[PATCH v5 2/7] Add a reference to ucounts for each cred

[Alexey Gladkov <gladkov.alexey@gmail.com>]

For RLIMIT_NPROC and some other rlimits the user_struct that holds the
global limit is kept alive for the lifetime of a process by keeping it
in struct cred. Adding a pointer to ucounts in the struct cred will
allow to track RLIMIT_NPROC not only for user in the system, but for
user in the user_namespace.

Updating ucounts may require memory allocation which may fail. So, we
cannot change cred.ucounts in the commit_creds() because this function
cannot fail and it should always return 0. For this reason, we modify
cred.ucounts before calling the commit_creds().

Signed-off-by: Alexey Gladkov <gladkov.alexey@gmail.com>
---
 fs/exec.c                      |  4 +++
 include/linux/cred.h           |  2 ++
 include/linux/user_namespace.h |  3 +++
 kernel/cred.c                  | 45 ++++++++++++++++++++++++++++++++++
 kernel/fork.c                  |  6 +++++
 kernel/sys.c                   | 12 +++++++++
 kernel/ucount.c                | 26 +++++++++++++++++---
 kernel/user_namespace.c        |  3 +++
 8 files changed, 98 insertions(+), 3 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 5d4d52039105..0371a3400be5 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1360,6 +1360,10 @@ int begin_new_exec(struct linux_binprm * bprm)
 	WRITE_ONCE(me->self_exec_id, me->self_exec_id + 1);
 	flush_signal_handlers(me, 0);
 
+	retval = set_cred_ucounts(bprm->cred);
+	if (retval < 0)
+		goto out_unlock;
+
 	/*
 	 * install the new credentials for this executable
 	 */
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 18639c069263..ad160e5fe5c6 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -144,6 +144,7 @@ struct cred {
 #endif
 	struct user_struct *user;	/* real user ID subscription */
 	struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */
+	struct ucounts *ucounts;
 	struct group_info *group_info;	/* supplementary groups for euid/fsgid */
 	/* RCU deletion */
 	union {
@@ -170,6 +171,7 @@ extern int set_security_override_from_ctx(struct cred *, const char *);
 extern int set_create_files_as(struct cred *, struct inode *);
 extern int cred_fscmp(const struct cred *, const struct cred *);
 extern void __init cred_init(void);
+extern int set_cred_ucounts(struct cred *);
 
 /*
  * check for validity of credentials
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 0bb833fd41f4..43f5847cc897 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -102,6 +102,9 @@ bool setup_userns_sysctls(struct user_namespace *ns);
 void retire_userns_sysctls(struct user_namespace *ns);
 struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type);
 void dec_ucount(struct ucounts *ucounts, enum ucount_type type);
+struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid);
+struct ucounts *get_ucounts(struct ucounts *ucounts);
+void put_ucounts(struct ucounts *ucounts);
 
 #ifdef CONFIG_USER_NS
 
diff --git a/kernel/cred.c b/kernel/cred.c
index 421b1149c651..8194a59e283f 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -119,6 +119,8 @@ static void put_cred_rcu(struct rcu_head *rcu)
 	if (cred->group_info)
 		put_group_info(cred->group_info);
 	free_uid(cred->user);
+	if (cred->ucounts)
+		put_ucounts(cred->ucounts);
 	put_user_ns(cred->user_ns);
 	kmem_cache_free(cred_jar, cred);
 }
@@ -284,6 +286,11 @@ struct cred *prepare_creds(void)
 
 	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
+
+	new->ucounts = get_ucounts(new->ucounts);
+	if (!new->ucounts)
+		goto error;
+
 	validate_creds(new);
 	return new;
 
@@ -363,6 +370,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 		ret = create_user_ns(new);
 		if (ret < 0)
 			goto error_put;
+		if (set_cred_ucounts(new) < 0)
+			goto error_put;
 	}
 
 #ifdef CONFIG_KEYS
@@ -653,6 +662,33 @@ int cred_fscmp(const struct cred *a, const struct cred *b)
 }
 EXPORT_SYMBOL(cred_fscmp);
 
+int set_cred_ucounts(struct cred *new)
+{
+	struct task_struct *task = current;
+	const struct cred *old = task->real_cred;
+	struct ucounts *old_ucounts = new->ucounts;
+
+	BUG_ON(task->cred != old);
+
+	if (new->user == old->user && new->user_ns == old->user_ns)
+		return 0;
+
+	/*
+	 * This optimization is needed because alloc_ucounts() uses locks
+	 * for table lookups.
+	 */
+	if (old_ucounts && old_ucounts->ns == new->user_ns && uid_eq(old_ucounts->uid, new->euid))
+		return 0;
+
+	if (!(new->ucounts = alloc_ucounts(new->user_ns, new->euid)))
+		return -EAGAIN;
+
+	if (old_ucounts)
+		put_ucounts(old_ucounts);
+
+	return 0;
+}
+
 /*
  * initialise the credentials stuff
  */
@@ -661,6 +697,11 @@ void __init cred_init(void)
 	/* allocate a slab in which we can store credentials */
 	cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL);
+	/*
+	 * This is needed here because this is the first cred and there is no
+	 * ucount reference to copy.
+	 */
+	init_cred.ucounts = alloc_ucounts(init_cred.user_ns, init_cred.euid);
 }
 
 /**
@@ -719,6 +760,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
 		goto error;
 
+	new->ucounts = get_ucounts(new->ucounts);
+	if (!new->ucounts)
+		goto error;
+
 	put_cred(old);
 	validate_creds(new);
 	return new;
diff --git a/kernel/fork.c b/kernel/fork.c
index 37720a6d04ea..b0d36dea0a9c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2959,6 +2959,12 @@ int ksys_unshare(unsigned long unshare_flags)
 	if (err)
 		goto bad_unshare_cleanup_cred;
 
+	if (new_cred) {
+		err = set_cred_ucounts(new_cred);
+		if (err)
+			goto bad_unshare_cleanup_cred;
+	}
+
 	if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) {
 		if (do_sysvsem) {
 			/*
diff --git a/kernel/sys.c b/kernel/sys.c
index 51f00fe20e4d..373def7debe8 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -553,6 +553,10 @@ long __sys_setreuid(uid_t ruid, uid_t euid)
 	if (retval < 0)
 		goto error;
 
+	retval = set_cred_ucounts(new);
+	if (retval < 0)
+		goto error;
+
 	return commit_creds(new);
 
 error:
@@ -611,6 +615,10 @@ long __sys_setuid(uid_t uid)
 	if (retval < 0)
 		goto error;
 
+	retval = set_cred_ucounts(new);
+	if (retval < 0)
+		goto error;
+
 	return commit_creds(new);
 
 error:
@@ -686,6 +694,10 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
 	if (retval < 0)
 		goto error;
 
+	retval = set_cred_ucounts(new);
+	if (retval < 0)
+		goto error;
+
 	return commit_creds(new);
 
 error:
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 04c561751af1..9644bced74b4 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -125,7 +125,7 @@ static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struc
 	return NULL;
 }
 
-static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
+struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid)
 {
 	struct hlist_head *hashent = ucounts_hashentry(ns, uid);
 	struct ucounts *ucounts, *new;
@@ -160,11 +160,31 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 	return ucounts;
 }
 
-static void put_ucounts(struct ucounts *ucounts)
+struct ucounts *get_ucounts(struct ucounts *ucounts)
+{
+	unsigned long flags;
+
+	if (!ucounts)
+		return NULL;
+
+	spin_lock_irqsave(&ucounts_lock, flags);
+	if (ucounts->count == INT_MAX) {
+		WARN_ONCE(1, "ucounts: counter has reached its maximum value");
+		ucounts = NULL;
+	} else {
+		ucounts->count += 1;
+	}
+	spin_unlock_irqrestore(&ucounts_lock, flags);
+
+	return ucounts;
+}
+
+void put_ucounts(struct ucounts *ucounts)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&ucounts_lock, flags);
+	BUG_ON(ucounts->count <= 0);
 	ucounts->count -= 1;
 	if (!ucounts->count)
 		hlist_del_init(&ucounts->node);
@@ -194,7 +214,7 @@ 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) {
 		long max;
 		tns = iter->ns;
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index af612945a4d0..516db53166ab 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -1281,6 +1281,9 @@ static int userns_install(struct nsset *nsset, struct ns_common *ns)
 	put_user_ns(cred->user_ns);
 	set_cred_user_ns(cred, get_user_ns(user_ns));
 
+	if (set_cred_ucounts(cred) < 0)
+		return -EINVAL;
+
 	return 0;
 }
 
-- 
2.29.2