ucounts: Count rlimits in each user namespace

Preface
-------
These patches are for binding the rlimit counters to a user in user namespace.
This patch set can be applied on top of:

git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git v5.12-rc4

Problem
-------
The RLIMIT_NPROC, RLIMIT_MEMLOCK, RLIMIT_SIGPENDING, RLIMIT_MSGQUEUE rlimits
implementation places the counters in user_struct [1]. These limits are global
between processes and persists for the lifetime of the process, even if
processes are in different user namespaces.

To illustrate the impact of rlimits, let's say there is a program that does not
fork. Some service-A wants to run this program as user X in multiple containers.
Since the program never fork the service wants to set RLIMIT_NPROC=1.

service-A
 \- program (uid=1000, container1, rlimit_nproc=1)
 \- program (uid=1000, container2, rlimit_nproc=1)

The service-A sets RLIMIT_NPROC=1 and runs the program in container1. When the
service-A tries to run a program with RLIMIT_NPROC=1 in container2 it fails
since user X already has one running process.

The problem is not that the limit from container1 affects container2. The
problem is that limit is verified against the global counter that reflects
the number of processes in all containers.

This problem can be worked around by using different users for each container
but in this case we face a different problem of uid mapping when transferring
files from one container to another.

Eric W. Biederman mentioned this issue [2][3].

Introduced changes
------------------
To address the problem, we bind rlimit counters to user namespace. Each counter
reflects the number of processes in a given uid in a given user namespace. The
result is a tree of rlimit counters with the biggest value at the root (aka
init_user_ns). The limit is considered exceeded if it's exceeded up in the tree.

[1]: https://lore.kernel.org/containers/[email protected]/
[2]: https://lists.linuxfoundation.org/pipermail/containers/2020-August/042096.html
[3]: https://lists.linuxfoundation.org/pipermail/containers/2020-October/042524.html

Changelog
---------
v11:
* Revert most of changes in signal.c to fix performance issues and remove
  unnecessary memory allocations.
* Fixed issue found by lkp robot (again).

v10:
* Fixed memory leak in __sigqueue_alloc.
* Handled an unlikely situation when all consumers will return ucounts at once.
* Addressed other review comments from Eric W. Biederman.

v9:
* Used a negative value to check that the ucounts->count is close to overflow.
* Rebased onto v5.12-rc4.

v8:
* Used atomic_t for ucounts reference counting. Also added counter overflow
  check (thanks to Linus Torvalds for the idea).
* Fixed other issues found by lkp-tests project in the patch that Reimplements
  RLIMIT_MEMLOCK on top of ucounts.

v7:
* Fixed issues found by lkp-tests project in the patch that Reimplements
  RLIMIT_MEMLOCK on top of ucounts.

v6:
* Fixed issues found by lkp-tests project.
* Rebased onto v5.11.

v5:
* Split the first commit into two commits: change ucounts.count type to atomic_long_t
  and add ucounts to cred. These commits were merged by mistake during the rebase.
* The __get_ucounts() renamed to alloc_ucounts().
* The cred.ucounts update has been moved from commit_creds() as it did not allow
  to handle errors.
* Added error handling of set_cred_ucounts().

v4:
* Reverted the type change of ucounts.count to refcount_t.
* Fixed typo in the kernel/cred.c

v3:
* Added get_ucounts() function to increase the reference count. The existing
  get_counts() function renamed to __get_ucounts().
* The type of ucounts.count changed from atomic_t to refcount_t.
* Dropped 'const' from set_cred_ucounts() arguments.
* Fixed a bug with freeing the cred structure after calling cred_alloc_blank().
* Commit messages have been updated.
* Added selftest.

v2:
* RLIMIT_MEMLOCK, RLIMIT_SIGPENDING and RLIMIT_MSGQUEUE are migrated to ucounts.
* Added ucounts for pair uid and user namespace into cred.
* Added the ability to increase ucount by more than 1.

v1:
* After discussion with Eric W. Biederman, I increased the size of ucounts to
  atomic_long_t.
* Added ucount_max to avoid the fork bomb.

--

Alexey Gladkov (9):
  Increase size of ucounts to atomic_long_t
  Add a reference to ucounts for each cred
  Use atomic_t for ucounts reference counting
  Reimplement RLIMIT_NPROC on top of ucounts
  Reimplement RLIMIT_MSGQUEUE on top of ucounts
  Reimplement RLIMIT_SIGPENDING on top of ucounts
  Reimplement RLIMIT_MEMLOCK on top of ucounts
  kselftests: Add test to check for rlimit changes in different user
    namespaces
  ucounts: Set ucount_max to the largest positive value the type can
    hold

 fs/exec.c                                     |   6 +-
 fs/hugetlbfs/inode.c                          |  16 +-
 fs/proc/array.c                               |   2 +-
 include/linux/cred.h                          |   4 +
 include/linux/hugetlb.h                       |   4 +-
 include/linux/mm.h                            |   4 +-
 include/linux/sched/user.h                    |   7 -
 include/linux/shmem_fs.h                      |   2 +-
 include/linux/signal_types.h                  |   4 +-
 include/linux/user_namespace.h                |  31 +++-
 ipc/mqueue.c                                  |  40 ++---
 ipc/shm.c                                     |  26 +--
 kernel/cred.c                                 |  50 +++++-
 kernel/exit.c                                 |   2 +-
 kernel/fork.c                                 |  18 +-
 kernel/signal.c                               |  25 +--
 kernel/sys.c                                  |  14 +-
 kernel/ucount.c                               | 116 ++++++++++---
 kernel/user.c                                 |   3 -
 kernel/user_namespace.c                       |   9 +-
 mm/memfd.c                                    |   4 +-
 mm/mlock.c                                    |  22 ++-
 mm/mmap.c                                     |   4 +-
 mm/shmem.c                                    |  10 +-
 tools/testing/selftests/Makefile              |   1 +
 tools/testing/selftests/rlimits/.gitignore    |   2 +
 tools/testing/selftests/rlimits/Makefile      |   6 +
 tools/testing/selftests/rlimits/config        |   1 +
 .../selftests/rlimits/rlimits-per-userns.c    | 161 ++++++++++++++++++
 29 files changed, 467 insertions(+), 127 deletions(-)
 create mode 100644 tools/testing/selftests/rlimits/.gitignore
 create mode 100644 tools/testing/selftests/rlimits/Makefile
 create mode 100644 tools/testing/selftests/rlimits/config
 create mode 100644 tools/testing/selftests/rlimits/rlimits-per-userns.c

Link: https://lkml.kernel.org/r/[email protected]

Author: ebiederm

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
 	 */
@@ -1874,7 +1878,7 @@ static int do_execveat_common(int fd, struct filename *filename,
 	 * whether NPROC limit is still exceeded.
 	 */
 	if ((current->flags & PF_NPROC_EXCEEDED) &&
-	    atomic_read(&current_user()->processes) > rlimit(RLIMIT_NPROC)) {
+	    is_ucounts_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) {
 		retval = -EAGAIN;
 		goto out_ret;
 	}

fs/hugetlbfs/inode.c

@@ -1443,7 +1443,7 @@ static int get_hstate_idx(int page_size_log)
  * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
  */
 struct file *hugetlb_file_setup(const char *name, size_t size,
-				vm_flags_t acctflag, struct user_struct **user,
+				vm_flags_t acctflag, struct ucounts **ucounts,
 				int creat_flags, int page_size_log)
 {
 	struct inode *inode;
@@ -1455,20 +1455,20 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	if (hstate_idx < 0)
 		return ERR_PTR(-ENODEV);
 
-	*user = NULL;
+	*ucounts = NULL;
 	mnt = hugetlbfs_vfsmount[hstate_idx];
 	if (!mnt)
 		return ERR_PTR(-ENOENT);
 
 	if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
-		*user = current_user();
-		if (user_shm_lock(size, *user)) {
+		*ucounts = current_ucounts();
+		if (user_shm_lock(size, *ucounts)) {
 			task_lock(current);
 			pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n",
 				current->comm, current->pid);
 			task_unlock(current);
 		} else {
-			*user = NULL;
+			*ucounts = NULL;
 			return ERR_PTR(-EPERM);
 		}
 	}
@@ -1495,9 +1495,9 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 
 	iput(inode);
 out:
-	if (*user) {
-		user_shm_unlock(size, *user);
-		*user = NULL;
+	if (*ucounts) {
+		user_shm_unlock(size, *ucounts);
+		*ucounts = NULL;
 	}
 	return file;
 }

fs/proc/array.c

@@ -284,7 +284,7 @@ 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 = atomic_read(&__task_cred(p)->user->sigpending);
+		qsize = get_ucounts_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING);
 		rcu_read_unlock();
 		qlim = task_rlimit(p, RLIMIT_SIGPENDING);
 		unlock_task_sighand(p, &flags);

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
@@ -370,6 +372,7 @@ 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)			\
 ({						\
@@ -386,6 +389,7 @@ 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

include/linux/hugetlb.h

@@ -434,7 +434,7 @@ 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)
@@ -454,7 +454,7 @@ 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);

include/linux/mm.h

@@ -1670,8 +1670,8 @@ 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.

include/linux/sched/user.h

@@ -12,19 +12,12 @@
  */
 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_FANOTIFY
 	atomic_t fanotify_listeners;
 #endif
 #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 */
 

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)

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. */

include/linux/user_namespace.h

@@ -50,9 +50,15 @@ enum ucount_type {
 	UCOUNT_INOTIFY_INSTANCES,
 	UCOUNT_INOTIFY_WATCHES,
 #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;
@@ -88,23 +94,42 @@ 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