Merge tag 'ucount-rlimits-cleanups-for-v5.19' of git://git.kernel.org…

…/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull ucounts update from Eric Biederman:
 "Split rlimit and ucount values and max values

  After the ucount rlimit code was merged a bunch of small but
  siginificant bugs were found and fixed. At the time it was realized
  that part of the problem was that while the ucount rlimits were very
  similar to the oridinary ucounts (in being nested counts with limits)
  the semantics were slightly different and the code would be less error
  prone if there was less sharing.

  This is the long awaited cleanup that should hopefully keep things
  more comprehensible and less error prone for whoever needs to touch
  that code next"

* tag 'ucount-rlimits-cleanups-for-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  ucounts: Split rlimit and ucount values and max values

fs/exec.c

@@ -1879,7 +1879,7 @@ static int do_execveat_common(int fd, struct filename *filename,
 	 * whether NPROC limit is still exceeded.
 	 */
 	if ((current->flags & PF_NPROC_EXCEEDED) &&
-	    is_ucounts_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
+	    is_rlimit_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
 		retval = -EAGAIN;
 		goto out_ret;
 	}

fs/proc/array.c

@@ -279,7 +279,7 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p)
 		collect_sigign_sigcatch(p, &ignored, &caught);
 		num_threads = get_nr_threads(p);
 		rcu_read_lock();  /* FIXME: is this correct? */
-		qsize = get_ucounts_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING);
+		qsize = get_rlimit_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING);
 		rcu_read_unlock();
 		qlim = task_rlimit(p, RLIMIT_SIGPENDING);
 		unlock_task_sighand(p, &flags);

include/linux/user_namespace.h

@@ -54,15 +54,17 @@ enum ucount_type {
 	UCOUNT_FANOTIFY_GROUPS,
 	UCOUNT_FANOTIFY_MARKS,
 #endif
+	UCOUNT_COUNTS,
+};
+
+enum rlimit_type {
 	UCOUNT_RLIMIT_NPROC,
 	UCOUNT_RLIMIT_MSGQUEUE,
 	UCOUNT_RLIMIT_SIGPENDING,
 	UCOUNT_RLIMIT_MEMLOCK,
-	UCOUNT_COUNTS,
+	UCOUNT_RLIMIT_COUNTS,
 };
 
-#define MAX_PER_NAMESPACE_UCOUNTS UCOUNT_RLIMIT_NPROC
-
 struct user_namespace {
 	struct uid_gid_map	uid_map;
 	struct uid_gid_map	gid_map;
@@ -99,6 +101,7 @@ struct user_namespace {
 #endif
 	struct ucounts		*ucounts;
 	long ucount_max[UCOUNT_COUNTS];
+	long rlimit_max[UCOUNT_RLIMIT_COUNTS];
 } __randomize_layout;
 
 struct ucounts {
@@ -107,6 +110,7 @@ struct ucounts {
 	kuid_t uid;
 	atomic_t count;
 	atomic_long_t ucount[UCOUNT_COUNTS];
+	atomic_long_t rlimit[UCOUNT_RLIMIT_COUNTS];
 };
 
 extern struct user_namespace init_user_ns;
@@ -120,21 +124,26 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid);
 struct ucounts * __must_check get_ucounts(struct ucounts *ucounts);
 void put_ucounts(struct ucounts *ucounts);
 
-static inline long get_ucounts_value(struct ucounts *ucounts, enum ucount_type type)
+static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type type)
 {
-	return atomic_long_read(&ucounts->ucount[type]);
+	return atomic_long_read(&ucounts->rlimit[type]);
 }
 
-long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v);
-bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v);
-long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type);
-void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type);
-bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max);
+long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v);
+bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v);
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type);
+void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type);
+bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max);
+
+static inline long get_userns_rlimit_max(struct user_namespace *ns, enum rlimit_type type)
+{
+	return READ_ONCE(ns->rlimit_max[type]);
+}
 
-static inline void set_rlimit_ucount_max(struct user_namespace *ns,
-		enum ucount_type type, unsigned long max)
+static inline void set_userns_rlimit_max(struct user_namespace *ns,
+		enum rlimit_type type, unsigned long max)
 {
-	ns->ucount_max[type] = max <= LONG_MAX ? max : LONG_MAX;
+	ns->rlimit_max[type] = max <= LONG_MAX ? max : LONG_MAX;
 }
 
 #ifdef CONFIG_USER_NS

kernel/fork.c

@@ -925,13 +925,13 @@ void __init fork_init(void)
 	init_task.signal->rlim[RLIMIT_SIGPENDING] =
 		init_task.signal->rlim[RLIMIT_NPROC];
 
-	for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++)
+	for (i = 0; i < UCOUNT_COUNTS; i++)
 		init_user_ns.ucount_max[i] = max_threads/2;
 
-	set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_NPROC,      RLIM_INFINITY);
-	set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE,   RLIM_INFINITY);
-	set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY);
-	set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK,    RLIM_INFINITY);
+	set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC,      RLIM_INFINITY);
+	set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE,   RLIM_INFINITY);
+	set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY);
+	set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK,    RLIM_INFINITY);
 
 #ifdef CONFIG_VMAP_STACK
 	cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
@@ -2117,7 +2117,7 @@ static __latent_entropy struct task_struct *copy_process(
 		goto bad_fork_free;
 
 	retval = -EAGAIN;
-	if (is_ucounts_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
+	if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
 		if (p->real_cred->user != INIT_USER &&
 		    !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
 			goto bad_fork_cleanup_count;

kernel/sys.c

@@ -496,7 +496,7 @@ static void flag_nproc_exceeded(struct cred *new)
 	 * for programs doing set*uid()+execve() by harmlessly deferring the
 	 * failure to the execve() stage.
 	 */
-	if (is_ucounts_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) &&
+	if (is_rlimit_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) &&
 			new->user != INIT_USER)
 		current->flags |= PF_NPROC_EXCEEDED;
 	else

kernel/ucount.c

@@ -87,10 +87,6 @@ static struct ctl_table user_table[] = {
 	UCOUNT_ENTRY("max_fanotify_groups"),
 	UCOUNT_ENTRY("max_fanotify_marks"),
 #endif
-	{ },
-	{ },
-	{ },
-	{ },
 	{ }
 };
 #endif /* CONFIG_SYSCTL */
@@ -263,29 +259,29 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type)
 	put_ucounts(ucounts);
 }
 
-long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
+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->ucount[type]);
+		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 = READ_ONCE(iter->ns->ucount_max[type]);
+		max = get_userns_rlimit_max(iter->ns, type);
 	}
 	return ret;
 }
 
-bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
+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->ucount[type]);
+		long dec = atomic_long_sub_return(v, &iter->rlimit[type]);
 		WARN_ON_ONCE(dec < 0);
 		if (iter == ucounts)
 			new = dec;
@@ -294,37 +290,37 @@ bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
 }
 
 static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts,
-				struct ucounts *last, enum ucount_type type)
+				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->ucount[type]);
+		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 ucount_type type)
+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 ucount_type type)
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type)
 {
 	/* 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->ucount[type]);
+		long new = atomic_long_add_return(1, &iter->rlimit[type]);
 		if (new < 0 || new > max)
 			goto unwind;
 		if (iter == ucounts)
 			ret = new;
-		max = READ_ONCE(iter->ns->ucount_max[type]);
+		max = get_userns_rlimit_max(iter->ns, type);
 		/*
 		 * Grab an extra ucount reference for the caller when
 		 * the rlimit count was previously 0.
@@ -336,24 +332,24 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
 	}
 	return ret;
 dec_unwind:
-	dec = atomic_long_sub_return(1, &iter->ucount[type]);
+	dec = atomic_long_sub_return(1, &iter->rlimit[type]);
 	WARN_ON_ONCE(dec < 0);
 unwind:
 	do_dec_rlimit_put_ucounts(ucounts, iter, type);
 	return 0;
 }
 
-bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long rlimit)
+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_ucounts_value(iter, type);
+		long val = get_rlimit_value(iter, type);
 		if (val < 0 || val > max)
 			return true;
-		max = READ_ONCE(iter->ns->ucount_max[type]);
+		max = get_userns_rlimit_max(iter->ns, type);
 	}
 	return false;
 }

kernel/user_namespace.c

@@ -136,13 +136,13 @@ int create_user_ns(struct cred *new)
 	ns->owner = owner;
 	ns->group = group;
 	INIT_WORK(&ns->work, free_user_ns);
-	for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) {
+	for (i = 0; i < UCOUNT_COUNTS; i++) {
 		ns->ucount_max[i] = INT_MAX;
 	}
-	set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit());
-	set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE));
-	set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING));
-	set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK));
+	set_userns_rlimit_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit());
+	set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE));
+	set_userns_rlimit_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING));
+	set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK));
 	ns->ucounts = ucounts;
 
 	/* Inherit USERNS_SETGROUPS_ALLOWED from our parent */