diff options
-rw-r--r-- | include/linux/netdevice.h | 6 | ||||
-rw-r--r-- | net/core/dev.c | 63 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 45 |
3 files changed, 64 insertions, 50 deletions
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 97254c089eb2..c38534c55ea1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -771,9 +771,15 @@ struct xps_map { /* * This structure holds all XPS maps for device. Maps are indexed by CPU. + * + * 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; + s16 num_tc; struct xps_map __rcu *attr_map[]; /* Either CPUs map or RXQs map */ }; diff --git a/net/core/dev.c b/net/core/dev.c index 6bc20eabd2b0..4e29d1994fdd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2491,7 +2491,7 @@ 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; @@ -2634,10 +2634,10 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, { const unsigned long *online_mask = NULL, *possible_mask = NULL; struct xps_dev_maps *dev_maps, *new_dev_maps = 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) { @@ -2672,19 +2672,29 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, 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 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) + 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->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); if (!map) @@ -2706,7 +2716,7 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, 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++) { + for (i = tc, tci = j * num_tc; copy && 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); @@ -2736,14 +2746,14 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, numa_node_id = -1; } #endif - } else if (dev_maps) { + } else if (copy) { /* 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++) { + for (i = num_tc - tc, tci++; copy && --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); @@ -2761,11 +2771,18 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, 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 (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; + } + + kfree_rcu(map, rcu); } } @@ -2789,12 +2806,12 @@ out_no_new_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++) + for (i = tc, tci = j * dev_maps->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++) + for (i = dev_maps->num_tc - tc, tci++; --i; tci++) active |= remove_xps_queue(dev_maps, tci, index); } @@ -2812,7 +2829,7 @@ error: j < nr_ids;) { 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) @@ -3944,13 +3961,15 @@ 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) + return queue_index; + + tci *= dev_maps->num_tc; + tci += tc; map = rcu_dereference(dev_maps->attr_map[tci]); if (map) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 5f76183ad5bc..1364d0f39cb0 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1364,9 +1364,9 @@ static const struct attribute_group dql_group = { static ssize_t xps_cpus_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; + int j, len, ret, tc = 0; unsigned long *mask; unsigned int index; @@ -1378,22 +1378,13 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, if (!rtnl_trylock()) return restart_syscall(); - 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; - } - - /* If queue belongs to subordinate dev use its map */ - dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; + /* 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) { - ret = -EINVAL; - goto err_rtnl_unlock; - } + tc = netdev_txq_to_tc(dev, index); + if (tc < 0) { + ret = -EINVAL; + goto err_rtnl_unlock; } mask = bitmap_zalloc(nr_cpu_ids, GFP_KERNEL); @@ -1404,12 +1395,12 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_cpus_map); - if (!dev_maps) + if (!dev_maps || tc >= dev_maps->num_tc) goto out_no_maps; for (j = -1; j = netif_attrmask_next(j, NULL, nr_cpu_ids), j < nr_cpu_ids;) { - int i, tci = j * num_tc + tc; + int i, tci = j * dev_maps->num_tc + tc; struct xps_map *map; map = rcu_dereference(dev_maps->attr_map[tci]); @@ -1480,9 +1471,9 @@ 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; + int j, len, ret, tc = 0; unsigned long *mask; unsigned int index; @@ -1491,14 +1482,12 @@ static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) 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; - } + 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; @@ -1507,12 +1496,12 @@ static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_rxqs_map); - if (!dev_maps) + if (!dev_maps || tc >= dev_maps->num_tc) 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; + int i, tci = j * dev_maps->num_tc + tc; struct xps_map *map; map = rcu_dereference(dev_maps->attr_map[tci]); |