2008-02-08 21:18:22 +09:00
|
|
|
#ifndef __IPC_NAMESPACE_H__
|
|
|
|
#define __IPC_NAMESPACE_H__
|
|
|
|
|
|
|
|
#include <linux/err.h>
|
2008-02-08 21:18:57 +09:00
|
|
|
#include <linux/idr.h>
|
|
|
|
#include <linux/rwsem.h>
|
2008-04-29 17:00:42 +09:00
|
|
|
#include <linux/notifier.h>
|
2011-03-24 08:43:24 +09:00
|
|
|
#include <linux/nsproxy.h>
|
2008-04-29 17:00:42 +09:00
|
|
|
|
|
|
|
/*
|
|
|
|
* ipc namespace events
|
|
|
|
*/
|
|
|
|
#define IPCNS_MEMCHANGED 0x00000001 /* Notify lowmem size changed */
|
2008-04-29 17:00:44 +09:00
|
|
|
#define IPCNS_CREATED 0x00000002 /* Notify new ipc namespace created */
|
|
|
|
#define IPCNS_REMOVED 0x00000003 /* Notify ipc namespace removed */
|
2008-04-29 17:00:42 +09:00
|
|
|
|
|
|
|
#define IPCNS_CALLBACK_PRI 0
|
|
|
|
|
2011-03-24 08:43:23 +09:00
|
|
|
struct user_namespace;
|
2008-02-08 21:18:57 +09:00
|
|
|
|
|
|
|
struct ipc_ids {
|
|
|
|
int in_use;
|
|
|
|
unsigned short seq;
|
|
|
|
unsigned short seq_max;
|
|
|
|
struct rw_semaphore rw_mutex;
|
|
|
|
struct idr ipcs_idr;
|
|
|
|
};
|
2008-02-08 21:18:22 +09:00
|
|
|
|
|
|
|
struct ipc_namespace {
|
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>
2009-04-07 11:01:10 +09:00
|
|
|
atomic_t count;
|
2008-02-08 21:18:57 +09:00
|
|
|
struct ipc_ids ids[3];
|
2008-02-08 21:18:22 +09:00
|
|
|
|
|
|
|
int sem_ctls[4];
|
|
|
|
int used_sems;
|
|
|
|
|
|
|
|
int msg_ctlmax;
|
|
|
|
int msg_ctlmnb;
|
|
|
|
int msg_ctlmni;
|
|
|
|
atomic_t msg_bytes;
|
|
|
|
atomic_t msg_hdrs;
|
2008-07-25 17:48:08 +09:00
|
|
|
int auto_msgmni;
|
2008-02-08 21:18:22 +09:00
|
|
|
|
|
|
|
size_t shm_ctlmax;
|
|
|
|
size_t shm_ctlall;
|
|
|
|
int shm_ctlmni;
|
|
|
|
int shm_tot;
|
2011-07-27 08:08:48 +09:00
|
|
|
/*
|
|
|
|
* Defines whether IPC_RMID is forced for _all_ shm segments regardless
|
|
|
|
* of shmctl()
|
|
|
|
*/
|
|
|
|
int shm_rmid_forced;
|
2008-04-29 17:00:42 +09:00
|
|
|
|
|
|
|
struct notifier_block ipcns_nb;
|
2009-04-07 11:01:08 +09:00
|
|
|
|
|
|
|
/* The kern_mount of the mqueuefs sb. We take a ref on it */
|
|
|
|
struct vfsmount *mq_mnt;
|
|
|
|
|
|
|
|
/* # queues in this ns, protected by mq_lock */
|
|
|
|
unsigned int mq_queues_count;
|
|
|
|
|
|
|
|
/* next fields are set through sysctl */
|
|
|
|
unsigned int mq_queues_max; /* initialized to DFLT_QUEUESMAX */
|
|
|
|
unsigned int mq_msg_max; /* initialized to DFLT_MSGMAX */
|
|
|
|
unsigned int mq_msgsize_max; /* initialized to DFLT_MSGSIZEMAX */
|
|
|
|
|
2011-03-24 08:43:23 +09:00
|
|
|
/* user_ns which owns the ipc ns */
|
|
|
|
struct user_namespace *user_ns;
|
2008-02-08 21:18:22 +09:00
|
|
|
};
|
|
|
|
|
|
|
|
extern struct ipc_namespace init_ipc_ns;
|
2008-04-29 17:00:40 +09:00
|
|
|
extern atomic_t nr_ipc_ns;
|
2008-02-08 21:18:22 +09:00
|
|
|
|
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>
2009-04-07 11:01:10 +09:00
|
|
|
extern spinlock_t mq_lock;
|
2008-04-29 17:00:42 +09:00
|
|
|
|
2009-04-07 11:01:08 +09:00
|
|
|
#ifdef CONFIG_SYSVIPC
|
2008-04-29 17:00:42 +09:00
|
|
|
extern int register_ipcns_notifier(struct ipc_namespace *);
|
2008-04-29 17:00:45 +09:00
|
|
|
extern int cond_register_ipcns_notifier(struct ipc_namespace *);
|
2008-07-25 17:48:08 +09:00
|
|
|
extern void unregister_ipcns_notifier(struct ipc_namespace *);
|
2008-04-29 17:00:42 +09:00
|
|
|
extern int ipcns_notify(unsigned long);
|
2011-07-27 08:08:48 +09:00
|
|
|
extern void shm_destroy_orphaned(struct ipc_namespace *ns);
|
2008-04-29 17:00:42 +09:00
|
|
|
#else /* CONFIG_SYSVIPC */
|
2009-04-07 11:01:08 +09:00
|
|
|
static inline int register_ipcns_notifier(struct ipc_namespace *ns)
|
|
|
|
{ return 0; }
|
|
|
|
static inline int cond_register_ipcns_notifier(struct ipc_namespace *ns)
|
|
|
|
{ return 0; }
|
|
|
|
static inline void unregister_ipcns_notifier(struct ipc_namespace *ns) { }
|
|
|
|
static inline int ipcns_notify(unsigned long l) { return 0; }
|
2011-07-27 08:08:48 +09:00
|
|
|
static inline void shm_destroy_orphaned(struct ipc_namespace *ns) {}
|
2008-04-29 17:00:42 +09:00
|
|
|
#endif /* CONFIG_SYSVIPC */
|
2008-02-08 21:18:22 +09:00
|
|
|
|
2009-04-07 11:01:08 +09:00
|
|
|
#ifdef CONFIG_POSIX_MQUEUE
|
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>
2009-04-07 11:01:10 +09:00
|
|
|
extern int mq_init_ns(struct ipc_namespace *ns);
|
2009-04-07 11:01:08 +09:00
|
|
|
/* default values */
|
ipc/mqueue: cleanup definition names and locations
Since commit b231cca4381e ("message queues: increase range limits") on
Oct 18, 2008, calls to mq_open() that did not pass in an attribute
struct and expected to get default values for the size of the queue and
the max message size now get the system wide maximums instead of
hardwired defaults like they used to get.
This was uncovered when one of the earlier patches in this patch set
increased the default system wide maximums at the same time it increased
the hard ceiling on the system wide maximums (a customer specifically
needed the hard ceiling brought back up, the new ceiling that commit
b231cca4381e introduced was too low for their production systems). By
increasing the default maximums and not realising they were tied to any
attempt to create a message queue without an attribute struct, I had
inadvertently made it such that all message queue creation attempts
without an attribute struct were failing because the new default
maximums would create a queue that exceeded the default rlimit for
message queue bytes.
As a result, the system wide defaults were brought back down to their
previous levels, and the system wide ceilings on the maximums were
raised to meet the customer's needs. However, the fact that the no
attribute struct behavior of mq_open() could be broken by changing the
system wide maximums for message queues was seen as fundamentally broken
itself. So we hardwired the no attribute case back like it used to be.
But, then we realized that on the very off chance that some piece of
software in the wild depended on that behavior, we could work around
that issue by adding two new knobs to /proc that allowed setting the
defaults for message queues created without an attr struct separately
from the system wide maximums.
What is not an option IMO is to leave the current behavior in place. No
piece of software should ever rely on setting the system wide maximums
in order to get a desired message queue. Such a reliance would be so
fundamentally multitasking OS unfriendly as to not really be tolerable.
Fortunately, we don't know of any software in the wild that uses this
except for a regression test program that caught the issue in the first
place. If there is though, we have made accommodations with the two new
/proc knobs (and that's all the accommodations such fundamentally broken
software can be allowed)..
This patch:
The various defines for minimums and maximums of the sysctl controllable
mqueue values are scattered amongst different files and named
inconsistently. Move them all into ipc_namespace.h and make them have
consistent names. Additionally, make the number of queues per namespace
also have a minimum and maximum and use the same sysctl function as the
other two settable variables.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Amerigo Wang <amwang@redhat.com>
Cc: Joe Korty <joe.korty@ccur.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-01 08:26:28 +09:00
|
|
|
#define MIN_QUEUESMAX 1
|
2009-04-07 11:01:08 +09:00
|
|
|
#define DFLT_QUEUESMAX 256 /* max number of message queues */
|
ipc/mqueue: cleanup definition names and locations
Since commit b231cca4381e ("message queues: increase range limits") on
Oct 18, 2008, calls to mq_open() that did not pass in an attribute
struct and expected to get default values for the size of the queue and
the max message size now get the system wide maximums instead of
hardwired defaults like they used to get.
This was uncovered when one of the earlier patches in this patch set
increased the default system wide maximums at the same time it increased
the hard ceiling on the system wide maximums (a customer specifically
needed the hard ceiling brought back up, the new ceiling that commit
b231cca4381e introduced was too low for their production systems). By
increasing the default maximums and not realising they were tied to any
attempt to create a message queue without an attribute struct, I had
inadvertently made it such that all message queue creation attempts
without an attribute struct were failing because the new default
maximums would create a queue that exceeded the default rlimit for
message queue bytes.
As a result, the system wide defaults were brought back down to their
previous levels, and the system wide ceilings on the maximums were
raised to meet the customer's needs. However, the fact that the no
attribute struct behavior of mq_open() could be broken by changing the
system wide maximums for message queues was seen as fundamentally broken
itself. So we hardwired the no attribute case back like it used to be.
But, then we realized that on the very off chance that some piece of
software in the wild depended on that behavior, we could work around
that issue by adding two new knobs to /proc that allowed setting the
defaults for message queues created without an attr struct separately
from the system wide maximums.
What is not an option IMO is to leave the current behavior in place. No
piece of software should ever rely on setting the system wide maximums
in order to get a desired message queue. Such a reliance would be so
fundamentally multitasking OS unfriendly as to not really be tolerable.
Fortunately, we don't know of any software in the wild that uses this
except for a regression test program that caught the issue in the first
place. If there is though, we have made accommodations with the two new
/proc knobs (and that's all the accommodations such fundamentally broken
software can be allowed)..
This patch:
The various defines for minimums and maximums of the sysctl controllable
mqueue values are scattered amongst different files and named
inconsistently. Move them all into ipc_namespace.h and make them have
consistent names. Additionally, make the number of queues per namespace
also have a minimum and maximum and use the same sysctl function as the
other two settable variables.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Amerigo Wang <amwang@redhat.com>
Cc: Joe Korty <joe.korty@ccur.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-01 08:26:28 +09:00
|
|
|
#define HARD_QUEUESMAX 1024
|
|
|
|
#define MIN_MSGMAX 1
|
ipc/mqueue: switch back to using non-max values on create
Commit b231cca4381e ("message queues: increase range limits") changed
how we create a queue that does not include an attr struct passed to
open so that it creates the queue with whatever the maximum values are.
However, if the admin has set the maximums to allow flexibility in
creating a queue (aka, both a large size and large queue are allowed,
but combined they create a queue too large for the RLIMIT_MSGQUEUE of
the user), then attempts to create a queue without an attr struct will
fail. Switch back to using acceptable defaults regardless of what the
maximums are.
Note: so far, we only know of a few applications that rely on this
behavior (specifically, set the maximums in /proc, then run the
application which calls mq_open() without passing in an attr struct, and
the application expects the newly created message queue to have the
maximum sizes that were set in /proc used on the mq_open() call, and all
of those applications that we know of are actually part of regression
test suites that were coded to do something like this:
for size in 4096 65536 $((1024 * 1024)) $((16 * 1024 * 1024)); do
echo $size > /proc/sys/fs/mqueue/msgsize_max
mq_open || echo "Error opening mq with size $size"
done
These test suites that depend on any behavior like this are broken. The
concept that programs should rely upon the system wide maximum in order
to get their desired results instead of simply using a attr struct to
specify what they want is fundamentally unfriendly programming practice
for any multi-tasking OS.
Fixing this will break those few apps that we know of (and those app
authors recognize the brokenness of their code and the need to fix it).
However, the following patch "mqueue: separate mqueue default value"
allows a workaround in the form of new knobs for the default msg queue
creation parameters for any software out there that we don't already
know about that might rely on this behavior at the moment.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: Amerigo Wang <amwang@redhat.com>
Cc: Joe Korty <joe.korty@ccur.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-01 08:26:29 +09:00
|
|
|
#define DFLT_MSG 10U
|
2009-04-07 11:01:08 +09:00
|
|
|
#define DFLT_MSGMAX 10 /* max number of messages in each queue */
|
2009-12-16 09:47:36 +09:00
|
|
|
#define HARD_MSGMAX (32768*sizeof(void *)/4)
|
ipc/mqueue: cleanup definition names and locations
Since commit b231cca4381e ("message queues: increase range limits") on
Oct 18, 2008, calls to mq_open() that did not pass in an attribute
struct and expected to get default values for the size of the queue and
the max message size now get the system wide maximums instead of
hardwired defaults like they used to get.
This was uncovered when one of the earlier patches in this patch set
increased the default system wide maximums at the same time it increased
the hard ceiling on the system wide maximums (a customer specifically
needed the hard ceiling brought back up, the new ceiling that commit
b231cca4381e introduced was too low for their production systems). By
increasing the default maximums and not realising they were tied to any
attempt to create a message queue without an attribute struct, I had
inadvertently made it such that all message queue creation attempts
without an attribute struct were failing because the new default
maximums would create a queue that exceeded the default rlimit for
message queue bytes.
As a result, the system wide defaults were brought back down to their
previous levels, and the system wide ceilings on the maximums were
raised to meet the customer's needs. However, the fact that the no
attribute struct behavior of mq_open() could be broken by changing the
system wide maximums for message queues was seen as fundamentally broken
itself. So we hardwired the no attribute case back like it used to be.
But, then we realized that on the very off chance that some piece of
software in the wild depended on that behavior, we could work around
that issue by adding two new knobs to /proc that allowed setting the
defaults for message queues created without an attr struct separately
from the system wide maximums.
What is not an option IMO is to leave the current behavior in place. No
piece of software should ever rely on setting the system wide maximums
in order to get a desired message queue. Such a reliance would be so
fundamentally multitasking OS unfriendly as to not really be tolerable.
Fortunately, we don't know of any software in the wild that uses this
except for a regression test program that caught the issue in the first
place. If there is though, we have made accommodations with the two new
/proc knobs (and that's all the accommodations such fundamentally broken
software can be allowed)..
This patch:
The various defines for minimums and maximums of the sysctl controllable
mqueue values are scattered amongst different files and named
inconsistently. Move them all into ipc_namespace.h and make them have
consistent names. Additionally, make the number of queues per namespace
also have a minimum and maximum and use the same sysctl function as the
other two settable variables.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Amerigo Wang <amwang@redhat.com>
Cc: Joe Korty <joe.korty@ccur.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-01 08:26:28 +09:00
|
|
|
#define MIN_MSGSIZEMAX 128
|
ipc/mqueue: switch back to using non-max values on create
Commit b231cca4381e ("message queues: increase range limits") changed
how we create a queue that does not include an attr struct passed to
open so that it creates the queue with whatever the maximum values are.
However, if the admin has set the maximums to allow flexibility in
creating a queue (aka, both a large size and large queue are allowed,
but combined they create a queue too large for the RLIMIT_MSGQUEUE of
the user), then attempts to create a queue without an attr struct will
fail. Switch back to using acceptable defaults regardless of what the
maximums are.
Note: so far, we only know of a few applications that rely on this
behavior (specifically, set the maximums in /proc, then run the
application which calls mq_open() without passing in an attr struct, and
the application expects the newly created message queue to have the
maximum sizes that were set in /proc used on the mq_open() call, and all
of those applications that we know of are actually part of regression
test suites that were coded to do something like this:
for size in 4096 65536 $((1024 * 1024)) $((16 * 1024 * 1024)); do
echo $size > /proc/sys/fs/mqueue/msgsize_max
mq_open || echo "Error opening mq with size $size"
done
These test suites that depend on any behavior like this are broken. The
concept that programs should rely upon the system wide maximum in order
to get their desired results instead of simply using a attr struct to
specify what they want is fundamentally unfriendly programming practice
for any multi-tasking OS.
Fixing this will break those few apps that we know of (and those app
authors recognize the brokenness of their code and the need to fix it).
However, the following patch "mqueue: separate mqueue default value"
allows a workaround in the form of new knobs for the default msg queue
creation parameters for any software out there that we don't already
know about that might rely on this behavior at the moment.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: Amerigo Wang <amwang@redhat.com>
Cc: Joe Korty <joe.korty@ccur.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-01 08:26:29 +09:00
|
|
|
#define DFLT_MSGSIZE 8192U
|
2009-04-07 11:01:08 +09:00
|
|
|
#define DFLT_MSGSIZEMAX 8192 /* max message size */
|
ipc/mqueue: cleanup definition names and locations
Since commit b231cca4381e ("message queues: increase range limits") on
Oct 18, 2008, calls to mq_open() that did not pass in an attribute
struct and expected to get default values for the size of the queue and
the max message size now get the system wide maximums instead of
hardwired defaults like they used to get.
This was uncovered when one of the earlier patches in this patch set
increased the default system wide maximums at the same time it increased
the hard ceiling on the system wide maximums (a customer specifically
needed the hard ceiling brought back up, the new ceiling that commit
b231cca4381e introduced was too low for their production systems). By
increasing the default maximums and not realising they were tied to any
attempt to create a message queue without an attribute struct, I had
inadvertently made it such that all message queue creation attempts
without an attribute struct were failing because the new default
maximums would create a queue that exceeded the default rlimit for
message queue bytes.
As a result, the system wide defaults were brought back down to their
previous levels, and the system wide ceilings on the maximums were
raised to meet the customer's needs. However, the fact that the no
attribute struct behavior of mq_open() could be broken by changing the
system wide maximums for message queues was seen as fundamentally broken
itself. So we hardwired the no attribute case back like it used to be.
But, then we realized that on the very off chance that some piece of
software in the wild depended on that behavior, we could work around
that issue by adding two new knobs to /proc that allowed setting the
defaults for message queues created without an attr struct separately
from the system wide maximums.
What is not an option IMO is to leave the current behavior in place. No
piece of software should ever rely on setting the system wide maximums
in order to get a desired message queue. Such a reliance would be so
fundamentally multitasking OS unfriendly as to not really be tolerable.
Fortunately, we don't know of any software in the wild that uses this
except for a regression test program that caught the issue in the first
place. If there is though, we have made accommodations with the two new
/proc knobs (and that's all the accommodations such fundamentally broken
software can be allowed)..
This patch:
The various defines for minimums and maximums of the sysctl controllable
mqueue values are scattered amongst different files and named
inconsistently. Move them all into ipc_namespace.h and make them have
consistent names. Additionally, make the number of queues per namespace
also have a minimum and maximum and use the same sysctl function as the
other two settable variables.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Amerigo Wang <amwang@redhat.com>
Cc: Joe Korty <joe.korty@ccur.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-01 08:26:28 +09:00
|
|
|
#define HARD_MSGSIZEMAX (8192*128)
|
2009-04-07 11:01:08 +09:00
|
|
|
#else
|
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>
2009-04-07 11:01:10 +09:00
|
|
|
static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; }
|
2009-04-07 11:01:08 +09:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#if defined(CONFIG_IPC_NS)
|
2008-02-08 21:18:22 +09:00
|
|
|
extern struct ipc_namespace *copy_ipcs(unsigned long flags,
|
2011-03-24 08:43:24 +09:00
|
|
|
struct task_struct *tsk);
|
2008-02-08 21:18:22 +09:00
|
|
|
static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
|
|
|
|
{
|
|
|
|
if (ns)
|
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>
2009-04-07 11:01:10 +09:00
|
|
|
atomic_inc(&ns->count);
|
2008-02-08 21:18:22 +09:00
|
|
|
return ns;
|
|
|
|
}
|
|
|
|
|
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>
2009-04-07 11:01:10 +09:00
|
|
|
extern void put_ipc_ns(struct ipc_namespace *ns);
|
2008-02-08 21:18:22 +09:00
|
|
|
#else
|
|
|
|
static inline struct ipc_namespace *copy_ipcs(unsigned long flags,
|
2011-03-24 08:43:24 +09:00
|
|
|
struct task_struct *tsk)
|
2008-02-08 21:18:22 +09:00
|
|
|
{
|
|
|
|
if (flags & CLONE_NEWIPC)
|
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
|
2011-03-24 08:43:24 +09:00
|
|
|
return tsk->nsproxy->ipc_ns;
|
2008-02-08 21:18:22 +09:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
|
|
|
|
{
|
|
|
|
return ns;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void put_ipc_ns(struct ipc_namespace *ns)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif
|
2009-04-07 11:01:11 +09:00
|
|
|
|
|
|
|
#ifdef CONFIG_POSIX_MQUEUE_SYSCTL
|
|
|
|
|
|
|
|
struct ctl_table_header;
|
|
|
|
extern struct ctl_table_header *mq_register_sysctl_table(void);
|
|
|
|
|
|
|
|
#else /* CONFIG_POSIX_MQUEUE_SYSCTL */
|
|
|
|
|
|
|
|
static inline struct ctl_table_header *mq_register_sysctl_table(void)
|
|
|
|
{
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif /* CONFIG_POSIX_MQUEUE_SYSCTL */
|
2008-02-08 21:18:22 +09:00
|
|
|
#endif
|