ipc: Store ipc sysctls in the ipc namespace

The ipc sysctls are not available for modification inside the user
namespace. Following the mqueue sysctls, we changed the implementation
to be more userns friendly.

So far, the changes do not provide additional access to files. This
will be done in a future patch.

Signed-off-by: Alexey Gladkov <legion@kernel.org>
Link: https://lkml.kernel.org/r/be6f9d014276f4dddd0c3aa05a86052856c1c555.1644862280.git.legion@kernel.org
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>

1 files changed, 122 insertions, 67 deletions

diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index f101c171753f..15210ac47e9e 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -13,43 +13,22 @@
 #include <linux/capability.h>
 #include <linux/ipc_namespace.h>
 #include <linux/msg.h>
+#include <linux/slab.h>
 #include "util.h"
 
-static void *get_ipc(struct ctl_table *table)
-{
-	char *which = table->data;
-	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
-	which = (which - (char *)&init_ipc_ns) + (char *)ipc_ns;
-	return which;
-}
-
-static int proc_ipc_dointvec(struct ctl_table *table, int write,
-		void *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, buffer, lenp, ppos);
-}
-
-static int proc_ipc_dointvec_minmax(struct ctl_table *table, int write,
+static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct ipc_namespace *ns = table->extra1;
 	struct ctl_table ipc_table;
+	int err;
 
 	memcpy(&ipc_table, table, sizeof(ipc_table));
-	ipc_table.data = get_ipc(table);
 
-	return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
-}
+	ipc_table.extra1 = SYSCTL_ZERO;
+	ipc_table.extra2 = SYSCTL_ONE;
 
-static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
-		void *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);
+	err = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 
 	if (err < 0)
 		return err;
@@ -58,17 +37,6 @@ static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
 	return err;
 }
 
-static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
-		void *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, buffer,
-					lenp, ppos);
-}
-
 static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -87,11 +55,17 @@ static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
 static int proc_ipc_sem_dointvec(struct ctl_table *table, int write,
 	void *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct ipc_namespace *ns = table->extra1;
+	struct ctl_table ipc_table;
 	int ret, semmni;
-	struct ipc_namespace *ns = current->nsproxy->ipc_ns;
+
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+
+	ipc_table.extra1 = NULL;
+	ipc_table.extra2 = NULL;
 
 	semmni = ns->sem_ctls[3];
-	ret = proc_ipc_dointvec(table, write, buffer, lenp, ppos);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (!ret)
 		ret = sem_check_semmni(current->nsproxy->ipc_ns);
@@ -108,12 +82,18 @@ static int proc_ipc_sem_dointvec(struct ctl_table *table, int write,
 static int proc_ipc_dointvec_minmax_checkpoint_restore(struct ctl_table *table,
 		int write, void *buffer, size_t *lenp, loff_t *ppos)
 {
-	struct user_namespace *user_ns = current->nsproxy->ipc_ns->user_ns;
+	struct ipc_namespace *ns = table->extra1;
+	struct ctl_table ipc_table;
 
-	if (write && !checkpoint_restore_ns_capable(user_ns))
+	if (write && !checkpoint_restore_ns_capable(ns->user_ns))
 		return -EPERM;
 
-	return proc_ipc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+
+	ipc_table.extra1 = SYSCTL_ZERO;
+	ipc_table.extra2 = SYSCTL_INT_MAX;
+
+	return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 }
 #endif
 
@@ -121,27 +101,27 @@ int ipc_mni = IPCMNI;
 int ipc_mni_shift = IPCMNI_SHIFT;
 int ipc_min_cycle = RADIX_TREE_MAP_SIZE;
 
-static struct ctl_table ipc_kern_table[] = {
+static struct ctl_table ipc_sysctls[] = {
 	{
 		.procname	= "shmmax",
 		.data		= &init_ipc_ns.shm_ctlmax,
 		.maxlen		= sizeof(init_ipc_ns.shm_ctlmax),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_doulongvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 	},
 	{
 		.procname	= "shmall",
 		.data		= &init_ipc_ns.shm_ctlall,
 		.maxlen		= sizeof(init_ipc_ns.shm_ctlall),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_doulongvec_minmax,
+		.proc_handler	= proc_doulongvec_minmax,
 	},
 	{
 		.procname	= "shmmni",
 		.data		= &init_ipc_ns.shm_ctlmni,
 		.maxlen		= sizeof(init_ipc_ns.shm_ctlmni),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= &ipc_mni,
 	},
@@ -151,15 +131,13 @@ static struct ctl_table ipc_kern_table[] = {
 		.maxlen		= sizeof(init_ipc_ns.shm_rmid_forced),
 		.mode		= 0644,
 		.proc_handler	= proc_ipc_dointvec_minmax_orphans,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "msgmax",
 		.data		= &init_ipc_ns.msg_ctlmax,
 		.maxlen		= sizeof(init_ipc_ns.msg_ctlmax),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_INT_MAX,
 	},
@@ -168,7 +146,7 @@ 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_dointvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= &ipc_mni,
 	},
@@ -186,7 +164,7 @@ static struct ctl_table ipc_kern_table[] = {
 		.data		= &init_ipc_ns.msg_ctlmnb,
 		.maxlen		= sizeof(init_ipc_ns.msg_ctlmnb),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_dointvec_minmax,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_INT_MAX,
 	},
@@ -204,8 +182,6 @@ static struct ctl_table ipc_kern_table[] = {
 		.maxlen		= sizeof(init_ipc_ns.ids[IPC_SEM_IDS].next_id),
 		.mode		= 0666,
 		.proc_handler	= proc_ipc_dointvec_minmax_checkpoint_restore,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_INT_MAX,
 	},
 	{
 		.procname	= "msg_next_id",
@@ -213,8 +189,6 @@ static struct ctl_table ipc_kern_table[] = {
 		.maxlen		= sizeof(init_ipc_ns.ids[IPC_MSG_IDS].next_id),
 		.mode		= 0666,
 		.proc_handler	= proc_ipc_dointvec_minmax_checkpoint_restore,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_INT_MAX,
 	},
 	{
 		.procname	= "shm_next_id",
@@ -222,25 +196,106 @@ static struct ctl_table ipc_kern_table[] = {
 		.maxlen		= sizeof(init_ipc_ns.ids[IPC_SHM_IDS].next_id),
 		.mode		= 0666,
 		.proc_handler	= proc_ipc_dointvec_minmax_checkpoint_restore,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_INT_MAX,
 	},
 #endif
 	{}
 };
 
-static struct ctl_table ipc_root_table[] = {
-	{
-		.procname	= "kernel",
-		.mode		= 0555,
-		.child		= ipc_kern_table,
-	},
-	{}
+static struct ctl_table_set *set_lookup(struct ctl_table_root *root)
+{
+	return &current->nsproxy->ipc_ns->ipc_set;
+}
+
+static int set_is_seen(struct ctl_table_set *set)
+{
+	return &current->nsproxy->ipc_ns->ipc_set == set;
+}
+
+static struct ctl_table_root set_root = {
+	.lookup = set_lookup,
 };
 
+bool setup_ipc_sysctls(struct ipc_namespace *ns)
+{
+	struct ctl_table *tbl;
+
+	setup_sysctl_set(&ns->ipc_set, &set_root, set_is_seen);
+
+	tbl = kmemdup(ipc_sysctls, sizeof(ipc_sysctls), GFP_KERNEL);
+	if (tbl) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(ipc_sysctls); i++) {
+			if (tbl[i].data == &init_ipc_ns.shm_ctlmax) {
+				tbl[i].data = &ns->shm_ctlmax;
+
+			} else if (tbl[i].data == &init_ipc_ns.shm_ctlall) {
+				tbl[i].data = &ns->shm_ctlall;
+
+			} else if (tbl[i].data == &init_ipc_ns.shm_ctlmni) {
+				tbl[i].data = &ns->shm_ctlmni;
+
+			} else if (tbl[i].data == &init_ipc_ns.shm_rmid_forced) {
+				tbl[i].data = &ns->shm_rmid_forced;
+				tbl[i].extra1 = ns;
+
+			} else if (tbl[i].data == &init_ipc_ns.msg_ctlmax) {
+				tbl[i].data = &ns->msg_ctlmax;
+
+			} else if (tbl[i].data == &init_ipc_ns.msg_ctlmni) {
+				tbl[i].data = &ns->msg_ctlmni;
+
+			} else if (tbl[i].data == &init_ipc_ns.msg_ctlmnb) {
+				tbl[i].data = &ns->msg_ctlmnb;
+
+			} else if (tbl[i].data == &init_ipc_ns.sem_ctls) {
+				tbl[i].data = &ns->sem_ctls;
+				tbl[i].extra1 = ns;
+#ifdef CONFIG_CHECKPOINT_RESTORE
+			} else if (tbl[i].data == &init_ipc_ns.ids[IPC_SEM_IDS].next_id) {
+				tbl[i].data = &ns->ids[IPC_SEM_IDS].next_id;
+				tbl[i].extra1 = ns;
+
+			} else if (tbl[i].data == &init_ipc_ns.ids[IPC_MSG_IDS].next_id) {
+				tbl[i].data = &ns->ids[IPC_MSG_IDS].next_id;
+				tbl[i].extra1 = ns;
+
+			} else if (tbl[i].data == &init_ipc_ns.ids[IPC_SHM_IDS].next_id) {
+				tbl[i].data = &ns->ids[IPC_SHM_IDS].next_id;
+				tbl[i].extra1 = ns;
+#endif
+			} else {
+				tbl[i].data = NULL;
+			}
+		}
+
+		ns->ipc_sysctls = __register_sysctl_table(&ns->ipc_set, "kernel", tbl);
+	}
+	if (!ns->ipc_sysctls) {
+		kfree(tbl);
+		retire_sysctl_set(&ns->ipc_set);
+		return false;
+	}
+
+	return true;
+}
+
+void retire_ipc_sysctls(struct ipc_namespace *ns)
+{
+	struct ctl_table *tbl;
+
+	tbl = ns->ipc_sysctls->ctl_table_arg;
+	unregister_sysctl_table(ns->ipc_sysctls);
+	retire_sysctl_set(&ns->ipc_set);
+	kfree(tbl);
+}
+
 static int __init ipc_sysctl_init(void)
 {
-	register_sysctl_table(ipc_root_table);
+	if (!setup_ipc_sysctls(&init_ipc_ns)) {
+		pr_warn("ipc sysctl registration failed\n");
+		return -ENOMEM;
+	}
 	return 0;
 }