Merge remote branch 'limits/writable_limits'

9 files changed, 146 insertions, 41 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index af643b5aefe8..b89417087581 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -128,6 +128,8 @@ struct pid_entry {
 		NULL, &proc_single_file_operations,	\
 		{ .proc_show = show } )
 
+static ssize_t proc_info_read(struct file * file, char __user * buf,
+			  size_t count, loff_t *ppos);
 /*
  * Count the number of hardlinks for the pid_entry table, excluding the .
  * and .. links.
@@ -521,6 +523,74 @@ static int proc_pid_limits(struct task_struct *task, char *buffer)
 	return count;
 }
 
+static ssize_t limits_write(struct file *file, const char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+	char str[32 + 1 + 16 + 1 + 16 + 1], *delim, *next;
+	struct rlimit new_rlimit;
+	unsigned int i;
+	int ret;
+
+	if (!task) {
+		count = -ESRCH;
+		goto out;
+	}
+	if (copy_from_user(str, buf, min(count, sizeof(str) - 1))) {
+		count = -EFAULT;
+		goto put_task;
+	}
+
+	str[min(count, sizeof(str) - 1)] = 0;
+
+	delim = strchr(str, '=');
+	if (!delim) {
+		count = -EINVAL;
+		goto put_task;
+	}
+	*delim++ = 0; /* for easy 'str' usage */
+	new_rlimit.rlim_cur = simple_strtoul(delim, &next, 0);
+	if (*next != ':') {
+		if (strncmp(delim, "unlimited:", 10)) {
+			count = -EINVAL;
+			goto put_task;
+		}
+		new_rlimit.rlim_cur = RLIM_INFINITY;
+		next = delim + 9; /* move to ':' */
+	}
+	delim = next + 1;
+	new_rlimit.rlim_max = simple_strtoul(delim, &next, 0);
+	if (*next != 0) {
+		if (strcmp(delim, "unlimited")) {
+			count = -EINVAL;
+			goto put_task;
+		}
+		new_rlimit.rlim_max = RLIM_INFINITY;
+	}
+
+	for (i = 0; i < RLIM_NLIMITS; i++)
+		if (!strcmp(str, lnames[i].name))
+			break;
+	if (i >= RLIM_NLIMITS) {
+		count = -EINVAL;
+		goto put_task;
+	}
+
+	ret = setrlimit(task, i, &new_rlimit);
+	if (ret)
+		count = ret;
+
+put_task:
+	put_task_struct(task);
+out:
+	return count;
+}
+
+static const struct file_operations proc_pid_limits_operations = {
+	.read		= proc_info_read,
+	.write		= limits_write,
+};
+
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
 static int proc_pid_syscall(struct task_struct *task, char *buffer)
 {
@@ -2500,7 +2570,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 	INF("auxv",       S_IRUSR, proc_pid_auxv),
 	ONE("status",     S_IRUGO, proc_pid_status),
 	ONE("personality", S_IRUSR, proc_pid_personality),
-	INF("limits",	  S_IRUSR, proc_pid_limits),
+	NOD("limits",	  S_IFREG|S_IRUSR|S_IWUSR, NULL,
+			&proc_pid_limits_operations,
+			{ .proc_read = proc_pid_limits }),
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
@@ -2834,7 +2906,9 @@ static const struct pid_entry tid_base_stuff[] = {
 	INF("auxv",      S_IRUSR, proc_pid_auxv),
 	ONE("status",    S_IRUGO, proc_pid_status),
 	ONE("personality", S_IRUSR, proc_pid_personality),
-	INF("limits",	 S_IRUSR, proc_pid_limits),
+	NOD("limits",	  S_IFREG|S_IRUSR|S_IWUSR, NULL,
+			&proc_pid_limits_operations,
+			{ .proc_read = proc_pid_limits }),
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",     S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 4f71bf4e628c..3e23844a6990 100644
--- a/include/linux/posix-timers.h
+++ b/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
diff --git a/include/linux/resource.h b/include/linux/resource.h
index 40fc7e626082..4301d67f8c44 100644
--- a/include/linux/resource.h
+++ b/include/linux/resource.h
@@ -71,5 +71,7 @@ struct rlimit {
 #include <asm/resource.h>
 
 int getrusage(struct task_struct *p, int who, struct rusage __user *ru);
+int setrlimit(struct task_struct *tsk, unsigned int resource,
+		struct rlimit *new_rlim);
 
 #endif
diff --git a/include/linux/security.h b/include/linux/security.h
index 466cbadbd1ef..9c3a43b20ce7 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1591,7 +1591,8 @@ 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);
@@ -1856,7 +1857,8 @@ int security_task_setgroups(struct group_info *group_info);
 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);
@@ -2472,7 +2474,8 @@ 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;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 5c9dc228747b..102c34516e76 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -13,16 +13,16 @@
 /*
  * Called after updating RLIMIT_CPU to set timer expiration if necessary.
  */
-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);
-	struct signal_struct *const sig = current->signal;
+	struct signal_struct *const sig = task->signal;
 
 	if (cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) ||
 	    cputime_gt(sig->it[CPUCLOCK_PROF].expires, cputime)) {
-		spin_lock_irq(&current->sighand->siglock);
-		set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
-		spin_unlock_irq(&current->sighand->siglock);
+		spin_lock_irq(&task->sighand->siglock);
+		set_process_cpu_timer(task, CPUCLOCK_PROF, &cputime, NULL);
+		spin_unlock_irq(&task->sighand->siglock);
 	}
 }
 
diff --git a/kernel/sys.c b/kernel/sys.c
index ce17760d9c51..605ab9c7be92 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1238,43 +1238,52 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
 
 #endif
 
-SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
+/* make sure you are allowed to change @tsk limits before calling this */
+int setrlimit(struct task_struct *tsk, unsigned int resource,
+		struct rlimit *new_rlim)
 {
-	struct rlimit new_rlim, *old_rlim;
+	struct rlimit *old_rlim;
 	int retval;
 
-	if (resource >= RLIM_NLIMITS)
+	if (new_rlim->rlim_cur > new_rlim->rlim_max)
 		return -EINVAL;
-	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
-		return -EFAULT;
-	if (new_rlim.rlim_cur > new_rlim.rlim_max)
-		return -EINVAL;
-	old_rlim = current->signal->rlim + resource;
-	if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
-	    !capable(CAP_SYS_RESOURCE))
-		return -EPERM;
-	if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
+	if (resource == RLIMIT_NOFILE && new_rlim->rlim_max > sysctl_nr_open)
 		return -EPERM;
 
-	retval = security_task_setrlimit(resource, &new_rlim);
+	/* optimization: 'current' doesn't need locking, e.g. setrlimit */
+	if (tsk != current) {
+		/* protect tsk->signal and tsk->sighand from disappearing */
+		read_lock(&tasklist_lock);
+		if (!tsk->sighand) {
+			retval = -ESRCH;
+			goto out;
+		}
+	}
+
+	retval = security_task_setrlimit(tsk, resource, new_rlim);
 	if (retval)
-		return retval;
+		goto out;
 
-	if (resource == RLIMIT_CPU && new_rlim.rlim_cur == 0) {
+	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;
+		new_rlim->rlim_cur = 1;
 	}
 
-	task_lock(current->group_leader);
-	*old_rlim = new_rlim;
-	task_unlock(current->group_leader);
+	old_rlim = tsk->signal->rlim + resource;
+	task_lock(tsk->group_leader);
+	if ((new_rlim->rlim_max <= old_rlim->rlim_max) ||
+				capable(CAP_SYS_RESOURCE))
+		*old_rlim = *new_rlim;
+	else
+		retval = -EPERM;
+	task_unlock(tsk->group_leader);
 
-	if (resource != RLIMIT_CPU)
+	if (retval || resource != RLIMIT_CPU)
 		goto out;
 
 	/*
@@ -1283,12 +1292,25 @@ 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 (new_rlim->rlim_cur == RLIM_INFINITY)
 		goto out;
 
-	update_rlimit_cpu(new_rlim.rlim_cur);
+	update_rlimit_cpu(tsk, new_rlim->rlim_cur);
 out:
-	return 0;
+	if (tsk != current)
+		read_unlock(&tasklist_lock);
+	return retval;
+}
+
+SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
+{
+	struct rlimit new_rlim;
+
+	if (resource >= RLIM_NLIMITS)
+		return -EINVAL;
+	if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
+		return -EFAULT;
+	return setrlimit(current, resource, &new_rlim);
 }
 
 /*
diff --git a/security/capability.c b/security/capability.c
index 5c700e1a4fd3..10f23a4c84e5 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -466,7 +466,8 @@ 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;
 }
diff --git a/security/security.c b/security/security.c
index 24e060be9fa5..b6e43a15f9aa 100644
--- a/security/security.c
+++ b/security/security.c
@@ -826,9 +826,10 @@ 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,
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index c96d63ec4753..18e2e5b47c27 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2365,7 +2365,8 @@ static void selinux_bprm_committing_creds(struct linux_binprm *bprm)
 			initrlim = init_task.signal->rlim + i;
 			rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur);
 		}
-		update_rlimit_cpu(rlim->rlim_cur);
+		update_rlimit_cpu(current,
+				current->signal->rlim[RLIMIT_CPU].rlim_cur);
 	}
 }
 
@@ -3398,16 +3399,17 @@ 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;
 }