1 files changed, 149 insertions, 109 deletions

diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index d3497465cc0..c3f0326e98d 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -18,7 +18,7 @@
 #include <linux/msg.h>
 #include "util.h"
 
-static void *get_ipc(ctl_table *table)
+static void *get_ipc(struct ctl_table *table)
 {
 	char *which = table->data;
 	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
@@ -26,40 +26,44 @@ static void *get_ipc(ctl_table *table)
 	return which;
 }
 
-/*
- * Routine that is called when a tunable has successfully been changed by
- * hand and it has a callback routine registered on the ipc namespace notifier
- * chain: we don't want such tunables to be recomputed anymore upon memory
- * add/remove or ipc namespace creation/removal.
- * They can come back to a recomputable state by being set to a <0 value.
- */
-static void tunable_set_callback(int val)
+#ifdef CONFIG_PROC_SYSCTL
+static int proc_ipc_dointvec(struct ctl_table *table, int write,
+	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	if (val >= 0)
-		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);
-	}
+	struct ctl_table ipc_table;
+
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+	ipc_table.data = get_ipc(table);
+
+	return proc_dointvec(&ipc_table, write, buffer, lenp, ppos);
 }
 
-#ifdef CONFIG_PROC_FS
-static int proc_ipc_dointvec(ctl_table *table, int write, struct file *filp,
+static int proc_ipc_dointvec_minmax(struct ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table ipc_table;
+
 	memcpy(&ipc_table, table, sizeof(ipc_table));
 	ipc_table.data = get_ipc(table);
 
-	return proc_dointvec(&ipc_table, write, filp, buffer, lenp, ppos);
+	return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
+}
+
+static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
+	void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ipc_namespace *ns = current->nsproxy->ipc_ns;
+	int err = proc_ipc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+	if (err < 0)
+		return err;
+	if (ns->shm_rmid_forced)
+		shm_destroy_orphaned(ns);
+	return err;
 }
 
-static int proc_ipc_callback_dointvec(ctl_table *table, int write,
-	struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos)
+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;
@@ -68,166 +72,202 @@ static int proc_ipc_callback_dointvec(ctl_table *table, int write,
 	memcpy(&ipc_table, table, sizeof(ipc_table));
 	ipc_table.data = get_ipc(table);
 
-	rc = proc_dointvec(&ipc_table, write, filp, buffer, lenp, ppos);
+	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 
 	if (write && !rc && lenp_bef == *lenp)
-		tunable_set_callback(*((int *)(ipc_table.data)));
+		/*
+		 * 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(ctl_table *table, int write,
-	struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos)
+static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
+	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table ipc_table;
 	memcpy(&ipc_table, table, sizeof(ipc_table));
 	ipc_table.data = get_ipc(table);
 
-	return proc_doulongvec_minmax(&ipc_table, write, filp, buffer,
+	return proc_doulongvec_minmax(&ipc_table, write, buffer,
 					lenp, ppos);
 }
 
-#else
-#define proc_ipc_doulongvec_minmax NULL
-#define proc_ipc_dointvec	   NULL
-#define proc_ipc_callback_dointvec NULL
-#endif
-
-#ifdef CONFIG_SYSCTL_SYSCALL
-/* The generic sysctl ipc data routine. */
-static int sysctl_ipc_data(ctl_table *table, int __user *name, int nlen,
-		void __user *oldval, size_t __user *oldlenp,
-		void __user *newval, size_t newlen)
+/*
+ * 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)
 {
-	size_t len;
-	void *data;
-
-	/* Get out of I don't have a variable */
-	if (!table->data || !table->maxlen)
-		return -ENOTDIR;
-
-	data = get_ipc(table);
-	if (!data)
-		return -ENOTDIR;
-
-	if (oldval && oldlenp) {
-		if (get_user(len, oldlenp))
-			return -EFAULT;
-		if (len) {
-			if (len > table->maxlen)
-				len = table->maxlen;
-			if (copy_to_user(oldval, data, len))
-				return -EFAULT;
-			if (put_user(len, oldlenp))
-				return -EFAULT;
-		}
-	}
-
-	if (newval && newlen) {
-		if (newlen > table->maxlen)
-			newlen = table->maxlen;
-
-		if (copy_from_user(data, newval, newlen))
-			return -EFAULT;
+	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);
 	}
-	return 1;
 }
 
-static int sysctl_ipc_registered_data(ctl_table *table, int __user *name,
-		int nlen, void __user *oldval, size_t __user *oldlenp,
-		void __user *newval, size_t newlen)
+static int proc_ipcauto_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 oldval;
 	int rc;
 
-	rc = sysctl_ipc_data(table, name, nlen, oldval, oldlenp, newval,
-		newlen);
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+	ipc_table.data = get_ipc(table);
+	oldval = *((int *)(ipc_table.data));
 
-	if (newval && newlen && rc > 0) {
+	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
+
+	if (write && !rc && lenp_bef == *lenp) {
+		int newval = *((int *)(ipc_table.data));
 		/*
-		 * Tunable has successfully been changed from userland
+		 * The file "auto_msgmni" has correctly been set.
+		 * React by (un)registering the corresponding tunable, if the
+		 * value has changed.
 		 */
-		int *data = get_ipc(table);
-
-		tunable_set_callback(*data);
+		if (newval != oldval)
+			ipc_auto_callback(newval);
 	}
 
 	return rc;
 }
+
 #else
-#define sysctl_ipc_data NULL
-#define sysctl_ipc_registered_data NULL
+#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
 #endif
 
+static int zero;
+static int one = 1;
+static int int_max = INT_MAX;
+
 static struct ctl_table ipc_kern_table[] = {
 	{
-		.ctl_name	= KERN_SHMMAX,
 		.procname	= "shmmax",
 		.data		= &init_ipc_ns.shm_ctlmax,
-		.maxlen		= sizeof (init_ipc_ns.shm_ctlmax),
+		.maxlen		= sizeof(init_ipc_ns.shm_ctlmax),
 		.mode		= 0644,
 		.proc_handler	= proc_ipc_doulongvec_minmax,
-		.strategy	= sysctl_ipc_data,
 	},
 	{
-		.ctl_name	= KERN_SHMALL,
 		.procname	= "shmall",
 		.data		= &init_ipc_ns.shm_ctlall,
-		.maxlen		= sizeof (init_ipc_ns.shm_ctlall),
+		.maxlen		= sizeof(init_ipc_ns.shm_ctlall),
 		.mode		= 0644,
 		.proc_handler	= proc_ipc_doulongvec_minmax,
-		.strategy	= sysctl_ipc_data,
 	},
 	{
-		.ctl_name	= KERN_SHMMNI,
 		.procname	= "shmmni",
 		.data		= &init_ipc_ns.shm_ctlmni,
-		.maxlen		= sizeof (init_ipc_ns.shm_ctlmni),
+		.maxlen		= sizeof(init_ipc_ns.shm_ctlmni),
 		.mode		= 0644,
 		.proc_handler	= proc_ipc_dointvec,
-		.strategy	= sysctl_ipc_data,
 	},
 	{
-		.ctl_name	= KERN_MSGMAX,
+		.procname	= "shm_rmid_forced",
+		.data		= &init_ipc_ns.shm_rmid_forced,
+		.maxlen		= sizeof(init_ipc_ns.shm_rmid_forced),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax_orphans,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{
 		.procname	= "msgmax",
 		.data		= &init_ipc_ns.msg_ctlmax,
-		.maxlen		= sizeof (init_ipc_ns.msg_ctlmax),
+		.maxlen		= sizeof(init_ipc_ns.msg_ctlmax),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec,
-		.strategy	= sysctl_ipc_data,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
 	},
 	{
-		.ctl_name	= KERN_MSGMNI,
 		.procname	= "msgmni",
 		.data		= &init_ipc_ns.msg_ctlmni,
-		.maxlen		= sizeof (init_ipc_ns.msg_ctlmni),
+		.maxlen		= sizeof(init_ipc_ns.msg_ctlmni),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_callback_dointvec,
-		.strategy	= sysctl_ipc_registered_data,
+		.proc_handler	= proc_ipc_callback_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
 	},
 	{
-		.ctl_name	= KERN_MSGMNB,
 		.procname	=  "msgmnb",
 		.data		= &init_ipc_ns.msg_ctlmnb,
-		.maxlen		= sizeof (init_ipc_ns.msg_ctlmnb),
+		.maxlen		= sizeof(init_ipc_ns.msg_ctlmnb),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec,
-		.strategy	= sysctl_ipc_data,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
 	},
 	{
-		.ctl_name	= KERN_SEM,
 		.procname	= "sem",
 		.data		= &init_ipc_ns.sem_ctls,
-		.maxlen		= 4*sizeof (int),
+		.maxlen		= 4*sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_ipc_dointvec,
-		.strategy	= sysctl_ipc_data,
 	},
+	{
+		.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",
+		.data		= &init_ipc_ns.ids[IPC_SEM_IDS].next_id,
+		.maxlen		= sizeof(init_ipc_ns.ids[IPC_SEM_IDS].next_id),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+	{
+		.procname	= "msg_next_id",
+		.data		= &init_ipc_ns.ids[IPC_MSG_IDS].next_id,
+		.maxlen		= sizeof(init_ipc_ns.ids[IPC_MSG_IDS].next_id),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+	{
+		.procname	= "shm_next_id",
+		.data		= &init_ipc_ns.ids[IPC_SHM_IDS].next_id,
+		.maxlen		= sizeof(init_ipc_ns.ids[IPC_SHM_IDS].next_id),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+#endif
 	{}
 };
 
 static struct ctl_table ipc_root_table[] = {
 	{
-		.ctl_name	= CTL_KERN,
 		.procname	= "kernel",
 		.mode		= 0555,
 		.child		= ipc_kern_table,
@@ -241,4 +281,4 @@ static int __init ipc_sysctl_init(void)
 	return 0;
 }
 
-__initcall(ipc_sysctl_init);
+device_initcall(ipc_sysctl_init);