Merge tag 'cgroup-for-7.1-rc1-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:

 - Fix UAF race in psi pressure_write() against cgroup file release by
   extending cgroup_mutex coverage and ordering of->priv access after
   cgroup_kn_lock_live()

 - Fix integer overflow in rdmacg_try_charge() when usage equals INT_MAX
   by performing the increment in s64

 - Fix asymmetric DL bandwidth accounting on cpuset attach rollback by
   recording the CPU used by dl_bw_alloc() so cancel_attach() returns
   the reservation to the same root domain

 - Fix nr_dying_subsys_* race that briefly showed 0 in cgroup.stat after
   rmdir by incrementing from kill_css() instead of offline_css()

 - Typo fix in cgroup-v2 documentation

* tag 'cgroup-for-7.1-rc1-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  docs: cgroup: fix typo 'protetion' -> 'protection'
  cgroup: Increment nr_dying_subsys_* from rmdir context
  cgroup/cpuset: record DL BW alloc CPU for attach rollback
  cgroup/rdma: fix integer overflow in rdmacg_try_charge()
  sched/psi: fix race between file release and pressure write

Author: torvalds

Documentation/admin-guide/cgroup-v2.rst

@@ -220,7 +220,7 @@ cgroup v2 currently supports the following mount options.
   memory_hugetlb_accounting
         Count HugeTLB memory usage towards the cgroup's overall
         memory usage for the memory controller (for the purpose of
-        statistics reporting and memory protetion). This is a new
+        statistics reporting and memory protection). This is a new
         behavior that could regress existing setups, so it must be
         explicitly opted in with this mount option.
 

kernel/cgroup/cgroup.c

@@ -3934,33 +3934,41 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v)
 static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
 			      size_t nbytes, enum psi_res res)
 {
-	struct cgroup_file_ctx *ctx = of->priv;
+	struct cgroup_file_ctx *ctx;
 	struct psi_trigger *new;
 	struct cgroup *cgrp;
 	struct psi_group *psi;
+	ssize_t ret = 0;
 
 	cgrp = cgroup_kn_lock_live(of->kn, false);
 	if (!cgrp)
 		return -ENODEV;
 
-	cgroup_get(cgrp);
-	cgroup_kn_unlock(of->kn);
+	ctx = of->priv;
+	if (!ctx) {
+		ret = -ENODEV;
+		goto out_unlock;
+	}
 
 	/* Allow only one trigger per file descriptor */
 	if (ctx->psi.trigger) {
-		cgroup_put(cgrp);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto out_unlock;
 	}
 
 	psi = cgroup_psi(cgrp);
 	new = psi_trigger_create(psi, buf, res, of->file, of);
 	if (IS_ERR(new)) {
-		cgroup_put(cgrp);
-		return PTR_ERR(new);
+		ret = PTR_ERR(new);
+		goto out_unlock;
 	}
 
 	smp_store_release(&ctx->psi.trigger, new);
-	cgroup_put(cgrp);
+
+out_unlock:
+	cgroup_kn_unlock(of->kn);
+	if (ret)
+		return ret;
 
 	return nbytes;
 }
@@ -5716,16 +5724,6 @@ static void offline_css(struct cgroup_subsys_state *css)
 	RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL);
 
 	wake_up_all(&css->cgroup->offline_waitq);
-
-	css->cgroup->nr_dying_subsys[ss->id]++;
-	/*
-	 * Parent css and cgroup cannot be freed until after the freeing
-	 * of child css, see css_free_rwork_fn().
-	 */
-	while ((css = css->parent)) {
-		css->nr_descendants--;
-		css->cgroup->nr_dying_subsys[ss->id]++;
-	}
 }
 
 /**
@@ -6038,6 +6036,8 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
  */
 static void kill_css(struct cgroup_subsys_state *css)
 {
+	struct cgroup_subsys *ss = css->ss;
+
 	lockdep_assert_held(&cgroup_mutex);
 
 	if (css->flags & CSS_DYING)
@@ -6074,6 +6074,16 @@ static void kill_css(struct cgroup_subsys_state *css)
 	 * css is confirmed to be seen as killed on all CPUs.
 	 */
 	percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn);
+
+	css->cgroup->nr_dying_subsys[ss->id]++;
+	/*
+	 * Parent css and cgroup cannot be freed until after the freeing
+	 * of child css, see css_free_rwork_fn().
+	 */
+	while ((css = css->parent)) {
+		css->nr_descendants--;
+		css->cgroup->nr_dying_subsys[ss->id]++;
+	}
 }
 
 /**

kernel/cgroup/cpuset-internal.h

@@ -168,6 +168,11 @@ struct cpuset {
 	int nr_deadline_tasks;
 	int nr_migrate_dl_tasks;
 	u64 sum_migrate_dl_bw;
+	/*
+	 * CPU used for temporary DL bandwidth allocation during attach;
+	 * -1 if no DL bandwidth was allocated in the current attach.
+	 */
+	int dl_bw_cpu;
 
 	/* Invalid partition error code, not lock protected */
 	enum prs_errcode prs_err;

kernel/cgroup/cpuset.c

@@ -288,6 +288,7 @@ struct cpuset top_cpuset = {
 	.flags = BIT(CS_CPU_EXCLUSIVE) |
 		 BIT(CS_MEM_EXCLUSIVE) | BIT(CS_SCHED_LOAD_BALANCE),
 	.partition_root_state = PRS_ROOT,
+	.dl_bw_cpu = -1,
 };
 
 /**
@@ -579,6 +580,8 @@ static struct cpuset *dup_or_alloc_cpuset(struct cpuset *cs)
 	if (!trial)
 		return NULL;
 
+	trial->dl_bw_cpu = -1;
+
 	/* Setup cpumask pointer array */
 	cpumask_var_t *pmask[4] = {
 		&trial->cpus_allowed,
@@ -2980,6 +2983,7 @@ static void reset_migrate_dl_data(struct cpuset *cs)
 {
 	cs->nr_migrate_dl_tasks = 0;
 	cs->sum_migrate_dl_bw = 0;
+	cs->dl_bw_cpu = -1;
 }
 
 /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
@@ -3056,6 +3060,8 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 			reset_migrate_dl_data(cs);
 			goto out_unlock;
 		}
+
+		cs->dl_bw_cpu = cpu;
 	}
 
 out_success:
@@ -3080,12 +3086,11 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset)
 	mutex_lock(&cpuset_mutex);
 	dec_attach_in_progress_locked(cs);
 
-	if (cs->nr_migrate_dl_tasks) {
-		int cpu = cpumask_any(cs->effective_cpus);
+	if (cs->dl_bw_cpu >= 0)
+		dl_bw_free(cs->dl_bw_cpu, cs->sum_migrate_dl_bw);
 
-		dl_bw_free(cpu, cs->sum_migrate_dl_bw);
+	if (cs->nr_migrate_dl_tasks)
 		reset_migrate_dl_data(cs);
-	}
 
 	mutex_unlock(&cpuset_mutex);
 }

kernel/cgroup/rdma.c

@@ -283,7 +283,7 @@ int rdmacg_try_charge(struct rdma_cgroup **rdmacg,
 			ret = PTR_ERR(rpool);
 			goto err;
 		} else {
-			new = rpool->resources[index].usage + 1;
+			new = (s64)rpool->resources[index].usage + 1;
 			if (new > rpool->resources[index].max) {
 				ret = -EAGAIN;
 				goto err;