1 files changed, 63 insertions, 112 deletions

diff --git a/kernel/padata.c b/kernel/padata.c
index 0fa6c2895460..f85f8bd788d0 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -47,15 +47,20 @@ 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 int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
+static inline void padata_get_pd(struct parallel_data *pd)
 {
-	int cpu, target_cpu;
+	refcount_inc(&pd->refcnt);
+}
 
-	target_cpu = cpumask_first(pd->cpumask.pcpu);
-	for (cpu = 0; cpu < cpu_index; cpu++)
-		target_cpu = cpumask_next(target_cpu, pd->cpumask.pcpu);
+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);
+}
 
-	return target_cpu;
+static inline void padata_put_pd(struct parallel_data *pd)
+{
+	padata_put_pd_cnt(pd, 1);
 }
 
 static int padata_cpu_hash(struct parallel_data *pd, unsigned int seq_nr)
@@ -66,7 +71,7 @@ static int padata_cpu_hash(struct parallel_data *pd, unsigned int seq_nr)
 	 */
 	int cpu_index = seq_nr % cpumask_weight(pd->cpumask.pcpu);
 
-	return padata_index_to_cpu(pd, cpu_index);
+	return cpumask_nth(cpu_index, pd->cpumask.pcpu);
 }
 
 static struct padata_work *padata_work_alloc(void)
@@ -176,9 +181,9 @@ int padata_do_parallel(struct padata_shell *ps,
 		       struct padata_priv *padata, int *cb_cpu)
 {
 	struct padata_instance *pinst = ps->pinst;
-	int i, cpu, cpu_index, err;
 	struct parallel_data *pd;
 	struct padata_work *pw;
+	int cpu_index, err;
 
 	rcu_read_lock_bh();
 
@@ -194,19 +199,14 @@ int padata_do_parallel(struct padata_shell *ps,
 
 		/* Select an alternate fallback CPU and notify the caller. */
 		cpu_index = *cb_cpu % cpumask_weight(pd->cpumask.cbcpu);
-
-		cpu = cpumask_first(pd->cpumask.cbcpu);
-		for (i = 0; i < cpu_index; i++)
-			cpu = cpumask_next(cpu, pd->cpumask.cbcpu);
-
-		*cb_cpu = cpu;
+		*cb_cpu = cpumask_nth(cpu_index, pd->cpumask.cbcpu);
 	}
 
 	err = -EBUSY;
 	if ((pinst->flags & PADATA_RESET))
 		goto out;
 
-	refcount_inc(&pd->refcnt);
+	padata_get_pd(pd);
 	padata->pd = pd;
 	padata->cb_cpu = *cb_cpu;
 
@@ -245,20 +245,17 @@ EXPORT_SYMBOL(padata_do_parallel);
  *   be parallel processed by another cpu and is not yet present in
  *   the cpu's reorder queue.
  */
-static struct padata_priv *padata_find_next(struct parallel_data *pd,
-					    bool remove_object)
+static struct padata_priv *padata_find_next(struct parallel_data *pd, int cpu,
+					    unsigned int processed)
 {
 	struct padata_priv *padata;
 	struct padata_list *reorder;
-	int cpu = pd->cpu;
 
 	reorder = per_cpu_ptr(pd->reorder_list, cpu);
 
 	spin_lock(&reorder->lock);
-	if (list_empty(&reorder->list)) {
-		spin_unlock(&reorder->lock);
-		return NULL;
-	}
+	if (list_empty(&reorder->list))
+		goto notfound;
 
 	padata = list_entry(reorder->list.next, struct padata_priv, list);
 
@@ -266,88 +263,52 @@ static struct padata_priv *padata_find_next(struct parallel_data *pd,
 	 * Checks the rare case where two or more parallel jobs have hashed to
 	 * the same CPU and one of the later ones finishes first.
 	 */
-	if (padata->seq_nr != pd->processed) {
-		spin_unlock(&reorder->lock);
-		return NULL;
-	}
-
-	if (remove_object) {
-		list_del_init(&padata->list);
-		++pd->processed;
-		pd->cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu, -1, false);
-	}
+	if (padata->seq_nr != processed)
+		goto notfound;
 
+	list_del_init(&padata->list);
 	spin_unlock(&reorder->lock);
 	return padata;
+
+notfound:
+	pd->processed = processed;
+	pd->cpu = cpu;
+	spin_unlock(&reorder->lock);
+	return NULL;
 }
 
-static void padata_reorder(struct parallel_data *pd)
+static void padata_reorder(struct padata_priv *padata)
 {
+	struct parallel_data *pd = padata->pd;
 	struct padata_instance *pinst = pd->ps->pinst;
-	int cb_cpu;
-	struct padata_priv *padata;
-	struct padata_serial_queue *squeue;
-	struct padata_list *reorder;
+	unsigned int processed;
+	int cpu;
 
-	/*
-	 * We need to ensure that only one cpu can work on dequeueing of
-	 * the reorder queue the time. Calculating in which percpu reorder
-	 * queue the next object will arrive takes some time. A spinlock
-	 * would be highly contended. Also it is not clear in which order
-	 * the objects arrive to the reorder queues. So a cpu could wait to
-	 * get the lock just to notice that there is nothing to do at the
-	 * moment. Therefore we use a trylock and let the holder of the lock
-	 * care for all the objects enqueued during the holdtime of the lock.
-	 */
-	if (!spin_trylock_bh(&pd->lock))
-		return;
+	processed = pd->processed;
+	cpu = pd->cpu;
 
-	while (1) {
-		padata = padata_find_next(pd, true);
+	do {
+		struct padata_serial_queue *squeue;
+		int cb_cpu;
 
-		/*
-		 * If the next object that needs serialization is parallel
-		 * processed by another cpu and is still on it's way to the
-		 * cpu's reorder queue, nothing to do for now.
-		 */
-		if (!padata)
-			break;
+		cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu);
+		processed++;
 
 		cb_cpu = padata->cb_cpu;
 		squeue = per_cpu_ptr(pd->squeue, cb_cpu);
 
 		spin_lock(&squeue->serial.lock);
 		list_add_tail(&padata->list, &squeue->serial.list);
-		spin_unlock(&squeue->serial.lock);
-
 		queue_work_on(cb_cpu, pinst->serial_wq, &squeue->work);
-	}
-
-	spin_unlock_bh(&pd->lock);
-
-	/*
-	 * The next object that needs serialization might have arrived to
-	 * the reorder queues in the meantime.
-	 *
-	 * Ensure reorder queue is read after pd->lock is dropped so we see
-	 * new objects from another task in padata_do_serial.  Pairs with
-	 * smp_mb in padata_do_serial.
-	 */
-	smp_mb();
-
-	reorder = per_cpu_ptr(pd->reorder_list, pd->cpu);
-	if (!list_empty(&reorder->list) && padata_find_next(pd, false))
-		queue_work(pinst->serial_wq, &pd->reorder_work);
-}
-
-static void invoke_padata_reorder(struct work_struct *work)
-{
-	struct parallel_data *pd;
 
-	local_bh_disable();
-	pd = container_of(work, struct parallel_data, reorder_work);
-	padata_reorder(pd);
-	local_bh_enable();
+		/*
+		 * If the next object that needs serialization is parallel
+		 * processed by another cpu and is still on it's way to the
+		 * cpu's reorder queue, end the loop.
+		 */
+		padata = padata_find_next(pd, cpu, processed);
+		spin_unlock(&squeue->serial.lock);
+	} while (padata);
 }
 
 static void padata_serial_worker(struct work_struct *serial_work)
@@ -380,8 +341,7 @@ static void padata_serial_worker(struct work_struct *serial_work)
 	}
 	local_bh_enable();
 
-	if (refcount_sub_and_test(cnt, &pd->refcnt))
-		padata_free_pd(pd);
+	padata_put_pd_cnt(pd, cnt);
 }
 
 /**
@@ -399,25 +359,24 @@ void padata_do_serial(struct padata_priv *padata)
 	struct padata_list *reorder = per_cpu_ptr(pd->reorder_list, hashed_cpu);
 	struct padata_priv *cur;
 	struct list_head *pos;
+	bool gotit = true;
 
 	spin_lock(&reorder->lock);
 	/* Sort in ascending order of sequence number. */
 	list_for_each_prev(pos, &reorder->list) {
 		cur = list_entry(pos, struct padata_priv, list);
-		if (cur->seq_nr < padata->seq_nr)
+		/* Compare by difference to consider integer wrap around */
+		if ((signed int)(cur->seq_nr - padata->seq_nr) < 0)
 			break;
 	}
-	list_add(&padata->list, pos);
+	if (padata->seq_nr != pd->processed) {
+		gotit = false;
+		list_add(&padata->list, pos);
+	}
 	spin_unlock(&reorder->lock);
 
-	/*
-	 * Ensure the addition to the reorder list is ordered correctly
-	 * with the trylock of pd->lock in padata_reorder.  Pairs with smp_mb
-	 * in padata_reorder.
-	 */
-	smp_mb();
-
-	padata_reorder(pd);
+	if (gotit)
+		padata_reorder(padata);
 }
 EXPORT_SYMBOL(padata_do_serial);
 
@@ -512,18 +471,14 @@ 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);
 
-	/*
-	 * chunk_size can be 0 if the caller sets min_chunk to 0. So force it
-	 * to at least 1 to prevent divide-by-0 panic in padata_mt_helper().`
-	 */
-	if (!ps.chunk_size)
-		ps.chunk_size = 1U;
-
 	list_for_each_entry(pw, &works, pw_list)
 		if (job->numa_aware) {
 			int old_node = atomic_read(&last_used_nid);
@@ -611,9 +566,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_shell *ps)
 	padata_init_squeues(pd);
 	pd->seq_nr = -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);
 
 	return pd;
 
@@ -684,8 +637,7 @@ static int padata_replace(struct padata_instance *pinst)
 	synchronize_rcu();
 
 	list_for_each_entry_continue_reverse(ps, &pinst->pslist, list)
-		if (refcount_dec_and_test(&ps->opd->refcnt))
-			padata_free_pd(ps->opd);
+		padata_put_pd(ps->opd);
 
 	pinst->flags &= ~PADATA_RESET;
 
@@ -973,7 +925,7 @@ 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;
@@ -1127,8 +1079,7 @@ void padata_free_shell(struct padata_shell *ps)
 	mutex_lock(&ps->pinst->lock);
 	list_del(&ps->list);
 	pd = rcu_dereference_protected(ps->pd, 1);
-	if (refcount_dec_and_test(&pd->refcnt))
-		padata_free_pd(pd);
+	padata_put_pd(pd);
 	mutex_unlock(&ps->pinst->lock);
 
 	kfree(ps);