ipc/msg: increase MSGMNI, remove scaling

SysV can be abused to allocate locked kernel memory.  For most systems, a
small limit doesn't make sense, see the discussion with regards to SHMMAX.

Therefore: increase MSGMNI to the maximum supported.

And: If we ignore the risk of locking too much memory, then an automatic
scaling of MSGMNI doesn't make sense.  Therefore the logic can be removed.

The code preserves auto_msgmni to avoid breaking any user space applications
that expect that the value exists.

Notes:
1) If an administrator must limit the memory allocations, then he can set
MSGMNI as necessary.

Or he can disable sysv entirely (as e.g. done by Android).

2) MSGMAX and MSGMNB are intentionally not increased, as these values are used
to control latency vs. throughput:
If MSGMNB is large, then msgsnd() just returns and more messages can be queued
before a task switch to a task that calls msgrcv() is forced.

[[email protected]: coding-style fixes]
Signed-off-by: Manfred Spraul <[email protected]>
Cc: Davidlohr Bueso <[email protected]>
Cc: Rafael Aquini <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Documentation/sysctl/kernel.txt

@@ -116,10 +116,12 @@ set during run time.
 
 auto_msgmni:
 
-Enables/Disables automatic recomputing of msgmni upon memory add/remove
-or upon ipc namespace creation/removal (see the msgmni description
-above). Echoing "1" into this file enables msgmni automatic recomputing.
-Echoing "0" turns it off. auto_msgmni default value is 1.
+This variable has no effect and may be removed in future kernel
+releases. Reading it always returns 0.
+Up to Linux 3.17, it enabled/disabled automatic recomputing of msgmni
+upon memory add/remove or upon ipc namespace creation/removal.
+Echoing "1" into this file enabled msgmni automatic recomputing.
+Echoing "0" turned it off. auto_msgmni default value was 1.
 
 
 ==============================================================

include/linux/ipc_namespace.h

@@ -7,15 +7,6 @@
 #include <linux/notifier.h>
 #include <linux/nsproxy.h>
 
-/*
- * ipc namespace events
- */
-#define IPCNS_MEMCHANGED   0x00000001   /* Notify lowmem size changed */
-#define IPCNS_CREATED  0x00000002   /* Notify new ipc namespace created */
-#define IPCNS_REMOVED  0x00000003   /* Notify ipc namespace removed */
-
-#define IPCNS_CALLBACK_PRI 0
-
 struct user_namespace;
 
 struct ipc_ids {
@@ -38,7 +29,6 @@ struct ipc_namespace {
 	unsigned int	msg_ctlmni;
 	atomic_t	msg_bytes;
 	atomic_t	msg_hdrs;
-	int		auto_msgmni;
 
 	size_t		shm_ctlmax;
 	size_t		shm_ctlall;
@@ -77,18 +67,8 @@ extern atomic_t nr_ipc_ns;
 extern spinlock_t mq_lock;
 
 #ifdef CONFIG_SYSVIPC
-extern int register_ipcns_notifier(struct ipc_namespace *);
-extern int cond_register_ipcns_notifier(struct ipc_namespace *);
-extern void unregister_ipcns_notifier(struct ipc_namespace *);
-extern int ipcns_notify(unsigned long);
 extern void shm_destroy_orphaned(struct ipc_namespace *ns);
 #else /* CONFIG_SYSVIPC */
-static inline int register_ipcns_notifier(struct ipc_namespace *ns)
-{ return 0; }
-static inline int cond_register_ipcns_notifier(struct ipc_namespace *ns)
-{ return 0; }
-static inline void unregister_ipcns_notifier(struct ipc_namespace *ns) { }
-static inline int ipcns_notify(unsigned long l) { return 0; }
 static inline void shm_destroy_orphaned(struct ipc_namespace *ns) {}
 #endif /* CONFIG_SYSVIPC */
 

include/uapi/linux/msg.h

@@ -51,16 +51,28 @@ struct msginfo {
 };
 
 /*
- * Scaling factor to compute msgmni:
- * the memory dedicated to msg queues (msgmni * msgmnb) should occupy
- * at most 1/MSG_MEM_SCALE of the lowmem (see the formula in ipc/msg.c):
- * up to 8MB       : msgmni = 16 (MSGMNI)
- * 4 GB            : msgmni = 8K
- * more than 16 GB : msgmni = 32K (IPCMNI)
+ * MSGMNI, MSGMAX and MSGMNB are default values which can be
+ * modified by sysctl.
+ *
+ * MSGMNI is the upper limit for the number of messages queues per
+ * namespace.
+ * It has been chosen to be as large possible without facilitating
+ * scenarios where userspace causes overflows when adjusting the limits via
+ * operations of the form retrieve current limit; add X; update limit".
+ *
+ * MSGMNB is the default size of a new message queue. Non-root tasks can
+ * decrease the size with msgctl(IPC_SET), root tasks
+ * (actually: CAP_SYS_RESOURCE) can both increase and decrease the queue
+ * size. The optimal value is application dependent.
+ * 16384 is used because it was always used (since 0.99.10)
+ *
+ * MAXMAX is the maximum size of an individual message, it's a global
+ * (per-namespace) limit that applies for all message queues.
+ * It's set to 1/2 of MSGMNB, to ensure that at least two messages fit into
+ * the queue. This is also an arbitrary choice (since 2.6.0).
  */
-#define MSG_MEM_SCALE 32
 
-#define MSGMNI    16   /* <= IPCMNI */     /* max # of msg queue identifiers */
+#define MSGMNI 32000   /* <= IPCMNI */     /* max # of msg queue identifiers */
 #define MSGMAX  8192   /* <= INT_MAX */   /* max size of message (bytes) */
 #define MSGMNB 16384   /* <= INT_MAX */   /* default max size of a message queue */
 

ipc/Makefile

@@ -3,7 +3,7 @@
 #
 
 obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o
-obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o ipcns_notifier.o syscall.o
+obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o syscall.o
 obj-$(CONFIG_SYSVIPC_SYSCTL) += ipc_sysctl.o
 obj_mq-$(CONFIG_COMPAT) += compat_mq.o
 obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o $(obj_mq-y)

ipc/ipc_sysctl.c

@@ -62,29 +62,6 @@ static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
 	return err;
 }
 
-static int proc_ipc_callback_dointvec_minmax(struct ctl_table *table, int write,
-	void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct ctl_table ipc_table;
-	size_t lenp_bef = *lenp;
-	int rc;
-
-	memcpy(&ipc_table, table, sizeof(ipc_table));
-	ipc_table.data = get_ipc(table);
-
-	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
-
-	if (write && !rc && lenp_bef == *lenp)
-		/*
-		 * Tunable has successfully been changed by hand. Disable its
-		 * automatic adjustment. This simply requires unregistering
-		 * the notifiers that trigger recalculation.
-		 */
-		unregister_ipcns_notifier(current->nsproxy->ipc_ns);
-
-	return rc;
-}
-
 static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -96,63 +73,27 @@ static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
 					lenp, ppos);
 }
 
-/*
- * Routine that is called when the file "auto_msgmni" has successfully been
- * written.
- * Two values are allowed:
- * 0: unregister msgmni's callback routine from the ipc namespace notifier
- *    chain. This means that msgmni won't be recomputed anymore upon memory
- *    add/remove or ipc namespace creation/removal.
- * 1: register back the callback routine.
- */
-static void ipc_auto_callback(int val)
-{
-	if (!val)
-		unregister_ipcns_notifier(current->nsproxy->ipc_ns);
-	else {
-		/*
-		 * Re-enable automatic recomputing only if not already
-		 * enabled.
-		 */
-		recompute_msgmni(current->nsproxy->ipc_ns);
-		cond_register_ipcns_notifier(current->nsproxy->ipc_ns);
-	}
-}
-
-static int proc_ipcauto_dointvec_minmax(struct ctl_table *table, int write,
+static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table ipc_table;
-	int oldval;
-	int rc;
+	int dummy = 0;
 
 	memcpy(&ipc_table, table, sizeof(ipc_table));
-	ipc_table.data = get_ipc(table);
-	oldval = *((int *)(ipc_table.data));
+	ipc_table.data = &dummy;
 
-	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
+	if (write)
+		pr_info_once("writing to auto_msgmni has no effect");
 
-	if (write && !rc) {
-		int newval = *((int *)(ipc_table.data));
-		/*
-		 * The file "auto_msgmni" has correctly been set.
-		 * React by (un)registering the corresponding tunable, if the
-		 * value has changed.
-		 */
-		if (newval != oldval)
-			ipc_auto_callback(newval);
-	}
-
-	return rc;
+	return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 }
 
 #else
 #define proc_ipc_doulongvec_minmax NULL
 #define proc_ipc_dointvec	   NULL
 #define proc_ipc_dointvec_minmax   NULL
 #define proc_ipc_dointvec_minmax_orphans   NULL
-#define proc_ipc_callback_dointvec_minmax  NULL
-#define proc_ipcauto_dointvec_minmax NULL
+#define proc_ipc_auto_msgmni	   NULL
 #endif
 
 static int zero;
@@ -204,10 +145,19 @@ static struct ctl_table ipc_kern_table[] = {
 		.data		= &init_ipc_ns.msg_ctlmni,
 		.maxlen		= sizeof(init_ipc_ns.msg_ctlmni),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_callback_dointvec_minmax,
+		.proc_handler	= proc_ipc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &int_max,
 	},
+	{
+		.procname	= "auto_msgmni",
+		.data		= NULL,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_auto_msgmni,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{
 		.procname	=  "msgmnb",
 		.data		= &init_ipc_ns.msg_ctlmnb,
@@ -224,15 +174,6 @@ static struct ctl_table ipc_kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_ipc_dointvec,
 	},
-	{
-		.procname	= "auto_msgmni",
-		.data		= &init_ipc_ns.auto_msgmni,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_ipcauto_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
-	},
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	{
 		.procname	= "sem_next_id",

ipc/msg.c

@@ -989,43 +989,12 @@ SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
 	return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill);
 }
 
-/*
- * Scale msgmni with the available lowmem size: the memory dedicated to msg
- * queues should occupy at most 1/MSG_MEM_SCALE of lowmem.
- * Also take into account the number of nsproxies created so far.
- * This should be done staying within the (MSGMNI , IPCMNI/nr_ipc_ns) range.
- */
-void recompute_msgmni(struct ipc_namespace *ns)
-{
-	struct sysinfo i;
-	unsigned long allowed;
-	int nb_ns;
-
-	si_meminfo(&i);
-	allowed = (((i.totalram - i.totalhigh) / MSG_MEM_SCALE) * i.mem_unit)
-		/ MSGMNB;
-	nb_ns = atomic_read(&nr_ipc_ns);
-	allowed /= nb_ns;
-
-	if (allowed < MSGMNI) {
-		ns->msg_ctlmni = MSGMNI;
-		return;
-	}
-
-	if (allowed > IPCMNI / nb_ns) {
-		ns->msg_ctlmni = IPCMNI / nb_ns;
-		return;
-	}
-
-	ns->msg_ctlmni = allowed;
-}
 
 void msg_init_ns(struct ipc_namespace *ns)
 {
 	ns->msg_ctlmax = MSGMAX;
 	ns->msg_ctlmnb = MSGMNB;
-
-	recompute_msgmni(ns);
+	ns->msg_ctlmni = MSGMNI;
 
 	atomic_set(&ns->msg_bytes, 0);
 	atomic_set(&ns->msg_hdrs, 0);
@@ -1069,9 +1038,6 @@ void __init msg_init(void)
 {
 	msg_init_ns(&init_ipc_ns);
 
-	printk(KERN_INFO "msgmni has been set to %d\n",
-		init_ipc_ns.msg_ctlmni);
-
 	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);