Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull user namespace rlimit handling update from Eric Biederman:
 "This is the work mainly by Alexey Gladkov to limit rlimits to the
  rlimits of the user that created a user namespace, and to allow users
  to have stricter limits on the resources created within a user
  namespace."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  cred: add missing return error code when set_cred_ucounts() failed
  ucounts: Silence warning in dec_rlimit_ucounts
  ucounts: Set ucount_max to the largest positive value the type can hold
  kselftests: Add test to check for rlimit changes in different user namespaces
  Reimplement RLIMIT_MEMLOCK on top of ucounts
  Reimplement RLIMIT_SIGPENDING on top of ucounts
  Reimplement RLIMIT_MSGQUEUE on top of ucounts
  Reimplement RLIMIT_NPROC on top of ucounts
  Use atomic_t for ucounts reference counting
  Add a reference to ucounts for each cred
  Increase size of ucounts to atomic_long_t

7 files changed, 40 insertions, 16 deletions

diff --git a/include/linux/cred.h b/include/linux/cred.h
index 14971322e1a0..fcbc6885cc09 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -143,6 +143,7 @@ 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 {
@@ -169,6 +170,7 @@ 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
@@ -369,6 +371,7 @@ static inline void put_cred(const struct cred *_cred)
 
 #define task_uid(task)		(task_cred_xxx((task), uid))
 #define task_euid(task)		(task_cred_xxx((task), euid))
+#define task_ucounts(task)	(task_cred_xxx((task), ucounts))
 
 #define current_cred_xxx(xxx)			\
 ({						\
@@ -385,6 +388,7 @@ static inline void put_cred(const struct cred *_cred)
 #define current_fsgid() 	(current_cred_xxx(fsgid))
 #define current_cap()		(current_cred_xxx(cap_effective))
 #define current_user()		(current_cred_xxx(user))
+#define current_ucounts()	(current_cred_xxx(ucounts))
 
 extern struct user_namespace init_user_ns;
 #ifdef CONFIG_USER_NS
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 3c0117656745..8ba79dc64ab8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -451,7 +451,7 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
 extern const struct file_operations hugetlbfs_file_operations;
 extern const struct vm_operations_struct hugetlb_vm_ops;
 struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
-				struct user_struct **user, int creat_flags,
+				struct ucounts **ucounts, int creat_flags,
 				int page_size_log);
 
 static inline bool is_file_hugepages(struct file *file)
@@ -471,7 +471,7 @@ static inline struct hstate *hstate_inode(struct inode *i)
 #define is_file_hugepages(file)			false
 static inline struct file *
 hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag,
-		struct user_struct **user, int creat_flags,
+		struct ucounts **ucounts, int creat_flags,
 		int page_size_log)
 {
 	return ERR_PTR(-ENOSYS);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8ae31622deef..01ecf9e3603c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1709,8 +1709,8 @@ extern bool can_do_mlock(void);
 #else
 static inline bool can_do_mlock(void) { return false; }
 #endif
-extern int user_shm_lock(size_t, struct user_struct *);
-extern void user_shm_unlock(size_t, struct user_struct *);
+extern int user_shm_lock(size_t, struct ucounts *);
+extern void user_shm_unlock(size_t, struct ucounts *);
 
 /*
  * Parameter block passed down to zap_pte_range in exceptional cases.
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 3632c5d6ec55..2462f7d07695 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -12,16 +12,9 @@
  */
 struct user_struct {
 	refcount_t __count;	/* reference count */
-	atomic_t processes;	/* How many processes does this user have? */
-	atomic_t sigpending;	/* How many pending signals does this user have? */
 #ifdef CONFIG_EPOLL
 	atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
 #endif
-#ifdef CONFIG_POSIX_MQUEUE
-	/* protected by mq_lock	*/
-	unsigned long mq_bytes;	/* How many bytes can be allocated to mqueue? */
-#endif
-	unsigned long locked_shm; /* How many pages of mlocked shm ? */
 	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
 	atomic_long_t pipe_bufs;  /* how many pages are allocated in pipe buffers */
 
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index d82b6f396588..aa77dcd1646f 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -65,7 +65,7 @@ extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt,
 extern int shmem_zero_setup(struct vm_area_struct *);
 extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags);
-extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
+extern int shmem_lock(struct file *file, int lock, struct ucounts *ucounts);
 #ifdef CONFIG_SHMEM
 extern const struct address_space_operations shmem_aops;
 static inline bool shmem_mapping(struct address_space *mapping)
diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h
index 68e06c75c5b2..34cb28b8f16c 100644
--- a/include/linux/signal_types.h
+++ b/include/linux/signal_types.h
@@ -13,6 +13,8 @@ typedef struct kernel_siginfo {
 	__SIGINFO;
 } kernel_siginfo_t;
 
+struct ucounts;
+
 /*
  * Real Time signals may be queued.
  */
@@ -21,7 +23,7 @@ struct sigqueue {
 	struct list_head list;
 	int flags;
 	kernel_siginfo_t info;
-	struct user_struct *user;
+	struct ucounts *ucounts;
 };
 
 /* flags values. */
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 1d08dbbcfe32..eb70cabe6e7f 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -54,9 +54,15 @@ enum ucount_type {
 	UCOUNT_FANOTIFY_GROUPS,
 	UCOUNT_FANOTIFY_MARKS,
 #endif
+	UCOUNT_RLIMIT_NPROC,
+	UCOUNT_RLIMIT_MSGQUEUE,
+	UCOUNT_RLIMIT_SIGPENDING,
+	UCOUNT_RLIMIT_MEMLOCK,
 	UCOUNT_COUNTS,
 };
 
+#define MAX_PER_NAMESPACE_UCOUNTS UCOUNT_RLIMIT_NPROC
+
 struct user_namespace {
 	struct uid_gid_map	uid_map;
 	struct uid_gid_map	gid_map;
@@ -92,23 +98,42 @@ struct user_namespace {
 	struct ctl_table_header *sysctls;
 #endif
 	struct ucounts		*ucounts;
-	int ucount_max[UCOUNT_COUNTS];
+	long ucount_max[UCOUNT_COUNTS];
 } __randomize_layout;
 
 struct ucounts {
 	struct hlist_node node;
 	struct user_namespace *ns;
 	kuid_t uid;
-	int count;
-	atomic_t ucount[UCOUNT_COUNTS];
+	atomic_t count;
+	atomic_long_t ucount[UCOUNT_COUNTS];
 };
 
 extern struct user_namespace init_user_ns;
+extern struct ucounts init_ucounts;
 
 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 * __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)
+{
+	return atomic_long_read(&ucounts->ucount[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);
+bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max);
+
+static inline void set_rlimit_ucount_max(struct user_namespace *ns,
+		enum ucount_type type, unsigned long max)
+{
+	ns->ucount_max[type] = max <= LONG_MAX ? max : LONG_MAX;
+}
 
 #ifdef CONFIG_USER_NS