linux-stable/ipc/msg.c

1065 lines
23 KiB
C
Raw Normal View History

/*
* linux/ipc/msg.c
* Copyright (C) 1992 Krishna Balasubramanian
*
* Removed all the remaining kerneld mess
* Catch the -EFAULT stuff properly
* Use GFP_KERNEL for messages as in 1.2
* Fixed up the unchecked user space derefs
* Copyright (C) 1998 Alan Cox & Andi Kleen
*
* /proc/sysvipc/msg support (c) 1999 Dragos Acostachioaie <dragos@iname.com>
*
* mostly rewritten, threaded and wake-one semantics added
* MSGMAX limit removed, sysctl's added
* (c) 1999 Manfred Spraul <manfred@colorfullife.com>
[PATCH] Rework of IPC auditing 1) The audit_ipc_perms() function has been split into two different functions: - audit_ipc_obj() - audit_ipc_set_perm() There's a key shift here... The audit_ipc_obj() collects the uid, gid, mode, and SElinux context label of the current ipc object. This audit_ipc_obj() hook is now found in several places. Most notably, it is hooked in ipcperms(), which is called in various places around the ipc code permforming a MAC check. Additionally there are several places where *checkid() is used to validate that an operation is being performed on a valid object while not necessarily having a nearby ipcperms() call. In these locations, audit_ipc_obj() is called to ensure that the information is captured by the audit system. The audit_set_new_perm() function is called any time the permissions on the ipc object changes. In this case, the NEW permissions are recorded (and note that an audit_ipc_obj() call exists just a few lines before each instance). 2) Support for an AUDIT_IPC_SET_PERM audit message type. This allows for separate auxiliary audit records for normal operations on an IPC object and permissions changes. Note that the same struct audit_aux_data_ipcctl is used and populated, however there are separate audit_log_format statements based on the type of the message. Finally, the AUDIT_IPC block of code in audit_free_aux() was extended to handle aux messages of this new type. No more mem leaks I hope ;-) Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2006-04-02 21:07:33 +00:00
*
* support for audit of ipc object properties and permission changes
* Dustin Kirkland <dustin.kirkland@us.ibm.com>
*
* namespaces support
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
*/
#include <linux/capability.h>
#include <linux/msg.h>
#include <linux/spinlock.h>
#include <linux/init.h>
ipc: scale msgmni to the amount of lowmem On large systems we'd like to allow a larger number of message queues. In some cases up to 32K. However simply setting MSGMNI to a larger value may cause problems for smaller systems. The first patch of this series introduces a default maximum number of message queue ids that scales with the amount of lowmem. Since msgmni is per namespace and there is no amount of memory dedicated to each namespace so far, the second patch of this series scales msgmni to the number of ipc namespaces too. Since msgmni depends on the amount of memory, it becomes necessary to recompute it upon memory add/remove. In the 4th patch, memory hotplug management is added: a notifier block is registered into the memory hotplug notifier chain for the ipc subsystem. Since the ipc namespaces are not linked together, they have their own notification chain: one notifier_block is defined per ipc namespace. Each time an ipc namespace is created (removed) it registers (unregisters) its notifier block in (from) the ipcns chain. The callback routine registered in the memory chain invokes the ipcns notifier chain with the IPCNS_MEMCHANGE event. Each callback routine registered in the ipcns namespace, in turn, recomputes msgmni for the owning namespace. The 5th patch makes it possible to keep the memory hotplug notifier chain's lock for a lesser amount of time: instead of directly notifying the ipcns notifier chain upon memory add/remove, a work item is added to the global workqueue. When activated, this work item is the one who notifies the ipcns notifier chain. Since msgmni depends on the number of ipc namespaces, it becomes necessary to recompute it upon ipc namespace creation / removal. The 6th patch uses the ipc namespace notifier chain for that purpose: that chain is notified each time an ipc namespace is created or removed. This makes it possible to recompute msgmni for all the namespaces each time one of them is created or removed. When msgmni is explicitely set from userspace, we should avoid recomputing it upon memory add/remove or ipcns creation/removal. This is what the 7th patch does: it simply unregisters the ipcns callback routine as soon as msgmni has been changed from procfs or sysctl(). Even if msgmni is set by hand, it should be possible to make it back automatically recomputed upon memory add/remove or ipcns creation/removal. This what is achieved in patch 8: if set to a negative value, msgmni is added back to the ipcns notifier chain, making it automatically recomputed again. This patch: Compute msg_ctlmni to make it scale with the amount of lowmem. msg_ctlmni is now set to make the message queues occupy 1/32 of the available lowmem. Some cleaning has also been done for the MSGPOOL constant: the msgctl man page says it's not used, but it also defines it as a size in bytes (the code expresses it in Kbytes). Signed-off-by: Nadia Derbey <Nadia.Derbey@bull.net> Cc: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: Matt Helsley <matthltc@us.ibm.com> Cc: Mingming Cao <cmm@us.ibm.com> Cc: Pierre Peiffer <pierre.peiffer@bull.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-29 08:00:39 +00:00
#include <linux/mm.h>
#include <linux/proc_fs.h>
#include <linux/list.h>
#include <linux/security.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
#include <linux/seq_file.h>
#include <linux/rwsem.h>
#include <linux/nsproxy.h>
namespaces: move the IPC namespace under IPC_NS option Currently the IPC namespace management code is spread over the ipc/*.c files. I moved this code into ipc/namespace.c file which is compiled out when needed. The linux/ipc_namespace.h file is used to store the prototypes of the functions in namespace.c and the stubs for NAMESPACES=n case. This is done so, because the stub for copy_ipc_namespace requires the knowledge of the CLONE_NEWIPC flag, which is in sched.h. But the linux/ipc.h file itself in included into many many .c files via the sys.h->sem.h sequence so adding the sched.h into it will make all these .c depend on sched.h which is not that good. On the other hand the knowledge about the namespaces stuff is required in 4 .c files only. Besides, this patch compiles out some auxiliary functions from ipc/sem.c, msg.c and shm.c files. It turned out that moving these functions into namespaces.c is not that easy because they use many other calls and macros from the original file. Moving them would make this patch complicated. On the other hand all these functions can be consolidated, so I will send a separate patch doing this a bit later. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: Serge Hallyn <serue@us.ibm.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:18:22 +00:00
#include <linux/ipc_namespace.h>
#include <asm/current.h>
#include <linux/uaccess.h>
#include "util.h"
/* one msg_receiver structure for each sleeping receiver */
struct msg_receiver {
struct list_head r_list;
struct task_struct *r_tsk;
int r_mode;
long r_msgtype;
long r_maxsize;
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
struct msg_msg *r_msg;
};
/* one msg_sender for each sleeping sender */
struct msg_sender {
struct list_head list;
struct task_struct *tsk;
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
size_t msgsz;
};
#define SEARCH_ANY 1
#define SEARCH_EQUAL 2
#define SEARCH_NOTEQUAL 3
#define SEARCH_LESSEQUAL 4
#define SEARCH_NUMBER 5
#define msg_ids(ns) ((ns)->ids[IPC_MSG_IDS])
static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id)
{
struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&msg_ids(ns), id);
if (IS_ERR(ipcp))
return ERR_CAST(ipcp);
return container_of(ipcp, struct msg_queue, q_perm);
}
static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns,
int id)
{
struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id);
if (IS_ERR(ipcp))
return ERR_CAST(ipcp);
return container_of(ipcp, struct msg_queue, q_perm);
}
static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s)
{
ipc_rmid(&msg_ids(ns), &s->q_perm);
}
ipc: fix race with LSMs Currently, IPC mechanisms do security and auditing related checks under RCU. However, since security modules can free the security structure, for example, through selinux_[sem,msg_queue,shm]_free_security(), we can race if the structure is freed before other tasks are done with it, creating a use-after-free condition. Manfred illustrates this nicely, for instance with shared mem and selinux: -> do_shmat calls rcu_read_lock() -> do_shmat calls shm_object_check(). Checks that the object is still valid - but doesn't acquire any locks. Then it returns. -> do_shmat calls security_shm_shmat (e.g. selinux_shm_shmat) -> selinux_shm_shmat calls ipc_has_perm() -> ipc_has_perm accesses ipc_perms->security shm_close() -> shm_close acquires rw_mutex & shm_lock -> shm_close calls shm_destroy -> shm_destroy calls security_shm_free (e.g. selinux_shm_free_security) -> selinux_shm_free_security calls ipc_free_security(&shp->shm_perm) -> ipc_free_security calls kfree(ipc_perms->security) This patch delays the freeing of the security structures after all RCU readers are done. Furthermore it aligns the security life cycle with that of the rest of IPC - freeing them based on the reference counter. For situations where we need not free security, the current behavior is kept. Linus states: "... the old behavior was suspect for another reason too: having the security blob go away from under a user sounds like it could cause various other problems anyway, so I think the old code was at least _prone_ to bugs even if it didn't have catastrophic behavior." I have tested this patch with IPC testcases from LTP on both my quad-core laptop and on a 64 core NUMA server. In both cases selinux is enabled, and tests pass for both voluntary and forced preemption models. While the mentioned races are theoretical (at least no one as reported them), I wanted to make sure that this new logic doesn't break anything we weren't aware of. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Davidlohr Bueso <davidlohr@hp.com> Acked-by: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-24 00:04:45 +00:00
static void msg_rcu_free(struct rcu_head *head)
{
struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
struct msg_queue *msq = ipc_rcu_to_struct(p);
security_msg_queue_free(msq);
ipc_rcu_free(head);
}
/**
* newque - Create a new msg queue
* @ns: namespace
* @params: ptr to the structure that contains the key and msgflg
*
* Called with msg_ids.rwsem held (writer)
*/
static int newque(struct ipc_namespace *ns, struct ipc_params *params)
{
struct msg_queue *msq;
int id, retval;
key_t key = params->key;
int msgflg = params->flg;
msq = ipc_rcu_alloc(sizeof(*msq));
if (!msq)
return -ENOMEM;
msq->q_perm.mode = msgflg & S_IRWXUGO;
msq->q_perm.key = key;
msq->q_perm.security = NULL;
retval = security_msg_queue_alloc(msq);
if (retval) {
ipc: fix race with LSMs Currently, IPC mechanisms do security and auditing related checks under RCU. However, since security modules can free the security structure, for example, through selinux_[sem,msg_queue,shm]_free_security(), we can race if the structure is freed before other tasks are done with it, creating a use-after-free condition. Manfred illustrates this nicely, for instance with shared mem and selinux: -> do_shmat calls rcu_read_lock() -> do_shmat calls shm_object_check(). Checks that the object is still valid - but doesn't acquire any locks. Then it returns. -> do_shmat calls security_shm_shmat (e.g. selinux_shm_shmat) -> selinux_shm_shmat calls ipc_has_perm() -> ipc_has_perm accesses ipc_perms->security shm_close() -> shm_close acquires rw_mutex & shm_lock -> shm_close calls shm_destroy -> shm_destroy calls security_shm_free (e.g. selinux_shm_free_security) -> selinux_shm_free_security calls ipc_free_security(&shp->shm_perm) -> ipc_free_security calls kfree(ipc_perms->security) This patch delays the freeing of the security structures after all RCU readers are done. Furthermore it aligns the security life cycle with that of the rest of IPC - freeing them based on the reference counter. For situations where we need not free security, the current behavior is kept. Linus states: "... the old behavior was suspect for another reason too: having the security blob go away from under a user sounds like it could cause various other problems anyway, so I think the old code was at least _prone_ to bugs even if it didn't have catastrophic behavior." I have tested this patch with IPC testcases from LTP on both my quad-core laptop and on a 64 core NUMA server. In both cases selinux is enabled, and tests pass for both voluntary and forced preemption models. While the mentioned races are theoretical (at least no one as reported them), I wanted to make sure that this new logic doesn't break anything we weren't aware of. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Davidlohr Bueso <davidlohr@hp.com> Acked-by: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-24 00:04:45 +00:00
ipc_rcu_putref(msq, ipc_rcu_free);
return retval;
}
msq->q_stime = msq->q_rtime = 0;
msq->q_ctime = get_seconds();
msq->q_cbytes = msq->q_qnum = 0;
msq->q_qbytes = ns->msg_ctlmnb;
msq->q_lspid = msq->q_lrpid = 0;
INIT_LIST_HEAD(&msq->q_messages);
INIT_LIST_HEAD(&msq->q_receivers);
INIT_LIST_HEAD(&msq->q_senders);
/* ipc_addid() locks msq upon success. */
id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
if (id < 0) {
ipc_rcu_putref(msq, msg_rcu_free);
return id;
}
ipc_unlock_object(&msq->q_perm);
rcu_read_unlock();
return msq->q_perm.id;
}
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
static inline bool msg_fits_inqueue(struct msg_queue *msq, size_t msgsz)
{
return msgsz + msq->q_cbytes <= msq->q_qbytes &&
1 + msq->q_qnum <= msq->q_qbytes;
}
static inline void ss_add(struct msg_queue *msq,
struct msg_sender *mss, size_t msgsz)
{
mss->tsk = current;
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
mss->msgsz = msgsz;
__set_current_state(TASK_INTERRUPTIBLE);
list_add_tail(&mss->list, &msq->q_senders);
}
static inline void ss_del(struct msg_sender *mss)
{
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
if (mss->list.next)
list_del(&mss->list);
}
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
static void ss_wakeup(struct msg_queue *msq,
struct wake_q_head *wake_q, bool kill)
{
struct msg_sender *mss, *t;
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
struct task_struct *stop_tsk = NULL;
struct list_head *h = &msq->q_senders;
list_for_each_entry_safe(mss, t, h, list) {
if (kill)
mss->list.next = NULL;
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
/*
* Stop at the first task we don't wakeup,
* we've already iterated the original
* sender queue.
*/
else if (stop_tsk == mss->tsk)
break;
/*
* We are not in an EIDRM scenario here, therefore
* verify that we really need to wakeup the task.
* To maintain current semantics and wakeup order,
* move the sender to the tail on behalf of the
* blocked task.
*/
else if (!msg_fits_inqueue(msq, mss->msgsz)) {
if (!stop_tsk)
stop_tsk = mss->tsk;
list_move_tail(&mss->list, &msq->q_senders);
continue;
}
wake_q_add(wake_q, mss->tsk);
}
}
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
static void expunge_all(struct msg_queue *msq, int res,
struct wake_q_head *wake_q)
{
struct msg_receiver *msr, *t;
list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) {
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
wake_q_add(wake_q, msr->r_tsk);
WRITE_ONCE(msr->r_msg, ERR_PTR(res));
}
}
/*
* freeque() wakes up waiters on the sender and receiver waiting queue,
* removes the message queue from message queue ID IDR, and cleans up all the
* messages associated with this queue.
*
* msg_ids.rwsem (writer) and the spinlock for this message queue are held
* before freeque() is called. msg_ids.rwsem remains locked on exit.
*/
static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
struct msg_msg *msg, *t;
struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm);
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
WAKE_Q(wake_q);
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
expunge_all(msq, -EIDRM, &wake_q);
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
ss_wakeup(msq, &wake_q, true);
msg_rmid(ns, msq);
ipc_unlock_object(&msq->q_perm);
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
wake_up_q(&wake_q);
rcu_read_unlock();
list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) {
atomic_dec(&ns->msg_hdrs);
free_msg(msg);
}
atomic_sub(msq->q_cbytes, &ns->msg_bytes);
ipc: fix race with LSMs Currently, IPC mechanisms do security and auditing related checks under RCU. However, since security modules can free the security structure, for example, through selinux_[sem,msg_queue,shm]_free_security(), we can race if the structure is freed before other tasks are done with it, creating a use-after-free condition. Manfred illustrates this nicely, for instance with shared mem and selinux: -> do_shmat calls rcu_read_lock() -> do_shmat calls shm_object_check(). Checks that the object is still valid - but doesn't acquire any locks. Then it returns. -> do_shmat calls security_shm_shmat (e.g. selinux_shm_shmat) -> selinux_shm_shmat calls ipc_has_perm() -> ipc_has_perm accesses ipc_perms->security shm_close() -> shm_close acquires rw_mutex & shm_lock -> shm_close calls shm_destroy -> shm_destroy calls security_shm_free (e.g. selinux_shm_free_security) -> selinux_shm_free_security calls ipc_free_security(&shp->shm_perm) -> ipc_free_security calls kfree(ipc_perms->security) This patch delays the freeing of the security structures after all RCU readers are done. Furthermore it aligns the security life cycle with that of the rest of IPC - freeing them based on the reference counter. For situations where we need not free security, the current behavior is kept. Linus states: "... the old behavior was suspect for another reason too: having the security blob go away from under a user sounds like it could cause various other problems anyway, so I think the old code was at least _prone_ to bugs even if it didn't have catastrophic behavior." I have tested this patch with IPC testcases from LTP on both my quad-core laptop and on a 64 core NUMA server. In both cases selinux is enabled, and tests pass for both voluntary and forced preemption models. While the mentioned races are theoretical (at least no one as reported them), I wanted to make sure that this new logic doesn't break anything we weren't aware of. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Davidlohr Bueso <davidlohr@hp.com> Acked-by: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-24 00:04:45 +00:00
ipc_rcu_putref(msq, msg_rcu_free);
}
/*
* Called with msg_ids.rwsem and ipcp locked.
*/
static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg)
{
struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm);
return security_msg_queue_associate(msq, msgflg);
}
SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg)
{
struct ipc_namespace *ns;
static const struct ipc_ops msg_ops = {
.getnew = newque,
.associate = msg_security,
};
struct ipc_params msg_params;
ns = current->nsproxy->ipc_ns;
msg_params.key = key;
msg_params.flg = msgflg;
return ipcget(ns, &msg_ids(ns), &msg_ops, &msg_params);
}
static inline unsigned long
copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version)
{
switch (version) {
case IPC_64:
return copy_to_user(buf, in, sizeof(*in));
case IPC_OLD:
{
struct msqid_ds out;
memset(&out, 0, sizeof(out));
ipc64_perm_to_ipc_perm(&in->msg_perm, &out.msg_perm);
out.msg_stime = in->msg_stime;
out.msg_rtime = in->msg_rtime;
out.msg_ctime = in->msg_ctime;
if (in->msg_cbytes > USHRT_MAX)
out.msg_cbytes = USHRT_MAX;
else
out.msg_cbytes = in->msg_cbytes;
out.msg_lcbytes = in->msg_cbytes;
if (in->msg_qnum > USHRT_MAX)
out.msg_qnum = USHRT_MAX;
else
out.msg_qnum = in->msg_qnum;
if (in->msg_qbytes > USHRT_MAX)
out.msg_qbytes = USHRT_MAX;
else
out.msg_qbytes = in->msg_qbytes;
out.msg_lqbytes = in->msg_qbytes;
out.msg_lspid = in->msg_lspid;
out.msg_lrpid = in->msg_lrpid;
return copy_to_user(buf, &out, sizeof(out));
}
default:
return -EINVAL;
}
}
static inline unsigned long
copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version)
{
switch (version) {
case IPC_64:
if (copy_from_user(out, buf, sizeof(*out)))
return -EFAULT;
return 0;
case IPC_OLD:
{
struct msqid_ds tbuf_old;
if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
return -EFAULT;
out->msg_perm.uid = tbuf_old.msg_perm.uid;
out->msg_perm.gid = tbuf_old.msg_perm.gid;
out->msg_perm.mode = tbuf_old.msg_perm.mode;
if (tbuf_old.msg_qbytes == 0)
out->msg_qbytes = tbuf_old.msg_lqbytes;
else
out->msg_qbytes = tbuf_old.msg_qbytes;
return 0;
}
default:
return -EINVAL;
}
}
/*
* This function handles some msgctl commands which require the rwsem
* to be held in write mode.
* NOTE: no locks must be held, the rwsem is taken inside this function.
*/
static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
struct msqid_ds __user *buf, int version)
{
struct kern_ipc_perm *ipcp;
struct msqid64_ds uninitialized_var(msqid64);
struct msg_queue *msq;
int err;
if (cmd == IPC_SET) {
if (copy_msqid_from_user(&msqid64, buf, version))
return -EFAULT;
}
down_write(&msg_ids(ns).rwsem);
rcu_read_lock();
ipcp = ipcctl_pre_down_nolock(ns, &msg_ids(ns), msqid, cmd,
&msqid64.msg_perm, msqid64.msg_qbytes);
if (IS_ERR(ipcp)) {
err = PTR_ERR(ipcp);
goto out_unlock1;
}
msq = container_of(ipcp, struct msg_queue, q_perm);
err = security_msg_queue_msgctl(msq, cmd);
if (err)
goto out_unlock1;
switch (cmd) {
case IPC_RMID:
ipc_lock_object(&msq->q_perm);
/* freeque unlocks the ipc object and rcu */
freeque(ns, ipcp);
goto out_up;
case IPC_SET:
{
WAKE_Q(wake_q);
if (msqid64.msg_qbytes > ns->msg_ctlmnb &&
!capable(CAP_SYS_RESOURCE)) {
err = -EPERM;
goto out_unlock1;
}
ipc_lock_object(&msq->q_perm);
err = ipc_update_perm(&msqid64.msg_perm, ipcp);
if (err)
goto out_unlock0;
msq->q_qbytes = msqid64.msg_qbytes;
msq->q_ctime = get_seconds();
/*
* Sleeping receivers might be excluded by
* stricter permissions.
*/
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
expunge_all(msq, -EAGAIN, &wake_q);
/*
* Sleeping senders might be able to send
* due to a larger queue size.
*/
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
ss_wakeup(msq, &wake_q, false);
ipc_unlock_object(&msq->q_perm);
wake_up_q(&wake_q);
goto out_unlock1;
}
default:
err = -EINVAL;
goto out_unlock1;
}
out_unlock0:
ipc_unlock_object(&msq->q_perm);
out_unlock1:
rcu_read_unlock();
out_up:
up_write(&msg_ids(ns).rwsem);
return err;
}
static int msgctl_nolock(struct ipc_namespace *ns, int msqid,
int cmd, int version, void __user *buf)
{
int err;
struct msg_queue *msq;
switch (cmd) {
case IPC_INFO:
case MSG_INFO:
{
struct msginfo msginfo;
int max_id;
if (!buf)
return -EFAULT;
/*
* We must not return kernel stack data.
* due to padding, it's not enough
* to set all member fields.
*/
err = security_msg_queue_msgctl(NULL, cmd);
if (err)
return err;
memset(&msginfo, 0, sizeof(msginfo));
msginfo.msgmni = ns->msg_ctlmni;
msginfo.msgmax = ns->msg_ctlmax;
msginfo.msgmnb = ns->msg_ctlmnb;
msginfo.msgssz = MSGSSZ;
msginfo.msgseg = MSGSEG;
down_read(&msg_ids(ns).rwsem);
if (cmd == MSG_INFO) {
msginfo.msgpool = msg_ids(ns).in_use;
msginfo.msgmap = atomic_read(&ns->msg_hdrs);
msginfo.msgtql = atomic_read(&ns->msg_bytes);
} else {
msginfo.msgmap = MSGMAP;
msginfo.msgpool = MSGPOOL;
msginfo.msgtql = MSGTQL;
}
max_id = ipc_get_maxid(&msg_ids(ns));
up_read(&msg_ids(ns).rwsem);
if (copy_to_user(buf, &msginfo, sizeof(struct msginfo)))
return -EFAULT;
return (max_id < 0) ? 0 : max_id;
}
case MSG_STAT:
case IPC_STAT:
{
struct msqid64_ds tbuf;
int success_return;
if (!buf)
return -EFAULT;
memset(&tbuf, 0, sizeof(tbuf));
rcu_read_lock();
if (cmd == MSG_STAT) {
msq = msq_obtain_object(ns, msqid);
if (IS_ERR(msq)) {
err = PTR_ERR(msq);
goto out_unlock;
}
success_return = msq->q_perm.id;
} else {
msq = msq_obtain_object_check(ns, msqid);
if (IS_ERR(msq)) {
err = PTR_ERR(msq);
goto out_unlock;
}
success_return = 0;
}
err = -EACCES;
if (ipcperms(ns, &msq->q_perm, S_IRUGO))
goto out_unlock;
err = security_msg_queue_msgctl(msq, cmd);
if (err)
goto out_unlock;
kernel_to_ipc64_perm(&msq->q_perm, &tbuf.msg_perm);
tbuf.msg_stime = msq->q_stime;
tbuf.msg_rtime = msq->q_rtime;
tbuf.msg_ctime = msq->q_ctime;
tbuf.msg_cbytes = msq->q_cbytes;
tbuf.msg_qnum = msq->q_qnum;
tbuf.msg_qbytes = msq->q_qbytes;
tbuf.msg_lspid = msq->q_lspid;
tbuf.msg_lrpid = msq->q_lrpid;
rcu_read_unlock();
if (copy_msqid_to_user(buf, &tbuf, version))
return -EFAULT;
return success_return;
}
default:
return -EINVAL;
}
return err;
out_unlock:
rcu_read_unlock();
return err;
}
SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
{
int version;
struct ipc_namespace *ns;
if (msqid < 0 || cmd < 0)
return -EINVAL;
version = ipc_parse_version(&cmd);
ns = current->nsproxy->ipc_ns;
switch (cmd) {
case IPC_INFO:
case MSG_INFO:
case MSG_STAT: /* msqid is an index rather than a msg queue id */
case IPC_STAT:
return msgctl_nolock(ns, msqid, cmd, version, buf);
case IPC_SET:
case IPC_RMID:
return msgctl_down(ns, msqid, cmd, buf, version);
default:
return -EINVAL;
}
}
static int testmsg(struct msg_msg *msg, long type, int mode)
{
switch (mode) {
case SEARCH_ANY:
case SEARCH_NUMBER:
return 1;
case SEARCH_LESSEQUAL:
if (msg->m_type <= type)
return 1;
break;
case SEARCH_EQUAL:
if (msg->m_type == type)
return 1;
break;
case SEARCH_NOTEQUAL:
if (msg->m_type != type)
return 1;
break;
}
return 0;
}
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg,
struct wake_q_head *wake_q)
{
struct msg_receiver *msr, *t;
list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) {
if (testmsg(msg, msr->r_msgtype, msr->r_mode) &&
!security_msg_queue_msgrcv(msq, msg, msr->r_tsk,
msr->r_msgtype, msr->r_mode)) {
list_del(&msr->r_list);
if (msr->r_maxsize < msg->m_ts) {
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
wake_q_add(wake_q, msr->r_tsk);
WRITE_ONCE(msr->r_msg, ERR_PTR(-E2BIG));
} else {
msq->q_lrpid = task_pid_vnr(msr->r_tsk);
msq->q_rtime = get_seconds();
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
wake_q_add(wake_q, msr->r_tsk);
WRITE_ONCE(msr->r_msg, msg);
return 1;
}
}
}
return 0;
}
long do_msgsnd(int msqid, long mtype, void __user *mtext,
size_t msgsz, int msgflg)
{
struct msg_queue *msq;
struct msg_msg *msg;
int err;
struct ipc_namespace *ns;
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
WAKE_Q(wake_q);
ns = current->nsproxy->ipc_ns;
if (msgsz > ns->msg_ctlmax || (long) msgsz < 0 || msqid < 0)
return -EINVAL;
if (mtype < 1)
return -EINVAL;
msg = load_msg(mtext, msgsz);
if (IS_ERR(msg))
return PTR_ERR(msg);
msg->m_type = mtype;
msg->m_ts = msgsz;
rcu_read_lock();
msq = msq_obtain_object_check(ns, msqid);
if (IS_ERR(msq)) {
err = PTR_ERR(msq);
goto out_unlock1;
}
ipc_lock_object(&msq->q_perm);
for (;;) {
struct msg_sender s;
err = -EACCES;
if (ipcperms(ns, &msq->q_perm, S_IWUGO))
goto out_unlock0;
/* raced with RMID? */
if (!ipc_valid_object(&msq->q_perm)) {
err = -EIDRM;
goto out_unlock0;
}
err = security_msg_queue_msgsnd(msq, msg, msgflg);
if (err)
goto out_unlock0;
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
if (msg_fits_inqueue(msq, msgsz))
break;
/* queue full, wait: */
if (msgflg & IPC_NOWAIT) {
err = -EAGAIN;
goto out_unlock0;
}
/* enqueue the sender and prepare to block */
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
ss_add(msq, &s, msgsz);
ipc,sem: fine grained locking for semtimedop Introduce finer grained locking for semtimedop, to handle the common case of a program wanting to manipulate one semaphore from an array with multiple semaphores. If the call is a semop manipulating just one semaphore in an array with multiple semaphores, only take the lock for that semaphore itself. If the call needs to manipulate multiple semaphores, or another caller is in a transaction that manipulates multiple semaphores, the sem_array lock is taken, as well as all the locks for the individual semaphores. On a 24 CPU system, performance numbers with the semop-multi test with N threads and N semaphores, look like this: vanilla Davidlohr's Davidlohr's + Davidlohr's + threads patches rwlock patches v3 patches 10 610652 726325 1783589 2142206 20 341570 365699 1520453 1977878 30 288102 307037 1498167 2037995 40 290714 305955 1612665 2256484 50 288620 312890 1733453 2650292 60 289987 306043 1649360 2388008 70 291298 306347 1723167 2717486 80 290948 305662 1729545 2763582 90 290996 306680 1736021 2757524 100 292243 306700 1773700 3059159 [davidlohr.bueso@hp.com: do not call sem_lock when bogus sma] [davidlohr.bueso@hp.com: make refcounter atomic] Signed-off-by: Rik van Riel <riel@redhat.com> Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Davidlohr Bueso <davidlohr.bueso@hp.com> Cc: Chegu Vinod <chegu_vinod@hp.com> Cc: Jason Low <jason.low2@hp.com> Reviewed-by: Michel Lespinasse <walken@google.com> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Stanislav Kinsbursky <skinsbursky@parallels.com> Tested-by: Emmanuel Benisty <benisty.e@gmail.com> Tested-by: Sedat Dilek <sedat.dilek@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 02:15:44 +00:00
if (!ipc_rcu_getref(msq)) {
err = -EIDRM;
goto out_unlock0;
ipc,sem: fine grained locking for semtimedop Introduce finer grained locking for semtimedop, to handle the common case of a program wanting to manipulate one semaphore from an array with multiple semaphores. If the call is a semop manipulating just one semaphore in an array with multiple semaphores, only take the lock for that semaphore itself. If the call needs to manipulate multiple semaphores, or another caller is in a transaction that manipulates multiple semaphores, the sem_array lock is taken, as well as all the locks for the individual semaphores. On a 24 CPU system, performance numbers with the semop-multi test with N threads and N semaphores, look like this: vanilla Davidlohr's Davidlohr's + Davidlohr's + threads patches rwlock patches v3 patches 10 610652 726325 1783589 2142206 20 341570 365699 1520453 1977878 30 288102 307037 1498167 2037995 40 290714 305955 1612665 2256484 50 288620 312890 1733453 2650292 60 289987 306043 1649360 2388008 70 291298 306347 1723167 2717486 80 290948 305662 1729545 2763582 90 290996 306680 1736021 2757524 100 292243 306700 1773700 3059159 [davidlohr.bueso@hp.com: do not call sem_lock when bogus sma] [davidlohr.bueso@hp.com: make refcounter atomic] Signed-off-by: Rik van Riel <riel@redhat.com> Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Davidlohr Bueso <davidlohr.bueso@hp.com> Cc: Chegu Vinod <chegu_vinod@hp.com> Cc: Jason Low <jason.low2@hp.com> Reviewed-by: Michel Lespinasse <walken@google.com> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Stanislav Kinsbursky <skinsbursky@parallels.com> Tested-by: Emmanuel Benisty <benisty.e@gmail.com> Tested-by: Sedat Dilek <sedat.dilek@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 02:15:44 +00:00
}
ipc_unlock_object(&msq->q_perm);
rcu_read_unlock();
schedule();
rcu_read_lock();
ipc_lock_object(&msq->q_perm);
ipc_rcu_putref(msq, msg_rcu_free);
/* raced with RMID? */
if (!ipc_valid_object(&msq->q_perm)) {
err = -EIDRM;
goto out_unlock0;
}
ss_del(&s);
if (signal_pending(current)) {
err = -ERESTARTNOHAND;
goto out_unlock0;
}
}
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
msq->q_lspid = task_tgid_vnr(current);
msq->q_stime = get_seconds();
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
if (!pipelined_send(msq, msg, &wake_q)) {
/* no one is waiting for this message, enqueue it */
list_add_tail(&msg->m_list, &msq->q_messages);
msq->q_cbytes += msgsz;
msq->q_qnum++;
atomic_add(msgsz, &ns->msg_bytes);
atomic_inc(&ns->msg_hdrs);
}
err = 0;
msg = NULL;
out_unlock0:
ipc_unlock_object(&msq->q_perm);
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
wake_up_q(&wake_q);
out_unlock1:
rcu_read_unlock();
if (msg != NULL)
free_msg(msg);
return err;
}
SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
int, msgflg)
{
long mtype;
if (get_user(mtype, &msgp->mtype))
return -EFAULT;
return do_msgsnd(msqid, mtype, msgp->mtext, msgsz, msgflg);
}
static inline int convert_mode(long *msgtyp, int msgflg)
{
if (msgflg & MSG_COPY)
return SEARCH_NUMBER;
/*
* find message of correct type.
* msgtyp = 0 => get first.
* msgtyp > 0 => get first message of matching type.
* msgtyp < 0 => get message with least type must be < abs(msgtype).
*/
if (*msgtyp == 0)
return SEARCH_ANY;
if (*msgtyp < 0) {
*msgtyp = -*msgtyp;
return SEARCH_LESSEQUAL;
}
if (msgflg & MSG_EXCEPT)
return SEARCH_NOTEQUAL;
return SEARCH_EQUAL;
}
static long do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz)
{
struct msgbuf __user *msgp = dest;
size_t msgsz;
if (put_user(msg->m_type, &msgp->mtype))
return -EFAULT;
msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz;
if (store_msg(msgp->mtext, msg, msgsz))
return -EFAULT;
return msgsz;
}
#ifdef CONFIG_CHECKPOINT_RESTORE
/*
* This function creates new kernel message structure, large enough to store
* bufsz message bytes.
*/
static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz)
{
struct msg_msg *copy;
/*
* Create dummy message to copy real message to.
*/
copy = load_msg(buf, bufsz);
if (!IS_ERR(copy))
copy->m_ts = bufsz;
return copy;
}
static inline void free_copy(struct msg_msg *copy)
{
if (copy)
free_msg(copy);
}
#else
static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz)
{
return ERR_PTR(-ENOSYS);
}
static inline void free_copy(struct msg_msg *copy)
{
}
#endif
static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode)
{
struct msg_msg *msg, *found = NULL;
long count = 0;
list_for_each_entry(msg, &msq->q_messages, m_list) {
if (testmsg(msg, *msgtyp, mode) &&
!security_msg_queue_msgrcv(msq, msg, current,
*msgtyp, mode)) {
if (mode == SEARCH_LESSEQUAL && msg->m_type != 1) {
*msgtyp = msg->m_type - 1;
found = msg;
} else if (mode == SEARCH_NUMBER) {
if (*msgtyp == count)
return msg;
} else
return msg;
count++;
}
}
return found ?: ERR_PTR(-EAGAIN);
}
long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg,
long (*msg_handler)(void __user *, struct msg_msg *, size_t))
{
int mode;
struct msg_queue *msq;
struct ipc_namespace *ns;
struct msg_msg *msg, *copy = NULL;
WAKE_Q(wake_q);
ns = current->nsproxy->ipc_ns;
if (msqid < 0 || (long) bufsz < 0)
return -EINVAL;
if (msgflg & MSG_COPY) {
ipc: Fix 2 bugs in msgrcv() MSG_COPY implementation While testing and documenting the msgrcv() MSG_COPY flag that Stanislav Kinsbursky added in commit 4a674f34ba04 ("ipc: introduce message queue copy feature" => kernel 3.8), I discovered a couple of bugs in the implementation. The two bugs concern MSG_COPY interactions with other msgrcv() flags, namely: (A) MSG_COPY + MSG_EXCEPT (B) MSG_COPY + !IPC_NOWAIT The bugs are distinct (and the fix for the first one is obvious), however my fix for both is a single-line patch, which is why I'm combining them in a single mail, rather than writing two mails+patches. ===== (A) MSG_COPY + MSG_EXCEPT ===== With the addition of the MSG_COPY flag, there are now two msgrcv() flags--MSG_COPY and MSG_EXCEPT--that modify the meaning of the 'msgtyp' argument in unrelated ways. Specifying both in the same call is a logical error that is currently permitted, with the effect that MSG_COPY has priority and MSG_EXCEPT is ignored. The call should give an error if both flags are specified. The patch below implements that behavior. ===== (B) (B) MSG_COPY + !IPC_NOWAIT ===== The test code that was submitted in commit 3a665531a3b7 ("selftests: IPC message queue copy feature test") shows MSG_COPY being used in conjunction with IPC_NOWAIT. In other words, if there is no message at the position 'msgtyp'. return immediately with the error in ENOMSG. What was not (fully) tested is the behavior if MSG_COPY is specified *without* IPC_NOWAIT, and there is an odd behavior. If the queue contains less than 'msgtyp' messages, then the call blocks until the next message is written to the queue. At that point, the msgrcv() call returns a copy of the newly added message, regardless of whether that message is at the ordinal position 'msgtyp'. This is clearly bogus, and problematic for applications that might want to make use of the MSG_COPY flag. I considered the following possible solutions to this problem: (1) Force the call to block until a message *does* appear at the position 'msgtyp'. (2) If the MSG_COPY flag is specified, the kernel should implicitly add IPC_NOWAIT, so that the call fails with ENOMSG for this case. (3) If the MSG_COPY flag is specified, but IPC_NOWAIT is not, generate an error (probably, EINVAL is the right one). I do not know if any application would really want to have the functionality of solution (1), especially since an application can determine in advance the number of messages in the queue using msgctl() IPC_STAT. Obviously, this solution would be the most work to implement. Solution (2) would have the effect of silently fixing any applications that tried to employ broken behavior. However, it would mean that if we later decided to implement solution (1), then user-space could not easily detect what the kernel supports (but, since I'm somewhat doubtful that solution (1) is needed, I'm not sure that this is much of a problem). Solution (3) would have the effect of informing broken applications that they are doing something broken. The downside is that this would cause a ABI breakage for any applications that are currently employing the broken behavior. However: a) Those applications are almost certainly not getting the results they expect. b) Possibly, those applications don't even exist, because MSG_COPY is currently hidden behind CONFIG_CHECKPOINT_RESTORE. The upside of solution (3) is that if we later decided to implement solution (1), user-space could determine what the kernel supports, via the error return. In my view, solution (3) is mildly preferable to solution (2), and solution (1) could still be done later if anyone really cares. The patch below implements solution (3). PS. For anyone out there still listening, it's the usual story: documenting an API (and the thinking about, and the testing of the API, that documentation entails) is the one of the single best ways of finding bugs in the API, as I've learned from a lot of experience. Best to do that documentation before releasing the API. Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Stanislav Kinsbursky <skinsbursky@parallels.com> Cc: Stanislav Kinsbursky <skinsbursky@parallels.com> Cc: stable@vger.kernel.org Cc: Serge Hallyn <serge.hallyn@canonical.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-03-10 13:46:07 +00:00
if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT))
return -EINVAL;
copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax));
if (IS_ERR(copy))
return PTR_ERR(copy);
}
mode = convert_mode(&msgtyp, msgflg);
rcu_read_lock();
msq = msq_obtain_object_check(ns, msqid);
if (IS_ERR(msq)) {
rcu_read_unlock();
free_copy(copy);
return PTR_ERR(msq);
}
for (;;) {
struct msg_receiver msr_d;
msg = ERR_PTR(-EACCES);
if (ipcperms(ns, &msq->q_perm, S_IRUGO))
goto out_unlock1;
ipc_lock_object(&msq->q_perm);
/* raced with RMID? */
if (!ipc_valid_object(&msq->q_perm)) {
msg = ERR_PTR(-EIDRM);
goto out_unlock0;
}
msg = find_msg(msq, &msgtyp, mode);
if (!IS_ERR(msg)) {
/*
* Found a suitable message.
* Unlink it from the queue.
*/
if ((bufsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
msg = ERR_PTR(-E2BIG);
goto out_unlock0;
}
/*
* If we are copying, then do not unlink message and do
* not update queue parameters.
*/
if (msgflg & MSG_COPY) {
msg = copy_msg(msg, copy);
goto out_unlock0;
}
list_del(&msg->m_list);
msq->q_qnum--;
msq->q_rtime = get_seconds();
msq->q_lrpid = task_tgid_vnr(current);
msq->q_cbytes -= msg->m_ts;
atomic_sub(msg->m_ts, &ns->msg_bytes);
atomic_dec(&ns->msg_hdrs);
ipc/msg: avoid waking sender upon full queue Blocked tasks queued in q_senders waiting for their message to fit in the queue are blindly awoken every time we think there's a remote chance this might happen. This could cause numerous (and expensive -- thundering herd-ish) bogus wakeups if the queue is still really full. Adding to the scheduling cost/overhead, there's also the fact that we need to take the ipc object lock and requeue ourselves in the q_senders list. By keeping track of the blocked sender's message size, we can know previously if the wakeup ought to occur or not. Otherwise, to maintain the current wakeup order we just move it to the tail. This is exactly what occurs right now if the sender needs to go back to sleep. The case of EIDRM is left completely untouched, as we need to wakeup all the tasks, and shouldn't be playing games in the first place. This patch was seen to save on the 'msgctl10' ltp testcase ~15% in context switches (avg out of ten runs). Although these tests are really about functionality (as opposed to performance), is does show the direct benefits of the optimization. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1469748819-19484-6-git-send-email-dave@stgolabs.net Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:55:02 +00:00
ss_wakeup(msq, &wake_q, false);
goto out_unlock0;
}
/* No message waiting. Wait for a message */
if (msgflg & IPC_NOWAIT) {
msg = ERR_PTR(-ENOMSG);
goto out_unlock0;
}
list_add_tail(&msr_d.r_list, &msq->q_receivers);
msr_d.r_tsk = current;
msr_d.r_msgtype = msgtyp;
msr_d.r_mode = mode;
if (msgflg & MSG_NOERROR)
msr_d.r_maxsize = INT_MAX;
else
msr_d.r_maxsize = bufsz;
msr_d.r_msg = ERR_PTR(-EAGAIN);
__set_current_state(TASK_INTERRUPTIBLE);
ipc_unlock_object(&msq->q_perm);
rcu_read_unlock();
schedule();
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
/*
* Lockless receive, part 1:
* We don't hold a reference to the queue and getting a
* reference would defeat the idea of a lockless operation,
* thus the code relies on rcu to guarantee the existence of
* msq:
* Prior to destruction, expunge_all(-EIRDM) changes r_msg.
* Thus if r_msg is -EAGAIN, then the queue not yet destroyed.
*/
rcu_read_lock();
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
/*
* Lockless receive, part 2:
* The work in pipelined_send() and expunge_all():
* - Set pointer to message
* - Queue the receiver task for later wakeup
* - Wake up the process after the lock is dropped.
*
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
* Should the process wake up before this wakeup (due to a
* signal) it will either see the message and continue ...
*/
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
msg = READ_ONCE(msr_d.r_msg);
if (msg != ERR_PTR(-EAGAIN))
goto out_unlock1;
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
/*
* ... or see -EAGAIN, acquire the lock to check the message
* again.
*/
ipc_lock_object(&msq->q_perm);
ipc/msg: implement lockless pipelined wakeups This patch moves the wakeup_process() invocation so it is not done under the ipc global lock by making use of a lockless wake_q. With this change, the waiter is woken up once the message has been assigned and it does not need to loop on SMP if the message points to NULL. In the signal case we still need to check the pointer under the lock to verify the state. This change should also avoid the introduction of preempt_disable() in -RT which avoids a busy-loop which pools for the NULL -> !NULL change if the waiter has a higher priority compared to the waker. By making use of wake_qs, the logic of sysv msg queues is greatly simplified (and very well suited as we can batch lockless wakeups), particularly around the lockless receive algorithm. This has been tested with Manred's pmsg-shared tool on a "AMD A10-7800 Radeon R7, 12 Compute Cores 4C+8G": test | before | after | diff -----------------|------------|------------|---------- pmsg-shared 8 60 | 19,347,422 | 30,442,191 | + ~57.34 % pmsg-shared 4 60 | 21,367,197 | 35,743,458 | + ~67.28 % pmsg-shared 2 60 | 22,884,224 | 24,278,200 | + ~6.09 % Link: http://lkml.kernel.org/r/1469748819-19484-2-git-send-email-dave@stgolabs.net Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Manfred Spraul <manfred@colorfullife.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-11 20:54:53 +00:00
msg = msr_d.r_msg;
if (msg != ERR_PTR(-EAGAIN))
goto out_unlock0;
list_del(&msr_d.r_list);
if (signal_pending(current)) {
msg = ERR_PTR(-ERESTARTNOHAND);
goto out_unlock0;
}
ipc_unlock_object(&msq->q_perm);
}
out_unlock0:
ipc_unlock_object(&msq->q_perm);
wake_up_q(&wake_q);
out_unlock1:
rcu_read_unlock();
if (IS_ERR(msg)) {
free_copy(copy);
return PTR_ERR(msg);
}
bufsz = msg_handler(buf, msg, bufsz);
free_msg(msg);
return bufsz;
}
SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
long, msgtyp, int, msgflg)
{
return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill);
}
void msg_init_ns(struct ipc_namespace *ns)
{
ns->msg_ctlmax = MSGMAX;
ns->msg_ctlmnb = MSGMNB;
ns->msg_ctlmni = MSGMNI;
atomic_set(&ns->msg_bytes, 0);
atomic_set(&ns->msg_hdrs, 0);
ipc_init_ids(&ns->ids[IPC_MSG_IDS]);
}
#ifdef CONFIG_IPC_NS
void msg_exit_ns(struct ipc_namespace *ns)
{
free_ipcs(ns, &msg_ids(ns), freeque);
idr_destroy(&ns->ids[IPC_MSG_IDS].ipcs_idr);
}
#endif
#ifdef CONFIG_PROC_FS
static int sysvipc_msg_proc_show(struct seq_file *s, void *it)
{
struct user_namespace *user_ns = seq_user_ns(s);
struct msg_queue *msq = it;
seq_printf(s,
"%10d %10d %4o %10lu %10lu %5u %5u %5u %5u %5u %5u %10lu %10lu %10lu\n",
msq->q_perm.key,
msq->q_perm.id,
msq->q_perm.mode,
msq->q_cbytes,
msq->q_qnum,
msq->q_lspid,
msq->q_lrpid,
from_kuid_munged(user_ns, msq->q_perm.uid),
from_kgid_munged(user_ns, msq->q_perm.gid),
from_kuid_munged(user_ns, msq->q_perm.cuid),
from_kgid_munged(user_ns, msq->q_perm.cgid),
msq->q_stime,
msq->q_rtime,
msq->q_ctime);
return 0;
}
#endif
void __init msg_init(void)
{
msg_init_ns(&init_ipc_ns);
ipc_init_proc_interface("sysvipc/msg",
" key msqid perms cbytes qnum lspid lrpid uid gid cuid cgid stime rtime ctime\n",
IPC_MSG_IDS, sysvipc_msg_proc_show);
}