Merge branch 'net-xps-improve-the-xps-maps-handling'

Antoine Tenart says:

====================
net: xps: improve the xps maps handling

This series aims at fixing various issues with the xps code, including
out-of-bound accesses and use-after-free. While doing so we try to
improve the xps code maintainability and readability.

The main change is moving dev->num_tc and dev->nr_ids in the xps maps, to
avoid out-of-bound accesses as those two fields can be updated after the
maps have been allocated. This allows further reworks, to improve the
xps code readability and allow to stop taking the rtnl lock when
reading the maps in sysfs. The maps are moved to an array in net_device,
which simplifies the code a lot.

One future improvement may be to remove the use of xps_map_mutex from
net/core/dev.c, but that may require extra care.

Thanks!
Antoine

Since v3:
  - Removed the 3 patches about the rtnl lock and __netif_set_xps_queue
    as there are extra issues. Those patches were not tied to the
    others, and I'll see want can be done as a separate effort.
  - One small fix in patch 12.

Since v2:
  - Patches 13-16 are new to the series.
  - Fixed another issue I found while preparing v3 (use after free of
    old xps maps).
  - Kept the rtnl lock when calling netdev_get_tx_queue and
    netdev_txq_to_tc.
  - Use get_device/put_device when using the sb_dev.
  - Take the rtnl lock in mlx5 and virtio_net when calling
    netif_set_xps_queue.
  - Fixed a coding style issue.

Since v1:
  - Reordered the patches to improve readability and avoid introducing
    issues in between patches.
  - Use dev_maps->nr_ids to allocate the mask in xps_queue_show but
    still default to nr_cpu_ids/dev->num_rx_queues in xps_queue_show
    when dev_maps hasn't been allocated yet for backward
    compatibility.:w
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 222 insertions, 231 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 77ba8e2fc11c..584a9bd59dda 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2015,7 +2015,7 @@ static void virtnet_set_affinity(struct virtnet_info *vi)
 		}
 		virtqueue_set_affinity(vi->rq[i].vq, mask);
 		virtqueue_set_affinity(vi->sq[i].vq, mask);
-		__netif_set_xps_queue(vi->dev, cpumask_bits(mask), i, false);
+		__netif_set_xps_queue(vi->dev, cpumask_bits(mask), i, XPS_CPUS);
 		cpumask_clear(mask);
 	}
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 97254c089eb2..4940509999be 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -754,6 +754,13 @@ struct rx_queue_attribute {
 			 const char *buf, size_t len);
 };
 
+/* XPS map type and offset of the xps map within net_device->xps_maps[]. */
+enum xps_map_type {
+	XPS_CPUS = 0,
+	XPS_RXQS,
+	XPS_MAPS_MAX,
+};
+
 #ifdef CONFIG_XPS
 /*
  * This structure holds an XPS map which can be of variable length.  The
@@ -771,9 +778,19 @@ struct xps_map {
 
 /*
  * This structure holds all XPS maps for device.  Maps are indexed by CPU.
+ *
+ * We keep track of the number of cpus/rxqs used when the struct is allocated,
+ * in nr_ids. This will help not accessing out-of-bound memory.
+ *
+ * We keep track of the number of traffic classes used when the struct is
+ * allocated, in num_tc. This will be used to navigate the maps, to ensure we're
+ * not crossing its upper bound, as the original dev->num_tc can be updated in
+ * the meantime.
  */
 struct xps_dev_maps {
 	struct rcu_head rcu;
+	unsigned int nr_ids;
+	s16 num_tc;
 	struct xps_map __rcu *attr_map[]; /* Either CPUs map or RXQs map */
 };
 
@@ -1763,8 +1780,7 @@ enum netdev_ml_priv_type {
  *	@tx_queue_len:		Max frames per queue allowed
  *	@tx_global_lock: 	XXX: need comments on this one
  *	@xdp_bulkq:		XDP device bulk queue
- *	@xps_cpus_map:		all CPUs map for XPS device
- *	@xps_rxqs_map:		all RXQs map for XPS device
+ *	@xps_maps:		all CPUs/RXQs maps for XPS device
  *
  *	@xps_maps:	XXX: need comments on this one
  *	@miniq_egress:		clsact qdisc specific data for
@@ -2060,8 +2076,7 @@ struct net_device {
 	struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
 
 #ifdef CONFIG_XPS
-	struct xps_dev_maps __rcu *xps_cpus_map;
-	struct xps_dev_maps __rcu *xps_rxqs_map;
+	struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
 #endif
 #ifdef CONFIG_NET_CLS_ACT
 	struct mini_Qdisc __rcu	*miniq_egress;
@@ -3691,7 +3706,7 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
 int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
 			u16 index);
 int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
-			  u16 index, bool is_rxqs_map);
+			  u16 index, enum xps_map_type type);
 
 /**
  *	netif_attr_test_mask - Test a CPU or Rx queue set in a mask
@@ -3786,7 +3801,7 @@ static inline int netif_set_xps_queue(struct net_device *dev,
 
 static inline int __netif_set_xps_queue(struct net_device *dev,
 					const unsigned long *mask,
-					u16 index, bool is_rxqs_map)
+					u16 index, enum xps_map_type type)
 {
 	return 0;
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index 6bc20eabd2b0..4961fc2e9b19 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2460,7 +2460,7 @@ static DEFINE_MUTEX(xps_map_mutex);
 	rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
 
 static bool remove_xps_queue(struct xps_dev_maps *dev_maps,
-			     int tci, u16 index)
+			     struct xps_dev_maps *old_maps, int tci, u16 index)
 {
 	struct xps_map *map = NULL;
 	int pos;
@@ -2479,6 +2479,8 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps,
 			break;
 		}
 
+		if (old_maps)
+			RCU_INIT_POINTER(old_maps->attr_map[tci], NULL);
 		RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL);
 		kfree_rcu(map, rcu);
 		return false;
@@ -2491,7 +2493,7 @@ static bool remove_xps_queue_cpu(struct net_device *dev,
 				 struct xps_dev_maps *dev_maps,
 				 int cpu, u16 offset, u16 count)
 {
-	int num_tc = dev->num_tc ? : 1;
+	int num_tc = dev_maps->num_tc;
 	bool active = false;
 	int tci;
 
@@ -2499,7 +2501,7 @@ static bool remove_xps_queue_cpu(struct net_device *dev,
 		int i, j;
 
 		for (i = count, j = offset; i--; j++) {
-			if (!remove_xps_queue(dev_maps, tci, j))
+			if (!remove_xps_queue(dev_maps, NULL, tci, j))
 				break;
 		}
 
@@ -2511,74 +2513,54 @@ static bool remove_xps_queue_cpu(struct net_device *dev,
 
 static void reset_xps_maps(struct net_device *dev,
 			   struct xps_dev_maps *dev_maps,
-			   bool is_rxqs_map)
+			   enum xps_map_type type)
 {
-	if (is_rxqs_map) {
-		static_key_slow_dec_cpuslocked(&xps_rxqs_needed);
-		RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
-	} else {
-		RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
-	}
 	static_key_slow_dec_cpuslocked(&xps_needed);
+	if (type == XPS_RXQS)
+		static_key_slow_dec_cpuslocked(&xps_rxqs_needed);
+
+	RCU_INIT_POINTER(dev->xps_maps[type], NULL);
+
 	kfree_rcu(dev_maps, rcu);
 }
 
-static void clean_xps_maps(struct net_device *dev, const unsigned long *mask,
-			   struct xps_dev_maps *dev_maps, unsigned int nr_ids,
-			   u16 offset, u16 count, bool is_rxqs_map)
+static void clean_xps_maps(struct net_device *dev, enum xps_map_type type,
+			   u16 offset, u16 count)
 {
+	struct xps_dev_maps *dev_maps;
 	bool active = false;
 	int i, j;
 
-	for (j = -1; j = netif_attrmask_next(j, mask, nr_ids),
-	     j < nr_ids;)
-		active |= remove_xps_queue_cpu(dev, dev_maps, j, offset,
-					       count);
+	dev_maps = xmap_dereference(dev->xps_maps[type]);
+	if (!dev_maps)
+		return;
+
+	for (j = 0; j < dev_maps->nr_ids; j++)
+		active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, count);
 	if (!active)
-		reset_xps_maps(dev, dev_maps, is_rxqs_map);
+		reset_xps_maps(dev, dev_maps, type);
 
-	if (!is_rxqs_map) {
-		for (i = offset + (count - 1); count--; i--) {
+	if (type == XPS_CPUS) {
+		for (i = offset + (count - 1); count--; i--)
 			netdev_queue_numa_node_write(
-				netdev_get_tx_queue(dev, i),
-				NUMA_NO_NODE);
-		}
+				netdev_get_tx_queue(dev, i), NUMA_NO_NODE);
 	}
 }
 
 static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
 				   u16 count)
 {
-	const unsigned long *possible_mask = NULL;
-	struct xps_dev_maps *dev_maps;
-	unsigned int nr_ids;
-
 	if (!static_key_false(&xps_needed))
 		return;
 
 	cpus_read_lock();
 	mutex_lock(&xps_map_mutex);
 
-	if (static_key_false(&xps_rxqs_needed)) {
-		dev_maps = xmap_dereference(dev->xps_rxqs_map);
-		if (dev_maps) {
-			nr_ids = dev->num_rx_queues;
-			clean_xps_maps(dev, possible_mask, dev_maps, nr_ids,
-				       offset, count, true);
-		}
-	}
-
-	dev_maps = xmap_dereference(dev->xps_cpus_map);
-	if (!dev_maps)
-		goto out_no_maps;
+	if (static_key_false(&xps_rxqs_needed))
+		clean_xps_maps(dev, XPS_RXQS, offset, count);
 
-	if (num_possible_cpus() > 1)
-		possible_mask = cpumask_bits(cpu_possible_mask);
-	nr_ids = nr_cpu_ids;
-	clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, offset, count,
-		       false);
+	clean_xps_maps(dev, XPS_CPUS, offset, count);
 
-out_no_maps:
 	mutex_unlock(&xps_map_mutex);
 	cpus_read_unlock();
 }
@@ -2628,16 +2610,35 @@ static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index,
 	return new_map;
 }
 
+/* Copy xps maps at a given index */
+static void xps_copy_dev_maps(struct xps_dev_maps *dev_maps,
+			      struct xps_dev_maps *new_dev_maps, int index,
+			      int tc, bool skip_tc)
+{
+	int i, tci = index * dev_maps->num_tc;
+	struct xps_map *map;
+
+	/* copy maps belonging to foreign traffic classes */
+	for (i = 0; i < dev_maps->num_tc; i++, tci++) {
+		if (i == tc && skip_tc)
+			continue;
+
+		/* fill in the new device map from the old device map */
+		map = xmap_dereference(dev_maps->attr_map[tci]);
+		RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
+	}
+}
+
 /* Must be called under cpus_read_lock */
 int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
-			  u16 index, bool is_rxqs_map)
+			  u16 index, enum xps_map_type type)
 {
-	const unsigned long *online_mask = NULL, *possible_mask = NULL;
-	struct xps_dev_maps *dev_maps, *new_dev_maps = NULL;
+	struct xps_dev_maps *dev_maps, *new_dev_maps = NULL, *old_dev_maps = NULL;
+	const unsigned long *online_mask = NULL;
+	bool active = false, copy = false;
 	int i, j, tci, numa_node_id = -2;
 	int maps_sz, num_tc = 1, tc = 0;
 	struct xps_map *map, *new_map;
-	bool active = false;
 	unsigned int nr_ids;
 
 	if (dev->num_tc) {
@@ -2655,38 +2656,48 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 	}
 
 	mutex_lock(&xps_map_mutex);
-	if (is_rxqs_map) {
+
+	dev_maps = xmap_dereference(dev->xps_maps[type]);
+	if (type == XPS_RXQS) {
 		maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues);
-		dev_maps = xmap_dereference(dev->xps_rxqs_map);
 		nr_ids = dev->num_rx_queues;
 	} else {
 		maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc);
-		if (num_possible_cpus() > 1) {
+		if (num_possible_cpus() > 1)
 			online_mask = cpumask_bits(cpu_online_mask);
-			possible_mask = cpumask_bits(cpu_possible_mask);
-		}
-		dev_maps = xmap_dereference(dev->xps_cpus_map);
 		nr_ids = nr_cpu_ids;
 	}
 
 	if (maps_sz < L1_CACHE_BYTES)
 		maps_sz = L1_CACHE_BYTES;
 
+	/* The old dev_maps could be larger or smaller than the one we're
+	 * setting up now, as dev->num_tc or nr_ids could have been updated in
+	 * between. We could try to be smart, but let's be safe instead and only
+	 * copy foreign traffic classes if the two map sizes match.
+	 */
+	if (dev_maps &&
+	    dev_maps->num_tc == num_tc && dev_maps->nr_ids == nr_ids)
+		copy = true;
+
 	/* allocate memory for queue storage */
 	for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids),
 	     j < nr_ids;) {
-		if (!new_dev_maps)
-			new_dev_maps = kzalloc(maps_sz, GFP_KERNEL);
 		if (!new_dev_maps) {
-			mutex_unlock(&xps_map_mutex);
-			return -ENOMEM;
+			new_dev_maps = kzalloc(maps_sz, GFP_KERNEL);
+			if (!new_dev_maps) {
+				mutex_unlock(&xps_map_mutex);
+				return -ENOMEM;
+			}
+
+			new_dev_maps->nr_ids = nr_ids;
+			new_dev_maps->num_tc = num_tc;
 		}
 
 		tci = j * num_tc + tc;
-		map = dev_maps ? xmap_dereference(dev_maps->attr_map[tci]) :
-				 NULL;
+		map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL;
 
-		map = expand_xps_map(map, j, index, is_rxqs_map);
+		map = expand_xps_map(map, j, index, type == XPS_RXQS);
 		if (!map)
 			goto error;
 
@@ -2699,29 +2710,21 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 	if (!dev_maps) {
 		/* Increment static keys at most once per type */
 		static_key_slow_inc_cpuslocked(&xps_needed);
-		if (is_rxqs_map)
+		if (type == XPS_RXQS)
 			static_key_slow_inc_cpuslocked(&xps_rxqs_needed);
 	}
 
-	for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
-	     j < nr_ids;) {
-		/* copy maps belonging to foreign traffic classes */
-		for (i = tc, tci = j * num_tc; dev_maps && i--; tci++) {
-			/* fill in the new device map from the old device map */
-			map = xmap_dereference(dev_maps->attr_map[tci]);
-			RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
-		}
+	for (j = 0; j < nr_ids; j++) {
+		bool skip_tc = false;
 
-		/* We need to explicitly update tci as prevous loop
-		 * could break out early if dev_maps is NULL.
-		 */
 		tci = j * num_tc + tc;
-
 		if (netif_attr_test_mask(j, mask, nr_ids) &&
 		    netif_attr_test_online(j, online_mask, nr_ids)) {
 			/* add tx-queue to CPU/rx-queue maps */
 			int pos = 0;
 
+			skip_tc = true;
+
 			map = xmap_dereference(new_dev_maps->attr_map[tci]);
 			while ((pos < map->len) && (map->queues[pos] != index))
 				pos++;
@@ -2729,78 +2732,81 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 			if (pos == map->len)
 				map->queues[map->len++] = index;
 #ifdef CONFIG_NUMA
-			if (!is_rxqs_map) {
+			if (type == XPS_CPUS) {
 				if (numa_node_id == -2)
 					numa_node_id = cpu_to_node(j);
 				else if (numa_node_id != cpu_to_node(j))
 					numa_node_id = -1;
 			}
 #endif
-		} else if (dev_maps) {
-			/* fill in the new device map from the old device map */
-			map = xmap_dereference(dev_maps->attr_map[tci]);
-			RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
 		}
 
-		/* copy maps belonging to foreign traffic classes */
-		for (i = num_tc - tc, tci++; dev_maps && --i; tci++) {
-			/* fill in the new device map from the old device map */
-			map = xmap_dereference(dev_maps->attr_map[tci]);
-			RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
-		}
+		if (copy)
+			xps_copy_dev_maps(dev_maps, new_dev_maps, j, tc,
+					  skip_tc);
 	}
 
-	if (is_rxqs_map)
-		rcu_assign_pointer(dev->xps_rxqs_map, new_dev_maps);
-	else
-		rcu_assign_pointer(dev->xps_cpus_map, new_dev_maps);
+	rcu_assign_pointer(dev->xps_maps[type], new_dev_maps);
 
 	/* Cleanup old maps */
 	if (!dev_maps)
 		goto out_no_old_maps;
 
-	for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
-	     j < nr_ids;) {
-		for (i = num_tc, tci = j * num_tc; i--; tci++) {
-			new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
+	for (j = 0; j < dev_maps->nr_ids; j++) {
+		for (i = num_tc, tci = j * dev_maps->num_tc; i--; tci++) {
 			map = xmap_dereference(dev_maps->attr_map[tci]);
-			if (map && map != new_map)
-				kfree_rcu(map, rcu);
+			if (!map)
+				continue;
+
+			if (copy) {
+				new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
+				if (map == new_map)
+					continue;
+			}
+
+			RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL);
+			kfree_rcu(map, rcu);
 		}
 	}
 
-	kfree_rcu(dev_maps, rcu);
+	old_dev_maps = dev_maps;
 
 out_no_old_maps:
 	dev_maps = new_dev_maps;
 	active = true;
 
 out_no_new_maps:
-	if (!is_rxqs_map) {
+	if (type == XPS_CPUS)
 		/* update Tx queue numa node */
 		netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index),
 					     (numa_node_id >= 0) ?
 					     numa_node_id : NUMA_NO_NODE);
-	}
 
 	if (!dev_maps)
 		goto out_no_maps;
 
 	/* removes tx-queue from unused CPUs/rx-queues */
-	for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
-	     j < nr_ids;) {
-		for (i = tc, tci = j * num_tc; i--; tci++)
-			active |= remove_xps_queue(dev_maps, tci, index);
-		if (!netif_attr_test_mask(j, mask, nr_ids) ||
-		    !netif_attr_test_online(j, online_mask, nr_ids))
-			active |= remove_xps_queue(dev_maps, tci, index);
-		for (i = num_tc - tc, tci++; --i; tci++)
-			active |= remove_xps_queue(dev_maps, tci, index);
+	for (j = 0; j < dev_maps->nr_ids; j++) {
+		tci = j * dev_maps->num_tc;
+
+		for (i = 0; i < dev_maps->num_tc; i++, tci++) {
+			if (i == tc &&
+			    netif_attr_test_mask(j, mask, dev_maps->nr_ids) &&
+			    netif_attr_test_online(j, online_mask, dev_maps->nr_ids))
+				continue;
+
+			active |= remove_xps_queue(dev_maps,
+						   copy ? old_dev_maps : NULL,
+						   tci, index);
+		}
 	}
 
+	if (old_dev_maps)
+		kfree_rcu(old_dev_maps, rcu);
+
 	/* free map if not active */
 	if (!active)
-		reset_xps_maps(dev, dev_maps, is_rxqs_map);
+		reset_xps_maps(dev, dev_maps, type);
 
 out_no_maps:
 	mutex_unlock(&xps_map_mutex);
@@ -2808,11 +2814,10 @@ out_no_maps:
 	return 0;
 error:
 	/* remove any maps that we added */
-	for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
-	     j < nr_ids;) {
+	for (j = 0; j < nr_ids; j++) {
 		for (i = num_tc, tci = j * num_tc; i--; tci++) {
 			new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
-			map = dev_maps ?
+			map = copy ?
 			      xmap_dereference(dev_maps->attr_map[tci]) :
 			      NULL;
 			if (new_map && new_map != map)
@@ -2833,7 +2838,7 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
 	int ret;
 
 	cpus_read_lock();
-	ret =  __netif_set_xps_queue(dev, cpumask_bits(mask), index, false);
+	ret =  __netif_set_xps_queue(dev, cpumask_bits(mask), index, XPS_CPUS);
 	cpus_read_unlock();
 
 	return ret;
@@ -3944,13 +3949,15 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb,
 			       struct xps_dev_maps *dev_maps, unsigned int tci)
 {
+	int tc = netdev_get_prio_tc_map(dev, skb->priority);
 	struct xps_map *map;
 	int queue_index = -1;
 
-	if (dev->num_tc) {
-		tci *= dev->num_tc;
-		tci += netdev_get_prio_tc_map(dev, skb->priority);
-	}
+	if (tc >= dev_maps->num_tc || tci >= dev_maps->nr_ids)
+		return queue_index;
+
+	tci *= dev_maps->num_tc;
+	tci += tc;
 
 	map = rcu_dereference(dev_maps->attr_map[tci]);
 	if (map) {
@@ -3981,18 +3988,18 @@ static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev,
 	if (!static_key_false(&xps_rxqs_needed))
 		goto get_cpus_map;
 
-	dev_maps = rcu_dereference(sb_dev->xps_rxqs_map);
+	dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_RXQS]);
 	if (dev_maps) {
 		int tci = sk_rx_queue_get(sk);
 
-		if (tci >= 0 && tci < dev->num_rx_queues)
+		if (tci >= 0)
 			queue_index = __get_xps_queue_idx(dev, skb, dev_maps,
 							  tci);
 	}
 
 get_cpus_map:
 	if (queue_index < 0) {
-		dev_maps = rcu_dereference(sb_dev->xps_cpus_map);
+		dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_CPUS]);
 		if (dev_maps) {
 			unsigned int tci = skb->sender_cpu - 1;
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 307628fdf380..562a42fcd437 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1361,83 +1361,94 @@ static const struct attribute_group dql_group = {
 #endif /* CONFIG_BQL */
 
 #ifdef CONFIG_XPS
-static ssize_t xps_cpus_show(struct netdev_queue *queue,
-			     char *buf)
+static ssize_t xps_queue_show(struct net_device *dev, unsigned int index,
+			      int tc, char *buf, enum xps_map_type type)
 {
-	int cpu, len, ret, num_tc = 1, tc = 0;
-	struct net_device *dev = queue->dev;
 	struct xps_dev_maps *dev_maps;
-	cpumask_var_t mask;
-	unsigned long index;
-
-	if (!netif_is_multiqueue(dev))
-		return -ENOENT;
+	unsigned long *mask;
+	unsigned int nr_ids;
+	int j, len;
 
-	index = get_netdev_queue_index(queue);
+	rcu_read_lock();
+	dev_maps = rcu_dereference(dev->xps_maps[type]);
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	/* Default to nr_cpu_ids/dev->num_rx_queues and do not just return 0
+	 * when dev_maps hasn't been allocated yet, to be backward compatible.
+	 */
+	nr_ids = dev_maps ? dev_maps->nr_ids :
+		 (type == XPS_CPUS ? nr_cpu_ids : dev->num_rx_queues);
 
-	if (dev->num_tc) {
-		/* Do not allow XPS on subordinate device directly */
-		num_tc = dev->num_tc;
-		if (num_tc < 0) {
-			ret = -EINVAL;
-			goto err_rtnl_unlock;
-		}
+	mask = bitmap_zalloc(nr_ids, GFP_KERNEL);
+	if (!mask) {
+		rcu_read_unlock();
+		return -ENOMEM;
+	}
 
-		/* If queue belongs to subordinate dev use its map */
-		dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+	if (!dev_maps || tc >= dev_maps->num_tc)
+		goto out_no_maps;
 
-		tc = netdev_txq_to_tc(dev, index);
-		if (tc < 0) {
-			ret = -EINVAL;
-			goto err_rtnl_unlock;
-		}
-	}
+	for (j = 0; j < nr_ids; j++) {
+		int i, tci = j * dev_maps->num_tc + tc;
+		struct xps_map *map;
 
-	if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
-		ret = -ENOMEM;
-		goto err_rtnl_unlock;
-	}
+		map = rcu_dereference(dev_maps->attr_map[tci]);
+		if (!map)
+			continue;
 
-	rcu_read_lock();
-	dev_maps = rcu_dereference(dev->xps_cpus_map);
-	if (dev_maps) {
-		for_each_possible_cpu(cpu) {
-			int i, tci = cpu * num_tc + tc;
-			struct xps_map *map;
-
-			map = rcu_dereference(dev_maps->attr_map[tci]);
-			if (!map)
-				continue;
-
-			for (i = map->len; i--;) {
-				if (map->queues[i] == index) {
-					cpumask_set_cpu(cpu, mask);
-					break;
-				}
+		for (i = map->len; i--;) {
+			if (map->queues[i] == index) {
+				set_bit(j, mask);
+				break;
 			}
 		}
 	}
+out_no_maps:
 	rcu_read_unlock();
 
-	rtnl_unlock();
+	len = bitmap_print_to_pagebuf(false, buf, mask, nr_ids);
+	bitmap_free(mask);
 
-	len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask));
-	free_cpumask_var(mask);
 	return len < PAGE_SIZE ? len : -EINVAL;
+}
+
+static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf)
+{
+	struct net_device *dev = queue->dev;
+	unsigned int index;
+	int len, tc;
+
+	if (!netif_is_multiqueue(dev))
+		return -ENOENT;
 
-err_rtnl_unlock:
+	index = get_netdev_queue_index(queue);
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	/* If queue belongs to subordinate dev use its map */
+	dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
+	tc = netdev_txq_to_tc(dev, index);
+	if (tc < 0) {
+		rtnl_unlock();
+		return -EINVAL;
+	}
+
+	/* Make sure the subordinate device can't be freed */
+	get_device(&dev->dev);
 	rtnl_unlock();
-	return ret;
+
+	len = xps_queue_show(dev, index, tc, buf, XPS_CPUS);
+
+	put_device(&dev->dev);
+	return len;
 }
 
 static ssize_t xps_cpus_store(struct netdev_queue *queue,
 			      const char *buf, size_t len)
 {
 	struct net_device *dev = queue->dev;
-	unsigned long index;
+	unsigned int index;
 	cpumask_var_t mask;
 	int err;
 
@@ -1476,64 +1487,21 @@ static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init
 
 static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf)
 {
-	int j, len, ret, num_tc = 1, tc = 0;
 	struct net_device *dev = queue->dev;
-	struct xps_dev_maps *dev_maps;
-	unsigned long *mask, index;
+	unsigned int index;
+	int tc;
 
 	index = get_netdev_queue_index(queue);
 
 	if (!rtnl_trylock())
 		return restart_syscall();
 
-	if (dev->num_tc) {
-		num_tc = dev->num_tc;
-		tc = netdev_txq_to_tc(dev, index);
-		if (tc < 0) {
-			ret = -EINVAL;
-			goto err_rtnl_unlock;
-		}
-	}
-	mask = bitmap_zalloc(dev->num_rx_queues, GFP_KERNEL);
-	if (!mask) {
-		ret = -ENOMEM;
-		goto err_rtnl_unlock;
-	}
-
-	rcu_read_lock();
-	dev_maps = rcu_dereference(dev->xps_rxqs_map);
-	if (!dev_maps)
-		goto out_no_maps;
-
-	for (j = -1; j = netif_attrmask_next(j, NULL, dev->num_rx_queues),
-	     j < dev->num_rx_queues;) {
-		int i, tci = j * num_tc + tc;
-		struct xps_map *map;
-
-		map = rcu_dereference(dev_maps->attr_map[tci]);
-		if (!map)
-			continue;
-
-		for (i = map->len; i--;) {
-			if (map->queues[i] == index) {
-				set_bit(j, mask);
-				break;
-			}
-		}
-	}
-out_no_maps:
-	rcu_read_unlock();
-
+	tc = netdev_txq_to_tc(dev, index);
 	rtnl_unlock();
+	if (tc < 0)
+		return -EINVAL;
 
-	len = bitmap_print_to_pagebuf(false, buf, mask, dev->num_rx_queues);
-	bitmap_free(mask);
-
-	return len < PAGE_SIZE ? len : -EINVAL;
-
-err_rtnl_unlock:
-	rtnl_unlock();
-	return ret;
+	return xps_queue_show(dev, index, tc, buf, XPS_RXQS);
 }
 
 static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
@@ -1541,7 +1509,8 @@ static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
 {
 	struct net_device *dev = queue->dev;
 	struct net *net = dev_net(dev);
-	unsigned long *mask, index;
+	unsigned long *mask;
+	unsigned int index;
 	int err;
 
 	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
@@ -1565,7 +1534,7 @@ static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
 	}
 
 	cpus_read_lock();
-	err = __netif_set_xps_queue(dev, mask, index, true);
+	err = __netif_set_xps_queue(dev, mask, index, XPS_RXQS);
 	cpus_read_unlock();
 
 	rtnl_unlock();