diff options
author | Serge E. Hallyn <serue@us.ibm.com> | 2009-04-06 19:01:10 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-04-07 08:31:09 -0700 |
commit | 7eafd7c74c3f2e67c27621b987b28397110d643f (patch) | |
tree | b4621aab78b6303f20386096c230b993044a4db7 /include | |
parent | 614b84cf4e4a920d2af32b8f147ea1e3b8c27ea6 (diff) | |
download | linux-3.10-7eafd7c74c3f2e67c27621b987b28397110d643f.tar.gz linux-3.10-7eafd7c74c3f2e67c27621b987b28397110d643f.tar.bz2 linux-3.10-7eafd7c74c3f2e67c27621b987b28397110d643f.zip |
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>
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/ipc_namespace.h | 16 |
1 files changed, 7 insertions, 9 deletions
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 3e6fcacebe8..3392d50de35 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -25,7 +25,7 @@ struct ipc_ids { }; struct ipc_namespace { - struct kref kref; + atomic_t count; struct ipc_ids ids[3]; int sem_ctls[4]; @@ -61,6 +61,7 @@ struct ipc_namespace { extern struct ipc_namespace init_ipc_ns; extern atomic_t nr_ipc_ns; +extern spinlock_t mq_lock; #if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC) #define INIT_IPC_NS(ns) .ns = &init_ipc_ns, #else @@ -82,18 +83,18 @@ static inline int ipcns_notify(unsigned long l) { return 0; } #endif /* CONFIG_SYSVIPC */ #ifdef CONFIG_POSIX_MQUEUE -extern void mq_init_ns(struct ipc_namespace *ns); +extern int mq_init_ns(struct ipc_namespace *ns); /* default values */ #define DFLT_QUEUESMAX 256 /* max number of message queues */ #define DFLT_MSGMAX 10 /* max number of messages in each queue */ #define HARD_MSGMAX (131072/sizeof(void *)) #define DFLT_MSGSIZEMAX 8192 /* max message size */ #else -#define mq_init_ns(ns) ((void) 0) +static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; } #endif #if defined(CONFIG_IPC_NS) -extern void free_ipc_ns(struct kref *kref); +extern void free_ipc_ns(struct ipc_namespace *ns); extern struct ipc_namespace *copy_ipcs(unsigned long flags, struct ipc_namespace *ns); extern void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, @@ -103,14 +104,11 @@ extern void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) { if (ns) - kref_get(&ns->kref); + atomic_inc(&ns->count); return ns; } -static inline void put_ipc_ns(struct ipc_namespace *ns) -{ - kref_put(&ns->kref, free_ipc_ns); -} +extern void put_ipc_ns(struct ipc_namespace *ns); #else static inline struct ipc_namespace *copy_ipcs(unsigned long flags, struct ipc_namespace *ns) |