Merge branch 'writable_limits' of git://decibel.fi.muni.cz/~xslaby/linux

* 'writable_limits' of git://decibel.fi.muni.cz/~xslaby/linux:
  unistd: add __NR_prlimit64 syscall numbers
  rlimits: implement prlimit64 syscall
  rlimits: switch more rlimit syscalls to do_prlimit
  rlimits: redo do_setrlimit to more generic do_prlimit
  rlimits: add rlimit64 structure
  rlimits: do security check under task_lock
  rlimits: allow setrlimit to non-current tasks
  rlimits: split sys_setrlimit
  rlimits: selinux, do rlimits changes under task_lock
  rlimits: make sure ->rlim_max never grows in sys_setrlimit
  rlimits: add task_struct to update_rlimit_cpu
  rlimits: security, add task_struct to setrlimit

Fix up various system call number conflicts.  We not only added fanotify
system calls in the meantime, but asm-generic/unistd.h added a wait4
along with a range of reserved per-architecture system calls.

arch/x86/ia32/ia32entry.S

@@ -844,4 +844,5 @@ ia32_sys_call_table:
 	.quad compat_sys_recvmmsg
 	.quad sys_fanotify_init
 	.quad sys32_fanotify_mark
+	.quad sys_prlimit64
 ia32_syscall_end:

arch/x86/include/asm/unistd_32.h

@@ -345,10 +345,11 @@
 #define __NR_recvmmsg		337
 #define __NR_fanotify_init	338
 #define __NR_fanotify_mark	339
+#define __NR_prlimit64		340
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 340
+#define NR_syscalls 341
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR

arch/x86/include/asm/unistd_64.h

@@ -667,6 +667,8 @@ __SYSCALL(__NR_recvmmsg, sys_recvmmsg)
 __SYSCALL(__NR_fanotify_init, sys_fanotify_init)
 #define __NR_fanotify_mark			301
 __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+#define __NR_prlimit64				302
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR

arch/x86/kernel/syscall_table_32.S

@@ -339,3 +339,4 @@ ENTRY(sys_call_table)
 	.long sys_recvmmsg
 	.long sys_fanotify_init
 	.long sys_fanotify_mark
+	.long sys_prlimit64

include/asm-generic/unistd.h

@@ -640,9 +640,11 @@ __SYSCALL(__NR_recvmmsg, sys_recvmmsg)
 
 #define __NR_wait4 260
 __SYSCALL(__NR_wait4, sys_wait4)
+#define __NR_prlimit64 261
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
 
 #undef __NR_syscalls
-#define __NR_syscalls 261
+#define __NR_syscalls 262
 
 /*
  * All syscalls below here should go away really,

include/linux/posix-timers.h

@@ -117,6 +117,6 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
 
 long clock_nanosleep_restart(struct restart_block *restart_block);
 
-void update_rlimit_cpu(unsigned long rlim_new);
+void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new);
 
 #endif

include/linux/resource.h

@@ -43,6 +43,13 @@ struct rlimit {
 	unsigned long	rlim_max;
 };
 
+#define RLIM64_INFINITY		(~0ULL)
+
+struct rlimit64 {
+	__u64 rlim_cur;
+	__u64 rlim_max;
+};
+
 #define	PRIO_MIN	(-20)
 #define	PRIO_MAX	20
 
@@ -73,6 +80,8 @@ struct rlimit {
 struct task_struct;
 
 int getrusage(struct task_struct *p, int who, struct rusage __user *ru);
+int do_prlimit(struct task_struct *tsk, unsigned int resource,
+		struct rlimit *new_rlim, struct rlimit *old_rlim);
 
 #endif /* __KERNEL__ */
 

include/linux/security.h

@@ -1499,7 +1499,8 @@ struct security_operations {
 	int (*task_setnice) (struct task_struct *p, int nice);
 	int (*task_setioprio) (struct task_struct *p, int ioprio);
 	int (*task_getioprio) (struct task_struct *p);
-	int (*task_setrlimit) (unsigned int resource, struct rlimit *new_rlim);
+	int (*task_setrlimit) (struct task_struct *p, unsigned int resource,
+			struct rlimit *new_rlim);
 	int (*task_setscheduler) (struct task_struct *p, int policy,
 				  struct sched_param *lp);
 	int (*task_getscheduler) (struct task_struct *p);
@@ -1749,7 +1750,8 @@ void security_task_getsecid(struct task_struct *p, u32 *secid);
 int security_task_setnice(struct task_struct *p, int nice);
 int security_task_setioprio(struct task_struct *p, int ioprio);
 int security_task_getioprio(struct task_struct *p);
-int security_task_setrlimit(unsigned int resource, struct rlimit *new_rlim);
+int security_task_setrlimit(struct task_struct *p, unsigned int resource,
+		struct rlimit *new_rlim);
 int security_task_setscheduler(struct task_struct *p,
 				int policy, struct sched_param *lp);
 int security_task_getscheduler(struct task_struct *p);
@@ -2311,7 +2313,8 @@ static inline int security_task_getioprio(struct task_struct *p)
 	return 0;
 }
 
-static inline int security_task_setrlimit(unsigned int resource,
+static inline int security_task_setrlimit(struct task_struct *p,
+					  unsigned int resource,
 					  struct rlimit *new_rlim)
 {
 	return 0;

include/linux/syscalls.h

@@ -35,6 +35,7 @@ struct oldold_utsname;
 struct old_utsname;
 struct pollfd;
 struct rlimit;
+struct rlimit64;
 struct rusage;
 struct sched_param;
 struct sel_arg_struct;
@@ -644,6 +645,9 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r
 #endif
 asmlinkage long sys_setrlimit(unsigned int resource,
 				struct rlimit __user *rlim);
+asmlinkage long sys_prlimit64(pid_t pid, unsigned int resource,
+				const struct rlimit64 __user *new_rlim,
+				struct rlimit64 __user *old_rlim);
 asmlinkage long sys_getrusage(int who, struct rusage __user *ru);
 asmlinkage long sys_umask(int mask);
 

kernel/compat.c

@@ -279,11 +279,6 @@ asmlinkage long compat_sys_setrlimit(unsigned int resource,
 		struct compat_rlimit __user *rlim)
 {
 	struct rlimit r;
-	int ret;
-	mm_segment_t old_fs = get_fs ();
-
-	if (resource >= RLIM_NLIMITS)
-		return -EINVAL;
 
 	if (!access_ok(VERIFY_READ, rlim, sizeof(*rlim)) ||
 	    __get_user(r.rlim_cur, &rlim->rlim_cur) ||
@@ -294,10 +289,7 @@ asmlinkage long compat_sys_setrlimit(unsigned int resource,
 		r.rlim_cur = RLIM_INFINITY;
 	if (r.rlim_max == COMPAT_RLIM_INFINITY)
 		r.rlim_max = RLIM_INFINITY;
-	set_fs(KERNEL_DS);
+	return do_prlimit(current, resource, &r, NULL);
-	ret = sys_setrlimit(resource, (struct rlimit __user *) &r);
-	set_fs(old_fs);
-	return ret;
 }
 
 #ifdef COMPAT_RLIM_OLD_INFINITY
@@ -329,16 +321,13 @@ asmlinkage long compat_sys_old_getrlimit(unsigned int resource,
 
 #endif
 
-asmlinkage long compat_sys_getrlimit (unsigned int resource,
+asmlinkage long compat_sys_getrlimit(unsigned int resource,
 		struct compat_rlimit __user *rlim)
 {
 	struct rlimit r;
 	int ret;
-	mm_segment_t old_fs = get_fs();
 
-	set_fs(KERNEL_DS);
+	ret = do_prlimit(current, resource, NULL, &r);
-	ret = sys_getrlimit(resource, (struct rlimit __user *) &r);
-	set_fs(old_fs);
 	if (!ret) {
 		if (r.rlim_cur > COMPAT_RLIM_INFINITY)
 			r.rlim_cur = COMPAT_RLIM_INFINITY;

kernel/posix-cpu-timers.c

@@ -16,13 +16,13 @@
  * siglock protection since other code may update expiration cache as
  * well.
  */
-void update_rlimit_cpu(unsigned long rlim_new)
+void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
 {
 	cputime_t cputime = secs_to_cputime(rlim_new);
 
-	spin_lock_irq(&current->sighand->siglock);
+	spin_lock_irq(&task->sighand->siglock);
-	set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
+	set_process_cpu_timer(task, CPUCLOCK_PROF, &cputime, NULL);
-	spin_unlock_irq(&current->sighand->siglock);
+	spin_unlock_irq(&task->sighand->siglock);
 }
 
 static int check_clock(const clockid_t which_clock)

kernel/sys.c

@@ -1236,15 +1236,14 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
 
 SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim)
 {
-	if (resource >= RLIM_NLIMITS)
+	struct rlimit value;
-		return -EINVAL;
+	int ret;
-	else {
+
-		struct rlimit value;
+	ret = do_prlimit(current, resource, NULL, &value);
-		task_lock(current->group_leader);
+	if (!ret)
-		value = current->signal->rlim[resource];
+		ret = copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
-		task_unlock(current->group_leader);
+
-		return copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
+	return ret;
-	}
 }
 
 #ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT
@@ -1272,44 +1271,89 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
 
 #endif
 
-SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
+static inline bool rlim64_is_infinity(__u64 rlim64)
 {
-	struct rlimit new_rlim, *old_rlim;
+#if BITS_PER_LONG < 64
-	int retval;
+	return rlim64 >= ULONG_MAX;
+#else
+	return rlim64 == RLIM64_INFINITY;
+#endif
+}
+
+static void rlim_to_rlim64(const struct rlimit *rlim, struct rlimit64 *rlim64)
+{
+	if (rlim->rlim_cur == RLIM_INFINITY)
+		rlim64->rlim_cur = RLIM64_INFINITY;
+	else
+		rlim64->rlim_cur = rlim->rlim_cur;
+	if (rlim->rlim_max == RLIM_INFINITY)
+		rlim64->rlim_max = RLIM64_INFINITY;
+	else
+		rlim64->rlim_max = rlim->rlim_max;
+}
+
+static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim)
+{
+	if (rlim64_is_infinity(rlim64->rlim_cur))
+		rlim->rlim_cur = RLIM_INFINITY;
+	else
+		rlim->rlim_cur = (unsigned long)rlim64->rlim_cur;
+	if (rlim64_is_infinity(rlim64->rlim_max))
+		rlim->rlim_max = RLIM_INFINITY;
+	else
+		rlim->rlim_max = (unsigned long)rlim64->rlim_max;
+}
+
+/* make sure you are allowed to change @tsk limits before calling this */
+int do_prlimit(struct task_struct *tsk, unsigned int resource,
+		struct rlimit *new_rlim, struct rlimit *old_rlim)
+{
+	struct rlimit *rlim;
+	int retval = 0;
 
 	if (resource >= RLIM_NLIMITS)
 		return -EINVAL;
-	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
+	if (new_rlim) {
-		return -EFAULT;
+		if (new_rlim->rlim_cur > new_rlim->rlim_max)
-	if (new_rlim.rlim_cur > new_rlim.rlim_max)
+			return -EINVAL;
-		return -EINVAL;
+		if (resource == RLIMIT_NOFILE &&
-	old_rlim = current->signal->rlim + resource;
+				new_rlim->rlim_max > sysctl_nr_open)
-	if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
+			return -EPERM;
-	    !capable(CAP_SYS_RESOURCE))
-		return -EPERM;
-	if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
-		return -EPERM;
-
-	retval = security_task_setrlimit(resource, &new_rlim);
-	if (retval)
-		return retval;
-
-	if (resource == RLIMIT_CPU && new_rlim.rlim_cur == 0) {
-		/*
-		 * The caller is asking for an immediate RLIMIT_CPU
-		 * expiry.  But we use the zero value to mean "it was
-		 * never set".  So let's cheat and make it one second
-		 * instead
-		 */
-		new_rlim.rlim_cur = 1;
 	}
 
-	task_lock(current->group_leader);
+	/* protect tsk->signal and tsk->sighand from disappearing */
-	*old_rlim = new_rlim;
+	read_lock(&tasklist_lock);
-	task_unlock(current->group_leader);
+	if (!tsk->sighand) {
-
+		retval = -ESRCH;
-	if (resource != RLIMIT_CPU)
 		goto out;
+	}
+
+	rlim = tsk->signal->rlim + resource;
+	task_lock(tsk->group_leader);
+	if (new_rlim) {
+		if (new_rlim->rlim_max > rlim->rlim_max &&
+				!capable(CAP_SYS_RESOURCE))
+			retval = -EPERM;
+		if (!retval)
+			retval = security_task_setrlimit(tsk->group_leader,
+					resource, new_rlim);
+		if (resource == RLIMIT_CPU && new_rlim->rlim_cur == 0) {
+			/*
+			 * The caller is asking for an immediate RLIMIT_CPU
+			 * expiry.  But we use the zero value to mean "it was
+			 * never set".  So let's cheat and make it one second
+			 * instead
+			 */
+			new_rlim->rlim_cur = 1;
+		}
+	}
+	if (!retval) {
+		if (old_rlim)
+			*old_rlim = *rlim;
+		if (new_rlim)
+			*rlim = *new_rlim;
+	}
+	task_unlock(tsk->group_leader);
 
 	/*
 	 * RLIMIT_CPU handling.   Note that the kernel fails to return an error
@@ -1317,14 +1361,84 @@ SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
 	 * very long-standing error, and fixing it now risks breakage of
 	 * applications, so we live with it
 	 */
-	if (new_rlim.rlim_cur == RLIM_INFINITY)
+	 if (!retval && new_rlim && resource == RLIMIT_CPU &&
-		goto out;
+			 new_rlim->rlim_cur != RLIM_INFINITY)
-
+		update_rlimit_cpu(tsk, new_rlim->rlim_cur);
-	update_rlimit_cpu(new_rlim.rlim_cur);
 out:
+	read_unlock(&tasklist_lock);
+	return retval;
+}
+
+/* rcu lock must be held */
+static int check_prlimit_permission(struct task_struct *task)
+{
+	const struct cred *cred = current_cred(), *tcred;
+
+	tcred = __task_cred(task);
+	if ((cred->uid != tcred->euid ||
+	     cred->uid != tcred->suid ||
+	     cred->uid != tcred->uid  ||
+	     cred->gid != tcred->egid ||
+	     cred->gid != tcred->sgid ||
+	     cred->gid != tcred->gid) &&
+	     !capable(CAP_SYS_RESOURCE)) {
+		return -EPERM;
+	}
+
 	return 0;
 }
 
+SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource,
+		const struct rlimit64 __user *, new_rlim,
+		struct rlimit64 __user *, old_rlim)
+{
+	struct rlimit64 old64, new64;
+	struct rlimit old, new;
+	struct task_struct *tsk;
+	int ret;
+
+	if (new_rlim) {
+		if (copy_from_user(&new64, new_rlim, sizeof(new64)))
+			return -EFAULT;
+		rlim64_to_rlim(&new64, &new);
+	}
+
+	rcu_read_lock();
+	tsk = pid ? find_task_by_vpid(pid) : current;
+	if (!tsk) {
+		rcu_read_unlock();
+		return -ESRCH;
+	}
+	ret = check_prlimit_permission(tsk);
+	if (ret) {
+		rcu_read_unlock();
+		return ret;
+	}
+	get_task_struct(tsk);
+	rcu_read_unlock();
+
+	ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL,
+			old_rlim ? &old : NULL);
+
+	if (!ret && old_rlim) {
+		rlim_to_rlim64(&old, &old64);
+		if (copy_to_user(old_rlim, &old64, sizeof(old64)))
+			ret = -EFAULT;
+	}
+
+	put_task_struct(tsk);
+	return ret;
+}
+
+SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
+{
+	struct rlimit new_rlim;
+
+	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
+		return -EFAULT;
+	return do_prlimit(current, resource, &new_rlim, NULL);
+}
+
 /*
  * It would make sense to put struct rusage in the task_struct,
  * except that would make the task_struct be *really big*.  After

security/capability.c

@@ -411,7 +411,8 @@ static int cap_task_getioprio(struct task_struct *p)
 	return 0;
 }
 
-static int cap_task_setrlimit(unsigned int resource, struct rlimit *new_rlim)
+static int cap_task_setrlimit(struct task_struct *p, unsigned int resource,
+		struct rlimit *new_rlim)
 {
 	return 0;
 }

security/security.c

@@ -780,9 +780,10 @@ int security_task_getioprio(struct task_struct *p)
 	return security_ops->task_getioprio(p);
 }
 
-int security_task_setrlimit(unsigned int resource, struct rlimit *new_rlim)
+int security_task_setrlimit(struct task_struct *p, unsigned int resource,
+		struct rlimit *new_rlim)
 {
-	return security_ops->task_setrlimit(resource, new_rlim);
+	return security_ops->task_setrlimit(p, resource, new_rlim);
 }
 
 int security_task_setscheduler(struct task_struct *p,

security/selinux/hooks.c

@@ -2284,12 +2284,15 @@ static void selinux_bprm_committing_creds(struct linux_binprm *bprm)
 	rc = avc_has_perm(new_tsec->osid, new_tsec->sid, SECCLASS_PROCESS,
 			  PROCESS__RLIMITINH, NULL);
 	if (rc) {
+		/* protect against do_prlimit() */
+		task_lock(current);
 		for (i = 0; i < RLIM_NLIMITS; i++) {
 			rlim = current->signal->rlim + i;
 			initrlim = init_task.signal->rlim + i;
 			rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur);
 		}
-		update_rlimit_cpu(current->signal->rlim[RLIMIT_CPU].rlim_cur);
+		task_unlock(current);
+		update_rlimit_cpu(current, rlimit(RLIMIT_CPU));
 	}
 }
 
@@ -3333,16 +3336,17 @@ static int selinux_task_getioprio(struct task_struct *p)
 	return current_has_perm(p, PROCESS__GETSCHED);
 }
 
-static int selinux_task_setrlimit(unsigned int resource, struct rlimit *new_rlim)
+static int selinux_task_setrlimit(struct task_struct *p, unsigned int resource,
+		struct rlimit *new_rlim)
 {
-	struct rlimit *old_rlim = current->signal->rlim + resource;
+	struct rlimit *old_rlim = p->signal->rlim + resource;
 
 	/* Control the ability to change the hard limit (whether
 	   lowering or raising it), so that the hard limit can
 	   later be used as a safe reset point for the soft limit
 	   upon context transitions.  See selinux_bprm_committing_creds. */
 	if (old_rlim->rlim_max != new_rlim->rlim_max)
-		return current_has_perm(current, PROCESS__SETRLIMIT);
+		return current_has_perm(p, PROCESS__SETRLIMIT);
 
 	return 0;
 }