1 files changed, 50 insertions, 49 deletions

diff --git a/block/ioprio.c b/block/ioprio.c
index 2e0559f157c8..73301a261429 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -17,73 +17,48 @@
  *
  * ioprio_set(PRIO_PROCESS, pid, prio);
  *
- * See also Documentation/block/ioprio.txt
+ * See also Documentation/block/ioprio.rst
  *
  */
 #include <linux/gfp.h>
 #include <linux/kernel.h>
-#include <linux/export.h>
 #include <linux/ioprio.h>
 #include <linux/cred.h>
 #include <linux/blkdev.h>
 #include <linux/capability.h>
-#include <linux/sched/user.h>
-#include <linux/sched/task.h>
 #include <linux/syscalls.h>
 #include <linux/security.h>
 #include <linux/pid_namespace.h>
 
-int set_task_ioprio(struct task_struct *task, int ioprio)
-{
-	int err;
-	struct io_context *ioc;
-	const struct cred *cred = current_cred(), *tcred;
-
-	rcu_read_lock();
-	tcred = __task_cred(task);
-	if (!uid_eq(tcred->uid, cred->euid) &&
-	    !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) {
-		rcu_read_unlock();
-		return -EPERM;
-	}
-	rcu_read_unlock();
-
-	err = security_task_setioprio(task, ioprio);
-	if (err)
-		return err;
-
-	ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
-	if (ioc) {
-		ioc->ioprio = ioprio;
-		put_io_context(ioc);
-	}
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(set_task_ioprio);
-
 int ioprio_check_cap(int ioprio)
 {
 	int class = IOPRIO_PRIO_CLASS(ioprio);
-	int data = IOPRIO_PRIO_DATA(ioprio);
+	int level = IOPRIO_PRIO_LEVEL(ioprio);
 
 	switch (class) {
 		case IOPRIO_CLASS_RT:
-			if (!capable(CAP_SYS_ADMIN))
+			/*
+			 * Originally this only checked for CAP_SYS_ADMIN,
+			 * which was implicitly allowed for pid 0 by security
+			 * modules such as SELinux. Make sure we check
+			 * CAP_SYS_ADMIN first to avoid a denial/avc for
+			 * possibly missing CAP_SYS_NICE permission.
+			 */
+			if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE))
 				return -EPERM;
-			/* fall through */
+			fallthrough;
 			/* rt has prio field too */
 		case IOPRIO_CLASS_BE:
-			if (data >= IOPRIO_BE_NR || data < 0)
+			if (level >= IOPRIO_NR_LEVELS)
 				return -EINVAL;
-
 			break;
 		case IOPRIO_CLASS_IDLE:
 			break;
 		case IOPRIO_CLASS_NONE:
-			if (data)
+			if (level)
 				return -EINVAL;
 			break;
+		case IOPRIO_CLASS_INVALID:
 		default:
 			return -EINVAL;
 	}
@@ -119,11 +94,17 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
 				pgrp = task_pgrp(current);
 			else
 				pgrp = find_vpid(who);
+
+			read_lock(&tasklist_lock);
 			do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
 				ret = set_task_ioprio(p, ioprio);
-				if (ret)
-					break;
+				if (ret) {
+					read_unlock(&tasklist_lock);
+					goto out;
+				}
 			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+			read_unlock(&tasklist_lock);
+
 			break;
 		case IOPRIO_WHO_USER:
 			uid = make_kuid(current_user_ns(), who);
@@ -153,6 +134,7 @@ free_uid:
 			ret = -EINVAL;
 	}
 
+out:
 	rcu_read_unlock();
 	return ret;
 }
@@ -164,22 +146,38 @@ static int get_task_ioprio(struct task_struct *p)
 	ret = security_task_getioprio(p);
 	if (ret)
 		goto out;
-	ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM);
+	task_lock(p);
+	ret = __get_task_ioprio(p);
+	task_unlock(p);
+out:
+	return ret;
+}
+
+/*
+ * Return raw IO priority value as set by userspace. We use this for
+ * ioprio_get(pid, IOPRIO_WHO_PROCESS) so that we keep historical behavior and
+ * also so that userspace can distinguish unset IO priority (which just gets
+ * overriden based on task's nice value) from IO priority set to some value.
+ */
+static int get_task_raw_ioprio(struct task_struct *p)
+{
+	int ret;
+
+	ret = security_task_getioprio(p);
+	if (ret)
+		goto out;
 	task_lock(p);
 	if (p->io_context)
 		ret = p->io_context->ioprio;
+	else
+		ret = IOPRIO_DEFAULT;
 	task_unlock(p);
 out:
 	return ret;
 }
 
-int ioprio_best(unsigned short aprio, unsigned short bprio)
+static int ioprio_best(unsigned short aprio, unsigned short bprio)
 {
-	if (!ioprio_valid(aprio))
-		aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
-	if (!ioprio_valid(bprio))
-		bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
-
 	return min(aprio, bprio);
 }
 
@@ -200,13 +198,14 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
 			else
 				p = find_task_by_vpid(who);
 			if (p)
-				ret = get_task_ioprio(p);
+				ret = get_task_raw_ioprio(p);
 			break;
 		case IOPRIO_WHO_PGRP:
 			if (!who)
 				pgrp = task_pgrp(current);
 			else
 				pgrp = find_vpid(who);
+			read_lock(&tasklist_lock);
 			do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
 				tmpio = get_task_ioprio(p);
 				if (tmpio < 0)
@@ -216,6 +215,8 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
 				else
 					ret = ioprio_best(ret, tmpio);
 			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+			read_unlock(&tasklist_lock);
+
 			break;
 		case IOPRIO_WHO_USER:
 			uid = make_kuid(current_user_ns(), who);