cgroup: Merge branch 'for-7.3-fixes' into for-7.4

Pull to receive 1765a153d9 ("cgroup/pids: Restore pids.events
notifications in local mode") for the pids.events notification
selftest.

Signed-off-by: Tejun Heo <tj@kernel.org>

kernel/cgroup/cgroup.c

@@ -5317,10 +5317,13 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 	if (it->flags & CSS_TASK_ITER_SKIPPED)
 		css_task_iter_advance(it);
 
-	if (it->task_pos) {
+	while (it->task_pos && !it->cur_task) {
 		it->cur_task = list_entry(it->task_pos, struct task_struct,
 					  cg_list);
-		get_task_struct(it->cur_task);
+		/* a task on dying_tasks with zero refcount is only valid for
+		 * RCU readers, not even interesting for
+		 * CSS_TASK_ITER_WITH_DEAD, find another one */
+		it->cur_task = tryget_task_struct(it->cur_task);
 		css_task_iter_advance(it);
 	}
 

kernel/cgroup/cpuset.c

@@ -152,6 +152,12 @@ static cpumask_var_t	isolated_cpus;		/* CSCB */
  */
 static bool		update_housekeeping;	/* RWCS */
 
+/*
+ * Set if "cpuset_v2_mode" mount option is used
+ * Cached at bind time and not lock protected; accessed via {READ,WRITE}_ONCE
+ */
+static bool		cpuset_v2_mode;
+
 /*
  * Copy of isolated_cpus to be passed to housekeeping_update()
  */
@@ -438,8 +444,7 @@ static inline bool cpuset_v2(void)
  */
 static inline bool is_in_v2_mode(void)
 {
-	return cpuset_v2() ||
-	      (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE);
+	return cpuset_v2() || READ_ONCE(cpuset_v2_mode);
 }
 
 /**
@@ -512,10 +517,26 @@ static void guarantee_active_cpus(struct task_struct *tsk,
 	rcu_read_lock();
 	cs = task_cs(tsk);
 
-	while (!cpumask_intersects(cs->effective_cpus, pmask))
+	while (!cpumask_intersects(cs->effective_cpus, pmask)) {
 		cs = parent_cs(cs);
-
+		if (unlikely(!cs)) {
+			/*
+			 * The top cpuset doesn't have any active cpu as a
+			 * consequence of a race between its caller and the cpu
+			 * hotplug operation where cpu_active_mask is updated
+			 * asynchronously before cpuset_handle_hotplug() is
+			 * being called to adjust the effective_cpus of the
+			 * affected cpusets. But we know the top cpuset's
+			 * effective_cpus is on its way to be identical to
+			 * cpu_active_mask minus the exclusive CPUs dedicated
+			 * to other valid cpuset partitions. Just pass back
+			 * the filtered cpu_active_mask in this case.
+			 */
+			goto out_unlock;
+		}
+	}
 	cpumask_and(pmask, pmask, cs->effective_cpus);
+out_unlock:
 	rcu_read_unlock();
 }
 
@@ -1567,10 +1588,11 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs,
 	 * above it or remote partition root underneath it is not allowed.
 	 */
 	compute_excpus(cs, tmp->new_cpus);
-	WARN_ON_ONCE(cpumask_intersects(tmp->new_cpus, subpartitions_cpus));
 	if (!cpumask_intersects(tmp->new_cpus, cpu_active_mask) ||
 	    cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus))
 		return PERR_INVCPUS;
+	if (cpumask_intersects(tmp->new_cpus, subpartitions_cpus))
+		return PERR_NOCPUS;
 	if (((new_prs == PRS_ISOLATED) &&
 	     !isolated_cpus_can_update(tmp->new_cpus, NULL)) ||
 	    prstate_housekeeping_conflict(new_prs, tmp->new_cpus))
@@ -3618,6 +3640,8 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
 	mutex_lock(&cpuset_mutex);
 	spin_lock_irq(&callback_lock);
 
+	WRITE_ONCE(cpuset_v2_mode,
+		   !!(cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE));
 	if (is_in_v2_mode()) {
 		cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
 		cpumask_copy(top_cpuset.effective_xcpus, cpu_possible_mask);
@@ -3930,15 +3954,16 @@ static void cpuset_handle_hotplug(void)
 	static cpumask_t new_cpus;
 	static nodemask_t new_mems;
 	bool cpus_updated, mems_updated;
-	bool on_dfl = is_in_v2_mode();
+	bool on_dfl;
 	struct tmpmasks tmp, *ptmp = NULL;
 
-	if (on_dfl && !alloc_tmpmasks(&tmp))
-		ptmp = &tmp;
-
 	lockdep_assert_cpus_held();
 	mutex_lock(&cpuset_mutex);
 
+	on_dfl = is_in_v2_mode();
+	if (on_dfl && !alloc_tmpmasks(&tmp))
+		ptmp = &tmp;
+
 	/* fetch the available cpus/mems and find out which changed how */
 	cpumask_copy(&new_cpus, cpu_active_mask);
 	new_mems = node_states[N_MEMORY];

kernel/cgroup/pids.c

@@ -253,6 +253,11 @@ static void pids_event(struct pids_cgroup *pids_forking,
 	}
 	if (!cgroup_subsys_on_dfl(pids_cgrp_subsys) ||
 	    cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) {
+		/*
+		 * pids.events reports the local counter on legacy hierarchies
+		 * and when pids_localevents is enabled.
+		 */
+		cgroup_file_notify(&p->events_file);
 		cgroup_file_notify(&p->events_local_file);
 		return;
 	}

tools/testing/selftests/cgroup/test_cpuset_prs.sh

@@ -298,6 +298,8 @@ TEST_MATRIX=(
 	" C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
 				   .      .      .      X1      .    0 A1:0-1|A2:2-4|A3:2-4 \
 								       A1:P0|A2:P2|A3:P-1 2-4"
+	" CX1-3:P1 CX1-3  CX1-3    .      .      .      P1      .    0 A1:1-3|A2:1-3|A3:1-3 \
+								       A1:P1|A2:P0|A3:P-1"
 
 	# Remote partition offline tests
 	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 .   0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"

tools/testing/selftests/cgroup/test_memcontrol.c

@@ -30,7 +30,7 @@ static int page_size;
 
 int get_temp_fd(void)
 {
-	return open(".", O_TMPFILE | O_RDWR | O_EXCL);
+	return open(".", O_TMPFILE | O_RDWR | O_EXCL, 0600);
 }
 
 int alloc_pagecache(int fd, size_t size)