2005-04-16 16:20:36 -06:00
|
|
|
/*
|
|
|
|
* POSIX message queues filesystem for Linux.
|
|
|
|
*
|
|
|
|
* Copyright (C) 2003,2004 Krzysztof Benedyczak (golbi@mat.uni.torun.pl)
|
2006-10-03 15:23:27 -06:00
|
|
|
* Michal Wronski (michal.wronski@gmail.com)
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
* Spinlocks: Mohamed Abbas (abbas.mohamed@intel.com)
|
|
|
|
* Lockless receive & send, fd based notify:
|
|
|
|
* Manfred Spraul (manfred@colorfullife.com)
|
|
|
|
*
|
2006-05-24 15:09:55 -06:00
|
|
|
* Audit: George Wilson (ltcgcw@us.ibm.com)
|
|
|
|
*
|
2005-04-16 16:20:36 -06:00
|
|
|
* This file is released under the GPL.
|
|
|
|
*/
|
|
|
|
|
2006-01-11 13:17:46 -07:00
|
|
|
#include <linux/capability.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/pagemap.h>
|
|
|
|
#include <linux/file.h>
|
|
|
|
#include <linux/mount.h>
|
|
|
|
#include <linux/namei.h>
|
|
|
|
#include <linux/sysctl.h>
|
|
|
|
#include <linux/poll.h>
|
|
|
|
#include <linux/mqueue.h>
|
|
|
|
#include <linux/msg.h>
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
#include <linux/netlink.h>
|
|
|
|
#include <linux/syscalls.h>
|
2006-05-24 15:09:55 -06:00
|
|
|
#include <linux/audit.h>
|
2005-05-01 09:59:14 -06:00
|
|
|
#include <linux/signal.h>
|
2006-03-26 02:37:17 -07:00
|
|
|
#include <linux/mutex.h>
|
2007-10-19 00:40:14 -06:00
|
|
|
#include <linux/nsproxy.h>
|
|
|
|
#include <linux/pid.h>
|
2009-04-06 20:01:08 -06:00
|
|
|
#include <linux/ipc_namespace.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 02:04:11 -06:00
|
|
|
#include <linux/slab.h>
|
2006-03-26 02:37:17 -07:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
#include <net/sock.h>
|
|
|
|
#include "util.h"
|
|
|
|
|
|
|
|
#define MQUEUE_MAGIC 0x19800202
|
|
|
|
#define DIRENT_SIZE 20
|
|
|
|
#define FILENT_SIZE 80
|
|
|
|
|
|
|
|
#define SEND 0
|
|
|
|
#define RECV 1
|
|
|
|
|
|
|
|
#define STATE_NONE 0
|
|
|
|
#define STATE_PENDING 1
|
|
|
|
#define STATE_READY 2
|
|
|
|
|
|
|
|
struct ext_wait_queue { /* queue of sleeping tasks */
|
|
|
|
struct task_struct *task;
|
|
|
|
struct list_head list;
|
|
|
|
struct msg_msg *msg; /* ptr of loaded message */
|
|
|
|
int state; /* one of STATE_* values */
|
|
|
|
};
|
|
|
|
|
|
|
|
struct mqueue_inode_info {
|
|
|
|
spinlock_t lock;
|
|
|
|
struct inode vfs_inode;
|
|
|
|
wait_queue_head_t wait_q;
|
|
|
|
|
|
|
|
struct msg_msg **messages;
|
|
|
|
struct mq_attr attr;
|
|
|
|
|
|
|
|
struct sigevent notify;
|
2006-10-02 03:17:26 -06:00
|
|
|
struct pid* notify_owner;
|
2005-09-10 01:26:54 -06:00
|
|
|
struct user_struct *user; /* user who created, for accounting */
|
2005-04-16 16:20:36 -06:00
|
|
|
struct sock *notify_sock;
|
|
|
|
struct sk_buff *notify_cookie;
|
|
|
|
|
|
|
|
/* for tasks waiting for free space and messages, respectively */
|
|
|
|
struct ext_wait_queue e_wait_q[2];
|
|
|
|
|
|
|
|
unsigned long qsize; /* size of queue in memory (sum of all msgs) */
|
|
|
|
};
|
|
|
|
|
2007-02-12 01:55:39 -07:00
|
|
|
static const struct inode_operations mqueue_dir_inode_operations;
|
2007-02-12 01:55:35 -07:00
|
|
|
static const struct file_operations mqueue_file_operations;
|
2009-09-21 18:01:09 -06:00
|
|
|
static const struct super_operations mqueue_super_ops;
|
2005-04-16 16:20:36 -06:00
|
|
|
static void remove_notification(struct mqueue_inode_info *info);
|
|
|
|
|
2006-12-06 21:33:20 -07:00
|
|
|
static struct kmem_cache *mqueue_inode_cachep;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
static struct ctl_table_header * mq_sysctl_table;
|
|
|
|
|
|
|
|
static inline struct mqueue_inode_info *MQUEUE_I(struct inode *inode)
|
|
|
|
{
|
|
|
|
return container_of(inode, struct mqueue_inode_info, vfs_inode);
|
|
|
|
}
|
|
|
|
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
/*
|
|
|
|
* This routine should be called with the mq_lock held.
|
|
|
|
*/
|
|
|
|
static inline struct ipc_namespace *__get_ns_from_inode(struct inode *inode)
|
2009-04-06 20:01:08 -06:00
|
|
|
{
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
return get_ipc_ns(inode->i_sb->s_fs_info);
|
2009-04-06 20:01:08 -06:00
|
|
|
}
|
|
|
|
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
static struct ipc_namespace *get_ns_from_inode(struct inode *inode)
|
2009-04-06 20:01:08 -06:00
|
|
|
{
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
struct ipc_namespace *ns;
|
|
|
|
|
|
|
|
spin_lock(&mq_lock);
|
|
|
|
ns = __get_ns_from_inode(inode);
|
|
|
|
spin_unlock(&mq_lock);
|
|
|
|
return ns;
|
2009-04-06 20:01:08 -06:00
|
|
|
}
|
|
|
|
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
static struct inode *mqueue_get_inode(struct super_block *sb,
|
|
|
|
struct ipc_namespace *ipc_ns, int mode,
|
|
|
|
struct mq_attr *attr)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2008-11-13 16:39:18 -07:00
|
|
|
struct user_struct *u = current_user();
|
2005-04-16 16:20:36 -06:00
|
|
|
struct inode *inode;
|
|
|
|
|
|
|
|
inode = new_inode(sb);
|
|
|
|
if (inode) {
|
|
|
|
inode->i_mode = mode;
|
2008-11-13 16:39:06 -07:00
|
|
|
inode->i_uid = current_fsuid();
|
|
|
|
inode->i_gid = current_fsgid();
|
2005-04-16 16:20:36 -06:00
|
|
|
inode->i_mtime = inode->i_ctime = inode->i_atime =
|
|
|
|
CURRENT_TIME;
|
|
|
|
|
|
|
|
if (S_ISREG(mode)) {
|
|
|
|
struct mqueue_inode_info *info;
|
|
|
|
struct task_struct *p = current;
|
|
|
|
unsigned long mq_bytes, mq_msg_tblsz;
|
|
|
|
|
|
|
|
inode->i_fop = &mqueue_file_operations;
|
|
|
|
inode->i_size = FILENT_SIZE;
|
|
|
|
/* mqueue specific info */
|
|
|
|
info = MQUEUE_I(inode);
|
|
|
|
spin_lock_init(&info->lock);
|
|
|
|
init_waitqueue_head(&info->wait_q);
|
|
|
|
INIT_LIST_HEAD(&info->e_wait_q[0].list);
|
|
|
|
INIT_LIST_HEAD(&info->e_wait_q[1].list);
|
2006-10-02 03:17:26 -06:00
|
|
|
info->notify_owner = NULL;
|
2005-04-16 16:20:36 -06:00
|
|
|
info->qsize = 0;
|
|
|
|
info->user = NULL; /* set when all is ok */
|
|
|
|
memset(&info->attr, 0, sizeof(info->attr));
|
2009-04-06 20:01:08 -06:00
|
|
|
info->attr.mq_maxmsg = ipc_ns->mq_msg_max;
|
|
|
|
info->attr.mq_msgsize = ipc_ns->mq_msgsize_max;
|
2005-04-16 16:20:36 -06:00
|
|
|
if (attr) {
|
|
|
|
info->attr.mq_maxmsg = attr->mq_maxmsg;
|
|
|
|
info->attr.mq_msgsize = attr->mq_msgsize;
|
|
|
|
}
|
|
|
|
mq_msg_tblsz = info->attr.mq_maxmsg * sizeof(struct msg_msg *);
|
2010-02-23 00:04:23 -07:00
|
|
|
info->messages = kmalloc(mq_msg_tblsz, GFP_KERNEL);
|
|
|
|
if (!info->messages)
|
|
|
|
goto out_inode;
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
mq_bytes = (mq_msg_tblsz +
|
|
|
|
(info->attr.mq_maxmsg * info->attr.mq_msgsize));
|
|
|
|
|
|
|
|
spin_lock(&mq_lock);
|
|
|
|
if (u->mq_bytes + mq_bytes < u->mq_bytes ||
|
|
|
|
u->mq_bytes + mq_bytes >
|
2010-03-10 16:23:05 -07:00
|
|
|
task_rlimit(p, RLIMIT_MSGQUEUE)) {
|
2005-04-16 16:20:36 -06:00
|
|
|
spin_unlock(&mq_lock);
|
2010-06-05 14:29:45 -06:00
|
|
|
/* mqueue_evict_inode() releases info->messages */
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out_inode;
|
|
|
|
}
|
|
|
|
u->mq_bytes += mq_bytes;
|
|
|
|
spin_unlock(&mq_lock);
|
|
|
|
|
|
|
|
/* all is ok */
|
|
|
|
info->user = get_uid(u);
|
|
|
|
} else if (S_ISDIR(mode)) {
|
2006-10-01 00:29:04 -06:00
|
|
|
inc_nlink(inode);
|
2005-04-16 16:20:36 -06:00
|
|
|
/* Some things misbehave if size == 0 on a directory */
|
|
|
|
inode->i_size = 2 * DIRENT_SIZE;
|
|
|
|
inode->i_op = &mqueue_dir_inode_operations;
|
|
|
|
inode->i_fop = &simple_dir_operations;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return inode;
|
|
|
|
out_inode:
|
|
|
|
iput(inode);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int mqueue_fill_super(struct super_block *sb, void *data, int silent)
|
|
|
|
{
|
|
|
|
struct inode *inode;
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
struct ipc_namespace *ns = data;
|
2010-02-23 00:04:26 -07:00
|
|
|
int error;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
sb->s_blocksize = PAGE_CACHE_SIZE;
|
|
|
|
sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
|
|
|
|
sb->s_magic = MQUEUE_MAGIC;
|
|
|
|
sb->s_op = &mqueue_super_ops;
|
|
|
|
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
inode = mqueue_get_inode(sb, ns, S_IFDIR | S_ISVTX | S_IRWXUGO,
|
|
|
|
NULL);
|
|
|
|
if (!inode) {
|
|
|
|
error = -ENOMEM;
|
|
|
|
goto out;
|
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
sb->s_root = d_alloc_root(inode);
|
|
|
|
if (!sb->s_root) {
|
|
|
|
iput(inode);
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
error = -ENOMEM;
|
2010-02-23 00:04:26 -07:00
|
|
|
goto out;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
2010-02-23 00:04:26 -07:00
|
|
|
error = 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
out:
|
|
|
|
return error;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
[PATCH] VFS: Permit filesystem to override root dentry on mount
Extend the get_sb() filesystem operation to take an extra argument that
permits the VFS to pass in the target vfsmount that defines the mountpoint.
The filesystem is then required to manually set the superblock and root dentry
pointers. For most filesystems, this should be done with simple_set_mnt()
which will set the superblock pointer and then set the root dentry to the
superblock's s_root (as per the old default behaviour).
The get_sb() op now returns an integer as there's now no need to return the
superblock pointer.
This patch permits a superblock to be implicitly shared amongst several mount
points, such as can be done with NFS to avoid potential inode aliasing. In
such a case, simple_set_mnt() would not be called, and instead the mnt_root
and mnt_sb would be set directly.
The patch also makes the following changes:
(*) the get_sb_*() convenience functions in the core kernel now take a vfsmount
pointer argument and return an integer, so most filesystems have to change
very little.
(*) If one of the convenience function is not used, then get_sb() should
normally call simple_set_mnt() to instantiate the vfsmount. This will
always return 0, and so can be tail-called from get_sb().
(*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the
dcache upon superblock destruction rather than shrink_dcache_anon().
This is required because the superblock may now have multiple trees that
aren't actually bound to s_root, but that still need to be cleaned up. The
currently called functions assume that the whole tree is rooted at s_root,
and that anonymous dentries are not the roots of trees which results in
dentries being left unculled.
However, with the way NFS superblock sharing are currently set to be
implemented, these assumptions are violated: the root of the filesystem is
simply a dummy dentry and inode (the real inode for '/' may well be
inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries
with child trees.
[*] Anonymous until discovered from another tree.
(*) The documentation has been adjusted, including the additional bit of
changing ext2_* into foo_* in the documentation.
[akpm@osdl.org: convert ipath_fs, do other stuff]
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 03:02:57 -06:00
|
|
|
static int mqueue_get_sb(struct file_system_type *fs_type,
|
|
|
|
int flags, const char *dev_name,
|
|
|
|
void *data, struct vfsmount *mnt)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
if (!(flags & MS_KERNMOUNT))
|
|
|
|
data = current->nsproxy->ipc_ns;
|
|
|
|
return get_sb_ns(fs_type, flags, data, mqueue_fill_super, mnt);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2008-07-25 20:45:34 -06:00
|
|
|
static void init_once(void *foo)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo;
|
|
|
|
|
2007-05-16 23:10:57 -06:00
|
|
|
inode_init_once(&p->vfs_inode);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
static struct inode *mqueue_alloc_inode(struct super_block *sb)
|
|
|
|
{
|
|
|
|
struct mqueue_inode_info *ei;
|
|
|
|
|
2006-12-06 21:33:17 -07:00
|
|
|
ei = kmem_cache_alloc(mqueue_inode_cachep, GFP_KERNEL);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (!ei)
|
|
|
|
return NULL;
|
|
|
|
return &ei->vfs_inode;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void mqueue_destroy_inode(struct inode *inode)
|
|
|
|
{
|
|
|
|
kmem_cache_free(mqueue_inode_cachep, MQUEUE_I(inode));
|
|
|
|
}
|
|
|
|
|
2010-06-05 14:29:45 -06:00
|
|
|
static void mqueue_evict_inode(struct inode *inode)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
struct mqueue_inode_info *info;
|
|
|
|
struct user_struct *user;
|
|
|
|
unsigned long mq_bytes;
|
|
|
|
int i;
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
struct ipc_namespace *ipc_ns;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2010-06-05 14:29:45 -06:00
|
|
|
end_writeback(inode);
|
|
|
|
|
|
|
|
if (S_ISDIR(inode->i_mode))
|
2005-04-16 16:20:36 -06:00
|
|
|
return;
|
2010-06-05 14:29:45 -06:00
|
|
|
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
ipc_ns = get_ns_from_inode(inode);
|
2005-04-16 16:20:36 -06:00
|
|
|
info = MQUEUE_I(inode);
|
|
|
|
spin_lock(&info->lock);
|
|
|
|
for (i = 0; i < info->attr.mq_curmsgs; i++)
|
|
|
|
free_msg(info->messages[i]);
|
|
|
|
kfree(info->messages);
|
|
|
|
spin_unlock(&info->lock);
|
|
|
|
|
2010-02-23 00:04:24 -07:00
|
|
|
/* Total amount of bytes accounted for the mqueue */
|
|
|
|
mq_bytes = info->attr.mq_maxmsg * (sizeof(struct msg_msg *)
|
|
|
|
+ info->attr.mq_msgsize);
|
2005-04-16 16:20:36 -06:00
|
|
|
user = info->user;
|
|
|
|
if (user) {
|
|
|
|
spin_lock(&mq_lock);
|
|
|
|
user->mq_bytes -= mq_bytes;
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
/*
|
|
|
|
* get_ns_from_inode() ensures that the
|
|
|
|
* (ipc_ns = sb->s_fs_info) is either a valid ipc_ns
|
|
|
|
* to which we now hold a reference, or it is NULL.
|
|
|
|
* We can't put it here under mq_lock, though.
|
|
|
|
*/
|
|
|
|
if (ipc_ns)
|
|
|
|
ipc_ns->mq_queues_count--;
|
2005-04-16 16:20:36 -06:00
|
|
|
spin_unlock(&mq_lock);
|
|
|
|
free_uid(user);
|
|
|
|
}
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
if (ipc_ns)
|
|
|
|
put_ipc_ns(ipc_ns);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
static int mqueue_create(struct inode *dir, struct dentry *dentry,
|
|
|
|
int mode, struct nameidata *nd)
|
|
|
|
{
|
|
|
|
struct inode *inode;
|
|
|
|
struct mq_attr *attr = dentry->d_fsdata;
|
|
|
|
int error;
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
struct ipc_namespace *ipc_ns;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
spin_lock(&mq_lock);
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
ipc_ns = __get_ns_from_inode(dir);
|
|
|
|
if (!ipc_ns) {
|
|
|
|
error = -EACCES;
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
2009-04-06 20:01:08 -06:00
|
|
|
if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
|
|
|
|
!capable(CAP_SYS_RESOURCE)) {
|
2005-04-16 16:20:36 -06:00
|
|
|
error = -ENOSPC;
|
2009-04-06 20:01:08 -06:00
|
|
|
goto out_unlock;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
2009-04-06 20:01:08 -06:00
|
|
|
ipc_ns->mq_queues_count++;
|
2005-04-16 16:20:36 -06:00
|
|
|
spin_unlock(&mq_lock);
|
|
|
|
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
inode = mqueue_get_inode(dir->i_sb, ipc_ns, mode, attr);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (!inode) {
|
|
|
|
error = -ENOMEM;
|
|
|
|
spin_lock(&mq_lock);
|
2009-04-06 20:01:08 -06:00
|
|
|
ipc_ns->mq_queues_count--;
|
|
|
|
goto out_unlock;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
put_ipc_ns(ipc_ns);
|
2005-04-16 16:20:36 -06:00
|
|
|
dir->i_size += DIRENT_SIZE;
|
|
|
|
dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME;
|
|
|
|
|
|
|
|
d_instantiate(dentry, inode);
|
|
|
|
dget(dentry);
|
|
|
|
return 0;
|
2009-04-06 20:01:08 -06:00
|
|
|
out_unlock:
|
2005-04-16 16:20:36 -06:00
|
|
|
spin_unlock(&mq_lock);
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
if (ipc_ns)
|
|
|
|
put_ipc_ns(ipc_ns);
|
2005-04-16 16:20:36 -06:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int mqueue_unlink(struct inode *dir, struct dentry *dentry)
|
|
|
|
{
|
|
|
|
struct inode *inode = dentry->d_inode;
|
|
|
|
|
|
|
|
dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME;
|
|
|
|
dir->i_size -= DIRENT_SIZE;
|
2006-10-01 00:29:03 -06:00
|
|
|
drop_nlink(inode);
|
2005-04-16 16:20:36 -06:00
|
|
|
dput(dentry);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This is routine for system read from queue file.
|
|
|
|
* To avoid mess with doing here some sort of mq_receive we allow
|
|
|
|
* to read only queue size & notification info (the only values
|
|
|
|
* that are interesting from user point of view and aren't accessible
|
|
|
|
* through std routines)
|
|
|
|
*/
|
|
|
|
static ssize_t mqueue_read_file(struct file *filp, char __user *u_data,
|
2008-07-25 02:48:07 -06:00
|
|
|
size_t count, loff_t *off)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2006-12-08 03:37:11 -07:00
|
|
|
struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode);
|
2005-04-16 16:20:36 -06:00
|
|
|
char buffer[FILENT_SIZE];
|
2008-07-25 02:48:07 -06:00
|
|
|
ssize_t ret;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
spin_lock(&info->lock);
|
|
|
|
snprintf(buffer, sizeof(buffer),
|
|
|
|
"QSIZE:%-10lu NOTIFY:%-5d SIGNO:%-5d NOTIFY_PID:%-6d\n",
|
|
|
|
info->qsize,
|
|
|
|
info->notify_owner ? info->notify.sigev_notify : 0,
|
|
|
|
(info->notify_owner &&
|
|
|
|
info->notify.sigev_notify == SIGEV_SIGNAL) ?
|
|
|
|
info->notify.sigev_signo : 0,
|
2008-02-08 05:19:20 -07:00
|
|
|
pid_vnr(info->notify_owner));
|
2005-04-16 16:20:36 -06:00
|
|
|
spin_unlock(&info->lock);
|
|
|
|
buffer[sizeof(buffer)-1] = '\0';
|
|
|
|
|
2008-07-25 02:48:07 -06:00
|
|
|
ret = simple_read_from_buffer(u_data, count, off, buffer,
|
|
|
|
strlen(buffer));
|
|
|
|
if (ret <= 0)
|
|
|
|
return ret;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2006-12-08 03:37:11 -07:00
|
|
|
filp->f_path.dentry->d_inode->i_atime = filp->f_path.dentry->d_inode->i_ctime = CURRENT_TIME;
|
2008-07-25 02:48:07 -06:00
|
|
|
return ret;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2006-06-23 03:05:12 -06:00
|
|
|
static int mqueue_flush_file(struct file *filp, fl_owner_t id)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2006-12-08 03:37:11 -07:00
|
|
|
struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
spin_lock(&info->lock);
|
2006-10-02 03:17:26 -06:00
|
|
|
if (task_tgid(current) == info->notify_owner)
|
2005-04-16 16:20:36 -06:00
|
|
|
remove_notification(info);
|
|
|
|
|
|
|
|
spin_unlock(&info->lock);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned int mqueue_poll_file(struct file *filp, struct poll_table_struct *poll_tab)
|
|
|
|
{
|
2006-12-08 03:37:11 -07:00
|
|
|
struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode);
|
2005-04-16 16:20:36 -06:00
|
|
|
int retval = 0;
|
|
|
|
|
|
|
|
poll_wait(filp, &info->wait_q, poll_tab);
|
|
|
|
|
|
|
|
spin_lock(&info->lock);
|
|
|
|
if (info->attr.mq_curmsgs)
|
|
|
|
retval = POLLIN | POLLRDNORM;
|
|
|
|
|
|
|
|
if (info->attr.mq_curmsgs < info->attr.mq_maxmsg)
|
|
|
|
retval |= POLLOUT | POLLWRNORM;
|
|
|
|
spin_unlock(&info->lock);
|
|
|
|
|
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Adds current to info->e_wait_q[sr] before element with smaller prio */
|
|
|
|
static void wq_add(struct mqueue_inode_info *info, int sr,
|
|
|
|
struct ext_wait_queue *ewp)
|
|
|
|
{
|
|
|
|
struct ext_wait_queue *walk;
|
|
|
|
|
|
|
|
ewp->task = current;
|
|
|
|
|
|
|
|
list_for_each_entry(walk, &info->e_wait_q[sr].list, list) {
|
|
|
|
if (walk->task->static_prio <= current->static_prio) {
|
|
|
|
list_add_tail(&ewp->list, &walk->list);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
list_add_tail(&ewp->list, &info->e_wait_q[sr].list);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Puts current task to sleep. Caller must hold queue lock. After return
|
|
|
|
* lock isn't held.
|
|
|
|
* sr: SEND or RECV
|
|
|
|
*/
|
|
|
|
static int wq_sleep(struct mqueue_inode_info *info, int sr,
|
2010-04-02 14:40:20 -06:00
|
|
|
ktime_t *timeout, struct ext_wait_queue *ewp)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
int retval;
|
|
|
|
signed long time;
|
|
|
|
|
|
|
|
wq_add(info, sr, ewp);
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
|
|
|
|
|
|
|
spin_unlock(&info->lock);
|
2010-04-02 14:40:20 -06:00
|
|
|
time = schedule_hrtimeout_range_clock(timeout,
|
|
|
|
HRTIMER_MODE_ABS, 0, CLOCK_REALTIME);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
while (ewp->state == STATE_PENDING)
|
|
|
|
cpu_relax();
|
|
|
|
|
|
|
|
if (ewp->state == STATE_READY) {
|
|
|
|
retval = 0;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
spin_lock(&info->lock);
|
|
|
|
if (ewp->state == STATE_READY) {
|
|
|
|
retval = 0;
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
|
|
|
if (signal_pending(current)) {
|
|
|
|
retval = -ERESTARTSYS;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (time == 0) {
|
|
|
|
retval = -ETIMEDOUT;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
list_del(&ewp->list);
|
|
|
|
out_unlock:
|
|
|
|
spin_unlock(&info->lock);
|
|
|
|
out:
|
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Returns waiting task that should be serviced first or NULL if none exists
|
|
|
|
*/
|
|
|
|
static struct ext_wait_queue *wq_get_first_waiter(
|
|
|
|
struct mqueue_inode_info *info, int sr)
|
|
|
|
{
|
|
|
|
struct list_head *ptr;
|
|
|
|
|
|
|
|
ptr = info->e_wait_q[sr].list.prev;
|
|
|
|
if (ptr == &info->e_wait_q[sr].list)
|
|
|
|
return NULL;
|
|
|
|
return list_entry(ptr, struct ext_wait_queue, list);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Auxiliary functions to manipulate messages' list */
|
|
|
|
static void msg_insert(struct msg_msg *ptr, struct mqueue_inode_info *info)
|
|
|
|
{
|
|
|
|
int k;
|
|
|
|
|
|
|
|
k = info->attr.mq_curmsgs - 1;
|
|
|
|
while (k >= 0 && info->messages[k]->m_type >= ptr->m_type) {
|
|
|
|
info->messages[k + 1] = info->messages[k];
|
|
|
|
k--;
|
|
|
|
}
|
|
|
|
info->attr.mq_curmsgs++;
|
|
|
|
info->qsize += ptr->m_ts;
|
|
|
|
info->messages[k + 1] = ptr;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct msg_msg *msg_get(struct mqueue_inode_info *info)
|
|
|
|
{
|
|
|
|
info->qsize -= info->messages[--info->attr.mq_curmsgs]->m_ts;
|
|
|
|
return info->messages[info->attr.mq_curmsgs];
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void set_cookie(struct sk_buff *skb, char code)
|
|
|
|
{
|
|
|
|
((char*)skb->data)[NOTIFY_COOKIE_LEN-1] = code;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The next function is only to split too long sys_mq_timedsend
|
|
|
|
*/
|
|
|
|
static void __do_notify(struct mqueue_inode_info *info)
|
|
|
|
{
|
|
|
|
/* notification
|
|
|
|
* invoked when there is registered process and there isn't process
|
|
|
|
* waiting synchronously for message AND state of queue changed from
|
|
|
|
* empty to not empty. Here we are sure that no one is waiting
|
|
|
|
* synchronously. */
|
|
|
|
if (info->notify_owner &&
|
|
|
|
info->attr.mq_curmsgs == 1) {
|
|
|
|
struct siginfo sig_i;
|
|
|
|
switch (info->notify.sigev_notify) {
|
|
|
|
case SIGEV_NONE:
|
|
|
|
break;
|
|
|
|
case SIGEV_SIGNAL:
|
|
|
|
/* sends signal */
|
|
|
|
|
|
|
|
sig_i.si_signo = info->notify.sigev_signo;
|
|
|
|
sig_i.si_errno = 0;
|
|
|
|
sig_i.si_code = SI_MESGQ;
|
|
|
|
sig_i.si_value = info->notify.sigev_value;
|
2009-01-07 19:08:50 -07:00
|
|
|
sig_i.si_pid = task_tgid_nr_ns(current,
|
|
|
|
ns_of_pid(info->notify_owner));
|
2008-11-13 16:39:06 -07:00
|
|
|
sig_i.si_uid = current_uid();
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2006-10-02 03:17:26 -06:00
|
|
|
kill_pid_info(info->notify.sigev_signo,
|
|
|
|
&sig_i, info->notify_owner);
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
case SIGEV_THREAD:
|
|
|
|
set_cookie(info->notify_cookie, NOTIFY_WOKENUP);
|
2007-10-10 22:14:03 -06:00
|
|
|
netlink_sendskb(info->notify_sock, info->notify_cookie);
|
2005-04-16 16:20:36 -06:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
/* after notification unregisters process */
|
2006-10-02 03:17:26 -06:00
|
|
|
put_pid(info->notify_owner);
|
|
|
|
info->notify_owner = NULL;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
wake_up(&info->wait_q);
|
|
|
|
}
|
|
|
|
|
2010-04-02 14:40:20 -06:00
|
|
|
static int prepare_timeout(const struct timespec __user *u_abs_timeout,
|
|
|
|
ktime_t *expires, struct timespec *ts)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2010-04-02 14:40:20 -06:00
|
|
|
if (copy_from_user(ts, u_abs_timeout, sizeof(struct timespec)))
|
|
|
|
return -EFAULT;
|
|
|
|
if (!timespec_valid(ts))
|
|
|
|
return -EINVAL;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2010-04-02 14:40:20 -06:00
|
|
|
*expires = timespec_to_ktime(*ts);
|
|
|
|
return 0;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
static void remove_notification(struct mqueue_inode_info *info)
|
|
|
|
{
|
2006-10-02 03:17:26 -06:00
|
|
|
if (info->notify_owner != NULL &&
|
2005-04-16 16:20:36 -06:00
|
|
|
info->notify.sigev_notify == SIGEV_THREAD) {
|
|
|
|
set_cookie(info->notify_cookie, NOTIFY_REMOVED);
|
2007-10-10 22:14:03 -06:00
|
|
|
netlink_sendskb(info->notify_sock, info->notify_cookie);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
2006-10-02 03:17:26 -06:00
|
|
|
put_pid(info->notify_owner);
|
|
|
|
info->notify_owner = NULL;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2009-04-06 20:01:08 -06:00
|
|
|
static int mq_attr_ok(struct ipc_namespace *ipc_ns, struct mq_attr *attr)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
if (attr->mq_maxmsg <= 0 || attr->mq_msgsize <= 0)
|
|
|
|
return 0;
|
|
|
|
if (capable(CAP_SYS_RESOURCE)) {
|
|
|
|
if (attr->mq_maxmsg > HARD_MSGMAX)
|
|
|
|
return 0;
|
|
|
|
} else {
|
2009-04-06 20:01:08 -06:00
|
|
|
if (attr->mq_maxmsg > ipc_ns->mq_msg_max ||
|
|
|
|
attr->mq_msgsize > ipc_ns->mq_msgsize_max)
|
2005-04-16 16:20:36 -06:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
/* check for overflow */
|
|
|
|
if (attr->mq_msgsize > ULONG_MAX/attr->mq_maxmsg)
|
|
|
|
return 0;
|
2010-02-23 00:04:24 -07:00
|
|
|
if ((unsigned long)(attr->mq_maxmsg * (attr->mq_msgsize
|
|
|
|
+ sizeof (struct msg_msg *))) <
|
2005-04-16 16:20:36 -06:00
|
|
|
(unsigned long)(attr->mq_maxmsg * attr->mq_msgsize))
|
|
|
|
return 0;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Invoked when creating a new queue via sys_mq_open
|
|
|
|
*/
|
2009-04-06 20:01:08 -06:00
|
|
|
static struct file *do_create(struct ipc_namespace *ipc_ns, struct dentry *dir,
|
|
|
|
struct dentry *dentry, int oflag, mode_t mode,
|
|
|
|
struct mq_attr *attr)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2008-11-13 16:39:22 -07:00
|
|
|
const struct cred *cred = current_cred();
|
2008-02-15 15:37:48 -07:00
|
|
|
struct file *result;
|
2005-04-16 16:20:36 -06:00
|
|
|
int ret;
|
|
|
|
|
2008-12-14 02:02:26 -07:00
|
|
|
if (attr) {
|
2010-02-23 00:04:26 -07:00
|
|
|
if (!mq_attr_ok(ipc_ns, attr)) {
|
|
|
|
ret = -EINVAL;
|
2006-01-14 13:29:55 -07:00
|
|
|
goto out;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
/* store for use during create */
|
2008-12-14 02:02:26 -07:00
|
|
|
dentry->d_fsdata = attr;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2009-03-29 17:08:22 -06:00
|
|
|
mode &= ~current_umask();
|
2009-04-06 20:01:08 -06:00
|
|
|
ret = mnt_want_write(ipc_ns->mq_mnt);
|
2008-02-15 15:37:48 -07:00
|
|
|
if (ret)
|
|
|
|
goto out;
|
2005-04-16 16:20:36 -06:00
|
|
|
ret = vfs_create(dir->d_inode, dentry, mode, NULL);
|
|
|
|
dentry->d_fsdata = NULL;
|
|
|
|
if (ret)
|
2008-02-15 15:37:48 -07:00
|
|
|
goto out_drop_write;
|
|
|
|
|
2009-04-06 20:01:08 -06:00
|
|
|
result = dentry_open(dentry, ipc_ns->mq_mnt, oflag, cred);
|
2008-02-15 15:37:48 -07:00
|
|
|
/*
|
|
|
|
* dentry_open() took a persistent mnt_want_write(),
|
|
|
|
* so we can now drop this one.
|
|
|
|
*/
|
2009-04-06 20:01:08 -06:00
|
|
|
mnt_drop_write(ipc_ns->mq_mnt);
|
2008-02-15 15:37:48 -07:00
|
|
|
return result;
|
|
|
|
|
|
|
|
out_drop_write:
|
2009-04-06 20:01:08 -06:00
|
|
|
mnt_drop_write(ipc_ns->mq_mnt);
|
2006-01-14 13:29:55 -07:00
|
|
|
out:
|
|
|
|
dput(dentry);
|
2009-04-06 20:01:08 -06:00
|
|
|
mntput(ipc_ns->mq_mnt);
|
2006-01-14 13:29:55 -07:00
|
|
|
return ERR_PTR(ret);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Opens existing queue */
|
2009-04-06 20:01:08 -06:00
|
|
|
static struct file *do_open(struct ipc_namespace *ipc_ns,
|
|
|
|
struct dentry *dentry, int oflag)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
2010-02-23 00:04:25 -07:00
|
|
|
int ret;
|
2008-11-13 16:39:22 -07:00
|
|
|
const struct cred *cred = current_cred();
|
|
|
|
|
|
|
|
static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
|
|
|
|
MAY_READ | MAY_WRITE };
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2006-01-14 13:29:55 -07:00
|
|
|
if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) {
|
2010-02-23 00:04:25 -07:00
|
|
|
ret = -EINVAL;
|
|
|
|
goto err;
|
2006-01-14 13:29:55 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2008-07-21 22:07:17 -06:00
|
|
|
if (inode_permission(dentry->d_inode, oflag2acc[oflag & O_ACCMODE])) {
|
2010-02-23 00:04:25 -07:00
|
|
|
ret = -EACCES;
|
|
|
|
goto err;
|
2006-01-14 13:29:55 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2009-04-06 20:01:08 -06:00
|
|
|
return dentry_open(dentry, ipc_ns->mq_mnt, oflag, cred);
|
2010-02-23 00:04:25 -07:00
|
|
|
|
|
|
|
err:
|
|
|
|
dput(dentry);
|
|
|
|
mntput(ipc_ns->mq_mnt);
|
|
|
|
return ERR_PTR(ret);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
2009-01-14 06:14:27 -07:00
|
|
|
SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, mode_t, mode,
|
|
|
|
struct mq_attr __user *, u_attr)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
struct dentry *dentry;
|
|
|
|
struct file *filp;
|
|
|
|
char *name;
|
2008-12-14 02:02:26 -07:00
|
|
|
struct mq_attr attr;
|
2005-04-16 16:20:36 -06:00
|
|
|
int fd, error;
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2008-12-14 02:02:26 -07:00
|
|
|
if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
audit_mq_open(oflag, mode, u_attr ? &attr : NULL);
|
2006-05-24 15:09:55 -06:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
if (IS_ERR(name = getname(u_name)))
|
|
|
|
return PTR_ERR(name);
|
|
|
|
|
2008-05-03 13:28:45 -06:00
|
|
|
fd = get_unused_fd_flags(O_CLOEXEC);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (fd < 0)
|
|
|
|
goto out_putname;
|
|
|
|
|
2009-04-06 20:01:08 -06:00
|
|
|
mutex_lock(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex);
|
|
|
|
dentry = lookup_one_len(name, ipc_ns->mq_mnt->mnt_root, strlen(name));
|
2005-04-16 16:20:36 -06:00
|
|
|
if (IS_ERR(dentry)) {
|
|
|
|
error = PTR_ERR(dentry);
|
2010-02-23 00:04:28 -07:00
|
|
|
goto out_putfd;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
2009-04-06 20:01:08 -06:00
|
|
|
mntget(ipc_ns->mq_mnt);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if (oflag & O_CREAT) {
|
|
|
|
if (dentry->d_inode) { /* entry already exists */
|
2007-06-07 10:19:32 -06:00
|
|
|
audit_inode(name, dentry);
|
2010-02-23 00:04:26 -07:00
|
|
|
if (oflag & O_EXCL) {
|
|
|
|
error = -EEXIST;
|
2006-01-14 13:29:55 -07:00
|
|
|
goto out;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2009-04-06 20:01:08 -06:00
|
|
|
filp = do_open(ipc_ns, dentry, oflag);
|
2005-04-16 16:20:36 -06:00
|
|
|
} else {
|
2009-04-06 20:01:08 -06:00
|
|
|
filp = do_create(ipc_ns, ipc_ns->mq_mnt->mnt_root,
|
|
|
|
dentry, oflag, mode,
|
2008-12-14 02:02:26 -07:00
|
|
|
u_attr ? &attr : NULL);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
2006-01-14 13:29:55 -07:00
|
|
|
} else {
|
2010-02-23 00:04:26 -07:00
|
|
|
if (!dentry->d_inode) {
|
|
|
|
error = -ENOENT;
|
2006-01-14 13:29:55 -07:00
|
|
|
goto out;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2007-06-07 10:19:32 -06:00
|
|
|
audit_inode(name, dentry);
|
2009-04-06 20:01:08 -06:00
|
|
|
filp = do_open(ipc_ns, dentry, oflag);
|
2006-01-14 13:29:55 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if (IS_ERR(filp)) {
|
|
|
|
error = PTR_ERR(filp);
|
|
|
|
goto out_putfd;
|
|
|
|
}
|
|
|
|
|
|
|
|
fd_install(fd, filp);
|
|
|
|
goto out_upsem;
|
|
|
|
|
2006-01-14 13:29:55 -07:00
|
|
|
out:
|
|
|
|
dput(dentry);
|
2009-04-06 20:01:08 -06:00
|
|
|
mntput(ipc_ns->mq_mnt);
|
2006-01-14 13:29:55 -07:00
|
|
|
out_putfd:
|
2005-04-16 16:20:36 -06:00
|
|
|
put_unused_fd(fd);
|
|
|
|
fd = error;
|
|
|
|
out_upsem:
|
2009-04-06 20:01:08 -06:00
|
|
|
mutex_unlock(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex);
|
2005-04-16 16:20:36 -06:00
|
|
|
out_putname:
|
|
|
|
putname(name);
|
|
|
|
return fd;
|
|
|
|
}
|
|
|
|
|
2009-01-14 06:14:27 -07:00
|
|
|
SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
int err;
|
|
|
|
char *name;
|
|
|
|
struct dentry *dentry;
|
|
|
|
struct inode *inode = NULL;
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
name = getname(u_name);
|
|
|
|
if (IS_ERR(name))
|
|
|
|
return PTR_ERR(name);
|
|
|
|
|
2009-04-06 20:01:08 -06:00
|
|
|
mutex_lock_nested(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex,
|
2007-03-06 02:42:09 -07:00
|
|
|
I_MUTEX_PARENT);
|
2009-04-06 20:01:08 -06:00
|
|
|
dentry = lookup_one_len(name, ipc_ns->mq_mnt->mnt_root, strlen(name));
|
2005-04-16 16:20:36 -06:00
|
|
|
if (IS_ERR(dentry)) {
|
|
|
|
err = PTR_ERR(dentry);
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!dentry->d_inode) {
|
|
|
|
err = -ENOENT;
|
|
|
|
goto out_err;
|
|
|
|
}
|
|
|
|
|
|
|
|
inode = dentry->d_inode;
|
|
|
|
if (inode)
|
|
|
|
atomic_inc(&inode->i_count);
|
2009-04-06 20:01:08 -06:00
|
|
|
err = mnt_want_write(ipc_ns->mq_mnt);
|
2008-02-15 15:37:34 -07:00
|
|
|
if (err)
|
|
|
|
goto out_err;
|
2005-04-16 16:20:36 -06:00
|
|
|
err = vfs_unlink(dentry->d_parent->d_inode, dentry);
|
2009-04-06 20:01:08 -06:00
|
|
|
mnt_drop_write(ipc_ns->mq_mnt);
|
2005-04-16 16:20:36 -06:00
|
|
|
out_err:
|
|
|
|
dput(dentry);
|
|
|
|
|
|
|
|
out_unlock:
|
2009-04-06 20:01:08 -06:00
|
|
|
mutex_unlock(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex);
|
2005-04-16 16:20:36 -06:00
|
|
|
putname(name);
|
|
|
|
if (inode)
|
|
|
|
iput(inode);
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Pipelined send and receive functions.
|
|
|
|
*
|
|
|
|
* If a receiver finds no waiting message, then it registers itself in the
|
|
|
|
* list of waiting receivers. A sender checks that list before adding the new
|
|
|
|
* message into the message array. If there is a waiting receiver, then it
|
|
|
|
* bypasses the message array and directly hands the message over to the
|
|
|
|
* receiver.
|
|
|
|
* The receiver accepts the message and returns without grabbing the queue
|
|
|
|
* spinlock. Therefore an intermediate STATE_PENDING state and memory barriers
|
|
|
|
* are necessary. The same algorithm is used for sysv semaphores, see
|
2006-03-28 02:56:23 -07:00
|
|
|
* ipc/sem.c for more details.
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
* The same algorithm is used for senders.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* pipelined_send() - send a message directly to the task waiting in
|
|
|
|
* sys_mq_timedreceive() (without inserting message into a queue).
|
|
|
|
*/
|
|
|
|
static inline void pipelined_send(struct mqueue_inode_info *info,
|
|
|
|
struct msg_msg *message,
|
|
|
|
struct ext_wait_queue *receiver)
|
|
|
|
{
|
|
|
|
receiver->msg = message;
|
|
|
|
list_del(&receiver->list);
|
|
|
|
receiver->state = STATE_PENDING;
|
|
|
|
wake_up_process(receiver->task);
|
2005-05-01 09:58:47 -06:00
|
|
|
smp_wmb();
|
2005-04-16 16:20:36 -06:00
|
|
|
receiver->state = STATE_READY;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* pipelined_receive() - if there is task waiting in sys_mq_timedsend()
|
|
|
|
* gets its message and put to the queue (we have one free place for sure). */
|
|
|
|
static inline void pipelined_receive(struct mqueue_inode_info *info)
|
|
|
|
{
|
|
|
|
struct ext_wait_queue *sender = wq_get_first_waiter(info, SEND);
|
|
|
|
|
|
|
|
if (!sender) {
|
|
|
|
/* for poll */
|
|
|
|
wake_up_interruptible(&info->wait_q);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
msg_insert(sender->msg, info);
|
|
|
|
list_del(&sender->list);
|
|
|
|
sender->state = STATE_PENDING;
|
|
|
|
wake_up_process(sender->task);
|
2005-05-01 09:58:47 -06:00
|
|
|
smp_wmb();
|
2005-04-16 16:20:36 -06:00
|
|
|
sender->state = STATE_READY;
|
|
|
|
}
|
|
|
|
|
2009-01-14 06:14:28 -07:00
|
|
|
SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
|
|
|
|
size_t, msg_len, unsigned int, msg_prio,
|
|
|
|
const struct timespec __user *, u_abs_timeout)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
struct file *filp;
|
|
|
|
struct inode *inode;
|
|
|
|
struct ext_wait_queue wait;
|
|
|
|
struct ext_wait_queue *receiver;
|
|
|
|
struct msg_msg *msg_ptr;
|
|
|
|
struct mqueue_inode_info *info;
|
2010-04-02 14:40:20 -06:00
|
|
|
ktime_t expires, *timeout = NULL;
|
|
|
|
struct timespec ts;
|
2005-04-16 16:20:36 -06:00
|
|
|
int ret;
|
|
|
|
|
2008-12-14 01:46:48 -07:00
|
|
|
if (u_abs_timeout) {
|
2010-04-02 14:40:20 -06:00
|
|
|
int res = prepare_timeout(u_abs_timeout, &expires, &ts);
|
|
|
|
if (res)
|
|
|
|
return res;
|
|
|
|
timeout = &expires;
|
2008-12-14 01:46:48 -07:00
|
|
|
}
|
2006-05-24 15:09:55 -06:00
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX))
|
|
|
|
return -EINVAL;
|
|
|
|
|
2010-04-02 14:40:20 -06:00
|
|
|
audit_mq_sendrecv(mqdes, msg_len, msg_prio, timeout ? &ts : NULL);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
filp = fget(mqdes);
|
2010-02-23 00:04:26 -07:00
|
|
|
if (unlikely(!filp)) {
|
|
|
|
ret = -EBADF;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2006-12-08 03:37:11 -07:00
|
|
|
inode = filp->f_path.dentry->d_inode;
|
2010-02-23 00:04:26 -07:00
|
|
|
if (unlikely(filp->f_op != &mqueue_file_operations)) {
|
|
|
|
ret = -EBADF;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out_fput;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
info = MQUEUE_I(inode);
|
2007-06-07 10:19:32 -06:00
|
|
|
audit_inode(NULL, filp->f_path.dentry);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2010-02-23 00:04:26 -07:00
|
|
|
if (unlikely(!(filp->f_mode & FMODE_WRITE))) {
|
|
|
|
ret = -EBADF;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out_fput;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
if (unlikely(msg_len > info->attr.mq_msgsize)) {
|
|
|
|
ret = -EMSGSIZE;
|
|
|
|
goto out_fput;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* First try to allocate memory, before doing anything with
|
|
|
|
* existing queues. */
|
|
|
|
msg_ptr = load_msg(u_msg_ptr, msg_len);
|
|
|
|
if (IS_ERR(msg_ptr)) {
|
|
|
|
ret = PTR_ERR(msg_ptr);
|
|
|
|
goto out_fput;
|
|
|
|
}
|
|
|
|
msg_ptr->m_ts = msg_len;
|
|
|
|
msg_ptr->m_type = msg_prio;
|
|
|
|
|
|
|
|
spin_lock(&info->lock);
|
|
|
|
|
|
|
|
if (info->attr.mq_curmsgs == info->attr.mq_maxmsg) {
|
|
|
|
if (filp->f_flags & O_NONBLOCK) {
|
|
|
|
spin_unlock(&info->lock);
|
|
|
|
ret = -EAGAIN;
|
|
|
|
} else {
|
|
|
|
wait.task = current;
|
|
|
|
wait.msg = (void *) msg_ptr;
|
|
|
|
wait.state = STATE_NONE;
|
|
|
|
ret = wq_sleep(info, SEND, timeout, &wait);
|
|
|
|
}
|
|
|
|
if (ret < 0)
|
|
|
|
free_msg(msg_ptr);
|
|
|
|
} else {
|
|
|
|
receiver = wq_get_first_waiter(info, RECV);
|
|
|
|
if (receiver) {
|
|
|
|
pipelined_send(info, msg_ptr, receiver);
|
|
|
|
} else {
|
|
|
|
/* adds message to the queue */
|
|
|
|
msg_insert(msg_ptr, info);
|
|
|
|
__do_notify(info);
|
|
|
|
}
|
|
|
|
inode->i_atime = inode->i_mtime = inode->i_ctime =
|
|
|
|
CURRENT_TIME;
|
|
|
|
spin_unlock(&info->lock);
|
|
|
|
ret = 0;
|
|
|
|
}
|
|
|
|
out_fput:
|
|
|
|
fput(filp);
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2009-01-14 06:14:28 -07:00
|
|
|
SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
|
|
|
|
size_t, msg_len, unsigned int __user *, u_msg_prio,
|
|
|
|
const struct timespec __user *, u_abs_timeout)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
ssize_t ret;
|
|
|
|
struct msg_msg *msg_ptr;
|
|
|
|
struct file *filp;
|
|
|
|
struct inode *inode;
|
|
|
|
struct mqueue_inode_info *info;
|
|
|
|
struct ext_wait_queue wait;
|
2010-04-02 14:40:20 -06:00
|
|
|
ktime_t expires, *timeout = NULL;
|
|
|
|
struct timespec ts;
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2008-12-14 01:46:48 -07:00
|
|
|
if (u_abs_timeout) {
|
2010-04-02 14:40:20 -06:00
|
|
|
int res = prepare_timeout(u_abs_timeout, &expires, &ts);
|
|
|
|
if (res)
|
|
|
|
return res;
|
|
|
|
timeout = &expires;
|
2008-12-14 01:46:48 -07:00
|
|
|
}
|
2006-05-24 15:09:55 -06:00
|
|
|
|
2010-04-02 14:40:20 -06:00
|
|
|
audit_mq_sendrecv(mqdes, msg_len, 0, timeout ? &ts : NULL);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
filp = fget(mqdes);
|
2010-02-23 00:04:26 -07:00
|
|
|
if (unlikely(!filp)) {
|
|
|
|
ret = -EBADF;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2006-12-08 03:37:11 -07:00
|
|
|
inode = filp->f_path.dentry->d_inode;
|
2010-02-23 00:04:26 -07:00
|
|
|
if (unlikely(filp->f_op != &mqueue_file_operations)) {
|
|
|
|
ret = -EBADF;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out_fput;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
info = MQUEUE_I(inode);
|
2007-06-07 10:19:32 -06:00
|
|
|
audit_inode(NULL, filp->f_path.dentry);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2010-02-23 00:04:26 -07:00
|
|
|
if (unlikely(!(filp->f_mode & FMODE_READ))) {
|
|
|
|
ret = -EBADF;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out_fput;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
/* checks if buffer is big enough */
|
|
|
|
if (unlikely(msg_len < info->attr.mq_msgsize)) {
|
|
|
|
ret = -EMSGSIZE;
|
|
|
|
goto out_fput;
|
|
|
|
}
|
|
|
|
|
|
|
|
spin_lock(&info->lock);
|
|
|
|
if (info->attr.mq_curmsgs == 0) {
|
|
|
|
if (filp->f_flags & O_NONBLOCK) {
|
|
|
|
spin_unlock(&info->lock);
|
|
|
|
ret = -EAGAIN;
|
|
|
|
} else {
|
|
|
|
wait.task = current;
|
|
|
|
wait.state = STATE_NONE;
|
|
|
|
ret = wq_sleep(info, RECV, timeout, &wait);
|
|
|
|
msg_ptr = wait.msg;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
msg_ptr = msg_get(info);
|
|
|
|
|
|
|
|
inode->i_atime = inode->i_mtime = inode->i_ctime =
|
|
|
|
CURRENT_TIME;
|
|
|
|
|
|
|
|
/* There is now free space in queue. */
|
|
|
|
pipelined_receive(info);
|
|
|
|
spin_unlock(&info->lock);
|
|
|
|
ret = 0;
|
|
|
|
}
|
|
|
|
if (ret == 0) {
|
|
|
|
ret = msg_ptr->m_ts;
|
|
|
|
|
|
|
|
if ((u_msg_prio && put_user(msg_ptr->m_type, u_msg_prio)) ||
|
|
|
|
store_msg(u_msg_ptr, msg_ptr, msg_ptr->m_ts)) {
|
|
|
|
ret = -EFAULT;
|
|
|
|
}
|
|
|
|
free_msg(msg_ptr);
|
|
|
|
}
|
|
|
|
out_fput:
|
|
|
|
fput(filp);
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Notes: the case when user wants us to deregister (with NULL as pointer)
|
|
|
|
* and he isn't currently owner of notification, will be silently discarded.
|
|
|
|
* It isn't explicitly defined in the POSIX.
|
|
|
|
*/
|
2009-01-14 06:14:28 -07:00
|
|
|
SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
|
|
|
|
const struct sigevent __user *, u_notification)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
struct file *filp;
|
|
|
|
struct sock *sock;
|
|
|
|
struct inode *inode;
|
|
|
|
struct sigevent notification;
|
|
|
|
struct mqueue_inode_info *info;
|
|
|
|
struct sk_buff *nc;
|
|
|
|
|
2008-12-10 05:16:12 -07:00
|
|
|
if (u_notification) {
|
2005-04-16 16:20:36 -06:00
|
|
|
if (copy_from_user(¬ification, u_notification,
|
|
|
|
sizeof(struct sigevent)))
|
|
|
|
return -EFAULT;
|
2008-12-10 05:16:12 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
audit_mq_notify(mqdes, u_notification ? ¬ification : NULL);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2008-12-10 05:16:12 -07:00
|
|
|
nc = NULL;
|
|
|
|
sock = NULL;
|
|
|
|
if (u_notification != NULL) {
|
2005-04-16 16:20:36 -06:00
|
|
|
if (unlikely(notification.sigev_notify != SIGEV_NONE &&
|
|
|
|
notification.sigev_notify != SIGEV_SIGNAL &&
|
|
|
|
notification.sigev_notify != SIGEV_THREAD))
|
|
|
|
return -EINVAL;
|
|
|
|
if (notification.sigev_notify == SIGEV_SIGNAL &&
|
2005-05-01 09:59:14 -06:00
|
|
|
!valid_signal(notification.sigev_signo)) {
|
2005-04-16 16:20:36 -06:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
if (notification.sigev_notify == SIGEV_THREAD) {
|
2007-11-07 03:42:09 -07:00
|
|
|
long timeo;
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/* create the notify skb */
|
|
|
|
nc = alloc_skb(NOTIFY_COOKIE_LEN, GFP_KERNEL);
|
2010-02-23 00:04:26 -07:00
|
|
|
if (!nc) {
|
|
|
|
ret = -ENOMEM;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
if (copy_from_user(nc->data,
|
|
|
|
notification.sigev_value.sival_ptr,
|
|
|
|
NOTIFY_COOKIE_LEN)) {
|
2010-02-23 00:04:26 -07:00
|
|
|
ret = -EFAULT;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* TODO: add a header? */
|
|
|
|
skb_put(nc, NOTIFY_COOKIE_LEN);
|
|
|
|
/* and attach it to the socket */
|
|
|
|
retry:
|
|
|
|
filp = fget(notification.sigev_signo);
|
2010-02-23 00:04:26 -07:00
|
|
|
if (!filp) {
|
|
|
|
ret = -EBADF;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
sock = netlink_getsockbyfilp(filp);
|
|
|
|
fput(filp);
|
|
|
|
if (IS_ERR(sock)) {
|
|
|
|
ret = PTR_ERR(sock);
|
|
|
|
sock = NULL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2007-11-07 03:42:09 -07:00
|
|
|
timeo = MAX_SCHEDULE_TIMEOUT;
|
2008-06-05 12:23:39 -06:00
|
|
|
ret = netlink_attachskb(sock, nc, &timeo, NULL);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (ret == 1)
|
2010-02-23 00:04:26 -07:00
|
|
|
goto retry;
|
2005-04-16 16:20:36 -06:00
|
|
|
if (ret) {
|
|
|
|
sock = NULL;
|
|
|
|
nc = NULL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
filp = fget(mqdes);
|
2010-02-23 00:04:26 -07:00
|
|
|
if (!filp) {
|
|
|
|
ret = -EBADF;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2006-12-08 03:37:11 -07:00
|
|
|
inode = filp->f_path.dentry->d_inode;
|
2010-02-23 00:04:26 -07:00
|
|
|
if (unlikely(filp->f_op != &mqueue_file_operations)) {
|
|
|
|
ret = -EBADF;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out_fput;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
info = MQUEUE_I(inode);
|
|
|
|
|
|
|
|
ret = 0;
|
|
|
|
spin_lock(&info->lock);
|
|
|
|
if (u_notification == NULL) {
|
2006-10-02 03:17:26 -06:00
|
|
|
if (info->notify_owner == task_tgid(current)) {
|
2005-04-16 16:20:36 -06:00
|
|
|
remove_notification(info);
|
|
|
|
inode->i_atime = inode->i_ctime = CURRENT_TIME;
|
|
|
|
}
|
2006-10-02 03:17:26 -06:00
|
|
|
} else if (info->notify_owner != NULL) {
|
2005-04-16 16:20:36 -06:00
|
|
|
ret = -EBUSY;
|
|
|
|
} else {
|
|
|
|
switch (notification.sigev_notify) {
|
|
|
|
case SIGEV_NONE:
|
|
|
|
info->notify.sigev_notify = SIGEV_NONE;
|
|
|
|
break;
|
|
|
|
case SIGEV_THREAD:
|
|
|
|
info->notify_sock = sock;
|
|
|
|
info->notify_cookie = nc;
|
|
|
|
sock = NULL;
|
|
|
|
nc = NULL;
|
|
|
|
info->notify.sigev_notify = SIGEV_THREAD;
|
|
|
|
break;
|
|
|
|
case SIGEV_SIGNAL:
|
|
|
|
info->notify.sigev_signo = notification.sigev_signo;
|
|
|
|
info->notify.sigev_value = notification.sigev_value;
|
|
|
|
info->notify.sigev_notify = SIGEV_SIGNAL;
|
|
|
|
break;
|
|
|
|
}
|
2006-10-02 03:17:26 -06:00
|
|
|
|
|
|
|
info->notify_owner = get_pid(task_tgid(current));
|
2005-04-16 16:20:36 -06:00
|
|
|
inode->i_atime = inode->i_ctime = CURRENT_TIME;
|
|
|
|
}
|
|
|
|
spin_unlock(&info->lock);
|
|
|
|
out_fput:
|
|
|
|
fput(filp);
|
|
|
|
out:
|
|
|
|
if (sock) {
|
|
|
|
netlink_detachskb(sock, nc);
|
|
|
|
} else if (nc) {
|
|
|
|
dev_kfree_skb(nc);
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2009-01-14 06:14:28 -07:00
|
|
|
SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
|
|
|
|
const struct mq_attr __user *, u_mqstat,
|
|
|
|
struct mq_attr __user *, u_omqstat)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
struct mq_attr mqstat, omqstat;
|
|
|
|
struct file *filp;
|
|
|
|
struct inode *inode;
|
|
|
|
struct mqueue_inode_info *info;
|
|
|
|
|
|
|
|
if (u_mqstat != NULL) {
|
|
|
|
if (copy_from_user(&mqstat, u_mqstat, sizeof(struct mq_attr)))
|
|
|
|
return -EFAULT;
|
|
|
|
if (mqstat.mq_flags & (~O_NONBLOCK))
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
filp = fget(mqdes);
|
2010-02-23 00:04:26 -07:00
|
|
|
if (!filp) {
|
|
|
|
ret = -EBADF;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
|
2006-12-08 03:37:11 -07:00
|
|
|
inode = filp->f_path.dentry->d_inode;
|
2010-02-23 00:04:26 -07:00
|
|
|
if (unlikely(filp->f_op != &mqueue_file_operations)) {
|
|
|
|
ret = -EBADF;
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out_fput;
|
2010-02-23 00:04:26 -07:00
|
|
|
}
|
2005-04-16 16:20:36 -06:00
|
|
|
info = MQUEUE_I(inode);
|
|
|
|
|
|
|
|
spin_lock(&info->lock);
|
|
|
|
|
|
|
|
omqstat = info->attr;
|
|
|
|
omqstat.mq_flags = filp->f_flags & O_NONBLOCK;
|
|
|
|
if (u_mqstat) {
|
2008-12-10 04:58:59 -07:00
|
|
|
audit_mq_getsetattr(mqdes, &mqstat);
|
2009-02-06 15:25:24 -07:00
|
|
|
spin_lock(&filp->f_lock);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (mqstat.mq_flags & O_NONBLOCK)
|
|
|
|
filp->f_flags |= O_NONBLOCK;
|
|
|
|
else
|
|
|
|
filp->f_flags &= ~O_NONBLOCK;
|
2009-02-06 15:25:24 -07:00
|
|
|
spin_unlock(&filp->f_lock);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
inode->i_atime = inode->i_ctime = CURRENT_TIME;
|
|
|
|
}
|
|
|
|
|
|
|
|
spin_unlock(&info->lock);
|
|
|
|
|
|
|
|
ret = 0;
|
|
|
|
if (u_omqstat != NULL && copy_to_user(u_omqstat, &omqstat,
|
|
|
|
sizeof(struct mq_attr)))
|
|
|
|
ret = -EFAULT;
|
|
|
|
|
|
|
|
out_fput:
|
|
|
|
fput(filp);
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2007-02-12 01:55:39 -07:00
|
|
|
static const struct inode_operations mqueue_dir_inode_operations = {
|
2005-04-16 16:20:36 -06:00
|
|
|
.lookup = simple_lookup,
|
|
|
|
.create = mqueue_create,
|
|
|
|
.unlink = mqueue_unlink,
|
|
|
|
};
|
|
|
|
|
2007-02-12 01:55:35 -07:00
|
|
|
static const struct file_operations mqueue_file_operations = {
|
2005-04-16 16:20:36 -06:00
|
|
|
.flush = mqueue_flush_file,
|
|
|
|
.poll = mqueue_poll_file,
|
|
|
|
.read = mqueue_read_file,
|
llseek: automatically add .llseek fop
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.
The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.
New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time. Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.
The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.
Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.
Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.
===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
// but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}
@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}
@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}
@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}
@ fops0 @
identifier fops;
@@
struct file_operations fops = {
...
};
@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
.llseek = llseek_f,
...
};
@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
.read = read_f,
...
};
@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
.write = write_f,
...
};
@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
.open = open_f,
...
};
// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
... .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};
@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
... .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};
// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
... .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};
// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};
// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};
@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+ .llseek = default_llseek, /* write accesses f_pos */
};
// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////
@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
.write = write_f,
.read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};
@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};
@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};
@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
2010-08-15 10:52:59 -06:00
|
|
|
.llseek = default_llseek,
|
2005-04-16 16:20:36 -06:00
|
|
|
};
|
|
|
|
|
2009-09-21 18:01:09 -06:00
|
|
|
static const struct super_operations mqueue_super_ops = {
|
2005-04-16 16:20:36 -06:00
|
|
|
.alloc_inode = mqueue_alloc_inode,
|
|
|
|
.destroy_inode = mqueue_destroy_inode,
|
2010-06-05 14:29:45 -06:00
|
|
|
.evict_inode = mqueue_evict_inode,
|
2005-04-16 16:20:36 -06:00
|
|
|
.statfs = simple_statfs,
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct file_system_type mqueue_fs_type = {
|
|
|
|
.name = "mqueue",
|
|
|
|
.get_sb = mqueue_get_sb,
|
|
|
|
.kill_sb = kill_litter_super,
|
|
|
|
};
|
|
|
|
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
int mq_init_ns(struct ipc_namespace *ns)
|
|
|
|
{
|
|
|
|
ns->mq_queues_count = 0;
|
|
|
|
ns->mq_queues_max = DFLT_QUEUESMAX;
|
|
|
|
ns->mq_msg_max = DFLT_MSGMAX;
|
|
|
|
ns->mq_msgsize_max = DFLT_MSGSIZEMAX;
|
|
|
|
|
|
|
|
ns->mq_mnt = kern_mount_data(&mqueue_fs_type, ns);
|
|
|
|
if (IS_ERR(ns->mq_mnt)) {
|
|
|
|
int err = PTR_ERR(ns->mq_mnt);
|
|
|
|
ns->mq_mnt = NULL;
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void mq_clear_sbinfo(struct ipc_namespace *ns)
|
|
|
|
{
|
|
|
|
ns->mq_mnt->mnt_sb->s_fs_info = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
void mq_put_mnt(struct ipc_namespace *ns)
|
|
|
|
{
|
|
|
|
mntput(ns->mq_mnt);
|
|
|
|
}
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
static int __init init_mqueue_fs(void)
|
|
|
|
{
|
|
|
|
int error;
|
|
|
|
|
|
|
|
mqueue_inode_cachep = kmem_cache_create("mqueue_inode_cache",
|
|
|
|
sizeof(struct mqueue_inode_info), 0,
|
2007-07-19 19:11:58 -06:00
|
|
|
SLAB_HWCACHE_ALIGN, init_once);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (mqueue_inode_cachep == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2010-02-23 00:04:27 -07:00
|
|
|
/* ignore failures - they are not fatal */
|
2009-04-06 20:01:11 -06:00
|
|
|
mq_sysctl_table = mq_register_sysctl_table();
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
error = register_filesystem(&mqueue_fs_type);
|
|
|
|
if (error)
|
|
|
|
goto out_sysctl;
|
|
|
|
|
namespaces: ipc namespaces: implement support for posix msqueues
Implement multiple mounts of the mqueue file system, and link it to usage
of CLONE_NEWIPC.
Each ipc ns has a corresponding mqueuefs superblock. When a user does
clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an
internal mount of a new mqueuefs sb linked to the new ipc ns.
When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the
mqueuefs superblock.
Posix message queues can be worked with both through the mq_* system calls
(see mq_overview(7)), and through the VFS through the mqueue mount. Any
usage of mq_open() and friends will work with the acting task's ipc
namespace. Any actions through the VFS will work with the mqueuefs in
which the file was created. So if a user doesn't remount mqueuefs after
unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls
/dev/mqueue".
If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns,
ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1)
ipc_ns:1 will be freed, (2) it's superblock will live on until task b
umounts the corresponding mqueuefs, and vfs actions will continue to
succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to
the deceased ipc_ns:1.
To make this happen, we must protect the ipc reference count when
a) a task exits and drops its ipcns->count, since it might be dropping
it to 0 and freeing the ipcns
b) a task accesses the ipcns through its mqueuefs interface, since it
bumps the ipcns refcount and might race with the last task in the ipcns
exiting.
So the kref is changed to an atomic_t so we can use
atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns
through ns = mqueuefs_sb->s_fs_info is protected by the same lock.
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 20:01:10 -06:00
|
|
|
spin_lock_init(&mq_lock);
|
|
|
|
|
|
|
|
init_ipc_ns.mq_mnt = kern_mount_data(&mqueue_fs_type, &init_ipc_ns);
|
2009-04-06 20:01:08 -06:00
|
|
|
if (IS_ERR(init_ipc_ns.mq_mnt)) {
|
|
|
|
error = PTR_ERR(init_ipc_ns.mq_mnt);
|
2005-04-16 16:20:36 -06:00
|
|
|
goto out_filesystem;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
out_filesystem:
|
|
|
|
unregister_filesystem(&mqueue_fs_type);
|
|
|
|
out_sysctl:
|
|
|
|
if (mq_sysctl_table)
|
|
|
|
unregister_sysctl_table(mq_sysctl_table);
|
2006-09-27 02:49:40 -06:00
|
|
|
kmem_cache_destroy(mqueue_inode_cachep);
|
2005-04-16 16:20:36 -06:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
__initcall(init_mqueue_fs);
|