x86/intel_rdt: Prevent pseudo-locking from using stale pointers

When the last CPU in an rdt_domain goes offline, its rdt_domain struct gets
freed. Current pseudo-locking code is unaware of this scenario and tries to
dereference the freed structure in a few places.

Add checks to prevent pseudo-locking code from doing this.

While further work is needed to seamlessly restore resource groups (not
just pseudo-locking) to their configuration when the domain is brought back
online, the immediate issue of invalid pointers is addressed here.

Fixes: f4e80d67a5 ("x86/intel_rdt: Resctrl files reflect pseudo-locked information")
Fixes: 443810fe61 ("x86/intel_rdt: Create debugfs files for pseudo-locking testing")
Fixes: 746e08590b ("x86/intel_rdt: Create character device exposing pseudo-locked region")
Fixes: 33dc3e410a ("x86/intel_rdt: Make CPU information accessible for pseudo-locked regions")
Signed-off-by: Jithu Joseph <jithu.joseph@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: gavin.hindman@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/231f742dbb7b00a31cc104416860e27dba6b072d.1539384145.git.reinette.chatre@intel.com

arch/x86/kernel/cpu/intel_rdt.c

@@ -608,6 +608,13 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 			cancel_delayed_work(&d->cqm_limbo);
 		}
 
+		/*
+		 * rdt_domain "d" is going to be freed below, so clear
+		 * its pointer from pseudo_lock_region struct.
+		 */
+		if (d->plr)
+			d->plr->d = NULL;
+
 		kfree(d->ctrl_val);
 		kfree(d->mbps_val);
 		bitmap_free(d->rmid_busy_llc);

arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c

@@ -404,8 +404,16 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			for_each_alloc_enabled_rdt_resource(r)
 				seq_printf(s, "%s:uninitialized\n", r->name);
 		} else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-			seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name,
+			if (!rdtgrp->plr->d) {
-				   rdtgrp->plr->d->id, rdtgrp->plr->cbm);
+				rdt_last_cmd_clear();
+				rdt_last_cmd_puts("Cache domain offline\n");
+				ret = -ENODEV;
+			} else {
+				seq_printf(s, "%s:%d=%x\n",
+					   rdtgrp->plr->r->name,
+					   rdtgrp->plr->d->id,
+					   rdtgrp->plr->cbm);
+			}
 		} else {
 			closid = rdtgrp->closid;
 			for_each_alloc_enabled_rdt_resource(r) {

arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c

@@ -1174,6 +1174,11 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 		goto out;
 	}
 
+	if (!plr->d) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	plr->thread_done = 0;
 	cpu = cpumask_first(&plr->d->cpu_mask);
 	if (!cpu_online(cpu)) {
@@ -1494,6 +1499,11 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
 
 	plr = rdtgrp->plr;
 
+	if (!plr->d) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+
 	/*
 	 * Task is required to run with affinity to the cpus associated
 	 * with the pseudo-locked region. If this is not the case the task

arch/x86/kernel/cpu/intel_rdt_rdtgroup.c

@@ -268,17 +268,27 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 			      struct seq_file *s, void *v)
 {
 	struct rdtgroup *rdtgrp;
+	struct cpumask *mask;
 	int ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 
 	if (rdtgrp) {
-		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
+			if (!rdtgrp->plr->d) {
-				   cpumask_pr_args(&rdtgrp->plr->d->cpu_mask));
+				rdt_last_cmd_clear();
-		else
+				rdt_last_cmd_puts("Cache domain offline\n");
+				ret = -ENODEV;
+			} else {
+				mask = &rdtgrp->plr->d->cpu_mask;
+				seq_printf(s, is_cpu_list(of) ?
+					   "%*pbl\n" : "%*pb\n",
+					   cpumask_pr_args(mask));
+			}
+		} else {
 			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
 				   cpumask_pr_args(&rdtgrp->cpu_mask));
+		}
 	} else {
 		ret = -ENOENT;
 	}
@@ -1282,6 +1292,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 	struct rdt_resource *r;
 	struct rdt_domain *d;
 	unsigned int size;
+	int ret = 0;
 	bool sep;
 	u32 ctrl;
 
@@ -1292,11 +1303,18 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 	}
 
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
-		seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name);
+		if (!rdtgrp->plr->d) {
-		size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
+			rdt_last_cmd_clear();
-					    rdtgrp->plr->d,
+			rdt_last_cmd_puts("Cache domain offline\n");
-					    rdtgrp->plr->cbm);
+			ret = -ENODEV;
-		seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+		} else {
+			seq_printf(s, "%*s:", max_name_width,
+				   rdtgrp->plr->r->name);
+			size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
+						    rdtgrp->plr->d,
+						    rdtgrp->plr->cbm);
+			seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+		}
 		goto out;
 	}
 
@@ -1326,7 +1344,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 out:
 	rdtgroup_kn_unlock(of->kn);
 
-	return 0;
+	return ret;
 }
 
 /* rdtgroup information files for one cache resource. */