[PATCH v4 2/6] cgroup/cpuset: Properly handle partition root tree

[Waiman Long]

For cpuset partition, the special state of PRS_ERROR (invalid partition
root) was originally designed to handle hotplug events.  In this state,
CPUs allocated to the partition root is released back to the parent
but the cpuset exclusive flags remain unchanged.

Since partition root sets the CPU_EXCLUSIVE flag, cpuset.cpus changes
that break the cpu exclusivity rule will not be allowed. However,
other changes to cpuset.cpus on a partition root may still cause it to
become invalid. So users must always check the partition root state of
"cpuset.cpus.partition" after making changes to cpuset.cpus to make sure
that the partition root is still valid.

For a partition root tree with parent and child partition roots, this
patch will now prohibit changing parent partition root back to member
as changes to "cpuset.cpus.partition" should not cause those child
partition roots to become invalid.

If some cpus are taken away from the parent partition root so that its
cpuset.cpus.effective becomes empty, it will pull cpus away from the
child partition roots and force them to become invalid which may allow
the parent partition root to remain valid.

This patch also makes partition root invalid in case changes to
"cpuset.cpus" violates any of the partition root constraints.

Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
 kernel/cgroup/cpuset.c | 141 +++++++++++++++++++++++------------------
 1 file changed, 78 insertions(+), 63 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index fcc11f2d3b5b..04db3c84c24b 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1208,6 +1208,14 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 		/*
 		 * partcmd_update with newmask:
 		 *
+		 * Make partition invalid if newmask isn't a subset of
+		 * (cpus_allowed | parent->effective_cpus).
+		 */
+		cpumask_or(tmp->addmask, cpuset->cpus_allowed,
+					 parent->effective_cpus);
+		part_error = !cpumask_subset(newmask, tmp->addmask);
+
+		/*
 		 * delmask = cpus_allowed & ~newmask & parent->subparts_cpus
 		 * addmask = newmask & parent->effective_cpus
 		 *		     & ~parent->subparts_cpus
@@ -1220,7 +1228,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 		adding = cpumask_andnot(tmp->addmask, tmp->addmask,
 					parent->subparts_cpus);
 		/*
-		 * Return error if the new effective_cpus could become empty.
+		 * Return error if parent's effective_cpus could become empty.
 		 */
 		if (adding &&
 		    cpumask_equal(parent->effective_cpus, tmp->addmask)) {
@@ -1242,19 +1250,23 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 		 *
 		 * addmask = cpus_allowed & parent->effective_cpus
 		 *
+		 * This gets invoked either due to a hotplug event or
+		 * from update_cpumasks_hier() where we can't return an
+		 * error. This can cause a partition root to become invalid
+		 * in the case of a hotplug.
+		 *
 		 * Note that parent's subparts_cpus may have been
 		 * pre-shrunk in case there is a change in the cpu list.
 		 * So no deletion is needed.
 		 */
 		adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed,
 				     parent->effective_cpus);
-		part_error = cpumask_equal(tmp->addmask,
-					   parent->effective_cpus);
+		part_error = (is_partition_root(cpuset) &&
+			      !parent->nr_subparts_cpus) ||
+			     cpumask_equal(tmp->addmask, parent->effective_cpus);
 	}
 
 	if (cmd == partcmd_update) {
-		int prev_prs = cpuset->partition_root_state;
-
 		/*
 		 * Check for possible transition between PRS_ENABLED
 		 * and PRS_ERROR.
@@ -1269,13 +1281,9 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 				new_prs = PRS_ENABLED;
 			break;
 		}
-		/*
-		 * Set part_error if previously in invalid state.
-		 */
-		part_error = (prev_prs == PRS_ERROR);
 	}
 
-	if (!part_error && (new_prs == PRS_ERROR))
+	if ((old_prs == PRS_ERROR) && (new_prs == PRS_ERROR))
 		return 0;	/* Nothing need to be done */
 
 	if (new_prs == PRS_ERROR) {
@@ -1407,6 +1415,11 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
 			case PRS_ENABLED:
 				if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp))
 					update_tasks_cpumask(parent);
+				/*
+				 * The cpuset partition_root_state may be
+				 * changed to PRS_ERROR. Capture it.
+				 */
+				new_prs = cp->partition_root_state;
 				break;
 
 			case PRS_ERROR:
@@ -1424,33 +1437,27 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
 
 		spin_lock_irq(&callback_lock);
 
-		cpumask_copy(cp->effective_cpus, tmp->new_cpus);
 		if (cp->nr_subparts_cpus && (new_prs != PRS_ENABLED)) {
+			/*
+			 * Put all active subparts_cpus back to effective_cpus.
+			 */
+			cpumask_or(tmp->new_cpus, tmp->new_cpus,
+				   cp->subparts_cpus);
+			cpumask_and(tmp->new_cpus, tmp->new_cpus,
+				    cpu_active_mask);
 			cp->nr_subparts_cpus = 0;
 			cpumask_clear(cp->subparts_cpus);
-		} else if (cp->nr_subparts_cpus) {
+		}
+
+		cpumask_copy(cp->effective_cpus, tmp->new_cpus);
+		if (cp->nr_subparts_cpus) {
 			/*
 			 * Make sure that effective_cpus & subparts_cpus
-			 * are mutually exclusive.
-			 *
-			 * In the unlikely event that effective_cpus
-			 * becomes empty. we clear cp->nr_subparts_cpus and
-			 * let its child partition roots to compete for
-			 * CPUs again.
+			 * of a partition root are mutually exclusive.
 			 */
 			cpumask_andnot(cp->effective_cpus, cp->effective_cpus,
 				       cp->subparts_cpus);
-			if (cpumask_empty(cp->effective_cpus)) {
-				cpumask_copy(cp->effective_cpus, tmp->new_cpus);
-				cpumask_clear(cp->subparts_cpus);
-				cp->nr_subparts_cpus = 0;
-			} else if (!cpumask_subset(cp->subparts_cpus,
-						   tmp->new_cpus)) {
-				cpumask_andnot(cp->subparts_cpus,
-					cp->subparts_cpus, tmp->new_cpus);
-				cp->nr_subparts_cpus
-					= cpumask_weight(cp->subparts_cpus);
-			}
+			WARN_ON_ONCE(cpumask_empty(cp->effective_cpus));
 		}
 
 		if (new_prs != old_prs)
@@ -1582,8 +1589,8 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	 * Make sure that subparts_cpus is a subset of cpus_allowed.
 	 */
 	if (cs->nr_subparts_cpus) {
-		cpumask_andnot(cs->subparts_cpus, cs->subparts_cpus,
-			       cs->cpus_allowed);
+		cpumask_and(cs->subparts_cpus, cs->subparts_cpus,
+			    cs->cpus_allowed);
 		cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus);
 	}
 	spin_unlock_irq(&callback_lock);
@@ -2005,20 +2012,26 @@ static int update_prstate(struct cpuset *cs, int new_prs)
 		}
 	} else {
 		/*
-		 * Turning off partition root will clear the
-		 * CS_CPU_EXCLUSIVE bit.
+		 * Switch back to member is always allowed if PRS_ERROR.
 		 */
 		if (old_prs == PRS_ERROR) {
-			update_flag(CS_CPU_EXCLUSIVE, cs, 0);
 			err = 0;
-			goto out;
+			goto reset_flag;
 		}
 
+		/*
+		 * A partition root cannot be reverted to member if some
+		 * CPUs have been distributed to child partition roots.
+		 */
+		if (!cpumask_empty(cs->subparts_cpus))
+			return -EBUSY;
+
 		err = update_parent_subparts_cpumask(cs, partcmd_disable,
 						     NULL, &tmpmask);
 		if (err)
 			goto out;
 
+reset_flag:
 		/* Turning off CS_CPU_EXCLUSIVE will not return error */
 		update_flag(CS_CPU_EXCLUSIVE, cs, 0);
 	}
@@ -3100,11 +3113,28 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 
 	/*
 	 * In the unlikely event that a partition root has empty
-	 * effective_cpus or its parent becomes erroneous, we have to
-	 * transition it to the erroneous state.
+	 * effective_cpus, we will have to force any child partitions,
+	 * if present, to become invalid by setting nr_subparts_cpus to 0
+	 * without causing itself to become invalid.
+	 */
+	if (is_partition_root(cs) && cs->nr_subparts_cpus &&
+	    cpumask_empty(&new_cpus)) {
+		cs->nr_subparts_cpus = 0;
+		cpumask_clear(cs->subparts_cpus);
+		compute_effective_cpumask(&new_cpus, cs, parent);
+	}
+
+	/*
+	 * If empty effective_cpus or zero nr_subparts_cpus or its parent
+	 * becomes erroneous, we have to transition it to the erroneous state.
 	 */
 	if (is_partition_root(cs) && (cpumask_empty(&new_cpus) ||
-	   (parent->partition_root_state == PRS_ERROR))) {
+	    (parent->partition_root_state == PRS_ERROR) ||
+	    !parent->nr_subparts_cpus)) {
+		int old_prs;
+
+		update_parent_subparts_cpumask(cs, partcmd_disable,
+					       NULL, tmp);
 		if (cs->nr_subparts_cpus) {
 			spin_lock_irq(&callback_lock);
 			cs->nr_subparts_cpus = 0;
@@ -3113,38 +3143,23 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 			compute_effective_cpumask(&new_cpus, cs, parent);
 		}
 
-		/*
-		 * If the effective_cpus is empty because the child
-		 * partitions take away all the CPUs, we can keep
-		 * the current partition and let the child partitions
-		 * fight for available CPUs.
-		 */
-		if ((parent->partition_root_state == PRS_ERROR) ||
-		     cpumask_empty(&new_cpus)) {
-			int old_prs;
-
-			update_parent_subparts_cpumask(cs, partcmd_disable,
-						       NULL, tmp);
-			old_prs = cs->partition_root_state;
-			if (old_prs != PRS_ERROR) {
-				spin_lock_irq(&callback_lock);
-				cs->partition_root_state = PRS_ERROR;
-				spin_unlock_irq(&callback_lock);
-				notify_partition_change(cs, old_prs, PRS_ERROR);
-			}
+		old_prs = cs->partition_root_state;
+		if (old_prs != PRS_ERROR) {
+			spin_lock_irq(&callback_lock);
+			cs->partition_root_state = PRS_ERROR;
+			spin_unlock_irq(&callback_lock);
+			notify_partition_change(cs, old_prs, PRS_ERROR);
 		}
 		cpuset_force_rebuild();
 	}
 
 	/*
 	 * On the other hand, an erroneous partition root may be transitioned
-	 * back to a regular one or a partition root with no CPU allocated
-	 * from the parent may change to erroneous.
+	 * back to a regular one.
 	 */
-	if (is_partition_root(parent) &&
-	   ((cs->partition_root_state == PRS_ERROR) ||
-	    !cpumask_intersects(&new_cpus, parent->subparts_cpus)) &&
-	     update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp))
+	else if (is_partition_root(parent) &&
+		(cs->partition_root_state == PRS_ERROR) &&
+		 update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp))
 		cpuset_force_rebuild();
 
 update_tasks:
-- 
2.18.1