1 files changed, 189 insertions, 69 deletions

diff --git a/kernel/ucount.c b/kernel/ucount.c
index 11b1596e2542..586af49fc03e 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -8,8 +8,17 @@
 #include <linux/kmemleak.h>
 #include <linux/user_namespace.h>
 
+struct ucounts init_ucounts = {
+	.ns    = &init_user_ns,
+	.uid   = GLOBAL_ROOT_UID,
+	.count = RCUREF_INIT(1),
+};
+
 #define UCOUNTS_HASHTABLE_BITS 10
-static struct hlist_head ucounts_hashtable[(1 << UCOUNTS_HASHTABLE_BITS)];
+#define UCOUNTS_HASHTABLE_ENTRIES (1 << UCOUNTS_HASHTABLE_BITS)
+static struct hlist_nulls_head ucounts_hashtable[UCOUNTS_HASHTABLE_ENTRIES] = {
+	[0 ... UCOUNTS_HASHTABLE_ENTRIES - 1] = HLIST_NULLS_HEAD_INIT(0)
+};
 static DEFINE_SPINLOCK(ucounts_lock);
 
 #define ucounts_hashfn(ns, uid)						\
@@ -18,7 +27,6 @@ static DEFINE_SPINLOCK(ucounts_lock);
 #define ucounts_hashentry(ns, uid)	\
 	(ucounts_hashtable + ucounts_hashfn(ns, uid))
 
-
 #ifdef CONFIG_SYSCTL
 static struct ctl_table_set *
 set_lookup(struct ctl_table_root *root)
@@ -32,7 +40,7 @@ static int set_is_seen(struct ctl_table_set *set)
 }
 
 static int set_permissions(struct ctl_table_header *head,
-				  struct ctl_table *table)
+			   const struct ctl_table *table)
 {
 	struct user_namespace *user_ns =
 		container_of(head->set, struct user_namespace, set);
@@ -52,16 +60,19 @@ static struct ctl_table_root set_root = {
 	.permissions = set_permissions,
 };
 
-#define UCOUNT_ENTRY(name)				\
-	{						\
-		.procname	= name,			\
-		.maxlen		= sizeof(int),		\
-		.mode		= 0644,			\
-		.proc_handler	= proc_dointvec_minmax,	\
-		.extra1		= SYSCTL_ZERO,		\
-		.extra2		= SYSCTL_INT_MAX,	\
+static long ue_zero = 0;
+static long ue_int_max = INT_MAX;
+
+#define UCOUNT_ENTRY(name)					\
+	{							\
+		.procname	= name,				\
+		.maxlen		= sizeof(long),			\
+		.mode		= 0644,				\
+		.proc_handler	= proc_doulongvec_minmax,	\
+		.extra1		= &ue_zero,			\
+		.extra2		= &ue_int_max,			\
 	}
-static struct ctl_table user_table[] = {
+static const struct ctl_table user_table[] = {
 	UCOUNT_ENTRY("max_user_namespaces"),
 	UCOUNT_ENTRY("max_pid_namespaces"),
 	UCOUNT_ENTRY("max_uts_namespaces"),
@@ -74,7 +85,10 @@ static struct ctl_table user_table[] = {
 	UCOUNT_ENTRY("max_inotify_instances"),
 	UCOUNT_ENTRY("max_inotify_watches"),
 #endif
-	{ }
+#ifdef CONFIG_FANOTIFY
+	UCOUNT_ENTRY("max_fanotify_groups"),
+	UCOUNT_ENTRY("max_fanotify_marks"),
+#endif
 };
 #endif /* CONFIG_SYSCTL */
 
@@ -83,7 +97,7 @@ bool setup_userns_sysctls(struct user_namespace *ns)
 #ifdef CONFIG_SYSCTL
 	struct ctl_table *tbl;
 
-	BUILD_BUG_ON(ARRAY_SIZE(user_table) != UCOUNT_COUNTS + 1);
+	BUILD_BUG_ON(ARRAY_SIZE(user_table) != UCOUNT_COUNTS);
 	setup_sysctl_set(&ns->set, &set_root, set_is_seen);
 	tbl = kmemdup(user_table, sizeof(user_table), GFP_KERNEL);
 	if (tbl) {
@@ -91,7 +105,8 @@ bool setup_userns_sysctls(struct user_namespace *ns)
 		for (i = 0; i < UCOUNT_COUNTS; i++) {
 			tbl[i].data = &ns->ucount_max[i];
 		}
-		ns->sysctls = __register_sysctl_table(&ns->set, "user", tbl);
+		ns->sysctls = __register_sysctl_table(&ns->set, "user", tbl,
+						      ARRAY_SIZE(user_table));
 	}
 	if (!ns->sysctls) {
 		kfree(tbl);
@@ -105,7 +120,7 @@ bool setup_userns_sysctls(struct user_namespace *ns)
 void retire_userns_sysctls(struct user_namespace *ns)
 {
 #ifdef CONFIG_SYSCTL
-	struct ctl_table *tbl;
+	const struct ctl_table *tbl;
 
 	tbl = ns->sysctls->ctl_table_arg;
 	unregister_sysctl_table(ns->sysctls);
@@ -114,79 +129,86 @@ void retire_userns_sysctls(struct user_namespace *ns)
 #endif
 }
 
-static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struct hlist_head *hashent)
+static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid,
+				    struct hlist_nulls_head *hashent)
 {
 	struct ucounts *ucounts;
+	struct hlist_nulls_node *pos;
 
-	hlist_for_each_entry(ucounts, hashent, node) {
-		if (uid_eq(ucounts->uid, uid) && (ucounts->ns == ns))
-			return ucounts;
+	guard(rcu)();
+	hlist_nulls_for_each_entry_rcu(ucounts, pos, hashent, node) {
+		if (uid_eq(ucounts->uid, uid) && (ucounts->ns == ns)) {
+			if (rcuref_get(&ucounts->count))
+				return ucounts;
+		}
 	}
 	return NULL;
 }
 
-static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
+static void hlist_add_ucounts(struct ucounts *ucounts)
 {
-	struct hlist_head *hashent = ucounts_hashentry(ns, uid);
+	struct hlist_nulls_head *hashent = ucounts_hashentry(ucounts->ns, ucounts->uid);
+
+	spin_lock_irq(&ucounts_lock);
+	hlist_nulls_add_head_rcu(&ucounts->node, hashent);
+	spin_unlock_irq(&ucounts_lock);
+}
+
+struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid)
+{
+	struct hlist_nulls_head *hashent = ucounts_hashentry(ns, uid);
 	struct ucounts *ucounts, *new;
 
+	ucounts = find_ucounts(ns, uid, hashent);
+	if (ucounts)
+		return ucounts;
+
+	new = kzalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+	new->ns = ns;
+	new->uid = uid;
+	rcuref_init(&new->count, 1);
+
 	spin_lock_irq(&ucounts_lock);
 	ucounts = find_ucounts(ns, uid, hashent);
-	if (!ucounts) {
+	if (ucounts) {
 		spin_unlock_irq(&ucounts_lock);
-
-		new = kzalloc(sizeof(*new), GFP_KERNEL);
-		if (!new)
-			return NULL;
-
-		new->ns = ns;
-		new->uid = uid;
-		new->count = 0;
-
-		spin_lock_irq(&ucounts_lock);
-		ucounts = find_ucounts(ns, uid, hashent);
-		if (ucounts) {
-			kfree(new);
-		} else {
-			hlist_add_head(&new->node, hashent);
-			ucounts = new;
-		}
+		kfree(new);
+		return ucounts;
 	}
-	if (ucounts->count == INT_MAX)
-		ucounts = NULL;
-	else
-		ucounts->count += 1;
+
+	hlist_nulls_add_head_rcu(&new->node, hashent);
+	get_user_ns(new->ns);
 	spin_unlock_irq(&ucounts_lock);
-	return ucounts;
+	return new;
 }
 
-static void put_ucounts(struct ucounts *ucounts)
+void put_ucounts(struct ucounts *ucounts)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&ucounts_lock, flags);
-	ucounts->count -= 1;
-	if (!ucounts->count)
-		hlist_del_init(&ucounts->node);
-	else
-		ucounts = NULL;
-	spin_unlock_irqrestore(&ucounts_lock, flags);
+	if (rcuref_put(&ucounts->count)) {
+		spin_lock_irqsave(&ucounts_lock, flags);
+		hlist_nulls_del_rcu(&ucounts->node);
+		spin_unlock_irqrestore(&ucounts_lock, flags);
 
-	kfree(ucounts);
+		put_user_ns(ucounts->ns);
+		kfree_rcu(ucounts, rcu);
+	}
 }
 
-static inline bool atomic_inc_below(atomic_t *v, int u)
+static inline bool atomic_long_inc_below(atomic_long_t *v, long u)
 {
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
+	long c = atomic_long_read(v);
+
+	do {
 		if (unlikely(c >= u))
 			return false;
-		old = atomic_cmpxchg(v, c, c+1);
-		if (likely(old == c))
-			return true;
-		c = old;
-	}
+	} while (!atomic_long_try_cmpxchg(v, &c, c+1));
+
+	return true;
 }
 
 struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid,
@@ -194,19 +216,19 @@ struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid,
 {
 	struct ucounts *ucounts, *iter, *bad;
 	struct user_namespace *tns;
-	ucounts = get_ucounts(ns, uid);
+	ucounts = alloc_ucounts(ns, uid);
 	for (iter = ucounts; iter; iter = tns->ucounts) {
-		int max;
+		long max;
 		tns = iter->ns;
 		max = READ_ONCE(tns->ucount_max[type]);
-		if (!atomic_inc_below(&iter->ucount[type], max))
+		if (!atomic_long_inc_below(&iter->ucount[type], max))
 			goto fail;
 	}
 	return ucounts;
 fail:
 	bad = iter;
 	for (iter = ucounts; iter != bad; iter = iter->ns->ucounts)
-		atomic_dec(&iter->ucount[type]);
+		atomic_long_dec(&iter->ucount[type]);
 
 	put_ucounts(ucounts);
 	return NULL;
@@ -216,12 +238,108 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type)
 {
 	struct ucounts *iter;
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
-		int dec = atomic_dec_if_positive(&iter->ucount[type]);
+		long dec = atomic_long_dec_if_positive(&iter->ucount[type]);
 		WARN_ON_ONCE(dec < 0);
 	}
 	put_ucounts(ucounts);
 }
 
+long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v)
+{
+	struct ucounts *iter;
+	long max = LONG_MAX;
+	long ret = 0;
+
+	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
+		long new = atomic_long_add_return(v, &iter->rlimit[type]);
+		if (new < 0 || new > max)
+			ret = LONG_MAX;
+		else if (iter == ucounts)
+			ret = new;
+		max = get_userns_rlimit_max(iter->ns, type);
+	}
+	return ret;
+}
+
+bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v)
+{
+	struct ucounts *iter;
+	long new = -1; /* Silence compiler warning */
+	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
+		long dec = atomic_long_sub_return(v, &iter->rlimit[type]);
+		WARN_ON_ONCE(dec < 0);
+		if (iter == ucounts)
+			new = dec;
+	}
+	return (new == 0);
+}
+
+static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts,
+				struct ucounts *last, enum rlimit_type type)
+{
+	struct ucounts *iter, *next;
+	for (iter = ucounts; iter != last; iter = next) {
+		long dec = atomic_long_sub_return(1, &iter->rlimit[type]);
+		WARN_ON_ONCE(dec < 0);
+		next = iter->ns->ucounts;
+		if (dec == 0)
+			put_ucounts(iter);
+	}
+}
+
+void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type)
+{
+	do_dec_rlimit_put_ucounts(ucounts, NULL, type);
+}
+
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type,
+			    bool override_rlimit)
+{
+	/* Caller must hold a reference to ucounts */
+	struct ucounts *iter;
+	long max = LONG_MAX;
+	long dec, ret = 0;
+
+	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
+		long new = atomic_long_add_return(1, &iter->rlimit[type]);
+		if (new < 0 || new > max)
+			goto dec_unwind;
+		if (iter == ucounts)
+			ret = new;
+		if (!override_rlimit)
+			max = get_userns_rlimit_max(iter->ns, type);
+		/*
+		 * Grab an extra ucount reference for the caller when
+		 * the rlimit count was previously 0.
+		 */
+		if (new != 1)
+			continue;
+		if (!get_ucounts(iter))
+			goto dec_unwind;
+	}
+	return ret;
+dec_unwind:
+	dec = atomic_long_sub_return(1, &iter->rlimit[type]);
+	WARN_ON_ONCE(dec < 0);
+	do_dec_rlimit_put_ucounts(ucounts, iter, type);
+	return 0;
+}
+
+bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long rlimit)
+{
+	struct ucounts *iter;
+	long max = rlimit;
+	if (rlimit > LONG_MAX)
+		max = LONG_MAX;
+	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
+		long val = get_rlimit_value(iter, type);
+		if (val < 0 || val > max)
+			return true;
+		max = get_userns_rlimit_max(iter->ns, type);
+	}
+	return false;
+}
+
 static __init int user_namespace_sysctl_init(void)
 {
 #ifdef CONFIG_SYSCTL
@@ -232,11 +350,13 @@ static __init int user_namespace_sysctl_init(void)
 	 * default set so that registrations in the child sets work
 	 * properly.
 	 */
-	user_header = register_sysctl("user", empty);
+	user_header = register_sysctl_sz("user", empty, 0);
 	kmemleak_ignore(user_header);
 	BUG_ON(!user_header);
 	BUG_ON(!setup_userns_sysctls(&init_user_ns));
 #endif
+	hlist_add_ucounts(&init_ucounts);
+	inc_rlimit_ucounts(&init_ucounts, UCOUNT_RLIMIT_NPROC, 1);
 	return 0;
 }
 subsys_initcall(user_namespace_sysctl_init);