1 files changed, 92 insertions, 47 deletions

diff --git a/kernel/padata.c b/kernel/padata.c
index d4d3ba6e1728..418987056340 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -9,19 +9,6 @@
  *
  * Copyright (c) 2020 Oracle and/or its affiliates.
  * Author: Daniel Jordan <daniel.m.jordan@oracle.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #include <linux/completion.h>
@@ -60,6 +47,22 @@ struct padata_mt_job_state {
 static void padata_free_pd(struct parallel_data *pd);
 static void __init padata_mt_helper(struct work_struct *work);
 
+static inline void padata_get_pd(struct parallel_data *pd)
+{
+	refcount_inc(&pd->refcnt);
+}
+
+static inline void padata_put_pd_cnt(struct parallel_data *pd, int cnt)
+{
+	if (refcount_sub_and_test(cnt, &pd->refcnt))
+		padata_free_pd(pd);
+}
+
+static inline void padata_put_pd(struct parallel_data *pd)
+{
+	padata_put_pd_cnt(pd, 1);
+}
+
 static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
 {
 	int cpu, target_cpu;
@@ -96,8 +99,16 @@ static struct padata_work *padata_work_alloc(void)
 	return pw;
 }
 
-static void padata_work_init(struct padata_work *pw, work_func_t work_fn,
-			     void *data, int flags)
+/*
+ * This function is marked __ref because this function may be optimized in such
+ * a way that it directly refers to work_fn's address, which causes modpost to
+ * complain when work_fn is marked __init. This scenario was observed with clang
+ * LTO, where padata_work_init() was optimized to refer directly to
+ * padata_mt_helper() because the calls to padata_work_init() with other work_fn
+ * values were eliminated or inlined.
+ */
+static void __ref padata_work_init(struct padata_work *pw, work_func_t work_fn,
+				   void *data, int flags)
 {
 	if (flags & PADATA_WORK_ONSTACK)
 		INIT_WORK_ONSTACK(&pw->pw_work, work_fn);
@@ -111,7 +122,7 @@ static int __init padata_work_alloc_mt(int nworks, void *data,
 {
 	int i;
 
-	spin_lock(&padata_works_lock);
+	spin_lock_bh(&padata_works_lock);
 	/* Start at 1 because the current task participates in the job. */
 	for (i = 1; i < nworks; ++i) {
 		struct padata_work *pw = padata_work_alloc();
@@ -121,7 +132,7 @@ static int __init padata_work_alloc_mt(int nworks, void *data,
 		padata_work_init(pw, padata_mt_helper, data, 0);
 		list_add(&pw->pw_list, head);
 	}
-	spin_unlock(&padata_works_lock);
+	spin_unlock_bh(&padata_works_lock);
 
 	return i;
 }
@@ -139,12 +150,12 @@ static void __init padata_works_free(struct list_head *works)
 	if (list_empty(works))
 		return;
 
-	spin_lock(&padata_works_lock);
+	spin_lock_bh(&padata_works_lock);
 	list_for_each_entry_safe(cur, next, works, pw_list) {
 		list_del(&cur->pw_list);
 		padata_work_free(cur);
 	}
-	spin_unlock(&padata_works_lock);
+	spin_unlock_bh(&padata_works_lock);
 }
 
 static void padata_parallel_worker(struct work_struct *parallel_work)
@@ -194,7 +205,7 @@ int padata_do_parallel(struct padata_shell *ps,
 		goto out;
 
 	if (!cpumask_test_cpu(*cb_cpu, pd->cpumask.cbcpu)) {
-		if (!cpumask_weight(pd->cpumask.cbcpu))
+		if (cpumask_empty(pd->cpumask.cbcpu))
 			goto out;
 
 		/* Select an alternate fallback CPU and notify the caller. */
@@ -207,11 +218,11 @@ int padata_do_parallel(struct padata_shell *ps,
 		*cb_cpu = cpu;
 	}
 
-	err =  -EBUSY;
+	err = -EBUSY;
 	if ((pinst->flags & PADATA_RESET))
 		goto out;
 
-	atomic_inc(&pd->refcnt);
+	padata_get_pd(pd);
 	padata->pd = pd;
 	padata->cb_cpu = *cb_cpu;
 
@@ -220,14 +231,16 @@ int padata_do_parallel(struct padata_shell *ps,
 	pw = padata_work_alloc();
 	spin_unlock(&padata_works_lock);
 
+	if (!pw) {
+		/* Maximum works limit exceeded, run in the current task. */
+		padata->parallel(padata);
+	}
+
 	rcu_read_unlock_bh();
 
 	if (pw) {
 		padata_work_init(pw, padata_parallel_worker, padata, 0);
 		queue_work(pinst->parallel_wq, &pw->pw_work);
-	} else {
-		/* Maximum works limit exceeded, run in the current task. */
-		padata->parallel(padata);
 	}
 
 	return 0;
@@ -339,8 +352,14 @@ static void padata_reorder(struct parallel_data *pd)
 	smp_mb();
 
 	reorder = per_cpu_ptr(pd->reorder_list, pd->cpu);
-	if (!list_empty(&reorder->list) && padata_find_next(pd, false))
+	if (!list_empty(&reorder->list) && padata_find_next(pd, false)) {
+		/*
+		 * Other context(eg. the padata_serial_worker) can finish the request.
+		 * To avoid UAF issue, add pd ref here, and put pd ref after reorder_work finish.
+		 */
+		padata_get_pd(pd);
 		queue_work(pinst->serial_wq, &pd->reorder_work);
+	}
 }
 
 static void invoke_padata_reorder(struct work_struct *work)
@@ -351,6 +370,8 @@ static void invoke_padata_reorder(struct work_struct *work)
 	pd = container_of(work, struct parallel_data, reorder_work);
 	padata_reorder(pd);
 	local_bh_enable();
+	/* Pairs with putting the reorder_work in the serial_wq */
+	padata_put_pd(pd);
 }
 
 static void padata_serial_worker(struct work_struct *serial_work)
@@ -383,8 +404,7 @@ static void padata_serial_worker(struct work_struct *serial_work)
 	}
 	local_bh_enable();
 
-	if (atomic_sub_and_test(cnt, &pd->refcnt))
-		padata_free_pd(pd);
+	padata_put_pd_cnt(pd, cnt);
 }
 
 /**
@@ -401,13 +421,17 @@ void padata_do_serial(struct padata_priv *padata)
 	int hashed_cpu = padata_cpu_hash(pd, padata->seq_nr);
 	struct padata_list *reorder = per_cpu_ptr(pd->reorder_list, hashed_cpu);
 	struct padata_priv *cur;
+	struct list_head *pos;
 
 	spin_lock(&reorder->lock);
 	/* Sort in ascending order of sequence number. */
-	list_for_each_entry_reverse(cur, &reorder->list, list)
-		if (cur->seq_nr < padata->seq_nr)
+	list_for_each_prev(pos, &reorder->list) {
+		cur = list_entry(pos, struct padata_priv, list);
+		/* Compare by difference to consider integer wrap around */
+		if ((signed int)(cur->seq_nr - padata->seq_nr) < 0)
 			break;
-	list_add(&padata->list, &cur->list);
+	}
+	list_add(&padata->list, pos);
 	spin_unlock(&reorder->lock);
 
 	/*
@@ -485,13 +509,14 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
 	struct padata_work my_work, *pw;
 	struct padata_mt_job_state ps;
 	LIST_HEAD(works);
-	int nworks;
+	int nworks, nid;
+	static atomic_t last_used_nid __initdata;
 
 	if (job->size == 0)
 		return;
 
 	/* Ensure at least one thread when size < min_chunk. */
-	nworks = max(job->size / job->min_chunk, 1ul);
+	nworks = max(job->size / max(job->min_chunk, job->align), 1ul);
 	nworks = min(nworks, job->max_threads);
 
 	if (nworks == 1) {
@@ -511,13 +536,25 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
 	 * thread function.  Load balance large jobs between threads by
 	 * increasing the number of chunks, guarantee at least the minimum
 	 * chunk size from the caller, and honor the caller's alignment.
+	 * Ensure chunk_size is at least 1 to prevent divide-by-0
+	 * panic in padata_mt_helper().
 	 */
 	ps.chunk_size = job->size / (ps.nworks * load_balance_factor);
 	ps.chunk_size = max(ps.chunk_size, job->min_chunk);
+	ps.chunk_size = max(ps.chunk_size, 1ul);
 	ps.chunk_size = roundup(ps.chunk_size, job->align);
 
 	list_for_each_entry(pw, &works, pw_list)
-		queue_work(system_unbound_wq, &pw->pw_work);
+		if (job->numa_aware) {
+			int old_node = atomic_read(&last_used_nid);
+
+			do {
+				nid = next_node_in(old_node, node_states[N_CPU]);
+			} while (!atomic_try_cmpxchg(&last_used_nid, &old_node, nid));
+			queue_work_node(nid, system_unbound_wq, &pw->pw_work);
+		} else {
+			queue_work(system_unbound_wq, &pw->pw_work);
+		}
 
 	/* Use the current thread, which saves starting a workqueue worker. */
 	padata_work_init(&my_work, padata_mt_helper, &ps, PADATA_WORK_ONSTACK);
@@ -593,7 +630,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_shell *ps)
 	padata_init_reorder_list(pd);
 	padata_init_squeues(pd);
 	pd->seq_nr = -1;
-	atomic_set(&pd->refcnt, 1);
+	refcount_set(&pd->refcnt, 1);
 	spin_lock_init(&pd->lock);
 	pd->cpu = cpumask_first(pd->cpumask.pcpu);
 	INIT_WORK(&pd->reorder_work, invoke_padata_reorder);
@@ -667,8 +704,7 @@ static int padata_replace(struct padata_instance *pinst)
 	synchronize_rcu();
 
 	list_for_each_entry_continue_reverse(ps, &pinst->pslist, list)
-		if (atomic_dec_and_test(&ps->opd->refcnt))
-			padata_free_pd(ps->opd);
+		padata_put_pd(ps->opd);
 
 	pinst->flags &= ~PADATA_RESET;
 
@@ -733,7 +769,7 @@ int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
 	struct cpumask *serial_mask, *parallel_mask;
 	int err = -EINVAL;
 
-	get_online_cpus();
+	cpus_read_lock();
 	mutex_lock(&pinst->lock);
 
 	switch (cpumask_type) {
@@ -753,7 +789,7 @@ int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
 
 out:
 	mutex_unlock(&pinst->lock);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return err;
 }
@@ -956,7 +992,7 @@ static ssize_t padata_sysfs_store(struct kobject *kobj, struct attribute *attr,
 
 	pinst = kobj2pinst(kobj);
 	pentry = attr2pentry(attr);
-	if (pentry->show)
+	if (pentry->store)
 		ret = pentry->store(pinst, attr, buf, count);
 
 	return ret;
@@ -967,7 +1003,7 @@ static const struct sysfs_ops padata_sysfs_ops = {
 	.store = padata_sysfs_store,
 };
 
-static struct kobj_type padata_attr_type = {
+static const struct kobj_type padata_attr_type = {
 	.sysfs_ops = &padata_sysfs_ops,
 	.default_groups = padata_default_groups,
 	.release = padata_sysfs_release,
@@ -992,7 +1028,7 @@ struct padata_instance *padata_alloc(const char *name)
 	if (!pinst->parallel_wq)
 		goto err_free_inst;
 
-	get_online_cpus();
+	cpus_read_lock();
 
 	pinst->serial_wq = alloc_workqueue("%s_serial", WQ_MEM_RECLAIM |
 					   WQ_CPU_INTENSIVE, 1, name);
@@ -1026,7 +1062,7 @@ struct padata_instance *padata_alloc(const char *name)
 						    &pinst->cpu_dead_node);
 #endif
 
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return pinst;
 
@@ -1036,7 +1072,7 @@ err_free_masks:
 err_free_serial_wq:
 	destroy_workqueue(pinst->serial_wq);
 err_put_cpus:
-	put_online_cpus();
+	cpus_read_unlock();
 	destroy_workqueue(pinst->parallel_wq);
 err_free_inst:
 	kfree(pinst);
@@ -1074,9 +1110,9 @@ struct padata_shell *padata_alloc_shell(struct padata_instance *pinst)
 
 	ps->pinst = pinst;
 
-	get_online_cpus();
+	cpus_read_lock();
 	pd = padata_alloc_pd(ps);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	if (!pd)
 		goto out_free_ps;
@@ -1102,12 +1138,21 @@ EXPORT_SYMBOL(padata_alloc_shell);
  */
 void padata_free_shell(struct padata_shell *ps)
 {
+	struct parallel_data *pd;
+
 	if (!ps)
 		return;
 
+	/*
+	 * Wait for all _do_serial calls to finish to avoid touching
+	 * freed pd's and ps's.
+	 */
+	synchronize_rcu();
+
 	mutex_lock(&ps->pinst->lock);
 	list_del(&ps->list);
-	padata_free_pd(rcu_dereference_protected(ps->pd, 1));
+	pd = rcu_dereference_protected(ps->pd, 1);
+	padata_put_pd(pd);
 	mutex_unlock(&ps->pinst->lock);
 
 	kfree(ps);