->dir + APCNC); +out: + spin_unlock_irqrestore(&base->lock, flags); + return err; +} + +void sbus_dma_prepare(struct cs4231_dma_control *dma_cont, int d) +{ + unsigned long flags; + u32 csr, test; + sbus_dma_info_t *base = &dma_cont->sbus_info; + + spin_lock_irqsave(&base->lock, flags); + csr = sbus_readl(base->regs + APCCSR); + test = APC_GENL_INT | APC_PLAY_INT | APC_XINT_ENA | + APC_XINT_PLAY | APC_XINT_PEMP | APC_XINT_GENL | + APC_XINT_PENA; + if ( base->dir == APC_RECORD ) + test = APC_GENL_INT | APC_CAPT_INT | APC_XINT_ENA | + APC_XINT_CAPT | APC_XINT_CEMP | APC_XINT_GENL; + csr |= test; + sbus_writel(csr, base->regs + APCCSR); + spin_unlock_irqrestore(&base->lock, flags); +} + +void sbus_dma_enable(struct cs4231_dma_control *dma_cont, int on) +{ + unsigned long flags; + u32 csr, shift; + sbus_dma_info_t *base = &dma_cont->sbus_info; + + spin_lock_irqsave(&base->lock, flags); + if (!on) { + if (base->dir == APC_PLAY) { + sbus_writel(0, base->regs + base->dir + APCNVA); + sbus_writel(1, base->regs + base->dir + APCC); + } + else + { + sbus_writel(0, base->regs + base->dir + APCNC); + sbus_writel(0, base->regs + base->dir + APCVA); + } + } + udelay(600); + csr = sbus_readl(base->regs + APCCSR); + shift = 0; + if ( base->dir == APC_PLAY ) + shift = 1; + if (on) + csr &= ~(APC_CPAUSE << shift); + else + csr |= (APC_CPAUSE << shift); + sbus_writel(csr, base->regs + APCCSR); + if (on) + csr |= (APC_CDMA_READY << shift); + else + csr &= ~(APC_CDMA_READY << shift); + sbus_writel(csr, base->regs + APCCSR); + + spin_unlock_irqrestore(&base->lock, flags); +} + +unsigned int sbus_dma_addr(struct cs4231_dma_control *dma_cont) +{ + sbus_dma_info_t *base = &dma_cont->sbus_info; + + return sbus_readl(base->regs + base->dir + APCVA); +} + +void sbus_dma_reset(cs4231_t *chip) +{ + sbus_writel(APC_CHIP_RESET, chip->port + APCCSR); + sbus_writel(0x00, chip->port + APCCSR); + sbus_writel(sbus_readl(chip->port + APCCSR) | APC_CDC_RESET, + chip->port + APCCSR); + + udelay(20); + + sbus_writel(sbus_readl(chip->port + APCCSR) & ~APC_CDC_RESET, + chip->port + APCCSR); + sbus_writel(sbus_readl(chip->port + APCCSR) | (APC_XINT_ENA | + APC_XINT_PENA | + APC_XINT_CENA), + chip->port + APCCSR); +} + +void sbus_dma_preallocate(cs4231_t *chip, snd_pcm_t *pcm) +{ + snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_SBUS, + snd_dma_sbus_data(chip->dev_u.sdev), + 64*1024, 128*1024); +} + +/* + * Init and exit routines + */ + static int snd_cs4231_sbus_free(cs4231_t *chip) { if (chip->irq[0]) @@ -1983,6 +1981,8 @@ static int __init snd_cs4231_sbus_create(snd_card_t *card, return -ENOMEM; spin_lock_init(&chip->lock); + spin_lock_init(&chip->c_dma.sbus_info.lock); + spin_lock_init(&chip->p_dma.sbus_info.lock); init_MUTEX(&chip->mce_mutex); init_MUTEX(&chip->open_mutex); chip->card = card; @@ -1998,6 +1998,25 @@ static int __init snd_cs4231_sbus_create(snd_card_t *card, return -EIO; } + chip->c_dma.sbus_info.regs = chip->port; + chip->p_dma.sbus_info.regs = chip->port; + chip->c_dma.sbus_info.dir = APC_RECORD; + chip->p_dma.sbus_info.dir = APC_PLAY; + + chip->p_dma.prepare = sbus_dma_prepare; + chip->p_dma.enable = sbus_dma_enable; + chip->p_dma.request = sbus_dma_request; + chip->p_dma.address = sbus_dma_addr; + chip->p_dma.reset = sbus_dma_reset; + chip->p_dma.preallocate = sbus_dma_preallocate; + + chip->c_dma.prepare = sbus_dma_prepare; + chip->c_dma.enable = sbus_dma_enable; + chip->c_dma.request = sbus_dma_request; + chip->c_dma.address = sbus_dma_addr; + chip->c_dma.reset = sbus_dma_reset; + chip->c_dma.preallocate = sbus_dma_preallocate; + if (request_irq(sdev->irqs[0], snd_cs4231_sbus_interrupt, SA_SHIRQ, "cs4231", chip)) { snd_printdd("cs4231-%d: Unable to grab SBUS IRQ %s\n", @@ -2051,15 +2070,70 @@ static int cs4231_sbus_attach(struct sbus_dev *sdev) #endif #ifdef EBUS_SUPPORT + +static void snd_cs4231_ebus_play_callback(struct ebus_dma_info *p, int event, void *cookie) +{ + cs4231_t *chip = cookie; + + snd_cs4231_play_callback(chip); +} + +static void snd_cs4231_ebus_capture_callback(struct ebus_dma_info *p, int event, void *cookie) +{ + cs4231_t *chip = cookie; + + snd_cs4231_capture_callback(chip); +} + +/* + * EBUS DMA wrappers + */ + +int _ebus_dma_request(struct cs4231_dma_control *dma_cont, dma_addr_t bus_addr, size_t len) +{ + return ebus_dma_request(&dma_cont->ebus_info, bus_addr, len); +} + +void _ebus_dma_enable(struct cs4231_dma_control *dma_cont, int on) +{ + ebus_dma_enable(&dma_cont->ebus_info, on); +} + +void _ebus_dma_prepare(struct cs4231_dma_control *dma_cont, int dir) +{ + ebus_dma_prepare(&dma_cont->ebus_info, dir); +} + +unsigned int _ebus_dma_addr(struct cs4231_dma_control *dma_cont) +{ + return ebus_dma_addr(&dma_cont->ebus_info); +} + +void _ebus_dma_reset(cs4231_t *chip) +{ + return; +} + +void _ebus_dma_preallocate(cs4231_t *chip, snd_pcm_t *pcm) +{ + snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, + snd_dma_pci_data(chip->dev_u.pdev), + 64*1024, 128*1024); +} + +/* + * Init and exit routines + */ + static int snd_cs4231_ebus_free(cs4231_t *chip) { - if (chip->eb2c.regs) { - ebus_dma_unregister(&chip->eb2c); - iounmap(chip->eb2c.regs); + if (chip->c_dma.ebus_info.regs) { + ebus_dma_unregister(&chip->c_dma.ebus_info); + iounmap(chip->c_dma.ebus_info.regs); } - if (chip->eb2p.regs) { - ebus_dma_unregister(&chip->eb2p); - iounmap(chip->eb2p.regs); + if (chip->p_dma.ebus_info.regs) { + ebus_dma_unregister(&chip->p_dma.ebus_info); + iounmap(chip->p_dma.ebus_info.regs); } if (chip->port) @@ -2097,8 +2171,8 @@ static int __init snd_cs4231_ebus_create(snd_card_t *card, return -ENOMEM; spin_lock_init(&chip->lock); - spin_lock_init(&chip->eb2c.lock); - spin_lock_init(&chip->eb2p.lock); + spin_lock_init(&chip->c_dma.ebus_info.lock); + spin_lock_init(&chip->p_dma.ebus_info.lock); init_MUTEX(&chip->mce_mutex); init_MUTEX(&chip->open_mutex); chip->flags |= CS4231_FLAG_EBUS; @@ -2106,43 +2180,57 @@ static int __init snd_cs4231_ebus_create(snd_card_t *card, chip->dev_u.pdev = edev->bus->self; memcpy(&chip->image, &snd_cs4231_original_image, sizeof(snd_cs4231_original_image)); - strcpy(chip->eb2c.name, "cs4231(capture)"); - chip->eb2c.flags = EBUS_DMA_FLAG_USE_EBDMA_HANDLER; - chip->eb2c.callback = snd_cs4231_ebus_capture_callback; - chip->eb2c.client_cookie = chip; - chip->eb2c.irq = edev->irqs[0]; - strcpy(chip->eb2p.name, "cs4231(play)"); - chip->eb2p.flags = EBUS_DMA_FLAG_USE_EBDMA_HANDLER; - chip->eb2p.callback = snd_cs4231_ebus_play_callback; - chip->eb2p.client_cookie = chip; - chip->eb2p.irq = edev->irqs[1]; + strcpy(chip->c_dma.ebus_info.name, "cs4231(capture)"); + chip->c_dma.ebus_info.flags = EBUS_DMA_FLAG_USE_EBDMA_HANDLER; + chip->c_dma.ebus_info.callback = snd_cs4231_ebus_capture_callback; + chip->c_dma.ebus_info.client_cookie = chip; + chip->c_dma.ebus_info.irq = edev->irqs[0]; + strcpy(chip->p_dma.ebus_info.name, "cs4231(play)"); + chip->p_dma.ebus_info.flags = EBUS_DMA_FLAG_USE_EBDMA_HANDLER; + chip->p_dma.ebus_info.callback = snd_cs4231_ebus_play_callback; + chip->p_dma.ebus_info.client_cookie = chip; + chip->p_dma.ebus_info.irq = edev->irqs[1]; + + chip->p_dma.prepare = _ebus_dma_prepare; + chip->p_dma.enable = _ebus_dma_enable; + chip->p_dma.request = _ebus_dma_request; + chip->p_dma.address = _ebus_dma_addr; + chip->p_dma.reset = _ebus_dma_reset; + chip->p_dma.preallocate = _ebus_dma_preallocate; + + chip->c_dma.prepare = _ebus_dma_prepare; + chip->c_dma.enable = _ebus_dma_enable; + chip->c_dma.request = _ebus_dma_request; + chip->c_dma.address = _ebus_dma_addr; + chip->c_dma.reset = _ebus_dma_reset; + chip->c_dma.preallocate = _ebus_dma_preallocate; chip->port = ioremap(edev->resource[0].start, 0x10); - chip->eb2p.regs = ioremap(edev->resource[1].start, 0x10); - chip->eb2c.regs = ioremap(edev->resource[2].start, 0x10); - if (!chip->port || !chip->eb2p.regs || !chip->eb2c.regs) { + chip->p_dma.ebus_info.regs = ioremap(edev->resource[1].start, 0x10); + chip->c_dma.ebus_info.regs = ioremap(edev->resource[2].start, 0x10); + if (!chip->port || !chip->p_dma.ebus_info.regs || !chip->c_dma.ebus_info.regs) { snd_cs4231_ebus_free(chip); snd_printdd("cs4231-%d: Unable to map chip registers.\n", dev); return -EIO; } - if (ebus_dma_register(&chip->eb2c)) { + if (ebus_dma_register(&chip->c_dma.ebus_info)) { snd_cs4231_ebus_free(chip); snd_printdd("cs4231-%d: Unable to register EBUS capture DMA\n", dev); return -EBUSY; } - if (ebus_dma_irq_enable(&chip->eb2c, 1)) { + if (ebus_dma_irq_enable(&chip->c_dma.ebus_info, 1)) { snd_cs4231_ebus_free(chip); snd_printdd("cs4231-%d: Unable to enable EBUS capture IRQ\n", dev); return -EBUSY; } - if (ebus_dma_register(&chip->eb2p)) { + if (ebus_dma_register(&chip->p_dma.ebus_info)) { snd_cs4231_ebus_free(chip); snd_printdd("cs4231-%d: Unable to register EBUS play DMA\n", dev); return -EBUSY; } - if (ebus_dma_irq_enable(&chip->eb2p, 1)) { + if (ebus_dma_irq_enable(&chip->p_dma.ebus_info, 1)) { snd_cs4231_ebus_free(chip); snd_printdd("cs4231-%d: Unable to enable EBUS play IRQ\n", dev); return -EBUSY; |